Merge tag 'v3.11-rc7' into devicetree/next

Linux 3.11-rc7
0 files changed, 0 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore
index 3b8b9b33be38..7e9932e55475 100644
--- a/.gitignore
+++ b/.gitignore
@@ -29,6 +29,7 @@ modules.builtin
 *.bz2
 *.lzma
 *.xz
+*.lz4
 *.lzo
 *.patch
 *.gcno
diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback
new file mode 100644
index 000000000000..8bb43b66eb55
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback
@@ -0,0 +1,17 @@
+What:           /sys/module/xen_blkback/parameters/max_buffer_pages
+Date:           March 2013
+KernelVersion:  3.11
+Contact:        Roger Pau Monné <roger.pau@citrix.com>
+Description:
+                Maximum number of free pages to keep in each block
+                backend buffer.
+
+What:           /sys/module/xen_blkback/parameters/max_persistent_grants
+Date:           March 2013
+KernelVersion:  3.11
+Contact:        Roger Pau Monné <roger.pau@citrix.com>
+Description:
+                Maximum number of grants to map persistently in
+                blkback. If the frontend tries to use more than
+                max_persistent_grants, the LRU kicks in and starts
+                removing 5% of max_persistent_grants every 100ms.
diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkfront b/Documentation/ABI/testing/sysfs-driver-xen-blkfront
new file mode 100644
index 000000000000..c0a6cb7eb314
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-xen-blkfront
@@ -0,0 +1,10 @@
+What:           /sys/module/xen_blkfront/parameters/max
+Date:           June 2013
+KernelVersion:  3.11
+Contact:        Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+Description:
+                Maximum number of segments that the frontend will negotiate
+                with the backend for indirect descriptors. The default value
+                is 32 - higher value means more potential throughput but more
+                memory usage. The backend picks the minimum of the frontend
+                and its default backend value.
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index cbfdf5486639..fe397f90a34f 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -84,7 +84,7 @@ X!Iinclude/linux/kobject.h
 
      <sect1><title>Kernel utility functions</title>
 !Iinclude/linux/kernel.h
-!Ekernel/printk.c
+!Ekernel/printk/printk.c
 !Ekernel/panic.c
 !Ekernel/sys.c
 !Ekernel/rcupdate.c
diff --git a/Documentation/DocBook/media_api.tmpl b/Documentation/DocBook/media_api.tmpl
index 6a8b7158697f..9c92bb879b6d 100644
--- a/Documentation/DocBook/media_api.tmpl
+++ b/Documentation/DocBook/media_api.tmpl
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" [
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.2//EN"
+	"http://www.oasis-open.org/docbook/xml/4.2/docbookx.dtd" [
 <!ENTITY % media-entities SYSTEM "./media-entities.tmpl"> %media-entities;
 <!ENTITY media-indices SYSTEM "./media-indices.tmpl">
 
diff --git a/Documentation/bcache.txt b/Documentation/bcache.txt
index c3365f26b2d9..32b6c3189d98 100644
--- a/Documentation/bcache.txt
+++ b/Documentation/bcache.txt
@@ -46,29 +46,33 @@ you format your backing devices and cache device at the same time, you won't
 have to manually attach:
   make-bcache -B /dev/sda /dev/sdb -C /dev/sdc
 
-To make bcache devices known to the kernel, echo them to /sys/fs/bcache/register:
+bcache-tools now ships udev rules, and bcache devices are known to the kernel
+immediately.  Without udev, you can manually register devices like this:
 
   echo /dev/sdb > /sys/fs/bcache/register
   echo /dev/sdc > /sys/fs/bcache/register
 
-To register your bcache devices automatically, you could add something like
-this to an init script:
+Registering the backing device makes the bcache device show up in /dev; you can
+now format it and use it as normal. But the first time using a new bcache
+device, it'll be running in passthrough mode until you attach it to a cache.
+See the section on attaching.
 
-  echo /dev/sd* > /sys/fs/bcache/register_quiet
+The devices show up as:
 
-It'll look for bcache superblocks and ignore everything that doesn't have one.
+  /dev/bcache<N>
 
-Registering the backing device makes the bcache show up in /dev; you can now
-format it and use it as normal. But the first time using a new bcache device,
-it'll be running in passthrough mode until you attach it to a cache. See the
-section on attaching.
+As well as (with udev):
 
-The devices show up at /dev/bcacheN, and can be controlled via sysfs from
-/sys/block/bcacheN/bcache:
+  /dev/bcache/by-uuid/<uuid>
+  /dev/bcache/by-label/<label>
+
+To get started:
 
   mkfs.ext4 /dev/bcache0
   mount /dev/bcache0 /mnt
 
+You can control bcache devices through sysfs at /sys/block/bcache<N>/bcache .
+
 Cache devices are managed as sets; multiple caches per set isn't supported yet
 but will allow for mirroring of metadata and dirty data in the future. Your new
 cache set shows up as /sys/fs/bcache/<UUID>
@@ -80,11 +84,11 @@ must be attached to your cache set to enable caching. Attaching a backing
 device to a cache set is done thusly, with the UUID of the cache set in
 /sys/fs/bcache:
 
-  echo <UUID> > /sys/block/bcache0/bcache/attach
+  echo <CSET-UUID> > /sys/block/bcache0/bcache/attach
 
 This only has to be done once. The next time you reboot, just reregister all
 your bcache devices. If a backing device has data in a cache somewhere, the
-/dev/bcache# device won't be created until the cache shows up - particularly
+/dev/bcache<N> device won't be created until the cache shows up - particularly
 important if you have writeback caching turned on.
 
 If you're booting up and your cache device is gone and never coming back, you
@@ -191,6 +195,9 @@ want for getting the best possible numbers when benchmarking.
 
 SYSFS - BACKING DEVICE:
 
+Available at /sys/block/<bdev>/bcache, /sys/block/bcache*/bcache and
+(if attached) /sys/fs/bcache/<cset-uuid>/bdev*
+
 attach
   Echo the UUID of a cache set to this file to enable caching.
 
@@ -300,6 +307,8 @@ cache_readaheads
 
 SYSFS - CACHE SET:
 
+Available at /sys/fs/bcache/<cset-uuid>
+
 average_key_size
   Average data per key in the btree.
 
@@ -390,6 +399,8 @@ trigger_gc
 
 SYSFS - CACHE DEVICE:
 
+Available at /sys/block/<cdev>/bcache
+
 block_size
   Minimum granularity of writes - should match hardware sector size.
 
diff --git a/Documentation/devicetree/bindings/clock/imx27-clock.txt b/Documentation/devicetree/bindings/clock/imx27-clock.txt
index ab1a56e9de9d..7a2070393732 100644
--- a/Documentation/devicetree/bindings/clock/imx27-clock.txt
+++ b/Documentation/devicetree/bindings/clock/imx27-clock.txt
@@ -98,6 +98,7 @@ clocks and IDs.
 	fpm                  83
 	mpll_osc_sel         84
 	mpll_sel             85
+	spll_gate	     86
 
 Examples:
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt b/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt
index a1ee681942cc..6113f9275f42 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt
@@ -4,7 +4,7 @@
 Required properties :
 
  - reg             : Offset and length of the register set for the device
- - compatible      : Should be "marvell,mv64xxx-i2c"
+ - compatible      : Should be "marvell,mv64xxx-i2c" or "allwinner,sun4i-i2c"
  - interrupts      : The interrupt number
 
 Optional properties :
diff --git a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
index d5a308629c57..30b0581bb1ce 100644
--- a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
+++ b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
@@ -31,9 +31,8 @@ Optional nodes:
 	       Optional sub-node properties:
 	       ti,warm-reset - maintain voltage during warm reset(boolean)
 	       ti,roof-floor - control voltage selection by pin(boolean)
-	       ti,sleep-mode - mode to adopt in pmic sleep 0 - off, 1 - auto,
+	       ti,mode-sleep - mode to adopt in pmic sleep 0 - off, 1 - auto,
 	       2 - eco, 3 - forced pwm
-	       ti,tstep - slope control 0 - Jump, 1 10mV/us, 2 5mV/us, 3 2.5mV/us
 	       ti,smps-range - OTP has the wrong range set for the hardware so override
 	       0 - low range, 1 - high range.
 
@@ -59,7 +58,6 @@ pmic {
 			ti,warm-reset;
 			ti,roof-floor;
 			ti,mode-sleep = <0>;
-			ti,tstep = <0>;
 			ti,smps-range = <1>;
 		};
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index d5a79caec147..366ce9b87240 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -26,6 +26,7 @@ est	ESTeem Wireless Modems
 fsl	Freescale Semiconductor
 GEFanuc	GE Fanuc Intelligent Platforms Embedded Systems, Inc.
 gef	GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+hisilicon	Hisilicon Limited.
 hp	Hewlett Packard
 ibm	International Business Machines (IBM)
 idt	Integrated Device Technologies, Inc.
@@ -43,6 +44,7 @@ nxp	NXP Semiconductors
 onnn	ON Semiconductor Corp.
 picochip	Picochip Ltd
 powervr	PowerVR (deprecated, use img)
+qca	Qualcomm Atheros, Inc.
 qcom	Qualcomm, Inc.
 ralink	Mediatek/Ralink Technology Corp.
 ramtron	Ramtron International
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 050d37fe6d40..8148a47fc70e 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -11,14 +11,14 @@ for non English (read: Japanese) speakers and is not intended as a
 fork. So if you have any comments or updates for this file, please try
 to update the original English file first.
 
-Last Updated: 2011/03/31
+Last Updated: 2013/07/19
 ==================================
 これは、
-linux-2.6.38/Documentation/HOWTO
+linux-3.10/Documentation/HOWTO
 の和訳です。
 
-翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ >
-翻訳日： 2011/3/28
+翻訳団体： JF プロジェクト < http://linuxjf.sourceforge.jp/ >
+翻訳日： 2013/7/19
 翻訳者： Tsugikazu Shibata <tshibata at ab dot jp dot nec dot com>
 校正者： 松倉さん <nbh--mats at nifty dot com>
          小林 雅典さん (Masanori Kobayasi) <zap03216 at nifty dot ne dot jp>
@@ -245,7 +245,7 @@ Linux カーネルソースツリーの中に含まれる、きれいにし、�
 自己参照方式で、索引がついた web 形式で、ソースコードを参照することが
 できます。この最新の素晴しいカーネルコードのリポジトリは以下で見つかり
 ます-
-	http://sosdg.org/~qiyong/lxr/
+	http://lxr.linux.no/+trees
 
 開発プロセス
 -----------------------
@@ -253,24 +253,24 @@ Linux カーネルソースツリーの中に含まれる、きれいにし、�
 Linux カーネルの開発プロセスは現在幾つかの異なるメインカーネル「ブラン
 チ」と多数のサブシステム毎のカーネルブランチから構成されます。
 これらのブランチとは-
-  - メインの 2.6.x カーネルツリー
-  - 2.6.x.y -stable カーネルツリー
-  - 2.6.x -git カーネルパッチ
+  - メインの 3.x カーネルツリー
+  - 3.x.y -stable カーネルツリー
+  - 3.x -git カーネルパッチ
   - サブシステム毎のカーネルツリーとパッチ
-  - 統合テストのための 2.6.x -next カーネルツリー
+  - 統合テストのための 3.x -next カーネルツリー
 
-2.6.x カーネルツリー
+3.x カーネルツリー
 -----------------
 
-2.6.x カーネルは Linus Torvalds によってメンテナンスされ、kernel.org
-の pub/linux/kernel/v2.6/ ディレクトリに存在します。この開発プロセスは
+3.x カーネルは Linus Torvalds によってメンテナンスされ、kernel.org
+の pub/linux/kernel/v3.x/ ディレクトリに存在します。この開発プロセスは
 以下のとおり-
 
   - 新しいカーネルがリリースされた直後に、2週間の特別期間が設けられ、
     この期間中に、メンテナ達は Linus に大きな差分を送ることができます。
     このような差分は通常 -next カーネルに数週間含まれてきたパッチです。
     大きな変更は git(カーネルのソース管理ツール、詳細は
-    http://git-scm.com/  参照) を使って送るのが好ましいやり方ですが、パッ
+    http://git-scm.com/ 参照) を使って送るのが好ましいやり方ですが、パッ
     チファイルの形式のまま送るのでも十分です。
 
   - 2週間後、-rc1 カーネルがリリースされ、この後にはカーネル全体の安定
@@ -302,20 +302,20 @@ Andrew Morton が Linux-kernel メーリングリストにカーネルリリー�
   実に認識されたバグの状況によりリリースされるのであり、前もって決めら
   れた計画によってリリースされるものではないからです。」
 
-2.6.x.y -stable カーネルツリー
+3.x.y -stable カーネルツリー
 ---------------------------
 
-バージョン番号が4つの数字に分かれているカーネルは -stable カーネルです。
-これには、2.6.x カーネルで見つかったセキュリティ問題や重大な後戻りに対
+バージョン番号が3つの数字に分かれているカーネルは -stable カーネルです。
+これには、3.x カーネルで見つかったセキュリティ問題や重大な後戻りに対
 する比較的小さい重要な修正が含まれます。
 
 これは、開発/実験的バージョンのテストに協力することに興味が無く、
 最新の安定したカーネルを使いたいユーザに推奨するブランチです。
 
-もし、2.6.x.y カーネルが存在しない場合には、番号が一番大きい 2.6.x が
+もし、3.x.y カーネルが存在しない場合には、番号が一番大きい 3.x が
 最新の安定版カーネルです。
 
-2.6.x.y は "stable" チーム <stable@kernel.org> でメンテされており、必
+3.x.y は "stable" チーム <stable@kernel.org> でメンテされており、必
 要に応じてリリースされます。通常のリリース期間は 2週間毎ですが、差し迫っ
 た問題がなければもう少し長くなることもあります。セキュリティ関連の問題
 の場合はこれに対してだいたいの場合、すぐにリリースがされます。
@@ -324,7 +324,7 @@ Andrew Morton が Linux-kernel メーリングリストにカーネルリリー�
 イルにはどのような種類の変更が -stable ツリーに受け入れ可能か、またリ
 リースプロセスがどう動くかが記述されています。
 
-2.6.x -git パッチ
+3.x -git パッチ
 ------------------
 
 git リポジトリで管理されているLinus のカーネルツリーの毎日のスナップ
@@ -358,14 +358,14 @@ quilt シリーズとして公開されているパッチキューも使われ�
 をつけることができます。大部分のこれらの patchwork のサイトは
 http://patchwork.kernel.org/ でリストされています。
 
-統合テストのための 2.6.x -next カーネルツリー
+統合テストのための 3.x -next カーネルツリー
 ---------------------------------------------
 
-サブシステムツリーの更新内容がメインラインの 2.6.x ツリーにマージされ
+サブシステムツリーの更新内容がメインラインの 3.x ツリーにマージされ
 る前に、それらは統合テストされる必要があります。この目的のため、実質的
 に全サブシステムツリーからほぼ毎日プルされてできる特別なテスト用のリ
 ポジトリが存在します-
-       http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
+       http://git.kernel.org/?p=linux/kernel/git/next/linux-next.git
        http://linux.f-seidel.de/linux-next/pmwiki/
 
 このやり方によって、-next カーネルは次のマージ機会でどんなものがメイン
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 15356aca938c..7f9d4f53882c 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2953,7 +2953,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			improve throughput, but will also increase the
 			amount of memory reserved for use by the client.
 
-	swapaccount[=0|1]
+	swapaccount=[0|1]
 			[KNL] Enable accounting of swap in memory resource
 			controller if no parameter or 1 is given or disable
 			it if 0 is given (See Documentation/cgroups/memory.txt)
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 1c15043aaee4..d569f2a424d5 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -52,7 +52,7 @@ Default: 64
 
 busy_read
 ----------------
-Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL)
+Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL)
 Approximate time in us to busy loop waiting for packets on the device queue.
 This sets the default value of the SO_BUSY_POLL socket option.
 Can be set or overridden per socket by setting socket option SO_BUSY_POLL,
@@ -63,7 +63,7 @@ Default: 0 (off)
 
 busy_poll
 ----------------
-Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL)
+Low latency busy poll timeout for poll and select. (needs CONFIG_NET_RX_BUSY_POLL)
 Approximate time in us to busy loop waiting for events.
 Recommended value depends on the number of sockets you poll on.
 For several sockets 50, for several hundreds 100.
diff --git a/MAINTAINERS b/MAINTAINERS
index bf61e04291ab..8197fbd70a3e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -965,6 +965,12 @@ M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
+ARM/TEXAS INSTRUMENT KEYSTONE ARCHITECTURE
+M:	Santosh Shilimkar <santosh.shilimkar@ti.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/mach-keystone/
+
 ARM/LOGICPD PXA270 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1259,7 +1265,6 @@ F:	drivers/rtc/rtc-coh901331.c
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git
 
 ARM/Ux500 ARM ARCHITECTURE
-M:	Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
 M:	Linus Walleij <linus.walleij@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -1406,7 +1411,7 @@ ATHEROS ATH6KL WIRELESS DRIVER
 M:	Kalle Valo <kvalo@qca.qualcomm.com>
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/en/users/Drivers/ath6kl
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath6kl.git
+T:	git git://github.com/kvalo/ath.git
 S:	Supported
 F:	drivers/net/wireless/ath/ath6kl/
 
@@ -1642,7 +1647,7 @@ S:	Maintained
 F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
-M:	Kent Overstreet <koverstreet@google.com>
+M:	Kent Overstreet <kmo@daterainc.com>
 L:	linux-bcache@vger.kernel.org
 W:	http://bcache.evilpiepirate.org
 S:	Maintained:
@@ -2871,7 +2876,7 @@ F:	drivers/media/usb/dvb-usb-v2/dvb_usb*
 F:	drivers/media/usb/dvb-usb-v2/usb_urb.c
 
 DYNAMIC DEBUG
-M:	Jason Baron <jbaron@redhat.com>
+M:	Jason Baron <jbaron@akamai.com>
 S:	Maintained
 F:	lib/dynamic_debug.c
 F:	include/linux/dynamic_debug.h
@@ -3346,7 +3351,7 @@ F:	Documentation/firmware_class/
 F:	drivers/base/firmware*.c
 F:	include/linux/firmware.h
 
-FLASHSYSTEM DRIVER (IBM FlashSystem 70/80 PCI SSD Flash Card)
+FLASH ADAPTER DRIVER (IBM Flash Adapter 900GB Full Height PCI Flash Card)
 M:	Joshua Morris <josh.h.morris@us.ibm.com>
 M:	Philip Kelleher <pjk1939@linux.vnet.ibm.com>
 S:	Maintained
@@ -3622,11 +3627,9 @@ F:	drivers/isdn/gigaset/
 F:	include/uapi/linux/gigaset_dev.h
 
 GPIO SUBSYSTEM
-M:	Grant Likely <grant.likely@linaro.org>
 M:	Linus Walleij <linus.walleij@linaro.org>
 S:	Maintained
 L:	linux-gpio@vger.kernel.org
-T:	git git://git.secretlab.ca/git/linux-2.6.git
 F:	Documentation/gpio.txt
 F:	drivers/gpio/
 F:	include/linux/gpio*
@@ -4472,8 +4475,6 @@ F:	drivers/irqchip/
 
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
-M:	Grant Likely <grant.likely@linaro.org>
-T:	git git://git.secretlab.ca/git/linux-2.6.git irqdomain/next
 S:	Maintained
 F:	Documentation/IRQ-domain.txt
 F:	include/linux/irqdomain.h
@@ -4990,7 +4991,7 @@ F:	arch/powerpc/platforms/44x/
 
 LINUX FOR POWERPC EMBEDDED XILINX VIRTEX
 L:	linuxppc-dev@lists.ozlabs.org
-S:	Unmaintained
+S:	Orphan
 F:	arch/powerpc/*/*virtex*
 F:	arch/powerpc/*/*/*virtex*
 
@@ -5580,9 +5581,9 @@ S:	Maintained
 F:	drivers/media/tuners/mxl5007t.*
 
 MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
-M:	Andrew Gallatin <gallatin@myri.com>
+M:	Hyong-Youb Kim <hykim@myri.com>
 L:	netdev@vger.kernel.org
-W:	http://www.myri.com/scs/download-Myri10GE.html
+W:	https://www.myricom.com/support/downloads/myri10ge.html
 S:	Supported
 F:	drivers/net/ethernet/myricom/myri10ge/
 
@@ -5883,10 +5884,10 @@ F:	drivers/i2c/busses/i2c-omap.c
 F:	include/linux/i2c-omap.h
 
 OMAP DEVICE TREE SUPPORT
-M:	Benoît Cousson <b-cousson@ti.com>
+M:	Benoît Cousson <bcousson@baylibre.com>
 M:	Tony Lindgren <tony@atomide.com>
 L:	linux-omap@vger.kernel.org
-L:	devicetree-discuss@lists.ozlabs.org (moderated for non-subscribers)
+L:	devicetree@vger.kernel.org
 S:	Maintained
 F:	arch/arm/boot/dts/*omap*
 F:	arch/arm/boot/dts/*am3*
@@ -5963,14 +5964,14 @@ S:	Maintained
 F:	drivers/char/hw_random/omap-rng.c
 
 OMAP HWMOD SUPPORT
-M:	Benoît Cousson <b-cousson@ti.com>
+M:	Benoît Cousson <bcousson@baylibre.com>
 M:	Paul Walmsley <paul@pwsan.com>
 L:	linux-omap@vger.kernel.org
 S:	Maintained
 F:	arch/arm/mach-omap2/omap_hwmod.*
 
 OMAP HWMOD DATA FOR OMAP4-BASED DEVICES
-M:	Benoît Cousson <b-cousson@ti.com>
+M:	Benoît Cousson <bcousson@baylibre.com>
 L:	linux-omap@vger.kernel.org
 S:	Maintained
 F:	arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -6050,17 +6051,28 @@ F:	drivers/i2c/busses/i2c-ocores.c
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
 M:	Grant Likely <grant.likely@linaro.org>
 M:	Rob Herring <rob.herring@calxeda.com>
-L:	devicetree-discuss@lists.ozlabs.org (moderated for non-subscribers)
+L:	devicetree@vger.kernel.org
 W:	http://fdt.secretlab.ca
 T:	git git://git.secretlab.ca/git/linux-2.6.git
 S:	Maintained
-F:	Documentation/devicetree
-F:	drivers/of
+F:	drivers/of/
 F:	include/linux/of*.h
-F:	scripts/dtc
+F:	scripts/dtc/
 K:	of_get_property
 K:	of_match_table
 
+OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS
+M:	Rob Herring <rob.herring@calxeda.com>
+M:	Pawel Moll <pawel.moll@arm.com>
+M:	Mark Rutland <mark.rutland@arm.com>
+M:	Stephen Warren <swarren@wwwdotorg.org>
+M:	Ian Campbell <ian.campbell@citrix.com>
+L:	devicetree@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/
+F:	arch/*/boot/dts/
+F:	include/dt-bindings/
+
 OPENRISC ARCHITECTURE
 M:	Jonas Bonn <jonas@southpole.se>
 W:	http://openrisc.net
@@ -6719,6 +6731,14 @@ T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
 F:	drivers/media/tuners/qt1010*
 
+QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
+M:	Kalle Valo <kvalo@qca.qualcomm.com>
+L:	ath10k@lists.infradead.org
+W:	http://wireless.kernel.org/en/users/Drivers/ath10k
+T:	git git://github.com/kvalo/ath.git
+S:	Supported
+F:	drivers/net/wireless/ath/ath10k/
+
 QUALCOMM HEXAGON ARCHITECTURE
 M:	Richard Kuo <rkuo@codeaurora.org>
 L:	linux-hexagon@vger.kernel.org
@@ -7346,7 +7366,6 @@ F:	drivers/net/ethernet/sfc/
 
 SGI GRU DRIVER
 M:	Dimitri Sivanich <sivanich@sgi.com>
-M:	Robin Holt <holt@sgi.com>
 S:	Maintained
 F:	drivers/misc/sgi-gru/
 
@@ -7366,7 +7385,8 @@ S:	Maintained for 2.6.
 F:	Documentation/sgi-visws.txt
 
 SGI XP/XPC/XPNET DRIVER
-M:	Robin Holt <holt@sgi.com>
+M:	Cliff Whickman <cpw@sgi.com>
+M:	Robin Holt <robinmholt@gmail.com>
 S:	Maintained
 F:	drivers/misc/sgi-xp/
 
@@ -7746,7 +7766,6 @@ F:	drivers/clk/spear/
 
 SPI SUBSYSTEM
 M:	Mark Brown <broonie@kernel.org>
-M:	Grant Likely <grant.likely@linaro.org>
 L:	linux-spi@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi.git
 Q:	http://patchwork.kernel.org/project/spi-devel-general/list/
@@ -7812,7 +7831,7 @@ F:	drivers/staging/asus_oled/
 
 STAGING - COMEDI
 M:	Ian Abbott <abbotti@mev.co.uk>
-M:	Mori Hess <fmhess@users.sourceforge.net>
+M:	H Hartley Sweeten <hsweeten@visionengravers.com>
 S:	Odd Fixes
 F:	drivers/staging/comedi/
 
@@ -8264,7 +8283,7 @@ S:	Maintained
 F:	sound/soc/codecs/twl4030*
 
 TI WILINK WIRELESS DRIVERS
-M:	Luciano Coelho <coelho@ti.com>
+M:	Luciano Coelho <luca@coelho.fi>
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/en/users/Drivers/wl12xx
 W:	http://wireless.kernel.org/en/users/Drivers/wl1251
@@ -8650,6 +8669,11 @@ T:	git git://git.alsa-project.org/alsa-kernel.git
 S:	Maintained
 F:	sound/usb/midi.*
 
+USB NETWORKING DRIVERS
+L:	linux-usb@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/net/usb/
+
 USB OHCI DRIVER
 M:	Alan Stern <stern@rowland.harvard.edu>
 L:	linux-usb@vger.kernel.org
@@ -9288,7 +9312,7 @@ S:	Maintained
 F:	drivers/net/ethernet/xilinx/xilinx_axienet*
 
 XILINX SYSTEMACE DRIVER
-S:	Unmaintained
+S:	Orphan
 F:	drivers/block/xsysace.c
 
 XILINX UARTLITE SERIAL DRIVER
diff --git a/Makefile b/Makefile
index a35f72a420c0..369882e4fc77 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc7
 NAME = Linux for Workgroups
 
 # *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index 8d2ae24b9f4a..1feb169274fe 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -407,6 +407,12 @@ config CLONE_BACKWARDS2
 	help
 	  Architecture has the first two arguments of clone(2) swapped.
 
+config CLONE_BACKWARDS3
+	bool
+	help
+	  Architecture has tls passed as the 3rd argument of clone(2),
+	  not the 5th one.
+
 config ODD_RT_SIGACTION
 	bool
 	help
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 837a1f2d8b96..082d9b4b5472 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -15,6 +15,7 @@ config ALPHA
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_STRNCPY_FROM_USER
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index c2cbe4fc391c..78b03ef39f6f 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -186,17 +186,24 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
  */
 static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 {
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
+	int c, new, old;
+	smp_mb();
+	__asm__ __volatile__(
+	"1:	ldl_l	%[old],%[mem]\n"
+	"	cmpeq	%[old],%[u],%[c]\n"
+	"	addl	%[old],%[a],%[new]\n"
+	"	bne	%[c],2f\n"
+	"	stl_c	%[new],%[mem]\n"
+	"	beq	%[new],3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br	1b\n"
+	".previous"
+	: [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c)
+	: [mem] "m"(*v), [a] "rI"(a), [u] "rI"((long)u)
+	: "memory");
+	smp_mb();
+	return old;
 }
 
 
@@ -207,21 +214,56 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
+ * Returns true iff @v was not @u.
  */
 static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 {
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
+	long c, tmp;
+	smp_mb();
+	__asm__ __volatile__(
+	"1:	ldq_l	%[tmp],%[mem]\n"
+	"	cmpeq	%[tmp],%[u],%[c]\n"
+	"	addq	%[tmp],%[a],%[tmp]\n"
+	"	bne	%[c],2f\n"
+	"	stq_c	%[tmp],%[mem]\n"
+	"	beq	%[tmp],3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br	1b\n"
+	".previous"
+	: [tmp] "=&r"(tmp), [c] "=&r"(c)
+	: [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u)
+	: "memory");
+	smp_mb();
+	return !c;
+}
+
+/*
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic variable, v, was not decremented.
+ */
+static inline long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long old, tmp;
+	smp_mb();
+	__asm__ __volatile__(
+	"1:	ldq_l	%[old],%[mem]\n"
+	"	subq	%[old],1,%[tmp]\n"
+	"	ble	%[old],2f\n"
+	"	stq_c	%[tmp],%[mem]\n"
+	"	beq	%[tmp],3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br	1b\n"
+	".previous"
+	: [old] "=&r"(old), [tmp] "=&r"(tmp)
+	: [mem] "m"(*v)
+	: "memory");
+	smp_mb();
+	return old - 1;
 }
 
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
diff --git a/arch/alpha/include/asm/param.h b/arch/alpha/include/asm/param.h
index bf46af51941b..a5b68b268bcf 100644
--- a/arch/alpha/include/asm/param.h
+++ b/arch/alpha/include/asm/param.h
@@ -3,7 +3,9 @@
 
 #include <uapi/asm/param.h>
 
-#define HZ		CONFIG_HZ
-#define USER_HZ		HZ
-# define CLOCKS_PER_SEC	HZ	/* frequency at which times() counts */
+# undef HZ
+# define HZ		CONFIG_HZ
+# define USER_HZ	1024
+# define CLOCKS_PER_SEC	USER_HZ	/* frequency at which times() counts */
+
 #endif /* _ASM_ALPHA_PARAM_H */
diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h
index 3bba21e41b81..37b570d01202 100644
--- a/arch/alpha/include/asm/spinlock.h
+++ b/arch/alpha/include/asm/spinlock.h
@@ -168,8 +168,4 @@ static inline void arch_write_unlock(arch_rwlock_t * lock)
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* _ALPHA_SPINLOCK_H */
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index 43baee17acdf..f2c94402e2c8 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -3,8 +3,7 @@
 
 #include <uapi/asm/unistd.h>
 
-
-#define NR_SYSCALLS			506
+#define NR_SYSCALLS			508
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
diff --git a/arch/alpha/include/uapi/asm/param.h b/arch/alpha/include/uapi/asm/param.h
index 29daed819ebd..dbcd9834af6d 100644
--- a/arch/alpha/include/uapi/asm/param.h
+++ b/arch/alpha/include/uapi/asm/param.h
@@ -1,13 +1,7 @@
 #ifndef _UAPI_ASM_ALPHA_PARAM_H
 #define _UAPI_ASM_ALPHA_PARAM_H
 
-/* ??? Gross.  I don't want to parameterize this, and supposedly the
-   hardware ignores reprogramming.  We also need userland buy-in to the 
-   change in HZ, since this is visible in the wait4 resources etc.  */
-
-#ifndef __KERNEL__
 #define HZ		1024
-#endif
 
 #define EXEC_PAGESIZE	8192
 
@@ -17,5 +11,4 @@
 
 #define MAXHOSTNAMELEN	64	/* max length of hostname */
 
-
 #endif /* _UAPI_ASM_ALPHA_PARAM_H */
diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h
index 801d28bcea51..53ae7bb1bfd1 100644
--- a/arch/alpha/include/uapi/asm/unistd.h
+++ b/arch/alpha/include/uapi/asm/unistd.h
@@ -467,5 +467,7 @@
 #define __NR_sendmmsg			503
 #define __NR_process_vm_readv		504
 #define __NR_process_vm_writev		505
+#define __NR_kcmp			506
+#define __NR_finit_module		507
 
 #endif /* _UAPI_ALPHA_UNISTD_H */
diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S
index f62a994ef126..a969b95ee5ac 100644
--- a/arch/alpha/kernel/entry.S
+++ b/arch/alpha/kernel/entry.S
@@ -12,11 +12,32 @@
 
 	.text
 	.set noat
+	.cfi_sections	.debug_frame
 
 /* Stack offsets.  */
 #define SP_OFF			184
 #define SWITCH_STACK_SIZE	320
 
+.macro	CFI_START_OSF_FRAME	func
+	.align	4
+	.globl	\func
+	.type	\func,@function
+\func:
+	.cfi_startproc simple
+	.cfi_return_column 64
+	.cfi_def_cfa	$sp, 48
+	.cfi_rel_offset	64, 8
+	.cfi_rel_offset	$gp, 16
+	.cfi_rel_offset	$16, 24
+	.cfi_rel_offset	$17, 32
+	.cfi_rel_offset	$18, 40
+.endm
+
+.macro	CFI_END_OSF_FRAME	func
+	.cfi_endproc
+	.size	\func, . - \func
+.endm
+
 /*
  * This defines the normal kernel pt-regs layout.
  *
@@ -27,100 +48,158 @@
  * the palcode-provided values are available to the signal handler.
  */
 
-#define SAVE_ALL			\
-	subq	$sp, SP_OFF, $sp;	\
-	stq	$0, 0($sp);		\
-	stq	$1, 8($sp);		\
-	stq	$2, 16($sp);		\
-	stq	$3, 24($sp);		\
-	stq	$4, 32($sp);		\
-	stq	$28, 144($sp);		\
-	lda	$2, alpha_mv;		\
-	stq	$5, 40($sp);		\
-	stq	$6, 48($sp);		\
-	stq	$7, 56($sp);		\
-	stq	$8, 64($sp);		\
-	stq	$19, 72($sp);		\
-	stq	$20, 80($sp);		\
-	stq	$21, 88($sp);		\
-	ldq	$2, HAE_CACHE($2);	\
-	stq	$22, 96($sp);		\
-	stq	$23, 104($sp);		\
-	stq	$24, 112($sp);		\
-	stq	$25, 120($sp);		\
-	stq	$26, 128($sp);		\
-	stq	$27, 136($sp);		\
-	stq	$2, 152($sp);		\
-	stq	$16, 160($sp);		\
-	stq	$17, 168($sp);		\
+.macro	SAVE_ALL
+	subq	$sp, SP_OFF, $sp
+	.cfi_adjust_cfa_offset	SP_OFF
+	stq	$0, 0($sp)
+	stq	$1, 8($sp)
+	stq	$2, 16($sp)
+	stq	$3, 24($sp)
+	stq	$4, 32($sp)
+	stq	$28, 144($sp)
+	.cfi_rel_offset	$0, 0
+	.cfi_rel_offset $1, 8
+	.cfi_rel_offset	$2, 16
+	.cfi_rel_offset	$3, 24
+	.cfi_rel_offset	$4, 32
+	.cfi_rel_offset	$28, 144
+	lda	$2, alpha_mv
+	stq	$5, 40($sp)
+	stq	$6, 48($sp)
+	stq	$7, 56($sp)
+	stq	$8, 64($sp)
+	stq	$19, 72($sp)
+	stq	$20, 80($sp)
+	stq	$21, 88($sp)
+	ldq	$2, HAE_CACHE($2)
+	stq	$22, 96($sp)
+	stq	$23, 104($sp)
+	stq	$24, 112($sp)
+	stq	$25, 120($sp)
+	stq	$26, 128($sp)
+	stq	$27, 136($sp)
+	stq	$2, 152($sp)
+	stq	$16, 160($sp)
+	stq	$17, 168($sp)
 	stq	$18, 176($sp)
+	.cfi_rel_offset	$5, 40
+	.cfi_rel_offset	$6, 48
+	.cfi_rel_offset	$7, 56
+	.cfi_rel_offset	$8, 64
+	.cfi_rel_offset $19, 72
+	.cfi_rel_offset	$20, 80
+	.cfi_rel_offset	$21, 88
+	.cfi_rel_offset $22, 96
+	.cfi_rel_offset	$23, 104
+	.cfi_rel_offset	$24, 112
+	.cfi_rel_offset	$25, 120
+	.cfi_rel_offset	$26, 128
+	.cfi_rel_offset	$27, 136
+.endm
 
-#define RESTORE_ALL			\
-	lda	$19, alpha_mv;		\
-	ldq	$0, 0($sp);		\
-	ldq	$1, 8($sp);		\
-	ldq	$2, 16($sp);		\
-	ldq	$3, 24($sp);		\
-	ldq	$21, 152($sp);		\
-	ldq	$20, HAE_CACHE($19);	\
-	ldq	$4, 32($sp);		\
-	ldq	$5, 40($sp);		\
-	ldq	$6, 48($sp);		\
-	ldq	$7, 56($sp);		\
-	subq	$20, $21, $20;		\
-	ldq	$8, 64($sp);		\
-	beq	$20, 99f;		\
-	ldq	$20, HAE_REG($19);	\
-	stq	$21, HAE_CACHE($19);	\
-	stq	$21, 0($20);		\
-99:;					\
-	ldq	$19, 72($sp);		\
-	ldq	$20, 80($sp);		\
-	ldq	$21, 88($sp);		\
-	ldq	$22, 96($sp);		\
-	ldq	$23, 104($sp);		\
-	ldq	$24, 112($sp);		\
-	ldq	$25, 120($sp);		\
-	ldq	$26, 128($sp);		\
-	ldq	$27, 136($sp);		\
-	ldq	$28, 144($sp);		\
+.macro	RESTORE_ALL
+	lda	$19, alpha_mv
+	ldq	$0, 0($sp)
+	ldq	$1, 8($sp)
+	ldq	$2, 16($sp)
+	ldq	$3, 24($sp)
+	ldq	$21, 152($sp)
+	ldq	$20, HAE_CACHE($19)
+	ldq	$4, 32($sp)
+	ldq	$5, 40($sp)
+	ldq	$6, 48($sp)
+	ldq	$7, 56($sp)
+	subq	$20, $21, $20
+	ldq	$8, 64($sp)
+	beq	$20, 99f
+	ldq	$20, HAE_REG($19)
+	stq	$21, HAE_CACHE($19)
+	stq	$21, 0($20)
+99:	ldq	$19, 72($sp)
+	ldq	$20, 80($sp)
+	ldq	$21, 88($sp)
+	ldq	$22, 96($sp)
+	ldq	$23, 104($sp)
+	ldq	$24, 112($sp)
+	ldq	$25, 120($sp)
+	ldq	$26, 128($sp)
+	ldq	$27, 136($sp)
+	ldq	$28, 144($sp)
 	addq	$sp, SP_OFF, $sp
+	.cfi_restore	$0
+	.cfi_restore	$1
+	.cfi_restore	$2
+	.cfi_restore	$3
+	.cfi_restore	$4
+	.cfi_restore	$5
+	.cfi_restore	$6
+	.cfi_restore	$7
+	.cfi_restore	$8
+	.cfi_restore	$19
+	.cfi_restore	$20
+	.cfi_restore	$21
+	.cfi_restore	$22
+	.cfi_restore	$23
+	.cfi_restore	$24
+	.cfi_restore	$25
+	.cfi_restore	$26
+	.cfi_restore	$27
+	.cfi_restore	$28
+	.cfi_adjust_cfa_offset	-SP_OFF
+.endm
+
+.macro	DO_SWITCH_STACK
+	bsr	$1, do_switch_stack
+	.cfi_adjust_cfa_offset	SWITCH_STACK_SIZE
+	.cfi_rel_offset	$9, 0
+	.cfi_rel_offset	$10, 8
+	.cfi_rel_offset	$11, 16
+	.cfi_rel_offset	$12, 24
+	.cfi_rel_offset	$13, 32
+	.cfi_rel_offset	$14, 40
+	.cfi_rel_offset	$15, 48
+	/* We don't really care about the FP registers for debugging.  */
+.endm
+
+.macro	UNDO_SWITCH_STACK
+	bsr	$1, undo_switch_stack
+	.cfi_restore	$9
+	.cfi_restore	$10
+	.cfi_restore	$11
+	.cfi_restore	$12
+	.cfi_restore	$13
+	.cfi_restore	$14
+	.cfi_restore	$15
+	.cfi_adjust_cfa_offset	-SWITCH_STACK_SIZE
+.endm
 
 /*
  * Non-syscall kernel entry points.
  */
 
-	.align	4
-	.globl	entInt
-	.ent	entInt
-entInt:
+CFI_START_OSF_FRAME entInt
 	SAVE_ALL
 	lda	$8, 0x3fff
 	lda	$26, ret_from_sys_call
 	bic	$sp, $8, $8
 	mov	$sp, $19
 	jsr	$31, do_entInt
-.end entInt
+CFI_END_OSF_FRAME entInt
 
-	.align	4
-	.globl	entArith
-	.ent	entArith
-entArith:
+CFI_START_OSF_FRAME entArith
 	SAVE_ALL
 	lda	$8, 0x3fff
 	lda	$26, ret_from_sys_call
 	bic	$sp, $8, $8
 	mov	$sp, $18
 	jsr	$31, do_entArith
-.end entArith
+CFI_END_OSF_FRAME entArith
 
-	.align	4
-	.globl	entMM
-	.ent	entMM
-entMM:
+CFI_START_OSF_FRAME entMM
 	SAVE_ALL
 /* save $9 - $15 so the inline exception code can manipulate them.  */
 	subq	$sp, 56, $sp
+	.cfi_adjust_cfa_offset	56
 	stq	$9, 0($sp)
 	stq	$10, 8($sp)
 	stq	$11, 16($sp)
@@ -128,6 +207,13 @@ entMM:
 	stq	$13, 32($sp)
 	stq	$14, 40($sp)
 	stq	$15, 48($sp)
+	.cfi_rel_offset	$9, 0
+	.cfi_rel_offset	$10, 8
+	.cfi_rel_offset	$11, 16
+	.cfi_rel_offset	$12, 24
+	.cfi_rel_offset	$13, 32
+	.cfi_rel_offset	$14, 40
+	.cfi_rel_offset	$15, 48
 	addq	$sp, 56, $19
 /* handle the fault */
 	lda	$8, 0x3fff
@@ -142,28 +228,33 @@ entMM:
 	ldq	$14, 40($sp)
 	ldq	$15, 48($sp)
 	addq	$sp, 56, $sp
+	.cfi_restore	$9
+	.cfi_restore	$10
+	.cfi_restore	$11
+	.cfi_restore	$12
+	.cfi_restore	$13
+	.cfi_restore	$14
+	.cfi_restore	$15
+	.cfi_adjust_cfa_offset	-56
 /* finish up the syscall as normal.  */
 	br	ret_from_sys_call
-.end entMM
+CFI_END_OSF_FRAME entMM
 
-	.align	4
-	.globl	entIF
-	.ent	entIF
-entIF:
+CFI_START_OSF_FRAME entIF
 	SAVE_ALL
 	lda	$8, 0x3fff
 	lda	$26, ret_from_sys_call
 	bic	$sp, $8, $8
 	mov	$sp, $17
 	jsr	$31, do_entIF
-.end entIF
+CFI_END_OSF_FRAME entIF
 
-	.align	4
-	.globl	entUna
-	.ent	entUna
-entUna:
+CFI_START_OSF_FRAME entUna
 	lda	$sp, -256($sp)
+	.cfi_adjust_cfa_offset	256
 	stq	$0, 0($sp)
+	.cfi_rel_offset	$0, 0
+	.cfi_remember_state
 	ldq	$0, 256($sp)	/* get PS */
 	stq	$1, 8($sp)
 	stq	$2, 16($sp)
@@ -195,6 +286,32 @@ entUna:
 	stq	$28, 224($sp)
 	mov	$sp, $19
 	stq	$gp, 232($sp)
+	.cfi_rel_offset	$1, 1*8
+	.cfi_rel_offset	$2, 2*8
+	.cfi_rel_offset	$3, 3*8
+	.cfi_rel_offset	$4, 4*8
+	.cfi_rel_offset	$5, 5*8
+	.cfi_rel_offset	$6, 6*8
+	.cfi_rel_offset	$7, 7*8
+	.cfi_rel_offset	$8, 8*8
+	.cfi_rel_offset	$9, 9*8
+	.cfi_rel_offset	$10, 10*8
+	.cfi_rel_offset	$11, 11*8
+	.cfi_rel_offset	$12, 12*8
+	.cfi_rel_offset	$13, 13*8
+	.cfi_rel_offset	$14, 14*8
+	.cfi_rel_offset	$15, 15*8
+	.cfi_rel_offset	$19, 19*8
+	.cfi_rel_offset	$20, 20*8
+	.cfi_rel_offset	$21, 21*8
+	.cfi_rel_offset	$22, 22*8
+	.cfi_rel_offset	$23, 23*8
+	.cfi_rel_offset	$24, 24*8
+	.cfi_rel_offset	$25, 25*8
+	.cfi_rel_offset	$26, 26*8
+	.cfi_rel_offset	$27, 27*8
+	.cfi_rel_offset	$28, 28*8
+	.cfi_rel_offset	$29, 29*8
 	lda	$8, 0x3fff
 	stq	$31, 248($sp)
 	bic	$sp, $8, $8
@@ -228,16 +345,45 @@ entUna:
 	ldq	$28, 224($sp)
 	ldq	$gp, 232($sp)
 	lda	$sp, 256($sp)
+	.cfi_restore	$1
+	.cfi_restore	$2
+	.cfi_restore	$3
+	.cfi_restore	$4
+	.cfi_restore	$5
+	.cfi_restore	$6
+	.cfi_restore	$7
+	.cfi_restore	$8
+	.cfi_restore	$9
+	.cfi_restore	$10
+	.cfi_restore	$11
+	.cfi_restore	$12
+	.cfi_restore	$13
+	.cfi_restore	$14
+	.cfi_restore	$15
+	.cfi_restore	$19
+	.cfi_restore	$20
+	.cfi_restore	$21
+	.cfi_restore	$22
+	.cfi_restore	$23
+	.cfi_restore	$24
+	.cfi_restore	$25
+	.cfi_restore	$26
+	.cfi_restore	$27
+	.cfi_restore	$28
+	.cfi_restore	$29
+	.cfi_adjust_cfa_offset	-256
 	call_pal PAL_rti
-.end entUna
 
 	.align	4
-	.ent	entUnaUser
 entUnaUser:
+	.cfi_restore_state
 	ldq	$0, 0($sp)	/* restore original $0 */
 	lda	$sp, 256($sp)	/* pop entUna's stack frame */
+	.cfi_restore	$0
+	.cfi_adjust_cfa_offset	-256
 	SAVE_ALL		/* setup normal kernel stack */
 	lda	$sp, -56($sp)
+	.cfi_adjust_cfa_offset	56
 	stq	$9, 0($sp)
 	stq	$10, 8($sp)
 	stq	$11, 16($sp)
@@ -245,6 +391,13 @@ entUnaUser:
 	stq	$13, 32($sp)
 	stq	$14, 40($sp)
 	stq	$15, 48($sp)
+	.cfi_rel_offset	$9, 0
+	.cfi_rel_offset	$10, 8
+	.cfi_rel_offset	$11, 16
+	.cfi_rel_offset	$12, 24
+	.cfi_rel_offset	$13, 32
+	.cfi_rel_offset	$14, 40
+	.cfi_rel_offset	$15, 48
 	lda	$8, 0x3fff
 	addq	$sp, 56, $19
 	bic	$sp, $8, $8
@@ -257,20 +410,25 @@ entUnaUser:
 	ldq	$14, 40($sp)
 	ldq	$15, 48($sp)
 	lda	$sp, 56($sp)
+	.cfi_restore	$9
+	.cfi_restore	$10
+	.cfi_restore	$11
+	.cfi_restore	$12
+	.cfi_restore	$13
+	.cfi_restore	$14
+	.cfi_restore	$15
+	.cfi_adjust_cfa_offset	-56
 	br	ret_from_sys_call
-.end entUnaUser
+CFI_END_OSF_FRAME entUna
 
-	.align	4
-	.globl	entDbg
-	.ent	entDbg
-entDbg:
+CFI_START_OSF_FRAME entDbg
 	SAVE_ALL
 	lda	$8, 0x3fff
 	lda	$26, ret_from_sys_call
 	bic	$sp, $8, $8
 	mov	$sp, $16
 	jsr	$31, do_entDbg
-.end entDbg
+CFI_END_OSF_FRAME entDbg
 
 /*
  * The system call entry point is special.  Most importantly, it looks
@@ -285,8 +443,12 @@ entDbg:
 
 	.align	4
 	.globl	entSys
-	.globl	ret_from_sys_call
-	.ent	entSys
+	.type	entSys, @function
+	.cfi_startproc simple
+	.cfi_return_column 64
+	.cfi_def_cfa	$sp, 48
+	.cfi_rel_offset	64, 8
+	.cfi_rel_offset	$gp, 16
 entSys:
 	SAVE_ALL
 	lda	$8, 0x3fff
@@ -300,6 +462,9 @@ entSys:
 	stq	$17, SP_OFF+32($sp)
 	s8addq	$0, $5, $5
 	stq	$18, SP_OFF+40($sp)
+	.cfi_rel_offset	$16, SP_OFF+24
+	.cfi_rel_offset	$17, SP_OFF+32
+	.cfi_rel_offset	$18, SP_OFF+40
 	blbs	$3, strace
 	beq	$4, 1f
 	ldq	$27, 0($5)
@@ -310,6 +475,7 @@ entSys:
 	stq	$31, 72($sp)		/* a3=0 => no error */
 
 	.align	4
+	.globl	ret_from_sys_call
 ret_from_sys_call:
 	cmovne	$26, 0, $18		/* $18 = 0 => non-restartable */
 	ldq	$0, SP_OFF($sp)
@@ -324,10 +490,12 @@ ret_to_user:
 	and	$17, _TIF_WORK_MASK, $2
 	bne	$2, work_pending
 restore_all:
+	.cfi_remember_state
 	RESTORE_ALL
 	call_pal PAL_rti
 
 ret_to_kernel:
+	.cfi_restore_state
 	lda	$16, 7
 	call_pal PAL_swpipl
 	br restore_all
@@ -356,7 +524,6 @@ $ret_success:
 	stq	$0, 0($sp)
 	stq	$31, 72($sp)	/* a3=0 => no error */
 	br	ret_from_sys_call
-.end entSys
 
 /*
  * Do all cleanup when returning from all interrupts and system calls.
@@ -370,7 +537,7 @@ $ret_success:
  */
 
 	.align	4
-	.ent	work_pending
+	.type	work_pending, @function
 work_pending:
 	and	$17, _TIF_NOTIFY_RESUME | _TIF_SIGPENDING, $2
 	bne	$2, $work_notifysig
@@ -387,23 +554,22 @@ $work_resched:
 
 $work_notifysig:
 	mov	$sp, $16
-	bsr	$1, do_switch_stack
+	DO_SWITCH_STACK
 	jsr	$26, do_work_pending
-	bsr	$1, undo_switch_stack
+	UNDO_SWITCH_STACK
 	br	restore_all
-.end work_pending
 
 /*
  * PTRACE syscall handler
  */
 
 	.align	4
-	.ent	strace
+	.type	strace, @function
 strace:
 	/* set up signal stack, call syscall_trace */
-	bsr	$1, do_switch_stack
+	DO_SWITCH_STACK
 	jsr	$26, syscall_trace_enter /* returns the syscall number */
-	bsr	$1, undo_switch_stack
+	UNDO_SWITCH_STACK
 
 	/* get the arguments back.. */
 	ldq	$16, SP_OFF+24($sp)
@@ -431,9 +597,9 @@ ret_from_straced:
 $strace_success:
 	stq	$0, 0($sp)		/* save return value */
 
-	bsr	$1, do_switch_stack
+	DO_SWITCH_STACK
 	jsr	$26, syscall_trace_leave
-	bsr	$1, undo_switch_stack
+	UNDO_SWITCH_STACK
 	br	$31, ret_from_sys_call
 
 	.align	3
@@ -447,26 +613,31 @@ $strace_error:
 	stq	$0, 0($sp)
 	stq	$1, 72($sp)	/* a3 for return */
 
-	bsr	$1, do_switch_stack
+	DO_SWITCH_STACK
 	mov	$18, $9		/* save old syscall number */
 	mov	$19, $10	/* save old a3 */
 	jsr	$26, syscall_trace_leave
 	mov	$9, $18
 	mov	$10, $19
-	bsr	$1, undo_switch_stack
+	UNDO_SWITCH_STACK
 
 	mov	$31, $26	/* tell "ret_from_sys_call" we can restart */
 	br	ret_from_sys_call
-.end strace
+CFI_END_OSF_FRAME entSys
 
 /*
  * Save and restore the switch stack -- aka the balance of the user context.
  */
 
 	.align	4
-	.ent	do_switch_stack
+	.type	do_switch_stack, @function
+	.cfi_startproc simple
+	.cfi_return_column 64
+	.cfi_def_cfa $sp, 0
+	.cfi_register 64, $1
 do_switch_stack:
 	lda	$sp, -SWITCH_STACK_SIZE($sp)
+	.cfi_adjust_cfa_offset	SWITCH_STACK_SIZE
 	stq	$9, 0($sp)
 	stq	$10, 8($sp)
 	stq	$11, 16($sp)
@@ -510,10 +681,14 @@ do_switch_stack:
 	stt	$f0, 312($sp)	# save fpcr in slot of $f31
 	ldt	$f0, 64($sp)	# dont let "do_switch_stack" change fp state.
 	ret	$31, ($1), 1
-.end do_switch_stack
+	.cfi_endproc
+	.size	do_switch_stack, .-do_switch_stack
 
 	.align	4
-	.ent	undo_switch_stack
+	.type	undo_switch_stack, @function
+	.cfi_startproc simple
+	.cfi_def_cfa $sp, 0
+	.cfi_register 64, $1
 undo_switch_stack:
 	ldq	$9, 0($sp)
 	ldq	$10, 8($sp)
@@ -558,7 +733,8 @@ undo_switch_stack:
 	ldt	$f30, 304($sp)
 	lda	$sp, SWITCH_STACK_SIZE($sp)
 	ret	$31, ($1), 1
-.end undo_switch_stack
+	.cfi_endproc
+	.size	undo_switch_stack, .-undo_switch_stack
 
 /*
  * The meat of the context switch code.
@@ -566,17 +742,18 @@ undo_switch_stack:
 
 	.align	4
 	.globl	alpha_switch_to
-	.ent	alpha_switch_to
+	.type	alpha_switch_to, @function
+	.cfi_startproc
 alpha_switch_to:
-	.prologue 0
-	bsr	$1, do_switch_stack
+	DO_SWITCH_STACK
 	call_pal PAL_swpctx
 	lda	$8, 0x3fff
-	bsr	$1, undo_switch_stack
+	UNDO_SWITCH_STACK
 	bic	$sp, $8, $8
 	mov	$17, $0
 	ret
-.end alpha_switch_to
+	.cfi_endproc
+	.size	alpha_switch_to, .-alpha_switch_to
 
 /*
  * New processes begin life here.
diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c
index f433fc11877a..28e4429596f3 100644
--- a/arch/alpha/kernel/irq_alpha.c
+++ b/arch/alpha/kernel/irq_alpha.c
@@ -236,7 +236,7 @@ void __init
 init_rtc_irq(void)
 {
 	irq_set_chip_and_handler_name(RTC_IRQ, &dummy_irq_chip,
-				      handle_simple_irq, "RTC");
+				      handle_percpu_irq, "RTC");
 	setup_irq(RTC_IRQ, &timer_irqaction);
 }
 
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 53b18a620e1c..9dbbcb3b9146 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -264,9 +264,10 @@ recv_secondary_console_msg(void)
 		if (cnt <= 0 || cnt >= 80)
 			strcpy(buf, "<<< BOGUS MSG >>>");
 		else {
-			cp1 = (char *) &cpu->ipc_buffer[11];
+			cp1 = (char *) &cpu->ipc_buffer[1];
 			cp2 = buf;
-			strcpy(cp2, cp1);
+			memcpy(cp2, cp1, cnt);
+			cp2[cnt] = '\0';
 			
 			while ((cp2 = strchr(cp2, '\r')) != 0) {
 				*cp2 = ' ';
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 5bf401f7ea97..6c35159bc00e 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -190,9 +190,6 @@ static struct irq_chip clipper_irq_type = {
 static void
 dp264_device_interrupt(unsigned long vector)
 {
-#if 1
-	printk("dp264_device_interrupt: NOT IMPLEMENTED YET!!\n");
-#else
 	unsigned long pld;
 	unsigned int i;
 
@@ -210,12 +207,7 @@ dp264_device_interrupt(unsigned long vector)
 			isa_device_interrupt(vector);
 		else
 			handle_irq(16 + i);
-#if 0
-		TSUNAMI_cchip->dir0.csr = 1UL << i; mb();
-		tmp = TSUNAMI_cchip->dir0.csr;
-#endif
 	}
-#endif
 }
 
 static void 
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index 407accc80877..c92e389ff219 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -317,8 +317,9 @@ marvel_init_irq(void)
 }
 
 static int 
-marvel_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
+marvel_map_irq(const struct pci_dev *cdev, u8 slot, u8 pin)
 {
+	struct pci_dev *dev = (struct pci_dev *)cdev;
 	struct pci_controller *hose = dev->sysdata;
 	struct io7_port *io7_port = hose->sysdata;
 	struct io7 *io7 = io7_port->io7;
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index 4284ec798ec9..dca9b3fb0071 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -524,6 +524,8 @@ sys_call_table:
 	.quad sys_sendmmsg
 	.quad sys_process_vm_readv
 	.quad sys_process_vm_writev		/* 505 */
+	.quad sys_kcmp
+	.quad sys_finit_module
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index e336694ca042..ea3395036556 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -105,9 +105,7 @@ void arch_irq_work_raise(void)
 
 static inline __u32 rpcc(void)
 {
-    __u32 result;
-    asm volatile ("rpcc %0" : "=r"(result));
-    return result;
+	return __builtin_alpha_rpcc();
 }
 
 int update_persistent_clock(struct timespec now)
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index be1fba334bd0..bd0665cdc840 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -66,8 +66,8 @@ dik_show_regs(struct pt_regs *regs, unsigned long *r9_15)
 {
 	printk("pc = [<%016lx>]  ra = [<%016lx>]  ps = %04lx    %s\n",
 	       regs->pc, regs->r26, regs->ps, print_tainted());
-	print_symbol("pc is at %s\n", regs->pc);
-	print_symbol("ra is at %s\n", regs->r26 );
+	printk("pc is at %pSR\n", (void *)regs->pc);
+	printk("ra is at %pSR\n", (void *)regs->r26);
 	printk("v0 = %016lx  t0 = %016lx  t1 = %016lx\n",
 	       regs->r0, regs->r1, regs->r2);
 	printk("t2 = %016lx  t3 = %016lx  t4 = %016lx\n",
@@ -132,9 +132,7 @@ dik_show_trace(unsigned long *sp)
 			continue;
 		if (tmp >= (unsigned long) &_etext)
 			continue;
-		printk("[<%lx>]", tmp);
-		print_symbol(" %s", tmp);
-		printk("\n");
+		printk("[<%lx>] %pSR\n", tmp, (void *)tmp);
 		if (i > 40) {
 			printk(" ...");
 			break;
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 8943c028d4bb..df57611652e5 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -38,6 +38,7 @@
 #include <asm/ptrace.h>
 #include <asm/processor.h>	/* For VMALLOC_START */
 #include <asm/thread_info.h>	/* For THREAD_SIZE */
+#include <asm/mmu.h>
 
 /* Note on the LD/ST addr modes with addr reg wback
  *
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
index 99c10475d477..9c548c7cf001 100644
--- a/arch/arc/lib/strchr-700.S
+++ b/arch/arc/lib/strchr-700.S
@@ -39,9 +39,18 @@ ARC_ENTRY strchr
 	ld.a	r2,[r0,4]
 	sub	r12,r6,r7
 	bic	r12,r12,r6
+#ifdef __LITTLE_ENDIAN__
 	and	r7,r12,r4
 	breq	r7,0,.Loop ; For speed, we want this branch to be unaligned.
 	b	.Lfound_char ; Likewise this one.
+#else
+	and	r12,r12,r4
+	breq	r12,0,.Loop ; For speed, we want this branch to be unaligned.
+	lsr_s	r12,r12,7
+	bic 	r2,r7,r6
+	b.d	.Lfound_char_b
+	and_s	r2,r2,r12
+#endif
 ; /* We require this code address to be unaligned for speed...  */
 .Laligned:
 	ld_s	r2,[r0]
@@ -95,6 +104,7 @@ ARC_ENTRY strchr
 	lsr	r7,r7,7
 
 	bic	r2,r7,r6
+.Lfound_char_b:
 	norm	r2,r2
 	sub_s	r0,r0,4
 	asr_s	r2,r2,3
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ba412e02ec0c..43594d5116ef 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -20,7 +20,6 @@ config ARM
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HARDIRQS_SW_RESEND
-	select HAVE_AOUT
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_SECCOMP_FILTER
@@ -218,7 +217,8 @@ config VECTORS_BASE
 	default DRAM_BASE if REMAP_VECTORS_TO_RAM
 	default 0x00000000
 	help
-	  The base address of exception vectors.
+	  The base address of exception vectors.  This must be two pages
+	  in size.
 
 config ARM_PATCH_PHYS_VIRT
 	bool "Patch physical to virtual translations at runtime" if EMBEDDED
@@ -1600,8 +1600,7 @@ config LOCAL_TIMERS
 config ARCH_NR_GPIO
 	int
 	default 1024 if ARCH_SHMOBILE || ARCH_TEGRA
-	default 512 if SOC_OMAP5
-	default 512 if ARCH_KEYSTONE
+	default 512 if ARCH_EXYNOS || ARCH_KEYSTONE || SOC_OMAP5
 	default 392 if ARCH_U8500
 	default 352 if ARCH_VT8500
 	default 288 if ARCH_SUNXI
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index e401a766c0bd..583f4a00ec32 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -804,9 +804,19 @@ config DEBUG_LL_INCLUDE
 
 config DEBUG_UNCOMPRESS
 	bool
-	default y if ARCH_MULTIPLATFORM && DEBUG_LL && \
-		     !DEBUG_OMAP2PLUS_UART && \
+	depends on ARCH_MULTIPLATFORM
+	default y if DEBUG_LL && !DEBUG_OMAP2PLUS_UART && \
 		     !DEBUG_TEGRA_UART
+	help
+	  This option influences the normal decompressor output for
+	  multiplatform kernels.  Normally, multiplatform kernels disable
+	  decompressor output because it is not possible to know where to
+	  send the decompressor output.
+
+	  When this option is set, the selected DEBUG_LL output method
+	  will be re-used for normal decompressor output on multiplatform
+	  kernels.
+	  
 
 config UNCOMPRESS_INCLUDE
 	string
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index c0ac0f5e5e5c..6fd2ceae305a 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -153,6 +153,7 @@ machine-$(CONFIG_ARCH_DAVINCI)		+= davinci
 machine-$(CONFIG_ARCH_DOVE)		+= dove
 machine-$(CONFIG_ARCH_EBSA110)		+= ebsa110
 machine-$(CONFIG_ARCH_EP93XX)		+= ep93xx
+machine-$(CONFIG_ARCH_EXYNOS)		+= exynos
 machine-$(CONFIG_ARCH_GEMINI)		+= gemini
 machine-$(CONFIG_ARCH_HIGHBANK)		+= highbank
 machine-$(CONFIG_ARCH_INTEGRATOR)	+= integrator
@@ -160,15 +161,16 @@ machine-$(CONFIG_ARCH_IOP13XX)		+= iop13xx
 machine-$(CONFIG_ARCH_IOP32X)		+= iop32x
 machine-$(CONFIG_ARCH_IOP33X)		+= iop33x
 machine-$(CONFIG_ARCH_IXP4XX)		+= ixp4xx
+machine-$(CONFIG_ARCH_KEYSTONE)		+= keystone
 machine-$(CONFIG_ARCH_KIRKWOOD)		+= kirkwood
 machine-$(CONFIG_ARCH_KS8695)		+= ks8695
 machine-$(CONFIG_ARCH_LPC32XX)		+= lpc32xx
 machine-$(CONFIG_ARCH_MMP)		+= mmp
 machine-$(CONFIG_ARCH_MSM)		+= msm
 machine-$(CONFIG_ARCH_MV78XX0)		+= mv78xx0
+machine-$(CONFIG_ARCH_MVEBU)		+= mvebu
 machine-$(CONFIG_ARCH_MXC)		+= imx
 machine-$(CONFIG_ARCH_MXS)		+= mxs
-machine-$(CONFIG_ARCH_MVEBU)		+= mvebu
 machine-$(CONFIG_ARCH_NETX)		+= netx
 machine-$(CONFIG_ARCH_NOMADIK)		+= nomadik
 machine-$(CONFIG_ARCH_NSPIRE)		+= nspire
@@ -176,7 +178,6 @@ machine-$(CONFIG_ARCH_OMAP1)		+= omap1
 machine-$(CONFIG_ARCH_OMAP2PLUS)	+= omap2
 machine-$(CONFIG_ARCH_ORION5X)		+= orion5x
 machine-$(CONFIG_ARCH_PICOXCELL)	+= picoxcell
-machine-$(CONFIG_ARCH_SIRF)		+= prima2
 machine-$(CONFIG_ARCH_PXA)		+= pxa
 machine-$(CONFIG_ARCH_REALVIEW)		+= realview
 machine-$(CONFIG_ARCH_ROCKCHIP)		+= rockchip
@@ -186,25 +187,24 @@ machine-$(CONFIG_ARCH_S3C64XX)		+= s3c64xx
 machine-$(CONFIG_ARCH_S5P64X0)		+= s5p64x0
 machine-$(CONFIG_ARCH_S5PC100)		+= s5pc100
 machine-$(CONFIG_ARCH_S5PV210)		+= s5pv210
-machine-$(CONFIG_ARCH_EXYNOS)		+= exynos
 machine-$(CONFIG_ARCH_SA1100)		+= sa1100
 machine-$(CONFIG_ARCH_SHARK)		+= shark
 machine-$(CONFIG_ARCH_SHMOBILE) 	+= shmobile
+machine-$(CONFIG_ARCH_SIRF)		+= prima2
+machine-$(CONFIG_ARCH_SOCFPGA)		+= socfpga
+machine-$(CONFIG_ARCH_STI)		+= sti
+machine-$(CONFIG_ARCH_SUNXI)		+= sunxi
 machine-$(CONFIG_ARCH_TEGRA)		+= tegra
 machine-$(CONFIG_ARCH_U300)		+= u300
 machine-$(CONFIG_ARCH_U8500)		+= ux500
 machine-$(CONFIG_ARCH_VERSATILE)	+= versatile
 machine-$(CONFIG_ARCH_VEXPRESS)		+= vexpress
+machine-$(CONFIG_ARCH_VIRT)		+= virt
 machine-$(CONFIG_ARCH_VT8500)		+= vt8500
 machine-$(CONFIG_ARCH_W90X900)		+= w90x900
+machine-$(CONFIG_ARCH_ZYNQ)		+= zynq
 machine-$(CONFIG_FOOTBRIDGE)		+= footbridge
-machine-$(CONFIG_ARCH_SOCFPGA)		+= socfpga
 machine-$(CONFIG_PLAT_SPEAR)		+= spear
-machine-$(CONFIG_ARCH_STI)		+= sti
-machine-$(CONFIG_ARCH_VIRT)		+= virt
-machine-$(CONFIG_ARCH_ZYNQ)		+= zynq
-machine-$(CONFIG_ARCH_SUNXI)		+= sunxi
-machine-$(CONFIG_ARCH_KEYSTONE)		+= keystone
 
 # Platform directory name.  This list is sorted alphanumerically
 # by CONFIG_* macro name.
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index d59b70c6a6a0..3d77dbe406f4 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -14,11 +14,11 @@
 	compatible = "atmel,at91sam9n12ek", "atmel,at91sam9n12", "atmel,at91sam9";
 
 	chosen {
-		bootargs = "mem=128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
+		bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
 	};
 
 	memory {
-		reg = <0x20000000 0x10000000>;
+		reg = <0x20000000 0x8000000>;
 	};
 
 	clocks {
diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi
index b753855b2058..49e3c45818c2 100644
--- a/arch/arm/boot/dts/at91sam9x5ek.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi
@@ -94,8 +94,9 @@
 
 		usb0: ohci@00600000 {
 			status = "okay";
-			num-ports = <2>;
-			atmel,vbus-gpio = <&pioD 19 GPIO_ACTIVE_LOW
+			num-ports = <3>;
+			atmel,vbus-gpio = <0 /* &pioD 18 GPIO_ACTIVE_LOW *//* Activate to have access to port A */
+					   &pioD 19 GPIO_ACTIVE_LOW
 					   &pioD 20 GPIO_ACTIVE_LOW
 					  >;
 		};
diff --git a/arch/arm/boot/dts/atlas6.dtsi b/arch/arm/boot/dts/atlas6.dtsi
index 9866cd736dee..a0f2721ea583 100644
--- a/arch/arm/boot/dts/atlas6.dtsi
+++ b/arch/arm/boot/dts/atlas6.dtsi
@@ -485,6 +485,12 @@
                                                 sirf,function = "usp0";
                                         };
                                 };
+				usp0_uart_nostreamctrl_pins_a: usp0@1 {
+                                        usp0 {
+                                                sirf,pins = "usp0_uart_nostreamctrl_grp";
+                                                sirf,function = "usp0_uart_nostreamctrl";
+                                        };
+                                };
                                 usp1_pins_a: usp1@0 {
                                         usp1 {
                                                 sirf,pins = "usp1grp";
@@ -515,16 +521,16 @@
                                                 sirf,function = "pulse_count";
                                         };
                                 };
-                                cko0_rst_pins_a: cko0_rst@0 {
-                                        cko0_rst {
-                                                sirf,pins = "cko0_rstgrp";
-                                                sirf,function = "cko0_rst";
+                                cko0_pins_a: cko0@0 {
+                                        cko0 {
+                                                sirf,pins = "cko0grp";
+                                                sirf,function = "cko0";
                                         };
                                 };
-                                cko1_rst_pins_a: cko1_rst@0 {
-                                        cko1_rst {
-                                                sirf,pins = "cko1_rstgrp";
-                                                sirf,function = "cko1_rst";
+                                cko1_pins_a: cko1@0 {
+                                        cko1 {
+                                                sirf,pins = "cko1grp";
+                                                sirf,function = "cko1";
                                         };
                                 };
 			};
diff --git a/arch/arm/boot/dts/imx28-apx4devkit.dts b/arch/arm/boot/dts/imx28-apx4devkit.dts
index 43bf3c796cba..0e7fed47bd8d 100644
--- a/arch/arm/boot/dts/imx28-apx4devkit.dts
+++ b/arch/arm/boot/dts/imx28-apx4devkit.dts
@@ -147,7 +147,7 @@
 					reg = <0x0a>;
 					VDDA-supply = <&reg_3p3v>;
 					VDDIO-supply = <&reg_3p3v>;
-
+					clocks = <&saif0>;
 				};
 
 				pcf8563: rtc@51 {
diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts
index 1f0d38d7b16f..e035f4664b97 100644
--- a/arch/arm/boot/dts/imx28-evk.dts
+++ b/arch/arm/boot/dts/imx28-evk.dts
@@ -195,7 +195,7 @@
 					reg = <0x0a>;
 					VDDA-supply = <&reg_3p3v>;
 					VDDIO-supply = <&reg_3p3v>;
-
+					clocks = <&saif0>;
 				};
 
 				at24@51 {
diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts
index 880df2f13be8..44d9da57736e 100644
--- a/arch/arm/boot/dts/imx28-m28evk.dts
+++ b/arch/arm/boot/dts/imx28-m28evk.dts
@@ -184,7 +184,7 @@
 					reg = <0x0a>;
 					VDDA-supply = <&reg_3p3v>;
 					VDDIO-supply = <&reg_3p3v>;
-
+					clocks = <&saif0>;
 				};
 
 				eeprom: eeprom@51 {
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 6a8acb01b1d3..9524a0571281 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -837,6 +837,7 @@
 				compatible = "fsl,imx28-saif";
 				reg = <0x80042000 0x2000>;
 				interrupts = <59 80>;
+				#clock-cells = <0>;
 				clocks = <&clks 53>;
 				dmas = <&dma_apbx 4>;
 				dma-names = "rx-tx";
diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts
index 6dd9486c755b..ad3471ca17c7 100644
--- a/arch/arm/boot/dts/imx51-babbage.dts
+++ b/arch/arm/boot/dts/imx51-babbage.dts
@@ -61,6 +61,16 @@
 		mux-int-port = <2>;
 		mux-ext-port = <3>;
 	};
+
+	clocks {
+		clk_26M: codec_clock {
+			compatible = "fixed-clock";
+			reg=<0>;
+			#clock-cells = <0>;
+			clock-frequency = <26000000>;
+			gpios = <&gpio4 26 1>;
+		};
+	};
 };
 
 &esdhc1 {
@@ -229,6 +239,7 @@
 				MX51_PAD_EIM_A27__GPIO2_21   0x5
 				MX51_PAD_CSPI1_SS0__GPIO4_24 0x85
 				MX51_PAD_CSPI1_SS1__GPIO4_25 0x85
+				MX51_PAD_CSPI1_RDY__GPIO4_26 0x80000000
 			>;
 		};
 	};
@@ -255,7 +266,7 @@
 	sgtl5000: codec@0a {
 		compatible = "fsl,sgtl5000";
 		reg = <0x0a>;
-		clock-frequency = <26000000>;
+		clocks = <&clk_26M>;
 		VDDA-supply = <&vdig_reg>;
 		VDDIO-supply = <&vvideo_reg>;
 	};
diff --git a/arch/arm/boot/dts/imx53-mba53.dts b/arch/arm/boot/dts/imx53-mba53.dts
index aaa33bc99f78..a63090267941 100644
--- a/arch/arm/boot/dts/imx53-mba53.dts
+++ b/arch/arm/boot/dts/imx53-mba53.dts
@@ -27,7 +27,7 @@
 
 	backlight {
 		compatible = "pwm-backlight";
-		pwms = <&pwm2 0 50000 0 0>;
+		pwms = <&pwm2 0 50000>;
 		brightness-levels = <0 24 28 32 36 40 44 48 52 56 60 64 68 72 76 80 84 88 92 96 100>;
 		default-brightness-level = <10>;
 		enable-gpios = <&gpio7 7 0>;
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 3895fbba8fce..569aa9f2c4ed 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -725,15 +725,15 @@
 				uart1 {
 					pinctrl_uart1_1: uart1grp-1 {
 						fsl,pins = <
-							MX53_PAD_CSI0_DAT10__UART1_TXD_MUX 0x1c5
-							MX53_PAD_CSI0_DAT11__UART1_RXD_MUX 0x1c5
+							MX53_PAD_CSI0_DAT10__UART1_TXD_MUX 0x1e4
+							MX53_PAD_CSI0_DAT11__UART1_RXD_MUX 0x1e4
 						>;
 					};
 
 					pinctrl_uart1_2: uart1grp-2 {
 						fsl,pins = <
-							MX53_PAD_PATA_DIOW__UART1_TXD_MUX  0x1c5
-							MX53_PAD_PATA_DMACK__UART1_RXD_MUX 0x1c5
+							MX53_PAD_PATA_DIOW__UART1_TXD_MUX  0x1e4
+							MX53_PAD_PATA_DMACK__UART1_RXD_MUX 0x1e4
 						>;
 					};
 
@@ -748,8 +748,8 @@
 				uart2 {
 					pinctrl_uart2_1: uart2grp-1 {
 						fsl,pins = <
-							MX53_PAD_PATA_BUFFER_EN__UART2_RXD_MUX 0x1c5
-							MX53_PAD_PATA_DMARQ__UART2_TXD_MUX     0x1c5
+							MX53_PAD_PATA_BUFFER_EN__UART2_RXD_MUX 0x1e4
+							MX53_PAD_PATA_DMARQ__UART2_TXD_MUX     0x1e4
 						>;
 					};
 
@@ -766,17 +766,17 @@
 				uart3 {
 					pinctrl_uart3_1: uart3grp-1 {
 						fsl,pins = <
-							MX53_PAD_PATA_CS_0__UART3_TXD_MUX 0x1c5
-							MX53_PAD_PATA_CS_1__UART3_RXD_MUX 0x1c5
-							MX53_PAD_PATA_DA_1__UART3_CTS	  0x1c5
-							MX53_PAD_PATA_DA_2__UART3_RTS	  0x1c5
+							MX53_PAD_PATA_CS_0__UART3_TXD_MUX 0x1e4
+							MX53_PAD_PATA_CS_1__UART3_RXD_MUX 0x1e4
+							MX53_PAD_PATA_DA_1__UART3_CTS	  0x1e4
+							MX53_PAD_PATA_DA_2__UART3_RTS	  0x1e4
 						>;
 					};
 
 					pinctrl_uart3_2: uart3grp-2 {
 						fsl,pins = <
-							MX53_PAD_PATA_CS_0__UART3_TXD_MUX 0x1c5
-							MX53_PAD_PATA_CS_1__UART3_RXD_MUX 0x1c5
+							MX53_PAD_PATA_CS_0__UART3_TXD_MUX 0x1e4
+							MX53_PAD_PATA_CS_1__UART3_RXD_MUX 0x1e4
 						>;
 					};
 
@@ -785,8 +785,8 @@
 				uart4 {
 					pinctrl_uart4_1: uart4grp-1 {
 						fsl,pins = <
-							MX53_PAD_KEY_COL0__UART4_TXD_MUX 0x1c5
-							MX53_PAD_KEY_ROW0__UART4_RXD_MUX 0x1c5
+							MX53_PAD_KEY_COL0__UART4_TXD_MUX 0x1e4
+							MX53_PAD_KEY_ROW0__UART4_RXD_MUX 0x1e4
 						>;
 					};
 				};
@@ -794,8 +794,8 @@
 				uart5 {
 					pinctrl_uart5_1: uart5grp-1 {
 						fsl,pins = <
-							MX53_PAD_KEY_COL1__UART5_TXD_MUX 0x1c5
-							MX53_PAD_KEY_ROW1__UART5_RXD_MUX 0x1c5
+							MX53_PAD_KEY_COL1__UART5_TXD_MUX 0x1e4
+							MX53_PAD_KEY_ROW1__UART5_RXD_MUX 0x1e4
 						>;
 					};
 				};
diff --git a/arch/arm/boot/dts/msm8960-cdp.dts b/arch/arm/boot/dts/msm8960-cdp.dts
index db2060c46540..9c1167b0459b 100644
--- a/arch/arm/boot/dts/msm8960-cdp.dts
+++ b/arch/arm/boot/dts/msm8960-cdp.dts
@@ -26,7 +26,7 @@
 		cpu-offset = <0x80000>;
 	};
 
-	msmgpio: gpio@fd510000 {
+	msmgpio: gpio@800000 {
 		compatible = "qcom,msm-gpio";
 		gpio-controller;
 		#gpio-cells = <2>;
@@ -34,7 +34,7 @@
 		interrupts = <0 32 0x4>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
-		reg = <0xfd510000 0x4000>;
+		reg = <0x800000 0x4000>;
 	};
 
 	serial@16440000 {
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 08b72678abff..65d7b601651c 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -235,7 +235,7 @@
 };
 
 &mmc1 {
-	vmmc-supply = <&vmmcsd_fixed>;
+	vmmc-supply = <&ldo9_reg>;
 	bus-width = <4>;
 };
 
@@ -282,6 +282,7 @@
 
 			regulators {
 				smps123_reg: smps123 {
+					/* VDD_OPP_MPU */
 					regulator-name = "smps123";
 					regulator-min-microvolt = < 600000>;
 					regulator-max-microvolt = <1500000>;
@@ -290,6 +291,7 @@
 				};
 
 				smps45_reg: smps45 {
+					/* VDD_OPP_MM */
 					regulator-name = "smps45";
 					regulator-min-microvolt = < 600000>;
 					regulator-max-microvolt = <1310000>;
@@ -298,6 +300,7 @@
 				};
 
 				smps6_reg: smps6 {
+					/* VDD_DDR3 - over VDD_SMPS6 */
 					regulator-name = "smps6";
 					regulator-min-microvolt = <1200000>;
 					regulator-max-microvolt = <1200000>;
@@ -306,6 +309,7 @@
 				};
 
 				smps7_reg: smps7 {
+					/* VDDS_1v8_OMAP over VDDS_1v8_MAIN */
 					regulator-name = "smps7";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -314,6 +318,7 @@
 				};
 
 				smps8_reg: smps8 {
+					/* VDD_OPP_CORE */
 					regulator-name = "smps8";
 					regulator-min-microvolt = < 600000>;
 					regulator-max-microvolt = <1310000>;
@@ -322,15 +327,15 @@
 				};
 
 				smps9_reg: smps9 {
+					/* VDDA_2v1_AUD over VDD_2v1 */
 					regulator-name = "smps9";
 					regulator-min-microvolt = <2100000>;
 					regulator-max-microvolt = <2100000>;
-					regulator-always-on;
-					regulator-boot-on;
 					ti,smps-range = <0x80>;
 				};
 
 				smps10_reg: smps10 {
+					/* VBUS_5V_OTG */
 					regulator-name = "smps10";
 					regulator-min-microvolt = <5000000>;
 					regulator-max-microvolt = <5000000>;
@@ -339,38 +344,40 @@
 				};
 
 				ldo1_reg: ldo1 {
+					/* VDDAPHY_CAM: vdda_csiport */
 					regulator-name = "ldo1";
-					regulator-min-microvolt = <2800000>;
-					regulator-max-microvolt = <2800000>;
-					regulator-always-on;
-					regulator-boot-on;
+					regulator-min-microvolt = <1500000>;
+					regulator-max-microvolt = <1800000>;
 				};
 
 				ldo2_reg: ldo2 {
+					/* VCC_2V8_DISP: Does not go anywhere */
 					regulator-name = "ldo2";
-					regulator-min-microvolt = <2900000>;
-					regulator-max-microvolt = <2900000>;
-					regulator-always-on;
-					regulator-boot-on;
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					/* Unused */
+					status = "disabled";
 				};
 
 				ldo3_reg: ldo3 {
+					/* VDDAPHY_MDM: vdda_lli */
 					regulator-name = "ldo3";
-					regulator-min-microvolt = <3000000>;
-					regulator-max-microvolt = <3000000>;
-					regulator-always-on;
+					regulator-min-microvolt = <1500000>;
+					regulator-max-microvolt = <1500000>;
 					regulator-boot-on;
+					/* Only if Modem is used */
+					status = "disabled";
 				};
 
 				ldo4_reg: ldo4 {
+					/* VDDAPHY_DISP: vdda_dsiport/hdmi */
 					regulator-name = "ldo4";
-					regulator-min-microvolt = <2200000>;
-					regulator-max-microvolt = <2200000>;
-					regulator-always-on;
-					regulator-boot-on;
+					regulator-min-microvolt = <1500000>;
+					regulator-max-microvolt = <1800000>;
 				};
 
 				ldo5_reg: ldo5 {
+					/* VDDA_1V8_PHY: usb/sata/hdmi.. */
 					regulator-name = "ldo5";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -379,38 +386,43 @@
 				};
 
 				ldo6_reg: ldo6 {
+					/* VDDS_1V2_WKUP: hsic/ldo_emu_wkup */
 					regulator-name = "ldo6";
-					regulator-min-microvolt = <1500000>;
-					regulator-max-microvolt = <1500000>;
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
 					regulator-always-on;
 					regulator-boot-on;
 				};
 
 				ldo7_reg: ldo7 {
+					/* VDD_VPP: vpp1 */
 					regulator-name = "ldo7";
-					regulator-min-microvolt = <1500000>;
-					regulator-max-microvolt = <1500000>;
-					regulator-always-on;
-					regulator-boot-on;
+					regulator-min-microvolt = <2000000>;
+					regulator-max-microvolt = <2000000>;
+					/* Only for efuse reprograming! */
+					status = "disabled";
 				};
 
 				ldo8_reg: ldo8 {
+					/* VDD_3v0: Does not go anywhere */
 					regulator-name = "ldo8";
-					regulator-min-microvolt = <1500000>;
-					regulator-max-microvolt = <1500000>;
-					regulator-always-on;
+					regulator-min-microvolt = <3000000>;
+					regulator-max-microvolt = <3000000>;
 					regulator-boot-on;
+					/* Unused */
+					status = "disabled";
 				};
 
 				ldo9_reg: ldo9 {
+					/* VCC_DV_SDIO: vdds_sdcard */
 					regulator-name = "ldo9";
 					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <3300000>;
-					regulator-always-on;
+					regulator-max-microvolt = <3000000>;
 					regulator-boot-on;
 				};
 
 				ldoln_reg: ldoln {
+					/* VDDA_1v8_REF: vdds_osc/mm_l4per.. */
 					regulator-name = "ldoln";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -419,12 +431,20 @@
 				};
 
 				ldousb_reg: ldousb {
+					/* VDDA_3V_USB: VDDA_USBHS33 */
 					regulator-name = "ldousb";
 					regulator-min-microvolt = <3250000>;
 					regulator-max-microvolt = <3250000>;
 					regulator-always-on;
 					regulator-boot-on;
 				};
+
+				regen3_reg: regen3 {
+					/* REGEN3 controls LDO9 supply to card */
+					regulator-name = "regen3";
+					regulator-always-on;
+					regulator-boot-on;
+				};
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/prima2.dtsi b/arch/arm/boot/dts/prima2.dtsi
index 05e9489cf95c..bbeb623fc2c6 100644
--- a/arch/arm/boot/dts/prima2.dtsi
+++ b/arch/arm/boot/dts/prima2.dtsi
@@ -515,16 +515,16 @@
                                                 sirf,function = "pulse_count";
                                         };
                                 };
-                                cko0_rst_pins_a: cko0_rst@0 {
-                                        cko0_rst {
-                                                sirf,pins = "cko0_rstgrp";
-                                                sirf,function = "cko0_rst";
+                                cko0_pins_a: cko0@0 {
+                                        cko0 {
+                                                sirf,pins = "cko0grp";
+                                                sirf,function = "cko0";
                                         };
                                 };
-                                cko1_rst_pins_a: cko1_rst@0 {
-                                        cko1_rst {
-                                                sirf,pins = "cko1_rstgrp";
-                                                sirf,function = "cko1_rst";
+                                cko1_pins_a: cko1@0 {
+                                        cko1 {
+                                                sirf,pins = "cko1grp";
+                                                sirf,function = "cko1";
                                         };
                                 };
 			};
diff --git a/arch/arm/boot/dts/stih416-pinctrl.dtsi b/arch/arm/boot/dts/stih416-pinctrl.dtsi
index 957b21a71b4b..0f246c979262 100644
--- a/arch/arm/boot/dts/stih416-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stih416-pinctrl.dtsi
@@ -166,6 +166,15 @@
 				reg		= <0x9000 0x100>;
 				st,bank-name	= "PIO31";
 			};
+
+			serial2-oe {
+				pinctrl_serial2_oe: serial2-1 {
+					st,pins {
+						output-enable	= <&PIO11 3 ALT2 OUT>;
+					};
+				};
+			};
+
 		};
 
 		pin-controller-rear {
@@ -218,7 +227,6 @@
 					st,pins {
 						tx	= <&PIO17 4 ALT2 OUT>;
 						rx	= <&PIO17 5 ALT2 IN>;
-						output-enable	= <&PIO11 3 ALT2 OUT>;
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/stih416.dtsi b/arch/arm/boot/dts/stih416.dtsi
index 3cecd9689a49..1a0326ea7d07 100644
--- a/arch/arm/boot/dts/stih416.dtsi
+++ b/arch/arm/boot/dts/stih416.dtsi
@@ -79,7 +79,7 @@
 			interrupts	= <0 197 0>;
 			clocks          = <&CLK_S_ICN_REG_0>;
 			pinctrl-names 	= "default";
-			pinctrl-0 	= <&pinctrl_serial2>;
+			pinctrl-0 	= <&pinctrl_serial2 &pinctrl_serial2_oe>;
 		};
 
 		/* SBC_UART1 */
diff --git a/arch/arm/boot/dts/stih41x.dtsi b/arch/arm/boot/dts/stih41x.dtsi
index 7321403cab8a..f5b9898d9c6e 100644
--- a/arch/arm/boot/dts/stih41x.dtsi
+++ b/arch/arm/boot/dts/stih41x.dtsi
@@ -6,10 +6,12 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		cpu@0 {
+			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0>;
 		};
 		cpu@1 {
+			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <1>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-colibri-512.dtsi b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
index 2fcb3f2ca160..5592be6f2f7a 100644
--- a/arch/arm/boot/dts/tegra20-colibri-512.dtsi
+++ b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
@@ -457,6 +457,7 @@
 	};
 
 	usb-phy@c5004000 {
+		status = "okay";
 		nvidia,phy-reset-gpio = <&gpio TEGRA_GPIO(V, 1)
 			GPIO_ACTIVE_LOW>;
 	};
diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts
index 365760b33a26..40e6fb280333 100644
--- a/arch/arm/boot/dts/tegra20-seaboard.dts
+++ b/arch/arm/boot/dts/tegra20-seaboard.dts
@@ -830,6 +830,8 @@
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
 			gpio = <&gpio 24 0>; /* PD0 */
+			regulator-always-on;
+			regulator-boot-on;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts
index ed4b901b0227..37c93d3c4812 100644
--- a/arch/arm/boot/dts/tegra20-trimslice.dts
+++ b/arch/arm/boot/dts/tegra20-trimslice.dts
@@ -412,6 +412,8 @@
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
 			gpio = <&gpio 170 0>; /* PV2 */
+			regulator-always-on;
+			regulator-boot-on;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/tegra20-whistler.dts b/arch/arm/boot/dts/tegra20-whistler.dts
index ab67c94db280..a3d0ebad78a1 100644
--- a/arch/arm/boot/dts/tegra20-whistler.dts
+++ b/arch/arm/boot/dts/tegra20-whistler.dts
@@ -588,6 +588,8 @@
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
 			gpio = <&tca6416 0 0>; /* GPIO_PMU0 */
+			regulator-always-on;
+			regulator-boot-on;
 		};
 
 		vbus3_reg: regulator@3 {
@@ -598,6 +600,8 @@
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
 			gpio = <&tca6416 1 0>; /* GPIO_PMU1 */
+			regulator-always-on;
+			regulator-boot-on;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/twl4030.dtsi b/arch/arm/boot/dts/twl4030.dtsi
index b3034da00a37..ae6a17aed9ee 100644
--- a/arch/arm/boot/dts/twl4030.dtsi
+++ b/arch/arm/boot/dts/twl4030.dtsi
@@ -47,6 +47,12 @@
 		regulator-max-microvolt = <3150000>;
 	};
 
+	vmmc2: regulator-vmmc2 {
+		compatible = "ti,twl4030-vmmc2";
+		regulator-min-microvolt = <1850000>;
+		regulator-max-microvolt = <3150000>;
+	};
+
 	vusb1v5: regulator-vusb1v5 {
 		compatible = "ti,twl4030-vusb1v5";
 	};
diff --git a/arch/arm/boot/dts/vf610.dtsi b/arch/arm/boot/dts/vf610.dtsi
index e1eb7dadda80..67d929cf9804 100644
--- a/arch/arm/boot/dts/vf610.dtsi
+++ b/arch/arm/boot/dts/vf610.dtsi
@@ -442,8 +442,8 @@
 				compatible = "fsl,mvf600-fec";
 				reg = <0x400d0000 0x1000>;
 				interrupts = <0 78 0x04>;
-				clocks = <&clks VF610_CLK_ENET>,
-					<&clks VF610_CLK_ENET>,
+				clocks = <&clks VF610_CLK_ENET0>,
+					<&clks VF610_CLK_ENET0>,
 					<&clks VF610_CLK_ENET>;
 				clock-names = "ipg", "ahb", "ptp";
 				status = "disabled";
@@ -453,8 +453,8 @@
 				compatible = "fsl,mvf600-fec";
 				reg = <0x400d1000 0x1000>;
 				interrupts = <0 79 0x04>;
-				clocks = <&clks VF610_CLK_ENET>,
-					<&clks VF610_CLK_ENET>,
+				clocks = <&clks VF610_CLK_ENET1>,
+					<&clks VF610_CLK_ENET1>,
 					<&clks VF610_CLK_ENET>;
 				clock-names = "ipg", "ahb", "ptp";
 				status = "disabled";
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index a432e6c1dac1..39ad030ac0c7 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -26,7 +26,6 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/edma.h>
-#include <linux/err.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
diff --git a/arch/arm/configs/da8xx_omapl_defconfig b/arch/arm/configs/da8xx_omapl_defconfig
index 7c868139bdb0..1571bea48bed 100644
--- a/arch/arm/configs/da8xx_omapl_defconfig
+++ b/arch/arm/configs/da8xx_omapl_defconfig
@@ -102,6 +102,8 @@ CONFIG_SND_SOC=m
 CONFIG_SND_DAVINCI_SOC=m
 # CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
+CONFIG_DMADEVICES=y
+CONFIG_TI_EDMA=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_XFS_FS=m
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index c86fd75e181a..ab2f7378352c 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -162,6 +162,8 @@ CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=m
 CONFIG_LEDS_TRIGGER_HEARTBEAT=m
 CONFIG_RTC_CLASS=y
+CONFIG_DMADEVICES=y
+CONFIG_TI_EDMA=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_XFS_FS=m
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index fe0bdc361d2c..6e572c64cf5a 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -53,6 +53,7 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_OMAP_OCP2SCP=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI_PLATFORM=y
@@ -61,6 +62,7 @@ CONFIG_SATA_MV=y
 CONFIG_NETDEVICES=y
 CONFIG_SUN4I_EMAC=y
 CONFIG_NET_CALXEDA_XGMAC=y
+CONFIG_KS8851=y
 CONFIG_SMSC911X=y
 CONFIG_STMMAC_ETH=y
 CONFIG_MDIO_SUN4I=y
@@ -89,6 +91,7 @@ CONFIG_I2C_DESIGNWARE_PLATFORM=y
 CONFIG_I2C_SIRF=y
 CONFIG_I2C_TEGRA=y
 CONFIG_SPI=y
+CONFIG_SPI_OMAP24XX=y
 CONFIG_SPI_PL022=y
 CONFIG_SPI_SIRF=y
 CONFIG_SPI_TEGRA114=y
@@ -111,11 +114,12 @@ CONFIG_FB_SIMPLE=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_MXC=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_ISP1760_HCD=y
 CONFIG_USB_STORAGE=y
+CONFIG_USB_CHIPIDEA=y
+CONFIG_USB_CHIPIDEA_HOST=y
 CONFIG_AB8500_USB=y
 CONFIG_NOP_USB_XCEIV=y
 CONFIG_OMAP_USB2=y
diff --git a/arch/arm/configs/nhk8815_defconfig b/arch/arm/configs/nhk8815_defconfig
index 35f8cf299fa2..263ae3869e32 100644
--- a/arch/arm/configs/nhk8815_defconfig
+++ b/arch/arm/configs/nhk8815_defconfig
@@ -1,6 +1,8 @@
 # CONFIG_LOCALVERSION_AUTO is not set
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -48,7 +50,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_TESTS=m
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_NAND_ECC_SMC=y
 CONFIG_MTD_NAND=y
@@ -94,8 +95,10 @@ CONFIG_I2C_GPIO=y
 CONFIG_I2C_NOMADIK=y
 CONFIG_DEBUG_GPIO=y
 # CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
 CONFIG_MMC=y
-CONFIG_MMC_CLKGATE=y
+CONFIG_MMC_UNSAFE_RESUME=y
+# CONFIG_MMC_BLOCK_BOUNCE is not set
 CONFIG_MMC_ARMMMCI=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
diff --git a/arch/arm/include/asm/a.out-core.h b/arch/arm/include/asm/a.out-core.h
deleted file mode 100644
index 92f10cb5c70c..000000000000
--- a/arch/arm/include/asm/a.out-core.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/* a.out coredump register dumper
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#ifndef _ASM_A_OUT_CORE_H
-#define _ASM_A_OUT_CORE_H
-
-#ifdef __KERNEL__
-
-#include <linux/user.h>
-#include <linux/elfcore.h>
-
-/*
- * fill in the user structure for an a.out core dump
- */
-static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
-{
-	struct task_struct *tsk = current;
-
-	dump->magic = CMAGIC;
-	dump->start_code = tsk->mm->start_code;
-	dump->start_stack = regs->ARM_sp & ~(PAGE_SIZE - 1);
-
-	dump->u_tsize = (tsk->mm->end_code - tsk->mm->start_code) >> PAGE_SHIFT;
-	dump->u_dsize = (tsk->mm->brk - tsk->mm->start_data + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	dump->u_ssize = 0;
-
-	memset(dump->u_debugreg, 0, sizeof(dump->u_debugreg));
-
-	if (dump->start_stack < 0x04000000)
-		dump->u_ssize = (0x04000000 - dump->start_stack) >> PAGE_SHIFT;
-
-	dump->regs = *regs;
-	dump->u_fpvalid = dump_fpu (regs, &dump->u_fp);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_A_OUT_CORE_H */
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 8c25dc4e9851..9672e978d50d 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -89,13 +89,18 @@ extern unsigned int processor_id;
 		__val;							\
 	})
 
+/*
+ * The memory clobber prevents gcc 4.5 from reordering the mrc before
+ * any is_smp() tests, which can cause undefined instruction aborts on
+ * ARM1136 r0 due to the missing extended CP15 registers.
+ */
 #define read_cpuid_ext(ext_reg)						\
 	({								\
 		unsigned int __val;					\
 		asm("mrc	p15, 0, %0, c0, " ext_reg		\
 		    : "=r" (__val)					\
 		    :							\
-		    : "cc");						\
+		    : "memory");					\
 		__val;							\
 	})
 
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 38050b1c4800..56211f2084ef 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -130,4 +130,10 @@ struct mm_struct;
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
+#ifdef CONFIG_MMU
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+int arch_setup_additional_pages(struct linux_binprm *, int);
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index e3d55547e755..6f18da09668b 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -6,8 +6,11 @@
 typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
 	atomic64_t	id;
+#else
+	int		switch_pending;
 #endif
 	unsigned int	vmalloc_seq;
+	unsigned long	sigpage;
 } mm_context_t;
 
 #ifdef CONFIG_CPU_HAS_ASID
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index b5792b7fd8d3..9b32f76bb0dd 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -56,7 +56,7 @@ static inline void check_and_switch_context(struct mm_struct *mm,
 		 * on non-ASID CPUs, the old mm will remain valid until the
 		 * finish_arch_post_lock_switch() call.
 		 */
-		set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
+		mm->context.switch_pending = 1;
 	else
 		cpu_switch_mm(mm->pgd, mm);
 }
@@ -65,9 +65,21 @@ static inline void check_and_switch_context(struct mm_struct *mm,
 	finish_arch_post_lock_switch
 static inline void finish_arch_post_lock_switch(void)
 {
-	if (test_and_clear_thread_flag(TIF_SWITCH_MM)) {
-		struct mm_struct *mm = current->mm;
-		cpu_switch_mm(mm->pgd, mm);
+	struct mm_struct *mm = current->mm;
+
+	if (mm && mm->context.switch_pending) {
+		/*
+		 * Preemption must be disabled during cpu_switch_mm() as we
+		 * have some stateful cache flush implementations. Check
+		 * switch_pending again in case we were preempted and the
+		 * switch to this mm was already done.
+		 */
+		preempt_disable();
+		if (mm->context.switch_pending) {
+			mm->context.switch_pending = 0;
+			cpu_switch_mm(mm->pgd, mm);
+		}
+		preempt_enable_no_resched();
 	}
 }
 
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 6363f3d1d505..4355f0ec44d6 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -142,7 +142,9 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
+#ifdef CONFIG_KUSER_HELPERS
 #define __HAVE_ARCH_GATE_AREA 1
+#endif
 
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level-types.h>
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 06e7d509eaac..413f3876341c 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -54,7 +54,6 @@ struct thread_struct {
 
 #define start_thread(regs,pc,sp)					\
 ({									\
-	unsigned long *stack = (unsigned long *)sp;			\
 	memset(regs->uregs, 0, sizeof(regs->uregs));			\
 	if (current->personality & ADDR_LIMIT_32BIT)			\
 		regs->ARM_cpsr = USR_MODE;				\
@@ -65,9 +64,6 @@ struct thread_struct {
 	regs->ARM_cpsr |= PSR_ENDSTATE;					\
 	regs->ARM_pc = pc & ~1;		/* pc */			\
 	regs->ARM_sp = sp;		/* sp */			\
-	regs->ARM_r2 = stack[2];	/* r2 (envp) */			\
-	regs->ARM_r1 = stack[1];	/* r1 (argv) */			\
-	regs->ARM_r0 = stack[0];	/* r0 (argc) */			\
 	nommu_start_thread(regs);					\
 })
 
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 6462a721ebd4..a252c0bfacf5 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -88,4 +88,7 @@ static inline u32 mpidr_hash_size(void)
 {
 	return 1 << mpidr_hash.bits;
 }
+
+extern int platform_can_cpu_hotplug(void);
+
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index f8b8965666e9..b07c09e5a0ac 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -107,7 +107,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 		"	subs	%1, %0, %0, ror #16\n"
 		"	addeq	%0, %0, %4\n"
 		"	strexeq	%2, %0, [%3]"
-		: "=&r" (slock), "=&r" (contended), "=r" (res)
+		: "=&r" (slock), "=&r" (contended), "=&r" (res)
 		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
 		: "cc");
 	} while (res);
@@ -168,17 +168,20 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	unsigned long tmp;
+	unsigned long contended, res;
 
-	__asm__ __volatile__(
-"	ldrex	%0, [%1]\n"
-"	teq	%0, #0\n"
-"	strexeq	%0, %2, [%1]"
-	: "=&r" (tmp)
-	: "r" (&rw->lock), "r" (0x80000000)
-	: "cc");
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	teq	%0, #0\n"
+		"	strexeq	%1, %3, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock), "r" (0x80000000)
+		: "cc");
+	} while (res);
 
-	if (tmp == 0) {
+	if (!contended) {
 		smp_mb();
 		return 1;
 	} else {
@@ -254,18 +257,26 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned long tmp, tmp2 = 1;
+	unsigned long contended, res;
 
-	__asm__ __volatile__(
-"	ldrex	%0, [%2]\n"
-"	adds	%0, %0, #1\n"
-"	strexpl	%1, %0, [%2]\n"
-	: "=&r" (tmp), "+r" (tmp2)
-	: "r" (&rw->lock)
-	: "cc");
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	adds	%0, %0, #1\n"
+		"	strexpl	%1, %0, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock)
+		: "cc");
+	} while (res);
 
-	smp_mb();
-	return tmp2 == 0;
+	/* If the lock is negative, then it is already held for write. */
+	if (contended < 0x80000000) {
+		smp_mb();
+		return 1;
+	} else {
+		return 0;
+	}
 }
 
 /* read_can_lock - would read_trylock() succeed? */
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 214d4158089a..2b8114fcba09 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -156,7 +156,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	20
-#define TIF_SWITCH_MM		22	/* deferred switch_mm */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 46e7cfb3e721..0baf7f0d9394 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -43,6 +43,7 @@ struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		fullmm;
 	struct vm_area_struct	*vma;
+	unsigned long		start, end;
 	unsigned long		range_start;
 	unsigned long		range_end;
 	unsigned int		nr;
@@ -107,10 +108,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = fullmm;
+	tlb->fullmm = !(start | (end+1));
+	tlb->start = start;
+	tlb->end = end;
 	tlb->vma = NULL;
 	tlb->max = ARRAY_SIZE(tlb->local);
 	tlb->pages = tlb->local;
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index fdbb9e369745..f467e9b3f8d5 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -443,7 +443,18 @@ static inline void local_flush_bp_all(void)
 		isb();
 }
 
+#include <asm/cputype.h>
 #ifdef CONFIG_ARM_ERRATA_798181
+static inline int erratum_a15_798181(void)
+{
+	unsigned int midr = read_cpuid_id();
+
+	/* Cortex-A15 r0p0..r3p2 affected */
+	if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2)
+		return 0;
+	return 1;
+}
+
 static inline void dummy_flush_tlb_a15_erratum(void)
 {
 	/*
@@ -453,6 +464,11 @@ static inline void dummy_flush_tlb_a15_erratum(void)
 	dsb();
 }
 #else
+static inline int erratum_a15_798181(void)
+{
+	return 0;
+}
+
 static inline void dummy_flush_tlb_a15_erratum(void)
 {
 }
diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
index 50af92bac737..4371f45c5784 100644
--- a/arch/arm/include/asm/virt.h
+++ b/arch/arm/include/asm/virt.h
@@ -29,6 +29,7 @@
 #define BOOT_CPU_MODE_MISMATCH	PSR_N_BIT
 
 #ifndef __ASSEMBLY__
+#include <asm/cacheflush.h>
 
 #ifdef CONFIG_ARM_VIRT_EXT
 /*
@@ -41,10 +42,21 @@
  */
 extern int __boot_cpu_mode;
 
+static inline void sync_boot_mode(void)
+{
+	/*
+	 * As secondaries write to __boot_cpu_mode with caches disabled, we
+	 * must flush the corresponding cache entries to ensure the visibility
+	 * of their writes.
+	 */
+	sync_cache_r(&__boot_cpu_mode);
+}
+
 void __hyp_set_vectors(unsigned long phys_vector_base);
 unsigned long __hyp_get_vectors(void);
 #else
 #define __boot_cpu_mode	(SVC_MODE)
+#define sync_boot_mode()
 #endif
 
 #ifndef ZIMAGE
diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild
index 47bcb2d254af..18d76fd5a2af 100644
--- a/arch/arm/include/uapi/asm/Kbuild
+++ b/arch/arm/include/uapi/asm/Kbuild
@@ -1,7 +1,6 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
-header-y += a.out.h
 header-y += byteorder.h
 header-y += fcntl.h
 header-y += hwcap.h
diff --git a/arch/arm/include/uapi/asm/a.out.h b/arch/arm/include/uapi/asm/a.out.h
deleted file mode 100644
index 083894b2e3bc..000000000000
--- a/arch/arm/include/uapi/asm/a.out.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __ARM_A_OUT_H__
-#define __ARM_A_OUT_H__
-
-#include <linux/personality.h>
-#include <linux/types.h>
-
-struct exec
-{
-  __u32 a_info;		/* Use macros N_MAGIC, etc for access */
-  __u32 a_text;		/* length of text, in bytes */
-  __u32 a_data;		/* length of data, in bytes */
-  __u32 a_bss;		/* length of uninitialized data area for file, in bytes */
-  __u32 a_syms;		/* length of symbol table data in file, in bytes */
-  __u32 a_entry;	/* start address */
-  __u32 a_trsize;	/* length of relocation info for text, in bytes */
-  __u32 a_drsize;	/* length of relocation info for data, in bytes */
-};
-
-/*
- * This is always the same
- */
-#define N_TXTADDR(a)	(0x00008000)
-
-#define N_TRSIZE(a)	((a).a_trsize)
-#define N_DRSIZE(a)	((a).a_drsize)
-#define N_SYMSIZE(a)	((a).a_syms)
-
-#define M_ARM 103
-
-#ifndef LIBRARY_START_TEXT
-#define LIBRARY_START_TEXT	(0x00c00000)
-#endif
-
-#endif /* __A_OUT_GNU_H__ */
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index a39cfc2a1f90..9cbe70c8b0ef 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -357,7 +357,8 @@ ENDPROC(__pabt_svc)
 	.endm
 
 	.macro	kuser_cmpxchg_check
-#if !defined(CONFIG_CPU_32v6K) && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS) && \
+    !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
 #ifndef CONFIG_MMU
 #warning "NPTL on non MMU needs fixing"
 #else
@@ -742,6 +743,18 @@ ENDPROC(__switch_to)
 #endif
 	.endm
 
+	.macro	kuser_pad, sym, size
+	.if	(. - \sym) & 3
+	.rept	4 - (. - \sym) & 3
+	.byte	0
+	.endr
+	.endif
+	.rept	(\size - (. - \sym)) / 4
+	.word	0xe7fddef1
+	.endr
+	.endm
+
+#ifdef CONFIG_KUSER_HELPERS
 	.align	5
 	.globl	__kuser_helper_start
 __kuser_helper_start:
@@ -832,18 +845,13 @@ kuser_cmpxchg64_fixup:
 #error "incoherent kernel configuration"
 #endif
 
-	/* pad to next slot */
-	.rept	(16 - (. - __kuser_cmpxchg64)/4)
-	.word	0
-	.endr
-
-	.align	5
+	kuser_pad __kuser_cmpxchg64, 64
 
 __kuser_memory_barrier:				@ 0xffff0fa0
 	smp_dmb	arm
 	usr_ret	lr
 
-	.align	5
+	kuser_pad __kuser_memory_barrier, 32
 
 __kuser_cmpxchg:				@ 0xffff0fc0
 
@@ -916,13 +924,14 @@ kuser_cmpxchg32_fixup:
 
 #endif
 
-	.align	5
+	kuser_pad __kuser_cmpxchg, 32
 
 __kuser_get_tls:				@ 0xffff0fe0
 	ldr	r0, [pc, #(16 - 8)]	@ read TLS, set in kuser_get_tls_init
 	usr_ret	lr
 	mrc	p15, 0, r0, c13, c0, 3	@ 0xffff0fe8 hardware TLS code
-	.rep	4
+	kuser_pad __kuser_get_tls, 16
+	.rep	3
 	.word	0			@ 0xffff0ff0 software TLS value, then
 	.endr				@ pad up to __kuser_helper_version
 
@@ -932,14 +941,16 @@ __kuser_helper_version:				@ 0xffff0ffc
 	.globl	__kuser_helper_end
 __kuser_helper_end:
 
+#endif
+
  THUMB(	.thumb	)
 
 /*
  * Vector stubs.
  *
- * This code is copied to 0xffff0200 so we can use branches in the
- * vectors, rather than ldr's.  Note that this code must not
- * exceed 0x300 bytes.
+ * This code is copied to 0xffff1000 so we can use branches in the
+ * vectors, rather than ldr's.  Note that this code must not exceed
+ * a page size.
  *
  * Common stub entry macro:
  *   Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC
@@ -986,8 +997,17 @@ ENDPROC(vector_\name)
 1:
 	.endm
 
-	.globl	__stubs_start
+	.section .stubs, "ax", %progbits
 __stubs_start:
+	@ This must be the first word
+	.word	vector_swi
+
+vector_rst:
+ ARM(	swi	SYS_ERROR0	)
+ THUMB(	svc	#0		)
+ THUMB(	nop			)
+	b	vector_und
+
 /*
  * Interrupt dispatcher
  */
@@ -1082,6 +1102,16 @@ __stubs_start:
 	.align	5
 
 /*=============================================================================
+ * Address exception handler
+ *-----------------------------------------------------------------------------
+ * These aren't too critical.
+ * (they're not supposed to happen, and won't happen in 32-bit data mode).
+ */
+
+vector_addrexcptn:
+	b	vector_addrexcptn
+
+/*=============================================================================
  * Undefined FIQs
  *-----------------------------------------------------------------------------
  * Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC
@@ -1094,45 +1124,19 @@ __stubs_start:
 vector_fiq:
 	subs	pc, lr, #4
 
-/*=============================================================================
- * Address exception handler
- *-----------------------------------------------------------------------------
- * These aren't too critical.
- * (they're not supposed to happen, and won't happen in 32-bit data mode).
- */
-
-vector_addrexcptn:
-	b	vector_addrexcptn
-
-/*
- * We group all the following data together to optimise
- * for CPUs with separate I & D caches.
- */
-	.align	5
-
-.LCvswi:
-	.word	vector_swi
-
-	.globl	__stubs_end
-__stubs_end:
-
-	.equ	stubs_offset, __vectors_start + 0x200 - __stubs_start
+	.globl	vector_fiq_offset
+	.equ	vector_fiq_offset, vector_fiq
 
-	.globl	__vectors_start
+	.section .vectors, "ax", %progbits
 __vectors_start:
- ARM(	swi	SYS_ERROR0	)
- THUMB(	svc	#0		)
- THUMB(	nop			)
-	W(b)	vector_und + stubs_offset
-	W(ldr)	pc, .LCvswi + stubs_offset
-	W(b)	vector_pabt + stubs_offset
-	W(b)	vector_dabt + stubs_offset
-	W(b)	vector_addrexcptn + stubs_offset
-	W(b)	vector_irq + stubs_offset
-	W(b)	vector_fiq + stubs_offset
-
-	.globl	__vectors_end
-__vectors_end:
+	W(b)	vector_rst
+	W(b)	vector_und
+	W(ldr)	pc, __vectors_start + 0x1000
+	W(b)	vector_pabt
+	W(b)	vector_dabt
+	W(b)	vector_addrexcptn
+	W(b)	vector_irq
+	W(b)	vector_fiq
 
 	.data
 
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index e00621f1403f..52b26432c9a9 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -49,7 +49,7 @@ __irq_entry:
 	mov	r1, sp
 	stmdb	sp!, {lr}
 	@ routine called with r0 = irq number, r1 = struct pt_regs *
-	bl	nvic_do_IRQ
+	bl	nvic_handle_irq
 
 	pop	{lr}
 	@
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 2adda11f712f..918875d96d5d 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -47,6 +47,11 @@
 #include <asm/irq.h>
 #include <asm/traps.h>
 
+#define FIQ_OFFSET ({					\
+		extern void *vector_fiq_offset;		\
+		(unsigned)&vector_fiq_offset;		\
+	})
+
 static unsigned long no_fiq_insn;
 
 /* Default reacquire function
@@ -79,14 +84,14 @@ int show_fiq_list(struct seq_file *p, int prec)
 
 void set_fiq_handler(void *start, unsigned int length)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-	memcpy((void *)0xffff001c, start, length);
-#else
-	memcpy(vectors_page + 0x1c, start, length);
-#endif
-	flush_icache_range(0xffff001c, 0xffff001c + length);
-	if (!vectors_high())
-		flush_icache_range(0x1c, 0x1c + length);
+	void *base = vectors_page;
+	unsigned offset = FIQ_OFFSET;
+
+	memcpy(base + offset, start, length);
+	if (!cache_is_vipt_nonaliasing())
+		flush_icache_range((unsigned long)base + offset, offset +
+				   length);
+	flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
 }
 
 int claim_fiq(struct fiq_handler *f)
@@ -144,6 +149,7 @@ EXPORT_SYMBOL(disable_fiq);
 
 void __init init_FIQ(int start)
 {
-	no_fiq_insn = *(unsigned long *)0xffff001c;
+	unsigned offset = FIQ_OFFSET;
+	no_fiq_insn = *(unsigned long *)(0xffff0000 + offset);
 	fiq_start = start;
 }
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index b361de143756..14235ba64a90 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -87,6 +87,7 @@ ENTRY(stext)
 ENDPROC(stext)
 
 #ifdef CONFIG_SMP
+	.text
 ENTRY(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 9cf6063020ae..2c7cc1e03473 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -343,6 +343,7 @@ __turn_mmu_on_loc:
 	.long	__turn_mmu_on_end
 
 #if defined(CONFIG_SMP)
+	.text
 ENTRY(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 4910232c4833..797b1a6a4906 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -56,8 +56,8 @@ ENTRY(__boot_cpu_mode)
 	ldr	\reg3, [\reg2]
 	ldr	\reg1, [\reg2, \reg3]
 	cmp	\mode, \reg1		@ matches primary CPU boot mode?
-	orrne	r7, r7, #BOOT_CPU_MODE_MISMATCH
-	strne	r7, [r5, r6]		@ record what happened and give up
+	orrne	\reg1, \reg1, #BOOT_CPU_MODE_MISMATCH
+	strne	\reg1, [\reg2, \reg3]	@ record what happened and give up
 	.endm
 
 #else	/* ZIMAGE */
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 4fb074c446bf..57221e349a7c 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -15,6 +15,7 @@
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
+#include <asm/smp_plat.h>
 #include <asm/system_misc.h>
 
 extern const unsigned char relocate_new_kernel[];
@@ -39,6 +40,14 @@ int machine_kexec_prepare(struct kimage *image)
 	int i, err;
 
 	/*
+	 * Validate that if the current HW supports SMP, then the SW supports
+	 * and implements CPU hotplug for the current HW. If not, we won't be
+	 * able to kexec reliably, so fail the prepare operation.
+	 */
+	if (num_possible_cpus() > 1 && !platform_can_cpu_hotplug())
+		return -EINVAL;
+
+	/*
 	 * No segment at default ATAGs address. try to locate
 	 * a dtb using magic.
 	 */
@@ -73,6 +82,7 @@ void machine_crash_nonpanic_core(void *unused)
 	crash_save_cpu(&regs, smp_processor_id());
 	flush_cache_all();
 
+	set_cpu_online(smp_processor_id(), false);
 	atomic_dec(&waiting_for_crash_ipi);
 	while (1)
 		cpu_relax();
@@ -134,10 +144,13 @@ void machine_kexec(struct kimage *image)
 	unsigned long reboot_code_buffer_phys;
 	void *reboot_code_buffer;
 
-	if (num_online_cpus() > 1) {
-		pr_err("kexec: error: multiple CPUs still online\n");
-		return;
-	}
+	/*
+	 * This can only happen if machine_shutdown() failed to disable some
+	 * CPU, and that can only happen if the checks in
+	 * machine_kexec_prepare() were not correct. If this fails, we can't
+	 * reliably kexec anyway, so BUG_ON is appropriate.
+	 */
+	BUG_ON(num_online_cpus() > 1);
 
 	page_list = image->head & PAGE_MASK;
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index d9f5cd4e533f..e186ee1e63f6 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -53,7 +53,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-	int mapping = (*event_map)[config];
+	int mapping;
+
+	if (config >= PERF_COUNT_HW_MAX)
+		return -EINVAL;
+
+	mapping = (*event_map)[config];
 	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -253,6 +258,9 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
+	if (is_software_event(event))
+		return 1;
+
 	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
 		return 1;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d3ca4f6915af..94f6b05f9e24 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -197,6 +197,7 @@ void machine_shutdown(void)
  */
 void machine_halt(void)
 {
+	local_irq_disable();
 	smp_send_stop();
 
 	local_irq_disable();
@@ -211,6 +212,7 @@ void machine_halt(void)
  */
 void machine_power_off(void)
 {
+	local_irq_disable();
 	smp_send_stop();
 
 	if (pm_power_off)
@@ -230,6 +232,7 @@ void machine_power_off(void)
  */
 void machine_restart(char *cmd)
 {
+	local_irq_disable();
 	smp_send_stop();
 
 	arm_pm_restart(reboot_mode, cmd);
@@ -426,10 +429,11 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 }
 
 #ifdef CONFIG_MMU
+#ifdef CONFIG_KUSER_HELPERS
 /*
  * The vectors page is always readable from user space for the
- * atomic helpers and the signal restart code. Insert it into the
- * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
+ * atomic helpers. Insert it into the gate_vma so that it is visible
+ * through ptrace and /proc/<pid>/mem.
  */
 static struct vm_area_struct gate_vma = {
 	.vm_start	= 0xffff0000,
@@ -458,9 +462,48 @@ int in_gate_area_no_mm(unsigned long addr)
 {
 	return in_gate_area(NULL, addr);
 }
+#define is_gate_vma(vma)	((vma) == &gate_vma)
+#else
+#define is_gate_vma(vma)	0
+#endif
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	return (vma == &gate_vma) ? "[vectors]" : NULL;
+	return is_gate_vma(vma) ? "[vectors]" :
+		(vma->vm_mm && vma->vm_start == vma->vm_mm->context.sigpage) ?
+		 "[sigpage]" : NULL;
+}
+
+static struct page *signal_page;
+extern struct page *get_signal_page(void);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr;
+	int ret;
+
+	if (!signal_page)
+		signal_page = get_signal_page();
+	if (!signal_page)
+		return -ENOMEM;
+
+	down_write(&mm->mmap_sem);
+	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	ret = install_special_mapping(mm, addr, PAGE_SIZE,
+		VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
+		&signal_page);
+
+	if (ret == 0)
+		mm->context.sigpage = addr;
+
+ up_fail:
+	up_write(&mm->mmap_sem);
+	return ret;
 }
 #endif
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 63af9a7ae512..afc2489ee13b 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -836,6 +836,8 @@ static int __init meminfo_cmp(const void *_a, const void *_b)
 void __init hyp_mode_check(void)
 {
 #ifdef CONFIG_ARM_VIRT_EXT
+	sync_boot_mode();
+
 	if (is_hyp_mode_available()) {
 		pr_info("CPU: All CPU(s) started in HYP mode.\n");
 		pr_info("CPU: Virtualization extensions available.\n");
@@ -971,6 +973,7 @@ static const char *hwcap_str[] = {
 	"vfpv4",
 	"idiva",
 	"idivt",
+	"vfpd32",
 	"lpae",
 	NULL
 };
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 1c16c35c271a..ab3304225272 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/errno.h>
+#include <linux/random.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/uaccess.h>
@@ -15,12 +16,11 @@
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
+#include <asm/traps.h>
 #include <asm/ucontext.h>
 #include <asm/unistd.h>
 #include <asm/vfp.h>
 
-#include "signal.h"
-
 /*
  * For ARM syscalls, we encode the syscall number into the instruction.
  */
@@ -40,11 +40,13 @@
 #define SWI_THUMB_SIGRETURN	(0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE))
 #define SWI_THUMB_RT_SIGRETURN	(0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
 
-const unsigned long sigreturn_codes[7] = {
+static const unsigned long sigreturn_codes[7] = {
 	MOV_R7_NR_SIGRETURN,    SWI_SYS_SIGRETURN,    SWI_THUMB_SIGRETURN,
 	MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN,
 };
 
+static unsigned long signal_return_offset;
+
 #ifdef CONFIG_CRUNCH
 static int preserve_crunch_context(struct crunch_sigframe __user *frame)
 {
@@ -400,14 +402,20 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig,
 		    __put_user(sigreturn_codes[idx+1], rc+1))
 			return 1;
 
-		if ((cpsr & MODE32_BIT) && !IS_ENABLED(CONFIG_ARM_MPU)) {
+#ifdef CONFIG_MMU
+		if (cpsr & MODE32_BIT) {
+			struct mm_struct *mm = current->mm;
+
 			/*
-			 * 32-bit code can use the new high-page
-			 * signal return code support except when the MPU has
-			 * protected the vectors page from PL0
+			 * 32-bit code can use the signal return page
+			 * except when the MPU has protected the vectors
+			 * page from PL0
 			 */
-			retcode = KERN_SIGRETURN_CODE + (idx << 2) + thumb;
-		} else {
+			retcode = mm->context.sigpage + signal_return_offset +
+				  (idx << 2) + thumb;
+		} else
+#endif
+		{
 			/*
 			 * Ensure that the instruction cache sees
 			 * the return code written onto the stack.
@@ -608,3 +616,33 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 	} while (thread_flags & _TIF_WORK_MASK);
 	return 0;
 }
+
+struct page *get_signal_page(void)
+{
+	unsigned long ptr;
+	unsigned offset;
+	struct page *page;
+	void *addr;
+
+	page = alloc_pages(GFP_KERNEL, 0);
+
+	if (!page)
+		return NULL;
+
+	addr = page_address(page);
+
+	/* Give the signal return code some randomness */
+	offset = 0x200 + (get_random_int() & 0x7fc);
+	signal_return_offset = offset;
+
+	/*
+	 * Copy signal return handlers into the vector page, and
+	 * set sigreturn to be a pointer to these.
+	 */
+	memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes));
+
+	ptr = (unsigned long)addr + offset;
+	flush_icache_range(ptr, ptr + sizeof(sigreturn_codes));
+
+	return page;
+}
diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h
deleted file mode 100644
index 5ff067b7c752..000000000000
--- a/arch/arm/kernel/signal.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- *  linux/arch/arm/kernel/signal.h
- *
- *  Copyright (C) 2005-2009 Russell King.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#define KERN_SIGRETURN_CODE	(CONFIG_VECTORS_BASE + 0x00000500)
-
-extern const unsigned long sigreturn_codes[7];
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index c2b4f8f0be9a..2dc19349eb19 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -145,6 +145,16 @@ int boot_secondary(unsigned int cpu, struct task_struct *idle)
 	return -ENOSYS;
 }
 
+int platform_can_cpu_hotplug(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	if (smp_ops.cpu_kill)
+		return 1;
+#endif
+
+	return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void percpu_timer_stop(void);
 
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index a98b62dca2fa..c2edfff573c2 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -70,23 +70,6 @@ static inline void ipi_flush_bp_all(void *ignored)
 	local_flush_bp_all();
 }
 
-#ifdef CONFIG_ARM_ERRATA_798181
-static int erratum_a15_798181(void)
-{
-	unsigned int midr = read_cpuid_id();
-
-	/* Cortex-A15 r0p0..r3p2 affected */
-	if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2)
-		return 0;
-	return 1;
-}
-#else
-static int erratum_a15_798181(void)
-{
-	return 0;
-}
-#endif
-
 static void ipi_flush_tlb_a15_erratum(void *arg)
 {
 	dmb();
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index cab094c234ee..ab517fcce21b 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -35,8 +35,6 @@
 #include <asm/tls.h>
 #include <asm/system_misc.h>
 
-#include "signal.h"
-
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
 
 void *vectors_page;
@@ -800,15 +798,26 @@ void __init trap_init(void)
 	return;
 }
 
-static void __init kuser_get_tls_init(unsigned long vectors)
+#ifdef CONFIG_KUSER_HELPERS
+static void __init kuser_init(void *vectors)
 {
+	extern char __kuser_helper_start[], __kuser_helper_end[];
+	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+
+	memcpy(vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz);
+
 	/*
 	 * vectors + 0xfe0 = __kuser_get_tls
 	 * vectors + 0xfe8 = hardware TLS instruction at 0xffff0fe8
 	 */
 	if (tls_emu || has_tls_reg)
-		memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4);
+		memcpy(vectors + 0xfe0, vectors + 0xfe8, 4);
 }
+#else
+static void __init kuser_init(void *vectors)
+{
+}
+#endif
 
 void __init early_trap_init(void *vectors_base)
 {
@@ -816,33 +825,30 @@ void __init early_trap_init(void *vectors_base)
 	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
-	extern char __kuser_helper_start[], __kuser_helper_end[];
-	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+	unsigned i;
 
 	vectors_page = vectors_base;
 
 	/*
+	 * Poison the vectors page with an undefined instruction.  This
+	 * instruction is chosen to be undefined for both ARM and Thumb
+	 * ISAs.  The Thumb version is an undefined instruction with a
+	 * branch back to the undefined instruction.
+	 */
+	for (i = 0; i < PAGE_SIZE / sizeof(u32); i++)
+		((u32 *)vectors_base)[i] = 0xe7fddef1;
+
+	/*
 	 * Copy the vectors, stubs and kuser helpers (in entry-armv.S)
 	 * into the vector page, mapped at 0xffff0000, and ensure these
 	 * are visible to the instruction stream.
 	 */
 	memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start);
-	memcpy((void *)vectors + 0x200, __stubs_start, __stubs_end - __stubs_start);
-	memcpy((void *)vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz);
+	memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start);
 
-	/*
-	 * Do processor specific fixups for the kuser helpers
-	 */
-	kuser_get_tls_init(vectors);
-
-	/*
-	 * Copy signal return handlers into the vector page, and
-	 * set sigreturn to be a pointer to these.
-	 */
-	memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE),
-	       sigreturn_codes, sizeof(sigreturn_codes));
+	kuser_init(vectors_base);
 
-	flush_icache_range(vectors, vectors + PAGE_SIZE);
+	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
 	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
 #else /* ifndef CONFIG_CPU_V7M */
 	/*
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index fa25e4e425f6..7bcee5c9b604 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -148,6 +148,23 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	__init_begin = .;
 #endif
+	/*
+	 * The vectors and stubs are relocatable code, and the
+	 * only thing that matters is their relative offsets
+	 */
+	__vectors_start = .;
+	.vectors 0 : AT(__vectors_start) {
+		*(.vectors)
+	}
+	. = __vectors_start + SIZEOF(.vectors);
+	__vectors_end = .;
+
+	__stubs_start = .;
+	.stubs 0x1000 : AT(__stubs_start) {
+		*(.stubs)
+	}
+	. = __stubs_start + SIZEOF(.stubs);
+	__stubs_end = .;
 
 	INIT_TEXT_SECTION(8)
 	.exit.text : {
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 4a5199070430..db9cf692d4dd 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -146,7 +146,11 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
 #define access_pmintenclr pm_fake
 
 /* Architected CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg cp15_regs[] = {
 	/* CSSELR: swapped by interrupt.S. */
@@ -154,8 +158,8 @@ static const struct coproc_reg cp15_regs[] = {
 			NULL, reset_unknown, c0_CSSELR },
 
 	/* TTBR0/TTBR1: swapped by interrupt.S. */
-	{ CRm( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
-	{ CRm( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
+	{ CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
+	{ CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
 
 	/* TTBCR: swapped by interrupt.S. */
 	{ CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
@@ -182,7 +186,7 @@ static const struct coproc_reg cp15_regs[] = {
 			NULL, reset_unknown, c6_IFAR },
 
 	/* PAR swapped by interrupt.S */
-	{ CRn( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
+	{ CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
 
 	/*
 	 * DC{C,I,CI}SW operations:
@@ -399,12 +403,13 @@ static bool index_to_params(u64 id, struct coproc_params *params)
 			      | KVM_REG_ARM_OPC1_MASK))
 			return false;
 		params->is_64bit = true;
-		params->CRm = ((id & KVM_REG_ARM_CRM_MASK)
+		/* CRm to CRn: see cp15_to_index for details */
+		params->CRn = ((id & KVM_REG_ARM_CRM_MASK)
 			       >> KVM_REG_ARM_CRM_SHIFT);
 		params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK)
 			       >> KVM_REG_ARM_OPC1_SHIFT);
 		params->Op2 = 0;
-		params->CRn = 0;
+		params->CRm = 0;
 		return true;
 	default:
 		return false;
@@ -898,7 +903,14 @@ static u64 cp15_to_index(const struct coproc_reg *reg)
 	if (reg->is_64) {
 		val |= KVM_REG_SIZE_U64;
 		val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
-		val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT);
+		/*
+		 * CRn always denotes the primary coproc. reg. nr. for the
+		 * in-kernel representation, but the user space API uses the
+		 * CRm for the encoding, because it is modelled after the
+		 * MRRC/MCRR instructions: see the ARM ARM rev. c page
+		 * B3-1445
+		 */
+		val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT);
 	} else {
 		val |= KVM_REG_SIZE_U32;
 		val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index b7301d3e4799..0461d5c8d3de 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -135,6 +135,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 		return -1;
 	if (i1->CRn != i2->CRn)
 		return i1->CRn - i2->CRn;
+	if (i1->is_64 != i2->is_64)
+		return i2->is_64 - i1->is_64;
 	if (i1->CRm != i2->CRm)
 		return i1->CRm - i2->CRm;
 	if (i1->Op1 != i2->Op1)
@@ -145,6 +147,7 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 
 #define CRn(_x)		.CRn = _x
 #define CRm(_x) 	.CRm = _x
+#define CRm64(_x)       .CRn = _x, .CRm = 0
 #define Op1(_x) 	.Op1 = _x
 #define Op2(_x) 	.Op2 = _x
 #define is64		.is_64 = true
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index 685063a6d0cf..cf93472b9dd6 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -114,7 +114,11 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu,
 
 /*
  * A15-specific CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg a15_regs[] = {
 	/* MPIDR: we use VMPIDR for guest access. */
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index b8e06b7a2833..0c25d9487d53 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -63,7 +63,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		      struct kvm_exit_mmio *mmio)
 {
-	unsigned long rt, len;
+	unsigned long rt;
+	int len;
 	bool is_write, sign_extend;
 
 	if (kvm_vcpu_dabt_isextabt(vcpu)) {
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index ca6bea4859b4..0988d9e04dd4 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -85,6 +85,12 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
+static bool page_empty(void *ptr)
+{
+	struct page *ptr_page = virt_to_page(ptr);
+	return page_count(ptr_page) == 1;
+}
+
 static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
 	pmd_t *pmd_table = pmd_offset(pud, 0);
@@ -103,12 +109,6 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 	put_page(virt_to_page(pmd));
 }
 
-static bool pmd_empty(pmd_t *pmd)
-{
-	struct page *pmd_page = virt_to_page(pmd);
-	return page_count(pmd_page) == 1;
-}
-
 static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
 {
 	if (pte_present(*pte)) {
@@ -118,12 +118,6 @@ static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
 	}
 }
 
-static bool pte_empty(pte_t *pte)
-{
-	struct page *pte_page = virt_to_page(pte);
-	return page_count(pte_page) == 1;
-}
-
 static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 			unsigned long long start, u64 size)
 {
@@ -132,37 +126,37 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 	pmd_t *pmd;
 	pte_t *pte;
 	unsigned long long addr = start, end = start + size;
-	u64 range;
+	u64 next;
 
 	while (addr < end) {
 		pgd = pgdp + pgd_index(addr);
 		pud = pud_offset(pgd, addr);
 		if (pud_none(*pud)) {
-			addr += PUD_SIZE;
+			addr = pud_addr_end(addr, end);
 			continue;
 		}
 
 		pmd = pmd_offset(pud, addr);
 		if (pmd_none(*pmd)) {
-			addr += PMD_SIZE;
+			addr = pmd_addr_end(addr, end);
 			continue;
 		}
 
 		pte = pte_offset_kernel(pmd, addr);
 		clear_pte_entry(kvm, pte, addr);
-		range = PAGE_SIZE;
+		next = addr + PAGE_SIZE;
 
 		/* If we emptied the pte, walk back up the ladder */
-		if (pte_empty(pte)) {
+		if (page_empty(pte)) {
 			clear_pmd_entry(kvm, pmd, addr);
-			range = PMD_SIZE;
-			if (pmd_empty(pmd)) {
+			next = pmd_addr_end(addr, end);
+			if (page_empty(pmd) && !page_empty(pud)) {
 				clear_pud_entry(kvm, pud, addr);
-				range = PUD_SIZE;
+				next = pud_addr_end(addr, end);
 			}
 		}
 
-		addr += range;
+		addr = next;
 	}
 }
 
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index 2abee6626aac..916e5a142917 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -227,6 +227,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("usart", "f8020000.serial", &usart1_clk),
 	CLKDEV_CON_DEV_ID("usart", "f8024000.serial", &usart2_clk),
 	CLKDEV_CON_DEV_ID("usart", "f8028000.serial", &usart3_clk),
+	CLKDEV_CON_DEV_ID("usart", "f8040000.serial", &uart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "f8044000.serial", &uart1_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "f8008000.timer", &tcb0_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "f800c000.timer", &tcb0_clk),
 	CLKDEV_CON_DEV_ID("mci_clk", "f0008000.mmc", &mmc0_clk),
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index dff4ddc5ef81..139e42da25f0 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -75,6 +75,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
 	.ecc_mode		= NAND_ECC_HW_SYNDROME,
+	.ecc_bits		= 4,
 	.bbt_options		= NAND_BBT_USE_FLASH,
 };
 
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index afbc439f11d4..4cdb61c54459 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -505,7 +505,7 @@ static struct vpbe_output dm365evm_vpbe_outputs[] = {
 /*
  * Amplifiers on the board
  */
-struct ths7303_platform_data ths7303_pdata = {
+static struct ths7303_platform_data ths7303_pdata = {
 	.ch_1 = 3,
 	.ch_2 = 3,
 	.ch_3 = 3,
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index a33686a6fbb2..fa4bfaf952d8 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -153,6 +153,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = {
 	.parts		= davinci_evm_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(davinci_evm_nandflash_partition),
 	.ecc_mode	= NAND_ECC_HW,
+	.ecc_bits	= 1,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.timing		= &davinci_evm_nandflash_timing,
 };
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index fbb8e5ab1dc1..0c005e876cac 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -90,6 +90,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
 	.ecc_mode		= NAND_ECC_HW,
+	.ecc_bits		= 1,
 	.options		= 0,
 };
 
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 2bc112adf565..808233b60e3d 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -88,6 +88,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = {
 	.parts		= davinci_ntosd2_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(davinci_ntosd2_nandflash_partition),
 	.ecc_mode	= NAND_ECC_HW,
+	.ecc_bits	= 1,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 };
 
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 42ef53f62c6c..86100d179694 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -860,7 +860,7 @@ static struct platform_device dm355_vpbe_display = {
 	},
 };
 
-struct venc_platform_data dm355_venc_pdata = {
+static struct venc_platform_data dm355_venc_pdata = {
 	.setup_pinmux	= dm355_vpbe_setup_pinmux,
 	.setup_clock	= dm355_venc_setup_clock,
 };
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index fa7af5eda52d..dad28029ba9b 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -1349,7 +1349,7 @@ static struct platform_device dm365_vpbe_display = {
 	},
 };
 
-struct venc_platform_data dm365_venc_pdata = {
+static struct venc_platform_data dm365_venc_pdata = {
 	.setup_pinmux	= dm365_vpbe_setup_pinmux,
 	.setup_clock	= dm365_venc_setup_clock,
 };
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 855d4a7b462d..5952e68c76c4 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -92,6 +92,7 @@ config SOC_EXYNOS5440
 	bool "SAMSUNG EXYNOS5440"
 	default y
 	depends on ARCH_EXYNOS5
+	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select ARCH_HAS_OPP
 	select HAVE_ARM_ARCH_TIMER
 	select AUTO_ZRELADDR
diff --git a/arch/arm/mach-exynos/Makefile b/arch/arm/mach-exynos/Makefile
index e970a7a4e278..53696154aead 100644
--- a/arch/arm/mach-exynos/Makefile
+++ b/arch/arm/mach-exynos/Makefile
@@ -14,7 +14,7 @@ obj-				:=
 
 obj-$(CONFIG_ARCH_EXYNOS)	+= common.o
 
-obj-$(CONFIG_PM)		+= pm.o
+obj-$(CONFIG_S5P_PM)		+= pm.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS) += pm_domains.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 
diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c
index 164685bd25c8..ba95e5db2501 100644
--- a/arch/arm/mach-exynos/common.c
+++ b/arch/arm/mach-exynos/common.c
@@ -58,7 +58,6 @@ static const char name_exynos5440[] = "EXYNOS5440";
 
 static void exynos4_map_io(void);
 static void exynos5_map_io(void);
-static void exynos5440_map_io(void);
 static int exynos_init(void);
 
 static struct cpu_table cpu_ids[] __initdata = {
@@ -95,7 +94,6 @@ static struct cpu_table cpu_ids[] __initdata = {
 	}, {
 		.idcode		= EXYNOS5440_SOC_ID,
 		.idmask		= EXYNOS5_SOC_MASK,
-		.map_io		= exynos5440_map_io,
 		.init		= exynos_init,
 		.name		= name_exynos5440,
 	},
@@ -150,11 +148,6 @@ static struct map_desc exynos4_iodesc[] __initdata = {
 		.length		= SZ_64K,
 		.type		= MT_DEVICE,
 	}, {
-		.virtual	= (unsigned long)S3C_VA_UART,
-		.pfn		= __phys_to_pfn(EXYNOS4_PA_UART),
-		.length		= SZ_512K,
-		.type		= MT_DEVICE,
-	}, {
 		.virtual	= (unsigned long)S5P_VA_CMU,
 		.pfn		= __phys_to_pfn(EXYNOS4_PA_CMU),
 		.length		= SZ_128K,
@@ -268,20 +261,6 @@ static struct map_desc exynos5_iodesc[] __initdata = {
 		.pfn		= __phys_to_pfn(EXYNOS5_PA_PMU),
 		.length		= SZ_64K,
 		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)S3C_VA_UART,
-		.pfn		= __phys_to_pfn(EXYNOS5_PA_UART),
-		.length		= SZ_512K,
-		.type		= MT_DEVICE,
-	},
-};
-
-static struct map_desc exynos5440_iodesc0[] __initdata = {
-	{
-		.virtual	= (unsigned long)S3C_VA_UART,
-		.pfn		= __phys_to_pfn(EXYNOS5440_PA_UART0),
-		.length		= SZ_512K,
-		.type		= MT_DEVICE,
 	},
 };
 
@@ -388,11 +367,6 @@ static void __init exynos5_map_io(void)
 		iotable_init(exynos5250_iodesc, ARRAY_SIZE(exynos5250_iodesc));
 }
 
-static void __init exynos5440_map_io(void)
-{
-	iotable_init(exynos5440_iodesc0, ARRAY_SIZE(exynos5440_iodesc0));
-}
-
 void __init exynos_init_time(void)
 {
 	of_clk_init(NULL);
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 3e156bcddcb4..972490fc09d6 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -97,6 +97,5 @@ struct exynos_pmu_conf {
 };
 
 extern void exynos_sys_powerdown_conf(enum sys_powerdown mode);
-extern void s3c_cpu_resume(void);
 
 #endif /* __ARCH_ARM_MACH_EXYNOS_COMMON_H */
diff --git a/arch/arm/mach-exynos/cpuidle.c b/arch/arm/mach-exynos/cpuidle.c
index 17a18ff3d71e..225ee8431c72 100644
--- a/arch/arm/mach-exynos/cpuidle.c
+++ b/arch/arm/mach-exynos/cpuidle.c
@@ -25,6 +25,7 @@
 #include <mach/regs-pmu.h>
 
 #include <plat/cpu.h>
+#include <plat/pm.h>
 
 #include "common.h"
 
diff --git a/arch/arm/mach-exynos/include/mach/memory.h b/arch/arm/mach-exynos/include/mach/memory.h
index 374ef2cf7152..2a4cdb7cb326 100644
--- a/arch/arm/mach-exynos/include/mach/memory.h
+++ b/arch/arm/mach-exynos/include/mach/memory.h
@@ -15,8 +15,13 @@
 
 #define PLAT_PHYS_OFFSET		UL(0x40000000)
 
+#ifndef CONFIG_ARM_LPAE
 /* Maximum of 256MiB in one bank */
 #define MAX_PHYSMEM_BITS	32
 #define SECTION_SIZE_BITS	28
+#else
+#define MAX_PHYSMEM_BITS	36
+#define SECTION_SIZE_BITS	31
+#endif
 
 #endif /* __ASM_ARCH_MEMORY_H */
diff --git a/arch/arm/mach-exynos/pm.c b/arch/arm/mach-exynos/pm.c
index 41c20692a13f..c679db577269 100644
--- a/arch/arm/mach-exynos/pm.c
+++ b/arch/arm/mach-exynos/pm.c
@@ -217,6 +217,9 @@ static __init int exynos_pm_drvinit(void)
 	struct clk *pll_base;
 	unsigned int tmp;
 
+	if (soc_is_exynos5440())
+		return 0;
+
 	s3c_pm_init();
 
 	/* All wakeup disable */
@@ -340,6 +343,9 @@ static struct syscore_ops exynos_pm_syscore_ops = {
 
 static __init int exynos_pm_syscore_init(void)
 {
+	if (soc_is_exynos5440())
+		return 0;
+
 	register_syscore_ops(&exynos_pm_syscore_ops);
 	return 0;
 }
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index a7cd2cf5e08d..3490a24f969e 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -276,8 +276,6 @@ int __init dc21285_setup(int nr, struct pci_sys_data *sys)
 
 	sys->mem_offset  = DC21285_PCI_MEM;
 
-	pci_ioremap_io(0, DC21285_PCI_IO);
-
 	pci_add_resource_offset(&sys->resources, &res[0], sys->mem_offset);
 	pci_add_resource_offset(&sys->resources, &res[1], sys->mem_offset);
 
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index dc5d6becd8c7..88815795fe26 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -115,6 +115,7 @@ static int highbank_platform_notifier(struct notifier_block *nb,
 {
 	struct resource *res;
 	int reg = -1;
+	u32 val;
 	struct device *dev = __dev;
 
 	if (event != BUS_NOTIFY_ADD_DEVICE)
@@ -141,10 +142,10 @@ static int highbank_platform_notifier(struct notifier_block *nb,
 		return NOTIFY_DONE;
 
 	if (of_property_read_bool(dev->of_node, "dma-coherent")) {
-		writel(0xff31, sregs_base + reg);
+		val = readl(sregs_base + reg);
+		writel(val | 0xff01, sregs_base + reg);
 		set_dma_ops(dev, &arm_coherent_dma_ops);
-	} else
-		writel(0, sregs_base + reg);
+	}
 
 	return NOTIFY_OK;
 }
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 4282e99f5ca1..86567d980b07 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -199,7 +199,8 @@ static const char *pcie_axi_sels[]	= { "axi", "ahb", };
 static const char *ssi_sels[]		= { "pll3_pfd2_508m", "pll3_pfd3_454m", "pll4_post_div", };
 static const char *usdhc_sels[]	= { "pll2_pfd2_396m", "pll2_pfd0_352m", };
 static const char *enfc_sels[]	= { "pll2_pfd0_352m", "pll2_bus", "pll3_usb_otg", "pll2_pfd2_396m", };
-static const char *emi_sels[]		= { "axi", "pll3_usb_otg", "pll2_pfd2_396m", "pll2_pfd0_352m", };
+static const char *emi_sels[]		= { "pll2_pfd2_396m", "pll3_usb_otg", "axi", "pll2_pfd0_352m", };
+static const char *emi_slow_sels[]      = { "axi", "pll3_usb_otg", "pll2_pfd2_396m", "pll2_pfd0_352m", };
 static const char *vdo_axi_sels[]	= { "axi", "ahb", };
 static const char *vpu_axi_sels[]	= { "axi", "pll2_pfd2_396m", "pll2_pfd0_352m", };
 static const char *cko1_sels[]	= { "pll3_usb_otg", "pll2_bus", "pll1_sys", "pll5_video_div",
@@ -392,7 +393,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[usdhc4_sel]       = imx_clk_mux("usdhc4_sel",       base + 0x1c, 19, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
 	clk[enfc_sel]         = imx_clk_mux("enfc_sel",         base + 0x2c, 16, 2, enfc_sels,         ARRAY_SIZE(enfc_sels));
 	clk[emi_sel]          = imx_clk_mux("emi_sel",          base + 0x1c, 27, 2, emi_sels,          ARRAY_SIZE(emi_sels));
-	clk[emi_slow_sel]     = imx_clk_mux("emi_slow_sel",     base + 0x1c, 29, 2, emi_sels,          ARRAY_SIZE(emi_sels));
+	clk[emi_slow_sel]     = imx_clk_mux("emi_slow_sel",     base + 0x1c, 29, 2, emi_slow_sels,     ARRAY_SIZE(emi_slow_sels));
 	clk[vdo_axi_sel]      = imx_clk_mux("vdo_axi_sel",      base + 0x18, 11, 1, vdo_axi_sels,      ARRAY_SIZE(vdo_axi_sels));
 	clk[vpu_axi_sel]      = imx_clk_mux("vpu_axi_sel",      base + 0x18, 14, 2, vpu_axi_sels,      ARRAY_SIZE(vpu_axi_sels));
 	clk[cko1_sel]         = imx_clk_mux("cko1_sel",         base + 0x60, 0,  4, cko1_sels,         ARRAY_SIZE(cko1_sels));
diff --git a/arch/arm/mach-imx/clk-vf610.c b/arch/arm/mach-imx/clk-vf610.c
index d617c0b7c809..b169a396d93b 100644
--- a/arch/arm/mach-imx/clk-vf610.c
+++ b/arch/arm/mach-imx/clk-vf610.c
@@ -183,6 +183,8 @@ static void __init vf610_clocks_init(struct device_node *ccm_node)
 	clk[VF610_CLK_ENET_TS_SEL] = imx_clk_mux("enet_ts_sel", CCM_CSCMR2, 0, 3, enet_ts_sels, 7);
 	clk[VF610_CLK_ENET] = imx_clk_gate("enet", "enet_sel", CCM_CSCDR1, 24);
 	clk[VF610_CLK_ENET_TS] = imx_clk_gate("enet_ts", "enet_ts_sel", CCM_CSCDR1, 23);
+	clk[VF610_CLK_ENET0] = imx_clk_gate2("enet0", "ipg_bus", CCM_CCGR9, CCM_CCGRx_CGn(0));
+	clk[VF610_CLK_ENET1] = imx_clk_gate2("enet1", "ipg_bus", CCM_CCGR9, CCM_CCGRx_CGn(1));
 
 	clk[VF610_CLK_PIT] = imx_clk_gate2("pit", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(7));
 
diff --git a/arch/arm/mach-imx/mx27.h b/arch/arm/mach-imx/mx27.h
index e074616d54ca..8a65f192e7f3 100644
--- a/arch/arm/mach-imx/mx27.h
+++ b/arch/arm/mach-imx/mx27.h
@@ -135,7 +135,7 @@
 #define MX27_INT_GPT4		(NR_IRQS_LEGACY + 4)
 #define MX27_INT_RTIC		(NR_IRQS_LEGACY + 5)
 #define MX27_INT_CSPI3		(NR_IRQS_LEGACY + 6)
-#define MX27_INT_SDHC		(NR_IRQS_LEGACY + 7)
+#define MX27_INT_MSHC		(NR_IRQS_LEGACY + 7)
 #define MX27_INT_GPIO		(NR_IRQS_LEGACY + 8)
 #define MX27_INT_SDHC3		(NR_IRQS_LEGACY + 9)
 #define MX27_INT_SDHC2		(NR_IRQS_LEGACY + 10)
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index fe4d9ff93a7e..b661c5c2870a 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -49,7 +49,7 @@ static const char *keystone_match[] __initconst = {
 	NULL,
 };
 
-void keystone_restart(char mode, const char *cmd)
+void keystone_restart(enum reboot_mode mode, const char *cmd)
 {
 	u32 val;
 
diff --git a/arch/arm/mach-msm/Kconfig b/arch/arm/mach-msm/Kconfig
index 614e41e7881b..905efc8cac79 100644
--- a/arch/arm/mach-msm/Kconfig
+++ b/arch/arm/mach-msm/Kconfig
@@ -121,8 +121,7 @@ config MSM_SMD
 	bool
 
 config MSM_GPIOMUX
-	depends on !(ARCH_MSM8X60 || ARCH_MSM8960)
-	bool "MSM V1 TLMM GPIOMUX architecture"
+	bool
 	help
 	  Support for MSM V1 TLMM GPIOMUX architecture.
 
diff --git a/arch/arm/mach-msm/gpiomux-v1.c b/arch/arm/mach-msm/gpiomux-v1.c
deleted file mode 100644
index 27de2abd7144..000000000000
--- a/arch/arm/mach-msm/gpiomux-v1.c
+++ /dev/null
@@ -1,33 +0,0 @@
-/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
- */
-#include <linux/kernel.h>
-#include "gpiomux.h"
-#include "proc_comm.h"
-
-void __msm_gpiomux_write(unsigned gpio, gpiomux_config_t val)
-{
-	unsigned tlmm_config  = (val & ~GPIOMUX_CTL_MASK) |
-				((gpio & 0x3ff) << 4);
-	unsigned tlmm_disable = 0;
-	int rc;
-
-	rc = msm_proc_comm(PCOM_RPC_GPIO_TLMM_CONFIG_EX,
-			   &tlmm_config, &tlmm_disable);
-	if (rc)
-		pr_err("%s: unexpected proc_comm failure %d: %08x %08x\n",
-		       __func__, rc, tlmm_config, tlmm_disable);
-}
diff --git a/arch/arm/mach-msm/gpiomux.h b/arch/arm/mach-msm/gpiomux.h
index 8e82f41a8923..4410d7766f93 100644
--- a/arch/arm/mach-msm/gpiomux.h
+++ b/arch/arm/mach-msm/gpiomux.h
@@ -73,16 +73,6 @@ extern struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS];
 int msm_gpiomux_write(unsigned gpio,
 		      gpiomux_config_t active,
 		      gpiomux_config_t suspended);
-
-/* Architecture-internal function for use by the framework only.
- * This function can assume the following:
- * - the gpio value has passed a bounds-check
- * - the gpiomux spinlock has been obtained
- *
- * This function is not for public consumption.  External users
- * should use msm_gpiomux_write.
- */
-void __msm_gpiomux_write(unsigned gpio, gpiomux_config_t val);
 #else
 static inline int msm_gpiomux_write(unsigned gpio,
 				    gpiomux_config_t active,
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 627fa7e41fba..3eed0006d189 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -62,7 +62,7 @@ config SOC_OMAP5
 	select HAVE_SMP
 	select COMMON_CLK
 	select HAVE_ARM_ARCH_TIMER
-	select ARM_ERRATA_798181
+	select ARM_ERRATA_798181 if SMP
 
 config SOC_AM33XX
 	bool "AM33XX support"
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index e5fbfed69aa2..be5d005ebad2 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -15,6 +15,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/irqdomain.h>
+#include <linux/clk.h>
 
 #include <asm/mach/arch.h>
 
@@ -35,6 +36,21 @@ static struct of_device_id omap_dt_match_table[] __initdata = {
 	{ }
 };
 
+/*
+ * Create alias for USB host PHY clock.
+ * Remove this when clock phandle can be provided via DT
+ */
+static void __init legacy_init_ehci_clk(char *clkname)
+{
+	int ret;
+
+	ret = clk_add_alias("main_clk", NULL, clkname, NULL);
+	if (ret) {
+		pr_err("%s:Failed to add main_clk alias to %s :%d\n",
+						__func__, clkname, ret);
+	}
+}
+
 static void __init omap_generic_init(void)
 {
 	omap_sdrc_init(NULL, NULL);
@@ -45,10 +61,15 @@ static void __init omap_generic_init(void)
 	 * HACK: call display setup code for selected boards to enable omapdss.
 	 * This will be removed when omapdss supports DT.
 	 */
-	if (of_machine_is_compatible("ti,omap4-panda"))
+	if (of_machine_is_compatible("ti,omap4-panda")) {
 		omap4_panda_display_init_of();
+		legacy_init_ehci_clk("auxclk3_ck");
+
+	}
 	else if (of_machine_is_compatible("ti,omap4-sdp"))
 		omap_4430sdp_display_init_of();
+	else if (of_machine_is_compatible("ti,omap5-uevm"))
+		legacy_init_ehci_clk("auxclk1_ck");
 }
 
 #ifdef CONFIG_SOC_OMAP2420
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index f6eeb87e4e95..827d15009a86 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -122,11 +122,7 @@ static struct musb_hdrc_config musb_config = {
 };
 
 static struct musb_hdrc_platform_data tusb_data = {
-#ifdef CONFIG_USB_GADGET_MUSB_HDRC
 	.mode		= MUSB_OTG,
-#else
-	.mode		= MUSB_HOST,
-#endif
 	.set_power	= tusb_set_power,
 	.min_power	= 25,	/* x2 = 50 mA drawn from VBUS as peripheral */
 	.power		= 100,	/* Max 100 mA VBUS for host mode */
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index d2ea68ea678a..7735105561d8 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -85,7 +85,7 @@ static struct omap_board_mux board_mux[] __initdata = {
 
 static struct omap_musb_board_data musb_board_data = {
 	.interface_type		= MUSB_INTERFACE_ULPI,
-	.mode			= MUSB_PERIPHERAL,
+	.mode			= MUSB_OTG,
 	.power			= 0,
 };
 
diff --git a/arch/arm/mach-omap2/dss-common.c b/arch/arm/mach-omap2/dss-common.c
index 393aeefaebb0..043e5705f2a6 100644
--- a/arch/arm/mach-omap2/dss-common.c
+++ b/arch/arm/mach-omap2/dss-common.c
@@ -42,7 +42,7 @@
 
 /* Using generic display panel */
 static struct tfp410_platform_data omap4_dvi_panel = {
-	.i2c_bus_num		= 3,
+	.i2c_bus_num		= 2,
 	.power_down_gpio	= PANDA_DVI_TFP410_POWER_DOWN_GPIO,
 };
 
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 5cc92874be7e..f99f68e1e85b 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -129,6 +129,7 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
 	struct device_node *node = pdev->dev.of_node;
 	const char *oh_name;
 	int oh_cnt, i, ret = 0;
+	bool device_active = false;
 
 	oh_cnt = of_property_count_strings(node, "ti,hwmods");
 	if (oh_cnt <= 0) {
@@ -152,6 +153,8 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
 			goto odbfd_exit1;
 		}
 		hwmods[i] = oh;
+		if (oh->flags & HWMOD_INIT_NO_IDLE)
+			device_active = true;
 	}
 
 	od = omap_device_alloc(pdev, hwmods, oh_cnt);
@@ -172,6 +175,11 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
 
 	pdev->dev.pm_domain = &omap_device_pm_domain;
 
+	if (device_active) {
+		omap_device_enable(pdev);
+		pm_runtime_set_active(&pdev->dev);
+	}
+
 odbfd_exit1:
 	kfree(hwmods);
 odbfd_exit:
@@ -842,6 +850,7 @@ static int __init omap_device_late_idle(struct device *dev, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct omap_device *od = to_omap_device(pdev);
+	int i;
 
 	if (!od)
 		return 0;
@@ -850,6 +859,15 @@ static int __init omap_device_late_idle(struct device *dev, void *data)
 	 * If omap_device state is enabled, but has no driver bound,
 	 * idle it.
 	 */
+
+	/*
+	 * Some devices (like memory controllers) are always kept
+	 * enabled, and should not be idled even with no drivers.
+	 */
+	for (i = 0; i < od->hwmods_cnt; i++)
+		if (od->hwmods[i]->flags & HWMOD_INIT_NO_IDLE)
+			return 0;
+
 	if (od->_driver_status != BUS_NOTIFY_BOUND_DRIVER) {
 		if (od->_state == OMAP_DEVICE_STATE_ENABLED) {
 			dev_warn(dev, "%s: enabled but no driver.  Idling\n",
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 7341eff63f56..7f4db12b1459 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2386,7 +2386,7 @@ static void __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data)
 
 		np = of_dev_hwmod_lookup(of_find_node_by_name(NULL, "ocp"), oh);
 		if (np)
-			va_start = of_iomap(np, 0);
+			va_start = of_iomap(np, oh->mpu_rt_idx);
 	} else {
 		va_start = ioremap(mem->pa_start, mem->pa_end - mem->pa_start);
 	}
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index aab33fd814c0..e1482a9b3bc2 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -95,6 +95,54 @@ extern struct omap_hwmod_sysc_fields omap_hwmod_sysc_type3;
 #define MODULEMODE_HWCTRL		1
 #define MODULEMODE_SWCTRL		2
 
+#define DEBUG_OMAP2UART1_FLAGS	0
+#define DEBUG_OMAP2UART2_FLAGS	0
+#define DEBUG_OMAP2UART3_FLAGS	0
+#define DEBUG_OMAP3UART3_FLAGS	0
+#define DEBUG_OMAP3UART4_FLAGS	0
+#define DEBUG_OMAP4UART3_FLAGS	0
+#define DEBUG_OMAP4UART4_FLAGS	0
+#define DEBUG_TI81XXUART1_FLAGS	0
+#define DEBUG_TI81XXUART2_FLAGS	0
+#define DEBUG_TI81XXUART3_FLAGS	0
+#define DEBUG_AM33XXUART1_FLAGS	0
+
+#define DEBUG_OMAPUART_FLAGS	(HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET)
+
+#if defined(CONFIG_DEBUG_OMAP2UART1)
+#undef DEBUG_OMAP2UART1_FLAGS
+#define DEBUG_OMAP2UART1_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP2UART2)
+#undef DEBUG_OMAP2UART2_FLAGS
+#define DEBUG_OMAP2UART2_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP2UART3)
+#undef DEBUG_OMAP2UART3_FLAGS
+#define DEBUG_OMAP2UART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP3UART3)
+#undef DEBUG_OMAP3UART3_FLAGS
+#define DEBUG_OMAP3UART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP3UART4)
+#undef DEBUG_OMAP3UART4_FLAGS
+#define DEBUG_OMAP3UART4_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP4UART3)
+#undef DEBUG_OMAP4UART3_FLAGS
+#define DEBUG_OMAP4UART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP4UART4)
+#undef DEBUG_OMAP4UART4_FLAGS
+#define DEBUG_OMAP4UART4_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_TI81XXUART1)
+#undef DEBUG_TI81XXUART1_FLAGS
+#define DEBUG_TI81XXUART1_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_TI81XXUART2)
+#undef DEBUG_TI81XXUART2_FLAGS
+#define DEBUG_TI81XXUART2_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_TI81XXUART3)
+#undef DEBUG_TI81XXUART3_FLAGS
+#define DEBUG_TI81XXUART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_AM33XXUART1)
+#undef DEBUG_AM33XXUART1_FLAGS
+#define DEBUG_AM33XXUART1_FLAGS DEBUG_OMAPUART_FLAGS
+#endif
 
 /**
  * struct omap_hwmod_mux_info - hwmod specific mux configuration
@@ -568,6 +616,7 @@ struct omap_hwmod_link {
  * @voltdm: pointer to voltage domain (filled in at runtime)
  * @dev_attr: arbitrary device attributes that can be passed to the driver
  * @_sysc_cache: internal-use hwmod flags
+ * @mpu_rt_idx: index of device address space for register target (for DT boot)
  * @_mpu_rt_va: cached register target start address (internal use)
  * @_mpu_port: cached MPU register target slave (internal use)
  * @opt_clks_cnt: number of @opt_clks
@@ -617,6 +666,7 @@ struct omap_hwmod {
 	struct list_head		node;
 	struct omap_hwmod_ocp_if	*_mpu_port;
 	u16				flags;
+	u8				mpu_rt_idx;
 	u8				response_lat;
 	u8				rst_lines_cnt;
 	u8				opt_clks_cnt;
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index d05fc7b54567..56cebb05509e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -512,7 +512,7 @@ struct omap_hwmod omap2xxx_uart1_hwmod = {
 	.mpu_irqs	= omap2_uart1_mpu_irqs,
 	.sdma_reqs	= omap2_uart1_sdma_reqs,
 	.main_clk	= "uart1_fck",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_OMAP2UART1_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -532,7 +532,7 @@ struct omap_hwmod omap2xxx_uart2_hwmod = {
 	.mpu_irqs	= omap2_uart2_mpu_irqs,
 	.sdma_reqs	= omap2_uart2_sdma_reqs,
 	.main_clk	= "uart2_fck",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_OMAP2UART2_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -552,7 +552,7 @@ struct omap_hwmod omap2xxx_uart3_hwmod = {
 	.mpu_irqs	= omap2_uart3_mpu_irqs,
 	.sdma_reqs	= omap2_uart3_sdma_reqs,
 	.main_clk	= "uart3_fck",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_OMAP2UART3_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index 28bbd56346a9..eb2f3b93b51c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -562,6 +562,7 @@ static struct omap_hwmod am33xx_cpgmac0_hwmod = {
 	.clkdm_name	= "cpsw_125mhz_clkdm",
 	.flags		= (HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY),
 	.main_clk	= "cpsw_125mhz_gclk",
+	.mpu_rt_idx	= 1,
 	.prcm		= {
 		.omap4	= {
 			.clkctrl_offs	= AM33XX_CM_PER_CPGMAC0_CLKCTRL_OFFSET,
@@ -1512,7 +1513,7 @@ static struct omap_hwmod am33xx_uart1_hwmod = {
 	.name		= "uart1",
 	.class		= &uart_class,
 	.clkdm_name	= "l4_wkup_clkdm",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_AM33XXUART1_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.main_clk	= "dpll_per_m2_div4_wkupdm_ck",
 	.prcm		= {
 		.omap4	= {
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index f7a3df2fb579..0c3a427da544 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -490,7 +490,7 @@ static struct omap_hwmod omap3xxx_uart1_hwmod = {
 	.mpu_irqs	= omap2_uart1_mpu_irqs,
 	.sdma_reqs	= omap2_uart1_sdma_reqs,
 	.main_clk	= "uart1_fck",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_TI81XXUART1_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -509,7 +509,7 @@ static struct omap_hwmod omap3xxx_uart2_hwmod = {
 	.mpu_irqs	= omap2_uart2_mpu_irqs,
 	.sdma_reqs	= omap2_uart2_sdma_reqs,
 	.main_clk	= "uart2_fck",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_TI81XXUART2_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -528,7 +528,8 @@ static struct omap_hwmod omap3xxx_uart3_hwmod = {
 	.mpu_irqs	= omap2_uart3_mpu_irqs,
 	.sdma_reqs	= omap2_uart3_sdma_reqs,
 	.main_clk	= "uart3_fck",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_OMAP3UART3_FLAGS | DEBUG_TI81XXUART3_FLAGS |
+				HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = OMAP3430_PER_MOD,
@@ -558,7 +559,7 @@ static struct omap_hwmod omap36xx_uart4_hwmod = {
 	.mpu_irqs	= uart4_mpu_irqs,
 	.sdma_reqs	= uart4_sdma_reqs,
 	.main_clk	= "uart4_fck",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_OMAP3UART4_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = OMAP3430_PER_MOD,
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index d04b5e60fdbe..9c3b504477d7 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2858,8 +2858,7 @@ static struct omap_hwmod omap44xx_uart3_hwmod = {
 	.name		= "uart3",
 	.class		= &omap44xx_uart_hwmod_class,
 	.clkdm_name	= "l4_per_clkdm",
-	.flags		= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET |
-				HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_OMAP4UART3_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.main_clk	= "func_48m_fclk",
 	.prcm = {
 		.omap4 = {
@@ -2875,7 +2874,7 @@ static struct omap_hwmod omap44xx_uart4_hwmod = {
 	.name		= "uart4",
 	.class		= &omap44xx_uart_hwmod_class,
 	.clkdm_name	= "l4_per_clkdm",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= DEBUG_OMAP4UART4_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
 	.main_clk	= "func_48m_fclk",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index f37ae96b70a1..3c70f5c1860f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -1375,7 +1375,7 @@ static struct omap_hwmod omap54xx_uart3_hwmod = {
 	.name		= "uart3",
 	.class		= &omap54xx_uart_hwmod_class,
 	.clkdm_name	= "l4per_clkdm",
-	.flags		= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET,
+	.flags		= DEBUG_OMAP4UART3_FLAGS,
 	.main_clk	= "func_48m_fclk",
 	.prcm = {
 		.omap4 = {
@@ -1391,6 +1391,7 @@ static struct omap_hwmod omap54xx_uart4_hwmod = {
 	.name		= "uart4",
 	.class		= &omap54xx_uart_hwmod_class,
 	.clkdm_name	= "l4per_clkdm",
+	.flags		= DEBUG_OMAP4UART4_FLAGS,
 	.main_clk	= "func_48m_fclk",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c
index 3a674de6cb63..a388f8c1bcb3 100644
--- a/arch/arm/mach-omap2/serial.c
+++ b/arch/arm/mach-omap2/serial.c
@@ -208,17 +208,6 @@ static int __init omap_serial_early_init(void)
 				pr_info("%s used as console in debug mode: uart%d clocks will not be gated",
 					uart_name, uart->num);
 			}
-
-			/*
-			 * omap-uart can be used for earlyprintk logs
-			 * So if omap-uart is used as console then prevent
-			 * uart reset and idle to get logs from omap-uart
-			 * until uart console driver is available to take
-			 * care for console messages.
-			 * Idling or resetting omap-uart while printing logs
-			 * early boot logs can stall the boot-up.
-			 */
-			oh->flags |= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET;
 		}
 	} while (1);
 
diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c
index 8c4de2708cf2..bc897231bd10 100644
--- a/arch/arm/mach-omap2/usb-musb.c
+++ b/arch/arm/mach-omap2/usb-musb.c
@@ -38,11 +38,8 @@ static struct musb_hdrc_config musb_config = {
 };
 
 static struct musb_hdrc_platform_data musb_plat = {
-#ifdef CONFIG_USB_GADGET_MUSB_HDRC
 	.mode		= MUSB_OTG,
-#else
-	.mode		= MUSB_HOST,
-#endif
+
 	/* .clock is set dynamically */
 	.config		= &musb_config,
 
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index f6726bb4eb95..3a3362fa793e 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -477,16 +477,24 @@ static int em_x270_usb_hub_init(void)
 	/* USB Hub power-on and reset */
 	gpio_direction_output(usb_hub_reset, 1);
 	gpio_direction_output(GPIO9_USB_VBUS_EN, 0);
-	regulator_enable(em_x270_usb_ldo);
+	err = regulator_enable(em_x270_usb_ldo);
+	if (err)
+		goto err_free_rst_gpio;
+
 	gpio_set_value(usb_hub_reset, 0);
 	gpio_set_value(usb_hub_reset, 1);
 	regulator_disable(em_x270_usb_ldo);
-	regulator_enable(em_x270_usb_ldo);
+	err = regulator_enable(em_x270_usb_ldo);
+	if (err)
+		goto err_free_rst_gpio;
+
 	gpio_set_value(usb_hub_reset, 0);
 	gpio_set_value(GPIO9_USB_VBUS_EN, 1);
 
 	return 0;
 
+err_free_rst_gpio:
+	gpio_free(usb_hub_reset);
 err_free_vbus_gpio:
 	gpio_free(GPIO9_USB_VBUS_EN);
 err_free_usb_ldo:
@@ -592,7 +600,7 @@ err_irq:
 	return err;
 }
 
-static void em_x270_mci_setpower(struct device *dev, unsigned int vdd)
+static int em_x270_mci_setpower(struct device *dev, unsigned int vdd)
 {
 	struct pxamci_platform_data* p_d = dev->platform_data;
 
@@ -600,10 +608,11 @@ static void em_x270_mci_setpower(struct device *dev, unsigned int vdd)
 		int vdd_uV = (2000 + (vdd - __ffs(MMC_VDD_20_21)) * 100) * 1000;
 
 		regulator_set_voltage(em_x270_sdio_ldo, vdd_uV, vdd_uV);
-		regulator_enable(em_x270_sdio_ldo);
+		return regulator_enable(em_x270_sdio_ldo);
 	} else {
 		regulator_disable(em_x270_sdio_ldo);
 	}
+	return 0;
 }
 
 static void em_x270_mci_exit(struct device *dev, void *data)
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index d2c652318376..dd70343c8708 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -408,7 +408,7 @@ static int mainstone_mci_init(struct device *dev, irq_handler_t mstone_detect_in
 	return err;
 }
 
-static void mainstone_mci_setpower(struct device *dev, unsigned int vdd)
+static int mainstone_mci_setpower(struct device *dev, unsigned int vdd)
 {
 	struct pxamci_platform_data* p_d = dev->platform_data;
 
@@ -420,6 +420,7 @@ static void mainstone_mci_setpower(struct device *dev, unsigned int vdd)
 		printk(KERN_DEBUG "%s: off\n", __func__);
 		MST_MSCWR1 &= ~MST_MSCWR1_MMC_ON;
 	}
+	return 0;
 }
 
 static void mainstone_mci_exit(struct device *dev, void *data)
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index fb7f1d1627dc..13e5b00eae90 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -335,7 +335,7 @@ static int pcm990_mci_init(struct device *dev, irq_handler_t mci_detect_int,
 	return err;
 }
 
-static void pcm990_mci_setpower(struct device *dev, unsigned int vdd)
+static int pcm990_mci_setpower(struct device *dev, unsigned int vdd)
 {
 	struct pxamci_platform_data *p_d = dev->platform_data;
 	u8 val;
@@ -348,6 +348,7 @@ static void pcm990_mci_setpower(struct device *dev, unsigned int vdd)
 		val &= ~PCM990_CTRL_MMC2PWR;
 
 	pcm990_cpld_writeb(PCM990_CTRL_MMC2PWR, PCM990_CTRL_REG5);
+	return 0;
 }
 
 static void pcm990_mci_exit(struct device *dev, void *data)
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 711d37e26bd8..aedf053a1de5 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -258,7 +258,7 @@ err_free_2:
 	return err;
 }
 
-static void poodle_mci_setpower(struct device *dev, unsigned int vdd)
+static int poodle_mci_setpower(struct device *dev, unsigned int vdd)
 {
 	struct pxamci_platform_data* p_d = dev->platform_data;
 
@@ -270,6 +270,8 @@ static void poodle_mci_setpower(struct device *dev, unsigned int vdd)
 		gpio_set_value(POODLE_GPIO_SD_PWR1, 0);
 		gpio_set_value(POODLE_GPIO_SD_PWR, 0);
 	}
+
+	return 0;
 }
 
 static void poodle_mci_exit(struct device *dev, void *data)
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 2125df0444e7..4c29173026e8 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -598,7 +598,7 @@ static inline void spitz_spi_init(void) {}
  * NOTE: The card detect interrupt isn't debounced so we delay it by 250ms to
  * give the card a chance to fully insert/eject.
  */
-static void spitz_mci_setpower(struct device *dev, unsigned int vdd)
+static int spitz_mci_setpower(struct device *dev, unsigned int vdd)
 {
 	struct pxamci_platform_data* p_d = dev->platform_data;
 
@@ -606,6 +606,8 @@ static void spitz_mci_setpower(struct device *dev, unsigned int vdd)
 		spitz_card_pwr_ctrl(SCOOP_CPR_SD_3V, SCOOP_CPR_SD_3V);
 	else
 		spitz_card_pwr_ctrl(SCOOP_CPR_SD_3V, 0x0);
+
+	return 0;
 }
 
 static struct pxamci_platform_data spitz_mci_platform_data = {
diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c
index 88fde43c948c..62aea3e835f3 100644
--- a/arch/arm/mach-pxa/stargate2.c
+++ b/arch/arm/mach-pxa/stargate2.c
@@ -734,9 +734,10 @@ static int stargate2_mci_init(struct device *dev,
  *
  * Very simple control. Either it is on or off and is controlled by
  * a gpio pin */
-static void stargate2_mci_setpower(struct device *dev, unsigned int vdd)
+static int stargate2_mci_setpower(struct device *dev, unsigned int vdd)
 {
 	gpio_set_value(SG2_SD_POWER_ENABLE, !!vdd);
+	return 0;
 }
 
 static void stargate2_mci_exit(struct device *dev, void *data)
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2410.c b/arch/arm/mach-s3c24xx/clock-s3c2410.c
index 34fffdf6fc1d..564553694b54 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2410.c
@@ -119,66 +119,101 @@ static struct clk init_clocks_off[] = {
 	}
 };
 
-static struct clk init_clocks[] = {
-	{
-		.name		= "lcd",
-		.parent		= &clk_h,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_LCDC,
-	}, {
-		.name		= "gpio",
-		.parent		= &clk_p,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_GPIO,
-	}, {
-		.name		= "usb-host",
-		.parent		= &clk_h,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_USBH,
-	}, {
-		.name		= "usb-device",
-		.parent		= &clk_h,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_USBD,
-	}, {
-		.name		= "timers",
-		.parent		= &clk_p,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_PWMT,
-	}, {
-		.name		= "uart",
-		.devname	= "s3c2410-uart.0",
-		.parent		= &clk_p,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_UART0,
-	}, {
-		.name		= "uart",
-		.devname	= "s3c2410-uart.1",
-		.parent		= &clk_p,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_UART1,
-	}, {
-		.name		= "uart",
-		.devname	= "s3c2410-uart.2",
-		.parent		= &clk_p,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_UART2,
-	}, {
-		.name		= "rtc",
-		.parent		= &clk_p,
-		.enable		= s3c2410_clkcon_enable,
-		.ctrlbit	= S3C2410_CLKCON_RTC,
-	}, {
-		.name		= "watchdog",
-		.parent		= &clk_p,
-		.ctrlbit	= 0,
-	}, {
-		.name		= "usb-bus-host",
-		.parent		= &clk_usb_bus,
-	}, {
-		.name		= "usb-bus-gadget",
-		.parent		= &clk_usb_bus,
-	},
+static struct clk clk_lcd = {
+	.name		= "lcd",
+	.parent		= &clk_h,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_LCDC,
+};
+
+static struct clk clk_gpio = {
+	.name		= "gpio",
+	.parent		= &clk_p,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_GPIO,
+};
+
+static struct clk clk_usb_host = {
+	.name		= "usb-host",
+	.parent		= &clk_h,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_USBH,
+};
+
+static struct clk clk_usb_device = {
+	.name		= "usb-device",
+	.parent		= &clk_h,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_USBD,
+};
+
+static struct clk clk_timers = {
+	.name		= "timers",
+	.parent		= &clk_p,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_PWMT,
+};
+
+struct clk s3c24xx_clk_uart0 = {
+	.name		= "uart",
+	.devname	= "s3c2410-uart.0",
+	.parent		= &clk_p,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_UART0,
+};
+
+struct clk s3c24xx_clk_uart1 = {
+	.name		= "uart",
+	.devname	= "s3c2410-uart.1",
+	.parent		= &clk_p,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_UART1,
+};
+
+struct clk s3c24xx_clk_uart2 = {
+	.name		= "uart",
+	.devname	= "s3c2410-uart.2",
+	.parent		= &clk_p,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_UART2,
+};
+
+static struct clk clk_rtc = {
+	.name		= "rtc",
+	.parent		= &clk_p,
+	.enable		= s3c2410_clkcon_enable,
+	.ctrlbit	= S3C2410_CLKCON_RTC,
+};
+
+static struct clk clk_watchdog = {
+	.name		= "watchdog",
+	.parent		= &clk_p,
+	.ctrlbit	= 0,
+};
+
+static struct clk clk_usb_bus_host = {
+	.name		= "usb-bus-host",
+	.parent		= &clk_usb_bus,
+};
+
+static struct clk clk_usb_bus_gadget = {
+	.name		= "usb-bus-gadget",
+	.parent		= &clk_usb_bus,
+};
+
+static struct clk *init_clocks[] = {
+	&clk_lcd,
+	&clk_gpio,
+	&clk_usb_host,
+	&clk_usb_device,
+	&clk_timers,
+	&s3c24xx_clk_uart0,
+	&s3c24xx_clk_uart1,
+	&s3c24xx_clk_uart2,
+	&clk_rtc,
+	&clk_watchdog,
+	&clk_usb_bus_host,
+	&clk_usb_bus_gadget,
 };
 
 /* s3c2410_baseclk_add()
@@ -195,7 +230,6 @@ int __init s3c2410_baseclk_add(void)
 {
 	unsigned long clkslow = __raw_readl(S3C2410_CLKSLOW);
 	unsigned long clkcon  = __raw_readl(S3C2410_CLKCON);
-	struct clk *clkp;
 	struct clk *xtal;
 	int ret;
 	int ptr;
@@ -207,8 +241,9 @@ int __init s3c2410_baseclk_add(void)
 
 	/* register clocks from clock array */
 
-	clkp = init_clocks;
-	for (ptr = 0; ptr < ARRAY_SIZE(init_clocks); ptr++, clkp++) {
+	for (ptr = 0; ptr < ARRAY_SIZE(init_clocks); ptr++) {
+		struct clk *clkp = init_clocks[ptr];
+
 		/* ensure that we note the clock state */
 
 		clkp->usage = clkcon & clkp->ctrlbit ? 1 : 0;
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2440.c b/arch/arm/mach-s3c24xx/clock-s3c2440.c
index 1069b5680826..aaf006d1d6dc 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2440.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2440.c
@@ -166,6 +166,9 @@ static struct clk_lookup s3c2440_clk_lookup[] = {
 	CLKDEV_INIT(NULL, "clk_uart_baud1", &s3c24xx_uclk),
 	CLKDEV_INIT(NULL, "clk_uart_baud2", &clk_p),
 	CLKDEV_INIT(NULL, "clk_uart_baud3", &s3c2440_clk_fclk_n),
+	CLKDEV_INIT("s3c2440-uart.0", "uart", &s3c24xx_clk_uart0),
+	CLKDEV_INIT("s3c2440-uart.1", "uart", &s3c24xx_clk_uart1),
+	CLKDEV_INIT("s3c2440-uart.2", "uart", &s3c24xx_clk_uart2),
 	CLKDEV_INIT("s3c2440-camif", "camera", &s3c2440_clk_cam_upll),
 };
 
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index e115f6742107..c5be60d85e4b 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -1162,9 +1162,6 @@ static void __init eva_init(void)
 	gpio_request_one(61, GPIOF_OUT_INIT_HIGH, NULL); /* LCDDON */
 	gpio_request_one(202, GPIOF_OUT_INIT_LOW, NULL); /* LCD0_LED_CONT */
 
-	/* Touchscreen */
-	gpio_request_one(166, GPIOF_OUT_INIT_HIGH, NULL); /* TP_RST_B */
-
 	/* GETHER */
 	gpio_request_one(18, GPIOF_OUT_INIT_HIGH, NULL); /* PHY_RST */
 
diff --git a/arch/arm/mach-shmobile/board-bockw.c b/arch/arm/mach-shmobile/board-bockw.c
index d5554646916c..3354a85c90f7 100644
--- a/arch/arm/mach-shmobile/board-bockw.c
+++ b/arch/arm/mach-shmobile/board-bockw.c
@@ -167,7 +167,13 @@ static const struct pinctrl_map bockw_pinctrl_map[] = {
 				  "usb1", "usb1"),
 	/* SDHI0 */
 	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
-				  "sdhi0", "sdhi0"),
+				  "sdhi0_data4", "sdhi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
+				  "sdhi0_ctrl", "sdhi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
+				  "sdhi0_cd", "sdhi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
+				  "sdhi0_wp", "sdhi0"),
 };
 
 #define FPGA	0x18200000
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index d73e21d3ea8a..8d6bd5c5efb9 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -59,7 +59,7 @@ static __initdata struct gpio_led_platform_data lager_leds_pdata = {
 #define GPIO_KEY(c, g, d, ...) \
 	{ .code = c, .gpio = g, .desc = d, .active_low = 1 }
 
-static __initdata struct gpio_keys_button gpio_buttons[] = {
+static struct gpio_keys_button gpio_buttons[] = {
 	GPIO_KEY(KEY_4,		RCAR_GP_PIN(1, 28),	"SW2-pin4"),
 	GPIO_KEY(KEY_3,		RCAR_GP_PIN(1, 26),	"SW2-pin3"),
 	GPIO_KEY(KEY_2,		RCAR_GP_PIN(1, 24),	"SW2-pin2"),
diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig
index d04e3bfe1918..835833e3c4f8 100644
--- a/arch/arm/mach-sti/Kconfig
+++ b/arch/arm/mach-sti/Kconfig
@@ -11,8 +11,9 @@ menuconfig ARCH_STI
 	select HAVE_SMP
 	select HAVE_ARM_SCU if SMP
 	select ARCH_REQUIRE_GPIOLIB
-	select ARM_ERRATA_720789
 	select ARM_ERRATA_754322
+	select ARM_ERRATA_764369
+	select ARM_ERRATA_775420
 	select PL310_ERRATA_753970 if CACHE_PL310
 	select PL310_ERRATA_769419 if CACHE_PL310
 	help
diff --git a/arch/arm/mach-sti/headsmp.S b/arch/arm/mach-sti/headsmp.S
index 78ebc7559f53..4c09bae86edf 100644
--- a/arch/arm/mach-sti/headsmp.S
+++ b/arch/arm/mach-sti/headsmp.S
@@ -16,8 +16,6 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
-	__INIT
-
 /*
  * ST specific entry point for secondary CPUs.  This provides
  * a "holding pen" into which all secondary cores are held until we're
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 5b799c29886e..5f252569c689 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -91,7 +91,7 @@ static void __init zynq_map_io(void)
 	zynq_scu_map_io();
 }
 
-static void zynq_system_reset(char mode, const char *cmd)
+static void zynq_system_reset(enum reboot_mode mode, const char *cmd)
 {
 	zynq_slcr_system_reset();
 }
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 6cacdc8dd654..cd2c88e7a8f7 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -421,24 +421,28 @@ config CPU_32v3
 	select CPU_USE_DOMAINS if MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select TLS_REG_EMUL if SMP || !MMU
+	select NEED_KUSER_HELPERS
 
 config CPU_32v4
 	bool
 	select CPU_USE_DOMAINS if MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select TLS_REG_EMUL if SMP || !MMU
+	select NEED_KUSER_HELPERS
 
 config CPU_32v4T
 	bool
 	select CPU_USE_DOMAINS if MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select TLS_REG_EMUL if SMP || !MMU
+	select NEED_KUSER_HELPERS
 
 config CPU_32v5
 	bool
 	select CPU_USE_DOMAINS if MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select TLS_REG_EMUL if SMP || !MMU
+	select NEED_KUSER_HELPERS
 
 config CPU_32v6
 	bool
@@ -776,6 +780,7 @@ config CPU_BPREDICT_DISABLE
 
 config TLS_REG_EMUL
 	bool
+	select NEED_KUSER_HELPERS
 	help
 	  An SMP system using a pre-ARMv6 processor (there are apparently
 	  a few prototypes like that in existence) and therefore access to
@@ -783,11 +788,43 @@ config TLS_REG_EMUL
 
 config NEEDS_SYSCALL_FOR_CMPXCHG
 	bool
+	select NEED_KUSER_HELPERS
 	help
 	  SMP on a pre-ARMv6 processor?  Well OK then.
 	  Forget about fast user space cmpxchg support.
 	  It is just not possible.
 
+config NEED_KUSER_HELPERS
+	bool
+
+config KUSER_HELPERS
+	bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS
+	default y
+	help
+	  Warning: disabling this option may break user programs.
+
+	  Provide kuser helpers in the vector page.  The kernel provides
+	  helper code to userspace in read only form at a fixed location
+	  in the high vector page to allow userspace to be independent of
+	  the CPU type fitted to the system.  This permits binaries to be
+	  run on ARMv4 through to ARMv7 without modification.
+
+	  See Documentation/arm/kernel_user_helpers.txt for details.
+
+	  However, the fixed address nature of these helpers can be used
+	  by ROP (return orientated programming) authors when creating
+	  exploits.
+
+	  If all of the binaries and libraries which run on your platform
+	  are built specifically for your platform, and make no use of
+	  these helpers, then you can turn this option off to hinder
+	  such exploits. However, in that case, if a binary or library
+	  relying on those helpers is run, it will receive a SIGILL signal,
+	  which will terminate the program.
+
+	  Say N here only if you are absolutely certain that you do not
+	  need these helpers; otherwise, the safe option is to say Y.
+
 config DMA_CACHE_RWFO
 	bool "Enable read/write for ownership DMA cache maintenance"
 	depends on CPU_V6K && SMP
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index b55b1015724b..4a0544492f10 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -245,7 +245,8 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
 		local_flush_bp_all();
 		local_flush_tlb_all();
-		dummy_flush_tlb_a15_erratum();
+		if (erratum_a15_798181())
+			dummy_flush_tlb_a15_erratum();
 	}
 
 	atomic64_set(&per_cpu(active_asids, cpu), asid);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4f56617a2392..53cdbd39ec8e 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -989,6 +989,7 @@ phys_addr_t arm_lowmem_limit __initdata = 0;
 
 void __init sanity_check_meminfo(void)
 {
+	phys_addr_t memblock_limit = 0;
 	int i, j, highmem = 0;
 	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
 
@@ -1052,9 +1053,32 @@ void __init sanity_check_meminfo(void)
 			bank->size = size_limit;
 		}
 #endif
-		if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit)
-			arm_lowmem_limit = bank->start + bank->size;
+		if (!bank->highmem) {
+			phys_addr_t bank_end = bank->start + bank->size;
 
+			if (bank_end > arm_lowmem_limit)
+				arm_lowmem_limit = bank_end;
+
+			/*
+			 * Find the first non-section-aligned page, and point
+			 * memblock_limit at it. This relies on rounding the
+			 * limit down to be section-aligned, which happens at
+			 * the end of this function.
+			 *
+			 * With this algorithm, the start or end of almost any
+			 * bank can be non-section-aligned. The only exception
+			 * is that the start of the bank 0 must be section-
+			 * aligned, since otherwise memory would need to be
+			 * allocated when mapping the start of bank 0, which
+			 * occurs before any free memory is mapped.
+			 */
+			if (!memblock_limit) {
+				if (!IS_ALIGNED(bank->start, SECTION_SIZE))
+					memblock_limit = bank->start;
+				else if (!IS_ALIGNED(bank_end, SECTION_SIZE))
+					memblock_limit = bank_end;
+			}
+		}
 		j++;
 	}
 #ifdef CONFIG_HIGHMEM
@@ -1079,7 +1103,18 @@ void __init sanity_check_meminfo(void)
 #endif
 	meminfo.nr_banks = j;
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
-	memblock_set_current_limit(arm_lowmem_limit);
+
+	/*
+	 * Round the memblock limit down to a section size.  This
+	 * helps to ensure that we will allocate memory from the
+	 * last full section, which should be mapped.
+	 */
+	if (memblock_limit)
+		memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+	if (!memblock_limit)
+		memblock_limit = arm_lowmem_limit;
+
+	memblock_set_current_limit(memblock_limit);
 }
 
 static inline void prepare_page_table(void)
@@ -1160,7 +1195,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors = early_alloc(PAGE_SIZE);
+	vectors = early_alloc(PAGE_SIZE * 2);
 
 	early_trap_init(vectors);
 
@@ -1205,15 +1240,27 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
+#ifdef CONFIG_KUSER_HELPERS
 	map.type = MT_HIGH_VECTORS;
+#else
+	map.type = MT_LOW_VECTORS;
+#endif
 	create_mapping(&map);
 
 	if (!vectors_high()) {
 		map.virtual = 0;
+		map.length = PAGE_SIZE * 2;
 		map.type = MT_LOW_VECTORS;
 		create_mapping(&map);
 	}
 
+	/* Now create a kernel read-only mapping */
+	map.pfn += 1;
+	map.virtual = 0xffff0000 + PAGE_SIZE;
+	map.length = PAGE_SIZE;
+	map.type = MT_LOW_VECTORS;
+	create_mapping(&map);
+
 	/*
 	 * Ask the machine support to map in the statically mapped devices.
 	 */
@@ -1276,8 +1323,6 @@ void __init paging_init(struct machine_desc *mdesc)
 {
 	void *zero_page;
 
-	memblock_set_current_limit(arm_lowmem_limit);
-
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index f64afb9f1bd5..bdd3be4be77a 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -110,7 +110,7 @@ ENTRY(cpu_v7_set_pte_ext)
  ARM(	str	r3, [r0, #2048]! )
  THUMB(	add	r0, r0, #2048 )
  THUMB(	str	r3, [r0] )
-	ALT_SMP(mov	pc,lr)
+	ALT_SMP(W(nop))
 	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index c36ac69488c8..01a719e18bb0 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -81,7 +81,7 @@ ENTRY(cpu_v7_set_pte_ext)
 	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
 	orreq	r2, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
-	ALT_SMP(mov	pc, lr)
+	ALT_SMP(W(nop))
 	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 5c6d5a3050ea..73398bcf9bd8 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -75,13 +75,14 @@ ENTRY(cpu_v7_do_idle)
 ENDPROC(cpu_v7_do_idle)
 
 ENTRY(cpu_v7_dcache_clean_area)
-	ALT_SMP(mov	pc, lr)			@ MP extensions imply L1 PTW
-	ALT_UP(W(nop))
-	dcache_line_size r2, r3
-1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+	ALT_SMP(W(nop))			@ MP extensions imply L1 PTW
+	ALT_UP_B(1f)
+	mov	pc, lr
+1:	dcache_line_size r2, r3
+2:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, r2
 	subs	r1, r1, r2
-	bhi	1b
+	bhi	2b
 	dsb
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index 3dc5cbea86cc..a5b5ff6e68d2 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -29,6 +29,13 @@ config PLAT_S5P
 	help
 	  Base platform code for Samsung's S5P series SoC.
 
+config SAMSUNG_PM
+	bool
+	depends on PM && (PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5P64X0 || S5P_PM)
+	default y
+	help
+	  Base platform power management code for samsung code
+
 if PLAT_SAMSUNG
 
 # boot configurations
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index 98d07d8fc7a7..199bbe304d02 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -51,7 +51,7 @@ obj-$(CONFIG_SAMSUNG_DMADEV)	+= dma-ops.o
 
 # PM support
 
-obj-$(CONFIG_PM)		+= pm.o
+obj-$(CONFIG_SAMSUNG_PM)	+= pm.o
 obj-$(CONFIG_SAMSUNG_PM_GPIO)	+= pm-gpio.o
 obj-$(CONFIG_SAMSUNG_PM_CHECK)	+= pm-check.o
 
diff --git a/arch/arm/plat-samsung/include/plat/clock.h b/arch/arm/plat-samsung/include/plat/clock.h
index a62753dc15ba..df45d6edc98d 100644
--- a/arch/arm/plat-samsung/include/plat/clock.h
+++ b/arch/arm/plat-samsung/include/plat/clock.h
@@ -83,6 +83,11 @@ extern struct clk clk_ext;
 extern struct clksrc_clk clk_epllref;
 extern struct clksrc_clk clk_esysclk;
 
+/* S3C24XX UART clocks */
+extern struct clk s3c24xx_clk_uart0;
+extern struct clk s3c24xx_clk_uart1;
+extern struct clk s3c24xx_clk_uart2;
+
 /* S3C64XX specific clocks */
 extern struct clk clk_h2;
 extern struct clk clk_27m;
diff --git a/arch/arm/plat-samsung/include/plat/pm.h b/arch/arm/plat-samsung/include/plat/pm.h
index 5d47ca35cabd..6bc1a8f471e3 100644
--- a/arch/arm/plat-samsung/include/plat/pm.h
+++ b/arch/arm/plat-samsung/include/plat/pm.h
@@ -19,7 +19,7 @@
 
 struct device;
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_SAMSUNG_PM
 
 extern __init int s3c_pm_init(void);
 extern __init int s3c64xx_pm_init(void);
@@ -58,8 +58,6 @@ extern unsigned char pm_uart_udivslot;  /* true to save UART UDIVSLOT */
 
 /* from sleep.S */
 
-extern void s3c_cpu_resume(void);
-
 extern int s3c2410_cpu_suspend(unsigned long);
 
 /* sleep save info */
@@ -106,12 +104,14 @@ extern void s3c_pm_do_save(struct sleep_save *ptr, int count);
 extern void s3c_pm_do_restore(struct sleep_save *ptr, int count);
 extern void s3c_pm_do_restore_core(struct sleep_save *ptr, int count);
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_SAMSUNG_PM
 extern int s3c_irq_wake(struct irq_data *data, unsigned int state);
 extern int s3c_irqext_wake(struct irq_data *data, unsigned int state);
+extern void s3c_cpu_resume(void);
 #else
 #define s3c_irq_wake NULL
 #define s3c_irqext_wake NULL
+#define s3c_cpu_resume NULL
 #endif
 
 /* PM debug functions */
diff --git a/arch/arm/plat-samsung/init.c b/arch/arm/plat-samsung/init.c
index 3e5c4619caa5..50a3ea0037db 100644
--- a/arch/arm/plat-samsung/init.c
+++ b/arch/arm/plat-samsung/init.c
@@ -55,12 +55,13 @@ void __init s3c_init_cpu(unsigned long idcode,
 
 	printk("CPU %s (id 0x%08lx)\n", cpu->name, idcode);
 
-	if (cpu->map_io == NULL || cpu->init == NULL) {
+	if (cpu->init == NULL) {
 		printk(KERN_ERR "CPU %s support not enabled\n", cpu->name);
 		panic("Unsupported Samsung CPU");
 	}
 
-	cpu->map_io();
+	if (cpu->map_io)
+		cpu->map_io();
 }
 
 /* s3c24xx_init_clocks
diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c
index ea3613642451..d0c23010b693 100644
--- a/arch/arm/plat-samsung/pm.c
+++ b/arch/arm/plat-samsung/pm.c
@@ -80,7 +80,7 @@ unsigned char pm_uart_udivslot;
 
 #ifdef CONFIG_SAMSUNG_PM_DEBUG
 
-static struct pm_uart_save uart_save[CONFIG_SERIAL_SAMSUNG_UARTS];
+static struct pm_uart_save uart_save;
 
 static void s3c_pm_save_uart(unsigned int uart, struct pm_uart_save *save)
 {
@@ -101,11 +101,7 @@ static void s3c_pm_save_uart(unsigned int uart, struct pm_uart_save *save)
 
 static void s3c_pm_save_uarts(void)
 {
-	struct pm_uart_save *save = uart_save;
-	unsigned int uart;
-
-	for (uart = 0; uart < CONFIG_SERIAL_SAMSUNG_UARTS; uart++, save++)
-		s3c_pm_save_uart(uart, save);
+	s3c_pm_save_uart(CONFIG_DEBUG_S3C_UART, &uart_save);
 }
 
 static void s3c_pm_restore_uart(unsigned int uart, struct pm_uart_save *save)
@@ -126,11 +122,7 @@ static void s3c_pm_restore_uart(unsigned int uart, struct pm_uart_save *save)
 
 static void s3c_pm_restore_uarts(void)
 {
-	struct pm_uart_save *save = uart_save;
-	unsigned int uart;
-
-	for (uart = 0; uart < CONFIG_SERIAL_SAMSUNG_UARTS; uart++, save++)
-		s3c_pm_restore_uart(uart, save);
+	s3c_pm_restore_uart(CONFIG_DEBUG_S3C_UART, &uart_save);
 }
 #else
 static void s3c_pm_save_uarts(void) { }
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index f71c37edca26..8a6295c86209 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -170,9 +170,10 @@ static void __init xen_percpu_init(void *unused)
 	per_cpu(xen_vcpu, cpu) = vcpup;
 
 	enable_percpu_irq(xen_events_irq, 0);
+	put_cpu();
 }
 
-static void xen_restart(char str, const char *cmd)
+static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
 {
 	struct sched_shutdown r = { .reason = SHUTDOWN_reboot };
 	int rc;
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index c92de4163eba..b25763bc0ec4 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -42,14 +42,15 @@
 #define	TPIDR_EL1	18	/* Thread ID, Privileged */
 #define	AMAIR_EL1	19	/* Aux Memory Attribute Indirection Register */
 #define	CNTKCTL_EL1	20	/* Timer Control Register (EL1) */
+#define	PAR_EL1		21	/* Physical Address Register */
 /* 32bit specific registers. Keep them at the end of the range */
-#define	DACR32_EL2	21	/* Domain Access Control Register */
-#define	IFSR32_EL2	22	/* Instruction Fault Status Register */
-#define	FPEXC32_EL2	23	/* Floating-Point Exception Control Register */
-#define	DBGVCR32_EL2	24	/* Debug Vector Catch Register */
-#define	TEECR32_EL1	25	/* ThumbEE Configuration Register */
-#define	TEEHBR32_EL1	26	/* ThumbEE Handler Base Register */
-#define	NR_SYS_REGS	27
+#define	DACR32_EL2	22	/* Domain Access Control Register */
+#define	IFSR32_EL2	23	/* Instruction Fault Status Register */
+#define	FPEXC32_EL2	24	/* Floating-Point Exception Control Register */
+#define	DBGVCR32_EL2	25	/* Debug Vector Catch Register */
+#define	TEECR32_EL1	26	/* ThumbEE Configuration Register */
+#define	TEEHBR32_EL1	27	/* ThumbEE Handler Base Register */
+#define	NR_SYS_REGS	28
 
 /* 32bit mapping */
 #define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
@@ -69,6 +70,8 @@
 #define c5_AIFSR	(AFSR1_EL1 * 2)	/* Auxiliary Instr Fault Status R */
 #define c6_DFAR		(FAR_EL1 * 2)	/* Data Fault Address Register */
 #define c6_IFAR		(c6_DFAR + 1)	/* Instruction Fault Address Register */
+#define c7_PAR		(PAR_EL1 * 2)	/* Physical Address Register */
+#define c7_PAR_high	(c7_PAR + 1)	/* PAR top 32 bits */
 #define c10_PRRR	(MAIR_EL1 * 2)	/* Primary Region Remap Register */
 #define c10_NMRR	(c10_PRRR + 1)	/* Normal Memory Remap Register */
 #define c12_VBAR	(VBAR_EL1 * 2)	/* Vector Base Address Register */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 644d73956864..0859a4ddd1e7 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -129,7 +129,7 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
 	/* Target CPU and feature flags */
-	u32 target;
+	int target;
 	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
 	/* Detect first run of a vcpu */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 3659e460071d..23a3c4791d86 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -24,10 +24,10 @@
 #include <linux/compiler.h>
 
 #ifndef CONFIG_ARM64_64K_PAGES
-#define THREAD_SIZE_ORDER	1
+#define THREAD_SIZE_ORDER	2
 #endif
 
-#define THREAD_SIZE		8192
+#define THREAD_SIZE		16384
 #define THREAD_START_SP		(THREAD_SIZE - 16)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 46b3beb4b773..717031a762c2 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -35,6 +35,7 @@ struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		fullmm;
 	struct vm_area_struct	*vma;
+	unsigned long		start, end;
 	unsigned long		range_start;
 	unsigned long		range_end;
 	unsigned int		nr;
@@ -97,10 +98,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = fullmm;
+	tlb->fullmm = !(start | (end+1));
+	tlb->start = start;
+	tlb->end = end;
 	tlb->vma = NULL;
 	tlb->max = ARRAY_SIZE(tlb->local);
 	tlb->pages = tlb->local;
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 439827271e3d..26e310c54344 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -21,6 +21,7 @@
 #define BOOT_CPU_MODE_EL2	(0x0e12b007)
 
 #ifndef __ASSEMBLY__
+#include <asm/cacheflush.h>
 
 /*
  * __boot_cpu_mode records what mode CPUs were booted in.
@@ -36,9 +37,20 @@ extern u32 __boot_cpu_mode[2];
 void __hyp_set_vectors(phys_addr_t phys_vector_base);
 phys_addr_t __hyp_get_vectors(void);
 
+static inline void sync_boot_mode(void)
+{
+	/*
+	 * As secondaries write to __boot_cpu_mode with caches disabled, we
+	 * must flush the corresponding cache entries to ensure the visibility
+	 * of their writes.
+	 */
+	__flush_dcache_area(__boot_cpu_mode, sizeof(__boot_cpu_mode));
+}
+
 /* Reports the availability of HYP mode */
 static inline bool is_hyp_mode_available(void)
 {
+	sync_boot_mode();
 	return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 &&
 		__boot_cpu_mode[1] == BOOT_CPU_MODE_EL2);
 }
@@ -46,6 +58,7 @@ static inline bool is_hyp_mode_available(void)
 /* Check if the bootloader has booted CPUs in different modes */
 static inline bool is_hyp_mode_mismatched(void)
 {
+	sync_boot_mode();
 	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
 }
 
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 1d1314280a03..6ad781b21c08 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -121,7 +121,7 @@
 
 	.macro	get_thread_info, rd
 	mov	\rd, sp
-	and	\rd, \rd, #~((1 << 13) - 1)	// top of 8K stack
+	and	\rd, \rd, #~(THREAD_SIZE - 1)	// top of stack
 	.endm
 
 /*
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9ba33c40cdf8..12e6ccb88691 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -107,7 +107,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-	int mapping = (*event_map)[config];
+	int mapping;
+
+	if (config >= PERF_COUNT_HW_MAX)
+		return -EINVAL;
+
+	mapping = (*event_map)[config];
 	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -317,6 +322,9 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct hw_perf_event fake_event = event->hw;
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
+	if (is_software_event(event))
+		return 1;
+
 	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
 		return 1;
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1788bf6b471f..57fb55c44c90 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -81,7 +81,7 @@ void soft_restart(unsigned long addr)
 void (*pm_power_off)(void);
 EXPORT_SYMBOL_GPL(pm_power_off);
 
-void (*arm_pm_restart)(char str, const char *cmd);
+void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 EXPORT_SYMBOL_GPL(arm_pm_restart);
 
 void arch_cpu_idle_prepare(void)
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index ff985e3d8b72..1ac0bbbdddb2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -214,6 +214,7 @@ __kvm_hyp_code_start:
 	mrs	x21,	tpidr_el1
 	mrs	x22, 	amair_el1
 	mrs	x23, 	cntkctl_el1
+	mrs	x24,	par_el1
 
 	stp	x4, x5, [x3]
 	stp	x6, x7, [x3, #16]
@@ -225,6 +226,7 @@ __kvm_hyp_code_start:
 	stp	x18, x19, [x3, #112]
 	stp	x20, x21, [x3, #128]
 	stp	x22, x23, [x3, #144]
+	str	x24, [x3, #160]
 .endm
 
 .macro restore_sysregs
@@ -243,6 +245,7 @@ __kvm_hyp_code_start:
 	ldp	x18, x19, [x3, #112]
 	ldp	x20, x21, [x3, #128]
 	ldp	x22, x23, [x3, #144]
+	ldr	x24, [x3, #160]
 
 	msr	vmpidr_el2,	x4
 	msr	csselr_el1,	x5
@@ -264,6 +267,7 @@ __kvm_hyp_code_start:
 	msr	tpidr_el1,	x21
 	msr	amair_el1,	x22
 	msr	cntkctl_el1,	x23
+	msr	par_el1,	x24
 .endm
 
 .macro skip_32bit_state tmp, target
@@ -600,6 +604,8 @@ END(__kvm_vcpu_run)
 
 // void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 ENTRY(__kvm_tlb_flush_vmid_ipa)
+	dsb	ishst
+
 	kern_hyp_va	x0
 	ldr	x2, [x0, #KVM_VTTBR]
 	msr	vttbr_el2, x2
@@ -621,6 +627,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 ENDPROC(__kvm_tlb_flush_vmid_ipa)
 
 ENTRY(__kvm_flush_vm_context)
+	dsb	ishst
 	tlbi	alle1is
 	ic	ialluis
 	dsb	sy
@@ -753,6 +760,10 @@ el1_trap:
 	 */
 	tbnz	x1, #7, 1f	// S1PTW is set
 
+	/* Preserve PAR_EL1 */
+	mrs	x3, par_el1
+	push	x3, xzr
+
 	/*
 	 * Permission fault, HPFAR_EL2 is invalid.
 	 * Resolve the IPA the hard way using the guest VA.
@@ -766,6 +777,8 @@ el1_trap:
 
 	/* Read result */
 	mrs	x3, par_el1
+	pop	x0, xzr			// Restore PAR_EL1 from the stack
+	msr	par_el1, x0
 	tbnz	x3, #0, 3f		// Bail out if we failed the translation
 	ubfx	x3, x3, #12, #36	// Extract IPA
 	lsl	x3, x3, #4		// and present it like HPFAR
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 94923609753b..02e9d09e1d80 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -211,6 +211,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	/* FAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
 	  NULL, reset_unknown, FAR_EL1 },
+	/* PAR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
+	  NULL, reset_unknown, PAR_EL1 },
 
 	/* PMINTENSET_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
diff --git a/arch/avr32/boards/atngw100/mrmt.c b/arch/avr32/boards/atngw100/mrmt.c
index f91431963452..7de083d19b7e 100644
--- a/arch/avr32/boards/atngw100/mrmt.c
+++ b/arch/avr32/boards/atngw100/mrmt.c
@@ -150,7 +150,6 @@ static struct ac97c_platform_data __initdata ac97c0_data = {
 static struct platform_device rmt_ts_device = {
 	.name	= "ucb1400_ts",
 	.id	= -1,
-	}
 };
 #endif
 
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 33a97929d055..77d442ab28c8 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -158,6 +158,7 @@ source "kernel/Kconfig.hz"
 endmenu
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 source "drivers/Kconfig"
 source "fs/Kconfig"
 
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index 7913695b2fcb..efbd2929aeb7 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -31,7 +31,7 @@ CONFIG_ACPI_FAN=m
 CONFIG_ACPI_DOCK=y
 CONFIG_ACPI_PROCESSOR=m
 CONFIG_ACPI_CONTAINER=m
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_ACPI=m
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/ia64/configs/gensparse_defconfig b/arch/ia64/configs/gensparse_defconfig
index f8e913365423..f64980dd20c3 100644
--- a/arch/ia64/configs/gensparse_defconfig
+++ b/arch/ia64/configs/gensparse_defconfig
@@ -25,7 +25,7 @@ CONFIG_ACPI_BUTTON=m
 CONFIG_ACPI_FAN=m
 CONFIG_ACPI_PROCESSOR=m
 CONFIG_ACPI_CONTAINER=m
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_ACPI=m
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/ia64/configs/tiger_defconfig b/arch/ia64/configs/tiger_defconfig
index a5a9e02e60a0..0f4e9e41f130 100644
--- a/arch/ia64/configs/tiger_defconfig
+++ b/arch/ia64/configs/tiger_defconfig
@@ -31,7 +31,7 @@ CONFIG_ACPI_BUTTON=m
 CONFIG_ACPI_FAN=m
 CONFIG_ACPI_PROCESSOR=m
 CONFIG_ACPI_CONTAINER=m
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_ACPI=m
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/ia64/configs/xen_domu_defconfig b/arch/ia64/configs/xen_domu_defconfig
index 37b9b422caad..b025acfde5c1 100644
--- a/arch/ia64/configs/xen_domu_defconfig
+++ b/arch/ia64/configs/xen_domu_defconfig
@@ -32,7 +32,7 @@ CONFIG_ACPI_BUTTON=m
 CONFIG_ACPI_FAN=m
 CONFIG_ACPI_PROCESSOR=m
 CONFIG_ACPI_CONTAINER=m
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_ACPI=m
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index ef3a9de01954..bc5efc7c3f3f 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -22,7 +22,7 @@
  * unmapping a portion of the virtual address space, these hooks are called according to
  * the following template:
  *
- *	tlb <- tlb_gather_mmu(mm, full_mm_flush);	// start unmap for address space MM
+ *	tlb <- tlb_gather_mmu(mm, start, end);		// start unmap for address space MM
  *	{
  *	  for each vma that needs a shootdown do {
  *	    tlb_start_vma(tlb, vma);
@@ -58,6 +58,7 @@ struct mmu_gather {
 	unsigned int		max;
 	unsigned char		fullmm;		/* non-zero means full mm flush */
 	unsigned char		need_flush;	/* really unmapped some PTEs? */
+	unsigned long		start, end;
 	unsigned long		start_addr;
 	unsigned long		end_addr;
 	struct page		**pages;
@@ -155,13 +156,15 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->max = ARRAY_SIZE(tlb->local);
 	tlb->pages = tlb->local;
 	tlb->nr = 0;
-	tlb->fullmm = full_mm_flush;
+	tlb->fullmm = !(start | (end+1));
+	tlb->start = start;
+	tlb->end = end;
 	tlb->start_addr = ~0UL;
 }
 
diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c
index 2291a7d69d49..fa277aecfb78 100644
--- a/arch/m68k/emu/natfeat.c
+++ b/arch/m68k/emu/natfeat.c
@@ -18,9 +18,11 @@
 #include <asm/machdep.h>
 #include <asm/natfeat.h>
 
+extern long nf_get_id2(const char *feature_name);
+
 asm("\n"
-"	.global nf_get_id,nf_call\n"
-"nf_get_id:\n"
+"	.global nf_get_id2,nf_call\n"
+"nf_get_id2:\n"
 "	.short	0x7300\n"
 "	rts\n"
 "nf_call:\n"
@@ -29,12 +31,25 @@ asm("\n"
 "1:	moveq.l	#0,%d0\n"
 "	rts\n"
 "	.section __ex_table,\"a\"\n"
-"	.long	nf_get_id,1b\n"
+"	.long	nf_get_id2,1b\n"
 "	.long	nf_call,1b\n"
 "	.previous");
-EXPORT_SYMBOL_GPL(nf_get_id);
 EXPORT_SYMBOL_GPL(nf_call);
 
+long nf_get_id(const char *feature_name)
+{
+	/* feature_name may be in vmalloc()ed memory, so make a copy */
+	char name_copy[32];
+	size_t n;
+
+	n = strlcpy(name_copy, feature_name, sizeof(name_copy));
+	if (n >= sizeof(name_copy))
+		return 0;
+
+	return nf_get_id2(name_copy);
+}
+EXPORT_SYMBOL_GPL(nf_get_id);
+
 void nfprint(const char *fmt, ...)
 {
 	static char buf[256];
diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h
index 444ea8a09e9f..ef881cfbbca9 100644
--- a/arch/m68k/include/asm/div64.h
+++ b/arch/m68k/include/asm/div64.h
@@ -15,16 +15,17 @@
 		unsigned long long n64;				\
 	} __n;							\
 	unsigned long __rem, __upper;				\
+	unsigned long __base = (base);				\
 								\
 	__n.n64 = (n);						\
 	if ((__upper = __n.n32[0])) {				\
 		asm ("divul.l %2,%1:%0"				\
-			: "=d" (__n.n32[0]), "=d" (__upper)	\
-			: "d" (base), "0" (__n.n32[0]));	\
+		     : "=d" (__n.n32[0]), "=d" (__upper)	\
+		     : "d" (__base), "0" (__n.n32[0]));		\
 	}							\
 	asm ("divu.l %2,%1:%0"					\
-		: "=d" (__n.n32[1]), "=d" (__rem)		\
-		: "d" (base), "1" (__upper), "0" (__n.n32[1]));	\
+	     : "=d" (__n.n32[1]), "=d" (__rem)			\
+	     : "d" (__base), "1" (__upper), "0" (__n.n32[1]));	\
 	(n) = __n.n64;						\
 	__rem;							\
 })
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d22a4ecffff4..4fab52294d98 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -28,7 +28,7 @@ config MICROBLAZE
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IDLE_POLL_SETUP
 	select MODULES_USE_ELF_RELA
-	select CLONE_BACKWARDS
+	select CLONE_BACKWARDS3
 
 config SWAP
 	def_bool n
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c3abed332301..e12764c2a9d0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -114,6 +114,7 @@ config BCM47XX
 	select FW_CFE
 	select HW_HAS_PCI
 	select IRQ_CPU
+	select SYS_HAS_CPU_MIPS32_R1
 	select NO_EXCEPT_FILL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
diff --git a/arch/mips/bcm47xx/Kconfig b/arch/mips/bcm47xx/Kconfig
index ba611927749b..2b8b118398c4 100644
--- a/arch/mips/bcm47xx/Kconfig
+++ b/arch/mips/bcm47xx/Kconfig
@@ -2,7 +2,6 @@ if BCM47XX
 
 config BCM47XX_SSB
 	bool "SSB Support for Broadcom BCM47XX"
-	select SYS_HAS_CPU_MIPS32_R1
 	select SSB
 	select SSB_DRIVER_MIPS
 	select SSB_DRIVER_EXTIF
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 1dc086087a72..fa44f3ec5302 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -17,6 +17,8 @@
 #define current_cpu_type()	current_cpu_data.cputype
 #endif
 
+#define boot_cpu_type()		cpu_data[0].cputype
+
 /*
  * SMP assumption: Options of CPU 0 are a superset of all processors.
  * This is true for all known MIPS systems.
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index 5b2f2e68e57f..9488fa5f8866 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -25,8 +25,12 @@
 #else
 #define CAC_BASE		_AC(0x80000000, UL)
 #endif
+#ifndef IO_BASE
 #define IO_BASE			_AC(0xa0000000, UL)
+#endif
+#ifndef UNCAC_BASE
 #define UNCAC_BASE		_AC(0xa0000000, UL)
+#endif
 
 #ifndef MAP_BASE
 #ifdef CONFIG_KVM_GUEST
diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h
index b7a23064841f..88e292b7719e 100644
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@@ -25,11 +25,12 @@ struct siginfo;
 /*
  * Careful to keep union _sifields from shifting ...
  */
-#if __SIZEOF_LONG__ == 4
+#if _MIPS_SZLONG == 32
 #define __ARCH_SI_PREAMBLE_SIZE (3 * sizeof(int))
-#endif
-#if __SIZEOF_LONG__ == 8
+#elif _MIPS_SZLONG == 64
 #define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
+#else
+#error _MIPS_SZLONG neither 32 nor 64
 #endif
 
 #include <asm-generic/siginfo.h>
diff --git a/arch/mips/kernel/bmips_vec.S b/arch/mips/kernel/bmips_vec.S
index f739aedcb509..bd79c4f9bff4 100644
--- a/arch/mips/kernel/bmips_vec.S
+++ b/arch/mips/kernel/bmips_vec.S
@@ -54,7 +54,11 @@ LEAF(bmips_smp_movevec)
 	/* set up CPU1 CBR; move BASE to 0xa000_0000 */
 	li	k0, 0xff400000
 	mtc0	k0, $22, 6
-	li	k1, CKSEG1 | BMIPS_RELO_VECTOR_CONTROL_1
+	/* set up relocation vector address based on thread ID */
+	mfc0	k1, $22, 3
+	srl	k1, 16
+	andi	k1, 0x8000
+	or	k1, CKSEG1 | BMIPS_RELO_VECTOR_CONTROL_0
 	or	k0, k1
 	li	k1, 0xa0080000
 	sw	k1, 0(k0)
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index c0bb4d59076a..126da74d4c55 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -66,6 +66,8 @@ static void __init bmips_smp_setup(void)
 	int i, cpu = 1, boot_cpu = 0;
 
 #if defined(CONFIG_CPU_BMIPS4350) || defined(CONFIG_CPU_BMIPS4380)
+	int cpu_hw_intr;
+
 	/* arbitration priority */
 	clear_c0_brcm_cmt_ctrl(0x30);
 
@@ -79,15 +81,13 @@ static void __init bmips_smp_setup(void)
 	 * MIPS interrupts 0,1 (SW INT 0,1) cross over to the other thread
 	 * MIPS interrupt 2 (HW INT 0) is the CPU0 L1 controller output
 	 * MIPS interrupt 3 (HW INT 1) is the CPU1 L1 controller output
-	 *
-	 * If booting from TP1, leave the existing CMT interrupt routing
-	 * such that TP0 responds to SW1 and TP1 responds to SW0.
 	 */
 	if (boot_cpu == 0)
-		change_c0_brcm_cmt_intr(0xf8018000,
-					(0x02 << 27) | (0x03 << 15));
+		cpu_hw_intr = 0x02;
 	else
-		change_c0_brcm_cmt_intr(0xf8018000, (0x1d << 27));
+		cpu_hw_intr = 0x1d;
+
+	change_c0_brcm_cmt_intr(0xf8018000, (cpu_hw_intr << 27) | (0x03 << 15));
 
 	/* single core, 2 threads (2 pipelines) */
 	max_cpus = 2;
@@ -202,9 +202,15 @@ static void bmips_init_secondary(void)
 #if defined(CONFIG_CPU_BMIPS4350) || defined(CONFIG_CPU_BMIPS4380)
 	void __iomem *cbr = BMIPS_GET_CBR();
 	unsigned long old_vec;
+	unsigned long relo_vector;
+	int boot_cpu;
+
+	boot_cpu = !!(read_c0_brcm_cmt_local() & (1 << 31));
+	relo_vector = boot_cpu ? BMIPS_RELO_VECTOR_CONTROL_0 :
+			  BMIPS_RELO_VECTOR_CONTROL_1;
 
-	old_vec = __raw_readl(cbr + BMIPS_RELO_VECTOR_CONTROL_1);
-	__raw_writel(old_vec & ~0x20000000, cbr + BMIPS_RELO_VECTOR_CONTROL_1);
+	old_vec = __raw_readl(cbr + relo_vector);
+	__raw_writel(old_vec & ~0x20000000, cbr + relo_vector);
 
 	clear_c0_cause(smp_processor_id() ? C_SW1 : C_SW0);
 #elif defined(CONFIG_CPU_BMIPS5000)
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index e773659ccf9f..46048d24328c 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -803,6 +803,32 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.next_pc_inc;
 		return 1;
 		break;
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+	case lwc2_op: /* This is bbit0 on Octeon */
+		if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0)
+			*contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			*contpc = regs->cp0_epc + 8;
+		return 1;
+	case ldc2_op: /* This is bbit032 on Octeon */
+		if ((regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32))) == 0)
+			*contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			*contpc = regs->cp0_epc + 8;
+		return 1;
+	case swc2_op: /* This is bbit1 on Octeon */
+		if (regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt))
+			*contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			*contpc = regs->cp0_epc + 8;
+		return 1;
+	case sdc2_op: /* This is bbit132 on Octeon */
+		if (regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32)))
+			*contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			*contpc = regs->cp0_epc + 8;
+		return 1;
+#endif
 	case cop0_op:
 	case cop1_op:
 	case cop2_op:
diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c
index e4b1140cdae0..3a2b6e9f25cf 100644
--- a/arch/mips/oprofile/op_model_mipsxx.c
+++ b/arch/mips/oprofile/op_model_mipsxx.c
@@ -166,7 +166,7 @@ static void mipsxx_reg_setup(struct op_counter_config *ctr)
 			reg.control[i] |= M_PERFCTL_USER;
 		if (ctr[i].exl)
 			reg.control[i] |= M_PERFCTL_EXL;
-		if (current_cpu_type() == CPU_XLR)
+		if (boot_cpu_type() == CPU_XLR)
 			reg.control[i] |= M_PERFCTL_COUNT_ALL_THREADS;
 		reg.counter[i] = 0x80000000 - ctr[i].count;
 	}
diff --git a/arch/mips/pnx833x/common/platform.c b/arch/mips/pnx833x/common/platform.c
index d22dc0d6f289..2b7e837dc2e2 100644
--- a/arch/mips/pnx833x/common/platform.c
+++ b/arch/mips/pnx833x/common/platform.c
@@ -206,11 +206,13 @@ static struct resource pnx833x_ethernet_resources[] = {
 		.end   = PNX8335_IP3902_PORTS_END,
 		.flags = IORESOURCE_MEM,
 	},
+#ifdef CONFIG_SOC_PNX8335
 	[1] = {
 		.start = PNX8335_PIC_ETHERNET_INT,
 		.end   = PNX8335_PIC_ETHERNET_INT,
 		.flags = IORESOURCE_IRQ,
 	},
+#endif
 };
 
 static struct platform_device pnx833x_ethernet_device = {
diff --git a/arch/mips/powertv/asic/asic_devices.c b/arch/mips/powertv/asic/asic_devices.c
index 9f64c2387808..0238af1ba503 100644
--- a/arch/mips/powertv/asic/asic_devices.c
+++ b/arch/mips/powertv/asic/asic_devices.c
@@ -529,8 +529,7 @@ EXPORT_SYMBOL(asic_resource_get);
  */
 void platform_release_memory(void *ptr, int size)
 {
-	free_reserved_area((unsigned long)ptr, (unsigned long)(ptr + size),
-			   -1, NULL);
+	free_reserved_area(ptr, ptr + size, -1, NULL);
 }
 EXPORT_SYMBOL(platform_release_memory);
 
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 99dbab1c59ac..d60bf98fa5cf 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -55,6 +55,7 @@ config GENERIC_CSUM
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 
diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig
new file mode 100644
index 000000000000..f11006361297
--- /dev/null
+++ b/arch/parisc/configs/c8000_defconfig
@@ -0,0 +1,279 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_FHANDLE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_RELAY=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_RD_LZO=y
+CONFIG_EXPERT=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_BLK_DEV_INTEGRITY=y
+CONFIG_PA8X00=y
+CONFIG_MLONGCALLS=y
+CONFIG_64BIT=y
+CONFIG_SMP=y
+CONFIG_PREEMPT=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_IOMMU_CCIO=y
+CONFIG_PCI=y
+CONFIG_PCI_LBA=y
+# CONFIG_SUPERIO is not set
+# CONFIG_CHASSIS_LCD_LED is not set
+# CONFIG_PDC_CHASSIS is not set
+# CONFIG_PDC_CHASSIS_WARN is not set
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_MISC=m
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=m
+CONFIG_XFRM_SUB_POLICY=y
+CONFIG_NET_KEY=m
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NET_IPIP=m
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_IPCOMP=m
+CONFIG_INET_XFRM_MODE_BEET=m
+CONFIG_INET_DIAG=m
+# CONFIG_IPV6 is not set
+CONFIG_IP_DCCP=m
+# CONFIG_IP_DCCP_CCID3 is not set
+CONFIG_TIPC=m
+CONFIG_LLC2=m
+CONFIG_DNS_RESOLVER=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_STANDALONE is not set
+CONFIG_PARPORT=y
+CONFIG_PARPORT_PC=y
+CONFIG_PARPORT_PC_FIFO=y
+CONFIG_BLK_DEV_UMEM=m
+CONFIG_BLK_DEV_LOOP=m
+CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_BLK_DEV_SX8=m
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=6144
+CONFIG_CDROM_PKTCDVD=m
+CONFIG_CDROM_PKTCDVD_WCACHE=y
+CONFIG_ATA_OVER_ETH=m
+CONFIG_IDE=y
+CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_PLATFORM=y
+CONFIG_BLK_DEV_GENERIC=y
+CONFIG_BLK_DEV_SIIMAGE=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_ST=m
+CONFIG_BLK_DEV_SR=m
+CONFIG_CHR_DEV_SG=y
+CONFIG_CHR_DEV_SCH=m
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_LOGGING=y
+CONFIG_SCSI_FC_ATTRS=y
+CONFIG_SCSI_SAS_LIBSAS=m
+CONFIG_ISCSI_TCP=m
+CONFIG_ISCSI_BOOT_SYSFS=m
+CONFIG_FUSION=y
+CONFIG_FUSION_SPI=y
+CONFIG_FUSION_SAS=y
+CONFIG_NETDEVICES=y
+CONFIG_DUMMY=m
+CONFIG_NETCONSOLE=m
+CONFIG_TUN=y
+CONFIG_E1000=y
+CONFIG_PPP=m
+CONFIG_PPP_BSDCOMP=m
+CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_MPPE=m
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=m
+CONFIG_PPP_SYNC_TTY=m
+# CONFIG_WLAN is not set
+CONFIG_INPUT_FF_MEMLESS=m
+# CONFIG_KEYBOARD_ATKBD is not set
+# CONFIG_KEYBOARD_HIL_OLD is not set
+# CONFIG_KEYBOARD_HIL is not set
+CONFIG_MOUSE_PS2=m
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_CM109=m
+CONFIG_SERIO_SERPORT=m
+CONFIG_SERIO_PARKBD=m
+CONFIG_SERIO_GSCPS2=m
+# CONFIG_HP_SDC is not set
+CONFIG_SERIO_PCIPS2=m
+CONFIG_SERIO_LIBPS2=y
+CONFIG_SERIO_RAW=m
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=8
+CONFIG_SERIAL_8250_RUNTIME_UARTS=8
+CONFIG_SERIAL_8250_EXTENDED=y
+# CONFIG_SERIAL_MUX is not set
+CONFIG_SERIAL_JSM=m
+CONFIG_PRINTER=y
+CONFIG_HW_RANDOM=y
+CONFIG_RAW_DRIVER=m
+CONFIG_PTP_1588_CLOCK=y
+CONFIG_SSB=m
+CONFIG_SSB_DRIVER_PCICORE=y
+CONFIG_AGP=y
+CONFIG_AGP_PARISC=y
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_FOREIGN_ENDIAN=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+# CONFIG_FB_STI is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+# CONFIG_BACKLIGHT_GENERIC is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_STI_CONSOLE is not set
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_SOUND=m
+CONFIG_SND=m
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_MIXER_OSS=m
+CONFIG_SND_PCM_OSS=m
+CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_VERBOSE_PRINTK=y
+CONFIG_SND_AD1889=m
+# CONFIG_SND_USB is not set
+# CONFIG_SND_GSC is not set
+CONFIG_HID_A4TECH=m
+CONFIG_HID_APPLE=m
+CONFIG_HID_BELKIN=m
+CONFIG_HID_CHERRY=m
+CONFIG_HID_CHICONY=m
+CONFIG_HID_CYPRESS=m
+CONFIG_HID_DRAGONRISE=m
+CONFIG_HID_EZKEY=m
+CONFIG_HID_KYE=m
+CONFIG_HID_GYRATION=m
+CONFIG_HID_TWINHAN=m
+CONFIG_HID_KENSINGTON=m
+CONFIG_HID_LOGITECH=m
+CONFIG_HID_LOGITECH_DJ=m
+CONFIG_HID_MICROSOFT=m
+CONFIG_HID_MONTEREY=m
+CONFIG_HID_NTRIG=m
+CONFIG_HID_ORTEK=m
+CONFIG_HID_PANTHERLORD=m
+CONFIG_HID_PETALYNX=m
+CONFIG_HID_SAMSUNG=m
+CONFIG_HID_SUNPLUS=m
+CONFIG_HID_GREENASIA=m
+CONFIG_HID_SMARTJOYPLUS=m
+CONFIG_HID_TOPSEED=m
+CONFIG_HID_THRUSTMASTER=m
+CONFIG_HID_ZEROPLUS=m
+CONFIG_USB_HID=m
+CONFIG_USB=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT2_FS_SECURITY=y
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=m
+CONFIG_REISERFS_FS=m
+CONFIG_REISERFS_PROC_INFO=y
+CONFIG_XFS_FS=m
+CONFIG_XFS_POSIX_ACL=y
+CONFIG_QUOTA=y
+CONFIG_QFMT_V1=m
+CONFIG_QFMT_V2=m
+CONFIG_AUTOFS4_FS=m
+CONFIG_FUSE_FS=m
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_MSDOS_FS=m
+CONFIG_VFAT_FS=m
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_XATTR=y
+CONFIG_NFS_FS=m
+CONFIG_NLS_CODEPAGE_437=m
+CONFIG_NLS_CODEPAGE_737=m
+CONFIG_NLS_CODEPAGE_775=m
+CONFIG_NLS_CODEPAGE_850=m
+CONFIG_NLS_CODEPAGE_852=m
+CONFIG_NLS_CODEPAGE_855=m
+CONFIG_NLS_CODEPAGE_857=m
+CONFIG_NLS_CODEPAGE_860=m
+CONFIG_NLS_CODEPAGE_861=m
+CONFIG_NLS_CODEPAGE_862=m
+CONFIG_NLS_CODEPAGE_863=m
+CONFIG_NLS_CODEPAGE_864=m
+CONFIG_NLS_CODEPAGE_865=m
+CONFIG_NLS_CODEPAGE_866=m
+CONFIG_NLS_CODEPAGE_869=m
+CONFIG_NLS_CODEPAGE_936=m
+CONFIG_NLS_CODEPAGE_950=m
+CONFIG_NLS_CODEPAGE_932=m
+CONFIG_NLS_CODEPAGE_949=m
+CONFIG_NLS_CODEPAGE_874=m
+CONFIG_NLS_ISO8859_8=m
+CONFIG_NLS_CODEPAGE_1250=m
+CONFIG_NLS_CODEPAGE_1251=m
+CONFIG_NLS_ASCII=m
+CONFIG_NLS_ISO8859_1=m
+CONFIG_NLS_ISO8859_2=m
+CONFIG_NLS_ISO8859_3=m
+CONFIG_NLS_ISO8859_4=m
+CONFIG_NLS_ISO8859_5=m
+CONFIG_NLS_ISO8859_6=m
+CONFIG_NLS_ISO8859_7=m
+CONFIG_NLS_ISO8859_9=m
+CONFIG_NLS_ISO8859_13=m
+CONFIG_NLS_ISO8859_14=m
+CONFIG_NLS_ISO8859_15=m
+CONFIG_NLS_KOI8_R=m
+CONFIG_NLS_KOI8_U=m
+CONFIG_NLS_UTF8=m
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_SLAB=y
+CONFIG_DEBUG_SLAB_LEAK=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_RT_MUTEX_TESTER=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_BLOCK_EXT_DEVT=y
+CONFIG_LATENCYTOP=y
+CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
+CONFIG_KEYS=y
+# CONFIG_CRYPTO_HW is not set
+CONFIG_FONTS=y
diff --git a/arch/parisc/include/asm/parisc-device.h b/arch/parisc/include/asm/parisc-device.h
index 9afdad6c2ffb..eaf4dc1c7294 100644
--- a/arch/parisc/include/asm/parisc-device.h
+++ b/arch/parisc/include/asm/parisc-device.h
@@ -23,6 +23,7 @@ struct parisc_device {
 	/* generic info returned from pdc_pat_cell_module() */
 	unsigned long	mod_info;	/* PAT specific - Misc Module info */
 	unsigned long	pmod_loc;	/* physical Module location */
+	unsigned long	mod0;
 #endif
 	u64		dma_mask;	/* DMA mask for I/O */
 	struct device 	dev;
@@ -61,4 +62,6 @@ parisc_get_drvdata(struct parisc_device *d)
 
 extern struct bus_type parisc_bus_type;
 
+int iosapic_serial_irq(struct parisc_device *dev);
+
 #endif /*_ASM_PARISC_PARISC_DEVICE_H_*/
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 2e65aa54bd10..c035673209f7 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -71,18 +71,27 @@ flush_cache_all_local(void)
 }
 EXPORT_SYMBOL(flush_cache_all_local);
 
+/* Virtual address of pfn.  */
+#define pfn_va(pfn)	__va(PFN_PHYS(pfn))
+
 void
 update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
-	struct page *page = pte_page(*ptep);
+	unsigned long pfn = pte_pfn(*ptep);
+	struct page *page;
 
-	if (pfn_valid(page_to_pfn(page)) && page_mapping(page) &&
-	    test_bit(PG_dcache_dirty, &page->flags)) {
+	/* We don't have pte special.  As a result, we can be called with
+	   an invalid pfn and we don't need to flush the kernel dcache page.
+	   This occurs with FireGL card in C8000.  */
+	if (!pfn_valid(pfn))
+		return;
 
-		flush_kernel_dcache_page(page);
+	page = pfn_to_page(pfn);
+	if (page_mapping(page) && test_bit(PG_dcache_dirty, &page->flags)) {
+		flush_kernel_dcache_page_addr(pfn_va(pfn));
 		clear_bit(PG_dcache_dirty, &page->flags);
 	} else if (parisc_requires_coherency())
-		flush_kernel_dcache_page(page);
+		flush_kernel_dcache_page_addr(pfn_va(pfn));
 }
 
 void
@@ -495,44 +504,42 @@ static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr)
 
 void flush_cache_mm(struct mm_struct *mm)
 {
+	struct vm_area_struct *vma;
+	pgd_t *pgd;
+
 	/* Flushing the whole cache on each cpu takes forever on
 	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
-	if (mm_total_size(mm) < parisc_cache_flush_threshold) {
-		struct vm_area_struct *vma;
-
-		if (mm->context == mfsp(3)) {
-			for (vma = mm->mmap; vma; vma = vma->vm_next) {
-				flush_user_dcache_range_asm(vma->vm_start,
-					vma->vm_end);
-				if (vma->vm_flags & VM_EXEC)
-					flush_user_icache_range_asm(
-					  vma->vm_start, vma->vm_end);
-			}
-		} else {
-			pgd_t *pgd = mm->pgd;
-
-			for (vma = mm->mmap; vma; vma = vma->vm_next) {
-				unsigned long addr;
-
-				for (addr = vma->vm_start; addr < vma->vm_end;
-				     addr += PAGE_SIZE) {
-					pte_t *ptep = get_ptep(pgd, addr);
-					if (ptep != NULL) {
-						pte_t pte = *ptep;
-						__flush_cache_page(vma, addr,
-						  page_to_phys(pte_page(pte)));
-					}
-				}
-			}
+	if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
+		flush_cache_all();
+		return;
+	}
+
+	if (mm->context == mfsp(3)) {
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
+			if ((vma->vm_flags & VM_EXEC) == 0)
+				continue;
+			flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
 		}
 		return;
 	}
 
-#ifdef CONFIG_SMP
-	flush_cache_all();
-#else
-	flush_cache_all_local();
-#endif
+	pgd = mm->pgd;
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long addr;
+
+		for (addr = vma->vm_start; addr < vma->vm_end;
+		     addr += PAGE_SIZE) {
+			unsigned long pfn;
+			pte_t *ptep = get_ptep(pgd, addr);
+			if (!ptep)
+				continue;
+			pfn = pte_pfn(*ptep);
+			if (!pfn_valid(pfn))
+				continue;
+			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+		}
+	}
 }
 
 void
@@ -556,33 +563,32 @@ flush_user_icache_range(unsigned long start, unsigned long end)
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
+	unsigned long addr;
+	pgd_t *pgd;
+
 	BUG_ON(!vma->vm_mm->context);
 
-	if ((end - start) < parisc_cache_flush_threshold) {
-		if (vma->vm_mm->context == mfsp(3)) {
-			flush_user_dcache_range_asm(start, end);
-			if (vma->vm_flags & VM_EXEC)
-				flush_user_icache_range_asm(start, end);
-		} else {
-			unsigned long addr;
-			pgd_t *pgd = vma->vm_mm->pgd;
-
-			for (addr = start & PAGE_MASK; addr < end;
-			     addr += PAGE_SIZE) {
-				pte_t *ptep = get_ptep(pgd, addr);
-				if (ptep != NULL) {
-					pte_t pte = *ptep;
-					flush_cache_page(vma,
-					   addr, pte_pfn(pte));
-				}
-			}
-		}
-	} else {
-#ifdef CONFIG_SMP
+	if ((end - start) >= parisc_cache_flush_threshold) {
 		flush_cache_all();
-#else
-		flush_cache_all_local();
-#endif
+		return;
+	}
+
+	if (vma->vm_mm->context == mfsp(3)) {
+		flush_user_dcache_range_asm(start, end);
+		if (vma->vm_flags & VM_EXEC)
+			flush_user_icache_range_asm(start, end);
+		return;
+	}
+
+	pgd = vma->vm_mm->pgd;
+	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+		unsigned long pfn;
+		pte_t *ptep = get_ptep(pgd, addr);
+		if (!ptep)
+			continue;
+		pfn = pte_pfn(*ptep);
+		if (pfn_valid(pfn))
+			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
 	}
 }
 
@@ -591,9 +597,10 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 {
 	BUG_ON(!vma->vm_mm->context);
 
-	flush_tlb_page(vma, vmaddr);
-	__flush_cache_page(vma, vmaddr, page_to_phys(pfn_to_page(pfn)));
-
+	if (pfn_valid(pfn)) {
+		flush_tlb_page(vma, vmaddr);
+		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+	}
 }
 
 #ifdef CONFIG_PARISC_TMPALIAS
diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c
index 3295ef4a185d..f0b6722fc706 100644
--- a/arch/parisc/kernel/inventory.c
+++ b/arch/parisc/kernel/inventory.c
@@ -211,6 +211,7 @@ pat_query_module(ulong pcell_loc, ulong mod_index)
 	/* REVISIT: who is the consumer of this? not sure yet... */
 	dev->mod_info = pa_pdc_cell->mod_info;	/* pass to PAT_GET_ENTITY() */
 	dev->pmod_loc = pa_pdc_cell->mod_location;
+	dev->mod0 = pa_pdc_cell->mod[0];
 
 	register_parisc_device(dev);	/* advertise device */
 
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 940188d1942c..07349b002687 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -56,13 +56,6 @@
 #define A(__x)	((unsigned long)(__x))
 
 /*
- * Atomically swap in the new signal mask, and wait for a signal.
- */
-#ifdef CONFIG_64BIT
-#include "sys32.h"
-#endif
-
-/*
  * Do a signal return - restore sigcontext.
  */
 
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index 33eca1b04926..6c6a271a6140 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -34,7 +34,6 @@
 #include <asm/uaccess.h>
 
 #include "signal32.h"
-#include "sys32.h"
 
 #define DEBUG_COMPAT_SIG 0 
 #define DEBUG_COMPAT_SIG_LEVEL 2
diff --git a/arch/parisc/kernel/sys32.h b/arch/parisc/kernel/sys32.h
deleted file mode 100644
index 60dd470f39f8..000000000000
--- a/arch/parisc/kernel/sys32.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* 
- *    Copyright (C) 2002 Richard Hirst <rhirst at parisc-linux.org>
- *    Copyright (C) 2003 James Bottomley <jejb at parisc-linux.org>
- *    Copyright (C) 2003 Randolph Chung <tausq with parisc-linux.org>
- *
- *    This program is free software; you can redistribute it and/or modify
- *    it under the terms of the GNU General Public License as published by
- *    the Free Software Foundation; either version 2 of the License, or
- *    (at your option) any later version.
- *
- *    This program is distributed in the hope that it will be useful,
- *    but WITHOUT ANY WARRANTY; without even the implied warranty of
- *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *    GNU General Public License for more details.
- *
- *    You should have received a copy of the GNU General Public License
- *    along with this program; if not, write to the Free Software
- *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef _PARISC64_KERNEL_SYS32_H
-#define _PARISC64_KERNEL_SYS32_H
-
-#include <linux/compat.h>
-
-/* Call a kernel syscall which will use kernel space instead of user
- * space for its copy_to/from_user.
- */
-#define KERNEL_SYSCALL(ret, syscall, args...) \
-{ \
-    mm_segment_t old_fs = get_fs(); \
-    set_fs(KERNEL_DS); \
-    ret = syscall(args); \
-    set_fs (old_fs); \
-}
-
-#endif
diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c
index a134ff4da12e..bb9f3b64de55 100644
--- a/arch/parisc/kernel/sys_parisc32.c
+++ b/arch/parisc/kernel/sys_parisc32.c
@@ -42,8 +42,6 @@
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 
-#include "sys32.h"
-
 #undef DEBUG
 
 #ifdef DEBUG
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3bf72cd2c8fc..dbd9d3c991e8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -566,7 +566,7 @@ config SCHED_SMT
 config PPC_DENORMALISATION
 	bool "PowerPC denormalisation exception handling"
 	depends on PPC_BOOK3S_64
-	default "n"
+	default "y" if PPC_POWERNV
 	---help---
 	  Add support for handling denormalisation of single precision
 	  values.  Useful for bare metal only.  If unsure say Y here.
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index c86fcb92358e..0e8cfd09da2f 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -58,7 +58,7 @@ CONFIG_SCHED_SMT=y
 CONFIG_PPC_DENORMALISATION=y
 CONFIG_PCCARD=y
 CONFIG_ELECTRA_CF=y
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_RPA=m
 CONFIG_HOTPLUG_PCI_RPA_DLPAR=m
 CONFIG_PACKET=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 4b20f76172e2..0085dc4642c5 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -32,7 +32,7 @@ CONFIG_IRQ_ALL_CPUS=y
 CONFIG_SPARSEMEM_MANUAL=y
 CONFIG_PCI_MSI=y
 CONFIG_PCCARD=y
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_XFRM_USER=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index bea8587c3af5..1d4b9763895d 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -53,7 +53,7 @@ CONFIG_PPC_64K_PAGES=y
 CONFIG_PPC_SUBPAGE_PROT=y
 CONFIG_SCHED_SMT=y
 CONFIG_PPC_DENORMALISATION=y
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_RPA=m
 CONFIG_HOTPLUG_PCI_RPA_DLPAR=m
 CONFIG_PACKET=y
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 09a8743143f3..d3e5e9bc8f94 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -55,6 +55,8 @@ struct device_node;
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
 #define EEH_PE_PHB_DEAD		(1 << 2)	/* Dead PHB		*/
 
+#define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
+
 struct eeh_pe {
 	int type;			/* PE type: PHB/Bus/Device	*/
 	int state;			/* PE EEH dependent mode	*/
@@ -72,8 +74,8 @@ struct eeh_pe {
 	struct list_head child;		/* Child PEs			*/
 };
 
-#define eeh_pe_for_each_dev(pe, edev) \
-		list_for_each_entry(edev, &pe->edevs, list)
+#define eeh_pe_for_each_dev(pe, edev, tmp) \
+		list_for_each_entry_safe(edev, tmp, &pe->edevs, list)
 
 /*
  * The struct is used to trace EEH state for the associated
@@ -82,7 +84,13 @@ struct eeh_pe {
  * another tree except the currently existing tree of PCI
  * buses and PCI devices
  */
-#define EEH_DEV_IRQ_DISABLED	(1<<0)	/* Interrupt disabled		*/
+#define EEH_DEV_BRIDGE		(1 << 0)	/* PCI bridge		*/
+#define EEH_DEV_ROOT_PORT	(1 << 1)	/* PCIe root port	*/
+#define EEH_DEV_DS_PORT		(1 << 2)	/* Downstream port	*/
+#define EEH_DEV_IRQ_DISABLED	(1 << 3)	/* Interrupt disabled	*/
+#define EEH_DEV_DISCONNECTED	(1 << 4)	/* Removing from PE	*/
+
+#define EEH_DEV_SYSFS		(1 << 8)	/* Sysfs created        */
 
 struct eeh_dev {
 	int mode;			/* EEH mode			*/
@@ -90,11 +98,13 @@ struct eeh_dev {
 	int config_addr;		/* Config address		*/
 	int pe_config_addr;		/* PE config address		*/
 	u32 config_space[16];		/* Saved PCI config space	*/
+	u8 pcie_cap;			/* Saved PCIe capability	*/
 	struct eeh_pe *pe;		/* Associated PE		*/
 	struct list_head list;		/* Form link list in the PE	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
 	struct device_node *dn;		/* Associated device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
+	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
 
 static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
@@ -193,8 +203,10 @@ int eeh_phb_pe_create(struct pci_controller *phb);
 struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
 struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
 int eeh_add_to_parent_pe(struct eeh_dev *edev);
-int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe);
+int eeh_rmv_from_parent_pe(struct eeh_dev *edev);
 void eeh_pe_update_time_stamp(struct eeh_pe *pe);
+void *eeh_pe_traverse(struct eeh_pe *root,
+		eeh_traverse_func fn, void *flag);
 void *eeh_pe_dev_traverse(struct eeh_pe *root,
 		eeh_traverse_func fn, void *flag);
 void eeh_pe_restore_bars(struct eeh_pe *pe);
@@ -209,10 +221,12 @@ unsigned long eeh_check_failure(const volatile void __iomem *token,
 				unsigned long val);
 int eeh_dev_check_failure(struct eeh_dev *edev);
 void eeh_addr_cache_build(void);
+void eeh_add_device_early(struct device_node *);
 void eeh_add_device_tree_early(struct device_node *);
+void eeh_add_device_late(struct pci_dev *);
 void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_add_sysfs_files(struct pci_bus *);
-void eeh_remove_bus_device(struct pci_dev *, int);
+void eeh_remove_device(struct pci_dev *);
 
 /**
  * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
@@ -252,13 +266,17 @@ static inline unsigned long eeh_check_failure(const volatile void __iomem *token
 
 static inline void eeh_addr_cache_build(void) { }
 
+static inline void eeh_add_device_early(struct device_node *dn) { }
+
 static inline void eeh_add_device_tree_early(struct device_node *dn) { }
 
+static inline void eeh_add_device_late(struct pci_dev *dev) { }
+
 static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
 
 static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
 
-static inline void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe) { }
+static inline void eeh_remove_device(struct pci_dev *dev) { }
 
 #define EEH_POSSIBLE_ERROR(val, type) (0)
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index ba713f166fa5..10be1dd01c6b 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -96,10 +96,11 @@ static inline bool arch_irqs_disabled(void)
 #endif
 
 #define hard_irq_disable()	do {			\
-	u8 _was_enabled = get_paca()->soft_enabled;	\
+	u8 _was_enabled;				\
 	__hard_irq_disable();				\
-	get_paca()->soft_enabled = 0;			\
-	get_paca()->irq_happened |= PACA_IRQ_HARD_DIS;	\
+	_was_enabled = local_paca->soft_enabled;	\
+	local_paca->soft_enabled = 0;			\
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;	\
 	if (_was_enabled)				\
 		trace_hardirqs_off();			\
 } while(0)
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index c1df590ec444..49fa55bfbac4 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -82,10 +82,9 @@ struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
 		   struct exception_table_entry *finish);
 
-#ifdef CONFIG_MODVERSIONS
+#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64)
 #define ARCH_RELOCATES_KCRCTAB
-
-extern const unsigned long reloc_start[];
+#define reloc_start PHYSICAL_START
 #endif
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_MODULE_H */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 2c1d8cb9b265..32d0d2018faf 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -209,7 +209,6 @@ static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn)
 extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn);
 
 /** Remove all of the PCI devices under this bus */
-extern void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe);
 extern void pcibios_remove_pci_devices(struct pci_bus *bus);
 
 /** Discover new pci devices under this bus, and add them */
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 2dd7bfc459be..8b2492644754 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <asm/hw_irq.h>
 #include <linux/device.h>
+#include <uapi/asm/perf_event.h>
 
 #define MAX_HWEVENTS		8
 #define MAX_EVENT_ALTERNATIVES	8
@@ -69,11 +70,6 @@ struct power_pmu {
 #define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
 #define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
 
-/*
- * We use the event config bit 63 as a flag to request EBB.
- */
-#define EVENT_CONFIG_EBB_SHIFT	63
-
 extern int register_power_pmu(struct power_pmu *);
 
 struct pt_regs;
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 47a35b08b963..e378cccfca55 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -247,6 +247,10 @@ struct thread_struct {
 	unsigned long	tm_orig_msr;	/* Thread's MSR on ctx switch */
 	struct pt_regs	ckpt_regs;	/* Checkpointed registers */
 
+	unsigned long	tm_tar;
+	unsigned long	tm_ppr;
+	unsigned long	tm_dscr;
+
 	/*
 	 * Transactional FP and VSX 0-31 register set.
 	 * NOTE: the sense of these is the opposite of the integer ckpt_regs!
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 5d7d9c2a5473..99222e27f173 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -254,19 +254,28 @@
 #define SPRN_HRMOR	0x139	/* Real mode offset register */
 #define SPRN_HSRR0	0x13A	/* Hypervisor Save/Restore 0 */
 #define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
+/* HFSCR and FSCR bit numbers are the same */
+#define FSCR_TAR_LG	8	/* Enable Target Address Register */
+#define FSCR_EBB_LG	7	/* Enable Event Based Branching */
+#define FSCR_TM_LG	5	/* Enable Transactional Memory */
+#define FSCR_PM_LG	4	/* Enable prob/priv access to PMU SPRs */
+#define FSCR_BHRB_LG	3	/* Enable Branch History Rolling Buffer*/
+#define FSCR_DSCR_LG	2	/* Enable Data Stream Control Register */
+#define FSCR_VECVSX_LG	1	/* Enable VMX/VSX  */
+#define FSCR_FP_LG	0	/* Enable Floating Point */
 #define SPRN_FSCR	0x099	/* Facility Status & Control Register */
-#define   FSCR_TAR	(1 << (63-55)) /* Enable Target Address Register */
-#define   FSCR_EBB	(1 << (63-56)) /* Enable Event Based Branching */
-#define   FSCR_DSCR	(1 << (63-61)) /* Enable Data Stream Control Register */
+#define   FSCR_TAR	__MASK(FSCR_TAR_LG)
+#define   FSCR_EBB	__MASK(FSCR_EBB_LG)
+#define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
-#define   HFSCR_TAR	(1 << (63-55)) /* Enable Target Address Register */
-#define   HFSCR_EBB	(1 << (63-56)) /* Enable Event Based Branching */
-#define   HFSCR_TM	(1 << (63-58)) /* Enable Transactional Memory */
-#define   HFSCR_PM	(1 << (63-60)) /* Enable prob/priv access to PMU SPRs */
-#define   HFSCR_BHRB	(1 << (63-59)) /* Enable Branch History Rolling Buffer*/
-#define   HFSCR_DSCR	(1 << (63-61)) /* Enable Data Stream Control Register */
-#define   HFSCR_VECVSX	(1 << (63-62)) /* Enable VMX/VSX  */
-#define   HFSCR_FP	(1 << (63-63)) /* Enable Floating Point */
+#define   HFSCR_TAR	__MASK(FSCR_TAR_LG)
+#define   HFSCR_EBB	__MASK(FSCR_EBB_LG)
+#define   HFSCR_TM	__MASK(FSCR_TM_LG)
+#define   HFSCR_PM	__MASK(FSCR_PM_LG)
+#define   HFSCR_BHRB	__MASK(FSCR_BHRB_LG)
+#define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
+#define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
+#define   HFSCR_FP	__MASK(FSCR_FP_LG)
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0	(1ul << (63-0))
@@ -1088,7 +1097,8 @@
 #define PVR_970MP	0x0044
 #define PVR_970GX	0x0045
 #define PVR_POWER7p	0x004A
-#define PVR_POWER8	0x004B
+#define PVR_POWER8E	0x004B
+#define PVR_POWER8	0x004D
 #define PVR_BE		0x0070
 #define PVR_PA6T	0x0090
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ffbaabebcdca..48cfc858abd6 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -145,6 +145,10 @@ extern void __cpu_die(unsigned int cpu);
 #define smp_setup_cpu_maps()
 static inline void inhibit_secondary_onlining(void) {}
 static inline void uninhibit_secondary_onlining(void) {}
+static inline const struct cpumask *cpu_sibling_mask(int cpu)
+{
+	return cpumask_of(cpu);
+}
 
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 49a13e0ef234..294c2cedcf7a 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -15,6 +15,15 @@ extern struct task_struct *__switch_to(struct task_struct *,
 struct thread_struct;
 extern struct task_struct *_switch(struct thread_struct *prev,
 				   struct thread_struct *next);
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline void save_tar(struct thread_struct *prev)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		prev->tar = mfspr(SPRN_TAR);
+}
+#else
+static inline void save_tar(struct thread_struct *prev) {}
+#endif
 
 extern void giveup_fpu(struct task_struct *);
 extern void load_up_fpu(void);
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 5182c8622b54..48be855ef37b 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -20,6 +20,7 @@ header-y += mman.h
 header-y += msgbuf.h
 header-y += nvram.h
 header-y += param.h
+header-y += perf_event.h
 header-y += poll.h
 header-y += posix_types.h
 header-y += ps3fb.h
diff --git a/arch/powerpc/include/uapi/asm/perf_event.h b/arch/powerpc/include/uapi/asm/perf_event.h
new file mode 100644
index 000000000000..80a4d40cf5bc
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/perf_event.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright 2013 Michael Ellerman, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2 of the
+ * License.
+ */
+
+#ifndef _UAPI_ASM_POWERPC_PERF_EVENT_H
+#define _UAPI_ASM_POWERPC_PERF_EVENT_H
+
+/*
+ * We use bit 63 of perf_event_attr.config as a flag to request EBB.
+ */
+#define PERF_EVENT_CONFIG_EBB_SHIFT	63
+
+#endif /* _UAPI_ASM_POWERPC_PERF_EVENT_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c7e8afc2ead0..8207459efe56 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -138,6 +138,9 @@ int main(void)
 	DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
 	DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
 	DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+	DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar));
+	DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
+	DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
 	DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
 	DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
 					 transact_vr[0]));
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 2a45d0f04385..22973a74df73 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -494,9 +494,27 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_restore		= __restore_cpu_power7,
 		.platform		= "power7+",
 	},
-	{	/* Power8 */
+	{	/* Power8E */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x004b0000,
+		.cpu_name		= "POWER8E (raw)",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.platform		= "power8",
+	},
+	{	/* Power8 */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x004d0000,
 		.cpu_name		= "POWER8 (raw)",
 		.cpu_features		= CPU_FTRS_POWER8,
 		.cpu_user_features	= COMMON_USER_POWER8,
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 39954fe941b8..55593ee2d5aa 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -231,7 +231,7 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
 void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 {
 	size_t loglen = 0;
-	struct eeh_dev *edev;
+	struct eeh_dev *edev, *tmp;
 	bool valid_cfg_log = true;
 
 	/*
@@ -251,7 +251,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 		eeh_pe_restore_bars(pe);
 
 		pci_regs_buf[0] = 0;
-		eeh_pe_for_each_dev(pe, edev) {
+		eeh_pe_for_each_dev(pe, edev, tmp) {
 			loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
 						      EEH_PCI_REGS_LOG_LEN - loglen);
 		}
@@ -499,8 +499,6 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
 	}
 
 	eeh_dev_check_failure(edev);
-
-	pci_dev_put(eeh_dev_to_pci_dev(edev));
 	return val;
 }
 
@@ -838,7 +836,7 @@ core_initcall_sync(eeh_init);
  * on the CEC architecture, type of the device, on earlier boot
  * command-line arguments & etc.
  */
-static void eeh_add_device_early(struct device_node *dn)
+void eeh_add_device_early(struct device_node *dn)
 {
 	struct pci_controller *phb;
 
@@ -886,7 +884,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
  * This routine must be used to complete EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
  */
-static void eeh_add_device_late(struct pci_dev *dev)
+void eeh_add_device_late(struct pci_dev *dev)
 {
 	struct device_node *dn;
 	struct eeh_dev *edev;
@@ -902,9 +900,23 @@ static void eeh_add_device_late(struct pci_dev *dev)
 		pr_debug("EEH: Already referenced !\n");
 		return;
 	}
-	WARN_ON(edev->pdev);
 
-	pci_dev_get(dev);
+	/*
+	 * The EEH cache might not be removed correctly because of
+	 * unbalanced kref to the device during unplug time, which
+	 * relies on pcibios_release_device(). So we have to remove
+	 * that here explicitly.
+	 */
+	if (edev->pdev) {
+		eeh_rmv_from_parent_pe(edev);
+		eeh_addr_cache_rmv_dev(edev->pdev);
+		eeh_sysfs_remove_device(edev->pdev);
+		edev->mode &= ~EEH_DEV_SYSFS;
+
+		edev->pdev = NULL;
+		dev->dev.archdata.edev = NULL;
+	}
+
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
@@ -967,7 +979,6 @@ EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
 /**
  * eeh_remove_device - Undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
- * @purge_pe: remove the PE or not
  *
  * This routine should be called when a device is removed from
  * a running system (e.g. by hotplug or dlpar).  It unregisters
@@ -975,7 +986,7 @@ EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
  * this device will no longer be detected after this call; thus,
  * i/o errors affecting this slot may leave this device unusable.
  */
-static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
+void eeh_remove_device(struct pci_dev *dev)
 {
 	struct eeh_dev *edev;
 
@@ -986,42 +997,29 @@ static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
 	/* Unregister the device with the EEH/PCI address search system */
 	pr_debug("EEH: Removing device %s\n", pci_name(dev));
 
-	if (!edev || !edev->pdev) {
+	if (!edev || !edev->pdev || !edev->pe) {
 		pr_debug("EEH: Not referenced !\n");
 		return;
 	}
+
+	/*
+	 * During the hotplug for EEH error recovery, we need the EEH
+	 * device attached to the parent PE in order for BAR restore
+	 * a bit later. So we keep it for BAR restore and remove it
+	 * from the parent PE during the BAR resotre.
+	 */
 	edev->pdev = NULL;
 	dev->dev.archdata.edev = NULL;
-	pci_dev_put(dev);
+	if (!(edev->pe->state & EEH_PE_KEEP))
+		eeh_rmv_from_parent_pe(edev);
+	else
+		edev->mode |= EEH_DEV_DISCONNECTED;
 
-	eeh_rmv_from_parent_pe(edev, purge_pe);
 	eeh_addr_cache_rmv_dev(dev);
 	eeh_sysfs_remove_device(dev);
+	edev->mode &= ~EEH_DEV_SYSFS;
 }
 
-/**
- * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device
- * @dev: PCI device
- * @purge_pe: remove the corresponding PE or not
- *
- * This routine must be called when a device is removed from the
- * running system through hotplug or dlpar. The corresponding
- * PCI address cache will be removed.
- */
-void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe)
-{
-	struct pci_bus *bus = dev->subordinate;
-	struct pci_dev *child, *tmp;
-
-	eeh_remove_device(dev, purge_pe);
-
-	if (bus && dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		list_for_each_entry_safe(child, tmp, &bus->devices, bus_list)
-			 eeh_remove_bus_device(child, purge_pe);
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_remove_bus_device);
-
 static int proc_eeh_show(struct seq_file *m, void *v)
 {
 	if (0 == eeh_subsystem_enabled) {
@@ -1063,7 +1061,7 @@ static const struct file_operations proc_eeh_operations = {
 
 static int __init eeh_init_proc(void)
 {
-	if (machine_is(pseries))
+	if (machine_is(pseries) || machine_is(powernv))
 		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
 	return 0;
 }
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index f9ac1232a746..e8c9fd546a5c 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -68,16 +68,12 @@ static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr)
 		struct pci_io_addr_range *piar;
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
 
-		if (addr < piar->addr_lo) {
+		if (addr < piar->addr_lo)
 			n = n->rb_left;
-		} else {
-			if (addr > piar->addr_hi) {
-				n = n->rb_right;
-			} else {
-				pci_dev_get(piar->pcidev);
-				return piar->edev;
-			}
-		}
+		else if (addr > piar->addr_hi)
+			n = n->rb_right;
+		else
+			return piar->edev;
 	}
 
 	return NULL;
@@ -156,7 +152,6 @@ eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 	if (!piar)
 		return NULL;
 
-	pci_dev_get(dev);
 	piar->addr_lo = alo;
 	piar->addr_hi = ahi;
 	piar->edev = pci_dev_to_eeh_dev(dev);
@@ -250,7 +245,6 @@ restart:
 
 		if (piar->pcidev == dev) {
 			rb_erase(n, &pci_io_addr_cache_root.rb_root);
-			pci_dev_put(piar->pcidev);
 			kfree(piar);
 			goto restart;
 		}
@@ -302,12 +296,10 @@ void eeh_addr_cache_build(void)
 		if (!edev)
 			continue;
 
-		pci_dev_get(dev);  /* matching put is in eeh_remove_device() */
 		dev->dev.archdata.edev = edev;
 		edev->pdev = dev;
 
 		eeh_addr_cache_insert_dev(dev);
-
 		eeh_sysfs_add_device(dev);
 	}
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 2b1ce17cae50..36bed5a12750 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -143,10 +143,14 @@ static void eeh_disable_irq(struct pci_dev *dev)
 static void eeh_enable_irq(struct pci_dev *dev)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+	struct irq_desc *desc;
 
 	if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
 		edev->mode &= ~EEH_DEV_IRQ_DISABLED;
-		enable_irq(dev->irq);
+
+		desc = irq_to_desc(dev->irq);
+		if (desc && desc->depth > 0)
+			enable_irq(dev->irq);
 	}
 }
 
@@ -338,6 +342,54 @@ static void *eeh_report_failure(void *data, void *userdata)
 	return NULL;
 }
 
+static void *eeh_rmv_device(void *data, void *userdata)
+{
+	struct pci_driver *driver;
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	int *removed = (int *)userdata;
+
+	/*
+	 * Actually, we should remove the PCI bridges as well.
+	 * However, that's lots of complexity to do that,
+	 * particularly some of devices under the bridge might
+	 * support EEH. So we just care about PCI devices for
+	 * simplicity here.
+	 */
+	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
+		return NULL;
+	driver = eeh_pcid_get(dev);
+	if (driver && driver->err_handler)
+		return NULL;
+
+	/* Remove it from PCI subsystem */
+	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
+		 pci_name(dev));
+	edev->bus = dev->bus;
+	edev->mode |= EEH_DEV_DISCONNECTED;
+	(*removed)++;
+
+	pci_stop_and_remove_bus_device(dev);
+
+	return NULL;
+}
+
+static void *eeh_pe_detach_dev(void *data, void *userdata)
+{
+	struct eeh_pe *pe = (struct eeh_pe *)data;
+	struct eeh_dev *edev, *tmp;
+
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		if (!(edev->mode & EEH_DEV_DISCONNECTED))
+			continue;
+
+		edev->mode &= ~(EEH_DEV_DISCONNECTED | EEH_DEV_IRQ_DISABLED);
+		eeh_rmv_from_parent_pe(edev);
+	}
+
+	return NULL;
+}
+
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
  * @pe: EEH PE
@@ -349,8 +401,9 @@ static void *eeh_report_failure(void *data, void *userdata)
  */
 static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 {
+	struct pci_bus *frozen_bus = eeh_pe_bus_get(pe);
 	struct timeval tstamp;
-	int cnt, rc;
+	int cnt, rc, removed = 0;
 
 	/* pcibios will clear the counter; save the value */
 	cnt = pe->freeze_count;
@@ -362,8 +415,11 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * devices are expected to be attached soon when calling
 	 * into pcibios_add_pci_devices().
 	 */
+	eeh_pe_state_mark(pe, EEH_PE_KEEP);
 	if (bus)
-		__pcibios_remove_pci_devices(bus, 0);
+		pcibios_remove_pci_devices(bus);
+	else if (frozen_bus)
+		eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
 
 	/* Reset the pci controller. (Asserts RST#; resets config space).
 	 * Reconfigure bridges and devices. Don't try to bring the system
@@ -384,9 +440,24 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * potentially weird things happen.
 	 */
 	if (bus) {
+		pr_info("EEH: Sleep 5s ahead of complete hotplug\n");
 		ssleep(5);
+
+		/*
+		 * The EEH device is still connected with its parent
+		 * PE. We should disconnect it so the binding can be
+		 * rebuilt when adding PCI devices.
+		 */
+		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
 		pcibios_add_pci_devices(bus);
+	} else if (frozen_bus && removed) {
+		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
+		ssleep(5);
+
+		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
+		pcibios_add_pci_devices(frozen_bus);
 	}
+	eeh_pe_state_clear(pe, EEH_PE_KEEP);
 
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 016588a6f5ed..f9450537e335 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -149,8 +149,8 @@ static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
  * callback returns something other than NULL, or no more PEs
  * to be traversed.
  */
-static void *eeh_pe_traverse(struct eeh_pe *root,
-			eeh_traverse_func fn, void *flag)
+void *eeh_pe_traverse(struct eeh_pe *root,
+		      eeh_traverse_func fn, void *flag)
 {
 	struct eeh_pe *pe;
 	void *ret;
@@ -176,7 +176,7 @@ void *eeh_pe_dev_traverse(struct eeh_pe *root,
 		eeh_traverse_func fn, void *flag)
 {
 	struct eeh_pe *pe;
-	struct eeh_dev *edev;
+	struct eeh_dev *edev, *tmp;
 	void *ret;
 
 	if (!root) {
@@ -186,7 +186,7 @@ void *eeh_pe_dev_traverse(struct eeh_pe *root,
 
 	/* Traverse root PE */
 	for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
-		eeh_pe_for_each_dev(pe, edev) {
+		eeh_pe_for_each_dev(pe, edev, tmp) {
 			ret = fn(edev, flag);
 			if (ret)
 				return ret;
@@ -333,7 +333,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 		while (parent) {
 			if (!(parent->type & EEH_PE_INVALID))
 				break;
-			parent->type &= ~EEH_PE_INVALID;
+			parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP);
 			parent = parent->parent;
 		}
 		pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
@@ -397,21 +397,20 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 /**
  * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE
  * @edev: EEH device
- * @purge_pe: remove PE or not
  *
  * The PE hierarchy tree might be changed when doing PCI hotplug.
  * Also, the PCI devices or buses could be removed from the system
  * during EEH recovery. So we have to call the function remove the
  * corresponding PE accordingly if necessary.
  */
-int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe)
+int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 {
 	struct eeh_pe *pe, *parent, *child;
 	int cnt;
 
 	if (!edev->pe) {
-		pr_warning("%s: No PE found for EEH device %s\n",
-			__func__, edev->dn->full_name);
+		pr_debug("%s: No PE found for EEH device %s\n",
+			 __func__, edev->dn->full_name);
 		return -EEXIST;
 	}
 
@@ -431,7 +430,7 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe)
 		if (pe->type & EEH_PE_PHB)
 			break;
 
-		if (purge_pe) {
+		if (!(pe->state & EEH_PE_KEEP)) {
 			if (list_empty(&pe->edevs) &&
 			    list_empty(&pe->child_list)) {
 				list_del(&pe->child);
@@ -502,7 +501,7 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
 	int state = *((int *)flag);
-	struct eeh_dev *tmp;
+	struct eeh_dev *edev, *tmp;
 	struct pci_dev *pdev;
 
 	/*
@@ -512,8 +511,8 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 	 * the PCI device driver.
 	 */
 	pe->state |= state;
-	eeh_pe_for_each_dev(pe, tmp) {
-		pdev = eeh_dev_to_pci_dev(tmp);
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdev = eeh_dev_to_pci_dev(edev);
 		if (pdev)
 			pdev->error_state = pci_channel_io_frozen;
 	}
@@ -579,7 +578,7 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state)
  * blocked on normal path during the stage. So we need utilize
  * eeh operations, which is always permitted.
  */
-static void eeh_bridge_check_link(struct pci_dev *pdev,
+static void eeh_bridge_check_link(struct eeh_dev *edev,
 				  struct device_node *dn)
 {
 	int cap;
@@ -590,16 +589,17 @@ static void eeh_bridge_check_link(struct pci_dev *pdev,
 	 * We only check root port and downstream ports of
 	 * PCIe switches
 	 */
-	if (!pci_is_pcie(pdev) ||
-	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
-	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
+	if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT)))
 		return;
 
-	pr_debug("%s: Check PCIe link for %s ...\n",
-		 __func__, pci_name(pdev));
+	pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n",
+		 __func__, edev->phb->global_number,
+		 edev->config_addr >> 8,
+		 PCI_SLOT(edev->config_addr & 0xFF),
+		 PCI_FUNC(edev->config_addr & 0xFF));
 
 	/* Check slot status */
-	cap = pdev->pcie_cap;
+	cap = edev->pcie_cap;
 	eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
 	if (!(val & PCI_EXP_SLTSTA_PDS)) {
 		pr_debug("  No card in the slot (0x%04x) !\n", val);
@@ -653,8 +653,7 @@ static void eeh_bridge_check_link(struct pci_dev *pdev,
 #define BYTE_SWAP(OFF)	(8*((OFF)/4)+3-(OFF))
 #define SAVED_BYTE(OFF)	(((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
 
-static void eeh_restore_bridge_bars(struct pci_dev *pdev,
-				    struct eeh_dev *edev,
+static void eeh_restore_bridge_bars(struct eeh_dev *edev,
 				    struct device_node *dn)
 {
 	int i;
@@ -680,7 +679,7 @@ static void eeh_restore_bridge_bars(struct pci_dev *pdev,
 	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
 
 	/* Check the PCIe link is ready */
-	eeh_bridge_check_link(pdev, dn);
+	eeh_bridge_check_link(edev, dn);
 }
 
 static void eeh_restore_device_bars(struct eeh_dev *edev,
@@ -729,19 +728,12 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
  */
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
-	struct pci_dev *pdev = NULL;
 	struct eeh_dev *edev = (struct eeh_dev *)data;
 	struct device_node *dn = eeh_dev_to_of_node(edev);
 
-	/* Trace the PCI bridge */
-	if (eeh_probe_mode_dev()) {
-		pdev = eeh_dev_to_pci_dev(edev);
-		if (pdev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
-                        pdev = NULL;
-        }
-
-	if (pdev)
-		eeh_restore_bridge_bars(pdev, edev, dn);
+	/* Do special restore for bridges */
+	if (edev->mode & EEH_DEV_BRIDGE)
+		eeh_restore_bridge_bars(edev, dn);
 	else
 		eeh_restore_device_bars(edev, dn);
 
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index e7ae3484918c..5d753d4f2c75 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -56,19 +56,40 @@ EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
 
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
 	int rc=0;
 
+	if (edev && (edev->mode & EEH_DEV_SYSFS))
+		return;
+
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 
 	if (rc)
 		printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
+	else if (edev)
+		edev->mode |= EEH_DEV_SYSFS;
 }
 
 void eeh_sysfs_remove_device(struct pci_dev *pdev)
 {
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+	/*
+	 * The parent directory might have been removed. We needn't
+	 * continue for that case.
+	 */
+	if (!pdev->dev.kobj.sd) {
+		if (edev)
+			edev->mode &= ~EEH_DEV_SYSFS;
+		return;
+	}
+
 	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+
+	if (edev)
+		edev->mode &= ~EEH_DEV_SYSFS;
 }
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index ab15b8d057ad..2bd0b885b0fe 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -449,15 +449,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 BEGIN_FTR_SECTION
-	/*
-	 * Back up the TAR across context switches.  Note that the TAR is not
-	 * available for use in the kernel.  (To provide this, the TAR should
-	 * be backed up/restored on exception entry/exit instead, and be in
-	 * pt_regs.  FIXME, this should be in pt_regs anyway (for debug).)
-	 */
-	mfspr	r0,SPRN_TAR
-	std	r0,THREAD_TAR(r3)
-
 	/* Event based branch registers */
 	mfspr	r0, SPRN_BESCR
 	std	r0, THREAD_BESCR(r3)
@@ -584,9 +575,34 @@ BEGIN_FTR_SECTION
 	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
 	cmpwi	r6,0
+	li	r8, FSCR_DSCR
 	bne	1f
 	ld	r0,0(r7)
-1:	cmpd	r0,r25
+	b	3f
+1:
+  BEGIN_FTR_SECTION_NESTED(70)
+	mfspr	r6, SPRN_FSCR
+	or	r6, r6, r8
+	mtspr	SPRN_FSCR, r6
+    BEGIN_FTR_SECTION_NESTED(69)
+	mfspr	r6, SPRN_HFSCR
+	or	r6, r6, r8
+	mtspr	SPRN_HFSCR, r6
+    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+	b	4f
+  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+3:
+  BEGIN_FTR_SECTION_NESTED(70)
+	mfspr	r6, SPRN_FSCR
+	andc	r6, r6, r8
+	mtspr	SPRN_FSCR, r6
+    BEGIN_FTR_SECTION_NESTED(69)
+	mfspr	r6, SPRN_HFSCR
+	andc	r6, r6, r8
+	mtspr	SPRN_HFSCR, r6
+    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+4:	cmpd	r0,r25
 	beq	2f
 	mtspr	SPRN_DSCR,r0
 2:
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4e00d223b2e3..902ca3c6b4b6 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -848,7 +848,7 @@ hv_facility_unavailable_relon_trampoline:
 	. = 0x4f80
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	facility_unavailable_relon_hv
+	b	hv_facility_unavailable_relon_hv
 
 	STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint)
 #ifdef CONFIG_PPC_DENORMALISATION
@@ -1175,6 +1175,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	b	.ret_from_except
 
 	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
+	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception)
 
 	.align	7
 	.globl	__end_handlers
@@ -1188,7 +1189,7 @@ __end_handlers:
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
-	STD_RELON_EXCEPTION_HV_OOL(0xf80, facility_unavailable)
+	STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2e51cde616d2..c69440cef7af 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -362,7 +362,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
 	seq_printf(p, "  Spurious interrupts\n");
 
-	seq_printf(p, "%*s: ", prec, "CNT");
+	seq_printf(p, "%*s: ", prec, "PMI");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
 	seq_printf(p, "  Performance monitoring interrupts\n");
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f46914a0f33e..7d22a675fe1a 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1462,6 +1462,8 @@ void pcibios_finish_adding_to_bus(struct pci_bus *bus)
 	/* Allocate bus and devices resources */
 	pcibios_allocate_bus_resources(bus);
 	pcibios_claim_one_bus(bus);
+	if (!pci_has_flag(PCI_PROBE_ONLY))
+		pci_assign_unassigned_bus_resources(bus);
 
 	/* Fixup EEH */
 	eeh_add_device_tree_late(bus);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 3f608800c06b..c1e17ae68a08 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -22,45 +22,40 @@
 #include <asm/eeh.h>
 
 /**
- * __pcibios_remove_pci_devices - remove all devices under this bus
+ * pcibios_release_device - release PCI device
+ * @dev: PCI device
+ *
+ * The function is called before releasing the indicated PCI device.
+ */
+void pcibios_release_device(struct pci_dev *dev)
+{
+	eeh_remove_device(dev);
+}
+
+/**
+ * pcibios_remove_pci_devices - remove all devices under this bus
  * @bus: the indicated PCI bus
- * @purge_pe: destroy the PE on removal of PCI devices
  *
  * Remove all of the PCI devices under this bus both from the
  * linux pci device tree, and from the powerpc EEH address cache.
- * By default, the corresponding PE will be destroied during the
- * normal PCI hotplug path. For PCI hotplug during EEH recovery,
- * the corresponding PE won't be destroied and deallocated.
  */
-void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe)
+void pcibios_remove_pci_devices(struct pci_bus *bus)
 {
 	struct pci_dev *dev, *tmp;
 	struct pci_bus *child_bus;
 
 	/* First go down child busses */
 	list_for_each_entry(child_bus, &bus->children, node)
-		__pcibios_remove_pci_devices(child_bus, purge_pe);
+		pcibios_remove_pci_devices(child_bus);
 
 	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
 		 pci_domain_nr(bus),  bus->number);
 	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
-		pr_debug("     * Removing %s...\n", pci_name(dev));
-		eeh_remove_bus_device(dev, purge_pe);
+		pr_debug("   Removing %s...\n", pci_name(dev));
 		pci_stop_and_remove_bus_device(dev);
 	}
 }
 
-/**
- * pcibios_remove_pci_devices - remove all devices under this bus
- * @bus: the indicated PCI bus
- *
- * Remove all of the PCI devices under this bus both from the
- * linux pci device tree, and from the powerpc EEH address cache.
- */
-void pcibios_remove_pci_devices(struct pci_bus *bus)
-{
-	__pcibios_remove_pci_devices(bus, 1);
-}
 EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
 
 /**
@@ -76,7 +71,7 @@ EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
  */
 void pcibios_add_pci_devices(struct pci_bus * bus)
 {
-	int slotno, num, mode, pass, max;
+	int slotno, mode, pass, max;
 	struct pci_dev *dev;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
@@ -90,11 +85,15 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 		/* use ofdt-based probe */
 		of_rescan_bus(dn, bus);
 	} else if (mode == PCI_PROBE_NORMAL) {
-		/* use legacy probe */
+		/*
+		 * Use legacy probe. In the partial hotplug case, we
+		 * probably have grandchildren devices unplugged. So
+		 * we don't check the return value from pci_scan_slot() in
+		 * order for fully rescan all the way down to pick them up.
+		 * They can have been removed during partial hotplug.
+		 */
 		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
-		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-		if (!num)
-			return;
+		pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
 		pcibios_setup_bus_devices(bus);
 		max = bus->busn_res.start;
 		for (pass = 0; pass < 2; pass++) {
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 6b0ba5854d99..15d9105323bf 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -230,11 +230,14 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		return;
 	}
 
-	bus = pci_add_new_bus(dev->bus, dev, busrange[0]);
+	bus = pci_find_bus(pci_domain_nr(dev->bus), busrange[0]);
 	if (!bus) {
-		printk(KERN_ERR "Failed to create pci bus for %s\n",
-		       node->full_name);
-		return;
+		bus = pci_add_new_bus(dev->bus, dev, busrange[0]);
+		if (!bus) {
+			printk(KERN_ERR "Failed to create pci bus for %s\n",
+			       node->full_name);
+			return;
+		}
 	}
 
 	bus->primary = dev->bus->number;
@@ -292,6 +295,38 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(of_scan_pci_bridge);
 
+static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus,
+			    struct device_node *dn)
+{
+	struct pci_dev *dev = NULL;
+	const u32 *reg;
+	int reglen, devfn;
+
+	pr_debug("  * %s\n", dn->full_name);
+	if (!of_device_is_available(dn))
+		return NULL;
+
+	reg = of_get_property(dn, "reg", &reglen);
+	if (reg == NULL || reglen < 20)
+		return NULL;
+	devfn = (reg[0] >> 8) & 0xff;
+
+	/* Check if the PCI device is already there */
+	dev = pci_get_slot(bus, devfn);
+	if (dev) {
+		pci_dev_put(dev);
+		return dev;
+	}
+
+	/* create a new pci_dev for this device */
+	dev = of_create_pci_dev(dn, bus, devfn);
+	if (!dev)
+		return NULL;
+
+	pr_debug("  dev header type: %x\n", dev->hdr_type);
+	return dev;
+}
+
 /**
  * __of_scan_bus - given a PCI bus node, setup bus and scan for child devices
  * @node: device tree node for the PCI bus
@@ -302,8 +337,6 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus,
 			  int rescan_existing)
 {
 	struct device_node *child;
-	const u32 *reg;
-	int reglen, devfn;
 	struct pci_dev *dev;
 
 	pr_debug("of_scan_bus(%s) bus no %d...\n",
@@ -311,16 +344,7 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus,
 
 	/* Scan direct children */
 	for_each_child_of_node(node, child) {
-		pr_debug("  * %s\n", child->full_name);
-		if (!of_device_is_available(child))
-			continue;
-		reg = of_get_property(child, "reg", &reglen);
-		if (reg == NULL || reglen < 20)
-			continue;
-		devfn = (reg[0] >> 8) & 0xff;
-
-		/* create a new pci_dev for this device */
-		dev = of_create_pci_dev(child, bus, devfn);
+		dev = of_scan_pci_dev(bus, child);
 		if (!dev)
 			continue;
 		pr_debug("    dev header type: %x\n", dev->hdr_type);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c517dbe705fd..8083be20fe5e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -600,6 +600,16 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	struct ppc64_tlb_batch *batch;
 #endif
 
+	/* Back up the TAR across context switches.
+	 * Note that the TAR is not available for use in the kernel.  (To
+	 * provide this, the TAR should be backed up/restored on exception
+	 * entry/exit instead, and be in pt_regs.  FIXME, this should be in
+	 * pt_regs anyway (for debug).)
+	 * Save the TAR here before we do treclaim/trecheckpoint as these
+	 * will change the TAR.
+	 */
+	save_tar(&prev->thread);
+
 	__switch_to_tm(prev);
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 5eccda9fd33f..607902424e73 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -644,7 +644,8 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xfffe0000), W(0x003a0000),	/* POWER5/POWER5+ */
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
-	W(0xffff0000), W(0x004b0000),	/* POWER8 */
+	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
 	W(0xffffffff), W(0x0f000002),	/* all 2.05-compliant */
@@ -706,7 +707,7 @@ unsigned char ibm_architecture_vec[] = {
 	 * must match by the macro below. Update the definition if
 	 * the structure layout changes.
 	 */
-#define IBM_ARCH_VEC_NRCORES_OFFSET	117
+#define IBM_ARCH_VEC_NRCORES_OFFSET	125
 	W(NR_CPUS),			/* number of cores supported */
 	0,
 	0,
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 51be8fb24803..0554d1f6d70d 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -233,6 +233,16 @@ dont_backup_fp:
 	std	r5, _CCR(r7)
 	std	r6, _XER(r7)
 
+
+	/* ******************** TAR, PPR, DSCR ********** */
+	mfspr	r3, SPRN_TAR
+	mfspr	r4, SPRN_PPR
+	mfspr	r5, SPRN_DSCR
+
+	std	r3, THREAD_TM_TAR(r12)
+	std	r4, THREAD_TM_PPR(r12)
+	std	r5, THREAD_TM_DSCR(r12)
+
 	/* MSR and flags:  We don't change CRs, and we don't need to alter
 	 * MSR.
 	 */
@@ -347,6 +357,16 @@ dont_restore_fp:
 	mtmsr	r6				/* FP/Vec off again! */
 
 restore_gprs:
+
+	/* ******************** TAR, PPR, DSCR ********** */
+	ld	r4, THREAD_TM_TAR(r3)
+	ld	r5, THREAD_TM_PPR(r3)
+	ld	r6, THREAD_TM_DSCR(r3)
+
+	mtspr	SPRN_TAR,	r4
+	mtspr	SPRN_PPR,	r5
+	mtspr	SPRN_DSCR,	r6
+
 	/* ******************** CR,LR,CCR,MSR ********** */
 	ld	r3, _CTR(r7)
 	ld	r4, _LINK(r7)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index bf33c22e38a4..e435bc089ea3 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -44,9 +44,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/pmc.h>
-#ifdef CONFIG_PPC32
 #include <asm/reg.h>
-#endif
 #ifdef CONFIG_PMAC_BACKLIGHT
 #include <asm/backlight.h>
 #endif
@@ -1296,43 +1294,54 @@ void vsx_unavailable_exception(struct pt_regs *regs)
 	die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
 }
 
+#ifdef CONFIG_PPC64
 void facility_unavailable_exception(struct pt_regs *regs)
 {
 	static char *facility_strings[] = {
-		"FPU",
-		"VMX/VSX",
-		"DSCR",
-		"PMU SPRs",
-		"BHRB",
-		"TM",
-		"AT",
-		"EBB",
-		"TAR",
+		[FSCR_FP_LG] = "FPU",
+		[FSCR_VECVSX_LG] = "VMX/VSX",
+		[FSCR_DSCR_LG] = "DSCR",
+		[FSCR_PM_LG] = "PMU SPRs",
+		[FSCR_BHRB_LG] = "BHRB",
+		[FSCR_TM_LG] = "TM",
+		[FSCR_EBB_LG] = "EBB",
+		[FSCR_TAR_LG] = "TAR",
 	};
-	char *facility, *prefix;
+	char *facility = "unknown";
 	u64 value;
+	u8 status;
+	bool hv;
 
-	if (regs->trap == 0xf60) {
-		value = mfspr(SPRN_FSCR);
-		prefix = "";
-	} else {
+	hv = (regs->trap == 0xf80);
+	if (hv)
 		value = mfspr(SPRN_HFSCR);
-		prefix = "Hypervisor ";
+	else
+		value = mfspr(SPRN_FSCR);
+
+	status = value >> 56;
+	if (status == FSCR_DSCR_LG) {
+		/* User is acessing the DSCR.  Set the inherit bit and allow
+		 * the user to set it directly in future by setting via the
+		 * H/FSCR DSCR bit.
+		 */
+		current->thread.dscr_inherit = 1;
+		if (hv)
+			mtspr(SPRN_HFSCR, value | HFSCR_DSCR);
+		else
+			mtspr(SPRN_FSCR,  value | FSCR_DSCR);
+		return;
 	}
 
-	value = value >> 56;
+	if ((status < ARRAY_SIZE(facility_strings)) &&
+	    facility_strings[status])
+		facility = facility_strings[status];
 
 	/* We restore the interrupt state now */
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	if (value < ARRAY_SIZE(facility_strings))
-		facility = facility_strings[value];
-	else
-		facility = "unknown";
-
 	pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n",
-		prefix, facility, regs->nip, regs->msr);
+	       hv ? "Hypervisor " : "", facility, regs->nip, regs->msr);
 
 	if (user_mode(regs)) {
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
@@ -1341,6 +1350,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
 
 	die("Unexpected facility unavailable exception", regs, SIGABRT);
 }
+#endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 654e479802f2..f096e72262f4 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -38,9 +38,6 @@ jiffies = jiffies_64 + 4;
 #endif
 SECTIONS
 {
-	. = 0;
-	reloc_start = .;
-
 	. = KERNELBASE;
 
 /*
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2efa9dde741a..7629cd3eb91a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1809,7 +1809,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		rma_size <<= PAGE_SHIFT;
 		rmls = lpcr_rmls(rma_size);
 		err = -EINVAL;
-		if (rmls < 0) {
+		if ((long)rmls < 0) {
 			pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
 			goto out_srcu;
 		}
@@ -1874,7 +1874,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	/* Allocate the guest's logical partition ID */
 
 	lpid = kvmppc_alloc_lpid();
-	if (lpid < 0)
+	if ((long)lpid < 0)
 		return -ENOMEM;
 	kvm->arch.lpid = lpid;
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 19498a567a81..c6e13d9a9e15 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1047,11 +1047,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_shadow_vcpu;
 
+	err = -ENOMEM;
 	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
-	/* the real shared page fills the last 4k of our page */
-	vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
 	if (!p)
 		goto uninit_vcpu;
+	/* the real shared page fills the last 4k of our page */
+	vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* default to book3s_64 (970fx) */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3f0c30ae4791..c33d939120c9 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -43,6 +43,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
+	unsigned long sllp;
 
 	/*
 	 * We need 14 to 65 bits of va for a tlibe of 4K page
@@ -64,7 +65,9 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 		/* clear out bits after (52) [0....52.....63] */
 		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
-		va |= mmu_psize_defs[apsize].sllp << 6;
+		sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
+			((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+		va |= sllp << 5;
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 			     : "memory");
@@ -98,6 +101,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
+	unsigned long sllp;
 
 	/* VPN_SHIFT can be atmost 12 */
 	va = vpn << VPN_SHIFT;
@@ -113,7 +117,9 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 		/* clear out bits after(52) [0....52.....63] */
 		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
-		va |= mmu_psize_defs[apsize].sllp << 6;
+		sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
+			((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+		va |= sllp << 5;
 		asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
 			     : : "r"(va) : "memory");
 		break;
@@ -554,6 +560,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			seg_off |= vpi << shift;
 		}
 		*vpn = vsid << (SID_SHIFT - VPN_SHIFT) | seg_off >> VPN_SHIFT;
+		break;
 	case MMU_SEGSIZE_1T:
 		/* We only have 40 - 23 bits of seg_off in avpn */
 		seg_off = (avpn & 0x1ffff) << 23;
@@ -563,6 +570,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			seg_off |= vpi << shift;
 		}
 		*vpn = vsid << (SID_SHIFT_1T - VPN_SHIFT) | seg_off >> VPN_SHIFT;
+		break;
 	default:
 		*vpn = size = 0;
 	}
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 08397217e8ac..5850798826cd 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -27,6 +27,7 @@
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
+#include <asm/cputhreads.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
@@ -1318,7 +1319,8 @@ static int update_cpu_associativity_changes_mask(void)
 			}
 		}
 		if (changed) {
-			cpumask_set_cpu(cpu, changes);
+			cpumask_or(changes, changes, cpu_sibling_mask(cpu));
+			cpu = cpu_last_thread_sibling(cpu);
 		}
 	}
 
@@ -1426,7 +1428,7 @@ static int update_cpu_topology(void *data)
 	if (!data)
 		return -EINVAL;
 
-	cpu = get_cpu();
+	cpu = smp_processor_id();
 
 	for (update = data; update; update = update->next) {
 		if (cpu != update->cpu)
@@ -1446,12 +1448,12 @@ static int update_cpu_topology(void *data)
  */
 int arch_update_cpu_topology(void)
 {
-	unsigned int cpu, changed = 0;
+	unsigned int cpu, sibling, changed = 0;
 	struct topology_update_data *updates, *ud;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	cpumask_t updated_cpus;
 	struct device *dev;
-	int weight, i = 0;
+	int weight, new_nid, i = 0;
 
 	weight = cpumask_weight(&cpu_associativity_changes_mask);
 	if (!weight)
@@ -1464,19 +1466,46 @@ int arch_update_cpu_topology(void)
 	cpumask_clear(&updated_cpus);
 
 	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
-		ud = &updates[i++];
-		ud->cpu = cpu;
-		vphn_get_associativity(cpu, associativity);
-		ud->new_nid = associativity_to_nid(associativity);
-
-		if (ud->new_nid < 0 || !node_online(ud->new_nid))
-			ud->new_nid = first_online_node;
+		/*
+		 * If siblings aren't flagged for changes, updates list
+		 * will be too short. Skip on this update and set for next
+		 * update.
+		 */
+		if (!cpumask_subset(cpu_sibling_mask(cpu),
+					&cpu_associativity_changes_mask)) {
+			pr_info("Sibling bits not set for associativity "
+					"change, cpu%d\n", cpu);
+			cpumask_or(&cpu_associativity_changes_mask,
+					&cpu_associativity_changes_mask,
+					cpu_sibling_mask(cpu));
+			cpu = cpu_last_thread_sibling(cpu);
+			continue;
+		}
 
-		ud->old_nid = numa_cpu_lookup_table[cpu];
-		cpumask_set_cpu(cpu, &updated_cpus);
+		/* Use associativity from first thread for all siblings */
+		vphn_get_associativity(cpu, associativity);
+		new_nid = associativity_to_nid(associativity);
+		if (new_nid < 0 || !node_online(new_nid))
+			new_nid = first_online_node;
+
+		if (new_nid == numa_cpu_lookup_table[cpu]) {
+			cpumask_andnot(&cpu_associativity_changes_mask,
+					&cpu_associativity_changes_mask,
+					cpu_sibling_mask(cpu));
+			cpu = cpu_last_thread_sibling(cpu);
+			continue;
+		}
 
-		if (i < weight)
-			ud->next = &updates[i];
+		for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+			ud = &updates[i++];
+			ud->cpu = sibling;
+			ud->new_nid = new_nid;
+			ud->old_nid = numa_cpu_lookup_table[sibling];
+			cpumask_set_cpu(sibling, &updated_cpus);
+			if (i < weight)
+				ud->next = &updates[i];
+		}
+		cpu = cpu_last_thread_sibling(cpu);
 	}
 
 	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index a3985aee77fe..eeae308cf982 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -484,7 +484,7 @@ static bool is_ebb_event(struct perf_event *event)
 	 * use bit 63 of the event code for something else if they wish.
 	 */
 	return (ppmu->flags & PPMU_EBB) &&
-	       ((event->attr.config >> EVENT_CONFIG_EBB_SHIFT) & 1);
+	       ((event->attr.config >> PERF_EVENT_CONFIG_EBB_SHIFT) & 1);
 }
 
 static int ebb_event_check(struct perf_event *event)
@@ -1252,8 +1252,11 @@ nocheck:
 
 	ret = 0;
  out:
-	if (has_branch_stack(event))
+	if (has_branch_stack(event)) {
 		power_pmu_bhrb_enable(event);
+		cpuhw->bhrb_filter = ppmu->bhrb_filter_map(
+					event->attr.branch_sample_type);
+	}
 
 	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 96a64d6a8bdf..2ee4a707f0df 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -118,7 +118,7 @@
 	 (EVENT_UNIT_MASK      << EVENT_UNIT_SHIFT)		|	\
 	 (EVENT_COMBINE_MASK   << EVENT_COMBINE_SHIFT)		|	\
 	 (EVENT_MARKED_MASK    << EVENT_MARKED_SHIFT)		|	\
-	 (EVENT_EBB_MASK       << EVENT_CONFIG_EBB_SHIFT)	|	\
+	 (EVENT_EBB_MASK       << PERF_EVENT_CONFIG_EBB_SHIFT)	|	\
 	  EVENT_PSEL_MASK)
 
 /* MMCRA IFM bits - POWER8 */
@@ -233,10 +233,10 @@ static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long
 	pmc   = (event >> EVENT_PMC_SHIFT)        & EVENT_PMC_MASK;
 	unit  = (event >> EVENT_UNIT_SHIFT)       & EVENT_UNIT_MASK;
 	cache = (event >> EVENT_CACHE_SEL_SHIFT)  & EVENT_CACHE_SEL_MASK;
-	ebb   = (event >> EVENT_CONFIG_EBB_SHIFT) & EVENT_EBB_MASK;
+	ebb   = (event >> PERF_EVENT_CONFIG_EBB_SHIFT) & EVENT_EBB_MASK;
 
 	/* Clear the EBB bit in the event, so event checks work below */
-	event &= ~(EVENT_EBB_MASK << EVENT_CONFIG_EBB_SHIFT);
+	event &= ~(EVENT_EBB_MASK << PERF_EVENT_CONFIG_EBB_SHIFT);
 
 	if (pmc) {
 		if (pmc > 6)
@@ -561,18 +561,13 @@ static int power8_generic_events[] = {
 static u64 power8_bhrb_filter_map(u64 branch_sample_type)
 {
 	u64 pmu_bhrb_filter = 0;
-	u64 br_privilege = branch_sample_type & ONLY_PLM;
 
-	/* BHRB and regular PMU events share the same prvillege state
+	/* BHRB and regular PMU events share the same privilege state
 	 * filter configuration. BHRB is always recorded along with a
-	 * regular PMU event. So privilege state filter criteria for BHRB
-	 * and the companion PMU events has to be the same. As a default
-	 * "perf record" tool sets all privillege bits ON when no filter
-	 * criteria is provided in the command line. So as along as all
-	 * privillege bits are ON or they are OFF, we are good to go.
+	 * regular PMU event. As the privilege state filter is handled
+	 * in the basic PMC configuration of the accompanying regular
+	 * PMU event, we ignore any separate BHRB specific request.
 	 */
-	if ((br_privilege != 7) && (br_privilege != 0))
-		return -1;
 
 	/* No branch filter requested */
 	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY)
@@ -621,10 +616,19 @@ static struct power_pmu power8_pmu = {
 
 static int __init init_power8_pmu(void)
 {
+	int rc;
+
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power8"))
 		return -ENODEV;
 
-	return register_power_pmu(&power8_pmu);
+	rc = register_power_pmu(&power8_pmu);
+	if (rc)
+		return rc;
+
+	/* Tell userspace that EBB is supported */
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+
+	return 0;
 }
 early_initcall(init_power8_pmu);
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 969cce73055a..79663d26e6ea 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -114,7 +114,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	 * the root bridge. So it's not reasonable to continue
 	 * the probing.
 	 */
-	if (!dn || !edev)
+	if (!dn || !edev || edev->pe)
 		return 0;
 
 	/* Skip for PCI-ISA bridge */
@@ -122,8 +122,19 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 		return 0;
 
 	/* Initialize eeh device */
-	edev->class_code	= dev->class;
-	edev->mode		= 0;
+	edev->class_code = dev->class;
+	edev->mode	&= 0xFFFFFF00;
+	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		edev->mode |= EEH_DEV_BRIDGE;
+	if (pci_is_pcie(dev)) {
+		edev->pcie_cap = pci_pcie_cap(dev);
+
+		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+			edev->mode |= EEH_DEV_ROOT_PORT;
+		else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
+			edev->mode |= EEH_DEV_DS_PORT;
+	}
+
 	edev->config_addr	= ((dev->bus->number << 8) | dev->devfn);
 	edev->pe_config_addr	= phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff);
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 49b57b9f835d..d8140b125e62 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1266,7 +1266,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE);
 }
 
-void pnv_pci_init_ioda2_phb(struct device_node *np)
+void __init pnv_pci_init_ioda2_phb(struct device_node *np)
 {
 	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
 }
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 1bd3399146ed..62b4f8025de0 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -19,7 +19,6 @@ config PPC_PSERIES
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
-	select HOTPLUG if SMP
 	select HOTPLUG_CPU if SMP
 	default y
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b456b157d33d..7fbc25b1813f 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -133,6 +133,48 @@ static int pseries_eeh_init(void)
 	return 0;
 }
 
+static int pseries_eeh_cap_start(struct device_node *dn)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	u32 status;
+
+	if (!pdn)
+		return 0;
+
+	rtas_read_config(pdn, PCI_STATUS, 2, &status);
+	if (!(status & PCI_STATUS_CAP_LIST))
+		return 0;
+
+	return PCI_CAPABILITY_LIST;
+}
+
+
+static int pseries_eeh_find_cap(struct device_node *dn, int cap)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	int pos = pseries_eeh_cap_start(dn);
+	int cnt = 48;	/* Maximal number of capabilities */
+	u32 id;
+
+	if (!pos)
+		return 0;
+
+        while (cnt--) {
+		rtas_read_config(pdn, pos, 1, &pos);
+		if (pos < 0x40)
+			break;
+		pos &= ~3;
+		rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+		if (id == 0xff)
+			break;
+		if (id == cap)
+			return pos;
+		pos += PCI_CAP_LIST_NEXT;
+	}
+
+	return 0;
+}
+
 /**
  * pseries_eeh_of_probe - EEH probe on the given device
  * @dn: OF node
@@ -146,14 +188,16 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 {
 	struct eeh_dev *edev;
 	struct eeh_pe pe;
+	struct pci_dn *pdn = PCI_DN(dn);
 	const u32 *class_code, *vendor_id, *device_id;
 	const u32 *regs;
+	u32 pcie_flags;
 	int enable = 0;
 	int ret;
 
 	/* Retrieve OF node and eeh device */
 	edev = of_node_to_eeh_dev(dn);
-	if (!of_device_is_available(dn))
+	if (edev->pe || !of_device_is_available(dn))
 		return NULL;
 
 	/* Retrieve class/vendor/device IDs */
@@ -167,9 +211,26 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 	if (dn->type && !strcmp(dn->type, "isa"))
 		return NULL;
 
-	/* Update class code and mode of eeh device */
+	/*
+	 * Update class code and mode of eeh device. We need
+	 * correctly reflects that current device is root port
+	 * or PCIe switch downstream port.
+	 */
 	edev->class_code = *class_code;
-	edev->mode = 0;
+	edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP);
+	edev->mode &= 0xFFFFFF00;
+	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		edev->mode |= EEH_DEV_BRIDGE;
+		if (edev->pcie_cap) {
+			rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+					 2, &pcie_flags);
+			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
+			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
+				edev->mode |= EEH_DEV_ROOT_PORT;
+			else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM)
+				edev->mode |= EEH_DEV_DS_PORT;
+		}
+	}
 
 	/* Retrieve the device address */
 	regs = of_get_property(dn, "reg", NULL);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 02d6e21619bb..8bad880bd177 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -146,7 +146,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	flags = 0;
 
 	/* Make pHyp happy */
-	if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU))
+	if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU))
 		hpte_r &= ~_PAGE_COHERENT;
 	if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N))
 		flags |= H_COALESCE_CAND;
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 9f8671a44551..6a5f2b1f32ca 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -569,35 +569,6 @@ error:
 	return ret;
 }
 
-static int unzip_oops(char *oops_buf, char *big_buf)
-{
-	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
-	u64 timestamp = oops_hdr->timestamp;
-	char *big_oops_data = NULL;
-	char *oops_data_buf = NULL;
-	size_t big_oops_data_sz;
-	int unzipped_len;
-
-	big_oops_data = big_buf + sizeof(struct oops_log_info);
-	big_oops_data_sz = big_oops_buf_sz - sizeof(struct oops_log_info);
-	oops_data_buf = oops_buf + sizeof(struct oops_log_info);
-
-	unzipped_len = nvram_decompress(oops_data_buf, big_oops_data,
-					oops_hdr->report_length,
-					big_oops_data_sz);
-
-	if (unzipped_len < 0) {
-		pr_err("nvram: decompression failed; returned %d\n",
-								unzipped_len);
-		return -1;
-	}
-	oops_hdr = (struct oops_log_info *)big_buf;
-	oops_hdr->version = OOPS_HDR_VERSION;
-	oops_hdr->report_length = (u16) unzipped_len;
-	oops_hdr->timestamp = timestamp;
-	return 0;
-}
-
 static int nvram_pstore_open(struct pstore_info *psi)
 {
 	/* Reset the iterator to start reading partitions again */
@@ -685,10 +656,9 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 	unsigned int err_type, id_no, size = 0;
 	struct nvram_os_partition *part = NULL;
 	char *buff = NULL, *big_buff = NULL;
-	int rc, sig = 0;
+	int sig = 0;
 	loff_t p;
 
-read_partition:
 	read_type++;
 
 	switch (nvram_type_ids[read_type]) {
@@ -749,30 +719,46 @@ read_partition:
 		*id = id_no;
 
 	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
+		int length, unzipped_len;
+		size_t hdr_size;
+
 		oops_hdr = (struct oops_log_info *)buff;
-		*buf = buff + sizeof(*oops_hdr);
+		if (oops_hdr->version < OOPS_HDR_VERSION) {
+			/* Old format oops header had 2-byte record size */
+			hdr_size = sizeof(u16);
+			length = oops_hdr->version;
+			time->tv_sec = 0;
+			time->tv_nsec = 0;
+		} else {
+			hdr_size = sizeof(*oops_hdr);
+			length = oops_hdr->report_length;
+			time->tv_sec = oops_hdr->timestamp;
+			time->tv_nsec = 0;
+		}
+		*buf = kmalloc(length, GFP_KERNEL);
+		if (*buf == NULL)
+			return -ENOMEM;
+		memcpy(*buf, buff + hdr_size, length);
+		kfree(buff);
 
 		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) {
 			big_buff = kmalloc(big_oops_buf_sz, GFP_KERNEL);
 			if (!big_buff)
 				return -ENOMEM;
 
-			rc = unzip_oops(buff, big_buff);
+			unzipped_len = nvram_decompress(*buf, big_buff,
+						length, big_oops_buf_sz);
 
-			if (rc != 0) {
-				kfree(buff);
+			if (unzipped_len < 0) {
+				pr_err("nvram: decompression failed, returned "
+					"rc %d\n", unzipped_len);
 				kfree(big_buff);
-				goto read_partition;
+			} else {
+				*buf = big_buff;
+				length = unzipped_len;
 			}
-
-			oops_hdr = (struct oops_log_info *)big_buff;
-			*buf = big_buff + sizeof(*oops_hdr);
-			kfree(buff);
 		}
-
-		time->tv_sec = oops_hdr->timestamp;
-		time->tv_nsec = 0;
-		return oops_hdr->report_length;
+		return length;
 	}
 
 	*buf = buff;
@@ -816,6 +802,7 @@ static int nvram_pstore_init(void)
 static void __init nvram_init_oops_partition(int rtas_partition_exists)
 {
 	int rc;
+	size_t size;
 
 	rc = pseries_nvram_init_os_partition(&oops_log_partition);
 	if (rc != 0) {
@@ -844,8 +831,9 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 	big_oops_buf_sz = (oops_data_sz * 100) / 45;
 	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
 	if (big_oops_buf) {
-		stream.workspace = kmalloc(zlib_deflate_workspacesize(
-				WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+		size = max(zlib_deflate_workspacesize(WINDOW_BITS, MEM_LEVEL),
+			zlib_inflate_workspacesize());
+		stream.workspace = kmalloc(size, GFP_KERNEL);
 		if (!stream.workspace) {
 			pr_err("nvram: No memory for compression workspace; "
 				"skipping compression of %s partition data\n",
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 7b3cbde8c783..721c0586b284 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -287,6 +287,9 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 	unsigned long *savep;
 	struct rtas_error_log *h, *errhdr = NULL;
 
+	/* Mask top two bits */
+	regs->gpr[3] &= ~(0x3UL << 62);
+
 	if (!VALID_FWNMI_BUFFER(regs->gpr[3])) {
 		printk(KERN_ERR "FWNMI: corrupt r3 0x%016lx\n", regs->gpr[3]);
 		return NULL;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 22f75b504f7f..8a4cae78f03c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -118,6 +118,7 @@ config S390
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZ4
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_XZ
@@ -227,11 +228,12 @@ config MARCH_Z196
 	  not work on older machines.
 
 config MARCH_ZEC12
-	bool "IBM zEC12"
+	bool "IBM zBC12 and zEC12"
 	select HAVE_MARCH_ZEC12_FEATURES if 64BIT
 	help
-	  Select this to enable optimizations for IBM zEC12 (2827 series). The
-	  kernel will be slightly faster but will not work on older machines.
+	  Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and
+	  2827 series). The kernel will be slightly faster but will not work on
+	  older machines.
 
 endchoice
 
@@ -709,6 +711,7 @@ config S390_GUEST
 	def_bool y
 	prompt "s390 support for virtio devices"
 	depends on 64BIT
+	select TTY
 	select VIRTUALIZATION
 	select VIRTIO
 	select VIRTIO_CONSOLE
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 3ad8f61c9985..866ecbe670e4 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -6,9 +6,9 @@
 
 BITS := $(if $(CONFIG_64BIT),64,31)
 
-targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 \
-	   vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo misc.o piggy.o \
-	   sizes.h head$(BITS).o
+targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
+targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
+targets += misc.o piggy.o sizes.h head$(BITS).o
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
@@ -48,6 +48,7 @@ vmlinux.bin.all-y := $(obj)/vmlinux.bin
 
 suffix-$(CONFIG_KERNEL_GZIP)  := gz
 suffix-$(CONFIG_KERNEL_BZIP2) := bz2
+suffix-$(CONFIG_KERNEL_LZ4)  := lz4
 suffix-$(CONFIG_KERNEL_LZMA)  := lzma
 suffix-$(CONFIG_KERNEL_LZO)  := lzo
 suffix-$(CONFIG_KERNEL_XZ)  := xz
@@ -56,6 +57,8 @@ $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
 	$(call if_changed,gzip)
 $(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y)
 	$(call if_changed,bzip2)
+$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y)
+	$(call if_changed,lz4)
 $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y)
 	$(call if_changed,lzma)
 $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y)
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index c4c6a1cf221b..57cbaff1f397 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -47,6 +47,10 @@ static unsigned long free_mem_end_ptr;
 #include "../../../../lib/decompress_bunzip2.c"
 #endif
 
+#ifdef CONFIG_KERNEL_LZ4
+#include "../../../../lib/decompress_unlz4.c"
+#endif
+
 #ifdef CONFIG_KERNEL_LZMA
 #include "../../../../lib/decompress_unlzma.c"
 #endif
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 4d8604e311f3..7d4676758733 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -693,7 +693,7 @@ static inline int find_next_bit_left(const unsigned long *addr,
 	size -= offset;
 	p = addr + offset / BITS_PER_LONG;
 	if (bit) {
-		set = __flo_word(0, *p & (~0UL << bit));
+		set = __flo_word(0, *p & (~0UL >> bit));
 		if (set >= size)
 			return size + offset;
 		if (set < BITS_PER_LONG)
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b75d7d686684..6d6d92b4ea11 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -32,6 +32,7 @@ struct mmu_gather {
 	struct mm_struct *mm;
 	struct mmu_table_batch *batch;
 	unsigned int fullmm;
+	unsigned long start, end;
 };
 
 struct mmu_table_batch {
@@ -48,10 +49,13 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 				  struct mm_struct *mm,
-				  unsigned int full_mm_flush)
+				  unsigned long start,
+				  unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
+	tlb->start = start;
+	tlb->end = end;
+	tlb->fullmm = !(start | (end+1));
 	tlb->batch = NULL;
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index a6fc037671b1..500aa1029bcb 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -52,12 +52,13 @@ static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs)
 
 static bool is_in_guest(struct pt_regs *regs)
 {
-	unsigned long ip = instruction_pointer(regs);
-
 	if (user_mode(regs))
 		return false;
-
-	return ip == (unsigned long) &sie_exit;
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+	return instruction_pointer(regs) == (unsigned long) &sie_exit;
+#else
+	return false;
+#endif
 }
 
 static unsigned long guest_is_user_mode(struct pt_regs *regs)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 497451ec5e26..aeed8a61fa0d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -994,6 +994,7 @@ static void __init setup_hwcaps(void)
 		strcpy(elf_platform, "z196");
 		break;
 	case 0x2827:
+	case 0x2828:
 		strcpy(elf_platform, "zEC12");
 		break;
 	}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ba694d2ba51e..34c1c9a90be2 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -702,14 +702,25 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		return rc;
 
 	vcpu->arch.sie_block->icptcode = 0;
-	preempt_disable();
-	kvm_guest_enter();
-	preempt_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	trace_kvm_s390_sie_enter(vcpu,
 				 atomic_read(&vcpu->arch.sie_block->cpuflags));
+
+	/*
+	 * As PF_VCPU will be used in fault handler, between guest_enter
+	 * and guest_exit should be no uaccess.
+	 */
+	preempt_disable();
+	kvm_guest_enter();
+	preempt_enable();
 	rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
+	kvm_guest_exit();
+
+	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
+		   vcpu->arch.sie_block->icptcode);
+	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
+
 	if (rc > 0)
 		rc = 0;
 	if (rc < 0) {
@@ -721,10 +732,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 			rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 		}
 	}
-	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
-		   vcpu->arch.sie_block->icptcode);
-	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
-	kvm_guest_exit();
 
 	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
 	return rc;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 0da3e6eb6be6..4cdc54e63ebc 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -16,6 +16,7 @@
 #include <linux/errno.h>
 #include <linux/compat.h>
 #include <asm/asm-offsets.h>
+#include <asm/facility.h>
 #include <asm/current.h>
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
@@ -532,8 +533,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	/* Only provide non-quiescing support if the host supports it */
-	if (vcpu->run->s.regs.gprs[reg1] & PFMF_NQ &&
-	    S390_lowcore.stfl_fac_list & 0x00020000)
+	if (vcpu->run->s.regs.gprs[reg1] & PFMF_NQ && !test_facility(14))
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	/* No support for conditional-SSKE */
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ce36ea80e4f9..ad446b0c55b6 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -69,6 +69,7 @@ static void __init setup_zero_pages(void)
 		order = 2;
 		break;
 	case 0x2827:	/* zEC12 */
+	case 0x2828:	/* zEC12 */
 	default:
 		order = 5;
 		break;
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index ffeb17ce7f31..930783d2c99b 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -440,7 +440,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 		switch (id.machine) {
 		case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
 		case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
-		case 0x2827:              ops->cpu_type = "s390/zEC12"; break;
+		case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break;
 		default: return -ENODEV;
 		}
 	}
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index c8def8bc9020..5fc237581caf 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -87,6 +87,8 @@ config STACKTRACE_SUPPORT
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 config MMU
 	def_bool y
 
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 2051821724c6..0cf4097b71e8 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -22,7 +22,7 @@ CONFIG_PREEMPT=y
 CONFIG_CMDLINE_OVERWRITE=y
 CONFIG_CMDLINE="console=ttySC1,115200 mem=64M root=/dev/nfs"
 CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_BINFMT_MISC=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index e61d43d9f689..362192ed12fe 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -36,10 +36,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
+	tlb->start = start;
+	tlb->end = end;
+	tlb->fullmm = !(start | (end+1));
 
 	init_tlb_gather(tlb);
 }
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 4febacd1a8a1..29b0301c18aa 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -45,10 +45,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
+	tlb->start = start;
+	tlb->end = end;
+	tlb->fullmm = !(start | (end+1));
 
 	init_tlb_gather(tlb);
 }
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index d606463aa6d6..b7388a425f09 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -225,7 +225,7 @@ static void low_free(unsigned long size, unsigned long addr)
 	unsigned long nr_pages;
 
 	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-	efi_call_phys2(sys_table->boottime->free_pages, addr, size);
+	efi_call_phys2(sys_table->boottime->free_pages, addr, nr_pages);
 }
 
 static void find_bits(unsigned long mask, u8 *pos, u8 *size)
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 7d6ba9db1be9..6c63c358a7e6 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -27,7 +27,6 @@ obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
 obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
-obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
@@ -82,4 +81,3 @@ crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
 crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
 sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
 sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
-crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o
diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S
deleted file mode 100644
index 35e97569d05f..000000000000
--- a/arch/x86/crypto/crct10dif-pcl-asm_64.S
+++ /dev/null
@@ -1,643 +0,0 @@
-########################################################################
-# Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
-#
-# Copyright (c) 2013, Intel Corporation
-#
-# Authors:
-#     Erdinc Ozturk <erdinc.ozturk@intel.com>
-#     Vinodh Gopal <vinodh.gopal@intel.com>
-#     James Guilford <james.guilford@intel.com>
-#     Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses.  You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions are
-# met:
-#
-# * Redistributions of source code must retain the above copyright
-#   notice, this list of conditions and the following disclaimer.
-#
-# * Redistributions in binary form must reproduce the above copyright
-#   notice, this list of conditions and the following disclaimer in the
-#   documentation and/or other materials provided with the
-#   distribution.
-#
-# * Neither the name of the Intel Corporation nor the names of its
-#   contributors may be used to endorse or promote products derived from
-#   this software without specific prior written permission.
-#
-#
-# THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
-# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
-# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
-# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
-# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-########################################################################
-#       Function API:
-#       UINT16 crc_t10dif_pcl(
-#               UINT16 init_crc, //initial CRC value, 16 bits
-#               const unsigned char *buf, //buffer pointer to calculate CRC on
-#               UINT64 len //buffer length in bytes (64-bit data)
-#       );
-#
-#       Reference paper titled "Fast CRC Computation for Generic
-#	Polynomials Using PCLMULQDQ Instruction"
-#       URL: http://www.intel.com/content/dam/www/public/us/en/documents
-#  /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
-#
-#
-
-#include <linux/linkage.h>
-
-.text
-
-#define        arg1 %rdi
-#define        arg2 %rsi
-#define        arg3 %rdx
-
-#define        arg1_low32 %edi
-
-ENTRY(crc_t10dif_pcl)
-.align 16
-
-	# adjust the 16-bit initial_crc value, scale it to 32 bits
-	shl	$16, arg1_low32
-
-	# Allocate Stack Space
-	mov     %rsp, %rcx
-	sub	$16*2, %rsp
-	# align stack to 16 byte boundary
-	and     $~(0x10 - 1), %rsp
-
-	# check if smaller than 256
-	cmp	$256, arg3
-
-	# for sizes less than 128, we can't fold 64B at a time...
-	jl	_less_than_128
-
-
-	# load the initial crc value
-	movd	arg1_low32, %xmm10	# initial crc
-
-	# crc value does not need to be byte-reflected, but it needs
-	# to be moved to the high part of the register.
-	# because data will be byte-reflected and will align with
-	# initial crc at correct place.
-	pslldq	$12, %xmm10
-
-	movdqa  SHUF_MASK(%rip), %xmm11
-	# receive the initial 64B data, xor the initial crc value
-	movdqu	16*0(arg2), %xmm0
-	movdqu	16*1(arg2), %xmm1
-	movdqu	16*2(arg2), %xmm2
-	movdqu	16*3(arg2), %xmm3
-	movdqu	16*4(arg2), %xmm4
-	movdqu	16*5(arg2), %xmm5
-	movdqu	16*6(arg2), %xmm6
-	movdqu	16*7(arg2), %xmm7
-
-	pshufb	%xmm11, %xmm0
-	# XOR the initial_crc value
-	pxor	%xmm10, %xmm0
-	pshufb	%xmm11, %xmm1
-	pshufb	%xmm11, %xmm2
-	pshufb	%xmm11, %xmm3
-	pshufb	%xmm11, %xmm4
-	pshufb	%xmm11, %xmm5
-	pshufb	%xmm11, %xmm6
-	pshufb	%xmm11, %xmm7
-
-	movdqa	rk3(%rip), %xmm10	#xmm10 has rk3 and rk4
-					#imm value of pclmulqdq instruction
-					#will determine which constant to use
-
-	#################################################################
-	# we subtract 256 instead of 128 to save one instruction from the loop
-	sub	$256, arg3
-
-	# at this section of the code, there is 64*x+y (0<=y<64) bytes of
-	# buffer. The _fold_64_B_loop will fold 64B at a time
-	# until we have 64+y Bytes of buffer
-
-
-	# fold 64B at a time. This section of the code folds 4 xmm
-	# registers in parallel
-_fold_64_B_loop:
-
-	# update the buffer pointer
-	add	$128, arg2		#    buf += 64#
-
-	movdqu	16*0(arg2), %xmm9
-	movdqu	16*1(arg2), %xmm12
-	pshufb	%xmm11, %xmm9
-	pshufb	%xmm11, %xmm12
-	movdqa	%xmm0, %xmm8
-	movdqa	%xmm1, %xmm13
-	pclmulqdq	$0x0 , %xmm10, %xmm0
-	pclmulqdq	$0x11, %xmm10, %xmm8
-	pclmulqdq	$0x0 , %xmm10, %xmm1
-	pclmulqdq	$0x11, %xmm10, %xmm13
-	pxor	%xmm9 , %xmm0
-	xorps	%xmm8 , %xmm0
-	pxor	%xmm12, %xmm1
-	xorps	%xmm13, %xmm1
-
-	movdqu	16*2(arg2), %xmm9
-	movdqu	16*3(arg2), %xmm12
-	pshufb	%xmm11, %xmm9
-	pshufb	%xmm11, %xmm12
-	movdqa	%xmm2, %xmm8
-	movdqa	%xmm3, %xmm13
-	pclmulqdq	$0x0, %xmm10, %xmm2
-	pclmulqdq	$0x11, %xmm10, %xmm8
-	pclmulqdq	$0x0, %xmm10, %xmm3
-	pclmulqdq	$0x11, %xmm10, %xmm13
-	pxor	%xmm9 , %xmm2
-	xorps	%xmm8 , %xmm2
-	pxor	%xmm12, %xmm3
-	xorps	%xmm13, %xmm3
-
-	movdqu	16*4(arg2), %xmm9
-	movdqu	16*5(arg2), %xmm12
-	pshufb	%xmm11, %xmm9
-	pshufb	%xmm11, %xmm12
-	movdqa	%xmm4, %xmm8
-	movdqa	%xmm5, %xmm13
-	pclmulqdq	$0x0,  %xmm10, %xmm4
-	pclmulqdq	$0x11, %xmm10, %xmm8
-	pclmulqdq	$0x0,  %xmm10, %xmm5
-	pclmulqdq	$0x11, %xmm10, %xmm13
-	pxor	%xmm9 ,  %xmm4
-	xorps	%xmm8 ,  %xmm4
-	pxor	%xmm12,  %xmm5
-	xorps	%xmm13,  %xmm5
-
-	movdqu	16*6(arg2), %xmm9
-	movdqu	16*7(arg2), %xmm12
-	pshufb	%xmm11, %xmm9
-	pshufb	%xmm11, %xmm12
-	movdqa	%xmm6 , %xmm8
-	movdqa	%xmm7 , %xmm13
-	pclmulqdq	$0x0 , %xmm10, %xmm6
-	pclmulqdq	$0x11, %xmm10, %xmm8
-	pclmulqdq	$0x0 , %xmm10, %xmm7
-	pclmulqdq	$0x11, %xmm10, %xmm13
-	pxor	%xmm9 , %xmm6
-	xorps	%xmm8 , %xmm6
-	pxor	%xmm12, %xmm7
-	xorps	%xmm13, %xmm7
-
-	sub	$128, arg3
-
-	# check if there is another 64B in the buffer to be able to fold
-	jge	_fold_64_B_loop
-	##################################################################
-
-
-	add	$128, arg2
-	# at this point, the buffer pointer is pointing at the last y Bytes
-	# of the buffer the 64B of folded data is in 4 of the xmm
-	# registers: xmm0, xmm1, xmm2, xmm3
-
-
-	# fold the 8 xmm registers to 1 xmm register with different constants
-
-	movdqa	rk9(%rip), %xmm10
-	movdqa	%xmm0, %xmm8
-	pclmulqdq	$0x11, %xmm10, %xmm0
-	pclmulqdq	$0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	xorps	%xmm0, %xmm7
-
-	movdqa	rk11(%rip), %xmm10
-	movdqa	%xmm1, %xmm8
-	pclmulqdq	 $0x11, %xmm10, %xmm1
-	pclmulqdq	 $0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	xorps	%xmm1, %xmm7
-
-	movdqa	rk13(%rip), %xmm10
-	movdqa	%xmm2, %xmm8
-	pclmulqdq	 $0x11, %xmm10, %xmm2
-	pclmulqdq	 $0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	pxor	%xmm2, %xmm7
-
-	movdqa	rk15(%rip), %xmm10
-	movdqa	%xmm3, %xmm8
-	pclmulqdq	$0x11, %xmm10, %xmm3
-	pclmulqdq	$0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	xorps	%xmm3, %xmm7
-
-	movdqa	rk17(%rip), %xmm10
-	movdqa	%xmm4, %xmm8
-	pclmulqdq	$0x11, %xmm10, %xmm4
-	pclmulqdq	$0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	pxor	%xmm4, %xmm7
-
-	movdqa	rk19(%rip), %xmm10
-	movdqa	%xmm5, %xmm8
-	pclmulqdq	$0x11, %xmm10, %xmm5
-	pclmulqdq	$0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	xorps	%xmm5, %xmm7
-
-	movdqa	rk1(%rip), %xmm10	#xmm10 has rk1 and rk2
-					#imm value of pclmulqdq instruction
-					#will determine which constant to use
-	movdqa	%xmm6, %xmm8
-	pclmulqdq	$0x11, %xmm10, %xmm6
-	pclmulqdq	$0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	pxor	%xmm6, %xmm7
-
-
-	# instead of 64, we add 48 to the loop counter to save 1 instruction
-	# from the loop instead of a cmp instruction, we use the negative
-	# flag with the jl instruction
-	add	$128-16, arg3
-	jl	_final_reduction_for_128
-
-	# now we have 16+y bytes left to reduce. 16 Bytes is in register xmm7
-	# and the rest is in memory. We can fold 16 bytes at a time if y>=16
-	# continue folding 16B at a time
-
-_16B_reduction_loop:
-	movdqa	%xmm7, %xmm8
-	pclmulqdq	$0x11, %xmm10, %xmm7
-	pclmulqdq	$0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	movdqu	(arg2), %xmm0
-	pshufb	%xmm11, %xmm0
-	pxor	%xmm0 , %xmm7
-	add	$16, arg2
-	sub	$16, arg3
-	# instead of a cmp instruction, we utilize the flags with the
-	# jge instruction equivalent of: cmp arg3, 16-16
-	# check if there is any more 16B in the buffer to be able to fold
-	jge	_16B_reduction_loop
-
-	#now we have 16+z bytes left to reduce, where 0<= z < 16.
-	#first, we reduce the data in the xmm7 register
-
-
-_final_reduction_for_128:
-	# check if any more data to fold. If not, compute the CRC of
-	# the final 128 bits
-	add	$16, arg3
-	je	_128_done
-
-	# here we are getting data that is less than 16 bytes.
-	# since we know that there was data before the pointer, we can
-	# offset the input pointer before the actual point, to receive
-	# exactly 16 bytes. after that the registers need to be adjusted.
-_get_last_two_xmms:
-	movdqa	%xmm7, %xmm2
-
-	movdqu	-16(arg2, arg3), %xmm1
-	pshufb	%xmm11, %xmm1
-
-	# get rid of the extra data that was loaded before
-	# load the shift constant
-	lea	pshufb_shf_table+16(%rip), %rax
-	sub	arg3, %rax
-	movdqu	(%rax), %xmm0
-
-	# shift xmm2 to the left by arg3 bytes
-	pshufb	%xmm0, %xmm2
-
-	# shift xmm7 to the right by 16-arg3 bytes
-	pxor	mask1(%rip), %xmm0
-	pshufb	%xmm0, %xmm7
-	pblendvb	%xmm2, %xmm1	#xmm0 is implicit
-
-	# fold 16 Bytes
-	movdqa	%xmm1, %xmm2
-	movdqa	%xmm7, %xmm8
-	pclmulqdq	$0x11, %xmm10, %xmm7
-	pclmulqdq	$0x0 , %xmm10, %xmm8
-	pxor	%xmm8, %xmm7
-	pxor	%xmm2, %xmm7
-
-_128_done:
-	# compute crc of a 128-bit value
-	movdqa	rk5(%rip), %xmm10	# rk5 and rk6 in xmm10
-	movdqa	%xmm7, %xmm0
-
-	#64b fold
-	pclmulqdq	$0x1, %xmm10, %xmm7
-	pslldq	$8   ,  %xmm0
-	pxor	%xmm0,  %xmm7
-
-	#32b fold
-	movdqa	%xmm7, %xmm0
-
-	pand	mask2(%rip), %xmm0
-
-	psrldq	$12, %xmm7
-	pclmulqdq	$0x10, %xmm10, %xmm7
-	pxor	%xmm0, %xmm7
-
-	#barrett reduction
-_barrett:
-	movdqa	rk7(%rip), %xmm10	# rk7 and rk8 in xmm10
-	movdqa	%xmm7, %xmm0
-	pclmulqdq	$0x01, %xmm10, %xmm7
-	pslldq	$4, %xmm7
-	pclmulqdq	$0x11, %xmm10, %xmm7
-
-	pslldq	$4, %xmm7
-	pxor	%xmm0, %xmm7
-	pextrd	$1, %xmm7, %eax
-
-_cleanup:
-	# scale the result back to 16 bits
-	shr	$16, %eax
-	mov     %rcx, %rsp
-	ret
-
-########################################################################
-
-.align 16
-_less_than_128:
-
-	# check if there is enough buffer to be able to fold 16B at a time
-	cmp	$32, arg3
-	jl	_less_than_32
-	movdqa  SHUF_MASK(%rip), %xmm11
-
-	# now if there is, load the constants
-	movdqa	rk1(%rip), %xmm10	# rk1 and rk2 in xmm10
-
-	movd	arg1_low32, %xmm0	# get the initial crc value
-	pslldq	$12, %xmm0	# align it to its correct place
-	movdqu	(arg2), %xmm7	# load the plaintext
-	pshufb	%xmm11, %xmm7	# byte-reflect the plaintext
-	pxor	%xmm0, %xmm7
-
-
-	# update the buffer pointer
-	add	$16, arg2
-
-	# update the counter. subtract 32 instead of 16 to save one
-	# instruction from the loop
-	sub	$32, arg3
-
-	jmp	_16B_reduction_loop
-
-
-.align 16
-_less_than_32:
-	# mov initial crc to the return value. this is necessary for
-	# zero-length buffers.
-	mov	arg1_low32, %eax
-	test	arg3, arg3
-	je	_cleanup
-
-	movdqa  SHUF_MASK(%rip), %xmm11
-
-	movd	arg1_low32, %xmm0	# get the initial crc value
-	pslldq	$12, %xmm0	# align it to its correct place
-
-	cmp	$16, arg3
-	je	_exact_16_left
-	jl	_less_than_16_left
-
-	movdqu	(arg2), %xmm7	# load the plaintext
-	pshufb	%xmm11, %xmm7	# byte-reflect the plaintext
-	pxor	%xmm0 , %xmm7	# xor the initial crc value
-	add	$16, arg2
-	sub	$16, arg3
-	movdqa	rk1(%rip), %xmm10	# rk1 and rk2 in xmm10
-	jmp	_get_last_two_xmms
-
-
-.align 16
-_less_than_16_left:
-	# use stack space to load data less than 16 bytes, zero-out
-	# the 16B in memory first.
-
-	pxor	%xmm1, %xmm1
-	mov	%rsp, %r11
-	movdqa	%xmm1, (%r11)
-
-	cmp	$4, arg3
-	jl	_only_less_than_4
-
-	# backup the counter value
-	mov	arg3, %r9
-	cmp	$8, arg3
-	jl	_less_than_8_left
-
-	# load 8 Bytes
-	mov	(arg2), %rax
-	mov	%rax, (%r11)
-	add	$8, %r11
-	sub	$8, arg3
-	add	$8, arg2
-_less_than_8_left:
-
-	cmp	$4, arg3
-	jl	_less_than_4_left
-
-	# load 4 Bytes
-	mov	(arg2), %eax
-	mov	%eax, (%r11)
-	add	$4, %r11
-	sub	$4, arg3
-	add	$4, arg2
-_less_than_4_left:
-
-	cmp	$2, arg3
-	jl	_less_than_2_left
-
-	# load 2 Bytes
-	mov	(arg2), %ax
-	mov	%ax, (%r11)
-	add	$2, %r11
-	sub	$2, arg3
-	add	$2, arg2
-_less_than_2_left:
-	cmp     $1, arg3
-        jl      _zero_left
-
-	# load 1 Byte
-	mov	(arg2), %al
-	mov	%al, (%r11)
-_zero_left:
-	movdqa	(%rsp), %xmm7
-	pshufb	%xmm11, %xmm7
-	pxor	%xmm0 , %xmm7	# xor the initial crc value
-
-	# shl r9, 4
-	lea	pshufb_shf_table+16(%rip), %rax
-	sub	%r9, %rax
-	movdqu	(%rax), %xmm0
-	pxor	mask1(%rip), %xmm0
-
-	pshufb	%xmm0, %xmm7
-	jmp	_128_done
-
-.align 16
-_exact_16_left:
-	movdqu	(arg2), %xmm7
-	pshufb	%xmm11, %xmm7
-	pxor	%xmm0 , %xmm7   # xor the initial crc value
-
-	jmp	_128_done
-
-_only_less_than_4:
-	cmp	$3, arg3
-	jl	_only_less_than_3
-
-	# load 3 Bytes
-	mov	(arg2), %al
-	mov	%al, (%r11)
-
-	mov	1(arg2), %al
-	mov	%al, 1(%r11)
-
-	mov	2(arg2), %al
-	mov	%al, 2(%r11)
-
-	movdqa	 (%rsp), %xmm7
-	pshufb	 %xmm11, %xmm7
-	pxor	 %xmm0 , %xmm7  # xor the initial crc value
-
-	psrldq	$5, %xmm7
-
-	jmp	_barrett
-_only_less_than_3:
-	cmp	$2, arg3
-	jl	_only_less_than_2
-
-	# load 2 Bytes
-	mov	(arg2), %al
-	mov	%al, (%r11)
-
-	mov	1(arg2), %al
-	mov	%al, 1(%r11)
-
-	movdqa	(%rsp), %xmm7
-	pshufb	%xmm11, %xmm7
-	pxor	%xmm0 , %xmm7   # xor the initial crc value
-
-	psrldq	$6, %xmm7
-
-	jmp	_barrett
-_only_less_than_2:
-
-	# load 1 Byte
-	mov	(arg2), %al
-	mov	%al, (%r11)
-
-	movdqa	(%rsp), %xmm7
-	pshufb	%xmm11, %xmm7
-	pxor	%xmm0 , %xmm7   # xor the initial crc value
-
-	psrldq	$7, %xmm7
-
-	jmp	_barrett
-
-ENDPROC(crc_t10dif_pcl)
-
-.data
-
-# precomputed constants
-# these constants are precomputed from the poly:
-# 0x8bb70000 (0x8bb7 scaled to 32 bits)
-.align 16
-# Q = 0x18BB70000
-# rk1 = 2^(32*3) mod Q << 32
-# rk2 = 2^(32*5) mod Q << 32
-# rk3 = 2^(32*15) mod Q << 32
-# rk4 = 2^(32*17) mod Q << 32
-# rk5 = 2^(32*3) mod Q << 32
-# rk6 = 2^(32*2) mod Q << 32
-# rk7 = floor(2^64/Q)
-# rk8 = Q
-rk1:
-.quad 0x2d56000000000000
-rk2:
-.quad 0x06df000000000000
-rk3:
-.quad 0x9d9d000000000000
-rk4:
-.quad 0x7cf5000000000000
-rk5:
-.quad 0x2d56000000000000
-rk6:
-.quad 0x1368000000000000
-rk7:
-.quad 0x00000001f65a57f8
-rk8:
-.quad 0x000000018bb70000
-
-rk9:
-.quad 0xceae000000000000
-rk10:
-.quad 0xbfd6000000000000
-rk11:
-.quad 0x1e16000000000000
-rk12:
-.quad 0x713c000000000000
-rk13:
-.quad 0xf7f9000000000000
-rk14:
-.quad 0x80a6000000000000
-rk15:
-.quad 0x044c000000000000
-rk16:
-.quad 0xe658000000000000
-rk17:
-.quad 0xad18000000000000
-rk18:
-.quad 0xa497000000000000
-rk19:
-.quad 0x6ee3000000000000
-rk20:
-.quad 0xe7b5000000000000
-
-
-
-mask1:
-.octa 0x80808080808080808080808080808080
-mask2:
-.octa 0x00000000FFFFFFFFFFFFFFFFFFFFFFFF
-
-SHUF_MASK:
-.octa 0x000102030405060708090A0B0C0D0E0F
-
-pshufb_shf_table:
-# use these values for shift constants for the pshufb instruction
-# different alignments result in values as shown:
-#	DDQ 0x008f8e8d8c8b8a898887868584838281 # shl 15 (16-1) / shr1
-#	DDQ 0x01008f8e8d8c8b8a8988878685848382 # shl 14 (16-3) / shr2
-#	DDQ 0x0201008f8e8d8c8b8a89888786858483 # shl 13 (16-4) / shr3
-#	DDQ 0x030201008f8e8d8c8b8a898887868584 # shl 12 (16-4) / shr4
-#	DDQ 0x04030201008f8e8d8c8b8a8988878685 # shl 11 (16-5) / shr5
-#	DDQ 0x0504030201008f8e8d8c8b8a89888786 # shl 10 (16-6) / shr6
-#	DDQ 0x060504030201008f8e8d8c8b8a898887 # shl 9  (16-7) / shr7
-#	DDQ 0x07060504030201008f8e8d8c8b8a8988 # shl 8  (16-8) / shr8
-#	DDQ 0x0807060504030201008f8e8d8c8b8a89 # shl 7  (16-9) / shr9
-#	DDQ 0x090807060504030201008f8e8d8c8b8a # shl 6  (16-10) / shr10
-#	DDQ 0x0a090807060504030201008f8e8d8c8b # shl 5  (16-11) / shr11
-#	DDQ 0x0b0a090807060504030201008f8e8d8c # shl 4  (16-12) / shr12
-#	DDQ 0x0c0b0a090807060504030201008f8e8d # shl 3  (16-13) / shr13
-#	DDQ 0x0d0c0b0a090807060504030201008f8e # shl 2  (16-14) / shr14
-#	DDQ 0x0e0d0c0b0a090807060504030201008f # shl 1  (16-15) / shr15
-.octa 0x8f8e8d8c8b8a89888786858483828100
-.octa 0x000e0d0c0b0a09080706050403020100
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
deleted file mode 100644
index 7845d7fd54c0..000000000000
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ /dev/null
@@ -1,151 +0,0 @@
-/*
- * Cryptographic API.
- *
- * T10 Data Integrity Field CRC16 Crypto Transform using PCLMULQDQ Instructions
- *
- * Copyright (C) 2013 Intel Corporation
- * Author: Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc-t10dif.h>
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <asm/i387.h>
-#include <asm/cpufeature.h>
-#include <asm/cpu_device_id.h>
-
-asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,
-				size_t len);
-
-struct chksum_desc_ctx {
-	__u16 crc;
-};
-
-/*
- * Steps through buffer one byte at at time, calculates reflected
- * crc using table.
- */
-
-static int chksum_init(struct shash_desc *desc)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	ctx->crc = 0;
-
-	return 0;
-}
-
-static int chksum_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int length)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	if (irq_fpu_usable()) {
-		kernel_fpu_begin();
-		ctx->crc = crc_t10dif_pcl(ctx->crc, data, length);
-		kernel_fpu_end();
-	} else
-		ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
-	return 0;
-}
-
-static int chksum_final(struct shash_desc *desc, u8 *out)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	*(__u16 *)out = ctx->crc;
-	return 0;
-}
-
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
-			u8 *out)
-{
-	if (irq_fpu_usable()) {
-		kernel_fpu_begin();
-		*(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
-		kernel_fpu_end();
-	} else
-		*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
-	return 0;
-}
-
-static int chksum_finup(struct shash_desc *desc, const u8 *data,
-			unsigned int len, u8 *out)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, len, out);
-}
-
-static int chksum_digest(struct shash_desc *desc, const u8 *data,
-			 unsigned int length, u8 *out)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
-}
-
-static struct shash_alg alg = {
-	.digestsize		=	CRC_T10DIF_DIGEST_SIZE,
-	.init		=	chksum_init,
-	.update		=	chksum_update,
-	.final		=	chksum_final,
-	.finup		=	chksum_finup,
-	.digest		=	chksum_digest,
-	.descsize		=	sizeof(struct chksum_desc_ctx),
-	.base			=	{
-		.cra_name		=	"crct10dif",
-		.cra_driver_name	=	"crct10dif-pclmul",
-		.cra_priority		=	200,
-		.cra_blocksize		=	CRC_T10DIF_BLOCK_SIZE,
-		.cra_module		=	THIS_MODULE,
-	}
-};
-
-static const struct x86_cpu_id crct10dif_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, crct10dif_cpu_id);
-
-static int __init crct10dif_intel_mod_init(void)
-{
-	if (!x86_match_cpu(crct10dif_cpu_id))
-		return -ENODEV;
-
-	return crypto_register_shash(&alg);
-}
-
-static void __exit crct10dif_intel_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-module_init(crct10dif_intel_mod_init);
-module_exit(crct10dif_intel_mod_fini);
-
-MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
-MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
-MODULE_LICENSE("GPL");
-
-MODULE_ALIAS("crct10dif");
-MODULE_ALIAS("crct10dif-pclmul");
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 653668d140f9..4a8cb8d7cbd5 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params)
 	 */
 	if (boot_params->sentinel) {
 		/* fields in boot_params are left uninitialized, clear them */
-		memset(&boot_params->olpc_ofw_header, 0,
+		memset(&boot_params->ext_ramdisk_image, 0,
 		       (char *)&boot_params->efi_info -
-			(char *)&boot_params->olpc_ofw_header);
+			(char *)&boot_params->ext_ramdisk_image);
 		memset(&boot_params->kbd_status, 0,
 		       (char *)&boot_params->hdr -
 		       (char *)&boot_params->kbd_status);
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 50e5c58ced23..4c019179a57d 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
 
 extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
 extern int apply_microcode_amd(int cpu);
-extern enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size);
+extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
 
 #ifdef CONFIG_MICROCODE_AMD_EARLY
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index f2b489cf1602..3bf2dd0cf61f 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -55,9 +55,53 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
+
+/*
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and
+ * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset
+ * into this range.
+ */
+#define PTE_FILE_MAX_BITS	28
+#define PTE_FILE_SHIFT1		(_PAGE_BIT_PRESENT + 1)
+#define PTE_FILE_SHIFT2		(_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3		(_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT4		(_PAGE_BIT_SOFT_DIRTY + 1)
+#define PTE_FILE_BITS1		(PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
+#define PTE_FILE_BITS3		(PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
+
+#define pte_to_pgoff(pte)						\
+	((((pte).pte_low >> (PTE_FILE_SHIFT1))				\
+	  & ((1U << PTE_FILE_BITS1) - 1)))				\
+	+ ((((pte).pte_low >> (PTE_FILE_SHIFT2))			\
+	    & ((1U << PTE_FILE_BITS2) - 1))				\
+	   << (PTE_FILE_BITS1))						\
+	+ ((((pte).pte_low >> (PTE_FILE_SHIFT3))			\
+	    & ((1U << PTE_FILE_BITS3) - 1))				\
+	   << (PTE_FILE_BITS1 + PTE_FILE_BITS2))			\
+	+ ((((pte).pte_low >> (PTE_FILE_SHIFT4)))			\
+	    << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))
+
+#define pgoff_to_pte(off)						\
+	((pte_t) { .pte_low =						\
+	 ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)	\
+	 + ((((off) >> PTE_FILE_BITS1)					\
+	     & ((1U << PTE_FILE_BITS2) - 1))				\
+	    << PTE_FILE_SHIFT2)						\
+	 + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))		\
+	     & ((1U << PTE_FILE_BITS3) - 1))				\
+	    << PTE_FILE_SHIFT3)						\
+	 + ((((off) >>							\
+	      (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)))	\
+	    << PTE_FILE_SHIFT4)						\
+	 + _PAGE_FILE })
+
+#else /* CONFIG_MEM_SOFT_DIRTY */
+
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
- * split up the 29 bits of offset into this range:
+ * split up the 29 bits of offset into this range.
  */
 #define PTE_FILE_MAX_BITS	29
 #define PTE_FILE_SHIFT1		(_PAGE_BIT_PRESENT + 1)
@@ -88,6 +132,8 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 	    << PTE_FILE_SHIFT3)						\
 	 + _PAGE_FILE })
 
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
 /* Encode and de-code a swap entry */
 #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 4cc9f2b7cdc3..81bb91b49a88 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -179,6 +179,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
+ *
+ * For soft-dirty tracking 11 bit is taken from
+ * the low part of pte as well.
  */
 #define pte_to_pgoff(pte) ((pte).pte_high)
 #define pgoff_to_pte(off)						\
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 7dc305a46058..1c00631164c2 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -314,6 +314,36 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
 }
 
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_mksoft_dirty(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline int pte_file_soft_dirty(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SOFT_DIRTY;
+}
+
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index c98ac63aae48..f4843e031131 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -61,12 +61,27 @@
  * they do not conflict with each other.
  */
 
+#define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_HIDDEN
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
+#define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
 #else
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
+/*
+ * Tracking soft dirty bit when a page goes to a swap is tricky.
+ * We need a bit which can be stored in pte _and_ not conflict
+ * with swap entry format. On x86 bits 6 and 7 are *not* involved
+ * into swap entry computation, but bit 6 is used for nonlinear
+ * file mapping, so we borrow bit 7 for soft dirty tracking.
+ */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY	_PAGE_PSE
+#else
+#define _PAGE_SWP_SOFT_DIRTY	(_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 33692eaabab5..e3ddd7db723f 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -233,8 +233,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
-/* The {read|write|spin}_lock() on x86 are full memory barriers. */
-static inline void smp_mb__after_lock(void) { }
-#define ARCH_HAS_SMP_MB_AFTER_LOCK
-
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f654ecefea5b..08a089043ccf 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -512,7 +512,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
 static const int amd_erratum_383[];
 static const int amd_erratum_400[];
-static bool cpu_has_amd_erratum(const int *erratum);
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
 static void init_amd(struct cpuinfo_x86 *c)
 {
@@ -729,11 +729,11 @@ static void init_amd(struct cpuinfo_x86 *c)
 		value &= ~(1ULL << 24);
 		wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
 
-		if (cpu_has_amd_erratum(amd_erratum_383))
+		if (cpu_has_amd_erratum(c, amd_erratum_383))
 			set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
 	}
 
-	if (cpu_has_amd_erratum(amd_erratum_400))
+	if (cpu_has_amd_erratum(c, amd_erratum_400))
 		set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
 
 	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
@@ -878,23 +878,13 @@ static const int amd_erratum_400[] =
 static const int amd_erratum_383[] =
 	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
 
-static bool cpu_has_amd_erratum(const int *erratum)
+
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
-	struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
 	int osvw_id = *erratum++;
 	u32 range;
 	u32 ms;
 
-	/*
-	 * If called early enough that current_cpu_data hasn't been initialized
-	 * yet, fall back to boot_cpu_data.
-	 */
-	if (cpu->x86 == 0)
-		cpu = &boot_cpu_data;
-
-	if (cpu->x86_vendor != X86_VENDOR_AMD)
-		return false;
-
 	if (osvw_id >= 0 && osvw_id < 65536 &&
 	    cpu_has(cpu, X86_FEATURE_OSVW)) {
 		u64 osvw_len;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index e2703520d120..c370e1c4468b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -111,8 +111,8 @@ static struct severity {
 #ifdef	CONFIG_MEMORY_FAILURE
 	MCESEV(
 		KEEP, "Action required but unaffected thread is continuable",
-		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR),
-		MCGMASK(MCG_STATUS_RIPV, MCG_STATUS_RIPV)
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR, MCI_UC_SAR|MCI_ADDR),
+		MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV)
 		),
 	MCESEV(
 		AR, "Action required: data load error in a user process",
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index fbc9210b45bc..a45d8d4ace10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2270,6 +2270,7 @@ __init int intel_pmu_init(void)
 	case 70:
 	case 71:
 	case 63:
+	case 69:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index cad791dbde95..1fb6c72717bd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = {
 static struct uncore_event_desc snbep_uncore_qpi_events[] = {
 	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
 	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x02,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x03,umask=0x04"),
+	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
 	{ /* end: all zeroes */ },
 };
 
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 94ab6b90dd3f..63bdb29b2549 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -196,15 +196,23 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 static void __init intel_remapping_check(int num, int slot, int func)
 {
 	u8 revision;
+	u16 device;
 
+	device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
 	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
 	/*
-	 * Revision 0x13 of this chipset supports irq remapping
-	 * but has an erratum that breaks its behavior, flag it as such
+ 	 * Revision 13 of all triggering devices id in this quirk have
+	 * a problem draining interrupts when irq remapping is enabled,
+	 * and should be flagged as broken.  Additionally revisions 0x12
+	 * and 0x22 of device id 0x3405 has this problem.
 	 */
 	if (revision == 0x13)
 		set_irq_remapping_broken();
+	else if ((device == 0x3405) &&
+	    ((revision == 0x12) ||
+	     (revision == 0x22)))
+		set_irq_remapping_broken();
 
 }
 
@@ -239,6 +247,8 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
 	{ PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST,
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+	{ PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST,
+	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{}
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 202d24f0f7e7..5d576ab34403 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -116,7 +116,7 @@ static void mxcsr_feature_mask_init(void)
 
 	if (cpu_has_fxsr) {
 		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-		asm volatile("fxsave %0" : : "m" (fx_scratch));
+		asm volatile("fxsave %0" : "+m" (fx_scratch));
 		mask = fx_scratch.mxcsr_mask;
 		if (mask == 0)
 			mask = 0x0000ffbf;
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 47ebb1dbfbcb..7123b5df479d 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -145,10 +145,9 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 	return 0;
 }
 
-static unsigned int verify_patch_size(int cpu, u32 patch_size,
+static unsigned int verify_patch_size(u8 family, u32 patch_size,
 				      unsigned int size)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 max_size;
 
 #define F1XH_MPB_MAX_SIZE 2048
@@ -156,7 +155,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 #define F15H_MPB_MAX_SIZE 4096
 #define F16H_MPB_MAX_SIZE 3458
 
-	switch (c->x86) {
+	switch (family) {
 	case 0x14:
 		max_size = F14H_MPB_MAX_SIZE;
 		break;
@@ -220,12 +219,13 @@ int apply_microcode_amd(int cpu)
 		return 0;
 	}
 
-	if (__apply_microcode_amd(mc_amd))
+	if (__apply_microcode_amd(mc_amd)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
-	else
-		pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
-			mc_amd->hdr.patch_id);
+		return -1;
+	}
+	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
+		mc_amd->hdr.patch_id);
 
 	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
 	c->microcode = mc_amd->hdr.patch_id;
@@ -276,9 +276,8 @@ static void cleanup(void)
  * driver cannot continue functioning normally. In such cases, we tear
  * down everything we've used up so far and exit.
  */
-static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
+static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_header_amd *mc_hdr;
 	struct ucode_patch *patch;
 	unsigned int patch_size, crnt_size, ret;
@@ -298,7 +297,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
 
 	/* check if patch is for the current family */
 	proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
-	if (proc_fam != c->x86)
+	if (proc_fam != family)
 		return crnt_size;
 
 	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
@@ -307,7 +306,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
 		return crnt_size;
 	}
 
-	ret = verify_patch_size(cpu, patch_size, leftover);
+	ret = verify_patch_size(family, patch_size, leftover);
 	if (!ret) {
 		pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
 		return crnt_size;
@@ -338,7 +337,8 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
 	return crnt_size;
 }
 
-static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
+					     size_t size)
 {
 	enum ucode_state ret = UCODE_ERROR;
 	unsigned int leftover;
@@ -361,7 +361,7 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz
 	}
 
 	while (leftover) {
-		crnt_size = verify_and_add_patch(cpu, fw, leftover);
+		crnt_size = verify_and_add_patch(family, fw, leftover);
 		if (crnt_size < 0)
 			return ret;
 
@@ -372,22 +372,22 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz
 	return UCODE_OK;
 }
 
-enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size)
+enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
 	enum ucode_state ret;
 
 	/* free old equiv table */
 	free_equiv_cpu_table();
 
-	ret = __load_microcode_amd(cpu, data, size);
+	ret = __load_microcode_amd(family, data, size);
 
 	if (ret != UCODE_OK)
 		cleanup();
 
 #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
 	/* save BSP's matching patch for early load */
-	if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(cpu);
+	if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
+		struct ucode_patch *p = find_patch(smp_processor_id());
 		if (p) {
 			memset(amd_bsp_mpb, 0, MPB_MAX_SIZE);
 			memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data),
@@ -440,7 +440,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(cpu, fw->data, fw->size);
+	ret = load_microcode_amd(c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);
diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c
index 1d14ffee5749..6073104ccaa3 100644
--- a/arch/x86/kernel/microcode_amd_early.c
+++ b/arch/x86/kernel/microcode_amd_early.c
@@ -238,25 +238,17 @@ static void __init collect_cpu_sig_on_bsp(void *arg)
 	uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
 #else
-static void collect_cpu_info_amd_early(struct cpuinfo_x86 *c,
-						 struct ucode_cpu_info *uci)
+void load_ucode_amd_ap(void)
 {
+	unsigned int cpu = smp_processor_id();
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	u32 rev, eax;
 
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
 	eax = cpuid_eax(0x00000001);
 
-	uci->cpu_sig.sig = eax;
 	uci->cpu_sig.rev = rev;
-	c->microcode = rev;
-	c->x86 = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
-}
-
-void load_ucode_amd_ap(void)
-{
-	unsigned int cpu = smp_processor_id();
-
-	collect_cpu_info_amd_early(&cpu_data(cpu), ucode_cpu_info + cpu);
+	uci->cpu_sig.sig = eax;
 
 	if (cpu && !ucode_loaded) {
 		void *ucode;
@@ -265,8 +257,10 @@ void load_ucode_amd_ap(void)
 			return;
 
 		ucode = (void *)(initrd_start + ucode_offset);
-		if (load_microcode_amd(0, ucode, ucode_size) != UCODE_OK)
+		eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
+		if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK)
 			return;
+
 		ucode_loaded = true;
 	}
 
@@ -278,6 +272,8 @@ int __init save_microcode_in_initrd_amd(void)
 {
 	enum ucode_state ret;
 	void *ucode;
+	u32 eax;
+
 #ifdef CONFIG_X86_32
 	unsigned int bsp = boot_cpu_data.cpu_index;
 	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
@@ -293,7 +289,10 @@ int __init save_microcode_in_initrd_amd(void)
 		return 0;
 
 	ucode = (void *)(initrd_start + ucode_offset);
-	ret = load_microcode_amd(0, ucode, ucode_size);
+	eax   = cpuid_eax(0x00000001);
+	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
+
+	ret = load_microcode_amd(eax, ucode, ucode_size);
 	if (ret != UCODE_OK)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index dbded5aedb81..30277e27431a 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
 				*begin = new_begin;
 		}
 	} else {
-		*begin = TASK_UNMAPPED_BASE;
+		*begin = current->mm->mmap_legacy_base;
 		*end = TASK_SIZE;
 	}
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 62c29a5bfe26..25e7e1372bb2 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -112,11 +112,13 @@ static unsigned long mmap_legacy_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+	mm->mmap_legacy_base = mmap_legacy_base();
+	mm->mmap_base = mmap_base();
+
 	if (mmap_is_legacy()) {
-		mm->mmap_base = mmap_legacy_base();
+		mm->mmap_base = mm->mmap_legacy_base;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 643b8b5eee86..8244f5ec2f4c 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/irq.h>
 #include <linux/module.h>
+#include <linux/reboot.h>
 #include <linux/serial_reg.h>
 #include <linux/serial_8250.h>
 #include <linux/reboot.h>
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 056d11faef21..8f3eea6b80c5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -313,6 +313,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
 	e820_add_region(start, end - start, type);
 }
 
+void xen_ignore_unusable(struct e820entry *list, size_t map_size)
+{
+	struct e820entry *entry;
+	unsigned int i;
+
+	for (i = 0, entry = list; i < map_size; i++, entry++) {
+		if (entry->type == E820_UNUSABLE)
+			entry->type = E820_RAM;
+	}
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
@@ -353,6 +364,17 @@ char * __init xen_memory_setup(void)
 	}
 	BUG_ON(rc);
 
+	/*
+	 * Xen won't allow a 1:1 mapping to be created to UNUSABLE
+	 * regions, so if we're using the machine memory map leave the
+	 * region as RAM as it is in the pseudo-physical map.
+	 *
+	 * UNUSABLE regions in domUs are not handled and will need
+	 * a patch in the future.
+	 */
+	if (xen_initial_domain())
+		xen_ignore_unusable(map, memmap.nr_entries);
+
 	/* Make sure the Xen-supplied memory map is well-ordered. */
 	sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index ca92754eb846..b81c88e51daa 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -694,8 +694,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc;
-	rc = native_cpu_up(cpu, tidle);
-	WARN_ON (xen_smp_intr_init(cpu));
+	/*
+	 * xen_smp_intr_init() needs to run before native_cpu_up()
+	 * so that IPI vectors are set up on the booting CPU before
+	 * it is marked online in native_cpu_up().
+	*/
+	rc = xen_smp_intr_init(cpu);
+	WARN_ON(rc);
+	if (!rc)
+		rc =  native_cpu_up(cpu, tidle);
 	return rc;
 }
 
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 69ce573f1224..aca01164f002 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -376,25 +376,6 @@ config CRYPTO_CRC32_PCLMUL
 	  which will enable any routine to use the CRC-32-IEEE 802.3 checksum
 	  and gain better performance as compared with the table implementation.
 
-config CRYPTO_CRCT10DIF
-	tristate "CRCT10DIF algorithm"
-	select CRYPTO_HASH
-	help
-	  CRC T10 Data Integrity Field computation is being cast as
-	  a crypto transform.  This allows for faster crc t10 diff
-	  transforms to be used if they are available.
-
-config CRYPTO_CRCT10DIF_PCLMUL
-	tristate "CRCT10DIF PCLMULQDQ hardware acceleration"
-	depends on X86 && 64BIT && CRC_T10DIF
-	select CRYPTO_HASH
-	help
-	  For x86_64 processors with SSE4.2 and PCLMULQDQ supported,
-	  CRC T10 DIF PCLMULQDQ computation can be hardware
-	  accelerated PCLMULQDQ instruction. This option will create
-	  'crct10dif-plcmul' module, which is faster when computing the
-	  crct10dif checksum as compared with the generic table implementation.
-
 config CRYPTO_GHASH
 	tristate "GHASH digest algorithm"
 	select CRYPTO_GF128MUL
diff --git a/crypto/Makefile b/crypto/Makefile
index 2d5ed08a239f..2ba0df2f908f 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -83,7 +83,6 @@ obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
 obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o
 obj-$(CONFIG_CRYPTO_CRC32) += crc32.o
-obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif.o
 obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
 obj-$(CONFIG_CRYPTO_LZO) += lzo.o
 obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
diff --git a/crypto/crct10dif.c b/crypto/crct10dif.c
deleted file mode 100644
index 92aca96d6b98..000000000000
--- a/crypto/crct10dif.c
+++ /dev/null
@@ -1,178 +0,0 @@
-/*
- * Cryptographic API.
- *
- * T10 Data Integrity Field CRC16 Crypto Transform
- *
- * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
- * Written by Martin K. Petersen <martin.petersen@oracle.com>
- * Copyright (C) 2013 Intel Corporation
- * Author: Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc-t10dif.h>
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-
-struct chksum_desc_ctx {
-	__u16 crc;
-};
-
-/* Table generated using the following polynomium:
- * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
- * gt: 0x8bb7
- */
-static const __u16 t10_dif_crc_table[256] = {
-	0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B,
-	0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6,
-	0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6,
-	0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B,
-	0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1,
-	0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C,
-	0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C,
-	0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781,
-	0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8,
-	0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255,
-	0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925,
-	0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698,
-	0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472,
-	0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF,
-	0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF,
-	0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02,
-	0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA,
-	0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067,
-	0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17,
-	0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA,
-	0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640,
-	0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD,
-	0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D,
-	0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30,
-	0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759,
-	0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4,
-	0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394,
-	0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29,
-	0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3,
-	0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E,
-	0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E,
-	0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3
-};
-
-__u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len)
-{
-	unsigned int i;
-
-	for (i = 0 ; i < len ; i++)
-		crc = (crc << 8) ^ t10_dif_crc_table[((crc >> 8) ^ buffer[i]) & 0xff];
-
-	return crc;
-}
-EXPORT_SYMBOL(crc_t10dif_generic);
-
-/*
- * Steps through buffer one byte at at time, calculates reflected
- * crc using table.
- */
-
-static int chksum_init(struct shash_desc *desc)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	ctx->crc = 0;
-
-	return 0;
-}
-
-static int chksum_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int length)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
-	return 0;
-}
-
-static int chksum_final(struct shash_desc *desc, u8 *out)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	*(__u16 *)out = ctx->crc;
-	return 0;
-}
-
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
-			u8 *out)
-{
-	*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
-	return 0;
-}
-
-static int chksum_finup(struct shash_desc *desc, const u8 *data,
-			unsigned int len, u8 *out)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, len, out);
-}
-
-static int chksum_digest(struct shash_desc *desc, const u8 *data,
-			 unsigned int length, u8 *out)
-{
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
-}
-
-static struct shash_alg alg = {
-	.digestsize		=	CRC_T10DIF_DIGEST_SIZE,
-	.init		=	chksum_init,
-	.update		=	chksum_update,
-	.final		=	chksum_final,
-	.finup		=	chksum_finup,
-	.digest		=	chksum_digest,
-	.descsize		=	sizeof(struct chksum_desc_ctx),
-	.base			=	{
-		.cra_name		=	"crct10dif",
-		.cra_driver_name	=	"crct10dif-generic",
-		.cra_priority		=	100,
-		.cra_blocksize		=	CRC_T10DIF_BLOCK_SIZE,
-		.cra_module		=	THIS_MODULE,
-	}
-};
-
-static int __init crct10dif_mod_init(void)
-{
-	int ret;
-
-	ret = crypto_register_shash(&alg);
-	return ret;
-}
-
-static void __exit crct10dif_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-module_init(crct10dif_mod_init);
-module_exit(crct10dif_mod_fini);
-
-MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
-MODULE_DESCRIPTION("T10 DIF CRC calculation.");
-MODULE_LICENSE("GPL");
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 25a5934f0e50..66d254ce0d11 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1174,10 +1174,6 @@ static int do_test(int m)
 		ret += tcrypt_test("ghash");
 		break;
 
-	case 47:
-		ret += tcrypt_test("crct10dif");
-		break;
-
 	case 100:
 		ret += tcrypt_test("hmac(md5)");
 		break;
@@ -1502,10 +1498,6 @@ static int do_test(int m)
 		test_hash_speed("crc32c", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 
-	case 320:
-		test_hash_speed("crct10dif", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-
 	case 399:
 		break;
 
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 2f00607039e2..ecddf921a9db 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -2046,16 +2046,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
-		.alg = "crct10dif",
-		.test = alg_test_hash,
-		.fips_allowed = 1,
-		.suite = {
-			.hash = {
-				.vecs = crct10dif_tv_template,
-				.count = CRCT10DIF_TEST_VECTORS
-			}
-		}
-	}, {
 		.alg = "cryptd(__driver-cbc-aes-aesni)",
 		.test = alg_test_null,
 		.fips_allowed = 1,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 7d44aa3d6b44..1e701bc075b9 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -450,39 +450,6 @@ static struct hash_testvec rmd320_tv_template[] = {
 	}
 };
 
-#define CRCT10DIF_TEST_VECTORS	3
-static struct hash_testvec crct10dif_tv_template[] = {
-	{
-		.plaintext = "abc",
-		.psize  = 3,
-#ifdef __LITTLE_ENDIAN
-		.digest = "\x3b\x44",
-#else
-		.digest = "\x44\x3b",
-#endif
-	}, {
-		.plaintext = "1234567890123456789012345678901234567890"
-			     "123456789012345678901234567890123456789",
-		.psize	= 79,
-#ifdef __LITTLE_ENDIAN
-		.digest	= "\x70\x4b",
-#else
-		.digest	= "\x4b\x70",
-#endif
-	}, {
-		.plaintext =
-		"abcddddddddddddddddddddddddddddddddddddddddddddddddddddd",
-		.psize  = 56,
-#ifdef __LITTLE_ENDIAN
-		.digest = "\xe3\x9c",
-#else
-		.digest = "\x9c\xe3",
-#endif
-		.np     = 2,
-		.tap    = { 28, 28 }
-	}
-};
-
 /*
  * SHA1 test vectors  from from FIPS PUB 180-1
  * Long vector from CAVS 5.0
diff --git a/drivers/accessibility/braille/braille_console.c b/drivers/accessibility/braille/braille_console.c
index d21167bfc865..dc34a5b8bcee 100644
--- a/drivers/accessibility/braille/braille_console.c
+++ b/drivers/accessibility/braille/braille_console.c
@@ -359,6 +359,9 @@ int braille_register_console(struct console *console, int index,
 		char *console_options, char *braille_options)
 {
 	int ret;
+
+	if (!(console->flags & CON_BRL))
+		return 0;
 	if (!console_options)
 		/* Only support VisioBraille for now */
 		console_options = "57600o8";
@@ -374,15 +377,17 @@ int braille_register_console(struct console *console, int index,
 	braille_co = console;
 	register_keyboard_notifier(&keyboard_notifier_block);
 	register_vt_notifier(&vt_notifier_block);
-	return 0;
+	return 1;
 }
 
 int braille_unregister_console(struct console *console)
 {
 	if (braille_co != console)
 		return -EINVAL;
+	if (!(console->flags & CON_BRL))
+		return 0;
 	unregister_keyboard_notifier(&keyboard_notifier_block);
 	unregister_vt_notifier(&vt_notifier_block);
 	braille_co = NULL;
-	return 0;
+	return 1;
 }
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index fd6c51cc3acb..5a74a9c1e42c 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -451,7 +451,6 @@ static void acpi_processor_remove(struct acpi_device *device)
 	/* Clean up. */
 	per_cpu(processor_device_array, pr->id) = NULL;
 	per_cpu(processors, pr->id) = NULL;
-	try_offline_node(cpu_to_node(pr->id));
 
 	/* Remove the CPU. */
 	get_online_cpus();
@@ -459,6 +458,8 @@ static void acpi_processor_remove(struct acpi_device *device)
 	acpi_unmap_lsapic(pr->id);
 	put_online_cpus();
 
+	try_offline_node(cpu_to_node(pr->id));
+
  out:
 	free_cpumask_var(pr->throttling.shared_cpu_map);
 	kfree(pr);
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 082b4dd252a8..d405fbad406a 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -117,6 +117,7 @@ struct acpi_battery {
 	struct acpi_device *device;
 	struct notifier_block pm_nb;
 	unsigned long update_time;
+	int revision;
 	int rate_now;
 	int capacity_now;
 	int voltage_now;
@@ -359,6 +360,7 @@ static struct acpi_offsets info_offsets[] = {
 };
 
 static struct acpi_offsets extended_info_offsets[] = {
+	{offsetof(struct acpi_battery, revision), 0},
 	{offsetof(struct acpi_battery, power_unit), 0},
 	{offsetof(struct acpi_battery, design_capacity), 0},
 	{offsetof(struct acpi_battery, full_charge_capacity), 0},
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index f68095756fb7..408f6b2a5fa8 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -31,6 +31,7 @@ static LIST_HEAD(bus_type_list);
 static DECLARE_RWSEM(bus_type_sem);
 
 #define PHYSICAL_NODE_STRING "physical_node"
+#define PHYSICAL_NODE_NAME_SIZE (sizeof(PHYSICAL_NODE_STRING) + 10)
 
 int register_acpi_bus_type(struct acpi_bus_type *type)
 {
@@ -78,41 +79,108 @@ static struct acpi_bus_type *acpi_get_bus_type(struct device *dev)
 	return ret;
 }
 
-static acpi_status do_acpi_find_child(acpi_handle handle, u32 lvl_not_used,
-				      void *addr_p, void **ret_p)
+static acpi_status acpi_dev_present(acpi_handle handle, u32 lvl_not_used,
+				  void *not_used, void **ret_p)
 {
-	unsigned long long addr, sta;
-	acpi_status status;
+	struct acpi_device *adev = NULL;
 
-	status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &addr);
-	if (ACPI_SUCCESS(status) && addr == *((u64 *)addr_p)) {
+	acpi_bus_get_device(handle, &adev);
+	if (adev) {
 		*ret_p = handle;
-		status = acpi_bus_get_status_handle(handle, &sta);
-		if (ACPI_SUCCESS(status) && (sta & ACPI_STA_DEVICE_ENABLED))
-			return AE_CTRL_TERMINATE;
+		return AE_CTRL_TERMINATE;
 	}
 	return AE_OK;
 }
 
-acpi_handle acpi_get_child(acpi_handle parent, u64 address)
+static bool acpi_extra_checks_passed(acpi_handle handle, bool is_bridge)
 {
-	void *ret = NULL;
+	unsigned long long sta;
+	acpi_status status;
+
+	status = acpi_bus_get_status_handle(handle, &sta);
+	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
+		return false;
+
+	if (is_bridge) {
+		void *test = NULL;
+
+		/* Check if this object has at least one child device. */
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+				    acpi_dev_present, NULL, NULL, &test);
+		return !!test;
+	}
+	return true;
+}
+
+struct find_child_context {
+	u64 addr;
+	bool is_bridge;
+	acpi_handle ret;
+	bool ret_checked;
+};
+
+static acpi_status do_find_child(acpi_handle handle, u32 lvl_not_used,
+				 void *data, void **not_used)
+{
+	struct find_child_context *context = data;
+	unsigned long long addr;
+	acpi_status status;
 
-	if (!parent)
-		return NULL;
+	status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &addr);
+	if (ACPI_FAILURE(status) || addr != context->addr)
+		return AE_OK;
 
-	acpi_walk_namespace(ACPI_TYPE_DEVICE, parent, 1, NULL,
-			    do_acpi_find_child, &address, &ret);
-	return (acpi_handle)ret;
+	if (!context->ret) {
+		/* This is the first matching object.  Save its handle. */
+		context->ret = handle;
+		return AE_OK;
+	}
+	/*
+	 * There is more than one matching object with the same _ADR value.
+	 * That really is unexpected, so we are kind of beyond the scope of the
+	 * spec here.  We have to choose which one to return, though.
+	 *
+	 * First, check if the previously found object is good enough and return
+	 * its handle if so.  Second, check the same for the object that we've
+	 * just found.
+	 */
+	if (!context->ret_checked) {
+		if (acpi_extra_checks_passed(context->ret, context->is_bridge))
+			return AE_CTRL_TERMINATE;
+		else
+			context->ret_checked = true;
+	}
+	if (acpi_extra_checks_passed(handle, context->is_bridge)) {
+		context->ret = handle;
+		return AE_CTRL_TERMINATE;
+	}
+	return AE_OK;
 }
-EXPORT_SYMBOL(acpi_get_child);
+
+acpi_handle acpi_find_child(acpi_handle parent, u64 addr, bool is_bridge)
+{
+	if (parent) {
+		struct find_child_context context = {
+			.addr = addr,
+			.is_bridge = is_bridge,
+		};
+
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, parent, 1, do_find_child,
+				    NULL, &context, NULL);
+		return context.ret;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(acpi_find_child);
 
 int acpi_bind_one(struct device *dev, acpi_handle handle)
 {
 	struct acpi_device *acpi_dev;
 	acpi_status status;
 	struct acpi_device_physical_node *physical_node, *pn;
-	char physical_node_name[sizeof(PHYSICAL_NODE_STRING) + 2];
+	char physical_node_name[PHYSICAL_NODE_NAME_SIZE];
+	struct list_head *physnode_list;
+	unsigned int node_id;
 	int retval = -EINVAL;
 
 	if (ACPI_HANDLE(dev)) {
@@ -139,25 +207,27 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
 
 	mutex_lock(&acpi_dev->physical_node_lock);
 
-	/* Sanity check. */
-	list_for_each_entry(pn, &acpi_dev->physical_node_list, node)
+	/*
+	 * Keep the list sorted by node_id so that the IDs of removed nodes can
+	 * be recycled easily.
+	 */
+	physnode_list = &acpi_dev->physical_node_list;
+	node_id = 0;
+	list_for_each_entry(pn, &acpi_dev->physical_node_list, node) {
+		/* Sanity check. */
 		if (pn->dev == dev) {
 			dev_warn(dev, "Already associated with ACPI node\n");
 			goto err_free;
 		}
-
-	/* allocate physical node id according to physical_node_id_bitmap */
-	physical_node->node_id =
-		find_first_zero_bit(acpi_dev->physical_node_id_bitmap,
-		ACPI_MAX_PHYSICAL_NODE);
-	if (physical_node->node_id >= ACPI_MAX_PHYSICAL_NODE) {
-		retval = -ENOSPC;
-		goto err_free;
+		if (pn->node_id == node_id) {
+			physnode_list = &pn->node;
+			node_id++;
+		}
 	}
 
-	set_bit(physical_node->node_id, acpi_dev->physical_node_id_bitmap);
+	physical_node->node_id = node_id;
 	physical_node->dev = dev;
-	list_add_tail(&physical_node->node, &acpi_dev->physical_node_list);
+	list_add(&physical_node->node, physnode_list);
 	acpi_dev->physical_node_count++;
 
 	mutex_unlock(&acpi_dev->physical_node_lock);
@@ -208,7 +278,7 @@ int acpi_unbind_one(struct device *dev)
 
 	mutex_lock(&acpi_dev->physical_node_lock);
 	list_for_each_safe(node, next, &acpi_dev->physical_node_list) {
-		char physical_node_name[sizeof(PHYSICAL_NODE_STRING) + 2];
+		char physical_node_name[PHYSICAL_NODE_NAME_SIZE];
 
 		entry = list_entry(node, struct acpi_device_physical_node,
 			node);
@@ -216,7 +286,6 @@ int acpi_unbind_one(struct device *dev)
 			continue;
 
 		list_del(node);
-		clear_bit(entry->node_id, acpi_dev->physical_node_id_bitmap);
 
 		acpi_dev->physical_node_count--;
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 227aca77ee1e..5da44e81dd4d 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -169,10 +169,8 @@ int acpi_create_platform_device(struct acpi_device *adev,
   -------------------------------------------------------------------------- */
 #if defined(CONFIG_ACPI_VIDEO) || defined(CONFIG_ACPI_VIDEO_MODULE)
 bool acpi_video_backlight_quirks(void);
-bool acpi_video_verify_backlight_support(void);
 #else
 static inline bool acpi_video_backlight_quirks(void) { return false; }
-static inline bool acpi_video_verify_backlight_support(void) { return false; }
 #endif
 
 #endif /* _ACPI_INTERNAL_H_ */
diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c
index aa1227a7e3f2..04a13784dd20 100644
--- a/drivers/acpi/proc.c
+++ b/drivers/acpi/proc.c
@@ -311,6 +311,8 @@ acpi_system_wakeup_device_seq_show(struct seq_file *seq, void *offset)
 			   dev->pnp.bus_id,
 			   (u32) dev->wakeup.sleep_state);
 
+		mutex_lock(&dev->physical_node_lock);
+
 		if (!dev->physical_node_count) {
 			seq_printf(seq, "%c%-8s\n",
 				dev->wakeup.flags.run_wake ? '*' : ' ',
@@ -338,6 +340,8 @@ acpi_system_wakeup_device_seq_show(struct seq_file *seq, void *offset)
 				put_device(ldev);
 			}
 		}
+
+		mutex_unlock(&dev->physical_node_lock);
 	}
 	mutex_unlock(&acpi_device_lock);
 	return 0;
@@ -347,12 +351,16 @@ static void physical_device_enable_wakeup(struct acpi_device *adev)
 {
 	struct acpi_device_physical_node *entry;
 
+	mutex_lock(&adev->physical_node_lock);
+
 	list_for_each_entry(entry,
 		&adev->physical_node_list, node)
 		if (entry->dev && device_can_wakeup(entry->dev)) {
 			bool enable = !device_may_wakeup(entry->dev);
 			device_set_wakeup_enable(entry->dev, enable);
 		}
+
+	mutex_unlock(&adev->physical_node_lock);
 }
 
 static ssize_t
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 6dd237e79b4f..3270d3c8ba4e 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -689,7 +689,7 @@ static int acpi_video_bqc_quirk(struct acpi_video_device *device,
 	 * Some systems always report current brightness level as maximum
 	 * through _BQC, we need to test another value for them.
 	 */
-	test_level = current_level == max_level ? br->levels[2] : max_level;
+	test_level = current_level == max_level ? br->levels[3] : max_level;
 
 	result = acpi_video_device_lcd_set_level(device, test_level);
 	if (result)
@@ -908,10 +908,7 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device)
 		device->cap._DDC = 1;
 	}
 
-	if (acpi_video_init_brightness(device))
-		return;
-
-	if (acpi_video_verify_backlight_support()) {
+	if (acpi_video_backlight_support()) {
 		struct backlight_properties props;
 		struct pci_dev *pdev;
 		acpi_handle acpi_parent;
@@ -920,6 +917,9 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device)
 		static int count = 0;
 		char *name;
 
+		result = acpi_video_init_brightness(device);
+		if (result)
+			return;
 		name = kasprintf(GFP_KERNEL, "acpi_video%d", count);
 		if (!name)
 			return;
@@ -979,11 +979,6 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device)
 		if (result)
 			printk(KERN_ERR PREFIX "Create sysfs link\n");
 
-	} else {
-		/* Remove the brightness object. */
-		kfree(device->brightness->levels);
-		kfree(device->brightness);
-		device->brightness = NULL;
 	}
 }
 
@@ -1366,8 +1361,8 @@ acpi_video_switch_brightness(struct acpi_video_device *device, int event)
 	unsigned long long level_current, level_next;
 	int result = -EINVAL;
 
-	/* no warning message if acpi_backlight=vendor or a quirk is used */
-	if (!acpi_video_verify_backlight_support())
+	/* no warning message if acpi_backlight=vendor is used */
+	if (!acpi_video_backlight_support())
 		return 0;
 
 	if (!device->brightness)
@@ -1875,46 +1870,6 @@ static int acpi_video_bus_remove(struct acpi_device *device)
 	return 0;
 }
 
-static acpi_status video_unregister_backlight(acpi_handle handle, u32 lvl,
-					      void *context, void **rv)
-{
-	struct acpi_device *acpi_dev;
-	struct acpi_video_bus *video;
-	struct acpi_video_device *dev, *next;
-
-	if (acpi_bus_get_device(handle, &acpi_dev))
-		return AE_OK;
-
-	if (acpi_match_device_ids(acpi_dev, video_device_ids))
-		return AE_OK;
-
-	video = acpi_driver_data(acpi_dev);
-	if (!video)
-		return AE_OK;
-
-	acpi_video_bus_stop_devices(video);
-	mutex_lock(&video->device_list_lock);
-	list_for_each_entry_safe(dev, next, &video->video_device_list, entry) {
-		if (dev->backlight) {
-			backlight_device_unregister(dev->backlight);
-			dev->backlight = NULL;
-			kfree(dev->brightness->levels);
-			kfree(dev->brightness);
-		}
-		if (dev->cooling_dev) {
-			sysfs_remove_link(&dev->dev->dev.kobj,
-					  "thermal_cooling");
-			sysfs_remove_link(&dev->cooling_dev->device.kobj,
-					  "device");
-			thermal_cooling_device_unregister(dev->cooling_dev);
-			dev->cooling_dev = NULL;
-		}
-	}
-	mutex_unlock(&video->device_list_lock);
-	acpi_video_bus_start_devices(video);
-	return AE_OK;
-}
-
 static int __init is_i740(struct pci_dev *dev)
 {
 	if (dev->device == 0x00D1)
@@ -1946,25 +1901,14 @@ static int __init intel_opregion_present(void)
 	return opregion;
 }
 
-int __acpi_video_register(bool backlight_quirks)
+int acpi_video_register(void)
 {
-	bool no_backlight;
-	int result;
-
-	no_backlight = backlight_quirks ? acpi_video_backlight_quirks() : false;
-
+	int result = 0;
 	if (register_count) {
 		/*
-		 * If acpi_video_register() has been called already, don't try
-		 * to register acpi_video_bus, but unregister backlight devices
-		 * if no backlight support is requested.
+		 * if the function of acpi_video_register is already called,
+		 * don't register the acpi_vide_bus again and return no error.
 		 */
-		if (no_backlight)
-			acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
-					    ACPI_UINT32_MAX,
-					    video_unregister_backlight,
-					    NULL, NULL, NULL);
-
 		return 0;
 	}
 
@@ -1980,7 +1924,7 @@ int __acpi_video_register(bool backlight_quirks)
 
 	return 0;
 }
-EXPORT_SYMBOL(__acpi_video_register);
+EXPORT_SYMBOL(acpi_video_register);
 
 void acpi_video_unregister(void)
 {
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 826e52def080..c3397748ba46 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -238,12 +238,7 @@ static void acpi_video_caps_check(void)
 
 bool acpi_video_backlight_quirks(void)
 {
-	if (acpi_gbl_osi_data >= ACPI_OSI_WIN_8) {
-		acpi_video_caps_check();
-		acpi_video_support |= ACPI_VIDEO_SKIP_BACKLIGHT;
-		return true;
-	}
-	return false;
+	return acpi_gbl_osi_data >= ACPI_OSI_WIN_8;
 }
 EXPORT_SYMBOL(acpi_video_backlight_quirks);
 
@@ -291,14 +286,6 @@ int acpi_video_backlight_support(void)
 }
 EXPORT_SYMBOL(acpi_video_backlight_support);
 
-/* For the ACPI video driver use only. */
-bool acpi_video_verify_backlight_support(void)
-{
-	return (acpi_video_support & ACPI_VIDEO_SKIP_BACKLIGHT) ?
-		false : acpi_video_backlight_support();
-}
-EXPORT_SYMBOL(acpi_video_verify_backlight_support);
-
 /*
  * Use acpi_backlight=vendor/video to force that backlight switching
  * is processed by vendor specific acpi drivers or video.ko driver.
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 80dc988f01e4..4e737728aee2 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -97,6 +97,15 @@ config SATA_AHCI_PLATFORM
 
 	  If unsure, say N.
 
+config AHCI_IMX
+	tristate "Freescale i.MX AHCI SATA support"
+	depends on SATA_AHCI_PLATFORM && MFD_SYSCON
+	help
+	  This option enables support for the Freescale i.MX SoC's
+	  onboard AHCI SATA.
+
+	  If unsure, say N.
+
 config SATA_FSL
 	tristate "Freescale 3.0Gbps SATA support"
 	depends on FSL_SOC
@@ -107,7 +116,7 @@ config SATA_FSL
 	  If unsure, say N.
 
 config SATA_INIC162X
-	tristate "Initio 162x SATA support"
+	tristate "Initio 162x SATA support (Very Experimental)"
 	depends on PCI
 	help
 	  This option enables support for Initio 162x Serial ATA.
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index c04d0fd038a3..46518c622460 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_SATA_INIC162X)	+= sata_inic162x.o
 obj-$(CONFIG_SATA_SIL24)	+= sata_sil24.o
 obj-$(CONFIG_SATA_DWC)		+= sata_dwc_460ex.o
 obj-$(CONFIG_SATA_HIGHBANK)	+= sata_highbank.o libahci.o
+obj-$(CONFIG_AHCI_IMX)		+= ahci_imx.o
 
 # SFF w/ custom DMA
 obj-$(CONFIG_PDC_ADMA)		+= pdc_adma.o
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 5064f3ea20f1..db4380d70031 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1146,11 +1146,18 @@ int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis)
 		return rc;
 
 	for (i = 0; i < host->n_ports; i++) {
+		const char* desc;
 		struct ahci_port_priv *pp = host->ports[i]->private_data;
 
+		/* pp is NULL for dummy ports */
+		if (pp)
+			desc = pp->irq_desc;
+		else
+			desc = dev_driver_string(host->dev);
+
 		rc = devm_request_threaded_irq(host->dev,
 			irq + i, ahci_hw_interrupt, ahci_thread_fn, IRQF_SHARED,
-			pp->irq_desc, host->ports[i]);
+			desc, host->ports[i]);
 		if (rc)
 			goto out_free_irqs;
 	}
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
new file mode 100644
index 000000000000..58debb0acc3a
--- /dev/null
+++ b/drivers/ata/ahci_imx.c
@@ -0,0 +1,236 @@
+/*
+ * Freescale IMX AHCI SATA platform driver
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * based on the AHCI SATA platform driver by Jeff Garzik and Anton Vorontsov
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/ahci_platform.h>
+#include <linux/of_device.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
+#include "ahci.h"
+
+enum {
+	HOST_TIMER1MS = 0xe0, /* Timer 1-ms */
+};
+
+struct imx_ahci_priv {
+	struct platform_device *ahci_pdev;
+	struct clk *sata_ref_clk;
+	struct clk *ahb_clk;
+	struct regmap *gpr;
+};
+
+static int imx6q_sata_init(struct device *dev, void __iomem *mmio)
+{
+	int ret = 0;
+	unsigned int reg_val;
+	struct imx_ahci_priv *imxpriv = dev_get_drvdata(dev->parent);
+
+	imxpriv->gpr =
+		syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr");
+	if (IS_ERR(imxpriv->gpr)) {
+		dev_err(dev, "failed to find fsl,imx6q-iomux-gpr regmap\n");
+		return PTR_ERR(imxpriv->gpr);
+	}
+
+	ret = clk_prepare_enable(imxpriv->sata_ref_clk);
+	if (ret < 0) {
+		dev_err(dev, "prepare-enable sata_ref clock err:%d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * set PHY Paremeters, two steps to configure the GPR13,
+	 * one write for rest of parameters, mask of first write
+	 * is 0x07fffffd, and the other one write for setting
+	 * the mpll_clk_en.
+	 */
+	regmap_update_bits(imxpriv->gpr, 0x34, IMX6Q_GPR13_SATA_RX_EQ_VAL_MASK
+			| IMX6Q_GPR13_SATA_RX_LOS_LVL_MASK
+			| IMX6Q_GPR13_SATA_RX_DPLL_MODE_MASK
+			| IMX6Q_GPR13_SATA_SPD_MODE_MASK
+			| IMX6Q_GPR13_SATA_MPLL_SS_EN
+			| IMX6Q_GPR13_SATA_TX_ATTEN_MASK
+			| IMX6Q_GPR13_SATA_TX_BOOST_MASK
+			| IMX6Q_GPR13_SATA_TX_LVL_MASK
+			| IMX6Q_GPR13_SATA_TX_EDGE_RATE
+			, IMX6Q_GPR13_SATA_RX_EQ_VAL_3_0_DB
+			| IMX6Q_GPR13_SATA_RX_LOS_LVL_SATA2M
+			| IMX6Q_GPR13_SATA_RX_DPLL_MODE_2P_4F
+			| IMX6Q_GPR13_SATA_SPD_MODE_3P0G
+			| IMX6Q_GPR13_SATA_MPLL_SS_EN
+			| IMX6Q_GPR13_SATA_TX_ATTEN_9_16
+			| IMX6Q_GPR13_SATA_TX_BOOST_3_33_DB
+			| IMX6Q_GPR13_SATA_TX_LVL_1_025_V);
+	regmap_update_bits(imxpriv->gpr, 0x34, IMX6Q_GPR13_SATA_MPLL_CLK_EN,
+			IMX6Q_GPR13_SATA_MPLL_CLK_EN);
+	usleep_range(100, 200);
+
+	/*
+	 * Configure the HWINIT bits of the HOST_CAP and HOST_PORTS_IMPL,
+	 * and IP vendor specific register HOST_TIMER1MS.
+	 * Configure CAP_SSS (support stagered spin up).
+	 * Implement the port0.
+	 * Get the ahb clock rate, and configure the TIMER1MS register.
+	 */
+	reg_val = readl(mmio + HOST_CAP);
+	if (!(reg_val & HOST_CAP_SSS)) {
+		reg_val |= HOST_CAP_SSS;
+		writel(reg_val, mmio + HOST_CAP);
+	}
+	reg_val = readl(mmio + HOST_PORTS_IMPL);
+	if (!(reg_val & 0x1)) {
+		reg_val |= 0x1;
+		writel(reg_val, mmio + HOST_PORTS_IMPL);
+	}
+
+	reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000;
+	writel(reg_val, mmio + HOST_TIMER1MS);
+
+	return 0;
+}
+
+static void imx6q_sata_exit(struct device *dev)
+{
+	struct imx_ahci_priv *imxpriv =  dev_get_drvdata(dev->parent);
+
+	regmap_update_bits(imxpriv->gpr, 0x34, IMX6Q_GPR13_SATA_MPLL_CLK_EN,
+			!IMX6Q_GPR13_SATA_MPLL_CLK_EN);
+	clk_disable_unprepare(imxpriv->sata_ref_clk);
+}
+
+static struct ahci_platform_data imx6q_sata_pdata = {
+	.init = imx6q_sata_init,
+	.exit = imx6q_sata_exit,
+};
+
+static const struct of_device_id imx_ahci_of_match[] = {
+	{ .compatible = "fsl,imx6q-ahci", .data = &imx6q_sata_pdata},
+	{},
+};
+MODULE_DEVICE_TABLE(of, imx_ahci_of_match);
+
+static int imx_ahci_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *mem, *irq, res[2];
+	const struct of_device_id *of_id;
+	const struct ahci_platform_data *pdata = NULL;
+	struct imx_ahci_priv *imxpriv;
+	struct device *ahci_dev;
+	struct platform_device *ahci_pdev;
+	int ret;
+
+	imxpriv = devm_kzalloc(dev, sizeof(*imxpriv), GFP_KERNEL);
+	if (!imxpriv) {
+		dev_err(dev, "can't alloc ahci_host_priv\n");
+		return -ENOMEM;
+	}
+
+	ahci_pdev = platform_device_alloc("ahci", -1);
+	if (!ahci_pdev)
+		return -ENODEV;
+
+	ahci_dev = &ahci_pdev->dev;
+	ahci_dev->parent = dev;
+
+	imxpriv->ahb_clk = devm_clk_get(dev, "ahb");
+	if (IS_ERR(imxpriv->ahb_clk)) {
+		dev_err(dev, "can't get ahb clock.\n");
+		ret = PTR_ERR(imxpriv->ahb_clk);
+		goto err_out;
+	}
+
+	imxpriv->sata_ref_clk = devm_clk_get(dev, "sata_ref");
+	if (IS_ERR(imxpriv->sata_ref_clk)) {
+		dev_err(dev, "can't get sata_ref clock.\n");
+		ret = PTR_ERR(imxpriv->sata_ref_clk);
+		goto err_out;
+	}
+
+	imxpriv->ahci_pdev = ahci_pdev;
+	platform_set_drvdata(pdev, imxpriv);
+
+	of_id = of_match_device(imx_ahci_of_match, dev);
+	if (of_id) {
+		pdata = of_id->data;
+	} else {
+		ret = -EINVAL;
+		goto err_out;
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!mem || !irq) {
+		dev_err(dev, "no mmio/irq resource\n");
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
+	res[0] = *mem;
+	res[1] = *irq;
+
+	ahci_dev->coherent_dma_mask = DMA_BIT_MASK(32);
+	ahci_dev->dma_mask = &ahci_dev->coherent_dma_mask;
+	ahci_dev->of_node = dev->of_node;
+
+	ret = platform_device_add_resources(ahci_pdev, res, 2);
+	if (ret)
+		goto err_out;
+
+	ret = platform_device_add_data(ahci_pdev, pdata, sizeof(*pdata));
+	if (ret)
+		goto err_out;
+
+	ret = platform_device_add(ahci_pdev);
+	if (ret) {
+err_out:
+		platform_device_put(ahci_pdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int imx_ahci_remove(struct platform_device *pdev)
+{
+	struct imx_ahci_priv *imxpriv = platform_get_drvdata(pdev);
+	struct platform_device *ahci_pdev = imxpriv->ahci_pdev;
+
+	platform_device_unregister(ahci_pdev);
+	return 0;
+}
+
+static struct platform_driver imx_ahci_driver = {
+	.probe = imx_ahci_probe,
+	.remove = imx_ahci_remove,
+	.driver = {
+		.name = "ahci-imx",
+		.owner = THIS_MODULE,
+		.of_match_table = imx_ahci_of_match,
+	},
+};
+module_platform_driver(imx_ahci_driver);
+
+MODULE_DESCRIPTION("Freescale i.MX AHCI SATA platform driver");
+MODULE_AUTHOR("Richard Zhu <Hong-Xing.Zhu@freescale.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ahci:imx");
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index b52a10c8eeb9..513ad7ed0c99 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -330,7 +330,7 @@ static const struct pci_device_id piix_pci_tbl[] = {
 	/* SATA Controller IDE (Wellsburg) */
 	{ 0x8086, 0x8d00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 	/* SATA Controller IDE (Wellsburg) */
-	{ 0x8086, 0x8d08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
+	{ 0x8086, 0x8d08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
 	/* SATA Controller IDE (Wellsburg) */
 	{ 0x8086, 0x8d60, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 	/* SATA Controller IDE (Wellsburg) */
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 1c41722bb7e2..20fd337a5731 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -289,24 +289,24 @@ static int sata_pmp_configure(struct ata_device *dev, int print_info)
 
 	/* Disable sending Early R_OK.
 	 * With "cached read" HDD testing and multiple ports busy on a SATA
-	 * host controller, 3726 PMP will very rarely drop a deferred
+	 * host controller, 3x26 PMP will very rarely drop a deferred
 	 * R_OK that was intended for the host. Symptom will be all
 	 * 5 drives under test will timeout, get reset, and recover.
 	 */
-	if (vendor == 0x1095 && devid == 0x3726) {
+	if (vendor == 0x1095 && (devid == 0x3726 || devid == 0x3826)) {
 		u32 reg;
 
 		err_mask = sata_pmp_read(&ap->link, PMP_GSCR_SII_POL, &reg);
 		if (err_mask) {
 			rc = -EIO;
-			reason = "failed to read Sil3726 Private Register";
+			reason = "failed to read Sil3x26 Private Register";
 			goto fail;
 		}
 		reg &= ~0x1;
 		err_mask = sata_pmp_write(&ap->link, PMP_GSCR_SII_POL, reg);
 		if (err_mask) {
 			rc = -EIO;
-			reason = "failed to write Sil3726 Private Register";
+			reason = "failed to write Sil3x26 Private Register";
 			goto fail;
 		}
 	}
@@ -383,8 +383,8 @@ static void sata_pmp_quirks(struct ata_port *ap)
 	u16 devid = sata_pmp_gscr_devid(gscr);
 	struct ata_link *link;
 
-	if (vendor == 0x1095 && devid == 0x3726) {
-		/* sil3726 quirks */
+	if (vendor == 0x1095 && (devid == 0x3726 || devid == 0x3826)) {
+		/* sil3x26 quirks */
 		ata_for_each_link(link, ap, EDGE) {
 			/* link reports offline after LPM */
 			link->flags |= ATA_LFLAG_NO_LPM;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 83c08907e042..b1e880a3c3da 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -206,8 +206,10 @@ static ssize_t ata_scsi_park_store(struct device *device,
 	unsigned long flags;
 	int rc;
 
-	rc = strict_strtol(buf, 10, &input);
-	if (rc || input < -2)
+	rc = kstrtol(buf, 10, &input);
+	if (rc)
+		return rc;
+	if (input < -2)
 		return -EINVAL;
 	if (input > ATA_TMOUT_MAX_PARK) {
 		rc = -EOVERFLOW;
diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c
index 4ec7c04b3f82..26386f0b89a8 100644
--- a/drivers/ata/pata_imx.c
+++ b/drivers/ata/pata_imx.c
@@ -237,6 +237,7 @@ static const struct of_device_id imx_pata_dt_ids[] = {
 		/* sentinel */
 	}
 };
+MODULE_DEVICE_TABLE(of, imx_pata_dt_ids);
 
 static struct platform_driver pata_imx_driver = {
 	.probe		= pata_imx_probe,
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 19720a0a4a65..851bd3f43ac6 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -293,6 +293,7 @@ static void fsl_sata_set_irq_coalescing(struct ata_host *host,
 {
 	struct sata_fsl_host_priv *host_priv = host->private_data;
 	void __iomem *hcr_base = host_priv->hcr_base;
+	unsigned long flags;
 
 	if (count > ICC_MAX_INT_COUNT_THRESHOLD)
 		count = ICC_MAX_INT_COUNT_THRESHOLD;
@@ -305,12 +306,12 @@ static void fsl_sata_set_irq_coalescing(struct ata_host *host,
 			(count > ICC_MIN_INT_COUNT_THRESHOLD))
 		ticks = ICC_SAFE_INT_TICKS;
 
-	spin_lock(&host->lock);
+	spin_lock_irqsave(&host->lock, flags);
 	iowrite32((count << 24 | ticks), hcr_base + ICC);
 
 	intr_coalescing_count = count;
 	intr_coalescing_ticks = ticks;
-	spin_unlock(&host->lock);
+	spin_unlock_irqrestore(&host->lock, flags);
 
 	DPRINTK("interrupt coalescing, count = 0x%x, ticks = %x\n",
 			intr_coalescing_count, intr_coalescing_ticks);
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index d047d92a456f..e9a4f46d962e 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -86,11 +86,11 @@ struct ecx_plat_data {
 
 #define SGPIO_SIGNALS			3
 #define ECX_ACTIVITY_BITS		0x300000
-#define ECX_ACTIVITY_SHIFT		2
+#define ECX_ACTIVITY_SHIFT		0
 #define ECX_LOCATE_BITS			0x80000
 #define ECX_LOCATE_SHIFT		1
 #define ECX_FAULT_BITS			0x400000
-#define ECX_FAULT_SHIFT			0
+#define ECX_FAULT_SHIFT			2
 static inline int sgpio_bit_shift(struct ecx_plat_data *pdata, u32 port,
 				u32 shift)
 {
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index e45131748248..5c54d957370a 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -6,6 +6,18 @@
  *
  * This file is released under GPL v2.
  *
+ * **** WARNING ****
+ *
+ * This driver never worked properly and unfortunately data corruption is
+ * relatively common.  There isn't anyone working on the driver and there's
+ * no support from the vendor.  Do not use this driver in any production
+ * environment.
+ *
+ * http://thread.gmane.org/gmane.linux.debian.devel.bugs.rc/378525/focus=54491
+ * https://bugzilla.kernel.org/show_bug.cgi?id=60565
+ *
+ * *****************
+ *
  * This controller is eccentric and easily locks up if something isn't
  * right.  Documentation is available at initio's website but it only
  * documents registers (not programming model).
@@ -807,6 +819,8 @@ static int inic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ata_print_version_once(&pdev->dev, DRV_VERSION);
 
+	dev_alert(&pdev->dev, "inic162x support is broken with common data corruption issues and will be disabled by default, contact linux-ide@vger.kernel.org if in production use\n");
+
 	/* alloc host */
 	host = ata_host_alloc_pinfo(&pdev->dev, ppi, NR_PORTS);
 	hpriv = devm_kzalloc(&pdev->dev, sizeof(*hpriv), GFP_KERNEL);
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index e69102696533..3455f833e473 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -719,7 +719,8 @@ static int regcache_sync_block_raw(struct regmap *map, void *block,
 		}
 	}
 
-	return regcache_sync_block_raw_flush(map, &data, base, regtmp);
+	return regcache_sync_block_raw_flush(map, &data, base, regtmp +
+			map->reg_stride);
 }
 
 int regcache_sync_block(struct regmap *map, void *block,
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index b81ddfea1da0..e07a5fd58ad7 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -532,11 +532,11 @@ config BLK_DEV_RBD
 	  If unsure, say N.
 
 config BLK_DEV_RSXX
-	tristate "IBM FlashSystem 70/80 PCIe SSD Device Driver"
+	tristate "IBM Flash Adapter 900GB Full Height PCIe Device Driver"
 	depends on PCI
 	help
 	  Device driver for IBM's high speed PCIe SSD
-	  storage devices: FlashSystem-70 and FlashSystem-80.
+	  storage device: Flash Adapter 900GB Full Height.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called rsxx.
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 99cb944a002d..4d45dba7fb8f 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -906,16 +906,10 @@ bio_pageinc(struct bio *bio)
 	int i;
 
 	bio_for_each_segment(bv, bio, i) {
-		page = bv->bv_page;
 		/* Non-zero page count for non-head members of
-		 * compound pages is no longer allowed by the kernel,
-		 * but this has never been seen here.
+		 * compound pages is no longer allowed by the kernel.
 		 */
-		if (unlikely(PageCompound(page)))
-			if (compound_trans_head(page) != page) {
-				pr_crit("page tail used for block I/O\n");
-				BUG();
-			}
+		page = compound_trans_head(bv->bv_page);
 		atomic_inc(&page->_count);
 	}
 }
@@ -924,10 +918,13 @@ static void
 bio_pagedec(struct bio *bio)
 {
 	struct bio_vec *bv;
+	struct page *page;
 	int i;
 
-	bio_for_each_segment(bv, bio, i)
-		atomic_dec(&bv->bv_page->_count);
+	bio_for_each_segment(bv, bio, i) {
+		page = compound_trans_head(bv->bv_page);
+		atomic_dec(&page->_count);
+	}
 }
 
 static void
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 6608076dc39e..28c73ca320a8 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -659,6 +659,27 @@ void drbd_al_shrink(struct drbd_conf *mdev)
 	wake_up(&mdev->al_wait);
 }
 
+int drbd_initialize_al(struct drbd_conf *mdev, void *buffer)
+{
+	struct al_transaction_on_disk *al = buffer;
+	struct drbd_md *md = &mdev->ldev->md;
+	sector_t al_base = md->md_offset + md->al_offset;
+	int al_size_4k = md->al_stripes * md->al_stripe_size_4k;
+	int i;
+
+	memset(al, 0, 4096);
+	al->magic = cpu_to_be32(DRBD_AL_MAGIC);
+	al->transaction_type = cpu_to_be16(AL_TR_INITIALIZED);
+	al->crc32c = cpu_to_be32(crc32c(0, al, 4096));
+
+	for (i = 0; i < al_size_4k; i++) {
+		int err = drbd_md_sync_page_io(mdev, mdev->ldev, al_base + i * 8, WRITE);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 static int w_update_odbm(struct drbd_work *w, int unused)
 {
 	struct update_odbm_work *udw = container_of(w, struct update_odbm_work, w);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index f943aacfdad8..2d7f608d181c 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -832,6 +832,7 @@ struct drbd_tconn {			/* is a resource from the config file */
 	unsigned susp_nod:1;		/* IO suspended because no data */
 	unsigned susp_fen:1;		/* IO suspended because fence peer handler runs */
 	struct mutex cstate_mutex;	/* Protects graceful disconnects */
+	unsigned int connect_cnt;	/* Inc each time a connection is established */
 
 	unsigned long flags;
 	struct net_conf *net_conf;	/* content protected by rcu */
@@ -1132,6 +1133,7 @@ extern void drbd_mdev_cleanup(struct drbd_conf *mdev);
 void drbd_print_uuids(struct drbd_conf *mdev, const char *text);
 
 extern void conn_md_sync(struct drbd_tconn *tconn);
+extern void drbd_md_write(struct drbd_conf *mdev, void *buffer);
 extern void drbd_md_sync(struct drbd_conf *mdev);
 extern int  drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev);
 extern void drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local);
@@ -1466,8 +1468,16 @@ extern void drbd_suspend_io(struct drbd_conf *mdev);
 extern void drbd_resume_io(struct drbd_conf *mdev);
 extern char *ppsize(char *buf, unsigned long long size);
 extern sector_t drbd_new_dev_size(struct drbd_conf *, struct drbd_backing_dev *, sector_t, int);
-enum determine_dev_size { dev_size_error = -1, unchanged = 0, shrunk = 1, grew = 2 };
-extern enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *, enum dds_flags) __must_hold(local);
+enum determine_dev_size {
+	DS_ERROR_SHRINK = -3,
+	DS_ERROR_SPACE_MD = -2,
+	DS_ERROR = -1,
+	DS_UNCHANGED = 0,
+	DS_SHRUNK = 1,
+	DS_GREW = 2
+};
+extern enum determine_dev_size
+drbd_determine_dev_size(struct drbd_conf *, enum dds_flags, struct resize_parms *) __must_hold(local);
 extern void resync_after_online_grow(struct drbd_conf *);
 extern void drbd_reconsider_max_bio_size(struct drbd_conf *mdev);
 extern enum drbd_state_rv drbd_set_role(struct drbd_conf *mdev,
@@ -1633,6 +1643,7 @@ extern int __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector,
 #define drbd_set_out_of_sync(mdev, sector, size) \
 	__drbd_set_out_of_sync(mdev, sector, size, __FILE__, __LINE__)
 extern void drbd_al_shrink(struct drbd_conf *mdev);
+extern int drbd_initialize_al(struct drbd_conf *, void *);
 
 /* drbd_nl.c */
 /* state info broadcast */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a5dca6affcbb..55635edf563b 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2762,8 +2762,6 @@ int __init drbd_init(void)
 	/*
 	 * allocate all necessary structs
 	 */
-	err = -ENOMEM;
-
 	init_waitqueue_head(&drbd_pp_wait);
 
 	drbd_proc = NULL; /* play safe for drbd_cleanup */
@@ -2773,6 +2771,7 @@ int __init drbd_init(void)
 	if (err)
 		goto fail;
 
+	err = -ENOMEM;
 	drbd_proc = proc_create_data("drbd", S_IFREG | S_IRUGO , NULL, &drbd_proc_fops, NULL);
 	if (!drbd_proc)	{
 		printk(KERN_ERR "drbd: unable to register proc file\n");
@@ -2803,7 +2802,6 @@ int __init drbd_init(void)
 fail:
 	drbd_cleanup();
 	if (err == -ENOMEM)
-		/* currently always the case */
 		printk(KERN_ERR "drbd: ran out of memory\n");
 	else
 		printk(KERN_ERR "drbd: initialization failure\n");
@@ -2881,34 +2879,14 @@ struct meta_data_on_disk {
 	u8 reserved_u8[4096 - (7*8 + 10*4)];
 } __packed;
 
-/**
- * drbd_md_sync() - Writes the meta data super block if the MD_DIRTY flag bit is set
- * @mdev:	DRBD device.
- */
-void drbd_md_sync(struct drbd_conf *mdev)
+
+
+void drbd_md_write(struct drbd_conf *mdev, void *b)
 {
-	struct meta_data_on_disk *buffer;
+	struct meta_data_on_disk *buffer = b;
 	sector_t sector;
 	int i;
 
-	/* Don't accidentally change the DRBD meta data layout. */
-	BUILD_BUG_ON(UI_SIZE != 4);
-	BUILD_BUG_ON(sizeof(struct meta_data_on_disk) != 4096);
-
-	del_timer(&mdev->md_sync_timer);
-	/* timer may be rearmed by drbd_md_mark_dirty() now. */
-	if (!test_and_clear_bit(MD_DIRTY, &mdev->flags))
-		return;
-
-	/* We use here D_FAILED and not D_ATTACHING because we try to write
-	 * metadata even if we detach due to a disk failure! */
-	if (!get_ldev_if_state(mdev, D_FAILED))
-		return;
-
-	buffer = drbd_md_get_buffer(mdev);
-	if (!buffer)
-		goto out;
-
 	memset(buffer, 0, sizeof(*buffer));
 
 	buffer->la_size_sect = cpu_to_be64(drbd_get_capacity(mdev->this_bdev));
@@ -2937,6 +2915,35 @@ void drbd_md_sync(struct drbd_conf *mdev)
 		dev_err(DEV, "meta data update failed!\n");
 		drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR);
 	}
+}
+
+/**
+ * drbd_md_sync() - Writes the meta data super block if the MD_DIRTY flag bit is set
+ * @mdev:	DRBD device.
+ */
+void drbd_md_sync(struct drbd_conf *mdev)
+{
+	struct meta_data_on_disk *buffer;
+
+	/* Don't accidentally change the DRBD meta data layout. */
+	BUILD_BUG_ON(UI_SIZE != 4);
+	BUILD_BUG_ON(sizeof(struct meta_data_on_disk) != 4096);
+
+	del_timer(&mdev->md_sync_timer);
+	/* timer may be rearmed by drbd_md_mark_dirty() now. */
+	if (!test_and_clear_bit(MD_DIRTY, &mdev->flags))
+		return;
+
+	/* We use here D_FAILED and not D_ATTACHING because we try to write
+	 * metadata even if we detach due to a disk failure! */
+	if (!get_ldev_if_state(mdev, D_FAILED))
+		return;
+
+	buffer = drbd_md_get_buffer(mdev);
+	if (!buffer)
+		goto out;
+
+	drbd_md_write(mdev, buffer);
 
 	/* Update mdev->ldev->md.la_size_sect,
 	 * since we updated it on metadata. */
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 9e3f441e7e84..8cc1e640f485 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -417,6 +417,7 @@ static enum drbd_fencing_p highest_fencing_policy(struct drbd_tconn *tconn)
 
 bool conn_try_outdate_peer(struct drbd_tconn *tconn)
 {
+	unsigned int connect_cnt;
 	union drbd_state mask = { };
 	union drbd_state val = { };
 	enum drbd_fencing_p fp;
@@ -428,6 +429,10 @@ bool conn_try_outdate_peer(struct drbd_tconn *tconn)
 		return false;
 	}
 
+	spin_lock_irq(&tconn->req_lock);
+	connect_cnt = tconn->connect_cnt;
+	spin_unlock_irq(&tconn->req_lock);
+
 	fp = highest_fencing_policy(tconn);
 	switch (fp) {
 	case FP_NOT_AVAIL:
@@ -492,8 +497,14 @@ bool conn_try_outdate_peer(struct drbd_tconn *tconn)
 	   here, because we might were able to re-establish the connection in the
 	   meantime. */
 	spin_lock_irq(&tconn->req_lock);
-	if (tconn->cstate < C_WF_REPORT_PARAMS && !test_bit(STATE_SENT, &tconn->flags))
-		_conn_request_state(tconn, mask, val, CS_VERBOSE);
+	if (tconn->cstate < C_WF_REPORT_PARAMS && !test_bit(STATE_SENT, &tconn->flags)) {
+		if (tconn->connect_cnt != connect_cnt)
+			/* In case the connection was established and droped
+			   while the fence-peer handler was running, ignore it */
+			conn_info(tconn, "Ignoring fence-peer exit code\n");
+		else
+			_conn_request_state(tconn, mask, val, CS_VERBOSE);
+	}
 	spin_unlock_irq(&tconn->req_lock);
 
 	return conn_highest_pdsk(tconn) <= D_OUTDATED;
@@ -816,15 +827,20 @@ void drbd_resume_io(struct drbd_conf *mdev)
  * Returns 0 on success, negative return values indicate errors.
  * You should call drbd_md_sync() after calling this function.
  */
-enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds_flags flags) __must_hold(local)
+enum determine_dev_size
+drbd_determine_dev_size(struct drbd_conf *mdev, enum dds_flags flags, struct resize_parms *rs) __must_hold(local)
 {
 	sector_t prev_first_sect, prev_size; /* previous meta location */
 	sector_t la_size_sect, u_size;
+	struct drbd_md *md = &mdev->ldev->md;
+	u32 prev_al_stripe_size_4k;
+	u32 prev_al_stripes;
 	sector_t size;
 	char ppb[10];
+	void *buffer;
 
 	int md_moved, la_size_changed;
-	enum determine_dev_size rv = unchanged;
+	enum determine_dev_size rv = DS_UNCHANGED;
 
 	/* race:
 	 * application request passes inc_ap_bio,
@@ -836,6 +852,11 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 	 * still lock the act_log to not trigger ASSERTs there.
 	 */
 	drbd_suspend_io(mdev);
+	buffer = drbd_md_get_buffer(mdev); /* Lock meta-data IO */
+	if (!buffer) {
+		drbd_resume_io(mdev);
+		return DS_ERROR;
+	}
 
 	/* no wait necessary anymore, actually we could assert that */
 	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
@@ -844,7 +865,17 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 	prev_size = mdev->ldev->md.md_size_sect;
 	la_size_sect = mdev->ldev->md.la_size_sect;
 
-	/* TODO: should only be some assert here, not (re)init... */
+	if (rs) {
+		/* rs is non NULL if we should change the AL layout only */
+
+		prev_al_stripes = md->al_stripes;
+		prev_al_stripe_size_4k = md->al_stripe_size_4k;
+
+		md->al_stripes = rs->al_stripes;
+		md->al_stripe_size_4k = rs->al_stripe_size / 4;
+		md->al_size_4k = (u64)rs->al_stripes * rs->al_stripe_size / 4;
+	}
+
 	drbd_md_set_sector_offsets(mdev, mdev->ldev);
 
 	rcu_read_lock();
@@ -852,6 +883,21 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 	rcu_read_unlock();
 	size = drbd_new_dev_size(mdev, mdev->ldev, u_size, flags & DDSF_FORCED);
 
+	if (size < la_size_sect) {
+		if (rs && u_size == 0) {
+			/* Remove "rs &&" later. This check should always be active, but
+			   right now the receiver expects the permissive behavior */
+			dev_warn(DEV, "Implicit shrink not allowed. "
+				 "Use --size=%llus for explicit shrink.\n",
+				 (unsigned long long)size);
+			rv = DS_ERROR_SHRINK;
+		}
+		if (u_size > size)
+			rv = DS_ERROR_SPACE_MD;
+		if (rv != DS_UNCHANGED)
+			goto err_out;
+	}
+
 	if (drbd_get_capacity(mdev->this_bdev) != size ||
 	    drbd_bm_capacity(mdev) != size) {
 		int err;
@@ -867,7 +913,7 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 				    "Leaving size unchanged at size = %lu KB\n",
 				    (unsigned long)size);
 			}
-			rv = dev_size_error;
+			rv = DS_ERROR;
 		}
 		/* racy, see comments above. */
 		drbd_set_my_capacity(mdev, size);
@@ -875,38 +921,57 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 		dev_info(DEV, "size = %s (%llu KB)\n", ppsize(ppb, size>>1),
 		     (unsigned long long)size>>1);
 	}
-	if (rv == dev_size_error)
-		goto out;
+	if (rv <= DS_ERROR)
+		goto err_out;
 
 	la_size_changed = (la_size_sect != mdev->ldev->md.la_size_sect);
 
 	md_moved = prev_first_sect != drbd_md_first_sector(mdev->ldev)
 		|| prev_size	   != mdev->ldev->md.md_size_sect;
 
-	if (la_size_changed || md_moved) {
-		int err;
+	if (la_size_changed || md_moved || rs) {
+		u32 prev_flags;
 
 		drbd_al_shrink(mdev); /* All extents inactive. */
+
+		prev_flags = md->flags;
+		md->flags &= ~MDF_PRIMARY_IND;
+		drbd_md_write(mdev, buffer);
+
 		dev_info(DEV, "Writing the whole bitmap, %s\n",
 			 la_size_changed && md_moved ? "size changed and md moved" :
 			 la_size_changed ? "size changed" : "md moved");
 		/* next line implicitly does drbd_suspend_io()+drbd_resume_io() */
-		err = drbd_bitmap_io(mdev, md_moved ? &drbd_bm_write_all : &drbd_bm_write,
-				     "size changed", BM_LOCKED_MASK);
-		if (err) {
-			rv = dev_size_error;
-			goto out;
-		}
-		drbd_md_mark_dirty(mdev);
+		drbd_bitmap_io(mdev, md_moved ? &drbd_bm_write_all : &drbd_bm_write,
+			       "size changed", BM_LOCKED_MASK);
+		drbd_initialize_al(mdev, buffer);
+
+		md->flags = prev_flags;
+		drbd_md_write(mdev, buffer);
+
+		if (rs)
+			dev_info(DEV, "Changed AL layout to al-stripes = %d, al-stripe-size-kB = %d\n",
+				 md->al_stripes, md->al_stripe_size_4k * 4);
 	}
 
 	if (size > la_size_sect)
-		rv = grew;
+		rv = DS_GREW;
 	if (size < la_size_sect)
-		rv = shrunk;
-out:
+		rv = DS_SHRUNK;
+
+	if (0) {
+	err_out:
+		if (rs) {
+			md->al_stripes = prev_al_stripes;
+			md->al_stripe_size_4k = prev_al_stripe_size_4k;
+			md->al_size_4k = (u64)prev_al_stripes * prev_al_stripe_size_4k;
+
+			drbd_md_set_sector_offsets(mdev, mdev->ldev);
+		}
+	}
 	lc_unlock(mdev->act_log);
 	wake_up(&mdev->al_wait);
+	drbd_md_put_buffer(mdev);
 	drbd_resume_io(mdev);
 
 	return rv;
@@ -1607,11 +1672,11 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	    !drbd_md_test_flag(mdev->ldev, MDF_CONNECTED_IND))
 		set_bit(USE_DEGR_WFC_T, &mdev->flags);
 
-	dd = drbd_determine_dev_size(mdev, 0);
-	if (dd == dev_size_error) {
+	dd = drbd_determine_dev_size(mdev, 0, NULL);
+	if (dd <= DS_ERROR) {
 		retcode = ERR_NOMEM_BITMAP;
 		goto force_diskless_dec;
-	} else if (dd == grew)
+	} else if (dd == DS_GREW)
 		set_bit(RESYNC_AFTER_NEG, &mdev->flags);
 
 	if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC) ||
@@ -2305,6 +2370,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 	struct drbd_conf *mdev;
 	enum drbd_ret_code retcode;
 	enum determine_dev_size dd;
+	bool change_al_layout = false;
 	enum dds_flags ddsf;
 	sector_t u_size;
 	int err;
@@ -2315,31 +2381,33 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto fail;
 
+	mdev = adm_ctx.mdev;
+	if (!get_ldev(mdev)) {
+		retcode = ERR_NO_DISK;
+		goto fail;
+	}
+
 	memset(&rs, 0, sizeof(struct resize_parms));
+	rs.al_stripes = mdev->ldev->md.al_stripes;
+	rs.al_stripe_size = mdev->ldev->md.al_stripe_size_4k * 4;
 	if (info->attrs[DRBD_NLA_RESIZE_PARMS]) {
 		err = resize_parms_from_attrs(&rs, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
 			drbd_msg_put_info(from_attrs_err_to_txt(err));
-			goto fail;
+			goto fail_ldev;
 		}
 	}
 
-	mdev = adm_ctx.mdev;
 	if (mdev->state.conn > C_CONNECTED) {
 		retcode = ERR_RESIZE_RESYNC;
-		goto fail;
+		goto fail_ldev;
 	}
 
 	if (mdev->state.role == R_SECONDARY &&
 	    mdev->state.peer == R_SECONDARY) {
 		retcode = ERR_NO_PRIMARY;
-		goto fail;
-	}
-
-	if (!get_ldev(mdev)) {
-		retcode = ERR_NO_DISK;
-		goto fail;
+		goto fail_ldev;
 	}
 
 	if (rs.no_resync && mdev->tconn->agreed_pro_version < 93) {
@@ -2358,6 +2426,28 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+	if (mdev->ldev->md.al_stripes != rs.al_stripes ||
+	    mdev->ldev->md.al_stripe_size_4k != rs.al_stripe_size / 4) {
+		u32 al_size_k = rs.al_stripes * rs.al_stripe_size;
+
+		if (al_size_k > (16 * 1024 * 1024)) {
+			retcode = ERR_MD_LAYOUT_TOO_BIG;
+			goto fail_ldev;
+		}
+
+		if (al_size_k < MD_32kB_SECT/2) {
+			retcode = ERR_MD_LAYOUT_TOO_SMALL;
+			goto fail_ldev;
+		}
+
+		if (mdev->state.conn != C_CONNECTED) {
+			retcode = ERR_MD_LAYOUT_CONNECTED;
+			goto fail_ldev;
+		}
+
+		change_al_layout = true;
+	}
+
 	if (mdev->ldev->known_size != drbd_get_capacity(mdev->ldev->backing_bdev))
 		mdev->ldev->known_size = drbd_get_capacity(mdev->ldev->backing_bdev);
 
@@ -2373,16 +2463,22 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	ddsf = (rs.resize_force ? DDSF_FORCED : 0) | (rs.no_resync ? DDSF_NO_RESYNC : 0);
-	dd = drbd_determine_dev_size(mdev, ddsf);
+	dd = drbd_determine_dev_size(mdev, ddsf, change_al_layout ? &rs : NULL);
 	drbd_md_sync(mdev);
 	put_ldev(mdev);
-	if (dd == dev_size_error) {
+	if (dd == DS_ERROR) {
 		retcode = ERR_NOMEM_BITMAP;
 		goto fail;
+	} else if (dd == DS_ERROR_SPACE_MD) {
+		retcode = ERR_MD_LAYOUT_NO_FIT;
+		goto fail;
+	} else if (dd == DS_ERROR_SHRINK) {
+		retcode = ERR_IMPLICIT_SHRINK;
+		goto fail;
 	}
 
 	if (mdev->state.conn == C_CONNECTED) {
-		if (dd == grew)
+		if (dd == DS_GREW)
 			set_bit(RESIZE_PENDING, &mdev->flags);
 
 		drbd_send_uuids(mdev);
@@ -2658,7 +2754,6 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 		const struct sib_info *sib)
 {
 	struct state_info *si = NULL; /* for sizeof(si->member); */
-	struct net_conf *nc;
 	struct nlattr *nla;
 	int got_ldev;
 	int err = 0;
@@ -2688,13 +2783,19 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 		goto nla_put_failure;
 
 	rcu_read_lock();
-	if (got_ldev)
-		if (disk_conf_to_skb(skb, rcu_dereference(mdev->ldev->disk_conf), exclude_sensitive))
-			goto nla_put_failure;
+	if (got_ldev) {
+		struct disk_conf *disk_conf;
 
-	nc = rcu_dereference(mdev->tconn->net_conf);
-	if (nc)
-		err = net_conf_to_skb(skb, nc, exclude_sensitive);
+		disk_conf = rcu_dereference(mdev->ldev->disk_conf);
+		err = disk_conf_to_skb(skb, disk_conf, exclude_sensitive);
+	}
+	if (!err) {
+		struct net_conf *nc;
+
+		nc = rcu_dereference(mdev->tconn->net_conf);
+		if (nc)
+			err = net_conf_to_skb(skb, nc, exclude_sensitive);
+	}
 	rcu_read_unlock();
 	if (err)
 		goto nla_put_failure;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 4222affff488..cc29cd3bf78b 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1039,6 +1039,8 @@ randomize:
 	rcu_read_lock();
 	idr_for_each_entry(&tconn->volumes, mdev, vnr) {
 		kref_get(&mdev->kref);
+		rcu_read_unlock();
+
 		/* Prevent a race between resync-handshake and
 		 * being promoted to Primary.
 		 *
@@ -1049,8 +1051,6 @@ randomize:
 		mutex_lock(mdev->state_mutex);
 		mutex_unlock(mdev->state_mutex);
 
-		rcu_read_unlock();
-
 		if (discard_my_data)
 			set_bit(DISCARD_MY_DATA, &mdev->flags);
 		else
@@ -3545,7 +3545,7 @@ static int receive_sizes(struct drbd_tconn *tconn, struct packet_info *pi)
 {
 	struct drbd_conf *mdev;
 	struct p_sizes *p = pi->data;
-	enum determine_dev_size dd = unchanged;
+	enum determine_dev_size dd = DS_UNCHANGED;
 	sector_t p_size, p_usize, my_usize;
 	int ldsc = 0; /* local disk size changed */
 	enum dds_flags ddsf;
@@ -3617,9 +3617,9 @@ static int receive_sizes(struct drbd_tconn *tconn, struct packet_info *pi)
 
 	ddsf = be16_to_cpu(p->dds_flags);
 	if (get_ldev(mdev)) {
-		dd = drbd_determine_dev_size(mdev, ddsf);
+		dd = drbd_determine_dev_size(mdev, ddsf, NULL);
 		put_ldev(mdev);
-		if (dd == dev_size_error)
+		if (dd == DS_ERROR)
 			return -EIO;
 		drbd_md_sync(mdev);
 	} else {
@@ -3647,7 +3647,7 @@ static int receive_sizes(struct drbd_tconn *tconn, struct packet_info *pi)
 			drbd_send_sizes(mdev, 0, ddsf);
 		}
 		if (test_and_clear_bit(RESIZE_PENDING, &mdev->flags) ||
-		    (dd == grew && mdev->state.conn == C_CONNECTED)) {
+		    (dd == DS_GREW && mdev->state.conn == C_CONNECTED)) {
 			if (mdev->state.pdsk >= D_INCONSISTENT &&
 			    mdev->state.disk >= D_INCONSISTENT) {
 				if (ddsf & DDSF_NO_RESYNC)
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 90c5be2b1d30..216d47b7e88b 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1115,8 +1115,10 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 		drbd_thread_restart_nowait(&mdev->tconn->receiver);
 
 	/* Resume AL writing if we get a connection */
-	if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)
+	if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED) {
 		drbd_resume_al(mdev);
+		mdev->tconn->connect_cnt++;
+	}
 
 	/* remember last attach time so request_timer_fn() won't
 	 * kill newly established sessions while we are still trying to thaw
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 5af21f2db29c..6e85e21445eb 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -31,6 +31,8 @@
 #include <linux/slab.h>
 #include <linux/bitops.h>
 #include <linux/delay.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 
 #include <linux/genhd.h>
 #include <linux/idr.h>
@@ -39,8 +41,9 @@
 #include "rsxx_cfg.h"
 
 #define NO_LEGACY 0
+#define SYNC_START_TIMEOUT (10 * 60) /* 10 minutes */
 
-MODULE_DESCRIPTION("IBM FlashSystem 70/80 PCIe SSD Device Driver");
+MODULE_DESCRIPTION("IBM Flash Adapter 900GB Full Height Device Driver");
 MODULE_AUTHOR("Joshua Morris/Philip Kelleher, IBM");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRIVER_VERSION);
@@ -49,9 +52,282 @@ static unsigned int force_legacy = NO_LEGACY;
 module_param(force_legacy, uint, 0444);
 MODULE_PARM_DESC(force_legacy, "Force the use of legacy type PCI interrupts");
 
+static unsigned int sync_start = 1;
+module_param(sync_start, uint, 0444);
+MODULE_PARM_DESC(sync_start, "On by Default: Driver load will not complete "
+			     "until the card startup has completed.");
+
 static DEFINE_IDA(rsxx_disk_ida);
 static DEFINE_SPINLOCK(rsxx_ida_lock);
 
+/* --------------------Debugfs Setup ------------------- */
+
+struct rsxx_cram {
+	u32 f_pos;
+	u32 offset;
+	void *i_private;
+};
+
+static int rsxx_attr_pci_regs_show(struct seq_file *m, void *p)
+{
+	struct rsxx_cardinfo *card = m->private;
+
+	seq_printf(m, "HWID		0x%08x\n",
+					ioread32(card->regmap + HWID));
+	seq_printf(m, "SCRATCH		0x%08x\n",
+					ioread32(card->regmap + SCRATCH));
+	seq_printf(m, "IER		0x%08x\n",
+					ioread32(card->regmap + IER));
+	seq_printf(m, "IPR		0x%08x\n",
+					ioread32(card->regmap + IPR));
+	seq_printf(m, "CREG_CMD		0x%08x\n",
+					ioread32(card->regmap + CREG_CMD));
+	seq_printf(m, "CREG_ADD		0x%08x\n",
+					ioread32(card->regmap + CREG_ADD));
+	seq_printf(m, "CREG_CNT		0x%08x\n",
+					ioread32(card->regmap + CREG_CNT));
+	seq_printf(m, "CREG_STAT	0x%08x\n",
+					ioread32(card->regmap + CREG_STAT));
+	seq_printf(m, "CREG_DATA0	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA0));
+	seq_printf(m, "CREG_DATA1	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA1));
+	seq_printf(m, "CREG_DATA2	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA2));
+	seq_printf(m, "CREG_DATA3	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA3));
+	seq_printf(m, "CREG_DATA4	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA4));
+	seq_printf(m, "CREG_DATA5	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA5));
+	seq_printf(m, "CREG_DATA6	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA6));
+	seq_printf(m, "CREG_DATA7	0x%08x\n",
+					ioread32(card->regmap + CREG_DATA7));
+	seq_printf(m, "INTR_COAL	0x%08x\n",
+					ioread32(card->regmap + INTR_COAL));
+	seq_printf(m, "HW_ERROR		0x%08x\n",
+					ioread32(card->regmap + HW_ERROR));
+	seq_printf(m, "DEBUG0		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG0));
+	seq_printf(m, "DEBUG1		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG1));
+	seq_printf(m, "DEBUG2		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG2));
+	seq_printf(m, "DEBUG3		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG3));
+	seq_printf(m, "DEBUG4		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG4));
+	seq_printf(m, "DEBUG5		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG5));
+	seq_printf(m, "DEBUG6		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG6));
+	seq_printf(m, "DEBUG7		0x%08x\n",
+					ioread32(card->regmap + PCI_DEBUG7));
+	seq_printf(m, "RECONFIG		0x%08x\n",
+					ioread32(card->regmap + PCI_RECONFIG));
+
+	return 0;
+}
+
+static int rsxx_attr_stats_show(struct seq_file *m, void *p)
+{
+	struct rsxx_cardinfo *card = m->private;
+	int i;
+
+	for (i = 0; i < card->n_targets; i++) {
+		seq_printf(m, "Ctrl %d CRC Errors	= %d\n",
+				i, card->ctrl[i].stats.crc_errors);
+		seq_printf(m, "Ctrl %d Hard Errors	= %d\n",
+				i, card->ctrl[i].stats.hard_errors);
+		seq_printf(m, "Ctrl %d Soft Errors	= %d\n",
+				i, card->ctrl[i].stats.soft_errors);
+		seq_printf(m, "Ctrl %d Writes Issued	= %d\n",
+				i, card->ctrl[i].stats.writes_issued);
+		seq_printf(m, "Ctrl %d Writes Failed	= %d\n",
+				i, card->ctrl[i].stats.writes_failed);
+		seq_printf(m, "Ctrl %d Reads Issued	= %d\n",
+				i, card->ctrl[i].stats.reads_issued);
+		seq_printf(m, "Ctrl %d Reads Failed	= %d\n",
+				i, card->ctrl[i].stats.reads_failed);
+		seq_printf(m, "Ctrl %d Reads Retried	= %d\n",
+				i, card->ctrl[i].stats.reads_retried);
+		seq_printf(m, "Ctrl %d Discards Issued	= %d\n",
+				i, card->ctrl[i].stats.discards_issued);
+		seq_printf(m, "Ctrl %d Discards Failed	= %d\n",
+				i, card->ctrl[i].stats.discards_failed);
+		seq_printf(m, "Ctrl %d DMA SW Errors	= %d\n",
+				i, card->ctrl[i].stats.dma_sw_err);
+		seq_printf(m, "Ctrl %d DMA HW Faults	= %d\n",
+				i, card->ctrl[i].stats.dma_hw_fault);
+		seq_printf(m, "Ctrl %d DMAs Cancelled	= %d\n",
+				i, card->ctrl[i].stats.dma_cancelled);
+		seq_printf(m, "Ctrl %d SW Queue Depth	= %d\n",
+				i, card->ctrl[i].stats.sw_q_depth);
+		seq_printf(m, "Ctrl %d HW Queue Depth	= %d\n",
+			i, atomic_read(&card->ctrl[i].stats.hw_q_depth));
+	}
+
+	return 0;
+}
+
+static int rsxx_attr_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, rsxx_attr_stats_show, inode->i_private);
+}
+
+static int rsxx_attr_pci_regs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, rsxx_attr_pci_regs_show, inode->i_private);
+}
+
+static ssize_t rsxx_cram_read(struct file *fp, char __user *ubuf,
+			      size_t cnt, loff_t *ppos)
+{
+	struct rsxx_cram *info = fp->private_data;
+	struct rsxx_cardinfo *card = info->i_private;
+	char *buf;
+	int st;
+
+	buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	info->f_pos = (u32)*ppos + info->offset;
+
+	st = rsxx_creg_read(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
+	if (st)
+		return st;
+
+	st = copy_to_user(ubuf, buf, cnt);
+	if (st)
+		return st;
+
+	info->offset += cnt;
+
+	kfree(buf);
+
+	return cnt;
+}
+
+static ssize_t rsxx_cram_write(struct file *fp, const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	struct rsxx_cram *info = fp->private_data;
+	struct rsxx_cardinfo *card = info->i_private;
+	char *buf;
+	int st;
+
+	buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	st = copy_from_user(buf, ubuf, cnt);
+	if (st)
+		return st;
+
+	info->f_pos = (u32)*ppos + info->offset;
+
+	st = rsxx_creg_write(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
+	if (st)
+		return st;
+
+	info->offset += cnt;
+
+	kfree(buf);
+
+	return cnt;
+}
+
+static int rsxx_cram_open(struct inode *inode, struct file *file)
+{
+	struct rsxx_cram *info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->i_private = inode->i_private;
+	info->f_pos = file->f_pos;
+	file->private_data = info;
+
+	return 0;
+}
+
+static int rsxx_cram_release(struct inode *inode, struct file *file)
+{
+	struct rsxx_cram *info = file->private_data;
+
+	if (!info)
+		return 0;
+
+	kfree(info);
+	file->private_data = NULL;
+
+	return 0;
+}
+
+static const struct file_operations debugfs_cram_fops = {
+	.owner		= THIS_MODULE,
+	.open		= rsxx_cram_open,
+	.read		= rsxx_cram_read,
+	.write		= rsxx_cram_write,
+	.release	= rsxx_cram_release,
+};
+
+static const struct file_operations debugfs_stats_fops = {
+	.owner		= THIS_MODULE,
+	.open		= rsxx_attr_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const struct file_operations debugfs_pci_regs_fops = {
+	.owner		= THIS_MODULE,
+	.open		= rsxx_attr_pci_regs_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void rsxx_debugfs_dev_new(struct rsxx_cardinfo *card)
+{
+	struct dentry *debugfs_stats;
+	struct dentry *debugfs_pci_regs;
+	struct dentry *debugfs_cram;
+
+	card->debugfs_dir = debugfs_create_dir(card->gendisk->disk_name, NULL);
+	if (IS_ERR_OR_NULL(card->debugfs_dir))
+		goto failed_debugfs_dir;
+
+	debugfs_stats = debugfs_create_file("stats", S_IRUGO,
+					    card->debugfs_dir, card,
+					    &debugfs_stats_fops);
+	if (IS_ERR_OR_NULL(debugfs_stats))
+		goto failed_debugfs_stats;
+
+	debugfs_pci_regs = debugfs_create_file("pci_regs", S_IRUGO,
+					       card->debugfs_dir, card,
+					       &debugfs_pci_regs_fops);
+	if (IS_ERR_OR_NULL(debugfs_pci_regs))
+		goto failed_debugfs_pci_regs;
+
+	debugfs_cram = debugfs_create_file("cram", S_IRUGO | S_IWUSR,
+					   card->debugfs_dir, card,
+					   &debugfs_cram_fops);
+	if (IS_ERR_OR_NULL(debugfs_cram))
+		goto failed_debugfs_cram;
+
+	return;
+failed_debugfs_cram:
+	debugfs_remove(debugfs_pci_regs);
+failed_debugfs_pci_regs:
+	debugfs_remove(debugfs_stats);
+failed_debugfs_stats:
+	debugfs_remove(card->debugfs_dir);
+failed_debugfs_dir:
+	card->debugfs_dir = NULL;
+}
+
 /*----------------- Interrupt Control & Handling -------------------*/
 
 static void rsxx_mask_interrupts(struct rsxx_cardinfo *card)
@@ -163,12 +439,13 @@ static irqreturn_t rsxx_isr(int irq, void *pdata)
 		}
 
 		if (isr & CR_INTR_CREG) {
-			schedule_work(&card->creg_ctrl.done_work);
+			queue_work(card->creg_ctrl.creg_wq,
+				   &card->creg_ctrl.done_work);
 			handled++;
 		}
 
 		if (isr & CR_INTR_EVENT) {
-			schedule_work(&card->event_work);
+			queue_work(card->event_wq, &card->event_work);
 			rsxx_disable_ier_and_isr(card, CR_INTR_EVENT);
 			handled++;
 		}
@@ -329,7 +606,7 @@ static int rsxx_eeh_frozen(struct pci_dev *dev)
 	int i;
 	int st;
 
-	dev_warn(&dev->dev, "IBM FlashSystem PCI: preparing for slot reset.\n");
+	dev_warn(&dev->dev, "IBM Flash Adapter PCI: preparing for slot reset.\n");
 
 	card->eeh_state = 1;
 	rsxx_mask_interrupts(card);
@@ -367,15 +644,26 @@ static void rsxx_eeh_failure(struct pci_dev *dev)
 {
 	struct rsxx_cardinfo *card = pci_get_drvdata(dev);
 	int i;
+	int cnt = 0;
 
-	dev_err(&dev->dev, "IBM FlashSystem PCI: disabling failed card.\n");
+	dev_err(&dev->dev, "IBM Flash Adapter PCI: disabling failed card.\n");
 
 	card->eeh_state = 1;
+	card->halt = 1;
 
-	for (i = 0; i < card->n_targets; i++)
-		del_timer_sync(&card->ctrl[i].activity_timer);
+	for (i = 0; i < card->n_targets; i++) {
+		spin_lock_bh(&card->ctrl[i].queue_lock);
+		cnt = rsxx_cleanup_dma_queue(&card->ctrl[i],
+					     &card->ctrl[i].queue);
+		spin_unlock_bh(&card->ctrl[i].queue_lock);
+
+		cnt += rsxx_dma_cancel(&card->ctrl[i]);
 
-	rsxx_eeh_cancel_dmas(card);
+		if (cnt)
+			dev_info(CARD_TO_DEV(card),
+				"Freed %d queued DMAs on channel %d\n",
+				cnt, card->ctrl[i].id);
+	}
 }
 
 static int rsxx_eeh_fifo_flush_poll(struct rsxx_cardinfo *card)
@@ -432,7 +720,7 @@ static pci_ers_result_t rsxx_slot_reset(struct pci_dev *dev)
 	int st;
 
 	dev_warn(&dev->dev,
-		"IBM FlashSystem PCI: recovering from slot reset.\n");
+		"IBM Flash Adapter PCI: recovering from slot reset.\n");
 
 	st = pci_enable_device(dev);
 	if (st)
@@ -485,7 +773,7 @@ static pci_ers_result_t rsxx_slot_reset(struct pci_dev *dev)
 				&card->ctrl[i].issue_dma_work);
 	}
 
-	dev_info(&dev->dev, "IBM FlashSystem PCI: recovery complete.\n");
+	dev_info(&dev->dev, "IBM Flash Adapter PCI: recovery complete.\n");
 
 	return PCI_ERS_RESULT_RECOVERED;
 
@@ -528,6 +816,7 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 {
 	struct rsxx_cardinfo *card;
 	int st;
+	unsigned int sync_timeout;
 
 	dev_info(&dev->dev, "PCI-Flash SSD discovered\n");
 
@@ -610,7 +899,11 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 	}
 
 	/************* Setup Processor Command Interface *************/
-	rsxx_creg_setup(card);
+	st = rsxx_creg_setup(card);
+	if (st) {
+		dev_err(CARD_TO_DEV(card), "Failed to setup creg interface.\n");
+		goto failed_creg_setup;
+	}
 
 	spin_lock_irq(&card->irq_lock);
 	rsxx_enable_ier_and_isr(card, CR_INTR_CREG);
@@ -650,6 +943,12 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 	}
 
 	/************* Setup Card Event Handler *************/
+	card->event_wq = create_singlethread_workqueue(DRIVER_NAME"_event");
+	if (!card->event_wq) {
+		dev_err(CARD_TO_DEV(card), "Failed card event setup.\n");
+		goto failed_event_handler;
+	}
+
 	INIT_WORK(&card->event_work, card_event_handler);
 
 	st = rsxx_setup_dev(card);
@@ -676,6 +975,33 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 		if (st)
 			dev_crit(CARD_TO_DEV(card),
 				"Failed issuing card startup\n");
+		if (sync_start) {
+			sync_timeout = SYNC_START_TIMEOUT;
+
+			dev_info(CARD_TO_DEV(card),
+				 "Waiting for card to startup\n");
+
+			do {
+				ssleep(1);
+				sync_timeout--;
+
+				rsxx_get_card_state(card, &card->state);
+			} while (sync_timeout &&
+				(card->state == CARD_STATE_STARTING));
+
+			if (card->state == CARD_STATE_STARTING) {
+				dev_warn(CARD_TO_DEV(card),
+					 "Card startup timed out\n");
+				card->size8 = 0;
+			} else {
+				dev_info(CARD_TO_DEV(card),
+					"card state: %s\n",
+					rsxx_card_state_to_str(card->state));
+				st = rsxx_get_card_size8(card, &card->size8);
+				if (st)
+					card->size8 = 0;
+			}
+		}
 	} else if (card->state == CARD_STATE_GOOD ||
 		   card->state == CARD_STATE_RD_ONLY_FAULT) {
 		st = rsxx_get_card_size8(card, &card->size8);
@@ -685,12 +1011,21 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 
 	rsxx_attach_dev(card);
 
+	/************* Setup Debugfs *************/
+	rsxx_debugfs_dev_new(card);
+
 	return 0;
 
 failed_create_dev:
+	destroy_workqueue(card->event_wq);
+	card->event_wq = NULL;
+failed_event_handler:
 	rsxx_dma_destroy(card);
 failed_dma_setup:
 failed_compatiblity_check:
+	destroy_workqueue(card->creg_ctrl.creg_wq);
+	card->creg_ctrl.creg_wq = NULL;
+failed_creg_setup:
 	spin_lock_irq(&card->irq_lock);
 	rsxx_disable_ier_and_isr(card, CR_INTR_ALL);
 	spin_unlock_irq(&card->irq_lock);
@@ -756,6 +1091,8 @@ static void rsxx_pci_remove(struct pci_dev *dev)
 	/* Prevent work_structs from re-queuing themselves. */
 	card->halt = 1;
 
+	debugfs_remove_recursive(card->debugfs_dir);
+
 	free_irq(dev->irq, card);
 
 	if (!force_legacy)
diff --git a/drivers/block/rsxx/cregs.c b/drivers/block/rsxx/cregs.c
index 4b5c020a0a65..926dce9c452f 100644
--- a/drivers/block/rsxx/cregs.c
+++ b/drivers/block/rsxx/cregs.c
@@ -431,6 +431,15 @@ static int __issue_creg_rw(struct rsxx_cardinfo *card,
 	*hw_stat = completion.creg_status;
 
 	if (completion.st) {
+		/*
+		* This read is needed to verify that there has not been any
+		* extreme errors that might have occurred, i.e. EEH. The
+		* function iowrite32 will not detect EEH errors, so it is
+		* necessary that we recover if such an error is the reason
+		* for the timeout. This is a dummy read.
+		*/
+		ioread32(card->regmap + SCRATCH);
+
 		dev_warn(CARD_TO_DEV(card),
 			"creg command failed(%d x%08x)\n",
 			completion.st, addr);
@@ -727,6 +736,11 @@ int rsxx_creg_setup(struct rsxx_cardinfo *card)
 {
 	card->creg_ctrl.active_cmd = NULL;
 
+	card->creg_ctrl.creg_wq =
+			create_singlethread_workqueue(DRIVER_NAME"_creg");
+	if (!card->creg_ctrl.creg_wq)
+		return -ENOMEM;
+
 	INIT_WORK(&card->creg_ctrl.done_work, creg_cmd_done);
 	mutex_init(&card->creg_ctrl.reset_lock);
 	INIT_LIST_HEAD(&card->creg_ctrl.queue);
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 4346d17d2949..d7af441880be 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -155,7 +155,8 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
 		atomic_set(&meta->error, 1);
 
 	if (atomic_dec_and_test(&meta->pending_dmas)) {
-		disk_stats_complete(card, meta->bio, meta->start_time);
+		if (!card->eeh_state && card->gendisk)
+			disk_stats_complete(card, meta->bio, meta->start_time);
 
 		bio_endio(meta->bio, atomic_read(&meta->error) ? -EIO : 0);
 		kmem_cache_free(bio_meta_pool, meta);
@@ -170,6 +171,12 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 
 	might_sleep();
 
+	if (!card)
+		goto req_err;
+
+	if (bio->bi_sector + (bio->bi_size >> 9) > get_capacity(card->gendisk))
+		goto req_err;
+
 	if (unlikely(card->halt)) {
 		st = -EFAULT;
 		goto req_err;
@@ -196,7 +203,8 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 	atomic_set(&bio_meta->pending_dmas, 0);
 	bio_meta->start_time = jiffies;
 
-	disk_stats_start(card, bio);
+	if (!unlikely(card->halt))
+		disk_stats_start(card, bio);
 
 	dev_dbg(CARD_TO_DEV(card), "BIO[%c]: meta: %p addr8: x%llx size: %d\n",
 		 bio_data_dir(bio) ? 'W' : 'R', bio_meta,
@@ -225,24 +233,6 @@ static bool rsxx_discard_supported(struct rsxx_cardinfo *card)
 	return (pci_rev >= RSXX_DISCARD_SUPPORT);
 }
 
-static unsigned short rsxx_get_logical_block_size(
-					struct rsxx_cardinfo *card)
-{
-	u32 capabilities = 0;
-	int st;
-
-	st = rsxx_get_card_capabilities(card, &capabilities);
-	if (st)
-		dev_warn(CARD_TO_DEV(card),
-			"Failed reading card capabilities register\n");
-
-	/* Earlier firmware did not have support for 512 byte accesses */
-	if (capabilities & CARD_CAP_SUBPAGE_WRITES)
-		return 512;
-	else
-		return RSXX_HW_BLK_SIZE;
-}
-
 int rsxx_attach_dev(struct rsxx_cardinfo *card)
 {
 	mutex_lock(&card->dev_lock);
@@ -305,7 +295,7 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
 		return -ENOMEM;
 	}
 
-	blk_size = rsxx_get_logical_block_size(card);
+	blk_size = card->config.data.block_size;
 
 	blk_queue_make_request(card->queue, rsxx_make_request);
 	blk_queue_bounce_limit(card->queue, BLK_BOUNCE_ANY);
@@ -347,6 +337,7 @@ void rsxx_destroy_dev(struct rsxx_cardinfo *card)
 	card->gendisk = NULL;
 
 	blk_cleanup_queue(card->queue);
+	card->queue->queuedata = NULL;
 	unregister_blkdev(card->major, DRIVER_NAME);
 }
 
diff --git a/drivers/block/rsxx/dma.c b/drivers/block/rsxx/dma.c
index 0607513cfb41..bed32f16b084 100644
--- a/drivers/block/rsxx/dma.c
+++ b/drivers/block/rsxx/dma.c
@@ -245,6 +245,22 @@ static void rsxx_complete_dma(struct rsxx_dma_ctrl *ctrl,
 	kmem_cache_free(rsxx_dma_pool, dma);
 }
 
+int rsxx_cleanup_dma_queue(struct rsxx_dma_ctrl *ctrl,
+			   struct list_head *q)
+{
+	struct rsxx_dma *dma;
+	struct rsxx_dma *tmp;
+	int cnt = 0;
+
+	list_for_each_entry_safe(dma, tmp, q, list) {
+		list_del(&dma->list);
+		rsxx_complete_dma(ctrl, dma, DMA_CANCELLED);
+		cnt++;
+	}
+
+	return cnt;
+}
+
 static void rsxx_requeue_dma(struct rsxx_dma_ctrl *ctrl,
 				 struct rsxx_dma *dma)
 {
@@ -252,9 +268,10 @@ static void rsxx_requeue_dma(struct rsxx_dma_ctrl *ctrl,
 	 * Requeued DMAs go to the front of the queue so they are issued
 	 * first.
 	 */
-	spin_lock(&ctrl->queue_lock);
+	spin_lock_bh(&ctrl->queue_lock);
+	ctrl->stats.sw_q_depth++;
 	list_add(&dma->list, &ctrl->queue);
-	spin_unlock(&ctrl->queue_lock);
+	spin_unlock_bh(&ctrl->queue_lock);
 }
 
 static void rsxx_handle_dma_error(struct rsxx_dma_ctrl *ctrl,
@@ -329,6 +346,7 @@ static void rsxx_handle_dma_error(struct rsxx_dma_ctrl *ctrl,
 static void dma_engine_stalled(unsigned long data)
 {
 	struct rsxx_dma_ctrl *ctrl = (struct rsxx_dma_ctrl *)data;
+	int cnt;
 
 	if (atomic_read(&ctrl->stats.hw_q_depth) == 0 ||
 	    unlikely(ctrl->card->eeh_state))
@@ -349,18 +367,28 @@ static void dma_engine_stalled(unsigned long data)
 			"DMA channel %d has stalled, faulting interface.\n",
 			ctrl->id);
 		ctrl->card->dma_fault = 1;
+
+		/* Clean up the DMA queue */
+		spin_lock(&ctrl->queue_lock);
+		cnt = rsxx_cleanup_dma_queue(ctrl, &ctrl->queue);
+		spin_unlock(&ctrl->queue_lock);
+
+		cnt += rsxx_dma_cancel(ctrl);
+
+		if (cnt)
+			dev_info(CARD_TO_DEV(ctrl->card),
+				"Freed %d queued DMAs on channel %d\n",
+				cnt, ctrl->id);
 	}
 }
 
-static void rsxx_issue_dmas(struct work_struct *work)
+static void rsxx_issue_dmas(struct rsxx_dma_ctrl *ctrl)
 {
-	struct rsxx_dma_ctrl *ctrl;
 	struct rsxx_dma *dma;
 	int tag;
 	int cmds_pending = 0;
 	struct hw_cmd *hw_cmd_buf;
 
-	ctrl = container_of(work, struct rsxx_dma_ctrl, issue_dma_work);
 	hw_cmd_buf = ctrl->cmd.buf;
 
 	if (unlikely(ctrl->card->halt) ||
@@ -368,22 +396,22 @@ static void rsxx_issue_dmas(struct work_struct *work)
 		return;
 
 	while (1) {
-		spin_lock(&ctrl->queue_lock);
+		spin_lock_bh(&ctrl->queue_lock);
 		if (list_empty(&ctrl->queue)) {
-			spin_unlock(&ctrl->queue_lock);
+			spin_unlock_bh(&ctrl->queue_lock);
 			break;
 		}
-		spin_unlock(&ctrl->queue_lock);
+		spin_unlock_bh(&ctrl->queue_lock);
 
 		tag = pop_tracker(ctrl->trackers);
 		if (tag == -1)
 			break;
 
-		spin_lock(&ctrl->queue_lock);
+		spin_lock_bh(&ctrl->queue_lock);
 		dma = list_entry(ctrl->queue.next, struct rsxx_dma, list);
 		list_del(&dma->list);
 		ctrl->stats.sw_q_depth--;
-		spin_unlock(&ctrl->queue_lock);
+		spin_unlock_bh(&ctrl->queue_lock);
 
 		/*
 		 * This will catch any DMAs that slipped in right before the
@@ -440,9 +468,8 @@ static void rsxx_issue_dmas(struct work_struct *work)
 	}
 }
 
-static void rsxx_dma_done(struct work_struct *work)
+static void rsxx_dma_done(struct rsxx_dma_ctrl *ctrl)
 {
-	struct rsxx_dma_ctrl *ctrl;
 	struct rsxx_dma *dma;
 	unsigned long flags;
 	u16 count;
@@ -450,7 +477,6 @@ static void rsxx_dma_done(struct work_struct *work)
 	u8 tag;
 	struct hw_status *hw_st_buf;
 
-	ctrl = container_of(work, struct rsxx_dma_ctrl, dma_done_work);
 	hw_st_buf = ctrl->status.buf;
 
 	if (unlikely(ctrl->card->halt) ||
@@ -520,33 +546,32 @@ static void rsxx_dma_done(struct work_struct *work)
 	rsxx_enable_ier(ctrl->card, CR_INTR_DMA(ctrl->id));
 	spin_unlock_irqrestore(&ctrl->card->irq_lock, flags);
 
-	spin_lock(&ctrl->queue_lock);
+	spin_lock_bh(&ctrl->queue_lock);
 	if (ctrl->stats.sw_q_depth)
 		queue_work(ctrl->issue_wq, &ctrl->issue_dma_work);
-	spin_unlock(&ctrl->queue_lock);
+	spin_unlock_bh(&ctrl->queue_lock);
 }
 
-static int rsxx_cleanup_dma_queue(struct rsxx_cardinfo *card,
-				      struct list_head *q)
+static void rsxx_schedule_issue(struct work_struct *work)
 {
-	struct rsxx_dma *dma;
-	struct rsxx_dma *tmp;
-	int cnt = 0;
+	struct rsxx_dma_ctrl *ctrl;
 
-	list_for_each_entry_safe(dma, tmp, q, list) {
-		list_del(&dma->list);
+	ctrl = container_of(work, struct rsxx_dma_ctrl, issue_dma_work);
 
-		if (dma->dma_addr)
-			pci_unmap_page(card->dev, dma->dma_addr,
-				       get_dma_size(dma),
-				       (dma->cmd == HW_CMD_BLK_WRITE) ?
-				       PCI_DMA_TODEVICE :
-				       PCI_DMA_FROMDEVICE);
-		kmem_cache_free(rsxx_dma_pool, dma);
-		cnt++;
-	}
+	mutex_lock(&ctrl->work_lock);
+	rsxx_issue_dmas(ctrl);
+	mutex_unlock(&ctrl->work_lock);
+}
 
-	return cnt;
+static void rsxx_schedule_done(struct work_struct *work)
+{
+	struct rsxx_dma_ctrl *ctrl;
+
+	ctrl = container_of(work, struct rsxx_dma_ctrl, dma_done_work);
+
+	mutex_lock(&ctrl->work_lock);
+	rsxx_dma_done(ctrl);
+	mutex_unlock(&ctrl->work_lock);
 }
 
 static int rsxx_queue_discard(struct rsxx_cardinfo *card,
@@ -698,10 +723,10 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 
 	for (i = 0; i < card->n_targets; i++) {
 		if (!list_empty(&dma_list[i])) {
-			spin_lock(&card->ctrl[i].queue_lock);
+			spin_lock_bh(&card->ctrl[i].queue_lock);
 			card->ctrl[i].stats.sw_q_depth += dma_cnt[i];
 			list_splice_tail(&dma_list[i], &card->ctrl[i].queue);
-			spin_unlock(&card->ctrl[i].queue_lock);
+			spin_unlock_bh(&card->ctrl[i].queue_lock);
 
 			queue_work(card->ctrl[i].issue_wq,
 				   &card->ctrl[i].issue_dma_work);
@@ -711,8 +736,11 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 	return 0;
 
 bvec_err:
-	for (i = 0; i < card->n_targets; i++)
-		rsxx_cleanup_dma_queue(card, &dma_list[i]);
+	for (i = 0; i < card->n_targets; i++) {
+		spin_lock_bh(&card->ctrl[i].queue_lock);
+		rsxx_cleanup_dma_queue(&card->ctrl[i], &dma_list[i]);
+		spin_unlock_bh(&card->ctrl[i].queue_lock);
+	}
 
 	return st;
 }
@@ -780,6 +808,7 @@ static int rsxx_dma_ctrl_init(struct pci_dev *dev,
 	spin_lock_init(&ctrl->trackers->lock);
 
 	spin_lock_init(&ctrl->queue_lock);
+	mutex_init(&ctrl->work_lock);
 	INIT_LIST_HEAD(&ctrl->queue);
 
 	setup_timer(&ctrl->activity_timer, dma_engine_stalled,
@@ -793,8 +822,8 @@ static int rsxx_dma_ctrl_init(struct pci_dev *dev,
 	if (!ctrl->done_wq)
 		return -ENOMEM;
 
-	INIT_WORK(&ctrl->issue_dma_work, rsxx_issue_dmas);
-	INIT_WORK(&ctrl->dma_done_work, rsxx_dma_done);
+	INIT_WORK(&ctrl->issue_dma_work, rsxx_schedule_issue);
+	INIT_WORK(&ctrl->dma_done_work, rsxx_schedule_done);
 
 	st = rsxx_hw_buffers_init(dev, ctrl);
 	if (st)
@@ -918,13 +947,30 @@ failed_dma_setup:
 	return st;
 }
 
+int rsxx_dma_cancel(struct rsxx_dma_ctrl *ctrl)
+{
+	struct rsxx_dma *dma;
+	int i;
+	int cnt = 0;
+
+	/* Clean up issued DMAs */
+	for (i = 0; i < RSXX_MAX_OUTSTANDING_CMDS; i++) {
+		dma = get_tracker_dma(ctrl->trackers, i);
+		if (dma) {
+			atomic_dec(&ctrl->stats.hw_q_depth);
+			rsxx_complete_dma(ctrl, dma, DMA_CANCELLED);
+			push_tracker(ctrl->trackers, i);
+			cnt++;
+		}
+	}
+
+	return cnt;
+}
 
 void rsxx_dma_destroy(struct rsxx_cardinfo *card)
 {
 	struct rsxx_dma_ctrl *ctrl;
-	struct rsxx_dma *dma;
-	int i, j;
-	int cnt = 0;
+	int i;
 
 	for (i = 0; i < card->n_targets; i++) {
 		ctrl = &card->ctrl[i];
@@ -943,33 +989,11 @@ void rsxx_dma_destroy(struct rsxx_cardinfo *card)
 			del_timer_sync(&ctrl->activity_timer);
 
 		/* Clean up the DMA queue */
-		spin_lock(&ctrl->queue_lock);
-		cnt = rsxx_cleanup_dma_queue(card, &ctrl->queue);
-		spin_unlock(&ctrl->queue_lock);
-
-		if (cnt)
-			dev_info(CARD_TO_DEV(card),
-				"Freed %d queued DMAs on channel %d\n",
-				cnt, i);
-
-		/* Clean up issued DMAs */
-		for (j = 0; j < RSXX_MAX_OUTSTANDING_CMDS; j++) {
-			dma = get_tracker_dma(ctrl->trackers, j);
-			if (dma) {
-				pci_unmap_page(card->dev, dma->dma_addr,
-					       get_dma_size(dma),
-					       (dma->cmd == HW_CMD_BLK_WRITE) ?
-					       PCI_DMA_TODEVICE :
-					       PCI_DMA_FROMDEVICE);
-				kmem_cache_free(rsxx_dma_pool, dma);
-				cnt++;
-			}
-		}
+		spin_lock_bh(&ctrl->queue_lock);
+		rsxx_cleanup_dma_queue(ctrl, &ctrl->queue);
+		spin_unlock_bh(&ctrl->queue_lock);
 
-		if (cnt)
-			dev_info(CARD_TO_DEV(card),
-				"Freed %d pending DMAs on channel %d\n",
-				cnt, i);
+		rsxx_dma_cancel(ctrl);
 
 		vfree(ctrl->trackers);
 
@@ -1013,7 +1037,7 @@ int rsxx_eeh_save_issued_dmas(struct rsxx_cardinfo *card)
 			cnt++;
 		}
 
-		spin_lock(&card->ctrl[i].queue_lock);
+		spin_lock_bh(&card->ctrl[i].queue_lock);
 		list_splice(&issued_dmas[i], &card->ctrl[i].queue);
 
 		atomic_sub(cnt, &card->ctrl[i].stats.hw_q_depth);
@@ -1028,7 +1052,7 @@ int rsxx_eeh_save_issued_dmas(struct rsxx_cardinfo *card)
 					       PCI_DMA_TODEVICE :
 					       PCI_DMA_FROMDEVICE);
 		}
-		spin_unlock(&card->ctrl[i].queue_lock);
+		spin_unlock_bh(&card->ctrl[i].queue_lock);
 	}
 
 	kfree(issued_dmas);
@@ -1036,30 +1060,13 @@ int rsxx_eeh_save_issued_dmas(struct rsxx_cardinfo *card)
 	return 0;
 }
 
-void rsxx_eeh_cancel_dmas(struct rsxx_cardinfo *card)
-{
-	struct rsxx_dma *dma;
-	struct rsxx_dma *tmp;
-	int i;
-
-	for (i = 0; i < card->n_targets; i++) {
-		spin_lock(&card->ctrl[i].queue_lock);
-		list_for_each_entry_safe(dma, tmp, &card->ctrl[i].queue, list) {
-			list_del(&dma->list);
-
-			rsxx_complete_dma(&card->ctrl[i], dma, DMA_CANCELLED);
-		}
-		spin_unlock(&card->ctrl[i].queue_lock);
-	}
-}
-
 int rsxx_eeh_remap_dmas(struct rsxx_cardinfo *card)
 {
 	struct rsxx_dma *dma;
 	int i;
 
 	for (i = 0; i < card->n_targets; i++) {
-		spin_lock(&card->ctrl[i].queue_lock);
+		spin_lock_bh(&card->ctrl[i].queue_lock);
 		list_for_each_entry(dma, &card->ctrl[i].queue, list) {
 			dma->dma_addr = pci_map_page(card->dev, dma->page,
 					dma->pg_off, get_dma_size(dma),
@@ -1067,12 +1074,12 @@ int rsxx_eeh_remap_dmas(struct rsxx_cardinfo *card)
 					PCI_DMA_TODEVICE :
 					PCI_DMA_FROMDEVICE);
 			if (!dma->dma_addr) {
-				spin_unlock(&card->ctrl[i].queue_lock);
+				spin_unlock_bh(&card->ctrl[i].queue_lock);
 				kmem_cache_free(rsxx_dma_pool, dma);
 				return -ENOMEM;
 			}
 		}
-		spin_unlock(&card->ctrl[i].queue_lock);
+		spin_unlock_bh(&card->ctrl[i].queue_lock);
 	}
 
 	return 0;
diff --git a/drivers/block/rsxx/rsxx_priv.h b/drivers/block/rsxx/rsxx_priv.h
index 382e8bf5c03b..5ad5055a4104 100644
--- a/drivers/block/rsxx/rsxx_priv.h
+++ b/drivers/block/rsxx/rsxx_priv.h
@@ -39,6 +39,7 @@
 #include <linux/vmalloc.h>
 #include <linux/timer.h>
 #include <linux/ioctl.h>
+#include <linux/delay.h>
 
 #include "rsxx.h"
 #include "rsxx_cfg.h"
@@ -114,6 +115,7 @@ struct rsxx_dma_ctrl {
 	struct timer_list		activity_timer;
 	struct dma_tracker_list		*trackers;
 	struct rsxx_dma_stats		stats;
+	struct mutex			work_lock;
 };
 
 struct rsxx_cardinfo {
@@ -134,6 +136,7 @@ struct rsxx_cardinfo {
 		spinlock_t		lock;
 		bool			active;
 		struct creg_cmd		*active_cmd;
+		struct workqueue_struct	*creg_wq;
 		struct work_struct	done_work;
 		struct list_head	queue;
 		unsigned int		q_depth;
@@ -154,6 +157,7 @@ struct rsxx_cardinfo {
 		int buf_len;
 	} log;
 
+	struct workqueue_struct	*event_wq;
 	struct work_struct	event_work;
 	unsigned int		state;
 	u64			size8;
@@ -181,6 +185,8 @@ struct rsxx_cardinfo {
 
 	int			n_targets;
 	struct rsxx_dma_ctrl	*ctrl;
+
+	struct dentry		*debugfs_dir;
 };
 
 enum rsxx_pci_regmap {
@@ -283,6 +289,7 @@ enum rsxx_creg_addr {
 	CREG_ADD_CAPABILITIES		= 0x80001050,
 	CREG_ADD_LOG			= 0x80002000,
 	CREG_ADD_NUM_TARGETS		= 0x80003000,
+	CREG_ADD_CRAM			= 0xA0000000,
 	CREG_ADD_CONFIG			= 0xB0000000,
 };
 
@@ -372,6 +379,8 @@ typedef void (*rsxx_dma_cb)(struct rsxx_cardinfo *card,
 int rsxx_dma_setup(struct rsxx_cardinfo *card);
 void rsxx_dma_destroy(struct rsxx_cardinfo *card);
 int rsxx_dma_init(void);
+int rsxx_cleanup_dma_queue(struct rsxx_dma_ctrl *ctrl, struct list_head *q);
+int rsxx_dma_cancel(struct rsxx_dma_ctrl *ctrl);
 void rsxx_dma_cleanup(void);
 void rsxx_dma_queue_reset(struct rsxx_cardinfo *card);
 int rsxx_dma_configure(struct rsxx_cardinfo *card);
@@ -382,7 +391,6 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 			   void *cb_data);
 int rsxx_hw_buffers_init(struct pci_dev *dev, struct rsxx_dma_ctrl *ctrl);
 int rsxx_eeh_save_issued_dmas(struct rsxx_cardinfo *card);
-void rsxx_eeh_cancel_dmas(struct rsxx_cardinfo *card);
 int rsxx_eeh_remap_dmas(struct rsxx_cardinfo *card);
 
 /***** cregs.c *****/
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index dd5b2fed97e9..bf4b9d282c04 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -50,110 +50,118 @@
 #include "common.h"
 
 /*
- * These are rather arbitrary. They are fairly large because adjacent requests
- * pulled from a communication ring are quite likely to end up being part of
- * the same scatter/gather request at the disc.
+ * Maximum number of unused free pages to keep in the internal buffer.
+ * Setting this to a value too low will reduce memory used in each backend,
+ * but can have a performance penalty.
  *
- * ** TRY INCREASING 'xen_blkif_reqs' IF WRITE SPEEDS SEEM TOO LOW **
- *
- * This will increase the chances of being able to write whole tracks.
- * 64 should be enough to keep us competitive with Linux.
+ * A sane value is xen_blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST, but can
+ * be set to a lower value that might degrade performance on some intensive
+ * IO workloads.
  */
-static int xen_blkif_reqs = 64;
-module_param_named(reqs, xen_blkif_reqs, int, 0);
-MODULE_PARM_DESC(reqs, "Number of blkback requests to allocate");
 
-/* Run-time switchable: /sys/module/blkback/parameters/ */
-static unsigned int log_stats;
-module_param(log_stats, int, 0644);
+static int xen_blkif_max_buffer_pages = 1024;
+module_param_named(max_buffer_pages, xen_blkif_max_buffer_pages, int, 0644);
+MODULE_PARM_DESC(max_buffer_pages,
+"Maximum number of free pages to keep in each block backend buffer");
 
 /*
- * Each outstanding request that we've passed to the lower device layers has a
- * 'pending_req' allocated to it. Each buffer_head that completes decrements
- * the pendcnt towards zero. When it hits zero, the specified domain has a
- * response queued for it, with the saved 'id' passed back.
+ * Maximum number of grants to map persistently in blkback. For maximum
+ * performance this should be the total numbers of grants that can be used
+ * to fill the ring, but since this might become too high, specially with
+ * the use of indirect descriptors, we set it to a value that provides good
+ * performance without using too much memory.
+ *
+ * When the list of persistent grants is full we clean it up using a LRU
+ * algorithm.
  */
-struct pending_req {
-	struct xen_blkif	*blkif;
-	u64			id;
-	int			nr_pages;
-	atomic_t		pendcnt;
-	unsigned short		operation;
-	int			status;
-	struct list_head	free_list;
-	DECLARE_BITMAP(unmap_seg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
-};
 
-#define BLKBACK_INVALID_HANDLE (~0)
+static int xen_blkif_max_pgrants = 1056;
+module_param_named(max_persistent_grants, xen_blkif_max_pgrants, int, 0644);
+MODULE_PARM_DESC(max_persistent_grants,
+                 "Maximum number of grants to map persistently");
 
-struct xen_blkbk {
-	struct pending_req	*pending_reqs;
-	/* List of all 'pending_req' available */
-	struct list_head	pending_free;
-	/* And its spinlock. */
-	spinlock_t		pending_free_lock;
-	wait_queue_head_t	pending_free_wq;
-	/* The list of all pages that are available. */
-	struct page		**pending_pages;
-	/* And the grant handles that are available. */
-	grant_handle_t		*pending_grant_handles;
-};
-
-static struct xen_blkbk *blkbk;
+/*
+ * The LRU mechanism to clean the lists of persistent grants needs to
+ * be executed periodically. The time interval between consecutive executions
+ * of the purge mechanism is set in ms.
+ */
+#define LRU_INTERVAL 100
 
 /*
- * Maximum number of grant pages that can be mapped in blkback.
- * BLKIF_MAX_SEGMENTS_PER_REQUEST * RING_SIZE is the maximum number of
- * pages that blkback will persistently map.
- * Currently, this is:
- * RING_SIZE = 32 (for all known ring types)
- * BLKIF_MAX_SEGMENTS_PER_REQUEST = 11
- * sizeof(struct persistent_gnt) = 48
- * So the maximum memory used to store the grants is:
- * 32 * 11 * 48 = 16896 bytes
+ * When the persistent grants list is full we will remove unused grants
+ * from the list. The percent number of grants to be removed at each LRU
+ * execution.
  */
-static inline unsigned int max_mapped_grant_pages(enum blkif_protocol protocol)
+#define LRU_PERCENT_CLEAN 5
+
+/* Run-time switchable: /sys/module/blkback/parameters/ */
+static unsigned int log_stats;
+module_param(log_stats, int, 0644);
+
+#define BLKBACK_INVALID_HANDLE (~0)
+
+/* Number of free pages to remove on each call to free_xenballooned_pages */
+#define NUM_BATCH_FREE_PAGES 10
+
+static inline int get_free_page(struct xen_blkif *blkif, struct page **page)
 {
-	switch (protocol) {
-	case BLKIF_PROTOCOL_NATIVE:
-		return __CONST_RING_SIZE(blkif, PAGE_SIZE) *
-			   BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	case BLKIF_PROTOCOL_X86_32:
-		return __CONST_RING_SIZE(blkif_x86_32, PAGE_SIZE) *
-			   BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	case BLKIF_PROTOCOL_X86_64:
-		return __CONST_RING_SIZE(blkif_x86_64, PAGE_SIZE) *
-			   BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	default:
-		BUG();
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkif->free_pages_lock, flags);
+	if (list_empty(&blkif->free_pages)) {
+		BUG_ON(blkif->free_pages_num != 0);
+		spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+		return alloc_xenballooned_pages(1, page, false);
 	}
+	BUG_ON(blkif->free_pages_num == 0);
+	page[0] = list_first_entry(&blkif->free_pages, struct page, lru);
+	list_del(&page[0]->lru);
+	blkif->free_pages_num--;
+	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+
 	return 0;
 }
 
-
-/*
- * Little helpful macro to figure out the index and virtual address of the
- * pending_pages[..]. For each 'pending_req' we have have up to
- * BLKIF_MAX_SEGMENTS_PER_REQUEST (11) pages. The seg would be from 0 through
- * 10 and would index in the pending_pages[..].
- */
-static inline int vaddr_pagenr(struct pending_req *req, int seg)
+static inline void put_free_pages(struct xen_blkif *blkif, struct page **page,
+                                  int num)
 {
-	return (req - blkbk->pending_reqs) *
-		BLKIF_MAX_SEGMENTS_PER_REQUEST + seg;
-}
+	unsigned long flags;
+	int i;
 
-#define pending_page(req, seg) pending_pages[vaddr_pagenr(req, seg)]
+	spin_lock_irqsave(&blkif->free_pages_lock, flags);
+	for (i = 0; i < num; i++)
+		list_add(&page[i]->lru, &blkif->free_pages);
+	blkif->free_pages_num += num;
+	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+}
 
-static inline unsigned long vaddr(struct pending_req *req, int seg)
+static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num)
 {
-	unsigned long pfn = page_to_pfn(blkbk->pending_page(req, seg));
-	return (unsigned long)pfn_to_kaddr(pfn);
-}
+	/* Remove requested pages in batches of NUM_BATCH_FREE_PAGES */
+	struct page *page[NUM_BATCH_FREE_PAGES];
+	unsigned int num_pages = 0;
+	unsigned long flags;
 
-#define pending_handle(_req, _seg) \
-	(blkbk->pending_grant_handles[vaddr_pagenr(_req, _seg)])
+	spin_lock_irqsave(&blkif->free_pages_lock, flags);
+	while (blkif->free_pages_num > num) {
+		BUG_ON(list_empty(&blkif->free_pages));
+		page[num_pages] = list_first_entry(&blkif->free_pages,
+		                                   struct page, lru);
+		list_del(&page[num_pages]->lru);
+		blkif->free_pages_num--;
+		if (++num_pages == NUM_BATCH_FREE_PAGES) {
+			spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+			free_xenballooned_pages(num_pages, page);
+			spin_lock_irqsave(&blkif->free_pages_lock, flags);
+			num_pages = 0;
+		}
+	}
+	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+	if (num_pages != 0)
+		free_xenballooned_pages(num_pages, page);
+}
 
+#define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page)))
 
 static int do_block_io_op(struct xen_blkif *blkif);
 static int dispatch_rw_block_io(struct xen_blkif *blkif,
@@ -170,13 +178,29 @@ static void make_response(struct xen_blkif *blkif, u64 id,
 	     (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL)
 
 
-static void add_persistent_gnt(struct rb_root *root,
+/*
+ * We don't need locking around the persistent grant helpers
+ * because blkback uses a single-thread for each backed, so we
+ * can be sure that this functions will never be called recursively.
+ *
+ * The only exception to that is put_persistent_grant, that can be called
+ * from interrupt context (by xen_blkbk_unmap), so we have to use atomic
+ * bit operations to modify the flags of a persistent grant and to count
+ * the number of used grants.
+ */
+static int add_persistent_gnt(struct xen_blkif *blkif,
 			       struct persistent_gnt *persistent_gnt)
 {
-	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct rb_node **new = NULL, *parent = NULL;
 	struct persistent_gnt *this;
 
+	if (blkif->persistent_gnt_c >= xen_blkif_max_pgrants) {
+		if (!blkif->vbd.overflow_max_grants)
+			blkif->vbd.overflow_max_grants = 1;
+		return -EBUSY;
+	}
 	/* Figure out where to put new node */
+	new = &blkif->persistent_gnts.rb_node;
 	while (*new) {
 		this = container_of(*new, struct persistent_gnt, node);
 
@@ -186,22 +210,28 @@ static void add_persistent_gnt(struct rb_root *root,
 		else if (persistent_gnt->gnt > this->gnt)
 			new = &((*new)->rb_right);
 		else {
-			pr_alert(DRV_PFX " trying to add a gref that's already in the tree\n");
-			BUG();
+			pr_alert_ratelimited(DRV_PFX " trying to add a gref that's already in the tree\n");
+			return -EINVAL;
 		}
 	}
 
+	bitmap_zero(persistent_gnt->flags, PERSISTENT_GNT_FLAGS_SIZE);
+	set_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags);
 	/* Add new node and rebalance tree. */
 	rb_link_node(&(persistent_gnt->node), parent, new);
-	rb_insert_color(&(persistent_gnt->node), root);
+	rb_insert_color(&(persistent_gnt->node), &blkif->persistent_gnts);
+	blkif->persistent_gnt_c++;
+	atomic_inc(&blkif->persistent_gnt_in_use);
+	return 0;
 }
 
-static struct persistent_gnt *get_persistent_gnt(struct rb_root *root,
+static struct persistent_gnt *get_persistent_gnt(struct xen_blkif *blkif,
 						 grant_ref_t gref)
 {
 	struct persistent_gnt *data;
-	struct rb_node *node = root->rb_node;
+	struct rb_node *node = NULL;
 
+	node = blkif->persistent_gnts.rb_node;
 	while (node) {
 		data = container_of(node, struct persistent_gnt, node);
 
@@ -209,13 +239,31 @@ static struct persistent_gnt *get_persistent_gnt(struct rb_root *root,
 			node = node->rb_left;
 		else if (gref > data->gnt)
 			node = node->rb_right;
-		else
+		else {
+			if(test_bit(PERSISTENT_GNT_ACTIVE, data->flags)) {
+				pr_alert_ratelimited(DRV_PFX " requesting a grant already in use\n");
+				return NULL;
+			}
+			set_bit(PERSISTENT_GNT_ACTIVE, data->flags);
+			atomic_inc(&blkif->persistent_gnt_in_use);
 			return data;
+		}
 	}
 	return NULL;
 }
 
-static void free_persistent_gnts(struct rb_root *root, unsigned int num)
+static void put_persistent_gnt(struct xen_blkif *blkif,
+                               struct persistent_gnt *persistent_gnt)
+{
+	if(!test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags))
+	          pr_alert_ratelimited(DRV_PFX " freeing a grant already unused");
+	set_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags);
+	clear_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags);
+	atomic_dec(&blkif->persistent_gnt_in_use);
+}
+
+static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
+                                 unsigned int num)
 {
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
@@ -240,7 +288,7 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num)
 			ret = gnttab_unmap_refs(unmap, NULL, pages,
 				segs_to_unmap);
 			BUG_ON(ret);
-			free_xenballooned_pages(segs_to_unmap, pages);
+			put_free_pages(blkif, pages, segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 
@@ -251,21 +299,148 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num)
 	BUG_ON(num != 0);
 }
 
+static void unmap_purged_grants(struct work_struct *work)
+{
+	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct persistent_gnt *persistent_gnt;
+	int ret, segs_to_unmap = 0;
+	struct xen_blkif *blkif = container_of(work, typeof(*blkif), persistent_purge_work);
+
+	while(!list_empty(&blkif->persistent_purge_list)) {
+		persistent_gnt = list_first_entry(&blkif->persistent_purge_list,
+		                                  struct persistent_gnt,
+		                                  remove_node);
+		list_del(&persistent_gnt->remove_node);
+
+		gnttab_set_unmap_op(&unmap[segs_to_unmap],
+			vaddr(persistent_gnt->page),
+			GNTMAP_host_map,
+			persistent_gnt->handle);
+
+		pages[segs_to_unmap] = persistent_gnt->page;
+
+		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+			ret = gnttab_unmap_refs(unmap, NULL, pages,
+				segs_to_unmap);
+			BUG_ON(ret);
+			put_free_pages(blkif, pages, segs_to_unmap);
+			segs_to_unmap = 0;
+		}
+		kfree(persistent_gnt);
+	}
+	if (segs_to_unmap > 0) {
+		ret = gnttab_unmap_refs(unmap, NULL, pages, segs_to_unmap);
+		BUG_ON(ret);
+		put_free_pages(blkif, pages, segs_to_unmap);
+	}
+}
+
+static void purge_persistent_gnt(struct xen_blkif *blkif)
+{
+	struct persistent_gnt *persistent_gnt;
+	struct rb_node *n;
+	unsigned int num_clean, total;
+	bool scan_used = false, clean_used = false;
+	struct rb_root *root;
+
+	if (blkif->persistent_gnt_c < xen_blkif_max_pgrants ||
+	    (blkif->persistent_gnt_c == xen_blkif_max_pgrants &&
+	    !blkif->vbd.overflow_max_grants)) {
+		return;
+	}
+
+	if (work_pending(&blkif->persistent_purge_work)) {
+		pr_alert_ratelimited(DRV_PFX "Scheduled work from previous purge is still pending, cannot purge list\n");
+		return;
+	}
+
+	num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN;
+	num_clean = blkif->persistent_gnt_c - xen_blkif_max_pgrants + num_clean;
+	num_clean = min(blkif->persistent_gnt_c, num_clean);
+	if ((num_clean == 0) ||
+	    (num_clean > (blkif->persistent_gnt_c - atomic_read(&blkif->persistent_gnt_in_use))))
+		return;
+
+	/*
+	 * At this point, we can assure that there will be no calls
+         * to get_persistent_grant (because we are executing this code from
+         * xen_blkif_schedule), there can only be calls to put_persistent_gnt,
+         * which means that the number of currently used grants will go down,
+         * but never up, so we will always be able to remove the requested
+         * number of grants.
+	 */
+
+	total = num_clean;
+
+	pr_debug(DRV_PFX "Going to purge %u persistent grants\n", num_clean);
+
+	INIT_LIST_HEAD(&blkif->persistent_purge_list);
+	root = &blkif->persistent_gnts;
+purge_list:
+	foreach_grant_safe(persistent_gnt, n, root, node) {
+		BUG_ON(persistent_gnt->handle ==
+			BLKBACK_INVALID_HANDLE);
+
+		if (clean_used) {
+			clear_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags);
+			continue;
+		}
+
+		if (test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags))
+			continue;
+		if (!scan_used &&
+		    (test_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags)))
+			continue;
+
+		rb_erase(&persistent_gnt->node, root);
+		list_add(&persistent_gnt->remove_node,
+		         &blkif->persistent_purge_list);
+		if (--num_clean == 0)
+			goto finished;
+	}
+	/*
+	 * If we get here it means we also need to start cleaning
+	 * grants that were used since last purge in order to cope
+	 * with the requested num
+	 */
+	if (!scan_used && !clean_used) {
+		pr_debug(DRV_PFX "Still missing %u purged frames\n", num_clean);
+		scan_used = true;
+		goto purge_list;
+	}
+finished:
+	if (!clean_used) {
+		pr_debug(DRV_PFX "Finished scanning for grants to clean, removing used flag\n");
+		clean_used = true;
+		goto purge_list;
+	}
+
+	blkif->persistent_gnt_c -= (total - num_clean);
+	blkif->vbd.overflow_max_grants = 0;
+
+	/* We can defer this work */
+	INIT_WORK(&blkif->persistent_purge_work, unmap_purged_grants);
+	schedule_work(&blkif->persistent_purge_work);
+	pr_debug(DRV_PFX "Purged %u/%u\n", (total - num_clean), total);
+	return;
+}
+
 /*
  * Retrieve from the 'pending_reqs' a free pending_req structure to be used.
  */
-static struct pending_req *alloc_req(void)
+static struct pending_req *alloc_req(struct xen_blkif *blkif)
 {
 	struct pending_req *req = NULL;
 	unsigned long flags;
 
-	spin_lock_irqsave(&blkbk->pending_free_lock, flags);
-	if (!list_empty(&blkbk->pending_free)) {
-		req = list_entry(blkbk->pending_free.next, struct pending_req,
+	spin_lock_irqsave(&blkif->pending_free_lock, flags);
+	if (!list_empty(&blkif->pending_free)) {
+		req = list_entry(blkif->pending_free.next, struct pending_req,
 				 free_list);
 		list_del(&req->free_list);
 	}
-	spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
+	spin_unlock_irqrestore(&blkif->pending_free_lock, flags);
 	return req;
 }
 
@@ -273,17 +448,17 @@ static struct pending_req *alloc_req(void)
  * Return the 'pending_req' structure back to the freepool. We also
  * wake up the thread if it was waiting for a free page.
  */
-static void free_req(struct pending_req *req)
+static void free_req(struct xen_blkif *blkif, struct pending_req *req)
 {
 	unsigned long flags;
 	int was_empty;
 
-	spin_lock_irqsave(&blkbk->pending_free_lock, flags);
-	was_empty = list_empty(&blkbk->pending_free);
-	list_add(&req->free_list, &blkbk->pending_free);
-	spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
+	spin_lock_irqsave(&blkif->pending_free_lock, flags);
+	was_empty = list_empty(&blkif->pending_free);
+	list_add(&req->free_list, &blkif->pending_free);
+	spin_unlock_irqrestore(&blkif->pending_free_lock, flags);
 	if (was_empty)
-		wake_up(&blkbk->pending_free_wq);
+		wake_up(&blkif->pending_free_wq);
 }
 
 /*
@@ -382,10 +557,12 @@ irqreturn_t xen_blkif_be_int(int irq, void *dev_id)
 static void print_stats(struct xen_blkif *blkif)
 {
 	pr_info("xen-blkback (%s): oo %3llu  |  rd %4llu  |  wr %4llu  |  f %4llu"
-		 "  |  ds %4llu\n",
+		 "  |  ds %4llu | pg: %4u/%4d\n",
 		 current->comm, blkif->st_oo_req,
 		 blkif->st_rd_req, blkif->st_wr_req,
-		 blkif->st_f_req, blkif->st_ds_req);
+		 blkif->st_f_req, blkif->st_ds_req,
+		 blkif->persistent_gnt_c,
+		 xen_blkif_max_pgrants);
 	blkif->st_print = jiffies + msecs_to_jiffies(10 * 1000);
 	blkif->st_rd_req = 0;
 	blkif->st_wr_req = 0;
@@ -397,6 +574,8 @@ int xen_blkif_schedule(void *arg)
 {
 	struct xen_blkif *blkif = arg;
 	struct xen_vbd *vbd = &blkif->vbd;
+	unsigned long timeout;
+	int ret;
 
 	xen_blkif_get(blkif);
 
@@ -406,27 +585,52 @@ int xen_blkif_schedule(void *arg)
 		if (unlikely(vbd->size != vbd_sz(vbd)))
 			xen_vbd_resize(blkif);
 
-		wait_event_interruptible(
+		timeout = msecs_to_jiffies(LRU_INTERVAL);
+
+		timeout = wait_event_interruptible_timeout(
 			blkif->wq,
-			blkif->waiting_reqs || kthread_should_stop());
-		wait_event_interruptible(
-			blkbk->pending_free_wq,
-			!list_empty(&blkbk->pending_free) ||
-			kthread_should_stop());
+			blkif->waiting_reqs || kthread_should_stop(),
+			timeout);
+		if (timeout == 0)
+			goto purge_gnt_list;
+		timeout = wait_event_interruptible_timeout(
+			blkif->pending_free_wq,
+			!list_empty(&blkif->pending_free) ||
+			kthread_should_stop(),
+			timeout);
+		if (timeout == 0)
+			goto purge_gnt_list;
 
 		blkif->waiting_reqs = 0;
 		smp_mb(); /* clear flag *before* checking for work */
 
-		if (do_block_io_op(blkif))
+		ret = do_block_io_op(blkif);
+		if (ret > 0)
 			blkif->waiting_reqs = 1;
+		if (ret == -EACCES)
+			wait_event_interruptible(blkif->shutdown_wq,
+						 kthread_should_stop());
+
+purge_gnt_list:
+		if (blkif->vbd.feature_gnt_persistent &&
+		    time_after(jiffies, blkif->next_lru)) {
+			purge_persistent_gnt(blkif);
+			blkif->next_lru = jiffies + msecs_to_jiffies(LRU_INTERVAL);
+		}
+
+		/* Shrink if we have more than xen_blkif_max_buffer_pages */
+		shrink_free_pagepool(blkif, xen_blkif_max_buffer_pages);
 
 		if (log_stats && time_after(jiffies, blkif->st_print))
 			print_stats(blkif);
 	}
 
+	/* Since we are shutting down remove all pages from the buffer */
+	shrink_free_pagepool(blkif, 0 /* All */);
+
 	/* Free all persistent grant pages */
 	if (!RB_EMPTY_ROOT(&blkif->persistent_gnts))
-		free_persistent_gnts(&blkif->persistent_gnts,
+		free_persistent_gnts(blkif, &blkif->persistent_gnts,
 			blkif->persistent_gnt_c);
 
 	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
@@ -441,148 +645,98 @@ int xen_blkif_schedule(void *arg)
 	return 0;
 }
 
-struct seg_buf {
-	unsigned int offset;
-	unsigned int nsec;
-};
 /*
  * Unmap the grant references, and also remove the M2P over-rides
  * used in the 'pending_req'.
  */
-static void xen_blkbk_unmap(struct pending_req *req)
+static void xen_blkbk_unmap(struct xen_blkif *blkif,
+                            struct grant_page *pages[],
+                            int num)
 {
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
-	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct page *unmap_pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	unsigned int i, invcount = 0;
-	grant_handle_t handle;
 	int ret;
 
-	for (i = 0; i < req->nr_pages; i++) {
-		if (!test_bit(i, req->unmap_seg))
+	for (i = 0; i < num; i++) {
+		if (pages[i]->persistent_gnt != NULL) {
+			put_persistent_gnt(blkif, pages[i]->persistent_gnt);
 			continue;
-		handle = pending_handle(req, i);
-		if (handle == BLKBACK_INVALID_HANDLE)
+		}
+		if (pages[i]->handle == BLKBACK_INVALID_HANDLE)
 			continue;
-		gnttab_set_unmap_op(&unmap[invcount], vaddr(req, i),
-				    GNTMAP_host_map, handle);
-		pending_handle(req, i) = BLKBACK_INVALID_HANDLE;
-		pages[invcount] = virt_to_page(vaddr(req, i));
-		invcount++;
+		unmap_pages[invcount] = pages[i]->page;
+		gnttab_set_unmap_op(&unmap[invcount], vaddr(pages[i]->page),
+				    GNTMAP_host_map, pages[i]->handle);
+		pages[i]->handle = BLKBACK_INVALID_HANDLE;
+		if (++invcount == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages,
+			                        invcount);
+			BUG_ON(ret);
+			put_free_pages(blkif, unmap_pages, invcount);
+			invcount = 0;
+		}
+	}
+	if (invcount) {
+		ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);
+		BUG_ON(ret);
+		put_free_pages(blkif, unmap_pages, invcount);
 	}
-
-	ret = gnttab_unmap_refs(unmap, NULL, pages, invcount);
-	BUG_ON(ret);
 }
 
-static int xen_blkbk_map(struct blkif_request *req,
-			 struct pending_req *pending_req,
-			 struct seg_buf seg[],
-			 struct page *pages[])
+static int xen_blkbk_map(struct xen_blkif *blkif,
+			 struct grant_page *pages[],
+			 int num, bool ro)
 {
 	struct gnttab_map_grant_ref map[BLKIF_MAX_SEGMENTS_PER_REQUEST];
-	struct persistent_gnt *persistent_gnts[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages_to_gnt[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct persistent_gnt *persistent_gnt = NULL;
-	struct xen_blkif *blkif = pending_req->blkif;
 	phys_addr_t addr = 0;
-	int i, j;
-	bool new_map;
-	int nseg = req->u.rw.nr_segments;
+	int i, seg_idx, new_map_idx;
 	int segs_to_map = 0;
 	int ret = 0;
+	int last_map = 0, map_until = 0;
 	int use_persistent_gnts;
 
 	use_persistent_gnts = (blkif->vbd.feature_gnt_persistent);
 
-	BUG_ON(blkif->persistent_gnt_c >
-		   max_mapped_grant_pages(pending_req->blkif->blk_protocol));
-
 	/*
 	 * Fill out preq.nr_sects with proper amount of sectors, and setup
 	 * assign map[..] with the PFN of the page in our domain with the
 	 * corresponding grant reference for each page.
 	 */
-	for (i = 0; i < nseg; i++) {
+again:
+	for (i = map_until; i < num; i++) {
 		uint32_t flags;
 
 		if (use_persistent_gnts)
 			persistent_gnt = get_persistent_gnt(
-				&blkif->persistent_gnts,
-				req->u.rw.seg[i].gref);
+				blkif,
+				pages[i]->gref);
 
 		if (persistent_gnt) {
 			/*
 			 * We are using persistent grants and
 			 * the grant is already mapped
 			 */
-			new_map = false;
-		} else if (use_persistent_gnts &&
-			   blkif->persistent_gnt_c <
-			   max_mapped_grant_pages(blkif->blk_protocol)) {
-			/*
-			 * We are using persistent grants, the grant is
-			 * not mapped but we have room for it
-			 */
-			new_map = true;
-			persistent_gnt = kmalloc(
-				sizeof(struct persistent_gnt),
-				GFP_KERNEL);
-			if (!persistent_gnt)
-				return -ENOMEM;
-			if (alloc_xenballooned_pages(1, &persistent_gnt->page,
-			    false)) {
-				kfree(persistent_gnt);
-				return -ENOMEM;
-			}
-			persistent_gnt->gnt = req->u.rw.seg[i].gref;
-			persistent_gnt->handle = BLKBACK_INVALID_HANDLE;
-
-			pages_to_gnt[segs_to_map] =
-				persistent_gnt->page;
-			addr = (unsigned long) pfn_to_kaddr(
-				page_to_pfn(persistent_gnt->page));
-
-			add_persistent_gnt(&blkif->persistent_gnts,
-				persistent_gnt);
-			blkif->persistent_gnt_c++;
-			pr_debug(DRV_PFX " grant %u added to the tree of persistent grants, using %u/%u\n",
-				 persistent_gnt->gnt, blkif->persistent_gnt_c,
-				 max_mapped_grant_pages(blkif->blk_protocol));
+			pages[i]->page = persistent_gnt->page;
+			pages[i]->persistent_gnt = persistent_gnt;
 		} else {
-			/*
-			 * We are either using persistent grants and
-			 * hit the maximum limit of grants mapped,
-			 * or we are not using persistent grants.
-			 */
-			if (use_persistent_gnts &&
-				!blkif->vbd.overflow_max_grants) {
-				blkif->vbd.overflow_max_grants = 1;
-				pr_alert(DRV_PFX " domain %u, device %#x is using maximum number of persistent grants\n",
-					 blkif->domid, blkif->vbd.handle);
-			}
-			new_map = true;
-			pages[i] = blkbk->pending_page(pending_req, i);
-			addr = vaddr(pending_req, i);
-			pages_to_gnt[segs_to_map] =
-				blkbk->pending_page(pending_req, i);
-		}
-
-		if (persistent_gnt) {
-			pages[i] = persistent_gnt->page;
-			persistent_gnts[i] = persistent_gnt;
-		} else {
-			persistent_gnts[i] = NULL;
-		}
-
-		if (new_map) {
+			if (get_free_page(blkif, &pages[i]->page))
+				goto out_of_memory;
+			addr = vaddr(pages[i]->page);
+			pages_to_gnt[segs_to_map] = pages[i]->page;
+			pages[i]->persistent_gnt = NULL;
 			flags = GNTMAP_host_map;
-			if (!persistent_gnt &&
-			    (pending_req->operation != BLKIF_OP_READ))
+			if (!use_persistent_gnts && ro)
 				flags |= GNTMAP_readonly;
 			gnttab_set_map_op(&map[segs_to_map++], addr,
-					  flags, req->u.rw.seg[i].gref,
+					  flags, pages[i]->gref,
 					  blkif->domid);
 		}
+		map_until = i + 1;
+		if (segs_to_map == BLKIF_MAX_SEGMENTS_PER_REQUEST)
+			break;
 	}
 
 	if (segs_to_map) {
@@ -595,49 +749,133 @@ static int xen_blkbk_map(struct blkif_request *req,
 	 * so that when we access vaddr(pending_req,i) it has the contents of
 	 * the page from the other domain.
 	 */
-	bitmap_zero(pending_req->unmap_seg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
-	for (i = 0, j = 0; i < nseg; i++) {
-		if (!persistent_gnts[i] ||
-		    persistent_gnts[i]->handle == BLKBACK_INVALID_HANDLE) {
+	for (seg_idx = last_map, new_map_idx = 0; seg_idx < map_until; seg_idx++) {
+		if (!pages[seg_idx]->persistent_gnt) {
 			/* This is a newly mapped grant */
-			BUG_ON(j >= segs_to_map);
-			if (unlikely(map[j].status != 0)) {
+			BUG_ON(new_map_idx >= segs_to_map);
+			if (unlikely(map[new_map_idx].status != 0)) {
 				pr_debug(DRV_PFX "invalid buffer -- could not remap it\n");
-				map[j].handle = BLKBACK_INVALID_HANDLE;
+				pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE;
 				ret |= 1;
-				if (persistent_gnts[i]) {
-					rb_erase(&persistent_gnts[i]->node,
-						 &blkif->persistent_gnts);
-					blkif->persistent_gnt_c--;
-					kfree(persistent_gnts[i]);
-					persistent_gnts[i] = NULL;
-				}
+				goto next;
 			}
+			pages[seg_idx]->handle = map[new_map_idx].handle;
+		} else {
+			continue;
 		}
-		if (persistent_gnts[i]) {
-			if (persistent_gnts[i]->handle ==
-			    BLKBACK_INVALID_HANDLE) {
+		if (use_persistent_gnts &&
+		    blkif->persistent_gnt_c < xen_blkif_max_pgrants) {
+			/*
+			 * We are using persistent grants, the grant is
+			 * not mapped but we might have room for it.
+			 */
+			persistent_gnt = kmalloc(sizeof(struct persistent_gnt),
+				                 GFP_KERNEL);
+			if (!persistent_gnt) {
 				/*
-				 * If this is a new persistent grant
-				 * save the handler
+				 * If we don't have enough memory to
+				 * allocate the persistent_gnt struct
+				 * map this grant non-persistenly
 				 */
-				persistent_gnts[i]->handle = map[j++].handle;
+				goto next;
 			}
-			pending_handle(pending_req, i) =
-				persistent_gnts[i]->handle;
+			persistent_gnt->gnt = map[new_map_idx].ref;
+			persistent_gnt->handle = map[new_map_idx].handle;
+			persistent_gnt->page = pages[seg_idx]->page;
+			if (add_persistent_gnt(blkif,
+			                       persistent_gnt)) {
+				kfree(persistent_gnt);
+				persistent_gnt = NULL;
+				goto next;
+			}
+			pages[seg_idx]->persistent_gnt = persistent_gnt;
+			pr_debug(DRV_PFX " grant %u added to the tree of persistent grants, using %u/%u\n",
+				 persistent_gnt->gnt, blkif->persistent_gnt_c,
+				 xen_blkif_max_pgrants);
+			goto next;
+		}
+		if (use_persistent_gnts && !blkif->vbd.overflow_max_grants) {
+			blkif->vbd.overflow_max_grants = 1;
+			pr_debug(DRV_PFX " domain %u, device %#x is using maximum number of persistent grants\n",
+			         blkif->domid, blkif->vbd.handle);
+		}
+		/*
+		 * We could not map this grant persistently, so use it as
+		 * a non-persistent grant.
+		 */
+next:
+		new_map_idx++;
+	}
+	segs_to_map = 0;
+	last_map = map_until;
+	if (map_until != num)
+		goto again;
 
-			if (ret)
-				continue;
-		} else {
-			pending_handle(pending_req, i) = map[j++].handle;
-			bitmap_set(pending_req->unmap_seg, i, 1);
+	return ret;
+
+out_of_memory:
+	pr_alert(DRV_PFX "%s: out of memory\n", __func__);
+	put_free_pages(blkif, pages_to_gnt, segs_to_map);
+	return -ENOMEM;
+}
+
+static int xen_blkbk_map_seg(struct pending_req *pending_req)
+{
+	int rc;
+
+	rc = xen_blkbk_map(pending_req->blkif, pending_req->segments,
+			   pending_req->nr_pages,
+	                   (pending_req->operation != BLKIF_OP_READ));
+
+	return rc;
+}
 
-			if (ret)
-				continue;
+static int xen_blkbk_parse_indirect(struct blkif_request *req,
+				    struct pending_req *pending_req,
+				    struct seg_buf seg[],
+				    struct phys_req *preq)
+{
+	struct grant_page **pages = pending_req->indirect_pages;
+	struct xen_blkif *blkif = pending_req->blkif;
+	int indirect_grefs, rc, n, nseg, i;
+	struct blkif_request_segment_aligned *segments = NULL;
+
+	nseg = pending_req->nr_pages;
+	indirect_grefs = INDIRECT_PAGES(nseg);
+	BUG_ON(indirect_grefs > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST);
+
+	for (i = 0; i < indirect_grefs; i++)
+		pages[i]->gref = req->u.indirect.indirect_grefs[i];
+
+	rc = xen_blkbk_map(blkif, pages, indirect_grefs, true);
+	if (rc)
+		goto unmap;
+
+	for (n = 0, i = 0; n < nseg; n++) {
+		if ((n % SEGS_PER_INDIRECT_FRAME) == 0) {
+			/* Map indirect segments */
+			if (segments)
+				kunmap_atomic(segments);
+			segments = kmap_atomic(pages[n/SEGS_PER_INDIRECT_FRAME]->page);
+		}
+		i = n % SEGS_PER_INDIRECT_FRAME;
+		pending_req->segments[n]->gref = segments[i].gref;
+		seg[n].nsec = segments[i].last_sect -
+			segments[i].first_sect + 1;
+		seg[n].offset = (segments[i].first_sect << 9);
+		if ((segments[i].last_sect >= (PAGE_SIZE >> 9)) ||
+		    (segments[i].last_sect < segments[i].first_sect)) {
+			rc = -EINVAL;
+			goto unmap;
 		}
-		seg[i].offset = (req->u.rw.seg[i].first_sect << 9);
+		preq->nr_sects += seg[n].nsec;
 	}
-	return ret;
+
+unmap:
+	if (segments)
+		kunmap_atomic(segments);
+	xen_blkbk_unmap(blkif, pages, indirect_grefs);
+	return rc;
 }
 
 static int dispatch_discard_io(struct xen_blkif *blkif,
@@ -647,7 +885,18 @@ static int dispatch_discard_io(struct xen_blkif *blkif,
 	int status = BLKIF_RSP_OKAY;
 	struct block_device *bdev = blkif->vbd.bdev;
 	unsigned long secure;
+	struct phys_req preq;
+
+	preq.sector_number = req->u.discard.sector_number;
+	preq.nr_sects      = req->u.discard.nr_sectors;
 
+	err = xen_vbd_translate(&preq, blkif, WRITE);
+	if (err) {
+		pr_warn(DRV_PFX "access denied: DISCARD [%llu->%llu] on dev=%04x\n",
+			preq.sector_number,
+			preq.sector_number + preq.nr_sects, blkif->vbd.pdevice);
+		goto fail_response;
+	}
 	blkif->st_ds_req++;
 
 	xen_blkif_get(blkif);
@@ -658,7 +907,7 @@ static int dispatch_discard_io(struct xen_blkif *blkif,
 	err = blkdev_issue_discard(bdev, req->u.discard.sector_number,
 				   req->u.discard.nr_sectors,
 				   GFP_KERNEL, secure);
-
+fail_response:
 	if (err == -EOPNOTSUPP) {
 		pr_debug(DRV_PFX "discard op failed, not supported\n");
 		status = BLKIF_RSP_EOPNOTSUPP;
@@ -674,7 +923,7 @@ static int dispatch_other_io(struct xen_blkif *blkif,
 			     struct blkif_request *req,
 			     struct pending_req *pending_req)
 {
-	free_req(pending_req);
+	free_req(blkif, pending_req);
 	make_response(blkif, req->u.other.id, req->operation,
 		      BLKIF_RSP_EOPNOTSUPP);
 	return -EIO;
@@ -726,7 +975,9 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
 	 * the proper response on the ring.
 	 */
 	if (atomic_dec_and_test(&pending_req->pendcnt)) {
-		xen_blkbk_unmap(pending_req);
+		xen_blkbk_unmap(pending_req->blkif,
+		                pending_req->segments,
+		                pending_req->nr_pages);
 		make_response(pending_req->blkif, pending_req->id,
 			      pending_req->operation, pending_req->status);
 		xen_blkif_put(pending_req->blkif);
@@ -734,7 +985,7 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
 			if (atomic_read(&pending_req->blkif->drain))
 				complete(&pending_req->blkif->drain_complete);
 		}
-		free_req(pending_req);
+		free_req(pending_req->blkif, pending_req);
 	}
 }
 
@@ -767,6 +1018,12 @@ __do_block_io_op(struct xen_blkif *blkif)
 	rp = blk_rings->common.sring->req_prod;
 	rmb(); /* Ensure we see queued requests up to 'rp'. */
 
+	if (RING_REQUEST_PROD_OVERFLOW(&blk_rings->common, rp)) {
+		rc = blk_rings->common.rsp_prod_pvt;
+		pr_warn(DRV_PFX "Frontend provided bogus ring requests (%d - %d = %d). Halting ring processing on dev=%04x\n",
+			rp, rc, rp - rc, blkif->vbd.pdevice);
+		return -EACCES;
+	}
 	while (rc != rp) {
 
 		if (RING_REQUEST_CONS_OVERFLOW(&blk_rings->common, rc))
@@ -777,7 +1034,7 @@ __do_block_io_op(struct xen_blkif *blkif)
 			break;
 		}
 
-		pending_req = alloc_req();
+		pending_req = alloc_req(blkif);
 		if (NULL == pending_req) {
 			blkif->st_oo_req++;
 			more_to_do = 1;
@@ -807,11 +1064,12 @@ __do_block_io_op(struct xen_blkif *blkif)
 		case BLKIF_OP_WRITE:
 		case BLKIF_OP_WRITE_BARRIER:
 		case BLKIF_OP_FLUSH_DISKCACHE:
+		case BLKIF_OP_INDIRECT:
 			if (dispatch_rw_block_io(blkif, &req, pending_req))
 				goto done;
 			break;
 		case BLKIF_OP_DISCARD:
-			free_req(pending_req);
+			free_req(blkif, pending_req);
 			if (dispatch_discard_io(blkif, &req))
 				goto done;
 			break;
@@ -853,17 +1111,28 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 				struct pending_req *pending_req)
 {
 	struct phys_req preq;
-	struct seg_buf seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct seg_buf *seg = pending_req->seg;
 	unsigned int nseg;
 	struct bio *bio = NULL;
-	struct bio *biolist[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct bio **biolist = pending_req->biolist;
 	int i, nbio = 0;
 	int operation;
 	struct blk_plug plug;
 	bool drain = false;
-	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct grant_page **pages = pending_req->segments;
+	unsigned short req_operation;
+
+	req_operation = req->operation == BLKIF_OP_INDIRECT ?
+			req->u.indirect.indirect_op : req->operation;
+	if ((req->operation == BLKIF_OP_INDIRECT) &&
+	    (req_operation != BLKIF_OP_READ) &&
+	    (req_operation != BLKIF_OP_WRITE)) {
+		pr_debug(DRV_PFX "Invalid indirect operation (%u)\n",
+			 req_operation);
+		goto fail_response;
+	}
 
-	switch (req->operation) {
+	switch (req_operation) {
 	case BLKIF_OP_READ:
 		blkif->st_rd_req++;
 		operation = READ;
@@ -885,33 +1154,47 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 	}
 
 	/* Check that the number of segments is sane. */
-	nseg = req->u.rw.nr_segments;
+	nseg = req->operation == BLKIF_OP_INDIRECT ?
+	       req->u.indirect.nr_segments : req->u.rw.nr_segments;
 
 	if (unlikely(nseg == 0 && operation != WRITE_FLUSH) ||
-	    unlikely(nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
+	    unlikely((req->operation != BLKIF_OP_INDIRECT) &&
+		     (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) ||
+	    unlikely((req->operation == BLKIF_OP_INDIRECT) &&
+		     (nseg > MAX_INDIRECT_SEGMENTS))) {
 		pr_debug(DRV_PFX "Bad number of segments in request (%d)\n",
 			 nseg);
 		/* Haven't submitted any bio's yet. */
 		goto fail_response;
 	}
 
-	preq.sector_number = req->u.rw.sector_number;
 	preq.nr_sects      = 0;
 
 	pending_req->blkif     = blkif;
 	pending_req->id        = req->u.rw.id;
-	pending_req->operation = req->operation;
+	pending_req->operation = req_operation;
 	pending_req->status    = BLKIF_RSP_OKAY;
 	pending_req->nr_pages  = nseg;
 
-	for (i = 0; i < nseg; i++) {
-		seg[i].nsec = req->u.rw.seg[i].last_sect -
-			req->u.rw.seg[i].first_sect + 1;
-		if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) ||
-		    (req->u.rw.seg[i].last_sect < req->u.rw.seg[i].first_sect))
+	if (req->operation != BLKIF_OP_INDIRECT) {
+		preq.dev               = req->u.rw.handle;
+		preq.sector_number     = req->u.rw.sector_number;
+		for (i = 0; i < nseg; i++) {
+			pages[i]->gref = req->u.rw.seg[i].gref;
+			seg[i].nsec = req->u.rw.seg[i].last_sect -
+				req->u.rw.seg[i].first_sect + 1;
+			seg[i].offset = (req->u.rw.seg[i].first_sect << 9);
+			if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) ||
+			    (req->u.rw.seg[i].last_sect <
+			     req->u.rw.seg[i].first_sect))
+				goto fail_response;
+			preq.nr_sects += seg[i].nsec;
+		}
+	} else {
+		preq.dev               = req->u.indirect.handle;
+		preq.sector_number     = req->u.indirect.sector_number;
+		if (xen_blkbk_parse_indirect(req, pending_req, seg, &preq))
 			goto fail_response;
-		preq.nr_sects += seg[i].nsec;
-
 	}
 
 	if (xen_vbd_translate(&preq, blkif, operation) != 0) {
@@ -948,7 +1231,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 	 * the hypercall to unmap the grants - that is all done in
 	 * xen_blkbk_unmap.
 	 */
-	if (xen_blkbk_map(req, pending_req, seg, pages))
+	if (xen_blkbk_map_seg(pending_req))
 		goto fail_flush;
 
 	/*
@@ -960,11 +1243,12 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 	for (i = 0; i < nseg; i++) {
 		while ((bio == NULL) ||
 		       (bio_add_page(bio,
-				     pages[i],
+				     pages[i]->page,
 				     seg[i].nsec << 9,
 				     seg[i].offset) == 0)) {
 
-			bio = bio_alloc(GFP_KERNEL, nseg-i);
+			int nr_iovecs = min_t(int, (nseg-i), BIO_MAX_PAGES);
+			bio = bio_alloc(GFP_KERNEL, nr_iovecs);
 			if (unlikely(bio == NULL))
 				goto fail_put_bio;
 
@@ -1009,11 +1293,12 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 	return 0;
 
  fail_flush:
-	xen_blkbk_unmap(pending_req);
+	xen_blkbk_unmap(blkif, pending_req->segments,
+	                pending_req->nr_pages);
  fail_response:
 	/* Haven't submitted any bio's yet. */
-	make_response(blkif, req->u.rw.id, req->operation, BLKIF_RSP_ERROR);
-	free_req(pending_req);
+	make_response(blkif, req->u.rw.id, req_operation, BLKIF_RSP_ERROR);
+	free_req(blkif, pending_req);
 	msleep(1); /* back off a bit */
 	return -EIO;
 
@@ -1070,73 +1355,20 @@ static void make_response(struct xen_blkif *blkif, u64 id,
 
 static int __init xen_blkif_init(void)
 {
-	int i, mmap_pages;
 	int rc = 0;
 
 	if (!xen_domain())
 		return -ENODEV;
 
-	blkbk = kzalloc(sizeof(struct xen_blkbk), GFP_KERNEL);
-	if (!blkbk) {
-		pr_alert(DRV_PFX "%s: out of memory!\n", __func__);
-		return -ENOMEM;
-	}
-
-	mmap_pages = xen_blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST;
-
-	blkbk->pending_reqs          = kzalloc(sizeof(blkbk->pending_reqs[0]) *
-					xen_blkif_reqs, GFP_KERNEL);
-	blkbk->pending_grant_handles = kmalloc(sizeof(blkbk->pending_grant_handles[0]) *
-					mmap_pages, GFP_KERNEL);
-	blkbk->pending_pages         = kzalloc(sizeof(blkbk->pending_pages[0]) *
-					mmap_pages, GFP_KERNEL);
-
-	if (!blkbk->pending_reqs || !blkbk->pending_grant_handles ||
-	    !blkbk->pending_pages) {
-		rc = -ENOMEM;
-		goto out_of_memory;
-	}
-
-	for (i = 0; i < mmap_pages; i++) {
-		blkbk->pending_grant_handles[i] = BLKBACK_INVALID_HANDLE;
-		blkbk->pending_pages[i] = alloc_page(GFP_KERNEL);
-		if (blkbk->pending_pages[i] == NULL) {
-			rc = -ENOMEM;
-			goto out_of_memory;
-		}
-	}
 	rc = xen_blkif_interface_init();
 	if (rc)
 		goto failed_init;
 
-	INIT_LIST_HEAD(&blkbk->pending_free);
-	spin_lock_init(&blkbk->pending_free_lock);
-	init_waitqueue_head(&blkbk->pending_free_wq);
-
-	for (i = 0; i < xen_blkif_reqs; i++)
-		list_add_tail(&blkbk->pending_reqs[i].free_list,
-			      &blkbk->pending_free);
-
 	rc = xen_blkif_xenbus_init();
 	if (rc)
 		goto failed_init;
 
-	return 0;
-
- out_of_memory:
-	pr_alert(DRV_PFX "%s: out of memory\n", __func__);
  failed_init:
-	kfree(blkbk->pending_reqs);
-	kfree(blkbk->pending_grant_handles);
-	if (blkbk->pending_pages) {
-		for (i = 0; i < mmap_pages; i++) {
-			if (blkbk->pending_pages[i])
-				__free_page(blkbk->pending_pages[i]);
-		}
-		kfree(blkbk->pending_pages);
-	}
-	kfree(blkbk);
-	blkbk = NULL;
 	return rc;
 }
 
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 60103e2517ba..8d8807563d99 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -50,6 +50,19 @@
 		 __func__, __LINE__, ##args)
 
 
+/*
+ * This is the maximum number of segments that would be allowed in indirect
+ * requests. This value will also be passed to the frontend.
+ */
+#define MAX_INDIRECT_SEGMENTS 256
+
+#define SEGS_PER_INDIRECT_FRAME \
+	(PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+#define MAX_INDIRECT_PAGES \
+	((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+#define INDIRECT_PAGES(_segs) \
+	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+
 /* Not a real protocol.  Used to generate ring structs which contain
  * the elements common to all protocols only.  This way we get a
  * compiler-checkable way to use common struct elements, so we can
@@ -83,12 +96,31 @@ struct blkif_x86_32_request_other {
 	uint64_t       id;           /* private guest value, echoed in resp  */
 } __attribute__((__packed__));
 
+struct blkif_x86_32_request_indirect {
+	uint8_t        indirect_op;
+	uint16_t       nr_segments;
+	uint64_t       id;
+	blkif_sector_t sector_number;
+	blkif_vdev_t   handle;
+	uint16_t       _pad1;
+	grant_ref_t    indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST];
+	/*
+	 * The maximum number of indirect segments (and pages) that will
+	 * be used is determined by MAX_INDIRECT_SEGMENTS, this value
+	 * is also exported to the guest (via xenstore
+	 * feature-max-indirect-segments entry), so the frontend knows how
+	 * many indirect segments the backend supports.
+	 */
+	uint64_t       _pad2;        /* make it 64 byte aligned */
+} __attribute__((__packed__));
+
 struct blkif_x86_32_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_x86_32_request_rw rw;
 		struct blkif_x86_32_request_discard discard;
 		struct blkif_x86_32_request_other other;
+		struct blkif_x86_32_request_indirect indirect;
 	} u;
 } __attribute__((__packed__));
 
@@ -127,12 +159,32 @@ struct blkif_x86_64_request_other {
 	uint64_t       id;           /* private guest value, echoed in resp  */
 } __attribute__((__packed__));
 
+struct blkif_x86_64_request_indirect {
+	uint8_t        indirect_op;
+	uint16_t       nr_segments;
+	uint32_t       _pad1;        /* offsetof(blkif_..,u.indirect.id)==8   */
+	uint64_t       id;
+	blkif_sector_t sector_number;
+	blkif_vdev_t   handle;
+	uint16_t       _pad2;
+	grant_ref_t    indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST];
+	/*
+	 * The maximum number of indirect segments (and pages) that will
+	 * be used is determined by MAX_INDIRECT_SEGMENTS, this value
+	 * is also exported to the guest (via xenstore
+	 * feature-max-indirect-segments entry), so the frontend knows how
+	 * many indirect segments the backend supports.
+	 */
+	uint32_t       _pad3;        /* make it 64 byte aligned */
+} __attribute__((__packed__));
+
 struct blkif_x86_64_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_x86_64_request_rw rw;
 		struct blkif_x86_64_request_discard discard;
 		struct blkif_x86_64_request_other other;
+		struct blkif_x86_64_request_indirect indirect;
 	} u;
 } __attribute__((__packed__));
 
@@ -182,12 +234,26 @@ struct xen_vbd {
 
 struct backend_info;
 
+/* Number of available flags */
+#define PERSISTENT_GNT_FLAGS_SIZE	2
+/* This persistent grant is currently in use */
+#define PERSISTENT_GNT_ACTIVE		0
+/*
+ * This persistent grant has been used, this flag is set when we remove the
+ * PERSISTENT_GNT_ACTIVE, to know that this grant has been used recently.
+ */
+#define PERSISTENT_GNT_WAS_ACTIVE	1
+
+/* Number of requests that we can fit in a ring */
+#define XEN_BLKIF_REQS			32
 
 struct persistent_gnt {
 	struct page *page;
 	grant_ref_t gnt;
 	grant_handle_t handle;
+	DECLARE_BITMAP(flags, PERSISTENT_GNT_FLAGS_SIZE);
 	struct rb_node node;
+	struct list_head remove_node;
 };
 
 struct xen_blkif {
@@ -219,6 +285,23 @@ struct xen_blkif {
 	/* tree to store persistent grants */
 	struct rb_root		persistent_gnts;
 	unsigned int		persistent_gnt_c;
+	atomic_t		persistent_gnt_in_use;
+	unsigned long           next_lru;
+
+	/* used by the kworker that offload work from the persistent purge */
+	struct list_head	persistent_purge_list;
+	struct work_struct	persistent_purge_work;
+
+	/* buffer of free pages to map grant refs */
+	spinlock_t		free_pages_lock;
+	int			free_pages_num;
+	struct list_head	free_pages;
+
+	/* List of all 'pending_req' available */
+	struct list_head	pending_free;
+	/* And its spinlock. */
+	spinlock_t		pending_free_lock;
+	wait_queue_head_t	pending_free_wq;
 
 	/* statistics */
 	unsigned long		st_print;
@@ -231,6 +314,41 @@ struct xen_blkif {
 	unsigned long long			st_wr_sect;
 
 	wait_queue_head_t	waiting_to_free;
+	/* Thread shutdown wait queue. */
+	wait_queue_head_t	shutdown_wq;
+};
+
+struct seg_buf {
+	unsigned long offset;
+	unsigned int nsec;
+};
+
+struct grant_page {
+	struct page 		*page;
+	struct persistent_gnt	*persistent_gnt;
+	grant_handle_t		handle;
+	grant_ref_t		gref;
+};
+
+/*
+ * Each outstanding request that we've passed to the lower device layers has a
+ * 'pending_req' allocated to it. Each buffer_head that completes decrements
+ * the pendcnt towards zero. When it hits zero, the specified domain has a
+ * response queued for it, with the saved 'id' passed back.
+ */
+struct pending_req {
+	struct xen_blkif	*blkif;
+	u64			id;
+	int			nr_pages;
+	atomic_t		pendcnt;
+	unsigned short		operation;
+	int			status;
+	struct list_head	free_list;
+	struct grant_page	*segments[MAX_INDIRECT_SEGMENTS];
+	/* Indirect descriptors */
+	struct grant_page	*indirect_pages[MAX_INDIRECT_PAGES];
+	struct seg_buf		seg[MAX_INDIRECT_SEGMENTS];
+	struct bio		*biolist[MAX_INDIRECT_SEGMENTS];
 };
 
 
@@ -257,6 +375,7 @@ int xen_blkif_xenbus_init(void);
 
 irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
 int xen_blkif_schedule(void *arg);
+int xen_blkif_purge_persistent(void *arg);
 
 int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
 			      struct backend_info *be, int state);
@@ -268,7 +387,7 @@ struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
 static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 					struct blkif_x86_32_request *src)
 {
-	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j;
 	dst->operation = src->operation;
 	switch (src->operation) {
 	case BLKIF_OP_READ:
@@ -291,6 +410,18 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 		dst->u.discard.sector_number = src->u.discard.sector_number;
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;
+	case BLKIF_OP_INDIRECT:
+		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
+		dst->u.indirect.nr_segments = src->u.indirect.nr_segments;
+		dst->u.indirect.handle = src->u.indirect.handle;
+		dst->u.indirect.id = src->u.indirect.id;
+		dst->u.indirect.sector_number = src->u.indirect.sector_number;
+		barrier();
+		j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments));
+		for (i = 0; i < j; i++)
+			dst->u.indirect.indirect_grefs[i] =
+				src->u.indirect.indirect_grefs[i];
+		break;
 	default:
 		/*
 		 * Don't know how to translate this op. Only get the
@@ -304,7 +435,7 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 static inline void blkif_get_x86_64_req(struct blkif_request *dst,
 					struct blkif_x86_64_request *src)
 {
-	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j;
 	dst->operation = src->operation;
 	switch (src->operation) {
 	case BLKIF_OP_READ:
@@ -327,6 +458,18 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst,
 		dst->u.discard.sector_number = src->u.discard.sector_number;
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;
+	case BLKIF_OP_INDIRECT:
+		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
+		dst->u.indirect.nr_segments = src->u.indirect.nr_segments;
+		dst->u.indirect.handle = src->u.indirect.handle;
+		dst->u.indirect.id = src->u.indirect.id;
+		dst->u.indirect.sector_number = src->u.indirect.sector_number;
+		barrier();
+		j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments));
+		for (i = 0; i < j; i++)
+			dst->u.indirect.indirect_grefs[i] =
+				src->u.indirect.indirect_grefs[i];
+		break;
 	default:
 		/*
 		 * Don't know how to translate this op. Only get the
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 04608a6502d7..fe5c3cd10c34 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -98,12 +98,17 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
 		err = PTR_ERR(blkif->xenblkd);
 		blkif->xenblkd = NULL;
 		xenbus_dev_error(blkif->be->dev, err, "start xenblkd");
+		return;
 	}
 }
 
 static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 {
 	struct xen_blkif *blkif;
+	struct pending_req *req, *n;
+	int i, j;
+
+	BUILD_BUG_ON(MAX_INDIRECT_PAGES > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST);
 
 	blkif = kmem_cache_zalloc(xen_blkif_cachep, GFP_KERNEL);
 	if (!blkif)
@@ -118,8 +123,57 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 	blkif->st_print = jiffies;
 	init_waitqueue_head(&blkif->waiting_to_free);
 	blkif->persistent_gnts.rb_node = NULL;
+	spin_lock_init(&blkif->free_pages_lock);
+	INIT_LIST_HEAD(&blkif->free_pages);
+	blkif->free_pages_num = 0;
+	atomic_set(&blkif->persistent_gnt_in_use, 0);
+
+	INIT_LIST_HEAD(&blkif->pending_free);
+
+	for (i = 0; i < XEN_BLKIF_REQS; i++) {
+		req = kzalloc(sizeof(*req), GFP_KERNEL);
+		if (!req)
+			goto fail;
+		list_add_tail(&req->free_list,
+		              &blkif->pending_free);
+		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+			req->segments[j] = kzalloc(sizeof(*req->segments[0]),
+			                           GFP_KERNEL);
+			if (!req->segments[j])
+				goto fail;
+		}
+		for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+			req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]),
+			                                 GFP_KERNEL);
+			if (!req->indirect_pages[j])
+				goto fail;
+		}
+	}
+	spin_lock_init(&blkif->pending_free_lock);
+	init_waitqueue_head(&blkif->pending_free_wq);
+	init_waitqueue_head(&blkif->shutdown_wq);
 
 	return blkif;
+
+fail:
+	list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
+		list_del(&req->free_list);
+		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+			if (!req->segments[j])
+				break;
+			kfree(req->segments[j]);
+		}
+		for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+			if (!req->indirect_pages[j])
+				break;
+			kfree(req->indirect_pages[j]);
+		}
+		kfree(req);
+	}
+
+	kmem_cache_free(xen_blkif_cachep, blkif);
+
+	return ERR_PTR(-ENOMEM);
 }
 
 static int xen_blkif_map(struct xen_blkif *blkif, unsigned long shared_page,
@@ -178,6 +232,7 @@ static void xen_blkif_disconnect(struct xen_blkif *blkif)
 {
 	if (blkif->xenblkd) {
 		kthread_stop(blkif->xenblkd);
+		wake_up(&blkif->shutdown_wq);
 		blkif->xenblkd = NULL;
 	}
 
@@ -198,8 +253,28 @@ static void xen_blkif_disconnect(struct xen_blkif *blkif)
 
 static void xen_blkif_free(struct xen_blkif *blkif)
 {
+	struct pending_req *req, *n;
+	int i = 0, j;
+
 	if (!atomic_dec_and_test(&blkif->refcnt))
 		BUG();
+
+	/* Check that there is no request in use */
+	list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
+		list_del(&req->free_list);
+
+		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
+			kfree(req->segments[j]);
+
+		for (j = 0; j < MAX_INDIRECT_PAGES; j++)
+			kfree(req->indirect_pages[j]);
+
+		kfree(req);
+		i++;
+	}
+
+	WARN_ON(i != XEN_BLKIF_REQS);
+
 	kmem_cache_free(xen_blkif_cachep, blkif);
 }
 
@@ -678,6 +753,11 @@ again:
 				 dev->nodename);
 		goto abort;
 	}
+	err = xenbus_printf(xbt, dev->nodename, "feature-max-indirect-segments", "%u",
+			    MAX_INDIRECT_SEGMENTS);
+	if (err)
+		dev_warn(&dev->dev, "writing %s/feature-max-indirect-segments (%d)",
+			 dev->nodename, err);
 
 	err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu",
 			    (unsigned long long)vbd_sz(&be->blkif->vbd));
@@ -704,6 +784,11 @@ again:
 				 dev->nodename);
 		goto abort;
 	}
+	err = xenbus_printf(xbt, dev->nodename, "physical-sector-size", "%u",
+			    bdev_physical_block_size(be->blkif->vbd.bdev));
+	if (err)
+		xenbus_dev_error(dev, err, "writing %s/physical-sector-size",
+				 dev->nodename);
 
 	err = xenbus_transaction_end(xbt, 0);
 	if (err == -EAGAIN)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d89ef86220f4..a4660bbee8a6 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -74,12 +74,30 @@ struct grant {
 struct blk_shadow {
 	struct blkif_request req;
 	struct request *request;
-	struct grant *grants_used[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct grant **grants_used;
+	struct grant **indirect_grants;
+	struct scatterlist *sg;
+};
+
+struct split_bio {
+	struct bio *bio;
+	atomic_t pending;
+	int err;
 };
 
 static DEFINE_MUTEX(blkfront_mutex);
 static const struct block_device_operations xlvbd_block_fops;
 
+/*
+ * Maximum number of segments in indirect requests, the actual value used by
+ * the frontend driver is the minimum of this value and the value provided
+ * by the backend driver.
+ */
+
+static unsigned int xen_blkif_max_segments = 32;
+module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
+MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests (default is 32)");
+
 #define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE)
 
 /*
@@ -98,7 +116,6 @@ struct blkfront_info
 	enum blkif_state connected;
 	int ring_ref;
 	struct blkif_front_ring ring;
-	struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	unsigned int evtchn, irq;
 	struct request_queue *rq;
 	struct work_struct work;
@@ -114,6 +131,7 @@ struct blkfront_info
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
 	unsigned int feature_persistent:1;
+	unsigned int max_indirect_segments;
 	int is_ready;
 };
 
@@ -142,6 +160,13 @@ static DEFINE_SPINLOCK(minor_lock);
 
 #define DEV_NAME	"xvd"	/* name in /dev */
 
+#define SEGS_PER_INDIRECT_FRAME \
+	(PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+#define INDIRECT_GREFS(_segs) \
+	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+
+static int blkfront_setup_indirect(struct blkfront_info *info);
+
 static int get_id_from_freelist(struct blkfront_info *info)
 {
 	unsigned long free = info->shadow_free;
@@ -358,7 +383,8 @@ static int blkif_queue_request(struct request *req)
 	struct blkif_request *ring_req;
 	unsigned long id;
 	unsigned int fsect, lsect;
-	int i, ref;
+	int i, ref, n;
+	struct blkif_request_segment_aligned *segments = NULL;
 
 	/*
 	 * Used to store if we are able to queue the request by just using
@@ -369,21 +395,27 @@ static int blkif_queue_request(struct request *req)
 	grant_ref_t gref_head;
 	struct grant *gnt_list_entry = NULL;
 	struct scatterlist *sg;
+	int nseg, max_grefs;
 
 	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
 		return 1;
 
-	/* Check if we have enought grants to allocate a requests */
-	if (info->persistent_gnts_c < BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+	max_grefs = info->max_indirect_segments ?
+		    info->max_indirect_segments +
+		    INDIRECT_GREFS(info->max_indirect_segments) :
+		    BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+	/* Check if we have enough grants to allocate a requests */
+	if (info->persistent_gnts_c < max_grefs) {
 		new_persistent_gnts = 1;
 		if (gnttab_alloc_grant_references(
-		    BLKIF_MAX_SEGMENTS_PER_REQUEST - info->persistent_gnts_c,
+		    max_grefs - info->persistent_gnts_c,
 		    &gref_head) < 0) {
 			gnttab_request_free_callback(
 				&info->callback,
 				blkif_restart_queue_callback,
 				info,
-				BLKIF_MAX_SEGMENTS_PER_REQUEST);
+				max_grefs);
 			return 1;
 		}
 	} else
@@ -394,42 +426,67 @@ static int blkif_queue_request(struct request *req)
 	id = get_id_from_freelist(info);
 	info->shadow[id].request = req;
 
-	ring_req->u.rw.id = id;
-	ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
-	ring_req->u.rw.handle = info->handle;
-
-	ring_req->operation = rq_data_dir(req) ?
-		BLKIF_OP_WRITE : BLKIF_OP_READ;
-
-	if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
-		/*
-		 * Ideally we can do an unordered flush-to-disk. In case the
-		 * backend onlysupports barriers, use that. A barrier request
-		 * a superset of FUA, so we can implement it the same
-		 * way.  (It's also a FLUSH+FUA, since it is
-		 * guaranteed ordered WRT previous writes.)
-		 */
-		ring_req->operation = info->flush_op;
-	}
-
 	if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
-		/* id, sector_number and handle are set above. */
 		ring_req->operation = BLKIF_OP_DISCARD;
 		ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+		ring_req->u.discard.id = id;
+		ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
 		if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
 			ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
 		else
 			ring_req->u.discard.flag = 0;
 	} else {
-		ring_req->u.rw.nr_segments = blk_rq_map_sg(req->q, req,
-							   info->sg);
-		BUG_ON(ring_req->u.rw.nr_segments >
-		       BLKIF_MAX_SEGMENTS_PER_REQUEST);
-
-		for_each_sg(info->sg, sg, ring_req->u.rw.nr_segments, i) {
+		BUG_ON(info->max_indirect_segments == 0 &&
+		       req->nr_phys_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
+		BUG_ON(info->max_indirect_segments &&
+		       req->nr_phys_segments > info->max_indirect_segments);
+		nseg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
+		ring_req->u.rw.id = id;
+		if (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+			/*
+			 * The indirect operation can only be a BLKIF_OP_READ or
+			 * BLKIF_OP_WRITE
+			 */
+			BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+			ring_req->operation = BLKIF_OP_INDIRECT;
+			ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
+				BLKIF_OP_WRITE : BLKIF_OP_READ;
+			ring_req->u.indirect.sector_number = (blkif_sector_t)blk_rq_pos(req);
+			ring_req->u.indirect.handle = info->handle;
+			ring_req->u.indirect.nr_segments = nseg;
+		} else {
+			ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
+			ring_req->u.rw.handle = info->handle;
+			ring_req->operation = rq_data_dir(req) ?
+				BLKIF_OP_WRITE : BLKIF_OP_READ;
+			if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+				/*
+				 * Ideally we can do an unordered flush-to-disk. In case the
+				 * backend onlysupports barriers, use that. A barrier request
+				 * a superset of FUA, so we can implement it the same
+				 * way.  (It's also a FLUSH+FUA, since it is
+				 * guaranteed ordered WRT previous writes.)
+				 */
+				ring_req->operation = info->flush_op;
+			}
+			ring_req->u.rw.nr_segments = nseg;
+		}
+		for_each_sg(info->shadow[id].sg, sg, nseg, i) {
 			fsect = sg->offset >> 9;
 			lsect = fsect + (sg->length >> 9) - 1;
 
+			if ((ring_req->operation == BLKIF_OP_INDIRECT) &&
+			    (i % SEGS_PER_INDIRECT_FRAME == 0)) {
+				if (segments)
+					kunmap_atomic(segments);
+
+				n = i / SEGS_PER_INDIRECT_FRAME;
+				gnt_list_entry = get_grant(&gref_head, info);
+				info->shadow[id].indirect_grants[n] = gnt_list_entry;
+				segments = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
+				ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
+			}
+
 			gnt_list_entry = get_grant(&gref_head, info);
 			ref = gnt_list_entry->gref;
 
@@ -441,8 +498,7 @@ static int blkif_queue_request(struct request *req)
 
 				BUG_ON(sg->offset + sg->length > PAGE_SIZE);
 
-				shared_data = kmap_atomic(
-					pfn_to_page(gnt_list_entry->pfn));
+				shared_data = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
 				bvec_data = kmap_atomic(sg_page(sg));
 
 				/*
@@ -461,13 +517,23 @@ static int blkif_queue_request(struct request *req)
 				kunmap_atomic(bvec_data);
 				kunmap_atomic(shared_data);
 			}
-
-			ring_req->u.rw.seg[i] =
-					(struct blkif_request_segment) {
-						.gref       = ref,
-						.first_sect = fsect,
-						.last_sect  = lsect };
+			if (ring_req->operation != BLKIF_OP_INDIRECT) {
+				ring_req->u.rw.seg[i] =
+						(struct blkif_request_segment) {
+							.gref       = ref,
+							.first_sect = fsect,
+							.last_sect  = lsect };
+			} else {
+				n = i % SEGS_PER_INDIRECT_FRAME;
+				segments[n] =
+					(struct blkif_request_segment_aligned) {
+							.gref       = ref,
+							.first_sect = fsect,
+							.last_sect  = lsect };
+			}
 		}
+		if (segments)
+			kunmap_atomic(segments);
 	}
 
 	info->ring.req_prod_pvt++;
@@ -542,7 +608,9 @@ wait:
 		flush_requests(info);
 }
 
-static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
+static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
+				unsigned int physical_sector_size,
+				unsigned int segments)
 {
 	struct request_queue *rq;
 	struct blkfront_info *info = gd->private_data;
@@ -564,14 +632,15 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
 	blk_queue_logical_block_size(rq, sector_size);
-	blk_queue_max_hw_sectors(rq, 512);
+	blk_queue_physical_block_size(rq, physical_sector_size);
+	blk_queue_max_hw_sectors(rq, (segments * PAGE_SIZE) / 512);
 
 	/* Each segment in a request is up to an aligned page in size. */
 	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
 	blk_queue_max_segment_size(rq, PAGE_SIZE);
 
 	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+	blk_queue_max_segments(rq, segments);
 
 	/* Make sure buffer addresses are sector-aligned. */
 	blk_queue_dma_alignment(rq, 511);
@@ -588,13 +657,16 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 static void xlvbd_flush(struct blkfront_info *info)
 {
 	blk_queue_flush(info->rq, info->feature_flush);
-	printk(KERN_INFO "blkfront: %s: %s: %s %s\n",
+	printk(KERN_INFO "blkfront: %s: %s: %s %s %s %s %s\n",
 	       info->gd->disk_name,
 	       info->flush_op == BLKIF_OP_WRITE_BARRIER ?
 		"barrier" : (info->flush_op == BLKIF_OP_FLUSH_DISKCACHE ?
 		"flush diskcache" : "barrier or flush"),
-	       info->feature_flush ? "enabled" : "disabled",
-	       info->feature_persistent ? "using persistent grants" : "");
+	       info->feature_flush ? "enabled;" : "disabled;",
+	       "persistent grants:",
+	       info->feature_persistent ? "enabled;" : "disabled;",
+	       "indirect descriptors:",
+	       info->max_indirect_segments ? "enabled;" : "disabled;");
 }
 
 static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
@@ -667,7 +739,8 @@ static char *encode_disk_name(char *ptr, unsigned int n)
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 			       struct blkfront_info *info,
-			       u16 vdisk_info, u16 sector_size)
+			       u16 vdisk_info, u16 sector_size,
+			       unsigned int physical_sector_size)
 {
 	struct gendisk *gd;
 	int nr_minors = 1;
@@ -734,7 +807,9 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	gd->driverfs_dev = &(info->xbdev->dev);
 	set_capacity(gd, capacity);
 
-	if (xlvbd_init_blk_queue(gd, sector_size)) {
+	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
+				 info->max_indirect_segments ? :
+				 BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
 		del_gendisk(gd);
 		goto release;
 	}
@@ -818,6 +893,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 {
 	struct grant *persistent_gnt;
 	struct grant *n;
+	int i, j, segs;
 
 	/* Prevent new requests being issued until we fix things up. */
 	spin_lock_irq(&info->io_lock);
@@ -843,6 +919,47 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 	}
 	BUG_ON(info->persistent_gnts_c != 0);
 
+	for (i = 0; i < BLK_RING_SIZE; i++) {
+		/*
+		 * Clear persistent grants present in requests already
+		 * on the shared ring
+		 */
+		if (!info->shadow[i].request)
+			goto free_shadow;
+
+		segs = info->shadow[i].req.operation == BLKIF_OP_INDIRECT ?
+		       info->shadow[i].req.u.indirect.nr_segments :
+		       info->shadow[i].req.u.rw.nr_segments;
+		for (j = 0; j < segs; j++) {
+			persistent_gnt = info->shadow[i].grants_used[j];
+			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
+			__free_page(pfn_to_page(persistent_gnt->pfn));
+			kfree(persistent_gnt);
+		}
+
+		if (info->shadow[i].req.operation != BLKIF_OP_INDIRECT)
+			/*
+			 * If this is not an indirect operation don't try to
+			 * free indirect segments
+			 */
+			goto free_shadow;
+
+		for (j = 0; j < INDIRECT_GREFS(segs); j++) {
+			persistent_gnt = info->shadow[i].indirect_grants[j];
+			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
+			__free_page(pfn_to_page(persistent_gnt->pfn));
+			kfree(persistent_gnt);
+		}
+
+free_shadow:
+		kfree(info->shadow[i].grants_used);
+		info->shadow[i].grants_used = NULL;
+		kfree(info->shadow[i].indirect_grants);
+		info->shadow[i].indirect_grants = NULL;
+		kfree(info->shadow[i].sg);
+		info->shadow[i].sg = NULL;
+	}
+
 	/* No more gnttab callback work. */
 	gnttab_cancel_free_callback(&info->callback);
 	spin_unlock_irq(&info->io_lock);
@@ -867,12 +984,13 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 			     struct blkif_response *bret)
 {
 	int i = 0;
-	struct bio_vec *bvec;
-	struct req_iterator iter;
-	unsigned long flags;
+	struct scatterlist *sg;
 	char *bvec_data;
 	void *shared_data;
-	unsigned int offset = 0;
+	int nseg;
+
+	nseg = s->req.operation == BLKIF_OP_INDIRECT ?
+		s->req.u.indirect.nr_segments : s->req.u.rw.nr_segments;
 
 	if (bret->operation == BLKIF_OP_READ) {
 		/*
@@ -881,26 +999,29 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 		 * than PAGE_SIZE, we have to keep track of the current offset,
 		 * to be sure we are copying the data from the right shared page.
 		 */
-		rq_for_each_segment(bvec, s->request, iter) {
-			BUG_ON((bvec->bv_offset + bvec->bv_len) > PAGE_SIZE);
-			if (bvec->bv_offset < offset)
-				i++;
-			BUG_ON(i >= s->req.u.rw.nr_segments);
+		for_each_sg(s->sg, sg, nseg, i) {
+			BUG_ON(sg->offset + sg->length > PAGE_SIZE);
 			shared_data = kmap_atomic(
 				pfn_to_page(s->grants_used[i]->pfn));
-			bvec_data = bvec_kmap_irq(bvec, &flags);
-			memcpy(bvec_data, shared_data + bvec->bv_offset,
-				bvec->bv_len);
-			bvec_kunmap_irq(bvec_data, &flags);
+			bvec_data = kmap_atomic(sg_page(sg));
+			memcpy(bvec_data   + sg->offset,
+			       shared_data + sg->offset,
+			       sg->length);
+			kunmap_atomic(bvec_data);
 			kunmap_atomic(shared_data);
-			offset = bvec->bv_offset + bvec->bv_len;
 		}
 	}
 	/* Add the persistent grant into the list of free grants */
-	for (i = 0; i < s->req.u.rw.nr_segments; i++) {
+	for (i = 0; i < nseg; i++) {
 		list_add(&s->grants_used[i]->node, &info->persistent_gnts);
 		info->persistent_gnts_c++;
 	}
+	if (s->req.operation == BLKIF_OP_INDIRECT) {
+		for (i = 0; i < INDIRECT_GREFS(nseg); i++) {
+			list_add(&s->indirect_grants[i]->node, &info->persistent_gnts);
+			info->persistent_gnts_c++;
+		}
+	}
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
@@ -1034,14 +1155,6 @@ static int setup_blkring(struct xenbus_device *dev,
 	SHARED_RING_INIT(sring);
 	FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE);
 
-	sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
-
-	/* Allocate memory for grants */
-	err = fill_grant_buffer(info, BLK_RING_SIZE *
-	                              BLKIF_MAX_SEGMENTS_PER_REQUEST);
-	if (err)
-		goto fail;
-
 	err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring));
 	if (err < 0) {
 		free_page((unsigned long)sring);
@@ -1223,13 +1336,84 @@ static int blkfront_probe(struct xenbus_device *dev,
 	return 0;
 }
 
+/*
+ * This is a clone of md_trim_bio, used to split a bio into smaller ones
+ */
+static void trim_bio(struct bio *bio, int offset, int size)
+{
+	/* 'bio' is a cloned bio which we need to trim to match
+	 * the given offset and size.
+	 * This requires adjusting bi_sector, bi_size, and bi_io_vec
+	 */
+	int i;
+	struct bio_vec *bvec;
+	int sofar = 0;
+
+	size <<= 9;
+	if (offset == 0 && size == bio->bi_size)
+		return;
+
+	bio->bi_sector += offset;
+	bio->bi_size = size;
+	offset <<= 9;
+	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+
+	while (bio->bi_idx < bio->bi_vcnt &&
+	       bio->bi_io_vec[bio->bi_idx].bv_len <= offset) {
+		/* remove this whole bio_vec */
+		offset -= bio->bi_io_vec[bio->bi_idx].bv_len;
+		bio->bi_idx++;
+	}
+	if (bio->bi_idx < bio->bi_vcnt) {
+		bio->bi_io_vec[bio->bi_idx].bv_offset += offset;
+		bio->bi_io_vec[bio->bi_idx].bv_len -= offset;
+	}
+	/* avoid any complications with bi_idx being non-zero*/
+	if (bio->bi_idx) {
+		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
+			(bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
+		bio->bi_vcnt -= bio->bi_idx;
+		bio->bi_idx = 0;
+	}
+	/* Make sure vcnt and last bv are not too big */
+	bio_for_each_segment(bvec, bio, i) {
+		if (sofar + bvec->bv_len > size)
+			bvec->bv_len = size - sofar;
+		if (bvec->bv_len == 0) {
+			bio->bi_vcnt = i;
+			break;
+		}
+		sofar += bvec->bv_len;
+	}
+}
+
+static void split_bio_end(struct bio *bio, int error)
+{
+	struct split_bio *split_bio = bio->bi_private;
+
+	if (error)
+		split_bio->err = error;
+
+	if (atomic_dec_and_test(&split_bio->pending)) {
+		split_bio->bio->bi_phys_segments = 0;
+		bio_endio(split_bio->bio, split_bio->err);
+		kfree(split_bio);
+	}
+	bio_put(bio);
+}
 
 static int blkif_recover(struct blkfront_info *info)
 {
 	int i;
-	struct blkif_request *req;
+	struct request *req, *n;
 	struct blk_shadow *copy;
-	int j;
+	int rc;
+	struct bio *bio, *cloned_bio;
+	struct bio_list bio_list, merge_bio;
+	unsigned int segs, offset;
+	int pending, size;
+	struct split_bio *split_bio;
+	struct list_head requests;
 
 	/* Stage 1: Make a safe copy of the shadow state. */
 	copy = kmemdup(info->shadow, sizeof(info->shadow),
@@ -1244,36 +1428,64 @@ static int blkif_recover(struct blkfront_info *info)
 	info->shadow_free = info->ring.req_prod_pvt;
 	info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
 
-	/* Stage 3: Find pending requests and requeue them. */
+	rc = blkfront_setup_indirect(info);
+	if (rc) {
+		kfree(copy);
+		return rc;
+	}
+
+	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
+	blk_queue_max_segments(info->rq, segs);
+	bio_list_init(&bio_list);
+	INIT_LIST_HEAD(&requests);
 	for (i = 0; i < BLK_RING_SIZE; i++) {
 		/* Not in use? */
 		if (!copy[i].request)
 			continue;
 
-		/* Grab a request slot and copy shadow state into it. */
-		req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
-		*req = copy[i].req;
-
-		/* We get a new request id, and must reset the shadow state. */
-		req->u.rw.id = get_id_from_freelist(info);
-		memcpy(&info->shadow[req->u.rw.id], &copy[i], sizeof(copy[i]));
-
-		if (req->operation != BLKIF_OP_DISCARD) {
-		/* Rewrite any grant references invalidated by susp/resume. */
-			for (j = 0; j < req->u.rw.nr_segments; j++)
-				gnttab_grant_foreign_access_ref(
-					req->u.rw.seg[j].gref,
-					info->xbdev->otherend_id,
-					pfn_to_mfn(copy[i].grants_used[j]->pfn),
-					0);
+		/*
+		 * Get the bios in the request so we can re-queue them.
+		 */
+		if (copy[i].request->cmd_flags &
+		    (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+			/*
+			 * Flush operations don't contain bios, so
+			 * we need to requeue the whole request
+			 */
+			list_add(&copy[i].request->queuelist, &requests);
+			continue;
 		}
-		info->shadow[req->u.rw.id].req = *req;
-
-		info->ring.req_prod_pvt++;
+		merge_bio.head = copy[i].request->bio;
+		merge_bio.tail = copy[i].request->biotail;
+		bio_list_merge(&bio_list, &merge_bio);
+		copy[i].request->bio = NULL;
+		blk_put_request(copy[i].request);
 	}
 
 	kfree(copy);
 
+	/*
+	 * Empty the queue, this is important because we might have
+	 * requests in the queue with more segments than what we
+	 * can handle now.
+	 */
+	spin_lock_irq(&info->io_lock);
+	while ((req = blk_fetch_request(info->rq)) != NULL) {
+		if (req->cmd_flags &
+		    (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+			list_add(&req->queuelist, &requests);
+			continue;
+		}
+		merge_bio.head = req->bio;
+		merge_bio.tail = req->biotail;
+		bio_list_merge(&bio_list, &merge_bio);
+		req->bio = NULL;
+		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
+			pr_alert("diskcache flush request found!\n");
+		__blk_put_request(info->rq, req);
+	}
+	spin_unlock_irq(&info->io_lock);
+
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
 
 	spin_lock_irq(&info->io_lock);
@@ -1281,14 +1493,50 @@ static int blkif_recover(struct blkfront_info *info)
 	/* Now safe for us to use the shared ring */
 	info->connected = BLKIF_STATE_CONNECTED;
 
-	/* Send off requeued requests */
-	flush_requests(info);
-
 	/* Kick any other new requests queued since we resumed */
 	kick_pending_request_queues(info);
 
+	list_for_each_entry_safe(req, n, &requests, queuelist) {
+		/* Requeue pending requests (flush or discard) */
+		list_del_init(&req->queuelist);
+		BUG_ON(req->nr_phys_segments > segs);
+		blk_requeue_request(info->rq, req);
+	}
 	spin_unlock_irq(&info->io_lock);
 
+	while ((bio = bio_list_pop(&bio_list)) != NULL) {
+		/* Traverse the list of pending bios and re-queue them */
+		if (bio_segments(bio) > segs) {
+			/*
+			 * This bio has more segments than what we can
+			 * handle, we have to split it.
+			 */
+			pending = (bio_segments(bio) + segs - 1) / segs;
+			split_bio = kzalloc(sizeof(*split_bio), GFP_NOIO);
+			BUG_ON(split_bio == NULL);
+			atomic_set(&split_bio->pending, pending);
+			split_bio->bio = bio;
+			for (i = 0; i < pending; i++) {
+				offset = (i * segs * PAGE_SIZE) >> 9;
+				size = min((unsigned int)(segs * PAGE_SIZE) >> 9,
+					   (unsigned int)(bio->bi_size >> 9) - offset);
+				cloned_bio = bio_clone(bio, GFP_NOIO);
+				BUG_ON(cloned_bio == NULL);
+				trim_bio(cloned_bio, offset, size);
+				cloned_bio->bi_private = split_bio;
+				cloned_bio->bi_end_io = split_bio_end;
+				submit_bio(cloned_bio->bi_rw, cloned_bio);
+			}
+			/*
+			 * Now we have to wait for all those smaller bios to
+			 * end, so we can also end the "parent" bio.
+			 */
+			continue;
+		}
+		/* We don't need to split this bio */
+		submit_bio(bio->bi_rw, bio);
+	}
+
 	return 0;
 }
 
@@ -1308,8 +1556,12 @@ static int blkfront_resume(struct xenbus_device *dev)
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
 	err = talk_to_blkback(dev, info);
-	if (info->connected == BLKIF_STATE_SUSPENDED && !err)
-		err = blkif_recover(info);
+
+	/*
+	 * We have to wait for the backend to switch to
+	 * connected state, since we want to read which
+	 * features it supports.
+	 */
 
 	return err;
 }
@@ -1387,6 +1639,60 @@ static void blkfront_setup_discard(struct blkfront_info *info)
 	kfree(type);
 }
 
+static int blkfront_setup_indirect(struct blkfront_info *info)
+{
+	unsigned int indirect_segments, segs;
+	int err, i;
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			    "feature-max-indirect-segments", "%u", &indirect_segments,
+			    NULL);
+	if (err) {
+		info->max_indirect_segments = 0;
+		segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+	} else {
+		info->max_indirect_segments = min(indirect_segments,
+						  xen_blkif_max_segments);
+		segs = info->max_indirect_segments;
+	}
+
+	err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE);
+	if (err)
+		goto out_of_memory;
+
+	for (i = 0; i < BLK_RING_SIZE; i++) {
+		info->shadow[i].grants_used = kzalloc(
+			sizeof(info->shadow[i].grants_used[0]) * segs,
+			GFP_NOIO);
+		info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * segs, GFP_NOIO);
+		if (info->max_indirect_segments)
+			info->shadow[i].indirect_grants = kzalloc(
+				sizeof(info->shadow[i].indirect_grants[0]) *
+				INDIRECT_GREFS(segs),
+				GFP_NOIO);
+		if ((info->shadow[i].grants_used == NULL) ||
+			(info->shadow[i].sg == NULL) ||
+		     (info->max_indirect_segments &&
+		     (info->shadow[i].indirect_grants == NULL)))
+			goto out_of_memory;
+		sg_init_table(info->shadow[i].sg, segs);
+	}
+
+
+	return 0;
+
+out_of_memory:
+	for (i = 0; i < BLK_RING_SIZE; i++) {
+		kfree(info->shadow[i].grants_used);
+		info->shadow[i].grants_used = NULL;
+		kfree(info->shadow[i].sg);
+		info->shadow[i].sg = NULL;
+		kfree(info->shadow[i].indirect_grants);
+		info->shadow[i].indirect_grants = NULL;
+	}
+	return -ENOMEM;
+}
+
 /*
  * Invoked when the backend is finally 'ready' (and has told produced
  * the details about the physical device - #sectors, size, etc).
@@ -1395,6 +1701,7 @@ static void blkfront_connect(struct blkfront_info *info)
 {
 	unsigned long long sectors;
 	unsigned long sector_size;
+	unsigned int physical_sector_size;
 	unsigned int binfo;
 	int err;
 	int barrier, flush, discard, persistent;
@@ -1414,8 +1721,15 @@ static void blkfront_connect(struct blkfront_info *info)
 		set_capacity(info->gd, sectors);
 		revalidate_disk(info->gd);
 
-		/* fall through */
+		return;
 	case BLKIF_STATE_SUSPENDED:
+		/*
+		 * If we are recovering from suspension, we need to wait
+		 * for the backend to announce it's features before
+		 * reconnecting, at least we need to know if the backend
+		 * supports indirect descriptors, and how many.
+		 */
+		blkif_recover(info);
 		return;
 
 	default:
@@ -1437,6 +1751,16 @@ static void blkfront_connect(struct blkfront_info *info)
 		return;
 	}
 
+	/*
+	 * physcial-sector-size is a newer field, so old backends may not
+	 * provide this. Assume physical sector size to be the same as
+	 * sector_size in that case.
+	 */
+	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+			   "physical-sector-size", "%u", &physical_sector_size);
+	if (err != 1)
+		physical_sector_size = sector_size;
+
 	info->feature_flush = 0;
 	info->flush_op = 0;
 
@@ -1483,7 +1807,15 @@ static void blkfront_connect(struct blkfront_info *info)
 	else
 		info->feature_persistent = persistent;
 
-	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
+	err = blkfront_setup_indirect(info);
+	if (err) {
+		xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
+				 info->xbdev->otherend);
+		return;
+	}
+
+	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size,
+				  physical_sector_size);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
 				 info->xbdev->otherend);
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index 11f467c00d0a..a12b923bbaca 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -91,6 +91,10 @@ static struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x0489, 0xe04e) },
 	{ USB_DEVICE(0x0489, 0xe056) },
 	{ USB_DEVICE(0x0489, 0xe04d) },
+	{ USB_DEVICE(0x04c5, 0x1330) },
+	{ USB_DEVICE(0x13d3, 0x3402) },
+	{ USB_DEVICE(0x0cf3, 0x3121) },
+	{ USB_DEVICE(0x0cf3, 0xe003) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE02C) },
@@ -128,6 +132,10 @@ static struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0x3121), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 },
@@ -193,24 +201,44 @@ error:
 
 static int ath3k_get_state(struct usb_device *udev, unsigned char *state)
 {
-	int pipe = 0;
+	int ret, pipe = 0;
+	char *buf;
+
+	buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
 	pipe = usb_rcvctrlpipe(udev, 0);
-	return usb_control_msg(udev, pipe, ATH3K_GETSTATE,
-			USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,
-			state, 0x01, USB_CTRL_SET_TIMEOUT);
+	ret = usb_control_msg(udev, pipe, ATH3K_GETSTATE,
+			      USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,
+			      buf, sizeof(*buf), USB_CTRL_SET_TIMEOUT);
+
+	*state = *buf;
+	kfree(buf);
+
+	return ret;
 }
 
 static int ath3k_get_version(struct usb_device *udev,
 			struct ath3k_version *version)
 {
-	int pipe = 0;
+	int ret, pipe = 0;
+	struct ath3k_version *buf;
+	const int size = sizeof(*buf);
+
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
 	pipe = usb_rcvctrlpipe(udev, 0);
-	return usb_control_msg(udev, pipe, ATH3K_GETVERSION,
-			USB_TYPE_VENDOR | USB_DIR_IN, 0, 0, version,
-			sizeof(struct ath3k_version),
-			USB_CTRL_SET_TIMEOUT);
+	ret = usb_control_msg(udev, pipe, ATH3K_GETVERSION,
+			      USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,
+			      buf, size, USB_CTRL_SET_TIMEOUT);
+
+	memcpy(version, buf, size);
+	kfree(buf);
+
+	return ret;
 }
 
 static int ath3k_load_fwfile(struct usb_device *udev,
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index de4cf4daa2f4..8e16f0af6358 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -154,6 +154,10 @@ static struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0x3121), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },
@@ -1095,7 +1099,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	if (IS_ERR(skb)) {
 		BT_ERR("%s sending Intel patch command (0x%4.4x) failed (%ld)",
 		       hdev->name, cmd->opcode, PTR_ERR(skb));
-		return -PTR_ERR(skb);
+		return PTR_ERR(skb);
 	}
 
 	/* It ensures that the returned event matches the event data read from
@@ -1147,7 +1151,7 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	if (IS_ERR(skb)) {
 		BT_ERR("%s sending initial HCI reset command failed (%ld)",
 		       hdev->name, PTR_ERR(skb));
-		return -PTR_ERR(skb);
+		return PTR_ERR(skb);
 	}
 	kfree_skb(skb);
 
@@ -1161,7 +1165,7 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	if (IS_ERR(skb)) {
 		BT_ERR("%s reading Intel fw version command failed (%ld)",
 		       hdev->name, PTR_ERR(skb));
-		return -PTR_ERR(skb);
+		return PTR_ERR(skb);
 	}
 
 	if (skb->len != sizeof(*ver)) {
@@ -1219,7 +1223,7 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 		BT_ERR("%s entering Intel manufacturer mode failed (%ld)",
 		       hdev->name, PTR_ERR(skb));
 		release_firmware(fw);
-		return -PTR_ERR(skb);
+		return PTR_ERR(skb);
 	}
 
 	if (skb->data[0]) {
@@ -1276,7 +1280,7 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	if (IS_ERR(skb)) {
 		BT_ERR("%s exiting Intel manufacturer mode failed (%ld)",
 		       hdev->name, PTR_ERR(skb));
-		return -PTR_ERR(skb);
+		return PTR_ERR(skb);
 	}
 	kfree_skb(skb);
 
@@ -1292,7 +1296,7 @@ exit_mfg_disable:
 	if (IS_ERR(skb)) {
 		BT_ERR("%s exiting Intel manufacturer mode failed (%ld)",
 		       hdev->name, PTR_ERR(skb));
-		return -PTR_ERR(skb);
+		return PTR_ERR(skb);
 	}
 	kfree_skb(skb);
 
@@ -1310,7 +1314,7 @@ exit_mfg_deactivate:
 	if (IS_ERR(skb)) {
 		BT_ERR("%s exiting Intel manufacturer mode failed (%ld)",
 		       hdev->name, PTR_ERR(skb));
-		return -PTR_ERR(skb);
+		return PTR_ERR(skb);
 	}
 	kfree_skb(skb);
 
diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c
index bf5d2477cb77..15f2e7025b78 100644
--- a/drivers/char/agp/parisc-agp.c
+++ b/drivers/char/agp/parisc-agp.c
@@ -129,7 +129,8 @@ parisc_agp_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
 	off_t j, io_pg_start;
 	int io_pg_count;
 
-	if (type != 0 || mem->type != 0) {
+	if (type != mem->type ||
+		agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type)) {
 		return -EINVAL;
 	}
 
@@ -175,7 +176,8 @@ parisc_agp_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
 	struct _parisc_agp_info *info = &parisc_agp_info;
 	int i, io_pg_start, io_pg_count;
 
-	if (type != 0 || mem->type != 0) {
+	if (type != mem->type ||
+		agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type)) {
 		return -EINVAL;
 	}
 
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 1b456fe9b87a..fc45567ad3ac 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -272,9 +272,12 @@ static struct port *find_port_by_devt_in_portdev(struct ports_device *portdev,
 	unsigned long flags;
 
 	spin_lock_irqsave(&portdev->ports_lock, flags);
-	list_for_each_entry(port, &portdev->ports, list)
-		if (port->cdev->dev == dev)
+	list_for_each_entry(port, &portdev->ports, list) {
+		if (port->cdev->dev == dev) {
+			kref_get(&port->kref);
 			goto out;
+		}
+	}
 	port = NULL;
 out:
 	spin_unlock_irqrestore(&portdev->ports_lock, flags);
@@ -746,6 +749,10 @@ static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
 
 	port = filp->private_data;
 
+	/* Port is hot-unplugged. */
+	if (!port->guest_connected)
+		return -ENODEV;
+
 	if (!port_has_data(port)) {
 		/*
 		 * If nothing's connected on the host just return 0 in
@@ -762,7 +769,7 @@ static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
 		if (ret < 0)
 			return ret;
 	}
-	/* Port got hot-unplugged. */
+	/* Port got hot-unplugged while we were waiting above. */
 	if (!port->guest_connected)
 		return -ENODEV;
 	/*
@@ -932,13 +939,25 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 	if (is_rproc_serial(port->out_vq->vdev))
 		return -EINVAL;
 
+	/*
+	 * pipe->nrbufs == 0 means there are no data to transfer,
+	 * so this returns just 0 for no data.
+	 */
+	pipe_lock(pipe);
+	if (!pipe->nrbufs) {
+		ret = 0;
+		goto error_out;
+	}
+
 	ret = wait_port_writable(port, filp->f_flags & O_NONBLOCK);
 	if (ret < 0)
-		return ret;
+		goto error_out;
 
 	buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
-	if (!buf)
-		return -ENOMEM;
+	if (!buf) {
+		ret = -ENOMEM;
+		goto error_out;
+	}
 
 	sgl.n = 0;
 	sgl.len = 0;
@@ -946,12 +965,17 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 	sgl.sg = buf->sg;
 	sg_init_table(sgl.sg, sgl.size);
 	ret = __splice_from_pipe(pipe, &sd, pipe_to_sg);
+	pipe_unlock(pipe);
 	if (likely(ret > 0))
 		ret = __send_to_port(port, buf->sg, sgl.n, sgl.len, buf, true);
 
 	if (unlikely(ret <= 0))
 		free_buf(buf, true);
 	return ret;
+
+error_out:
+	pipe_unlock(pipe);
+	return ret;
 }
 
 static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
@@ -1019,14 +1043,14 @@ static int port_fops_open(struct inode *inode, struct file *filp)
 	struct port *port;
 	int ret;
 
+	/* We get the port with a kref here */
 	port = find_port_by_devt(cdev->dev);
+	if (!port) {
+		/* Port was unplugged before we could proceed */
+		return -ENXIO;
+	}
 	filp->private_data = port;
 
-	/* Prevent against a port getting hot-unplugged at the same time */
-	spin_lock_irq(&port->portdev->ports_lock);
-	kref_get(&port->kref);
-	spin_unlock_irq(&port->portdev->ports_lock);
-
 	/*
 	 * Don't allow opening of console port devices -- that's done
 	 * via /dev/hvc
@@ -1498,14 +1522,6 @@ static void remove_port(struct kref *kref)
 
 	port = container_of(kref, struct port, kref);
 
-	sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
-	device_destroy(pdrvdata.class, port->dev->devt);
-	cdev_del(port->cdev);
-
-	kfree(port->name);
-
-	debugfs_remove(port->debugfs_file);
-
 	kfree(port);
 }
 
@@ -1539,12 +1555,14 @@ static void unplug_port(struct port *port)
 	spin_unlock_irq(&port->portdev->ports_lock);
 
 	if (port->guest_connected) {
+		/* Let the app know the port is going down. */
+		send_sigio_to_port(port);
+
+		/* Do this after sigio is actually sent */
 		port->guest_connected = false;
 		port->host_connected = false;
-		wake_up_interruptible(&port->waitqueue);
 
-		/* Let the app know the port is going down. */
-		send_sigio_to_port(port);
+		wake_up_interruptible(&port->waitqueue);
 	}
 
 	if (is_console_port(port)) {
@@ -1563,6 +1581,14 @@ static void unplug_port(struct port *port)
 	 */
 	port->portdev = NULL;
 
+	sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
+	device_destroy(pdrvdata.class, port->dev->devt);
+	cdev_del(port->cdev);
+
+	kfree(port->name);
+
+	debugfs_remove(port->debugfs_file);
+
 	/*
 	 * Locks around here are not necessary - a port can't be
 	 * opened after we removed the port struct from ports_list
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 1bdb882c845b..4e5739773c33 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -581,11 +581,15 @@ struct samsung_div_clock exynos4x12_div_clks[] __initdata = {
 	DIV(none, "div_spi1_isp", "mout_spi1_isp", E4X12_DIV_ISP, 16, 4),
 	DIV(none, "div_spi1_isp_pre", "div_spi1_isp", E4X12_DIV_ISP, 20, 8),
 	DIV(none, "div_uart_isp", "mout_uart_isp", E4X12_DIV_ISP, 28, 4),
-	DIV(div_isp0, "div_isp0", "aclk200", E4X12_DIV_ISP0, 0, 3),
-	DIV(div_isp1, "div_isp1", "aclk200", E4X12_DIV_ISP0, 4, 3),
+	DIV_F(div_isp0, "div_isp0", "aclk200", E4X12_DIV_ISP0, 0, 3,
+						CLK_GET_RATE_NOCACHE, 0),
+	DIV_F(div_isp1, "div_isp1", "aclk200", E4X12_DIV_ISP0, 4, 3,
+						CLK_GET_RATE_NOCACHE, 0),
 	DIV(none, "div_mpwm", "div_isp1", E4X12_DIV_ISP1, 0, 3),
-	DIV(div_mcuisp0, "div_mcuisp0", "aclk400_mcuisp", E4X12_DIV_ISP1, 4, 3),
-	DIV(div_mcuisp1, "div_mcuisp1", "div_mcuisp0", E4X12_DIV_ISP1, 8, 3),
+	DIV_F(div_mcuisp0, "div_mcuisp0", "aclk400_mcuisp", E4X12_DIV_ISP1,
+						4, 3, CLK_GET_RATE_NOCACHE, 0),
+	DIV_F(div_mcuisp1, "div_mcuisp1", "div_mcuisp0", E4X12_DIV_ISP1,
+						8, 3, CLK_GET_RATE_NOCACHE, 0),
 	DIV(sclk_fimg2d, "sclk_fimg2d", "mout_g2d", DIV_DMC1, 0, 4),
 };
 
@@ -863,57 +867,57 @@ struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 	GATE_DA(i2s0, "samsung-i2s.0", "i2s0", "aclk100",
 			E4X12_GATE_IP_MAUDIO, 3, 0, 0, "iis"),
 	GATE(fimc_isp, "isp", "aclk200", E4X12_GATE_ISP0, 0,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(fimc_drc, "drc", "aclk200", E4X12_GATE_ISP0, 1,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(fimc_fd, "fd", "aclk200", E4X12_GATE_ISP0, 2,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(fimc_lite0, "lite0", "aclk200", E4X12_GATE_ISP0, 3,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(fimc_lite1, "lite1", "aclk200", E4X12_GATE_ISP0, 4,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(mcuisp, "mcuisp", "aclk200", E4X12_GATE_ISP0, 5,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(gicisp, "gicisp", "aclk200", E4X12_GATE_ISP0, 7,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(smmu_isp, "smmu_isp", "aclk200", E4X12_GATE_ISP0, 8,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(smmu_drc, "smmu_drc", "aclk200", E4X12_GATE_ISP0, 9,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(smmu_fd, "smmu_fd", "aclk200", E4X12_GATE_ISP0, 10,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(smmu_lite0, "smmu_lite0", "aclk200", E4X12_GATE_ISP0, 11,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(smmu_lite1, "smmu_lite1", "aclk200", E4X12_GATE_ISP0, 12,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(ppmuispmx, "ppmuispmx", "aclk200", E4X12_GATE_ISP0, 20,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(ppmuispx, "ppmuispx", "aclk200", E4X12_GATE_ISP0, 21,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(mcuctl_isp, "mcuctl_isp", "aclk200", E4X12_GATE_ISP0, 23,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(mpwm_isp, "mpwm_isp", "aclk200", E4X12_GATE_ISP0, 24,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(i2c0_isp, "i2c0_isp", "aclk200", E4X12_GATE_ISP0, 25,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(i2c1_isp, "i2c1_isp", "aclk200", E4X12_GATE_ISP0, 26,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(mtcadc_isp, "mtcadc_isp", "aclk200", E4X12_GATE_ISP0, 27,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(pwm_isp, "pwm_isp", "aclk200", E4X12_GATE_ISP0, 28,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(wdt_isp, "wdt_isp", "aclk200", E4X12_GATE_ISP0, 30,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(uart_isp, "uart_isp", "aclk200", E4X12_GATE_ISP0, 31,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(asyncaxim, "asyncaxim", "aclk200", E4X12_GATE_ISP1, 0,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(smmu_ispcx, "smmu_ispcx", "aclk200", E4X12_GATE_ISP1, 4,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(spi0_isp, "spi0_isp", "aclk200", E4X12_GATE_ISP1, 12,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(spi1_isp, "spi1_isp", "aclk200", E4X12_GATE_ISP1, 13,
-			CLK_IGNORE_UNUSED, 0),
+			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(g2d, "g2d", "aclk200", GATE_IP_DMC, 23, 0, 0),
 };
 
diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c
index 5c205b60a82a..089d3e30e221 100644
--- a/drivers/clk/zynq/clkc.c
+++ b/drivers/clk/zynq/clkc.c
@@ -71,6 +71,7 @@ static DEFINE_SPINLOCK(armpll_lock);
 static DEFINE_SPINLOCK(ddrpll_lock);
 static DEFINE_SPINLOCK(iopll_lock);
 static DEFINE_SPINLOCK(armclk_lock);
+static DEFINE_SPINLOCK(swdtclk_lock);
 static DEFINE_SPINLOCK(ddrclk_lock);
 static DEFINE_SPINLOCK(dciclk_lock);
 static DEFINE_SPINLOCK(gem0clk_lock);
@@ -293,7 +294,7 @@ static void __init zynq_clk_setup(struct device_node *np)
 	}
 	clks[swdt] = clk_register_mux(NULL, clk_output_name[swdt],
 			swdt_ext_clk_mux_parents, 2, CLK_SET_RATE_PARENT,
-			SLCR_SWDT_CLK_SEL, 0, 1, 0, &gem0clk_lock);
+			SLCR_SWDT_CLK_SEL, 0, 1, 0, &swdtclk_lock);
 
 	/* DDR clocks */
 	clk = clk_register_divider(NULL, "ddr2x_div", "ddrpll", 0,
@@ -364,8 +365,9 @@ static void __init zynq_clk_setup(struct device_node *np)
 			CLK_SET_RATE_PARENT, SLCR_GEM0_CLK_CTRL, 20, 6,
 			CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
 			&gem0clk_lock);
-	clk = clk_register_mux(NULL, "gem0_emio_mux", gem0_mux_parents, 2, 0,
-			SLCR_GEM0_CLK_CTRL, 6, 1, 0, &gem0clk_lock);
+	clk = clk_register_mux(NULL, "gem0_emio_mux", gem0_mux_parents, 2,
+			CLK_SET_RATE_PARENT, SLCR_GEM0_CLK_CTRL, 6, 1, 0,
+			&gem0clk_lock);
 	clks[gem0] = clk_register_gate(NULL, clk_output_name[gem0],
 			"gem0_emio_mux", CLK_SET_RATE_PARENT,
 			SLCR_GEM0_CLK_CTRL, 0, 0, &gem0clk_lock);
@@ -386,8 +388,9 @@ static void __init zynq_clk_setup(struct device_node *np)
 			CLK_SET_RATE_PARENT, SLCR_GEM1_CLK_CTRL, 20, 6,
 			CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
 			&gem1clk_lock);
-	clk = clk_register_mux(NULL, "gem1_emio_mux", gem1_mux_parents, 2, 0,
-			SLCR_GEM1_CLK_CTRL, 6, 1, 0, &gem1clk_lock);
+	clk = clk_register_mux(NULL, "gem1_emio_mux", gem1_mux_parents, 2,
+			CLK_SET_RATE_PARENT, SLCR_GEM1_CLK_CTRL, 6, 1, 0,
+			&gem1clk_lock);
 	clks[gem1] = clk_register_gate(NULL, clk_output_name[gem1],
 			"gem1_emio_mux", CLK_SET_RATE_PARENT,
 			SLCR_GEM1_CLK_CTRL, 0, 0, &gem1clk_lock);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index a4ad7339588d..f0a5e2b0eb8a 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1177,14 +1177,11 @@ static int __cpufreq_remove_dev(struct device *dev,
 				__func__, cpu_dev->id, cpu);
 	}
 
-	if ((cpus == 1) && (cpufreq_driver->target))
-		__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
-	pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
-	cpufreq_cpu_put(data);
-
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
+		if (cpufreq_driver->target)
+			__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
+
 		lock_policy_rwsem_read(cpu);
 		kobj = &data->kobj;
 		cmp = &data->kobj_unregister;
@@ -1205,9 +1202,13 @@ static int __cpufreq_remove_dev(struct device *dev,
 		free_cpumask_var(data->related_cpus);
 		free_cpumask_var(data->cpus);
 		kfree(data);
-	} else if (cpufreq_driver->target) {
-		__cpufreq_governor(data, CPUFREQ_GOV_START);
-		__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+	} else {
+		pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
+		cpufreq_cpu_put(data);
+		if (cpufreq_driver->target) {
+			__cpufreq_governor(data, CPUFREQ_GOV_START);
+			__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+		}
 	}
 
 	per_cpu(cpufreq_policy_cpu, cpu) = -1;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 0ceb2eff5a7e..f97cb3d8c5a2 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -221,8 +221,8 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
+		const char *buf, size_t count)
 {
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input, j;
@@ -235,10 +235,10 @@ static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
 	if (input > 1)
 		input = 1;
 
-	if (input == cs_tuners->ignore_nice) /* nothing to do */
+	if (input == cs_tuners->ignore_nice_load) /* nothing to do */
 		return count;
 
-	cs_tuners->ignore_nice = input;
+	cs_tuners->ignore_nice_load = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
@@ -246,7 +246,7 @@ static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
 		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
 		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
 					&dbs_info->cdbs.prev_cpu_wall, 0);
-		if (cs_tuners->ignore_nice)
+		if (cs_tuners->ignore_nice_load)
 			dbs_info->cdbs.prev_cpu_nice =
 				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 	}
@@ -279,7 +279,7 @@ show_store_one(cs, sampling_rate);
 show_store_one(cs, sampling_down_factor);
 show_store_one(cs, up_threshold);
 show_store_one(cs, down_threshold);
-show_store_one(cs, ignore_nice);
+show_store_one(cs, ignore_nice_load);
 show_store_one(cs, freq_step);
 declare_show_sampling_rate_min(cs);
 
@@ -287,7 +287,7 @@ gov_sys_pol_attr_rw(sampling_rate);
 gov_sys_pol_attr_rw(sampling_down_factor);
 gov_sys_pol_attr_rw(up_threshold);
 gov_sys_pol_attr_rw(down_threshold);
-gov_sys_pol_attr_rw(ignore_nice);
+gov_sys_pol_attr_rw(ignore_nice_load);
 gov_sys_pol_attr_rw(freq_step);
 gov_sys_pol_attr_ro(sampling_rate_min);
 
@@ -297,7 +297,7 @@ static struct attribute *dbs_attributes_gov_sys[] = {
 	&sampling_down_factor_gov_sys.attr,
 	&up_threshold_gov_sys.attr,
 	&down_threshold_gov_sys.attr,
-	&ignore_nice_gov_sys.attr,
+	&ignore_nice_load_gov_sys.attr,
 	&freq_step_gov_sys.attr,
 	NULL
 };
@@ -313,7 +313,7 @@ static struct attribute *dbs_attributes_gov_pol[] = {
 	&sampling_down_factor_gov_pol.attr,
 	&up_threshold_gov_pol.attr,
 	&down_threshold_gov_pol.attr,
-	&ignore_nice_gov_pol.attr,
+	&ignore_nice_load_gov_pol.attr,
 	&freq_step_gov_pol.attr,
 	NULL
 };
@@ -338,7 +338,7 @@ static int cs_init(struct dbs_data *dbs_data)
 	tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
 	tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD;
 	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice = 0;
+	tuners->ignore_nice_load = 0;
 	tuners->freq_step = DEF_FREQUENCY_STEP;
 
 	dbs_data->tuners = tuners;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 7b839a8db2a7..e59afaa9da23 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -47,9 +47,9 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 	unsigned int j;
 
 	if (dbs_data->cdata->governor == GOV_ONDEMAND)
-		ignore_nice = od_tuners->ignore_nice;
+		ignore_nice = od_tuners->ignore_nice_load;
 	else
-		ignore_nice = cs_tuners->ignore_nice;
+		ignore_nice = cs_tuners->ignore_nice_load;
 
 	policy = cdbs->cur_policy;
 
@@ -298,12 +298,12 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		cs_tuners = dbs_data->tuners;
 		cs_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
 		sampling_rate = cs_tuners->sampling_rate;
-		ignore_nice = cs_tuners->ignore_nice;
+		ignore_nice = cs_tuners->ignore_nice_load;
 	} else {
 		od_tuners = dbs_data->tuners;
 		od_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
 		sampling_rate = od_tuners->sampling_rate;
-		ignore_nice = od_tuners->ignore_nice;
+		ignore_nice = od_tuners->ignore_nice_load;
 		od_ops = dbs_data->cdata->gov_ops;
 		io_busy = od_tuners->io_is_busy;
 	}
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 6663ec3b3056..d5f12b4b11b8 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -165,7 +165,7 @@ struct cs_cpu_dbs_info_s {
 
 /* Per policy Governers sysfs tunables */
 struct od_dbs_tuners {
-	unsigned int ignore_nice;
+	unsigned int ignore_nice_load;
 	unsigned int sampling_rate;
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
@@ -175,7 +175,7 @@ struct od_dbs_tuners {
 };
 
 struct cs_dbs_tuners {
-	unsigned int ignore_nice;
+	unsigned int ignore_nice_load;
 	unsigned int sampling_rate;
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 93eb5cbcc1f6..c087347d6688 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -403,8 +403,8 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
+		const char *buf, size_t count)
 {
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	unsigned int input;
@@ -419,10 +419,10 @@ static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
 	if (input > 1)
 		input = 1;
 
-	if (input == od_tuners->ignore_nice) { /* nothing to do */
+	if (input == od_tuners->ignore_nice_load) { /* nothing to do */
 		return count;
 	}
-	od_tuners->ignore_nice = input;
+	od_tuners->ignore_nice_load = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
@@ -430,7 +430,7 @@ static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
 		dbs_info = &per_cpu(od_cpu_dbs_info, j);
 		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
 			&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
-		if (od_tuners->ignore_nice)
+		if (od_tuners->ignore_nice_load)
 			dbs_info->cdbs.prev_cpu_nice =
 				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
@@ -461,7 +461,7 @@ show_store_one(od, sampling_rate);
 show_store_one(od, io_is_busy);
 show_store_one(od, up_threshold);
 show_store_one(od, sampling_down_factor);
-show_store_one(od, ignore_nice);
+show_store_one(od, ignore_nice_load);
 show_store_one(od, powersave_bias);
 declare_show_sampling_rate_min(od);
 
@@ -469,7 +469,7 @@ gov_sys_pol_attr_rw(sampling_rate);
 gov_sys_pol_attr_rw(io_is_busy);
 gov_sys_pol_attr_rw(up_threshold);
 gov_sys_pol_attr_rw(sampling_down_factor);
-gov_sys_pol_attr_rw(ignore_nice);
+gov_sys_pol_attr_rw(ignore_nice_load);
 gov_sys_pol_attr_rw(powersave_bias);
 gov_sys_pol_attr_ro(sampling_rate_min);
 
@@ -478,7 +478,7 @@ static struct attribute *dbs_attributes_gov_sys[] = {
 	&sampling_rate_gov_sys.attr,
 	&up_threshold_gov_sys.attr,
 	&sampling_down_factor_gov_sys.attr,
-	&ignore_nice_gov_sys.attr,
+	&ignore_nice_load_gov_sys.attr,
 	&powersave_bias_gov_sys.attr,
 	&io_is_busy_gov_sys.attr,
 	NULL
@@ -494,7 +494,7 @@ static struct attribute *dbs_attributes_gov_pol[] = {
 	&sampling_rate_gov_pol.attr,
 	&up_threshold_gov_pol.attr,
 	&sampling_down_factor_gov_pol.attr,
-	&ignore_nice_gov_pol.attr,
+	&ignore_nice_load_gov_pol.attr,
 	&powersave_bias_gov_pol.attr,
 	&io_is_busy_gov_pol.attr,
 	NULL
@@ -544,7 +544,7 @@ static int od_init(struct dbs_data *dbs_data)
 	}
 
 	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice = 0;
+	tuners->ignore_nice_load = 0;
 	tuners->powersave_bias = default_powersave_bias;
 	tuners->io_is_busy = should_io_be_busy();
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b012d7600e1a..7cde885011ed 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -103,10 +103,10 @@ struct pstate_adjust_policy {
 static struct pstate_adjust_policy default_policy = {
 	.sample_rate_ms = 10,
 	.deadband = 0,
-	.setpoint = 109,
-	.p_gain_pct = 17,
+	.setpoint = 97,
+	.p_gain_pct = 20,
 	.d_gain_pct = 0,
-	.i_gain_pct = 4,
+	.i_gain_pct = 0,
 };
 
 struct perf_limits {
@@ -468,12 +468,12 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
 	int32_t busy_scaled;
-	int32_t core_busy, turbo_pstate, current_pstate;
+	int32_t core_busy, max_pstate, current_pstate;
 
 	core_busy = int_tofp(cpu->samples[cpu->sample_ptr].core_pct_busy);
-	turbo_pstate = int_tofp(cpu->pstate.turbo_pstate);
+	max_pstate = int_tofp(cpu->pstate.max_pstate);
 	current_pstate = int_tofp(cpu->pstate.current_pstate);
-	busy_scaled = mul_fp(core_busy, div_fp(turbo_pstate, current_pstate));
+	busy_scaled = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
 
 	return fp_toint(busy_scaled);
 }
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index bb838b985077..9536852c504a 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -118,11 +118,6 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		clk_put(cpuclk);
 		return -EINVAL;
 	}
-	ret = clk_set_rate(cpuclk, rate);
-	if (ret) {
-		clk_put(cpuclk);
-		return ret;
-	}
 
 	/* clock table init */
 	for (i = 2;
@@ -130,6 +125,12 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	     i++)
 		loongson2_clockmod_table[i].frequency = (rate * i) / 8;
 
+	ret = clk_set_rate(cpuclk, rate);
+	if (ret) {
+		clk_put(cpuclk);
+		return ret;
+	}
+
 	policy->cur = loongson2_cpufreq_get(policy->cpu);
 
 	cpufreq_frequency_table_get_attr(&loongson2_clockmod_table[0],
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index fe343a06b7da..bc580b67a652 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -28,13 +28,6 @@
 #define MAX_INTERESTING 50000
 #define STDDEV_THRESH 400
 
-/* 60 * 60 > STDDEV_THRESH * INTERVALS = 400 * 8 */
-#define MAX_DEVIATION 60
-
-static DEFINE_PER_CPU(struct hrtimer, menu_hrtimer);
-static DEFINE_PER_CPU(int, hrtimer_status);
-/* menu hrtimer mode */
-enum {MENU_HRTIMER_STOP, MENU_HRTIMER_REPEAT, MENU_HRTIMER_GENERAL};
 
 /*
  * Concepts and ideas behind the menu governor
@@ -116,13 +109,6 @@ enum {MENU_HRTIMER_STOP, MENU_HRTIMER_REPEAT, MENU_HRTIMER_GENERAL};
  *
  */
 
-/*
- * The C-state residency is so long that is is worthwhile to exit
- * from the shallow C-state and re-enter into a deeper C-state.
- */
-static unsigned int perfect_cstate_ms __read_mostly = 30;
-module_param(perfect_cstate_ms, uint, 0000);
-
 struct menu_device {
 	int		last_state_idx;
 	int             needs_update;
@@ -205,52 +191,17 @@ static u64 div_round64(u64 dividend, u32 divisor)
 	return div_u64(dividend + (divisor / 2), divisor);
 }
 
-/* Cancel the hrtimer if it is not triggered yet */
-void menu_hrtimer_cancel(void)
-{
-	int cpu = smp_processor_id();
-	struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
-
-	/* The timer is still not time out*/
-	if (per_cpu(hrtimer_status, cpu)) {
-		hrtimer_cancel(hrtmr);
-		per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
-	}
-}
-EXPORT_SYMBOL_GPL(menu_hrtimer_cancel);
-
-/* Call back for hrtimer is triggered */
-static enum hrtimer_restart menu_hrtimer_notify(struct hrtimer *hrtimer)
-{
-	int cpu = smp_processor_id();
-	struct menu_device *data = &per_cpu(menu_devices, cpu);
-
-	/* In general case, the expected residency is much larger than
-	 *  deepest C-state target residency, but prediction logic still
-	 *  predicts a small predicted residency, so the prediction
-	 *  history is totally broken if the timer is triggered.
-	 *  So reset the correction factor.
-	 */
-	if (per_cpu(hrtimer_status, cpu) == MENU_HRTIMER_GENERAL)
-		data->correction_factor[data->bucket] = RESOLUTION * DECAY;
-
-	per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
-
-	return HRTIMER_NORESTART;
-}
-
 /*
  * Try detecting repeating patterns by keeping track of the last 8
  * intervals, and checking if the standard deviation of that set
  * of points is below a threshold. If it is... then use the
  * average of these 8 points as the estimated value.
  */
-static u32 get_typical_interval(struct menu_device *data)
+static void get_typical_interval(struct menu_device *data)
 {
 	int i = 0, divisor = 0;
 	uint64_t max = 0, avg = 0, stddev = 0;
 	int64_t thresh = LLONG_MAX; /* Discard outliers above this value. */
-	unsigned int ret = 0;
 
 again:
 
@@ -291,16 +242,13 @@ again:
 	if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3))
 							|| stddev <= 20) {
 		data->predicted_us = avg;
-		ret = 1;
-		return ret;
+		return;
 
 	} else if ((divisor * 4) > INTERVALS * 3) {
 		/* Exclude the max interval */
 		thresh = max - 1;
 		goto again;
 	}
-
-	return ret;
 }
 
 /**
@@ -315,9 +263,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	int i;
 	int multiplier;
 	struct timespec t;
-	int repeat = 0, low_predicted = 0;
-	int cpu = smp_processor_id();
-	struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -352,7 +297,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
 					 RESOLUTION * DECAY);
 
-	repeat = get_typical_interval(data);
+	get_typical_interval(data);
 
 	/*
 	 * We want to default to C1 (hlt), not to busy polling
@@ -373,10 +318,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 		if (s->disabled || su->disable)
 			continue;
-		if (s->target_residency > data->predicted_us) {
-			low_predicted = 1;
+		if (s->target_residency > data->predicted_us)
 			continue;
-		}
 		if (s->exit_latency > latency_req)
 			continue;
 		if (s->exit_latency * multiplier > data->predicted_us)
@@ -386,44 +329,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		data->exit_us = s->exit_latency;
 	}
 
-	/* not deepest C-state chosen for low predicted residency */
-	if (low_predicted) {
-		unsigned int timer_us = 0;
-		unsigned int perfect_us = 0;
-
-		/*
-		 * Set a timer to detect whether this sleep is much
-		 * longer than repeat mode predicted.  If the timer
-		 * triggers, the code will evaluate whether to put
-		 * the CPU into a deeper C-state.
-		 * The timer is cancelled on CPU wakeup.
-		 */
-		timer_us = 2 * (data->predicted_us + MAX_DEVIATION);
-
-		perfect_us = perfect_cstate_ms * 1000;
-
-		if (repeat && (4 * timer_us < data->expected_us)) {
-			RCU_NONIDLE(hrtimer_start(hrtmr,
-				ns_to_ktime(1000 * timer_us),
-				HRTIMER_MODE_REL_PINNED));
-			/* In repeat case, menu hrtimer is started */
-			per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_REPEAT;
-		} else if (perfect_us < data->expected_us) {
-			/*
-			 * The next timer is long. This could be because
-			 * we did not make a useful prediction.
-			 * In that case, it makes sense to re-enter
-			 * into a deeper C-state after some time.
-			 */
-			RCU_NONIDLE(hrtimer_start(hrtmr,
-				ns_to_ktime(1000 * timer_us),
-				HRTIMER_MODE_REL_PINNED));
-			/* In general case, menu hrtimer is started */
-			per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_GENERAL;
-		}
-
-	}
-
 	return data->last_state_idx;
 }
 
@@ -514,9 +419,6 @@ static int menu_enable_device(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev)
 {
 	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
-	struct hrtimer *t = &per_cpu(menu_hrtimer, dev->cpu);
-	hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	t->function = menu_hrtimer_notify;
 
 	memset(data, 0, sizeof(struct menu_device));
 
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 5996521a1caf..84573b4d6f92 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -429,7 +429,7 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 	dma_addr_t src_dma, dst_dma;
 	int ret = 0;
 
-	desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
+	desc = kmalloc(CAAM_CMD_SZ * 8 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
 	if (!desc) {
 		dev_err(jrdev, "unable to allocate key input memory\n");
 		return -ENOMEM;
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index ce3dc3e9688c..0bbdea5059f3 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -867,6 +867,7 @@ static int pch_dma_probe(struct pci_dev *pdev,
 
 	if (!(pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) {
 		dev_err(&pdev->dev, "Cannot find proper base address\n");
+		err = -ENODEV;
 		goto err_disable_pdev;
 	}
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 593827b3fdd4..fa645d825009 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2505,6 +2505,10 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx)
 	/* Assign cookies to all nodes */
 	while (!list_empty(&last->node)) {
 		desc = list_entry(last->node.next, struct dma_pl330_desc, node);
+		if (pch->cyclic) {
+			desc->txd.callback = last->txd.callback;
+			desc->txd.callback_param = last->txd.callback_param;
+		}
 
 		dma_cookie_assign(&desc->txd);
 
@@ -2688,45 +2692,82 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
 		size_t period_len, enum dma_transfer_direction direction,
 		unsigned long flags, void *context)
 {
-	struct dma_pl330_desc *desc;
+	struct dma_pl330_desc *desc = NULL, *first = NULL;
 	struct dma_pl330_chan *pch = to_pchan(chan);
+	struct dma_pl330_dmac *pdmac = pch->dmac;
+	unsigned int i;
 	dma_addr_t dst;
 	dma_addr_t src;
 
-	desc = pl330_get_desc(pch);
-	if (!desc) {
-		dev_err(pch->dmac->pif.dev, "%s:%d Unable to fetch desc\n",
-			__func__, __LINE__);
+	if (len % period_len != 0)
 		return NULL;
-	}
 
-	switch (direction) {
-	case DMA_MEM_TO_DEV:
-		desc->rqcfg.src_inc = 1;
-		desc->rqcfg.dst_inc = 0;
-		desc->req.rqtype = MEMTODEV;
-		src = dma_addr;
-		dst = pch->fifo_addr;
-		break;
-	case DMA_DEV_TO_MEM:
-		desc->rqcfg.src_inc = 0;
-		desc->rqcfg.dst_inc = 1;
-		desc->req.rqtype = DEVTOMEM;
-		src = pch->fifo_addr;
-		dst = dma_addr;
-		break;
-	default:
+	if (!is_slave_direction(direction)) {
 		dev_err(pch->dmac->pif.dev, "%s:%d Invalid dma direction\n",
 		__func__, __LINE__);
 		return NULL;
 	}
 
-	desc->rqcfg.brst_size = pch->burst_sz;
-	desc->rqcfg.brst_len = 1;
+	for (i = 0; i < len / period_len; i++) {
+		desc = pl330_get_desc(pch);
+		if (!desc) {
+			dev_err(pch->dmac->pif.dev, "%s:%d Unable to fetch desc\n",
+				__func__, __LINE__);
 
-	pch->cyclic = true;
+			if (!first)
+				return NULL;
+
+			spin_lock_irqsave(&pdmac->pool_lock, flags);
+
+			while (!list_empty(&first->node)) {
+				desc = list_entry(first->node.next,
+						struct dma_pl330_desc, node);
+				list_move_tail(&desc->node, &pdmac->desc_pool);
+			}
+
+			list_move_tail(&first->node, &pdmac->desc_pool);
 
-	fill_px(&desc->px, dst, src, period_len);
+			spin_unlock_irqrestore(&pdmac->pool_lock, flags);
+
+			return NULL;
+		}
+
+		switch (direction) {
+		case DMA_MEM_TO_DEV:
+			desc->rqcfg.src_inc = 1;
+			desc->rqcfg.dst_inc = 0;
+			desc->req.rqtype = MEMTODEV;
+			src = dma_addr;
+			dst = pch->fifo_addr;
+			break;
+		case DMA_DEV_TO_MEM:
+			desc->rqcfg.src_inc = 0;
+			desc->rqcfg.dst_inc = 1;
+			desc->req.rqtype = DEVTOMEM;
+			src = pch->fifo_addr;
+			dst = dma_addr;
+			break;
+		default:
+			break;
+		}
+
+		desc->rqcfg.brst_size = pch->burst_sz;
+		desc->rqcfg.brst_len = 1;
+		fill_px(&desc->px, dst, src, period_len);
+
+		if (!first)
+			first = desc;
+		else
+			list_add_tail(&desc->node, &first->node);
+
+		dma_addr += period_len;
+	}
+
+	if (!desc)
+		return NULL;
+
+	pch->cyclic = true;
+	desc->txd.flags = flags;
 
 	return &desc->txd;
 }
diff --git a/drivers/dma/sh/shdma.c b/drivers/dma/sh/shdma.c
index b67f45f5c271..5039fbc88254 100644
--- a/drivers/dma/sh/shdma.c
+++ b/drivers/dma/sh/shdma.c
@@ -400,8 +400,8 @@ static size_t sh_dmae_get_partial(struct shdma_chan *schan,
 						    shdma_chan);
 	struct sh_dmae_desc *sh_desc = container_of(sdesc,
 					struct sh_dmae_desc, shdma_desc);
-	return (sh_desc->hw.tcr - sh_dmae_readl(sh_chan, TCR)) <<
-		sh_chan->xmit_shift;
+	return sh_desc->hw.tcr -
+		(sh_dmae_readl(sh_chan, TCR) << sh_chan->xmit_shift);
 }
 
 /* Called from error IRQ or NMI */
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 27e86d938262..89e109022d78 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -48,6 +48,8 @@ static LIST_HEAD(mc_devices);
  */
 static void const *edac_mc_owner;
 
+static struct bus_type mc_bus[EDAC_MAX_MCS];
+
 unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
 			         unsigned len)
 {
@@ -723,6 +725,11 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
 	int ret = -EINVAL;
 	edac_dbg(0, "\n");
 
+	if (mci->mc_idx >= EDAC_MAX_MCS) {
+		pr_warn_once("Too many memory controllers: %d\n", mci->mc_idx);
+		return -ENODEV;
+	}
+
 #ifdef CONFIG_EDAC_DEBUG
 	if (edac_debug_level >= 3)
 		edac_mc_dump_mci(mci);
@@ -762,6 +769,8 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
 	/* set load time so that error rate can be tracked */
 	mci->start_time = jiffies;
 
+	mci->bus = &mc_bus[mci->mc_idx];
+
 	if (edac_create_sysfs_mci_device(mci)) {
 		edac_mc_printk(mci, KERN_WARNING,
 			"failed to create sysfs device\n");
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index ef15a7e613bc..e7c32c4f7837 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -370,7 +370,7 @@ static int edac_create_csrow_object(struct mem_ctl_info *mci,
 		return -ENODEV;
 
 	csrow->dev.type = &csrow_attr_type;
-	csrow->dev.bus = &mci->bus;
+	csrow->dev.bus = mci->bus;
 	device_initialize(&csrow->dev);
 	csrow->dev.parent = &mci->dev;
 	csrow->mci = mci;
@@ -605,7 +605,7 @@ static int edac_create_dimm_object(struct mem_ctl_info *mci,
 	dimm->mci = mci;
 
 	dimm->dev.type = &dimm_attr_type;
-	dimm->dev.bus = &mci->bus;
+	dimm->dev.bus = mci->bus;
 	device_initialize(&dimm->dev);
 
 	dimm->dev.parent = &mci->dev;
@@ -975,11 +975,13 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci)
 	 * The memory controller needs its own bus, in order to avoid
 	 * namespace conflicts at /sys/bus/edac.
 	 */
-	mci->bus.name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx);
-	if (!mci->bus.name)
+	mci->bus->name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx);
+	if (!mci->bus->name)
 		return -ENOMEM;
-	edac_dbg(0, "creating bus %s\n", mci->bus.name);
-	err = bus_register(&mci->bus);
+
+	edac_dbg(0, "creating bus %s\n", mci->bus->name);
+
+	err = bus_register(mci->bus);
 	if (err < 0)
 		return err;
 
@@ -988,7 +990,7 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci)
 	device_initialize(&mci->dev);
 
 	mci->dev.parent = mci_pdev;
-	mci->dev.bus = &mci->bus;
+	mci->dev.bus = mci->bus;
 	dev_set_name(&mci->dev, "mc%d", mci->mc_idx);
 	dev_set_drvdata(&mci->dev, mci);
 	pm_runtime_forbid(&mci->dev);
@@ -997,8 +999,8 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci)
 	err = device_add(&mci->dev);
 	if (err < 0) {
 		edac_dbg(1, "failure: create device %s\n", dev_name(&mci->dev));
-		bus_unregister(&mci->bus);
-		kfree(mci->bus.name);
+		bus_unregister(mci->bus);
+		kfree(mci->bus->name);
 		return err;
 	}
 
@@ -1064,8 +1066,8 @@ fail:
 	}
 fail2:
 	device_unregister(&mci->dev);
-	bus_unregister(&mci->bus);
-	kfree(mci->bus.name);
+	bus_unregister(mci->bus);
+	kfree(mci->bus->name);
 	return err;
 }
 
@@ -1098,8 +1100,8 @@ void edac_unregister_sysfs(struct mem_ctl_info *mci)
 {
 	edac_dbg(1, "Unregistering device %s\n", dev_name(&mci->dev));
 	device_unregister(&mci->dev);
-	bus_unregister(&mci->bus);
-	kfree(mci->bus.name);
+	bus_unregister(mci->bus);
+	kfree(mci->bus->name);
 }
 
 static void mc_attr_release(struct device *dev)
diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c
index 1b635178cc44..157b934e8ce3 100644
--- a/drivers/edac/i5100_edac.c
+++ b/drivers/edac/i5100_edac.c
@@ -974,7 +974,7 @@ static int i5100_setup_debugfs(struct mem_ctl_info *mci)
 	if (!i5100_debugfs)
 		return -ENODEV;
 
-	priv->debugfs = debugfs_create_dir(mci->bus.name, i5100_debugfs);
+	priv->debugfs = debugfs_create_dir(mci->bus->name, i5100_debugfs);
 
 	if (!priv->debugfs)
 		return -ENOMEM;
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index 7ef316fdc4d9..ac1b43a04285 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -54,6 +54,7 @@
 #define FW_CDEV_KERNEL_VERSION			5
 #define FW_CDEV_VERSION_EVENT_REQUEST2		4
 #define FW_CDEV_VERSION_ALLOCATE_REGION_END	4
+#define FW_CDEV_VERSION_AUTO_FLUSH_ISO_OVERFLOW	5
 
 struct client {
 	u32 version;
@@ -1005,6 +1006,8 @@ static int ioctl_create_iso_context(struct client *client, union ioctl_arg *arg)
 			a->channel, a->speed, a->header_size, cb, client);
 	if (IS_ERR(context))
 		return PTR_ERR(context);
+	if (client->version < FW_CDEV_VERSION_AUTO_FLUSH_ISO_OVERFLOW)
+		context->drop_overflow_headers = true;
 
 	/* We only support one context at this time. */
 	spin_lock_irq(&client->lock);
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 9e1db6490b9a..afb701ec90ca 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -2749,8 +2749,11 @@ static void copy_iso_headers(struct iso_context *ctx, const u32 *dma_hdr)
 {
 	u32 *ctx_hdr;
 
-	if (ctx->header_length + ctx->base.header_size > PAGE_SIZE)
+	if (ctx->header_length + ctx->base.header_size > PAGE_SIZE) {
+		if (ctx->base.drop_overflow_headers)
+			return;
 		flush_iso_completions(ctx);
+	}
 
 	ctx_hdr = ctx->header + ctx->header_length;
 	ctx->last_timestamp = (u16)le32_to_cpu((__force __le32)dma_hdr[0]);
@@ -2910,8 +2913,11 @@ static int handle_it_packet(struct context *context,
 
 	sync_it_packet_for_cpu(context, d);
 
-	if (ctx->header_length + 4 > PAGE_SIZE)
+	if (ctx->header_length + 4 > PAGE_SIZE) {
+		if (ctx->base.drop_overflow_headers)
+			return 1;
 		flush_iso_completions(ctx);
+	}
 
 	ctx_hdr = ctx->header + ctx->header_length;
 	ctx->last_timestamp = le16_to_cpu(last->res_count);
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index eb760a218da4..232fa8fce26a 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -419,6 +419,13 @@ static void __init dmi_format_ids(char *buf, size_t len)
 			    dmi_get_system_info(DMI_BIOS_DATE));
 }
 
+/*
+ * Check for DMI/SMBIOS headers in the system firmware image.  Any
+ * SMBIOS header must start 16 bytes before the DMI header, so take a
+ * 32 byte buffer and check for DMI at offset 16 and SMBIOS at offset
+ * 0.  If the DMI header is present, set dmi_ver accordingly (SMBIOS
+ * takes precedence) and return 0.  Otherwise return 1.
+ */
 static int __init dmi_present(const u8 *buf)
 {
 	int smbios_ver;
@@ -506,6 +513,13 @@ void __init dmi_scan_machine(void)
 		if (p == NULL)
 			goto error;
 
+		/*
+		 * Iterate over all possible DMI header addresses q.
+		 * Maintain the 32 bytes around q in buf.  On the
+		 * first iteration, substitute zero for the
+		 * out-of-range bytes so there is no chance of falsely
+		 * detecting an SMBIOS header.
+		 */
 		memset(buf, 0, 16);
 		for (q = p; q < p + 0x10000; q += 16) {
 			memcpy_fromio(buf + 16, q, 16);
diff --git a/drivers/gpio/gpio-msm-v1.c b/drivers/gpio/gpio-msm-v1.c
index e3ceaacde45c..73b73969d361 100644
--- a/drivers/gpio/gpio-msm-v1.c
+++ b/drivers/gpio/gpio-msm-v1.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
+#include <linux/err.h>
 
 #include <mach/msm_gpiomux.h>
 
diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c
index f4491a497cc8..c2fa77086eb5 100644
--- a/drivers/gpio/gpio-msm-v2.c
+++ b/drivers/gpio/gpio-msm-v2.c
@@ -378,7 +378,7 @@ static int msm_gpio_probe(struct platform_device *pdev)
 	int ret, ngpio;
 	struct resource *res;
 
-	if (!of_property_read_u32(pdev->dev.of_node, "ngpio", &ngpio)) {
+	if (of_property_read_u32(pdev->dev.of_node, "ngpio", &ngpio)) {
 		dev_err(&pdev->dev, "%s: ngpio property missing\n", __func__);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 98d670825a1a..6e8887fe6c1b 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -323,6 +323,7 @@ int ast_bo_create(struct drm_device *dev, int size, int align,
 
 	astbo->gem.driver_private = NULL;
 	astbo->bo.bdev = &ast->ttm.bdev;
+	astbo->bo.bdev->dev_mapping = dev->dev_mapping;
 
 	ast_ttm_placement(astbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 0047012045c2..69fd8f1ac8df 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -328,6 +328,7 @@ int cirrus_bo_create(struct drm_device *dev, int size, int align,
 
 	cirrusbo->gem.driver_private = NULL;
 	cirrusbo->bo.bdev = &cirrus->ttm.bdev;
+	cirrusbo->bo.bdev->dev_mapping = dev->dev_mapping;
 
 	cirrus_ttm_placement(cirrusbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 738a4294d820..6a647493ca7f 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -677,6 +677,11 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 					/* don't break so fail path works correct */
 					fail = 1;
 				break;
+
+				if (connector->dpms != DRM_MODE_DPMS_ON) {
+					DRM_DEBUG_KMS("connector dpms not on, full mode switch\n");
+					mode_changed = true;
+				}
 			}
 		}
 
@@ -754,6 +759,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 				ret = -EINVAL;
 				goto fail;
 			}
+			DRM_DEBUG_KMS("Setting connector DPMS state to on\n");
+			for (i = 0; i < set->num_connectors; i++) {
+				DRM_DEBUG_KMS("\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id,
+					      drm_get_connector_name(set->connectors[i]));
+				set->connectors[i]->funcs->dpms(set->connectors[i], DRM_MODE_DPMS_ON);
+			}
 		}
 		drm_helper_disable_unused_functions(dev);
 	} else if (fb_changed) {
@@ -771,22 +782,6 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 		}
 	}
 
-	/*
-	 * crtc set_config helpers implicit set the crtc and all connected
-	 * encoders to DPMS on for a full mode set. But for just an fb update it
-	 * doesn't do that. To not confuse userspace, do an explicit DPMS_ON
-	 * unconditionally. This will also ensure driver internal dpms state is
-	 * consistent again.
-	 */
-	if (set->crtc->enabled) {
-		DRM_DEBUG_KMS("Setting connector DPMS state to on\n");
-		for (i = 0; i < set->num_connectors; i++) {
-			DRM_DEBUG_KMS("\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id,
-				      drm_get_connector_name(set->connectors[i]));
-			set->connectors[i]->funcs->dpms(set->connectors[i], DRM_MODE_DPMS_ON);
-		}
-	}
-
 	kfree(save_connectors);
 	kfree(save_encoders);
 	kfree(save_crtcs);
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 8bcce7866d36..f92da0a32f0d 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -708,7 +708,10 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 	/* Subtract time delta from raw timestamp to get final
 	 * vblank_time timestamp for end of vblank.
 	 */
-	etime = ktime_sub_ns(etime, delta_ns);
+	if (delta_ns < 0)
+		etime = ktime_add_ns(etime, -delta_ns);
+	else
+		etime = ktime_sub_ns(etime, delta_ns);
 	*vblank_time = ktime_to_timeval(etime);
 
 	DRM_DEBUG("crtc %d : v %d p(%d,%d)@ %ld.%ld -> %ld.%ld [e %d us, %d rep]\n",
diff --git a/drivers/gpu/drm/exynos/exynos_ddc.c b/drivers/gpu/drm/exynos/exynos_ddc.c
index 95c75edef01a..30ef41bcd7b8 100644
--- a/drivers/gpu/drm/exynos/exynos_ddc.c
+++ b/drivers/gpu/drm/exynos/exynos_ddc.c
@@ -15,7 +15,6 @@
 
 #include <linux/kernel.h>
 #include <linux/i2c.h>
-#include <linux/module.h>
 
 
 #include "exynos_drm_drv.h"
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 61b094f689a7..6e047bd53e2f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -12,7 +12,6 @@
  *
  */
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 3e106beca5b6..1c263dac3c1c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -14,7 +14,6 @@
 #include <drm/drmP.h>
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/of_device.h>
@@ -130,7 +129,6 @@ static const struct of_device_id fimd_driver_dt_match[] = {
 	  .data = &exynos5_fimd_driver_data },
 	{},
 };
-MODULE_DEVICE_TABLE(of, fimd_driver_dt_match);
 #endif
 
 static inline struct fimd_driver_data *drm_fimd_get_driver_data(
@@ -1082,7 +1080,6 @@ static struct platform_device_id fimd_driver_ids[] = {
 	},
 	{},
 };
-MODULE_DEVICE_TABLE(platform, fimd_driver_ids);
 
 static const struct dev_pm_ops fimd_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(fimd_suspend, fimd_resume)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 42a5a5466075..eddea4941483 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -806,9 +805,20 @@ static void g2d_dma_start(struct g2d_data *g2d,
 	struct g2d_cmdlist_node *node =
 				list_first_entry(&runqueue_node->run_cmdlist,
 						struct g2d_cmdlist_node, list);
+	int ret;
+
+	ret = pm_runtime_get_sync(g2d->dev);
+	if (ret < 0) {
+		dev_warn(g2d->dev, "failed pm power on.\n");
+		return;
+	}
 
-	pm_runtime_get_sync(g2d->dev);
-	clk_enable(g2d->gate_clk);
+	ret = clk_prepare_enable(g2d->gate_clk);
+	if (ret < 0) {
+		dev_warn(g2d->dev, "failed to enable clock.\n");
+		pm_runtime_put_sync(g2d->dev);
+		return;
+	}
 
 	writel_relaxed(node->dma_addr, g2d->regs + G2D_DMA_SFR_BASE_ADDR);
 	writel_relaxed(G2D_DMA_START, g2d->regs + G2D_DMA_COMMAND);
@@ -861,7 +871,7 @@ static void g2d_runqueue_worker(struct work_struct *work)
 					    runqueue_work);
 
 	mutex_lock(&g2d->runqueue_mutex);
-	clk_disable(g2d->gate_clk);
+	clk_disable_unprepare(g2d->gate_clk);
 	pm_runtime_put_sync(g2d->dev);
 
 	complete(&g2d->runqueue_node->complete);
@@ -1521,7 +1531,6 @@ static const struct of_device_id exynos_g2d_match[] = {
 	{ .compatible = "samsung,exynos5250-g2d" },
 	{},
 };
-MODULE_DEVICE_TABLE(of, exynos_g2d_match);
 #endif
 
 struct platform_driver g2d_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 472e3b25e7f2..90b8a1a5344c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -12,7 +12,6 @@
  *
  */
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
index aaa550d622f0..8d3bc01d6834 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
@@ -15,7 +15,6 @@
 
 #include <linux/kernel.h>
 #include <linux/wait.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index b1ef8e7ff9c9..d2b6ab4def93 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -12,7 +12,6 @@
  *
  */
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
 #include <linux/clk.h>
@@ -342,10 +341,10 @@ int exynos_drm_ipp_get_property(struct drm_device *drm_dev, void *data,
 		 */
 		ippdrv = ipp_find_obj(&ctx->ipp_idr, &ctx->ipp_lock,
 						prop_list->ipp_id);
-		if (!ippdrv) {
+		if (IS_ERR(ippdrv)) {
 			DRM_ERROR("not found ipp%d driver.\n",
 					prop_list->ipp_id);
-			return -EINVAL;
+			return PTR_ERR(ippdrv);
 		}
 
 		prop_list = ippdrv->prop_list;
@@ -970,9 +969,9 @@ int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
 	/* find command node */
 	c_node = ipp_find_obj(&ctx->prop_idr, &ctx->prop_lock,
 		qbuf->prop_id);
-	if (!c_node) {
+	if (IS_ERR(c_node)) {
 		DRM_ERROR("failed to get command node.\n");
-		return -EFAULT;
+		return PTR_ERR(c_node);
 	}
 
 	/* buffer control */
@@ -1106,9 +1105,9 @@ int exynos_drm_ipp_cmd_ctrl(struct drm_device *drm_dev, void *data,
 
 	c_node = ipp_find_obj(&ctx->prop_idr, &ctx->prop_lock,
 		cmd_ctrl->prop_id);
-	if (!c_node) {
+	if (IS_ERR(c_node)) {
 		DRM_ERROR("invalid command node list.\n");
-		return -EINVAL;
+		return PTR_ERR(c_node);
 	}
 
 	if (!exynos_drm_ipp_check_valid(ippdrv->dev, cmd_ctrl->ctrl,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 427640aa5148..49669aa24c45 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 41cc74d83e4e..c57c56519add 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -13,7 +13,6 @@
 #include <drm/drmP.h>
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 
 #include <drm/exynos_drm.h>
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 62ef5971ac3c..2f5c6942c968 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -24,7 +24,6 @@
 #include <linux/spinlock.h>
 #include <linux/wait.h>
 #include <linux/i2c.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
diff --git a/drivers/gpu/drm/exynos/exynos_hdmiphy.c b/drivers/gpu/drm/exynos/exynos_hdmiphy.c
index ef04255076c7..6e320ae9afed 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmiphy.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmiphy.c
@@ -15,7 +15,6 @@
 
 #include <linux/kernel.h>
 #include <linux/i2c.h>
-#include <linux/module.h>
 
 #include "exynos_drm_drv.h"
 #include "exynos_hdmi.h"
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 42ffb71c63bc..c9a137caea41 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -23,7 +23,6 @@
 #include <linux/spinlock.h>
 #include <linux/wait.h>
 #include <linux/i2c.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index 19e36603b23b..3bc8414533c9 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -500,7 +500,8 @@ static bool psb_intel_sdvo_read_response(struct psb_intel_sdvo *psb_intel_sdvo,
 				  &status))
 		goto log_fail;
 
-	while (status == SDVO_CMD_STATUS_PENDING && retry--) {
+	while ((status == SDVO_CMD_STATUS_PENDING ||
+		status == SDVO_CMD_STATUS_TARGET_NOT_SPECIFIED) && retry--) {
 		udelay(15);
 		if (!psb_intel_sdvo_read_byte(psb_intel_sdvo,
 					  SDVO_I2C_CMD_STATUS,
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index cf188ab7051a..f4669802a0fb 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1495,6 +1495,15 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	dev_priv->dev = dev;
 	dev_priv->info = info;
 
+	spin_lock_init(&dev_priv->irq_lock);
+	spin_lock_init(&dev_priv->gpu_error.lock);
+	spin_lock_init(&dev_priv->rps.lock);
+	spin_lock_init(&dev_priv->gt_lock);
+	spin_lock_init(&dev_priv->backlight.lock);
+	mutex_init(&dev_priv->dpio_lock);
+	mutex_init(&dev_priv->rps.hw_lock);
+	mutex_init(&dev_priv->modeset_restore_lock);
+
 	i915_dump_device_info(dev_priv);
 
 	if (i915_get_bridge_dev(dev)) {
@@ -1585,6 +1594,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	intel_detect_pch(dev);
 
 	intel_irq_init(dev);
+	intel_pm_init(dev);
+	intel_gt_sanitize(dev);
 	intel_gt_init(dev);
 
 	/* Try to make sure MCHBAR is enabled before poking at it */
@@ -1610,15 +1621,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (!IS_I945G(dev) && !IS_I945GM(dev))
 		pci_enable_msi(dev->pdev);
 
-	spin_lock_init(&dev_priv->irq_lock);
-	spin_lock_init(&dev_priv->gpu_error.lock);
-	spin_lock_init(&dev_priv->rps.lock);
-	spin_lock_init(&dev_priv->backlight.lock);
-	mutex_init(&dev_priv->dpio_lock);
-
-	mutex_init(&dev_priv->rps.hw_lock);
-	mutex_init(&dev_priv->modeset_restore_lock);
-
 	dev_priv->num_plane = 1;
 	if (IS_VALLEYVIEW(dev))
 		dev_priv->num_plane = 2;
@@ -1648,7 +1650,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (INTEL_INFO(dev)->num_pipes) {
 		/* Must be done after probing outputs */
 		intel_opregion_init(dev);
-		acpi_video_register_with_quirks();
+		acpi_video_register();
 	}
 
 	if (IS_GEN5(dev))
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f4af1ca0fb62..45b3c030f483 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -706,7 +706,7 @@ static int i915_drm_thaw(struct drm_device *dev)
 {
 	int error = 0;
 
-	intel_gt_reset(dev);
+	intel_gt_sanitize(dev);
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		mutex_lock(&dev->struct_mutex);
@@ -732,7 +732,7 @@ int i915_resume(struct drm_device *dev)
 
 	pci_set_master(dev->pdev);
 
-	intel_gt_reset(dev);
+	intel_gt_sanitize(dev);
 
 	/*
 	 * Platforms with opregion should have sane BIOS, older ones (gen3 and
@@ -1253,21 +1253,21 @@ hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg)
 
 #define __i915_read(x, y) \
 u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
+	unsigned long irqflags; \
 	u##x val = 0; \
+	spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
 	if (IS_GEN5(dev_priv->dev)) \
 		ilk_dummy_write(dev_priv); \
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
-		unsigned long irqflags; \
-		spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
 		if (dev_priv->forcewake_count == 0) \
 			dev_priv->gt.force_wake_get(dev_priv); \
 		val = read##y(dev_priv->regs + reg); \
 		if (dev_priv->forcewake_count == 0) \
 			dev_priv->gt.force_wake_put(dev_priv); \
-		spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
 	} else { \
 		val = read##y(dev_priv->regs + reg); \
 	} \
+	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
 	trace_i915_reg_rw(false, reg, val, sizeof(val)); \
 	return val; \
 }
@@ -1280,8 +1280,10 @@ __i915_read(64, q)
 
 #define __i915_write(x, y) \
 void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
+	unsigned long irqflags; \
 	u32 __fifo_ret = 0; \
 	trace_i915_reg_rw(true, reg, val, sizeof(val)); \
+	spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
@@ -1293,6 +1295,7 @@ void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
 		gen6_gt_check_fifodbg(dev_priv); \
 	} \
 	hsw_unclaimed_reg_check(dev_priv, reg); \
+	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
 }
 __i915_write(8, b)
 __i915_write(16, w)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a416645bcd23..1929bffc1c77 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -555,6 +555,7 @@ enum intel_sbi_destination {
 #define QUIRK_PIPEA_FORCE (1<<0)
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
 #define QUIRK_INVERT_BRIGHTNESS (1<<2)
+#define QUIRK_NO_PCH_PWM_ENABLE (1<<3)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -1581,9 +1582,10 @@ void i915_hangcheck_elapsed(unsigned long data);
 void i915_handle_error(struct drm_device *dev, bool wedged);
 
 extern void intel_irq_init(struct drm_device *dev);
+extern void intel_pm_init(struct drm_device *dev);
 extern void intel_hpd_init(struct drm_device *dev);
 extern void intel_gt_init(struct drm_device *dev);
-extern void intel_gt_reset(struct drm_device *dev);
+extern void intel_gt_sanitize(struct drm_device *dev);
 
 void i915_error_state_free(struct kref *error_ref);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 97afd2639fb6..d9e2208cfe98 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2258,7 +2258,17 @@ void i915_gem_restore_fences(struct drm_device *dev)
 
 	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
-		i915_gem_write_fence(dev, i, reg->obj);
+
+		/*
+		 * Commit delayed tiling changes if we have an object still
+		 * attached to the fence, otherwise just clear the fence.
+		 */
+		if (reg->obj) {
+			i915_gem_object_update_fence(reg->obj, reg,
+						     reg->obj->tiling_mode);
+		} else {
+			i915_gem_write_fence(dev, i, NULL);
+		}
 	}
 }
 
@@ -2795,6 +2805,10 @@ static void i915_gem_write_fence(struct drm_device *dev, int reg,
 	if (i915_gem_object_needs_mb(dev_priv->fence_regs[reg].obj))
 		mb();
 
+	WARN(obj && (!obj->stride || !obj->tiling_mode),
+	     "bogus fence setup with stride: 0x%x, tiling mode: %i\n",
+	     obj->stride, obj->tiling_mode);
+
 	switch (INTEL_INFO(dev)->gen) {
 	case 7:
 	case 6:
@@ -2836,6 +2850,7 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 		fence->obj = NULL;
 		list_del_init(&fence->lru_list);
 	}
+	obj->fence_dirty = false;
 }
 
 static int
@@ -2965,7 +2980,6 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
 		return 0;
 
 	i915_gem_object_update_fence(obj, reg, enable);
-	obj->fence_dirty = false;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index dc53a527126b..9e6578330801 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -85,9 +85,17 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 				   struct sg_table *sg,
 				   enum dma_data_direction dir)
 {
+	struct drm_i915_gem_object *obj = attachment->dmabuf->priv;
+
+	mutex_lock(&obj->base.dev->struct_mutex);
+
 	dma_unmap_sg(attachment->dev, sg->sgl, sg->nents, dir);
 	sg_free_table(sg);
 	kfree(sg);
+
+	i915_gem_object_unpin_pages(obj);
+
+	mutex_unlock(&obj->base.dev->struct_mutex);
 }
 
 static void i915_gem_dmabuf_release(struct dma_buf *dma_buf)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f2326fc60ac9..53cddd985406 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -752,6 +752,8 @@
 					will not assert AGPBUSY# and will only
 					be delivered when out of C3. */
 #define   INSTPM_FORCE_ORDERING				(1<<7) /* GEN6+ */
+#define   INSTPM_TLB_INVALIDATE	(1<<9)
+#define   INSTPM_SYNC_FLUSH	(1<<5)
 #define ACTHD	        0x020c8
 #define FW_BLC		0x020d8
 #define FW_BLC2		0x020dc
@@ -1856,10 +1858,16 @@
 #define CRT_HOTPLUG_DETECT_VOLTAGE_475MV	(1 << 2)
 
 #define PORT_HOTPLUG_STAT	(dev_priv->info->display_mmio_offset + 0x61114)
-/* HDMI/DP bits are gen4+ */
-#define   PORTB_HOTPLUG_LIVE_STATUS               (1 << 29)
+/*
+ * HDMI/DP bits are gen4+
+ *
+ * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused.
+ * Please check the detailed lore in the commit message for for experimental
+ * evidence.
+ */
+#define   PORTD_HOTPLUG_LIVE_STATUS               (1 << 29)
 #define   PORTC_HOTPLUG_LIVE_STATUS               (1 << 28)
-#define   PORTD_HOTPLUG_LIVE_STATUS               (1 << 27)
+#define   PORTB_HOTPLUG_LIVE_STATUS               (1 << 27)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTC_HOTPLUG_INT_STATUS		(3 << 19)
 #define   PORTB_HOTPLUG_INT_STATUS		(3 << 17)
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 324211ac9c55..b042ee5c4070 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -301,7 +301,7 @@ static void intel_ddi_mode_set(struct drm_encoder *encoder,
 		struct intel_digital_port *intel_dig_port =
 			enc_to_dig_port(encoder);
 
-		intel_dp->DP = intel_dig_port->port_reversal |
+		intel_dp->DP = intel_dig_port->saved_port_bits |
 			       DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW;
 		intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count);
 
@@ -1109,7 +1109,8 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder)
 		 * enabling the port.
 		 */
 		I915_WRITE(DDI_BUF_CTL(port),
-			   intel_dig_port->port_reversal | DDI_BUF_CTL_ENABLE);
+			   intel_dig_port->saved_port_bits |
+			   DDI_BUF_CTL_ENABLE);
 	} else if (type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
@@ -1347,8 +1348,9 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	intel_encoder->get_config = intel_ddi_get_config;
 
 	intel_dig_port->port = port;
-	intel_dig_port->port_reversal = I915_READ(DDI_BUF_CTL(port)) &
-					DDI_BUF_PORT_REVERSAL;
+	intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
+					  (DDI_BUF_PORT_REVERSAL |
+					   DDI_A_4_LANES);
 	intel_dig_port->dp.output_reg = DDI_BUF_CTL(port);
 
 	intel_encoder->type = INTEL_OUTPUT_UNKNOWN;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 85f3eb74d2b7..be79f477a38f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4913,22 +4913,19 @@ static void i9xx_get_pfit_config(struct intel_crtc *crtc,
 	uint32_t tmp;
 
 	tmp = I915_READ(PFIT_CONTROL);
+	if (!(tmp & PFIT_ENABLE))
+		return;
 
+	/* Check whether the pfit is attached to our pipe. */
 	if (INTEL_INFO(dev)->gen < 4) {
 		if (crtc->pipe != PIPE_B)
 			return;
-
-		/* gen2/3 store dither state in pfit control, needs to match */
-		pipe_config->gmch_pfit.control = tmp & PANEL_8TO6_DITHER_ENABLE;
 	} else {
 		if ((tmp & PFIT_PIPE_MASK) != (crtc->pipe << PFIT_PIPE_SHIFT))
 			return;
 	}
 
-	if (!(tmp & PFIT_ENABLE))
-		return;
-
-	pipe_config->gmch_pfit.control = I915_READ(PFIT_CONTROL);
+	pipe_config->gmch_pfit.control = tmp;
 	pipe_config->gmch_pfit.pgm_ratios = I915_READ(PFIT_PGM_RATIOS);
 	if (INTEL_INFO(dev)->gen < 5)
 		pipe_config->gmch_pfit.lvds_border_bits =
@@ -8272,9 +8269,11 @@ check_crtc_state(struct drm_device *dev)
 
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list,
 				    base.head) {
+			enum pipe pipe;
 			if (encoder->base.crtc != &crtc->base)
 				continue;
-			if (encoder->get_config)
+			if (encoder->get_config &&
+			    encoder->get_hw_state(encoder, &pipe))
 				encoder->get_config(encoder, &pipe_config);
 		}
 
@@ -8317,6 +8316,8 @@ check_shared_dpll_state(struct drm_device *dev)
 		     pll->active, pll->refcount);
 		WARN(pll->active && !pll->on,
 		     "pll in active use but not on in sw tracking\n");
+		WARN(pll->on && !pll->active,
+		     "pll in on but not on in use in sw tracking\n");
 		WARN(pll->on != active,
 		     "pll on state mismatch (expected %i, found %i)\n",
 		     pll->on, active);
@@ -8541,15 +8542,20 @@ static void intel_set_config_restore_state(struct drm_device *dev,
 }
 
 static bool
-is_crtc_connector_off(struct drm_crtc *crtc, struct drm_connector *connectors,
-		      int num_connectors)
+is_crtc_connector_off(struct drm_mode_set *set)
 {
 	int i;
 
-	for (i = 0; i < num_connectors; i++)
-		if (connectors[i].encoder &&
-		    connectors[i].encoder->crtc == crtc &&
-		    connectors[i].dpms != DRM_MODE_DPMS_ON)
+	if (set->num_connectors == 0)
+		return false;
+
+	if (WARN_ON(set->connectors == NULL))
+		return false;
+
+	for (i = 0; i < set->num_connectors; i++)
+		if (set->connectors[i]->encoder &&
+		    set->connectors[i]->encoder->crtc == set->crtc &&
+		    set->connectors[i]->dpms != DRM_MODE_DPMS_ON)
 			return true;
 
 	return false;
@@ -8562,10 +8568,8 @@ intel_set_config_compute_mode_changes(struct drm_mode_set *set,
 
 	/* We should be able to check here if the fb has the same properties
 	 * and then just flip_or_move it */
-	if (set->connectors != NULL &&
-	    is_crtc_connector_off(set->crtc, *set->connectors,
-				  set->num_connectors)) {
-			config->mode_changed = true;
+	if (is_crtc_connector_off(set)) {
+		config->mode_changed = true;
 	} else if (set->crtc->fb != set->fb) {
 		/* If we have no fb then treat it as a full mode set */
 		if (set->crtc->fb == NULL) {
@@ -9398,6 +9402,17 @@ static void quirk_invert_brightness(struct drm_device *dev)
 	DRM_INFO("applying inverted panel brightness quirk\n");
 }
 
+/*
+ * Some machines (Dell XPS13) suffer broken backlight controls if
+ * BLM_PCH_PWM_ENABLE is set.
+ */
+static void quirk_no_pcm_pwm_enable(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	dev_priv->quirks |= QUIRK_NO_PCH_PWM_ENABLE;
+	DRM_INFO("applying no-PCH_PWM_ENABLE quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -9467,6 +9482,11 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Acer Aspire 4736Z */
 	{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
+
+	/* Dell XPS13 HD Sandy Bridge */
+	{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
+	/* Dell XPS13 HD and XPS13 FHD Ivy Bridge */
+	{ 0x0166, 0x1028, 0x058b, quirk_no_pcm_pwm_enable },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -9817,8 +9837,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		}
 		pll->refcount = pll->active;
 
-		DRM_DEBUG_KMS("%s hw state readout: refcount %i\n",
-			      pll->name, pll->refcount);
+		DRM_DEBUG_KMS("%s hw state readout: refcount %i, on %i\n",
+			      pll->name, pll->refcount, pll->on);
 	}
 
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
@@ -9869,6 +9889,7 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 	struct drm_plane *plane;
 	struct intel_crtc *crtc;
 	struct intel_encoder *encoder;
+	int i;
 
 	intel_modeset_readout_hw_state(dev);
 
@@ -9884,6 +9905,18 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 		intel_dump_pipe_config(crtc, &crtc->config, "[setup_hw_state]");
 	}
 
+	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+		struct intel_shared_dpll *pll = &dev_priv->shared_dplls[i];
+
+		if (!pll->on || pll->active)
+			continue;
+
+		DRM_DEBUG_KMS("%s enabled but not in use, disabling\n", pll->name);
+
+		pll->disable(dev_priv, pll);
+		pll->on = false;
+	}
+
 	if (force_restore) {
 		/*
 		 * We need to use raw interfaces for restoring state to avoid
@@ -10009,6 +10042,8 @@ struct intel_display_error_state {
 
 	u32 power_well_driver;
 
+	int num_transcoders;
+
 	struct intel_cursor_error_state {
 		u32 control;
 		u32 position;
@@ -10017,16 +10052,7 @@ struct intel_display_error_state {
 	} cursor[I915_MAX_PIPES];
 
 	struct intel_pipe_error_state {
-		enum transcoder cpu_transcoder;
-		u32 conf;
 		u32 source;
-
-		u32 htotal;
-		u32 hblank;
-		u32 hsync;
-		u32 vtotal;
-		u32 vblank;
-		u32 vsync;
 	} pipe[I915_MAX_PIPES];
 
 	struct intel_plane_error_state {
@@ -10038,6 +10064,19 @@ struct intel_display_error_state {
 		u32 surface;
 		u32 tile_offset;
 	} plane[I915_MAX_PIPES];
+
+	struct intel_transcoder_error_state {
+		enum transcoder cpu_transcoder;
+
+		u32 conf;
+
+		u32 htotal;
+		u32 hblank;
+		u32 hsync;
+		u32 vtotal;
+		u32 vblank;
+		u32 vsync;
+	} transcoder[4];
 };
 
 struct intel_display_error_state *
@@ -10045,9 +10084,17 @@ intel_display_capture_error_state(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_display_error_state *error;
-	enum transcoder cpu_transcoder;
+	int transcoders[] = {
+		TRANSCODER_A,
+		TRANSCODER_B,
+		TRANSCODER_C,
+		TRANSCODER_EDP,
+	};
 	int i;
 
+	if (INTEL_INFO(dev)->num_pipes == 0)
+		return NULL;
+
 	error = kmalloc(sizeof(*error), GFP_ATOMIC);
 	if (error == NULL)
 		return NULL;
@@ -10056,9 +10103,6 @@ intel_display_capture_error_state(struct drm_device *dev)
 		error->power_well_driver = I915_READ(HSW_PWR_WELL_DRIVER);
 
 	for_each_pipe(i) {
-		cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv, i);
-		error->pipe[i].cpu_transcoder = cpu_transcoder;
-
 		if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) {
 			error->cursor[i].control = I915_READ(CURCNTR(i));
 			error->cursor[i].position = I915_READ(CURPOS(i));
@@ -10082,14 +10126,25 @@ intel_display_capture_error_state(struct drm_device *dev)
 			error->plane[i].tile_offset = I915_READ(DSPTILEOFF(i));
 		}
 
-		error->pipe[i].conf = I915_READ(PIPECONF(cpu_transcoder));
 		error->pipe[i].source = I915_READ(PIPESRC(i));
-		error->pipe[i].htotal = I915_READ(HTOTAL(cpu_transcoder));
-		error->pipe[i].hblank = I915_READ(HBLANK(cpu_transcoder));
-		error->pipe[i].hsync = I915_READ(HSYNC(cpu_transcoder));
-		error->pipe[i].vtotal = I915_READ(VTOTAL(cpu_transcoder));
-		error->pipe[i].vblank = I915_READ(VBLANK(cpu_transcoder));
-		error->pipe[i].vsync = I915_READ(VSYNC(cpu_transcoder));
+	}
+
+	error->num_transcoders = INTEL_INFO(dev)->num_pipes;
+	if (HAS_DDI(dev_priv->dev))
+		error->num_transcoders++; /* Account for eDP. */
+
+	for (i = 0; i < error->num_transcoders; i++) {
+		enum transcoder cpu_transcoder = transcoders[i];
+
+		error->transcoder[i].cpu_transcoder = cpu_transcoder;
+
+		error->transcoder[i].conf = I915_READ(PIPECONF(cpu_transcoder));
+		error->transcoder[i].htotal = I915_READ(HTOTAL(cpu_transcoder));
+		error->transcoder[i].hblank = I915_READ(HBLANK(cpu_transcoder));
+		error->transcoder[i].hsync = I915_READ(HSYNC(cpu_transcoder));
+		error->transcoder[i].vtotal = I915_READ(VTOTAL(cpu_transcoder));
+		error->transcoder[i].vblank = I915_READ(VBLANK(cpu_transcoder));
+		error->transcoder[i].vsync = I915_READ(VSYNC(cpu_transcoder));
 	}
 
 	/* In the code above we read the registers without checking if the power
@@ -10111,22 +10166,16 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 {
 	int i;
 
+	if (!error)
+		return;
+
 	err_printf(m, "Num Pipes: %d\n", INTEL_INFO(dev)->num_pipes);
 	if (HAS_POWER_WELL(dev))
 		err_printf(m, "PWR_WELL_CTL2: %08x\n",
 			   error->power_well_driver);
 	for_each_pipe(i) {
 		err_printf(m, "Pipe [%d]:\n", i);
-		err_printf(m, "  CPU transcoder: %c\n",
-			   transcoder_name(error->pipe[i].cpu_transcoder));
-		err_printf(m, "  CONF: %08x\n", error->pipe[i].conf);
 		err_printf(m, "  SRC: %08x\n", error->pipe[i].source);
-		err_printf(m, "  HTOTAL: %08x\n", error->pipe[i].htotal);
-		err_printf(m, "  HBLANK: %08x\n", error->pipe[i].hblank);
-		err_printf(m, "  HSYNC: %08x\n", error->pipe[i].hsync);
-		err_printf(m, "  VTOTAL: %08x\n", error->pipe[i].vtotal);
-		err_printf(m, "  VBLANK: %08x\n", error->pipe[i].vblank);
-		err_printf(m, "  VSYNC: %08x\n", error->pipe[i].vsync);
 
 		err_printf(m, "Plane [%d]:\n", i);
 		err_printf(m, "  CNTR: %08x\n", error->plane[i].control);
@@ -10147,5 +10196,17 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  POS: %08x\n", error->cursor[i].position);
 		err_printf(m, "  BASE: %08x\n", error->cursor[i].base);
 	}
+
+	for (i = 0; i < error->num_transcoders; i++) {
+		err_printf(m, "  CPU transcoder: %c\n",
+			   transcoder_name(error->transcoder[i].cpu_transcoder));
+		err_printf(m, "  CONF: %08x\n", error->transcoder[i].conf);
+		err_printf(m, "  HTOTAL: %08x\n", error->transcoder[i].htotal);
+		err_printf(m, "  HBLANK: %08x\n", error->transcoder[i].hblank);
+		err_printf(m, "  HSYNC: %08x\n", error->transcoder[i].hsync);
+		err_printf(m, "  VTOTAL: %08x\n", error->transcoder[i].vtotal);
+		err_printf(m, "  VBLANK: %08x\n", error->transcoder[i].vblank);
+		err_printf(m, "  VSYNC: %08x\n", error->transcoder[i].vsync);
+	}
 }
 #endif
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index c8c9b6f48230..b7d6e09456ce 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -504,7 +504,7 @@ struct intel_dp {
 struct intel_digital_port {
 	struct intel_encoder base;
 	enum port port;
-	u32 port_reversal;
+	u32 saved_port_bits;
 	struct intel_dp dp;
 	struct intel_hdmi hdmi;
 };
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 98df2a0c85bd..2fd3fd5b943e 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -785,10 +785,22 @@ static void intel_disable_hdmi(struct intel_encoder *encoder)
 	}
 }
 
+static int hdmi_portclock_limit(struct intel_hdmi *hdmi)
+{
+	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
+
+	if (IS_G4X(dev))
+		return 165000;
+	else if (IS_HASWELL(dev))
+		return 300000;
+	else
+		return 225000;
+}
+
 static int intel_hdmi_mode_valid(struct drm_connector *connector,
 				 struct drm_display_mode *mode)
 {
-	if (mode->clock > 165000)
+	if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector)))
 		return MODE_CLOCK_HIGH;
 	if (mode->clock < 20000)
 		return MODE_CLOCK_LOW;
@@ -806,6 +818,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode;
 	int clock_12bpc = pipe_config->requested_mode.clock * 3 / 2;
+	int portclock_limit = hdmi_portclock_limit(intel_hdmi);
 	int desired_bpp;
 
 	if (intel_hdmi->color_range_auto) {
@@ -829,7 +842,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	 * outputs. We also need to check that the higher clock still fits
 	 * within limits.
 	 */
-	if (pipe_config->pipe_bpp > 8*3 && clock_12bpc <= 225000
+	if (pipe_config->pipe_bpp > 8*3 && clock_12bpc <= portclock_limit
 	    && HAS_PCH_SPLIT(dev)) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
@@ -846,7 +859,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 		pipe_config->pipe_bpp = desired_bpp;
 	}
 
-	if (adjusted_mode->clock > 225000) {
+	if (adjusted_mode->clock > portclock_limit) {
 		DRM_DEBUG_KMS("too high HDMI clock, rejecting mode\n");
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 021e8daa022d..61348eae2f04 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -109,6 +109,13 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 		flags |= DRM_MODE_FLAG_PVSYNC;
 
 	pipe_config->adjusted_mode.flags |= flags;
+
+	/* gen2/3 store dither state in pfit control, needs to match */
+	if (INTEL_INFO(dev)->gen < 4) {
+		tmp = I915_READ(PFIT_CONTROL);
+
+		pipe_config->gmch_pfit.control |= tmp & PANEL_8TO6_DITHER_ENABLE;
+	}
 }
 
 /* The LVDS pin pair needs to be on before the DPLLs are enabled.
@@ -290,14 +297,11 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 
 		intel_pch_panel_fitting(intel_crtc, pipe_config,
 					intel_connector->panel.fitting_mode);
-		return true;
 	} else {
 		intel_gmch_panel_fitting(intel_crtc, pipe_config,
 					 intel_connector->panel.fitting_mode);
-	}
 
-	drm_mode_set_crtcinfo(adjusted_mode, 0);
-	pipe_config->timings_set = true;
+	}
 
 	/*
 	 * XXX: It would be nice to support lower refresh rates on the
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 80bea1d3209f..5950888ae1d0 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -194,6 +194,9 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc,
 	    adjusted_mode->vdisplay == mode->vdisplay)
 		goto out;
 
+	drm_mode_set_crtcinfo(adjusted_mode, 0);
+	pipe_config->timings_set = true;
+
 	switch (fitting_mode) {
 	case DRM_MODE_SCALE_CENTER:
 		/*
@@ -494,8 +497,11 @@ void intel_panel_set_backlight(struct drm_device *dev, u32 level, u32 max)
 		goto out;
 	}
 
-	/* scale to hardware */
-	level = level * freq / max;
+	/* scale to hardware, but be careful to not overflow */
+	if (freq < max)
+		level = level * freq / max;
+	else
+		level = freq / max * level;
 
 	dev_priv->backlight.level = level;
 	if (dev_priv->backlight.device)
@@ -512,6 +518,17 @@ void intel_panel_disable_backlight(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long flags;
 
+	/*
+	 * Do not disable backlight on the vgaswitcheroo path. When switching
+	 * away from i915, the other client may depend on i915 to handle the
+	 * backlight. This will leave the backlight on unnecessarily when
+	 * another client is not activated.
+	 */
+	if (dev->switch_power_state == DRM_SWITCH_POWER_CHANGING) {
+		DRM_DEBUG_DRIVER("Skipping backlight disable on vga switch\n");
+		return;
+	}
+
 	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
 
 	dev_priv->backlight.enabled = false;
@@ -580,7 +597,8 @@ void intel_panel_enable_backlight(struct drm_device *dev,
 		POSTING_READ(reg);
 		I915_WRITE(reg, tmp | BLM_PWM_ENABLE);
 
-		if (HAS_PCH_SPLIT(dev)) {
+		if (HAS_PCH_SPLIT(dev) &&
+		    !(dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)) {
 			tmp = I915_READ(BLC_PWM_PCH_CTL1);
 			tmp |= BLM_PCH_PWM_ENABLE;
 			tmp &= ~BLM_PCH_OVERRIDE_ENABLE;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d10e6735771f..b0e4a0bd1313 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5063,8 +5063,26 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 		}
 	} else {
 		if (enable_requested) {
+			unsigned long irqflags;
+			enum pipe p;
+
 			I915_WRITE(HSW_PWR_WELL_DRIVER, 0);
+			POSTING_READ(HSW_PWR_WELL_DRIVER);
 			DRM_DEBUG_KMS("Requesting to disable the power well\n");
+
+			/*
+			 * After this, the registers on the pipes that are part
+			 * of the power well will become zero, so we have to
+			 * adjust our counters according to that.
+			 *
+			 * FIXME: Should we do this in general in
+			 * drm_vblank_post_modeset?
+			 */
+			spin_lock_irqsave(&dev->vbl_lock, irqflags);
+			for_each_pipe(p)
+				if (p != PIPE_A)
+					dev->last_vblank[p] = 0;
+			spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 		}
 	}
 }
@@ -5476,7 +5494,7 @@ static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
-void intel_gt_reset(struct drm_device *dev)
+void intel_gt_sanitize(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -5487,16 +5505,16 @@ void intel_gt_reset(struct drm_device *dev)
 		if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
 			__gen6_gt_force_wake_mt_reset(dev_priv);
 	}
+
+	/* BIOS often leaves RC6 enabled, but disable it for hw init */
+	if (INTEL_INFO(dev)->gen >= 6)
+		intel_disable_gt_powersave(dev);
 }
 
 void intel_gt_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	spin_lock_init(&dev_priv->gt_lock);
-
-	intel_gt_reset(dev);
-
 	if (IS_VALLEYVIEW(dev)) {
 		dev_priv->gt.force_wake_get = vlv_force_wake_get;
 		dev_priv->gt.force_wake_put = vlv_force_wake_put;
@@ -5536,6 +5554,12 @@ void intel_gt_init(struct drm_device *dev)
 		dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
 		dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
 	}
+}
+
+void intel_pm_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
 	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
 			  intel_gen6_powersave_work);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 664118d8c1d6..079ef0129e74 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -968,6 +968,18 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 
 	I915_WRITE(mmio, (u32)ring->status_page.gfx_addr);
 	POSTING_READ(mmio);
+
+	/* Flush the TLB for this page */
+	if (INTEL_INFO(dev)->gen >= 6) {
+		u32 reg = RING_INSTPM(ring->mmio_base);
+		I915_WRITE(reg,
+			   _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
+					      INSTPM_SYNC_FLUSH));
+		if (wait_for((I915_READ(reg) & INSTPM_SYNC_FLUSH) == 0,
+			     1000))
+			DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
+				  ring->name);
+	}
 }
 
 static int
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 251784aa2225..503a414cbdad 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -29,6 +29,7 @@ static void mga_crtc_load_lut(struct drm_crtc *crtc)
 	struct mga_crtc *mga_crtc = to_mga_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct mga_device *mdev = dev->dev_private;
+	struct drm_framebuffer *fb = crtc->fb;
 	int i;
 
 	if (!crtc->enabled)
@@ -36,6 +37,28 @@ static void mga_crtc_load_lut(struct drm_crtc *crtc)
 
 	WREG8(DAC_INDEX + MGA1064_INDEX, 0);
 
+	if (fb && fb->bits_per_pixel == 16) {
+		int inc = (fb->depth == 15) ? 8 : 4;
+		u8 r, b;
+		for (i = 0; i < MGAG200_LUT_SIZE; i += inc) {
+			if (fb->depth == 16) {
+				if (i > (MGAG200_LUT_SIZE >> 1)) {
+					r = b = 0;
+				} else {
+					r = mga_crtc->lut_r[i << 1];
+					b = mga_crtc->lut_b[i << 1];
+				}
+			} else {
+				r = mga_crtc->lut_r[i];
+				b = mga_crtc->lut_b[i];
+			}
+			/* VGA registers */
+			WREG8(DAC_INDEX + MGA1064_COL_PAL, r);
+			WREG8(DAC_INDEX + MGA1064_COL_PAL, mga_crtc->lut_g[i]);
+			WREG8(DAC_INDEX + MGA1064_COL_PAL, b);
+		}
+		return;
+	}
 	for (i = 0; i < MGAG200_LUT_SIZE; i++) {
 		/* VGA registers */
 		WREG8(DAC_INDEX + MGA1064_COL_PAL, mga_crtc->lut_r[i]);
@@ -877,7 +900,7 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc,
 
 	pitch = crtc->fb->pitches[0] / (crtc->fb->bits_per_pixel / 8);
 	if (crtc->fb->bits_per_pixel == 24)
-		pitch = pitch >> (4 - bppshift);
+		pitch = (pitch * 3) >> (4 - bppshift);
 	else
 		pitch = pitch >> (4 - bppshift);
 
@@ -1251,6 +1274,24 @@ static void mga_crtc_destroy(struct drm_crtc *crtc)
 	kfree(mga_crtc);
 }
 
+static void mga_crtc_disable(struct drm_crtc *crtc)
+{
+	int ret;
+	DRM_DEBUG_KMS("\n");
+	mga_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	if (crtc->fb) {
+		struct mga_framebuffer *mga_fb = to_mga_framebuffer(crtc->fb);
+		struct drm_gem_object *obj = mga_fb->obj;
+		struct mgag200_bo *bo = gem_to_mga_bo(obj);
+		ret = mgag200_bo_reserve(bo, false);
+		if (ret)
+			return;
+		mgag200_bo_push_sysram(bo);
+		mgag200_bo_unreserve(bo);
+	}
+	crtc->fb = NULL;
+}
+
 /* These provide the minimum set of functions required to handle a CRTC */
 static const struct drm_crtc_funcs mga_crtc_funcs = {
 	.cursor_set = mga_crtc_cursor_set,
@@ -1261,6 +1302,7 @@ static const struct drm_crtc_funcs mga_crtc_funcs = {
 };
 
 static const struct drm_crtc_helper_funcs mga_helper_funcs = {
+	.disable = mga_crtc_disable,
 	.dpms = mga_crtc_dpms,
 	.mode_fixup = mga_crtc_mode_fixup,
 	.mode_set = mga_crtc_mode_set,
@@ -1581,6 +1623,8 @@ static struct drm_connector *mga_vga_init(struct drm_device *dev)
 
 	drm_connector_helper_add(connector, &mga_vga_connector_helper_funcs);
 
+	drm_sysfs_connector_add(connector);
+
 	mga_connector->i2c = mgag200_i2c_create(dev);
 	if (!mga_connector->i2c)
 		DRM_ERROR("failed to add ddc bus\n");
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 3acb2b044c7b..d70e4a92773b 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -323,6 +323,7 @@ int mgag200_bo_create(struct drm_device *dev, int size, int align,
 
 	mgabo->gem.driver_private = NULL;
 	mgabo->bo.bdev = &mdev->ttm.bdev;
+	mgabo->bo.bdev->dev_mapping = dev->dev_mapping;
 
 	mgag200_ttm_placement(mgabo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
@@ -353,6 +354,7 @@ int mgag200_bo_pin(struct mgag200_bo *bo, u32 pl_flag, u64 *gpu_addr)
 		bo->pin_count++;
 		if (gpu_addr)
 			*gpu_addr = mgag200_bo_gpu_offset(bo);
+		return 0;
 	}
 
 	mgag200_ttm_placement(bo, pl_flag);
diff --git a/drivers/gpu/drm/nouveau/core/core/mm.c b/drivers/gpu/drm/nouveau/core/core/mm.c
index d8291724dbd4..7a4e0891c5f8 100644
--- a/drivers/gpu/drm/nouveau/core/core/mm.c
+++ b/drivers/gpu/drm/nouveau/core/core/mm.c
@@ -98,6 +98,8 @@ nouveau_mm_head(struct nouveau_mm *mm, u8 type, u32 size_max, u32 size_min,
 	u32 splitoff;
 	u32 s, e;
 
+	BUG_ON(!type);
+
 	list_for_each_entry(this, &mm->free, fl_entry) {
 		e = this->offset + this->length;
 		s = this->offset;
@@ -162,6 +164,8 @@ nouveau_mm_tail(struct nouveau_mm *mm, u8 type, u32 size_max, u32 size_min,
 	struct nouveau_mm_node *prev, *this, *next;
 	u32 mask = align - 1;
 
+	BUG_ON(!type);
+
 	list_for_each_entry_reverse(this, &mm->free, fl_entry) {
 		u32 e = this->offset + this->length;
 		u32 s = this->offset;
diff --git a/drivers/gpu/drm/nouveau/core/engine/bsp/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/bsp/nvc0.c
index 262c9f5f5f60..ce860de43e61 100644
--- a/drivers/gpu/drm/nouveau/core/engine/bsp/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/bsp/nvc0.c
@@ -90,6 +90,7 @@ nvc0_bsp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		return ret;
 
 	nv_subdev(priv)->unit = 0x00008000;
+	nv_subdev(priv)->intr = nouveau_falcon_intr;
 	nv_engine(priv)->cclass = &nvc0_bsp_cclass;
 	nv_engine(priv)->sclass = nvc0_bsp_sclass;
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/bsp/nve0.c b/drivers/gpu/drm/nouveau/core/engine/bsp/nve0.c
index c46882c83982..ba6aeca0285e 100644
--- a/drivers/gpu/drm/nouveau/core/engine/bsp/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/bsp/nve0.c
@@ -90,6 +90,7 @@ nve0_bsp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		return ret;
 
 	nv_subdev(priv)->unit = 0x00008000;
+	nv_subdev(priv)->intr = nouveau_falcon_intr;
 	nv_engine(priv)->cclass = &nve0_bsp_cclass;
 	nv_engine(priv)->sclass = nve0_bsp_sclass;
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
index 373dbcc523b2..a19e7d79b847 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
@@ -36,6 +36,8 @@ nva3_hda_eld(struct nv50_disp_priv *priv, int or, u8 *data, u32 size)
 	if (data && data[0]) {
 		for (i = 0; i < size; i++)
 			nv_wr32(priv, 0x61c440 + soff, (i << 8) | data[i]);
+		for (; i < 0x60; i++)
+			nv_wr32(priv, 0x61c440 + soff, (i << 8));
 		nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000003);
 	} else
 	if (data) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
index dc57e24fc1df..717639386ced 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
@@ -41,6 +41,8 @@ nvd0_hda_eld(struct nv50_disp_priv *priv, int or, u8 *data, u32 size)
 	if (data && data[0]) {
 		for (i = 0; i < size; i++)
 			nv_wr32(priv, 0x10ec00 + soff, (i << 8) | data[i]);
+		for (; i < 0x60; i++)
+			nv_wr32(priv, 0x10ec00 + soff, (i << 8));
 		nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000003);
 	} else
 	if (data) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
index ab1e918469a8..526b75242899 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
@@ -47,14 +47,8 @@ int
 nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
 {
 	struct nv50_disp_priv *priv = (void *)object->engine;
-	struct nouveau_bios *bios = nouveau_bios(priv);
-	const u16 type = (mthd & NV50_DISP_SOR_MTHD_TYPE) >> 12;
 	const u8  head = (mthd & NV50_DISP_SOR_MTHD_HEAD) >> 3;
-	const u8  link = (mthd & NV50_DISP_SOR_MTHD_LINK) >> 2;
 	const u8    or = (mthd & NV50_DISP_SOR_MTHD_OR);
-	const u16 mask = (0x0100 << head) | (0x0040 << link) | (0x0001 << or);
-	struct dcb_output outp;
-	u8  ver, hdr;
 	u32 data;
 	int ret = -EINVAL;
 
@@ -62,8 +56,6 @@ nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
 		return -EINVAL;
 	data = *(u32 *)args;
 
-	if (type && !dcb_outp_match(bios, type, mask, &ver, &hdr, &outp))
-		return -ENODEV;
 
 	switch (mthd & ~0x3f) {
 	case NV50_DISP_SOR_PWR:
diff --git a/drivers/gpu/drm/nouveau/core/engine/falcon.c b/drivers/gpu/drm/nouveau/core/engine/falcon.c
index 3c7a31f7590e..e03fc8e4dc1d 100644
--- a/drivers/gpu/drm/nouveau/core/engine/falcon.c
+++ b/drivers/gpu/drm/nouveau/core/engine/falcon.c
@@ -23,6 +23,25 @@
 #include <engine/falcon.h>
 #include <subdev/timer.h>
 
+void
+nouveau_falcon_intr(struct nouveau_subdev *subdev)
+{
+	struct nouveau_falcon *falcon = (void *)subdev;
+	u32 dispatch = nv_ro32(falcon, 0x01c);
+	u32 intr = nv_ro32(falcon, 0x008) & dispatch & ~(dispatch >> 16);
+
+	if (intr & 0x00000010) {
+		nv_debug(falcon, "ucode halted\n");
+		nv_wo32(falcon, 0x004, 0x00000010);
+		intr &= ~0x00000010;
+	}
+
+	if (intr)  {
+		nv_error(falcon, "unhandled intr 0x%08x\n", intr);
+		nv_wo32(falcon, 0x004, intr);
+	}
+}
+
 u32
 _nouveau_falcon_rd32(struct nouveau_object *object, u64 addr)
 {
diff --git a/drivers/gpu/drm/nouveau/core/engine/mpeg/nv31.c b/drivers/gpu/drm/nouveau/core/engine/mpeg/nv31.c
index 49ecbb859b25..c19004301309 100644
--- a/drivers/gpu/drm/nouveau/core/engine/mpeg/nv31.c
+++ b/drivers/gpu/drm/nouveau/core/engine/mpeg/nv31.c
@@ -265,8 +265,8 @@ nv31_mpeg_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 int
 nv31_mpeg_init(struct nouveau_object *object)
 {
-	struct nouveau_engine *engine = nv_engine(object->engine);
-	struct nv31_mpeg_priv *priv = (void *)engine;
+	struct nouveau_engine *engine = nv_engine(object);
+	struct nv31_mpeg_priv *priv = (void *)object;
 	struct nouveau_fb *pfb = nouveau_fb(object);
 	int ret, i;
 
@@ -284,7 +284,10 @@ nv31_mpeg_init(struct nouveau_object *object)
 	/* PMPEG init */
 	nv_wr32(priv, 0x00b32c, 0x00000000);
 	nv_wr32(priv, 0x00b314, 0x00000100);
-	nv_wr32(priv, 0x00b220, nv44_graph_class(priv) ? 0x00000044 : 0x00000031);
+	if (nv_device(priv)->chipset >= 0x40 && nv44_graph_class(priv))
+		nv_wr32(priv, 0x00b220, 0x00000044);
+	else
+		nv_wr32(priv, 0x00b220, 0x00000031);
 	nv_wr32(priv, 0x00b300, 0x02001ec1);
 	nv_mask(priv, 0x00b32c, 0x00000001, 0x00000001);
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/mpeg/nv40.c b/drivers/gpu/drm/nouveau/core/engine/mpeg/nv40.c
index f7c581ad1991..dd6196072e9c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/mpeg/nv40.c
+++ b/drivers/gpu/drm/nouveau/core/engine/mpeg/nv40.c
@@ -61,6 +61,7 @@ nv40_mpeg_context_ctor(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
+	nv_wo32(&chan->base.base, 0x78, 0x02001ec1);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/ppp/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/ppp/nvc0.c
index 98072c1ff360..73719aaa62d6 100644
--- a/drivers/gpu/drm/nouveau/core/engine/ppp/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/ppp/nvc0.c
@@ -90,6 +90,7 @@ nvc0_ppp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		return ret;
 
 	nv_subdev(priv)->unit = 0x00000002;
+	nv_subdev(priv)->intr = nouveau_falcon_intr;
 	nv_engine(priv)->cclass = &nvc0_ppp_cclass;
 	nv_engine(priv)->sclass = nvc0_ppp_sclass;
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/vp/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/vp/nvc0.c
index 1879229b60eb..ac1f62aace72 100644
--- a/drivers/gpu/drm/nouveau/core/engine/vp/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/vp/nvc0.c
@@ -90,6 +90,7 @@ nvc0_vp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		return ret;
 
 	nv_subdev(priv)->unit = 0x00020000;
+	nv_subdev(priv)->intr = nouveau_falcon_intr;
 	nv_engine(priv)->cclass = &nvc0_vp_cclass;
 	nv_engine(priv)->sclass = nvc0_vp_sclass;
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/vp/nve0.c b/drivers/gpu/drm/nouveau/core/engine/vp/nve0.c
index d28ecbf7bc49..d4c3108479c9 100644
--- a/drivers/gpu/drm/nouveau/core/engine/vp/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/vp/nve0.c
@@ -90,6 +90,7 @@ nve0_vp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		return ret;
 
 	nv_subdev(priv)->unit = 0x00020000;
+	nv_subdev(priv)->intr = nouveau_falcon_intr;
 	nv_engine(priv)->cclass = &nve0_vp_cclass;
 	nv_engine(priv)->sclass = nve0_vp_sclass;
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/xtensa.c b/drivers/gpu/drm/nouveau/core/engine/xtensa.c
index 0639bc59d0a5..5f6ede7c4892 100644
--- a/drivers/gpu/drm/nouveau/core/engine/xtensa.c
+++ b/drivers/gpu/drm/nouveau/core/engine/xtensa.c
@@ -118,7 +118,13 @@ _nouveau_xtensa_init(struct nouveau_object *object)
 			return ret;
 		}
 
-		ret = nouveau_gpuobj_new(object, NULL, fw->size, 0x1000, 0,
+		if (fw->size > 0x40000) {
+			nv_warn(xtensa, "firmware %s too large\n", name);
+			release_firmware(fw);
+			return -EINVAL;
+		}
+
+		ret = nouveau_gpuobj_new(object, NULL, 0x40000, 0x1000, 0,
 					 &xtensa->gpu_fw);
 		if (ret) {
 			release_firmware(fw);
diff --git a/drivers/gpu/drm/nouveau/core/include/engine/falcon.h b/drivers/gpu/drm/nouveau/core/include/engine/falcon.h
index 1edec386ab36..181aa7da524d 100644
--- a/drivers/gpu/drm/nouveau/core/include/engine/falcon.h
+++ b/drivers/gpu/drm/nouveau/core/include/engine/falcon.h
@@ -72,6 +72,8 @@ int nouveau_falcon_create_(struct nouveau_object *, struct nouveau_object *,
 			   struct nouveau_oclass *, u32, bool, const char *,
 			   const char *, int, void **);
 
+void nouveau_falcon_intr(struct nouveau_subdev *subdev);
+
 #define _nouveau_falcon_dtor _nouveau_engine_dtor
 int  _nouveau_falcon_init(struct nouveau_object *);
 int  _nouveau_falcon_fini(struct nouveau_object *, bool);
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
index d5502267c30f..9d2cd2006250 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
@@ -20,8 +20,8 @@ nouveau_mc(void *obj)
 	return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_MC];
 }
 
-#define nouveau_mc_create(p,e,o,d)                                             \
-	nouveau_mc_create_((p), (e), (o), sizeof(**d), (void **)d)
+#define nouveau_mc_create(p,e,o,m,d)                                           \
+	nouveau_mc_create_((p), (e), (o), (m), sizeof(**d), (void **)d)
 #define nouveau_mc_destroy(p) ({                                               \
 	struct nouveau_mc *pmc = (p); _nouveau_mc_dtor(nv_object(pmc));        \
 })
@@ -33,7 +33,8 @@ nouveau_mc(void *obj)
 })
 
 int  nouveau_mc_create_(struct nouveau_object *, struct nouveau_object *,
-			struct nouveau_oclass *, int, void **);
+			struct nouveau_oclass *, const struct nouveau_mc_intr *,
+			int, void **);
 void _nouveau_mc_dtor(struct nouveau_object *);
 int  _nouveau_mc_init(struct nouveau_object *);
 int  _nouveau_mc_fini(struct nouveau_object *, bool);
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/vm.h b/drivers/gpu/drm/nouveau/core/include/subdev/vm.h
index f2e87b105666..fcf57fa309bf 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/vm.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/vm.h
@@ -55,7 +55,7 @@ struct nouveau_vma {
 struct nouveau_vm {
 	struct nouveau_vmmgr *vmm;
 	struct nouveau_mm mm;
-	int refcount;
+	struct kref refcount;
 
 	struct list_head pgd_list;
 	atomic_t engref[NVDEV_SUBDEV_NR];
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
index 6c974dd83e8b..db9d6ddde52c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
@@ -81,7 +81,7 @@ void nv44_fb_tile_prog(struct nouveau_fb *, int, struct nouveau_fb_tile *);
 void nv46_fb_tile_init(struct nouveau_fb *, int i, u32 addr, u32 size,
 		       u32 pitch, u32 flags, struct nouveau_fb_tile *);
 
-void nv50_ram_put(struct nouveau_fb *, struct nouveau_mem **);
+void __nv50_ram_put(struct nouveau_fb *, struct nouveau_mem *);
 extern int nv50_fb_memtype[0x80];
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv49.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv49.c
index 19e3a9a63a02..ab7ef0ac9e34 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv49.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv49.c
@@ -40,15 +40,15 @@ nv49_ram_create(struct nouveau_object *parent, struct nouveau_object *engine,
 		return ret;
 
 	switch (pfb914 & 0x00000003) {
-	case 0x00000000: pfb->ram->type = NV_MEM_TYPE_DDR1; break;
-	case 0x00000001: pfb->ram->type = NV_MEM_TYPE_DDR2; break;
-	case 0x00000002: pfb->ram->type = NV_MEM_TYPE_GDDR3; break;
+	case 0x00000000: ram->type = NV_MEM_TYPE_DDR1; break;
+	case 0x00000001: ram->type = NV_MEM_TYPE_DDR2; break;
+	case 0x00000002: ram->type = NV_MEM_TYPE_GDDR3; break;
 	case 0x00000003: break;
 	}
 
-	pfb->ram->size  =  nv_rd32(pfb, 0x10020c) & 0xff000000;
-	pfb->ram->parts = (nv_rd32(pfb, 0x100200) & 0x00000003) + 1;
-	pfb->ram->tags  =  nv_rd32(pfb, 0x100320);
+	ram->size  =  nv_rd32(pfb, 0x10020c) & 0xff000000;
+	ram->parts = (nv_rd32(pfb, 0x100200) & 0x00000003) + 1;
+	ram->tags  =  nv_rd32(pfb, 0x100320);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv4e.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv4e.c
index 7192aa6e5577..63a6aab86028 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv4e.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv4e.c
@@ -38,8 +38,8 @@ nv4e_ram_create(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
-	pfb->ram->size = nv_rd32(pfb, 0x10020c) & 0xff000000;
-	pfb->ram->type = NV_MEM_TYPE_STOLEN;
+	ram->size = nv_rd32(pfb, 0x10020c) & 0xff000000;
+	ram->type = NV_MEM_TYPE_STOLEN;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
index af5aa7ee8ad9..903baff77fdd 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
@@ -27,17 +27,10 @@
 #include "priv.h"
 
 void
-nv50_ram_put(struct nouveau_fb *pfb, struct nouveau_mem **pmem)
+__nv50_ram_put(struct nouveau_fb *pfb, struct nouveau_mem *mem)
 {
 	struct nouveau_mm_node *this;
-	struct nouveau_mem *mem;
 
-	mem = *pmem;
-	*pmem = NULL;
-	if (unlikely(mem == NULL))
-		return;
-
-	mutex_lock(&pfb->base.mutex);
 	while (!list_empty(&mem->regions)) {
 		this = list_first_entry(&mem->regions, typeof(*this), rl_entry);
 
@@ -46,6 +39,19 @@ nv50_ram_put(struct nouveau_fb *pfb, struct nouveau_mem **pmem)
 	}
 
 	nouveau_mm_free(&pfb->tags, &mem->tag);
+}
+
+void
+nv50_ram_put(struct nouveau_fb *pfb, struct nouveau_mem **pmem)
+{
+	struct nouveau_mem *mem = *pmem;
+
+	*pmem = NULL;
+	if (unlikely(mem == NULL))
+		return;
+
+	mutex_lock(&pfb->base.mutex);
+	__nv50_ram_put(pfb, mem);
 	mutex_unlock(&pfb->base.mutex);
 
 	kfree(mem);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
index 9c3634acbb9d..cf97c4de4a6b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
@@ -33,11 +33,19 @@ void
 nvc0_ram_put(struct nouveau_fb *pfb, struct nouveau_mem **pmem)
 {
 	struct nouveau_ltcg *ltcg = nouveau_ltcg(pfb);
+	struct nouveau_mem *mem = *pmem;
 
-	if ((*pmem)->tag)
-		ltcg->tags_free(ltcg, &(*pmem)->tag);
+	*pmem = NULL;
+	if (unlikely(mem == NULL))
+		return;
 
-	nv50_ram_put(pfb, pmem);
+	mutex_lock(&pfb->base.mutex);
+	if (mem->tag)
+		ltcg->tags_free(ltcg, &mem->tag);
+	__nv50_ram_put(pfb, mem);
+	mutex_unlock(&pfb->base.mutex);
+
+	kfree(mem);
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c
index bf489dcf46e2..c4c1d415e7fe 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c
@@ -103,7 +103,7 @@ nv50_gpio_intr(struct nouveau_subdev *subdev)
 	int i;
 
 	intr0 = nv_rd32(priv, 0xe054) & nv_rd32(priv, 0xe050);
-	if (nv_device(priv)->chipset >= 0x90)
+	if (nv_device(priv)->chipset > 0x92)
 		intr1 = nv_rd32(priv, 0xe074) & nv_rd32(priv, 0xe070);
 
 	hi = (intr0 & 0x0000ffff) | (intr1 << 16);
@@ -115,7 +115,7 @@ nv50_gpio_intr(struct nouveau_subdev *subdev)
 	}
 
 	nv_wr32(priv, 0xe054, intr0);
-	if (nv_device(priv)->chipset >= 0x90)
+	if (nv_device(priv)->chipset > 0x92)
 		nv_wr32(priv, 0xe074, intr1);
 }
 
@@ -146,7 +146,7 @@ nv50_gpio_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_gpio_create(parent, engine, oclass,
-				  nv_device(parent)->chipset >= 0x90 ? 32 : 16,
+				  nv_device(parent)->chipset > 0x92 ? 32 : 16,
 				  &priv);
 	*pobject = nv_object(priv);
 	if (ret)
@@ -182,7 +182,7 @@ nv50_gpio_init(struct nouveau_object *object)
 	/* disable, and ack any pending gpio interrupts */
 	nv_wr32(priv, 0xe050, 0x00000000);
 	nv_wr32(priv, 0xe054, 0xffffffff);
-	if (nv_device(priv)->chipset >= 0x90) {
+	if (nv_device(priv)->chipset > 0x92) {
 		nv_wr32(priv, 0xe070, 0x00000000);
 		nv_wr32(priv, 0xe074, 0xffffffff);
 	}
@@ -195,7 +195,7 @@ nv50_gpio_fini(struct nouveau_object *object, bool suspend)
 {
 	struct nv50_gpio_priv *priv = (void *)object;
 	nv_wr32(priv, 0xe050, 0x00000000);
-	if (nv_device(priv)->chipset >= 0x90)
+	if (nv_device(priv)->chipset > 0x92)
 		nv_wr32(priv, 0xe070, 0x00000000);
 	return nouveau_gpio_fini(&priv->base, suspend);
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c
index bcca883018f4..cce65cc56514 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c
@@ -30,8 +30,9 @@ struct nvc0_ltcg_priv {
 	struct nouveau_ltcg base;
 	u32 part_nr;
 	u32 subp_nr;
-	struct nouveau_mm tags;
 	u32 num_tags;
+	u32 tag_base;
+	struct nouveau_mm tags;
 	struct nouveau_mm_node *tag_ram;
 };
 
@@ -117,10 +118,6 @@ nvc0_ltcg_init_tag_ram(struct nouveau_fb *pfb, struct nvc0_ltcg_priv *priv)
 	u32 tag_size, tag_margin, tag_align;
 	int ret;
 
-	nv_wr32(priv, 0x17e8d8, priv->part_nr);
-	if (nv_device(pfb)->card_type >= NV_E0)
-		nv_wr32(priv, 0x17e000, priv->part_nr);
-
 	/* tags for 1/4 of VRAM should be enough (8192/4 per GiB of VRAM) */
 	priv->num_tags = (pfb->ram->size >> 17) / 4;
 	if (priv->num_tags > (1 << 17))
@@ -142,7 +139,7 @@ nvc0_ltcg_init_tag_ram(struct nouveau_fb *pfb, struct nvc0_ltcg_priv *priv)
 	tag_size += tag_align;
 	tag_size  = (tag_size + 0xfff) >> 12; /* round up */
 
-	ret = nouveau_mm_tail(&pfb->vram, 0, tag_size, tag_size, 1,
+	ret = nouveau_mm_tail(&pfb->vram, 1, tag_size, tag_size, 1,
 	                      &priv->tag_ram);
 	if (ret) {
 		priv->num_tags = 0;
@@ -152,7 +149,7 @@ nvc0_ltcg_init_tag_ram(struct nouveau_fb *pfb, struct nvc0_ltcg_priv *priv)
 		tag_base += tag_align - 1;
 		ret = do_div(tag_base, tag_align);
 
-		nv_wr32(priv, 0x17e8d4, tag_base);
+		priv->tag_base = tag_base;
 	}
 	ret = nouveau_mm_init(&priv->tags, 0, priv->num_tags, 1);
 
@@ -182,8 +179,6 @@ nvc0_ltcg_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	}
 	priv->subp_nr = nv_rd32(priv, 0x17e8dc) >> 28;
 
-	nv_mask(priv, 0x17e820, 0x00100000, 0x00000000); /* INTR_EN &= ~0x10 */
-
 	ret = nvc0_ltcg_init_tag_ram(pfb, priv);
 	if (ret)
 		return ret;
@@ -209,13 +204,32 @@ nvc0_ltcg_dtor(struct nouveau_object *object)
 	nouveau_ltcg_destroy(ltcg);
 }
 
+static int
+nvc0_ltcg_init(struct nouveau_object *object)
+{
+	struct nouveau_ltcg *ltcg = (struct nouveau_ltcg *)object;
+	struct nvc0_ltcg_priv *priv = (struct nvc0_ltcg_priv *)ltcg;
+	int ret;
+
+	ret = nouveau_ltcg_init(ltcg);
+	if (ret)
+		return ret;
+
+	nv_mask(priv, 0x17e820, 0x00100000, 0x00000000); /* INTR_EN &= ~0x10 */
+	nv_wr32(priv, 0x17e8d8, priv->part_nr);
+	if (nv_device(ltcg)->card_type >= NV_E0)
+		nv_wr32(priv, 0x17e000, priv->part_nr);
+	nv_wr32(priv, 0x17e8d4, priv->tag_base);
+	return 0;
+}
+
 struct nouveau_oclass
 nvc0_ltcg_oclass = {
 	.handle = NV_SUBDEV(LTCG, 0xc0),
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nvc0_ltcg_ctor,
 		.dtor = nvc0_ltcg_dtor,
-		.init = _nouveau_ltcg_init,
+		.init = nvc0_ltcg_init,
 		.fini = _nouveau_ltcg_fini,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
index 1c0330b8c9a4..ec9cd6f10f91 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
@@ -80,7 +80,9 @@ _nouveau_mc_dtor(struct nouveau_object *object)
 
 int
 nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine,
-		   struct nouveau_oclass *oclass, int length, void **pobject)
+		   struct nouveau_oclass *oclass,
+		   const struct nouveau_mc_intr *intr_map,
+		   int length, void **pobject)
 {
 	struct nouveau_device *device = nv_device(parent);
 	struct nouveau_mc *pmc;
@@ -92,6 +94,8 @@ nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	pmc->intr_map = intr_map;
+
 	ret = request_irq(device->pdev->irq, nouveau_mc_intr,
 			  IRQF_SHARED, "nouveau", pmc);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c
index 8c769715227b..64aa4edb0d9d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c
@@ -50,12 +50,11 @@ nv04_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv04_mc_priv *priv;
 	int ret;
 
-	ret = nouveau_mc_create(parent, engine, oclass, &priv);
+	ret = nouveau_mc_create(parent, engine, oclass, nv04_mc_intr, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	priv->base.intr_map = nv04_mc_intr;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
index 51919371810f..d9891782bf28 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
@@ -36,12 +36,11 @@ nv44_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv44_mc_priv *priv;
 	int ret;
 
-	ret = nouveau_mc_create(parent, engine, oclass, &priv);
+	ret = nouveau_mc_create(parent, engine, oclass, nv04_mc_intr, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	priv->base.intr_map = nv04_mc_intr;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
index 0cb322a5e72c..2b1afe225db8 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
@@ -41,7 +41,7 @@ nv50_mc_intr[] = {
 	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
-	{ 0x0000d101, NVDEV_SUBDEV_FB },
+	{ 0x0002d101, NVDEV_SUBDEV_FB },
 	{},
 };
 
@@ -53,12 +53,11 @@ nv50_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv50_mc_priv *priv;
 	int ret;
 
-	ret = nouveau_mc_create(parent, engine, oclass, &priv);
+	ret = nouveau_mc_create(parent, engine, oclass, nv50_mc_intr, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	priv->base.intr_map = nv50_mc_intr;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
index e82fd21b5041..0d57b4d3e001 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
@@ -54,12 +54,11 @@ nv98_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv98_mc_priv *priv;
 	int ret;
 
-	ret = nouveau_mc_create(parent, engine, oclass, &priv);
+	ret = nouveau_mc_create(parent, engine, oclass, nv98_mc_intr, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	priv->base.intr_map = nv98_mc_intr;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
index c5da3babbc62..104175c5a2dd 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
@@ -57,12 +57,11 @@ nvc0_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nvc0_mc_priv *priv;
 	int ret;
 
-	ret = nouveau_mc_create(parent, engine, oclass, &priv);
+	ret = nouveau_mc_create(parent, engine, oclass, nvc0_mc_intr, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	priv->base.intr_map = nvc0_mc_intr;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
index 67fcb6c852ac..ef3133e7575c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
@@ -361,7 +361,7 @@ nouveau_vm_create(struct nouveau_vmmgr *vmm, u64 offset, u64 length,
 
 	INIT_LIST_HEAD(&vm->pgd_list);
 	vm->vmm = vmm;
-	vm->refcount = 1;
+	kref_init(&vm->refcount);
 	vm->fpde = offset >> (vmm->pgt_bits + 12);
 	vm->lpde = (offset + length - 1) >> (vmm->pgt_bits + 12);
 
@@ -441,8 +441,9 @@ nouveau_vm_unlink(struct nouveau_vm *vm, struct nouveau_gpuobj *mpgd)
 }
 
 static void
-nouveau_vm_del(struct nouveau_vm *vm)
+nouveau_vm_del(struct kref *kref)
 {
+	struct nouveau_vm *vm = container_of(kref, typeof(*vm), refcount);
 	struct nouveau_vm_pgd *vpgd, *tmp;
 
 	list_for_each_entry_safe(vpgd, tmp, &vm->pgd_list, head) {
@@ -458,27 +459,19 @@ int
 nouveau_vm_ref(struct nouveau_vm *ref, struct nouveau_vm **ptr,
 	       struct nouveau_gpuobj *pgd)
 {
-	struct nouveau_vm *vm;
-	int ret;
-
-	vm = ref;
-	if (vm) {
-		ret = nouveau_vm_link(vm, pgd);
+	if (ref) {
+		int ret = nouveau_vm_link(ref, pgd);
 		if (ret)
 			return ret;
 
-		vm->refcount++;
+		kref_get(&ref->refcount);
 	}
 
-	vm = *ptr;
-	*ptr = ref;
-
-	if (vm) {
-		nouveau_vm_unlink(vm, pgd);
-
-		if (--vm->refcount == 0)
-			nouveau_vm_del(vm);
+	if (*ptr) {
+		nouveau_vm_unlink(*ptr, pgd);
+		kref_put(&(*ptr)->refcount, nouveau_vm_del);
 	}
 
+	*ptr = ref;
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index 0782bd2f1e04..6a13ffb53bdb 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -606,6 +606,24 @@ nv_crtc_mode_set_regs(struct drm_crtc *crtc, struct drm_display_mode * mode)
 	regp->ramdac_a34 = 0x1;
 }
 
+static int
+nv_crtc_swap_fbs(struct drm_crtc *crtc, struct drm_framebuffer *old_fb)
+{
+	struct nv04_display *disp = nv04_display(crtc->dev);
+	struct nouveau_framebuffer *nvfb = nouveau_framebuffer(crtc->fb);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
+	int ret;
+
+	ret = nouveau_bo_pin(nvfb->nvbo, TTM_PL_FLAG_VRAM);
+	if (ret == 0) {
+		if (disp->image[nv_crtc->index])
+			nouveau_bo_unpin(disp->image[nv_crtc->index]);
+		nouveau_bo_ref(nvfb->nvbo, &disp->image[nv_crtc->index]);
+	}
+
+	return ret;
+}
+
 /**
  * Sets up registers for the given mode/adjusted_mode pair.
  *
@@ -622,10 +640,15 @@ nv_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode,
 	struct drm_device *dev = crtc->dev;
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 	struct nouveau_drm *drm = nouveau_drm(dev);
+	int ret;
 
 	NV_DEBUG(drm, "CTRC mode on CRTC %d:\n", nv_crtc->index);
 	drm_mode_debug_printmodeline(adjusted_mode);
 
+	ret = nv_crtc_swap_fbs(crtc, old_fb);
+	if (ret)
+		return ret;
+
 	/* unlock must come after turning off FP_TG_CONTROL in output_prepare */
 	nv_lock_vga_crtc_shadow(dev, nv_crtc->index, -1);
 
@@ -722,6 +745,7 @@ static void nv_crtc_commit(struct drm_crtc *crtc)
 
 static void nv_crtc_destroy(struct drm_crtc *crtc)
 {
+	struct nv04_display *disp = nv04_display(crtc->dev);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 
 	if (!nv_crtc)
@@ -729,6 +753,10 @@ static void nv_crtc_destroy(struct drm_crtc *crtc)
 
 	drm_crtc_cleanup(crtc);
 
+	if (disp->image[nv_crtc->index])
+		nouveau_bo_unpin(disp->image[nv_crtc->index]);
+	nouveau_bo_ref(NULL, &disp->image[nv_crtc->index]);
+
 	nouveau_bo_unmap(nv_crtc->cursor.nvbo);
 	nouveau_bo_unpin(nv_crtc->cursor.nvbo);
 	nouveau_bo_ref(NULL, &nv_crtc->cursor.nvbo);
@@ -754,6 +782,16 @@ nv_crtc_gamma_load(struct drm_crtc *crtc)
 }
 
 static void
+nv_crtc_disable(struct drm_crtc *crtc)
+{
+	struct nv04_display *disp = nv04_display(crtc->dev);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
+	if (disp->image[nv_crtc->index])
+		nouveau_bo_unpin(disp->image[nv_crtc->index]);
+	nouveau_bo_ref(NULL, &disp->image[nv_crtc->index]);
+}
+
+static void
 nv_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b, uint32_t start,
 		  uint32_t size)
 {
@@ -791,7 +829,6 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc,
 	struct drm_framebuffer *drm_fb;
 	struct nouveau_framebuffer *fb;
 	int arb_burst, arb_lwm;
-	int ret;
 
 	NV_DEBUG(drm, "index %d\n", nv_crtc->index);
 
@@ -801,10 +838,8 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-
 	/* If atomic, we want to switch to the fb we were passed, so
-	 * now we update pointers to do that.  (We don't pin; just
-	 * assume we're already pinned and update the base address.)
+	 * now we update pointers to do that.
 	 */
 	if (atomic) {
 		drm_fb = passed_fb;
@@ -812,17 +847,6 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc,
 	} else {
 		drm_fb = crtc->fb;
 		fb = nouveau_framebuffer(crtc->fb);
-		/* If not atomic, we can go ahead and pin, and unpin the
-		 * old fb we were passed.
-		 */
-		ret = nouveau_bo_pin(fb->nvbo, TTM_PL_FLAG_VRAM);
-		if (ret)
-			return ret;
-
-		if (passed_fb) {
-			struct nouveau_framebuffer *ofb = nouveau_framebuffer(passed_fb);
-			nouveau_bo_unpin(ofb->nvbo);
-		}
 	}
 
 	nv_crtc->fb.offset = fb->nvbo->bo.offset;
@@ -877,6 +901,9 @@ static int
 nv04_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
 			struct drm_framebuffer *old_fb)
 {
+	int ret = nv_crtc_swap_fbs(crtc, old_fb);
+	if (ret)
+		return ret;
 	return nv04_crtc_do_mode_set_base(crtc, old_fb, x, y, false);
 }
 
@@ -1027,6 +1054,7 @@ static const struct drm_crtc_helper_funcs nv04_crtc_helper_funcs = {
 	.mode_set_base = nv04_crtc_mode_set_base,
 	.mode_set_base_atomic = nv04_crtc_mode_set_base_atomic,
 	.load_lut = nv_crtc_gamma_load,
+	.disable = nv_crtc_disable,
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.h b/drivers/gpu/drm/nouveau/dispnv04/disp.h
index a0a031dad13f..9928187f0a7d 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.h
@@ -81,6 +81,7 @@ struct nv04_display {
 	uint32_t saved_vga_font[4][16384];
 	uint32_t dac_users[4];
 	struct nouveau_object *core;
+	struct nouveau_bo *image[2];
 };
 
 static inline struct nv04_display *
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 4b1afb131380..af20fba3a1a4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -148,6 +148,7 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
 
 	if (unlikely(nvbo->gem))
 		DRM_ERROR("bo %p still attached to GEM object\n", bo);
+	WARN_ON(nvbo->pin_refcnt > 0);
 	nv10_bo_put_tile_region(dev, nvbo->tile, NULL);
 	kfree(nvbo);
 }
@@ -197,6 +198,17 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 	size_t acc_size;
 	int ret;
 	int type = ttm_bo_type_device;
+	int lpg_shift = 12;
+	int max_size;
+
+	if (drm->client.base.vm)
+		lpg_shift = drm->client.base.vm->vmm->lpg_shift;
+	max_size = INT_MAX & ~((1 << lpg_shift) - 1);
+
+	if (size <= 0 || size > max_size) {
+		nv_warn(drm, "skipped size %x\n", (u32)size);
+		return -EINVAL;
+	}
 
 	if (sg)
 		type = ttm_bo_type_sg;
@@ -340,13 +352,15 @@ nouveau_bo_unpin(struct nouveau_bo *nvbo)
 {
 	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	struct ttm_buffer_object *bo = &nvbo->bo;
-	int ret;
+	int ret, ref;
 
 	ret = ttm_bo_reserve(bo, false, false, false, 0);
 	if (ret)
 		return ret;
 
-	if (--nvbo->pin_refcnt)
+	ref = --nvbo->pin_refcnt;
+	WARN_ON_ONCE(ref < 0);
+	if (ref)
 		goto out;
 
 	nouveau_bo_placement_set(nvbo, bo->mem.placement, 0);
@@ -578,7 +592,7 @@ nve0_bo_move_init(struct nouveau_channel *chan, u32 handle)
 	int ret = RING_SPACE(chan, 2);
 	if (ret == 0) {
 		BEGIN_NVC0(chan, NvSubCopy, 0x0000, 1);
-		OUT_RING  (chan, handle);
+		OUT_RING  (chan, handle & 0x0000ffff);
 		FIRE_RING (chan);
 	}
 	return ret;
@@ -973,7 +987,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	int ret;
 
-	mutex_lock(&chan->cli->mutex);
+	mutex_lock_nested(&chan->cli->mutex, SINGLE_DEPTH_NESTING);
 
 	/* create temporary vmas for the transfer and attach them to the
 	 * old nouveau_mem node, these will get cleaned up after ttm has
@@ -1014,7 +1028,7 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 			    struct ttm_mem_reg *, struct ttm_mem_reg *);
 		int (*init)(struct nouveau_channel *, u32 handle);
 	} _methods[] = {
-		{  "COPY", 0, 0xa0b5, nve0_bo_move_copy, nve0_bo_move_init },
+		{  "COPY", 4, 0xa0b5, nve0_bo_move_copy, nve0_bo_move_init },
 		{  "GRCE", 0, 0xa0b5, nve0_bo_move_copy, nvc0_bo_move_init },
 		{ "COPY1", 5, 0x90b8, nvc0_bo_move_copy, nvc0_bo_move_init },
 		{ "COPY0", 4, 0x90b5, nvc0_bo_move_copy, nvc0_bo_move_init },
@@ -1034,7 +1048,7 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 		struct nouveau_channel *chan;
 		u32 handle = (mthd->engine << 16) | mthd->oclass;
 
-		if (mthd->init == nve0_bo_move_init)
+		if (mthd->engine)
 			chan = drm->cechan;
 		else
 			chan = drm->channel;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 708b2d1c0037..a03e75deacaf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -138,7 +138,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev,
 {
 	struct nouveau_framebuffer *nouveau_fb;
 	struct drm_gem_object *gem;
-	int ret;
+	int ret = -ENOMEM;
 
 	gem = drm_gem_object_lookup(dev, file_priv, mode_cmd->handles[0]);
 	if (!gem)
@@ -146,15 +146,19 @@ nouveau_user_framebuffer_create(struct drm_device *dev,
 
 	nouveau_fb = kzalloc(sizeof(struct nouveau_framebuffer), GFP_KERNEL);
 	if (!nouveau_fb)
-		return ERR_PTR(-ENOMEM);
+		goto err_unref;
 
 	ret = nouveau_framebuffer_init(dev, nouveau_fb, mode_cmd, nouveau_gem_object(gem));
-	if (ret) {
-		drm_gem_object_unreference(gem);
-		return ERR_PTR(ret);
-	}
+	if (ret)
+		goto err;
 
 	return &nouveau_fb->base;
+
+err:
+	kfree(nouveau_fb);
+err_unref:
+	drm_gem_object_unreference(gem);
+	return ERR_PTR(ret);
 }
 
 static const struct drm_mode_config_funcs nouveau_mode_config_funcs = {
@@ -524,9 +528,12 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	struct nouveau_page_flip_state *s;
 	struct nouveau_channel *chan = NULL;
 	struct nouveau_fence *fence;
-	struct list_head res;
-	struct ttm_validate_buffer res_val[2];
+	struct ttm_validate_buffer resv[2] = {
+		{ .bo = &old_bo->bo },
+		{ .bo = &new_bo->bo },
+	};
 	struct ww_acquire_ctx ticket;
+	LIST_HEAD(res);
 	int ret;
 
 	if (!drm->channel)
@@ -545,27 +552,19 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		chan = drm->channel;
 	spin_unlock(&old_bo->bo.bdev->fence_lock);
 
-	mutex_lock(&chan->cli->mutex);
-
 	if (new_bo != old_bo) {
 		ret = nouveau_bo_pin(new_bo, TTM_PL_FLAG_VRAM);
-		if (likely(!ret)) {
-			res_val[0].bo = &old_bo->bo;
-			res_val[1].bo = &new_bo->bo;
-			INIT_LIST_HEAD(&res);
-			list_add_tail(&res_val[0].head, &res);
-			list_add_tail(&res_val[1].head, &res);
-			ret = ttm_eu_reserve_buffers(&ticket, &res);
-			if (ret)
-				nouveau_bo_unpin(new_bo);
-		}
-	} else
-		ret = ttm_bo_reserve(&new_bo->bo, false, false, false, 0);
+		if (ret)
+			goto fail_free;
 
-	if (ret) {
-		mutex_unlock(&chan->cli->mutex);
-		goto fail_free;
+		list_add(&resv[1].head, &res);
 	}
+	list_add(&resv[0].head, &res);
+
+	mutex_lock(&chan->cli->mutex);
+	ret = ttm_eu_reserve_buffers(&ticket, &res);
+	if (ret)
+		goto fail_unpin;
 
 	/* Initialize a page flip struct */
 	*s = (struct nouveau_page_flip_state)
@@ -576,10 +575,11 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	/* Emit a page flip */
 	if (nv_device(drm->device)->card_type >= NV_50) {
 		ret = nv50_display_flip_next(crtc, fb, chan, 0);
-		if (ret) {
-			mutex_unlock(&chan->cli->mutex);
+		if (ret)
 			goto fail_unreserve;
-		}
+	} else {
+		struct nv04_display *dispnv04 = nv04_display(dev);
+		nouveau_bo_ref(new_bo, &dispnv04->image[nouveau_crtc(crtc)->index]);
 	}
 
 	ret = nouveau_page_flip_emit(chan, old_bo, new_bo, s, &fence);
@@ -590,22 +590,18 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	/* Update the crtc struct and cleanup */
 	crtc->fb = fb;
 
-	if (old_bo != new_bo) {
-		ttm_eu_fence_buffer_objects(&ticket, &res, fence);
+	ttm_eu_fence_buffer_objects(&ticket, &res, fence);
+	if (old_bo != new_bo)
 		nouveau_bo_unpin(old_bo);
-	} else {
-		nouveau_bo_fence(new_bo, fence);
-		ttm_bo_unreserve(&new_bo->bo);
-	}
 	nouveau_fence_unref(&fence);
 	return 0;
 
 fail_unreserve:
-	if (old_bo != new_bo) {
-		ttm_eu_backoff_reservation(&ticket, &res);
+	ttm_eu_backoff_reservation(&ticket, &res);
+fail_unpin:
+	mutex_unlock(&chan->cli->mutex);
+	if (old_bo != new_bo)
 		nouveau_bo_unpin(new_bo);
-	} else
-		ttm_bo_unreserve(&new_bo->bo);
 fail_free:
 	kfree(s);
 	return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 218a4b522fe5..61972668fd05 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -192,6 +192,18 @@ nouveau_accel_init(struct nouveau_drm *drm)
 
 		arg0 = NVE0_CHANNEL_IND_ENGINE_GR;
 		arg1 = 1;
+	} else
+	if (device->chipset >= 0xa3 &&
+	    device->chipset != 0xaa &&
+	    device->chipset != 0xac) {
+		ret = nouveau_channel_new(drm, &drm->client, NVDRM_DEVICE,
+					  NVDRM_CHAN + 1, NvDmaFB, NvDmaTT,
+					  &drm->cechan);
+		if (ret)
+			NV_ERROR(drm, "failed to create ce channel, %d\n", ret);
+
+		arg0 = NvDmaFB;
+		arg1 = NvDmaTT;
 	} else {
 		arg0 = NvDmaFB;
 		arg1 = NvDmaTT;
@@ -284,8 +296,6 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	return 0;
 }
 
-static struct lock_class_key drm_client_lock_class_key;
-
 static int
 nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 {
@@ -297,7 +307,6 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 	ret = nouveau_cli_create(pdev, "DRM", sizeof(*drm), (void**)&drm);
 	if (ret)
 		return ret;
-	lockdep_set_class(&drm->client.mutex, &drm_client_lock_class_key);
 
 	dev->dev_private = drm;
 	drm->dev = dev;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 9352010030e9..8f6d63d7edd3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -385,6 +385,7 @@ out_unlock:
 	mutex_unlock(&dev->struct_mutex);
 	if (chan)
 		nouveau_bo_vma_del(nvbo, &fbcon->nouveau_fb.vma);
+	nouveau_bo_unmap(nvbo);
 out_unpin:
 	nouveau_bo_unpin(nvbo);
 out_unref:
@@ -397,7 +398,8 @@ void
 nouveau_fbcon_output_poll_changed(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	drm_fb_helper_hotplug_event(&drm->fbcon->helper);
+	if (drm->fbcon)
+		drm_fb_helper_hotplug_event(&drm->fbcon->helper);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 1680d9187bab..be3149932c2d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -143,7 +143,7 @@ nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan)
 	int ret;
 
 	fence->channel  = chan;
-	fence->timeout  = jiffies + (3 * DRM_HZ);
+	fence->timeout  = jiffies + (15 * DRM_HZ);
 	fence->sequence = ++fctx->sequence;
 
 	ret = fctx->emit(fence);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index e72d09c068a8..830cb7bad922 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -50,12 +50,6 @@ nouveau_gem_object_del(struct drm_gem_object *gem)
 		return;
 	nvbo->gem = NULL;
 
-	/* Lockdep hates you for doing reserve with gem object lock held */
-	if (WARN_ON_ONCE(nvbo->pin_refcnt)) {
-		nvbo->pin_refcnt = 1;
-		nouveau_bo_unpin(nvbo);
-	}
-
 	if (gem->import_attach)
 		drm_prime_gem_destroy(gem, nvbo->bo.sg);
 
diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c
index 8e47a9bae8c3..22aa9963ea6f 100644
--- a/drivers/gpu/drm/nouveau/nv17_fence.c
+++ b/drivers/gpu/drm/nouveau/nv17_fence.c
@@ -76,7 +76,7 @@ nv17_fence_context_new(struct nouveau_channel *chan)
 	struct ttm_mem_reg *mem = &priv->bo->bo.mem;
 	struct nouveau_object *object;
 	u32 start = mem->start * PAGE_SIZE;
-	u32 limit = mem->start + mem->size - 1;
+	u32 limit = start + mem->size - 1;
 	int ret = 0;
 
 	fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL);
diff --git a/drivers/gpu/drm/nouveau/nv40_pm.c b/drivers/gpu/drm/nouveau/nv40_pm.c
index 3af5bcd0b203..625f80d53dc2 100644
--- a/drivers/gpu/drm/nouveau/nv40_pm.c
+++ b/drivers/gpu/drm/nouveau/nv40_pm.c
@@ -131,7 +131,7 @@ nv40_calc_pll(struct drm_device *dev, u32 reg, struct nvbios_pll *pll,
 	if (clk < pll->vco1.max_freq)
 		pll->vco2.max_freq = 0;
 
-	pclk->pll_calc(pclk, pll, clk, &coef);
+	ret = pclk->pll_calc(pclk, pll, clk, &coef);
 	if (ret == 0)
 		return -ERANGE;
 
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 54dc6355b0c2..8b40a36c1b57 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -355,6 +355,7 @@ struct nv50_oimm {
 
 struct nv50_head {
 	struct nouveau_crtc base;
+	struct nouveau_bo *image;
 	struct nv50_curs curs;
 	struct nv50_sync sync;
 	struct nv50_ovly ovly;
@@ -517,9 +518,10 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 {
 	struct nouveau_framebuffer *nv_fb = nouveau_framebuffer(fb);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
+	struct nv50_head *head = nv50_head(crtc);
 	struct nv50_sync *sync = nv50_sync(crtc);
-	int head = nv_crtc->index, ret;
 	u32 *push;
+	int ret;
 
 	swap_interval <<= 4;
 	if (swap_interval == 0)
@@ -537,7 +539,7 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 			return ret;
 
 		BEGIN_NV04(chan, 0, NV11_SUBCHAN_DMA_SEMAPHORE, 2);
-		OUT_RING  (chan, NvEvoSema0 + head);
+		OUT_RING  (chan, NvEvoSema0 + nv_crtc->index);
 		OUT_RING  (chan, sync->addr ^ 0x10);
 		BEGIN_NV04(chan, 0, NV11_SUBCHAN_SEMAPHORE_RELEASE, 1);
 		OUT_RING  (chan, sync->data + 1);
@@ -546,7 +548,7 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		OUT_RING  (chan, sync->data);
 	} else
 	if (chan && nv_mclass(chan->object) < NVC0_CHANNEL_IND_CLASS) {
-		u64 addr = nv84_fence_crtc(chan, head) + sync->addr;
+		u64 addr = nv84_fence_crtc(chan, nv_crtc->index) + sync->addr;
 		ret = RING_SPACE(chan, 12);
 		if (ret)
 			return ret;
@@ -565,7 +567,7 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		OUT_RING  (chan, NV84_SUBCHAN_SEMAPHORE_TRIGGER_ACQUIRE_EQUAL);
 	} else
 	if (chan) {
-		u64 addr = nv84_fence_crtc(chan, head) + sync->addr;
+		u64 addr = nv84_fence_crtc(chan, nv_crtc->index) + sync->addr;
 		ret = RING_SPACE(chan, 10);
 		if (ret)
 			return ret;
@@ -630,6 +632,8 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	evo_mthd(push, 0x0080, 1);
 	evo_data(push, 0x00000000);
 	evo_kick(push, sync);
+
+	nouveau_bo_ref(nv_fb->nvbo, &head->image);
 	return 0;
 }
 
@@ -1038,18 +1042,17 @@ static int
 nv50_crtc_swap_fbs(struct drm_crtc *crtc, struct drm_framebuffer *old_fb)
 {
 	struct nouveau_framebuffer *nvfb = nouveau_framebuffer(crtc->fb);
+	struct nv50_head *head = nv50_head(crtc);
 	int ret;
 
 	ret = nouveau_bo_pin(nvfb->nvbo, TTM_PL_FLAG_VRAM);
-	if (ret)
-		return ret;
-
-	if (old_fb) {
-		nvfb = nouveau_framebuffer(old_fb);
-		nouveau_bo_unpin(nvfb->nvbo);
+	if (ret == 0) {
+		if (head->image)
+			nouveau_bo_unpin(head->image);
+		nouveau_bo_ref(nvfb->nvbo, &head->image);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int
@@ -1198,6 +1201,15 @@ nv50_crtc_lut_load(struct drm_crtc *crtc)
 	}
 }
 
+static void
+nv50_crtc_disable(struct drm_crtc *crtc)
+{
+	struct nv50_head *head = nv50_head(crtc);
+	if (head->image)
+		nouveau_bo_unpin(head->image);
+	nouveau_bo_ref(NULL, &head->image);
+}
+
 static int
 nv50_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
 		     uint32_t handle, uint32_t width, uint32_t height)
@@ -1271,18 +1283,29 @@ nv50_crtc_destroy(struct drm_crtc *crtc)
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 	struct nv50_disp *disp = nv50_disp(crtc->dev);
 	struct nv50_head *head = nv50_head(crtc);
+
 	nv50_dmac_destroy(disp->core, &head->ovly.base);
 	nv50_pioc_destroy(disp->core, &head->oimm.base);
 	nv50_dmac_destroy(disp->core, &head->sync.base);
 	nv50_pioc_destroy(disp->core, &head->curs.base);
+
+	/*XXX: this shouldn't be necessary, but the core doesn't call
+	 *     disconnect() during the cleanup paths
+	 */
+	if (head->image)
+		nouveau_bo_unpin(head->image);
+	nouveau_bo_ref(NULL, &head->image);
+
 	nouveau_bo_unmap(nv_crtc->cursor.nvbo);
 	if (nv_crtc->cursor.nvbo)
 		nouveau_bo_unpin(nv_crtc->cursor.nvbo);
 	nouveau_bo_ref(NULL, &nv_crtc->cursor.nvbo);
+
 	nouveau_bo_unmap(nv_crtc->lut.nvbo);
 	if (nv_crtc->lut.nvbo)
 		nouveau_bo_unpin(nv_crtc->lut.nvbo);
 	nouveau_bo_ref(NULL, &nv_crtc->lut.nvbo);
+
 	drm_crtc_cleanup(crtc);
 	kfree(crtc);
 }
@@ -1296,6 +1319,7 @@ static const struct drm_crtc_helper_funcs nv50_crtc_hfunc = {
 	.mode_set_base = nv50_crtc_mode_set_base,
 	.mode_set_base_atomic = nv50_crtc_mode_set_base_atomic,
 	.load_lut = nv50_crtc_lut_load,
+	.disable = nv50_crtc_disable,
 };
 
 static const struct drm_crtc_funcs nv50_crtc_func = {
diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c
index f9701e567db8..0ee363840035 100644
--- a/drivers/gpu/drm/nouveau/nv50_fence.c
+++ b/drivers/gpu/drm/nouveau/nv50_fence.c
@@ -39,6 +39,8 @@ nv50_fence_context_new(struct nouveau_channel *chan)
 	struct nv10_fence_chan *fctx;
 	struct ttm_mem_reg *mem = &priv->bo->bo.mem;
 	struct nouveau_object *object;
+	u32 start = mem->start * PAGE_SIZE;
+	u32 limit = start + mem->size - 1;
 	int ret, i;
 
 	fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL);
@@ -51,26 +53,28 @@ nv50_fence_context_new(struct nouveau_channel *chan)
 	fctx->base.sync = nv17_fence_sync;
 
 	ret = nouveau_object_new(nv_object(chan->cli), chan->handle,
-				 NvSema, 0x0002,
+				 NvSema, 0x003d,
 				 &(struct nv_dma_class) {
 					.flags = NV_DMA_TARGET_VRAM |
 						 NV_DMA_ACCESS_RDWR,
-					.start = mem->start * PAGE_SIZE,
-					.limit = mem->size - 1,
+					.start = start,
+					.limit = limit,
 				 }, sizeof(struct nv_dma_class),
 				 &object);
 
 	/* dma objects for display sync channel semaphore blocks */
 	for (i = 0; !ret && i < dev->mode_config.num_crtc; i++) {
 		struct nouveau_bo *bo = nv50_display_crtc_sema(dev, i);
+		u32 start = bo->bo.mem.start * PAGE_SIZE;
+		u32 limit = start + bo->bo.mem.size - 1;
 
 		ret = nouveau_object_new(nv_object(chan->cli), chan->handle,
 					 NvEvoSema0 + i, 0x003d,
 					 &(struct nv_dma_class) {
 						.flags = NV_DMA_TARGET_VRAM |
 							 NV_DMA_ACCESS_RDWR,
-						.start = bo->bo.offset,
-						.limit = bo->bo.offset + 0xfff,
+						.start = start,
+						.limit = limit,
 					 }, sizeof(struct nv_dma_class),
 					 &object);
 	}
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index 93c2f2cceb51..eb89653a7a17 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -179,9 +179,10 @@ qxl_push_command_ring_release(struct qxl_device *qdev, struct qxl_release *relea
 			      uint32_t type, bool interruptible)
 {
 	struct qxl_command cmd;
+	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
 
 	cmd.type = type;
-	cmd.data = qxl_bo_physical_address(qdev, release->bos[0], release->release_offset);
+	cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
 
 	return qxl_ring_push(qdev->command_ring, &cmd, interruptible);
 }
@@ -191,9 +192,10 @@ qxl_push_cursor_ring_release(struct qxl_device *qdev, struct qxl_release *releas
 			     uint32_t type, bool interruptible)
 {
 	struct qxl_command cmd;
+	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
 
 	cmd.type = type;
-	cmd.data = qxl_bo_physical_address(qdev, release->bos[0], release->release_offset);
+	cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
 
 	return qxl_ring_push(qdev->cursor_ring, &cmd, interruptible);
 }
@@ -214,7 +216,6 @@ int qxl_garbage_collect(struct qxl_device *qdev)
 	struct qxl_release *release;
 	uint64_t id, next_id;
 	int i = 0;
-	int ret;
 	union qxl_release_info *info;
 
 	while (qxl_ring_pop(qdev->release_ring, &id)) {
@@ -224,17 +225,10 @@ int qxl_garbage_collect(struct qxl_device *qdev)
 			if (release == NULL)
 				break;
 
-			ret = qxl_release_reserve(qdev, release, false);
-			if (ret) {
-				qxl_io_log(qdev, "failed to reserve release on garbage collect %lld\n", id);
-				DRM_ERROR("failed to reserve release %lld\n", id);
-			}
-
 			info = qxl_release_map(qdev, release);
 			next_id = info->next;
 			qxl_release_unmap(qdev, release, info);
 
-			qxl_release_unreserve(qdev, release);
 			QXL_INFO(qdev, "popped %lld, next %lld\n", id,
 				next_id);
 
@@ -259,27 +253,29 @@ int qxl_garbage_collect(struct qxl_device *qdev)
 	return i;
 }
 
-int qxl_alloc_bo_reserved(struct qxl_device *qdev, unsigned long size,
+int qxl_alloc_bo_reserved(struct qxl_device *qdev,
+			  struct qxl_release *release,
+			  unsigned long size,
 			  struct qxl_bo **_bo)
 {
 	struct qxl_bo *bo;
 	int ret;
 
 	ret = qxl_bo_create(qdev, size, false /* not kernel - device */,
-			    QXL_GEM_DOMAIN_VRAM, NULL, &bo);
+			    false, QXL_GEM_DOMAIN_VRAM, NULL, &bo);
 	if (ret) {
 		DRM_ERROR("failed to allocate VRAM BO\n");
 		return ret;
 	}
-	ret = qxl_bo_reserve(bo, false);
-	if (unlikely(ret != 0))
+	ret = qxl_release_list_add(release, bo);
+	if (ret)
 		goto out_unref;
 
 	*_bo = bo;
 	return 0;
 out_unref:
 	qxl_bo_unref(&bo);
-	return 0;
+	return ret;
 }
 
 static int wait_for_io_cmd_user(struct qxl_device *qdev, uint8_t val, long port, bool intr)
@@ -503,6 +499,10 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev,
 	if (ret)
 		return ret;
 
+	ret = qxl_release_reserve_list(release, true);
+	if (ret)
+		return ret;
+
 	cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_SURFACE_CMD_CREATE;
 	cmd->u.surface_create.format = surf->surf.format;
@@ -524,14 +524,11 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev,
 
 	surf->surf_create = release;
 
-	/* no need to add a release to the fence for this bo,
+	/* no need to add a release to the fence for this surface bo,
 	   since it is only released when we ask to destroy the surface
 	   and it would never signal otherwise */
-	qxl_fence_releaseable(qdev, release);
-
 	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
-
-	qxl_release_unreserve(qdev, release);
+	qxl_release_fence_buffer_objects(release);
 
 	surf->hw_surf_alloc = true;
 	spin_lock(&qdev->surf_id_idr_lock);
@@ -573,12 +570,9 @@ int qxl_hw_surface_dealloc(struct qxl_device *qdev,
 	cmd->surface_id = id;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_fence_releaseable(qdev, release);
-
 	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 
-	qxl_release_unreserve(qdev, release);
-
+	qxl_release_fence_buffer_objects(release);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index f76f5dd7bfc4..835caba026d3 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -179,7 +179,7 @@ static void qxl_crtc_destroy(struct drm_crtc *crtc)
 	kfree(qxl_crtc);
 }
 
-static void
+static int
 qxl_hide_cursor(struct qxl_device *qdev)
 {
 	struct qxl_release *release;
@@ -188,14 +188,22 @@ qxl_hide_cursor(struct qxl_device *qdev)
 
 	ret = qxl_alloc_release_reserved(qdev, sizeof(*cmd), QXL_RELEASE_CURSOR_CMD,
 					 &release, NULL);
+	if (ret)
+		return ret;
+
+	ret = qxl_release_reserve_list(release, true);
+	if (ret) {
+		qxl_release_free(qdev, release);
+		return ret;
+	}
 
 	cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_CURSOR_HIDE;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_fence_releaseable(qdev, release);
 	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
-	qxl_release_unreserve(qdev, release);
+	qxl_release_fence_buffer_objects(release);
+	return 0;
 }
 
 static int qxl_crtc_cursor_set2(struct drm_crtc *crtc,
@@ -216,10 +224,8 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	int size = 64*64*4;
 	int ret = 0;
-	if (!handle) {
-		qxl_hide_cursor(qdev);
-		return 0;
-	}
+	if (!handle)
+		return qxl_hide_cursor(qdev);
 
 	obj = drm_gem_object_lookup(crtc->dev, file_priv, handle);
 	if (!obj) {
@@ -234,8 +240,9 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc,
 		goto out_unref;
 
 	ret = qxl_bo_pin(user_bo, QXL_GEM_DOMAIN_CPU, NULL);
+	qxl_bo_unreserve(user_bo);
 	if (ret)
-		goto out_unreserve;
+		goto out_unref;
 
 	ret = qxl_bo_kmap(user_bo, &user_ptr);
 	if (ret)
@@ -246,14 +253,20 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc,
 					 &release, NULL);
 	if (ret)
 		goto out_kunmap;
-	ret = qxl_alloc_bo_reserved(qdev, sizeof(struct qxl_cursor) + size,
-				    &cursor_bo);
+
+	ret = qxl_alloc_bo_reserved(qdev, release, sizeof(struct qxl_cursor) + size,
+			   &cursor_bo);
 	if (ret)
 		goto out_free_release;
-	ret = qxl_bo_kmap(cursor_bo, (void **)&cursor);
+
+	ret = qxl_release_reserve_list(release, false);
 	if (ret)
 		goto out_free_bo;
 
+	ret = qxl_bo_kmap(cursor_bo, (void **)&cursor);
+	if (ret)
+		goto out_backoff;
+
 	cursor->header.unique = 0;
 	cursor->header.type = SPICE_CURSOR_TYPE_ALPHA;
 	cursor->header.width = 64;
@@ -269,11 +282,7 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	qxl_bo_kunmap(cursor_bo);
 
-	/* finish with the userspace bo */
 	qxl_bo_kunmap(user_bo);
-	qxl_bo_unpin(user_bo);
-	qxl_bo_unreserve(user_bo);
-	drm_gem_object_unreference_unlocked(obj);
 
 	cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_CURSOR_SET;
@@ -281,30 +290,35 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc,
 	cmd->u.set.position.y = qcrtc->cur_y;
 
 	cmd->u.set.shape = qxl_bo_physical_address(qdev, cursor_bo, 0);
-	qxl_release_add_res(qdev, release, cursor_bo);
 
 	cmd->u.set.visible = 1;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_fence_releaseable(qdev, release);
 	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
-	qxl_release_unreserve(qdev, release);
+	qxl_release_fence_buffer_objects(release);
+
+	/* finish with the userspace bo */
+	ret = qxl_bo_reserve(user_bo, false);
+	if (!ret) {
+		qxl_bo_unpin(user_bo);
+		qxl_bo_unreserve(user_bo);
+	}
+	drm_gem_object_unreference_unlocked(obj);
 
-	qxl_bo_unreserve(cursor_bo);
 	qxl_bo_unref(&cursor_bo);
 
 	return ret;
+
+out_backoff:
+	qxl_release_backoff_reserve_list(release);
 out_free_bo:
 	qxl_bo_unref(&cursor_bo);
 out_free_release:
-	qxl_release_unreserve(qdev, release);
 	qxl_release_free(qdev, release);
 out_kunmap:
 	qxl_bo_kunmap(user_bo);
 out_unpin:
 	qxl_bo_unpin(user_bo);
-out_unreserve:
-	qxl_bo_unreserve(user_bo);
 out_unref:
 	drm_gem_object_unreference_unlocked(obj);
 	return ret;
@@ -322,6 +336,14 @@ static int qxl_crtc_cursor_move(struct drm_crtc *crtc,
 
 	ret = qxl_alloc_release_reserved(qdev, sizeof(*cmd), QXL_RELEASE_CURSOR_CMD,
 				   &release, NULL);
+	if (ret)
+		return ret;
+
+	ret = qxl_release_reserve_list(release, true);
+	if (ret) {
+		qxl_release_free(qdev, release);
+		return ret;
+	}
 
 	qcrtc->cur_x = x;
 	qcrtc->cur_y = y;
@@ -332,9 +354,9 @@ static int qxl_crtc_cursor_move(struct drm_crtc *crtc,
 	cmd->u.position.y = qcrtc->cur_y;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_fence_releaseable(qdev, release);
 	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
-	qxl_release_unreserve(qdev, release);
+	qxl_release_fence_buffer_objects(release);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c
index 3c8c3dbf9378..56e1d633875e 100644
--- a/drivers/gpu/drm/qxl/qxl_draw.c
+++ b/drivers/gpu/drm/qxl/qxl_draw.c
@@ -23,25 +23,29 @@
 #include "qxl_drv.h"
 #include "qxl_object.h"
 
+static int alloc_clips(struct qxl_device *qdev,
+		       struct qxl_release *release,
+		       unsigned num_clips,
+		       struct qxl_bo **clips_bo)
+{
+	int size = sizeof(struct qxl_clip_rects) + sizeof(struct qxl_rect) * num_clips;
+
+	return qxl_alloc_bo_reserved(qdev, release, size, clips_bo);
+}
+
 /* returns a pointer to the already allocated qxl_rect array inside
  * the qxl_clip_rects. This is *not* the same as the memory allocated
  * on the device, it is offset to qxl_clip_rects.chunk.data */
 static struct qxl_rect *drawable_set_clipping(struct qxl_device *qdev,
 					      struct qxl_drawable *drawable,
 					      unsigned num_clips,
-					      struct qxl_bo **clips_bo,
-					      struct qxl_release *release)
+					      struct qxl_bo *clips_bo)
 {
 	struct qxl_clip_rects *dev_clips;
 	int ret;
-	int size = sizeof(*dev_clips) + sizeof(struct qxl_rect) * num_clips;
-	ret = qxl_alloc_bo_reserved(qdev, size, clips_bo);
-	if (ret)
-		return NULL;
 
-	ret = qxl_bo_kmap(*clips_bo, (void **)&dev_clips);
+	ret = qxl_bo_kmap(clips_bo, (void **)&dev_clips);
 	if (ret) {
-		qxl_bo_unref(clips_bo);
 		return NULL;
 	}
 	dev_clips->num_rects = num_clips;
@@ -52,20 +56,34 @@ static struct qxl_rect *drawable_set_clipping(struct qxl_device *qdev,
 }
 
 static int
+alloc_drawable(struct qxl_device *qdev, struct qxl_release **release)
+{
+	int ret;
+	ret = qxl_alloc_release_reserved(qdev, sizeof(struct qxl_drawable),
+					 QXL_RELEASE_DRAWABLE, release,
+					 NULL);
+	return ret;
+}
+
+static void
+free_drawable(struct qxl_device *qdev, struct qxl_release *release)
+{
+	qxl_release_free(qdev, release);
+}
+
+/* release needs to be reserved at this point */
+static int
 make_drawable(struct qxl_device *qdev, int surface, uint8_t type,
 	      const struct qxl_rect *rect,
-	      struct qxl_release **release)
+	      struct qxl_release *release)
 {
 	struct qxl_drawable *drawable;
-	int i, ret;
+	int i;
 
-	ret = qxl_alloc_release_reserved(qdev, sizeof(*drawable),
-					 QXL_RELEASE_DRAWABLE, release,
-					 NULL);
-	if (ret)
-		return ret;
+	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
+	if (!drawable)
+		return -ENOMEM;
 
-	drawable = (struct qxl_drawable *)qxl_release_map(qdev, *release);
 	drawable->type = type;
 
 	drawable->surface_id = surface;		/* Only primary for now */
@@ -91,14 +109,23 @@ make_drawable(struct qxl_device *qdev, int surface, uint8_t type,
 		drawable->bbox = *rect;
 
 	drawable->mm_time = qdev->rom->mm_clock;
-	qxl_release_unmap(qdev, *release, &drawable->release_info);
+	qxl_release_unmap(qdev, release, &drawable->release_info);
 	return 0;
 }
 
-static int qxl_palette_create_1bit(struct qxl_bo **palette_bo,
+static int alloc_palette_object(struct qxl_device *qdev,
+				struct qxl_release *release,
+				struct qxl_bo **palette_bo)
+{
+	return qxl_alloc_bo_reserved(qdev, release,
+				     sizeof(struct qxl_palette) + sizeof(uint32_t) * 2,
+				     palette_bo);
+}
+
+static int qxl_palette_create_1bit(struct qxl_bo *palette_bo,
+				   struct qxl_release *release,
 				   const struct qxl_fb_image *qxl_fb_image)
 {
-	struct qxl_device *qdev = qxl_fb_image->qdev;
 	const struct fb_image *fb_image = &qxl_fb_image->fb_image;
 	uint32_t visual = qxl_fb_image->visual;
 	const uint32_t *pseudo_palette = qxl_fb_image->pseudo_palette;
@@ -108,12 +135,7 @@ static int qxl_palette_create_1bit(struct qxl_bo **palette_bo,
 	static uint64_t unique; /* we make no attempt to actually set this
 				 * correctly globaly, since that would require
 				 * tracking all of our palettes. */
-
-	ret = qxl_alloc_bo_reserved(qdev,
-				    sizeof(struct qxl_palette) + sizeof(uint32_t) * 2,
-				    palette_bo);
-
-	ret = qxl_bo_kmap(*palette_bo, (void **)&pal);
+	ret = qxl_bo_kmap(palette_bo, (void **)&pal);
 	pal->num_ents = 2;
 	pal->unique = unique++;
 	if (visual == FB_VISUAL_TRUECOLOR || visual == FB_VISUAL_DIRECTCOLOR) {
@@ -126,7 +148,7 @@ static int qxl_palette_create_1bit(struct qxl_bo **palette_bo,
 	}
 	pal->ents[0] = bgcolor;
 	pal->ents[1] = fgcolor;
-	qxl_bo_kunmap(*palette_bo);
+	qxl_bo_kunmap(palette_bo);
 	return 0;
 }
 
@@ -144,44 +166,63 @@ void qxl_draw_opaque_fb(const struct qxl_fb_image *qxl_fb_image,
 	const char *src = fb_image->data;
 	int depth = fb_image->depth;
 	struct qxl_release *release;
-	struct qxl_bo *image_bo;
 	struct qxl_image *image;
 	int ret;
-
+	struct qxl_drm_image *dimage;
+	struct qxl_bo *palette_bo = NULL;
 	if (stride == 0)
 		stride = depth * width / 8;
 
+	ret = alloc_drawable(qdev, &release);
+	if (ret)
+		return;
+
+	ret = qxl_image_alloc_objects(qdev, release,
+				      &dimage,
+				      height, stride);
+	if (ret)
+		goto out_free_drawable;
+
+	if (depth == 1) {
+		ret = alloc_palette_object(qdev, release, &palette_bo);
+		if (ret)
+			goto out_free_image;
+	}
+
+	/* do a reservation run over all the objects we just allocated */
+	ret = qxl_release_reserve_list(release, true);
+	if (ret)
+		goto out_free_palette;
+
 	rect.left = x;
 	rect.right = x + width;
 	rect.top = y;
 	rect.bottom = y + height;
 
-	ret = make_drawable(qdev, 0, QXL_DRAW_COPY, &rect, &release);
-	if (ret)
-		return;
+	ret = make_drawable(qdev, 0, QXL_DRAW_COPY, &rect, release);
+	if (ret) {
+		qxl_release_backoff_reserve_list(release);
+		goto out_free_palette;
+	}
 
-	ret = qxl_image_create(qdev, release, &image_bo,
-			       (const uint8_t *)src, 0, 0,
-			       width, height, depth, stride);
+	ret = qxl_image_init(qdev, release, dimage,
+			     (const uint8_t *)src, 0, 0,
+			     width, height, depth, stride);
 	if (ret) {
-		qxl_release_unreserve(qdev, release);
+		qxl_release_backoff_reserve_list(release);
 		qxl_release_free(qdev, release);
 		return;
 	}
 
 	if (depth == 1) {
-		struct qxl_bo *palette_bo;
 		void *ptr;
-		ret = qxl_palette_create_1bit(&palette_bo, qxl_fb_image);
-		qxl_release_add_res(qdev, release, palette_bo);
+		ret = qxl_palette_create_1bit(palette_bo, release, qxl_fb_image);
 
-		ptr = qxl_bo_kmap_atomic_page(qdev, image_bo, 0);
+		ptr = qxl_bo_kmap_atomic_page(qdev, dimage->bo, 0);
 		image = ptr;
 		image->u.bitmap.palette =
 			qxl_bo_physical_address(qdev, palette_bo, 0);
-		qxl_bo_kunmap_atomic_page(qdev, image_bo, ptr);
-		qxl_bo_unreserve(palette_bo);
-		qxl_bo_unref(&palette_bo);
+		qxl_bo_kunmap_atomic_page(qdev, dimage->bo, ptr);
 	}
 
 	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
@@ -199,16 +240,20 @@ void qxl_draw_opaque_fb(const struct qxl_fb_image *qxl_fb_image,
 	drawable->u.copy.mask.bitmap = 0;
 
 	drawable->u.copy.src_bitmap =
-		qxl_bo_physical_address(qdev, image_bo, 0);
+		qxl_bo_physical_address(qdev, dimage->bo, 0);
 	qxl_release_unmap(qdev, release, &drawable->release_info);
 
-	qxl_release_add_res(qdev, release, image_bo);
-	qxl_bo_unreserve(image_bo);
-	qxl_bo_unref(&image_bo);
-
-	qxl_fence_releaseable(qdev, release);
 	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
-	qxl_release_unreserve(qdev, release);
+	qxl_release_fence_buffer_objects(release);
+
+out_free_palette:
+	if (palette_bo)
+		qxl_bo_unref(&palette_bo);
+out_free_image:
+	qxl_image_free_objects(qdev, dimage);
+out_free_drawable:
+	if (ret)
+		free_drawable(qdev, release);
 }
 
 /* push a draw command using the given clipping rectangles as
@@ -243,10 +288,14 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 	int depth = qxl_fb->base.bits_per_pixel;
 	uint8_t *surface_base;
 	struct qxl_release *release;
-	struct qxl_bo *image_bo;
 	struct qxl_bo *clips_bo;
+	struct qxl_drm_image *dimage;
 	int ret;
 
+	ret = alloc_drawable(qdev, &release);
+	if (ret)
+		return;
+
 	left = clips->x1;
 	right = clips->x2;
 	top = clips->y1;
@@ -263,36 +312,52 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 
 	width = right - left;
 	height = bottom - top;
+
+	ret = alloc_clips(qdev, release, num_clips, &clips_bo);
+	if (ret)
+		goto out_free_drawable;
+
+	ret = qxl_image_alloc_objects(qdev, release,
+				      &dimage,
+				      height, stride);
+	if (ret)
+		goto out_free_clips;
+
+	/* do a reservation run over all the objects we just allocated */
+	ret = qxl_release_reserve_list(release, true);
+	if (ret)
+		goto out_free_image;
+
 	drawable_rect.left = left;
 	drawable_rect.right = right;
 	drawable_rect.top = top;
 	drawable_rect.bottom = bottom;
+
 	ret = make_drawable(qdev, 0, QXL_DRAW_COPY, &drawable_rect,
-			    &release);
+			    release);
 	if (ret)
-		return;
+		goto out_release_backoff;
 
 	ret = qxl_bo_kmap(bo, (void **)&surface_base);
 	if (ret)
-		goto out_unref;
+		goto out_release_backoff;
 
-	ret = qxl_image_create(qdev, release, &image_bo, surface_base,
-			       left, top, width, height, depth, stride);
+
+	ret = qxl_image_init(qdev, release, dimage, surface_base,
+			     left, top, width, height, depth, stride);
 	qxl_bo_kunmap(bo);
 	if (ret)
-		goto out_unref;
+		goto out_release_backoff;
+
+	rects = drawable_set_clipping(qdev, drawable, num_clips, clips_bo);
+	if (!rects)
+		goto out_release_backoff;
 
-	rects = drawable_set_clipping(qdev, drawable, num_clips, &clips_bo, release);
-	if (!rects) {
-		qxl_bo_unref(&image_bo);
-		goto out_unref;
-	}
 	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
 
 	drawable->clip.type = SPICE_CLIP_TYPE_RECTS;
 	drawable->clip.data = qxl_bo_physical_address(qdev,
 						      clips_bo, 0);
-	qxl_release_add_res(qdev, release, clips_bo);
 
 	drawable->u.copy.src_area.top = 0;
 	drawable->u.copy.src_area.bottom = height;
@@ -306,11 +371,9 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 	drawable->u.copy.mask.pos.y = 0;
 	drawable->u.copy.mask.bitmap = 0;
 
-	drawable->u.copy.src_bitmap = qxl_bo_physical_address(qdev, image_bo, 0);
+	drawable->u.copy.src_bitmap = qxl_bo_physical_address(qdev, dimage->bo, 0);
 	qxl_release_unmap(qdev, release, &drawable->release_info);
-	qxl_release_add_res(qdev, release, image_bo);
-	qxl_bo_unreserve(image_bo);
-	qxl_bo_unref(&image_bo);
+
 	clips_ptr = clips;
 	for (i = 0; i < num_clips; i++, clips_ptr += inc) {
 		rects[i].left   = clips_ptr->x1;
@@ -319,17 +382,22 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 		rects[i].bottom = clips_ptr->y2;
 	}
 	qxl_bo_kunmap(clips_bo);
-	qxl_bo_unreserve(clips_bo);
-	qxl_bo_unref(&clips_bo);
 
-	qxl_fence_releaseable(qdev, release);
 	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
-	qxl_release_unreserve(qdev, release);
-	return;
+	qxl_release_fence_buffer_objects(release);
+
+out_release_backoff:
+	if (ret)
+		qxl_release_backoff_reserve_list(release);
+out_free_image:
+	qxl_image_free_objects(qdev, dimage);
+out_free_clips:
+	qxl_bo_unref(&clips_bo);
+out_free_drawable:
+	/* only free drawable on error */
+	if (ret)
+		free_drawable(qdev, release);
 
-out_unref:
-	qxl_release_unreserve(qdev, release);
-	qxl_release_free(qdev, release);
 }
 
 void qxl_draw_copyarea(struct qxl_device *qdev,
@@ -342,22 +410,36 @@ void qxl_draw_copyarea(struct qxl_device *qdev,
 	struct qxl_release *release;
 	int ret;
 
+	ret = alloc_drawable(qdev, &release);
+	if (ret)
+		return;
+
+	/* do a reservation run over all the objects we just allocated */
+	ret = qxl_release_reserve_list(release, true);
+	if (ret)
+		goto out_free_release;
+
 	rect.left = dx;
 	rect.top = dy;
 	rect.right = dx + width;
 	rect.bottom = dy + height;
-	ret = make_drawable(qdev, 0, QXL_COPY_BITS, &rect, &release);
-	if (ret)
-		return;
+	ret = make_drawable(qdev, 0, QXL_COPY_BITS, &rect, release);
+	if (ret) {
+		qxl_release_backoff_reserve_list(release);
+		goto out_free_release;
+	}
 
 	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
 	drawable->u.copy_bits.src_pos.x = sx;
 	drawable->u.copy_bits.src_pos.y = sy;
-
 	qxl_release_unmap(qdev, release, &drawable->release_info);
-	qxl_fence_releaseable(qdev, release);
+
 	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
-	qxl_release_unreserve(qdev, release);
+	qxl_release_fence_buffer_objects(release);
+
+out_free_release:
+	if (ret)
+		free_drawable(qdev, release);
 }
 
 void qxl_draw_fill(struct qxl_draw_fill *qxl_draw_fill_rec)
@@ -370,10 +452,21 @@ void qxl_draw_fill(struct qxl_draw_fill *qxl_draw_fill_rec)
 	struct qxl_release *release;
 	int ret;
 
-	ret = make_drawable(qdev, 0, QXL_DRAW_FILL, &rect, &release);
+	ret = alloc_drawable(qdev, &release);
 	if (ret)
 		return;
 
+	/* do a reservation run over all the objects we just allocated */
+	ret = qxl_release_reserve_list(release, true);
+	if (ret)
+		goto out_free_release;
+
+	ret = make_drawable(qdev, 0, QXL_DRAW_FILL, &rect, release);
+	if (ret) {
+		qxl_release_backoff_reserve_list(release);
+		goto out_free_release;
+	}
+
 	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
 	drawable->u.fill.brush.type = SPICE_BRUSH_TYPE_SOLID;
 	drawable->u.fill.brush.u.color = color;
@@ -384,7 +477,11 @@ void qxl_draw_fill(struct qxl_draw_fill *qxl_draw_fill_rec)
 	drawable->u.fill.mask.bitmap = 0;
 
 	qxl_release_unmap(qdev, release, &drawable->release_info);
-	qxl_fence_releaseable(qdev, release);
+
 	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
-	qxl_release_unreserve(qdev, release);
+	qxl_release_fence_buffer_objects(release);
+
+out_free_release:
+	if (ret)
+		free_drawable(qdev, release);
 }
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index aacb791464a3..7e96f4f11738 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -42,6 +42,9 @@
 #include <ttm/ttm_placement.h>
 #include <ttm/ttm_module.h>
 
+/* just for ttm_validate_buffer */
+#include <ttm/ttm_execbuf_util.h>
+
 #include <drm/qxl_drm.h>
 #include "qxl_dev.h"
 
@@ -118,9 +121,9 @@ struct qxl_bo {
 	uint32_t surface_id;
 	struct qxl_fence fence; /* per bo fence  - list of releases */
 	struct qxl_release *surf_create;
-	atomic_t reserve_count;
 };
 #define gem_to_qxl_bo(gobj) container_of((gobj), struct qxl_bo, gem_base)
+#define to_qxl_bo(tobj) container_of((tobj), struct qxl_bo, tbo)
 
 struct qxl_gem {
 	struct mutex		mutex;
@@ -128,12 +131,7 @@ struct qxl_gem {
 };
 
 struct qxl_bo_list {
-	struct list_head lhead;
-	struct qxl_bo *bo;
-};
-
-struct qxl_reloc_list {
-	struct list_head bos;
+	struct ttm_validate_buffer tv;
 };
 
 struct qxl_crtc {
@@ -195,10 +193,20 @@ enum {
 struct qxl_release {
 	int id;
 	int type;
-	int bo_count;
 	uint32_t release_offset;
 	uint32_t surface_release_id;
-	struct qxl_bo *bos[QXL_MAX_RES];
+	struct ww_acquire_ctx ticket;
+	struct list_head bos;
+};
+
+struct qxl_drm_chunk {
+	struct list_head head;
+	struct qxl_bo *bo;
+};
+
+struct qxl_drm_image {
+	struct qxl_bo *bo;
+	struct list_head chunk_list;
 };
 
 struct qxl_fb_image {
@@ -314,6 +322,7 @@ struct qxl_device {
 	struct workqueue_struct *gc_queue;
 	struct work_struct gc_work;
 
+	struct work_struct fb_work;
 };
 
 /* forward declaration for QXL_INFO_IO */
@@ -433,12 +442,19 @@ int qxl_mmap(struct file *filp, struct vm_area_struct *vma);
 
 /* qxl image */
 
-int qxl_image_create(struct qxl_device *qdev,
-		     struct qxl_release *release,
-		     struct qxl_bo **image_bo,
-		     const uint8_t *data,
-		     int x, int y, int width, int height,
-		     int depth, int stride);
+int qxl_image_init(struct qxl_device *qdev,
+		   struct qxl_release *release,
+		   struct qxl_drm_image *dimage,
+		   const uint8_t *data,
+		   int x, int y, int width, int height,
+		   int depth, int stride);
+int
+qxl_image_alloc_objects(struct qxl_device *qdev,
+			struct qxl_release *release,
+			struct qxl_drm_image **image_ptr,
+			int height, int stride);
+void qxl_image_free_objects(struct qxl_device *qdev, struct qxl_drm_image *dimage);
+
 void qxl_update_screen(struct qxl_device *qxl);
 
 /* qxl io operations (qxl_cmd.c) */
@@ -459,20 +475,15 @@ int qxl_ring_push(struct qxl_ring *ring, const void *new_elt, bool interruptible
 void qxl_io_flush_release(struct qxl_device *qdev);
 void qxl_io_flush_surfaces(struct qxl_device *qdev);
 
-int qxl_release_reserve(struct qxl_device *qdev,
-			struct qxl_release *release, bool no_wait);
-void qxl_release_unreserve(struct qxl_device *qdev,
-			   struct qxl_release *release);
 union qxl_release_info *qxl_release_map(struct qxl_device *qdev,
 					struct qxl_release *release);
 void qxl_release_unmap(struct qxl_device *qdev,
 		       struct qxl_release *release,
 		       union qxl_release_info *info);
-/*
- * qxl_bo_add_resource.
- *
- */
-void qxl_bo_add_resource(struct qxl_bo *main_bo, struct qxl_bo *resource);
+int qxl_release_list_add(struct qxl_release *release, struct qxl_bo *bo);
+int qxl_release_reserve_list(struct qxl_release *release, bool no_intr);
+void qxl_release_backoff_reserve_list(struct qxl_release *release);
+void qxl_release_fence_buffer_objects(struct qxl_release *release);
 
 int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
 				       enum qxl_surface_cmd_type surface_cmd_type,
@@ -481,15 +492,16 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
 int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 			       int type, struct qxl_release **release,
 			       struct qxl_bo **rbo);
-int qxl_fence_releaseable(struct qxl_device *qdev,
-			  struct qxl_release *release);
+
 int
 qxl_push_command_ring_release(struct qxl_device *qdev, struct qxl_release *release,
 			      uint32_t type, bool interruptible);
 int
 qxl_push_cursor_ring_release(struct qxl_device *qdev, struct qxl_release *release,
 			     uint32_t type, bool interruptible);
-int qxl_alloc_bo_reserved(struct qxl_device *qdev, unsigned long size,
+int qxl_alloc_bo_reserved(struct qxl_device *qdev,
+			  struct qxl_release *release,
+			  unsigned long size,
 			  struct qxl_bo **_bo);
 /* qxl drawing commands */
 
@@ -510,15 +522,9 @@ void qxl_draw_copyarea(struct qxl_device *qdev,
 		       u32 sx, u32 sy,
 		       u32 dx, u32 dy);
 
-uint64_t
-qxl_release_alloc(struct qxl_device *qdev, int type,
-		  struct qxl_release **ret);
-
 void qxl_release_free(struct qxl_device *qdev,
 		      struct qxl_release *release);
-void qxl_release_add_res(struct qxl_device *qdev,
-			 struct qxl_release *release,
-			 struct qxl_bo *bo);
+
 /* used by qxl_debugfs_release */
 struct qxl_release *qxl_release_from_id_locked(struct qxl_device *qdev,
 						   uint64_t id);
@@ -561,7 +567,7 @@ void qxl_surface_evict(struct qxl_device *qdev, struct qxl_bo *surf, bool freein
 int qxl_update_surface(struct qxl_device *qdev, struct qxl_bo *surf);
 
 /* qxl_fence.c */
-int qxl_fence_add_release(struct qxl_fence *qfence, uint32_t rel_id);
+void qxl_fence_add_release_locked(struct qxl_fence *qfence, uint32_t rel_id);
 int qxl_fence_remove_release(struct qxl_fence *qfence, uint32_t rel_id);
 int qxl_fence_init(struct qxl_device *qdev, struct qxl_fence *qfence);
 void qxl_fence_fini(struct qxl_fence *qfence);
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index 76f39d88d684..88722f233430 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -37,12 +37,29 @@
 
 #define QXL_DIRTY_DELAY (HZ / 30)
 
+#define QXL_FB_OP_FILLRECT 1
+#define QXL_FB_OP_COPYAREA 2
+#define QXL_FB_OP_IMAGEBLIT 3
+
+struct qxl_fb_op {
+	struct list_head head;
+	int op_type;
+	union {
+		struct fb_fillrect fr;
+		struct fb_copyarea ca;
+		struct fb_image ib;
+	} op;
+	void *img_data;
+};
+
 struct qxl_fbdev {
 	struct drm_fb_helper helper;
 	struct qxl_framebuffer	qfb;
 	struct list_head	fbdev_list;
 	struct qxl_device	*qdev;
 
+	spinlock_t delayed_ops_lock;
+	struct list_head delayed_ops;
 	void *shadow;
 	int size;
 
@@ -164,8 +181,69 @@ static struct fb_deferred_io qxl_defio = {
 	.deferred_io	= qxl_deferred_io,
 };
 
-static void qxl_fb_fillrect(struct fb_info *info,
-			    const struct fb_fillrect *fb_rect)
+static void qxl_fb_delayed_fillrect(struct qxl_fbdev *qfbdev,
+				    const struct fb_fillrect *fb_rect)
+{
+	struct qxl_fb_op *op;
+	unsigned long flags;
+
+	op = kmalloc(sizeof(struct qxl_fb_op), GFP_ATOMIC | __GFP_NOWARN);
+	if (!op)
+		return;
+
+	op->op.fr = *fb_rect;
+	op->img_data = NULL;
+	op->op_type = QXL_FB_OP_FILLRECT;
+
+	spin_lock_irqsave(&qfbdev->delayed_ops_lock, flags);
+	list_add_tail(&op->head, &qfbdev->delayed_ops);
+	spin_unlock_irqrestore(&qfbdev->delayed_ops_lock, flags);
+}
+
+static void qxl_fb_delayed_copyarea(struct qxl_fbdev *qfbdev,
+				    const struct fb_copyarea *fb_copy)
+{
+	struct qxl_fb_op *op;
+	unsigned long flags;
+
+	op = kmalloc(sizeof(struct qxl_fb_op), GFP_ATOMIC | __GFP_NOWARN);
+	if (!op)
+		return;
+
+	op->op.ca = *fb_copy;
+	op->img_data = NULL;
+	op->op_type = QXL_FB_OP_COPYAREA;
+
+	spin_lock_irqsave(&qfbdev->delayed_ops_lock, flags);
+	list_add_tail(&op->head, &qfbdev->delayed_ops);
+	spin_unlock_irqrestore(&qfbdev->delayed_ops_lock, flags);
+}
+
+static void qxl_fb_delayed_imageblit(struct qxl_fbdev *qfbdev,
+				     const struct fb_image *fb_image)
+{
+	struct qxl_fb_op *op;
+	unsigned long flags;
+	uint32_t size = fb_image->width * fb_image->height * (fb_image->depth >= 8 ? fb_image->depth / 8 : 1);
+
+	op = kmalloc(sizeof(struct qxl_fb_op) + size, GFP_ATOMIC | __GFP_NOWARN);
+	if (!op)
+		return;
+
+	op->op.ib = *fb_image;
+	op->img_data = (void *)(op + 1);
+	op->op_type = QXL_FB_OP_IMAGEBLIT;
+
+	memcpy(op->img_data, fb_image->data, size);
+
+	op->op.ib.data = op->img_data;
+	spin_lock_irqsave(&qfbdev->delayed_ops_lock, flags);
+	list_add_tail(&op->head, &qfbdev->delayed_ops);
+	spin_unlock_irqrestore(&qfbdev->delayed_ops_lock, flags);
+}
+
+static void qxl_fb_fillrect_internal(struct fb_info *info,
+				     const struct fb_fillrect *fb_rect)
 {
 	struct qxl_fbdev *qfbdev = info->par;
 	struct qxl_device *qdev = qfbdev->qdev;
@@ -203,17 +281,28 @@ static void qxl_fb_fillrect(struct fb_info *info,
 	qxl_draw_fill_rec.rect = rect;
 	qxl_draw_fill_rec.color = color;
 	qxl_draw_fill_rec.rop = rop;
+
+	qxl_draw_fill(&qxl_draw_fill_rec);
+}
+
+static void qxl_fb_fillrect(struct fb_info *info,
+			    const struct fb_fillrect *fb_rect)
+{
+	struct qxl_fbdev *qfbdev = info->par;
+	struct qxl_device *qdev = qfbdev->qdev;
+
 	if (!drm_can_sleep()) {
-		qxl_io_log(qdev,
-			"%s: TODO use RCU, mysterious locks with spin_lock\n",
-			__func__);
+		qxl_fb_delayed_fillrect(qfbdev, fb_rect);
+		schedule_work(&qdev->fb_work);
 		return;
 	}
-	qxl_draw_fill(&qxl_draw_fill_rec);
+	/* make sure any previous work is done */
+	flush_work(&qdev->fb_work);
+	qxl_fb_fillrect_internal(info, fb_rect);
 }
 
-static void qxl_fb_copyarea(struct fb_info *info,
-			    const struct fb_copyarea *region)
+static void qxl_fb_copyarea_internal(struct fb_info *info,
+				     const struct fb_copyarea *region)
 {
 	struct qxl_fbdev *qfbdev = info->par;
 
@@ -223,37 +312,89 @@ static void qxl_fb_copyarea(struct fb_info *info,
 			  region->dx, region->dy);
 }
 
+static void qxl_fb_copyarea(struct fb_info *info,
+			    const struct fb_copyarea *region)
+{
+	struct qxl_fbdev *qfbdev = info->par;
+	struct qxl_device *qdev = qfbdev->qdev;
+
+	if (!drm_can_sleep()) {
+		qxl_fb_delayed_copyarea(qfbdev, region);
+		schedule_work(&qdev->fb_work);
+		return;
+	}
+	/* make sure any previous work is done */
+	flush_work(&qdev->fb_work);
+	qxl_fb_copyarea_internal(info, region);
+}
+
 static void qxl_fb_imageblit_safe(struct qxl_fb_image *qxl_fb_image)
 {
 	qxl_draw_opaque_fb(qxl_fb_image, 0);
 }
 
+static void qxl_fb_imageblit_internal(struct fb_info *info,
+				      const struct fb_image *image)
+{
+	struct qxl_fbdev *qfbdev = info->par;
+	struct qxl_fb_image qxl_fb_image;
+
+	/* ensure proper order  rendering operations - TODO: must do this
+	 * for everything. */
+	qxl_fb_image_init(&qxl_fb_image, qfbdev->qdev, info, image);
+	qxl_fb_imageblit_safe(&qxl_fb_image);
+}
+
 static void qxl_fb_imageblit(struct fb_info *info,
 			     const struct fb_image *image)
 {
 	struct qxl_fbdev *qfbdev = info->par;
 	struct qxl_device *qdev = qfbdev->qdev;
-	struct qxl_fb_image qxl_fb_image;
 
 	if (!drm_can_sleep()) {
-		/* we cannot do any ttm_bo allocation since that will fail on
-		 * ioremap_wc..__get_vm_area_node, so queue the work item
-		 * instead This can happen from printk inside an interrupt
-		 * context, i.e.: smp_apic_timer_interrupt..check_cpu_stall */
-		qxl_io_log(qdev,
-			"%s: TODO use RCU, mysterious locks with spin_lock\n",
-			   __func__);
+		qxl_fb_delayed_imageblit(qfbdev, image);
+		schedule_work(&qdev->fb_work);
 		return;
 	}
+	/* make sure any previous work is done */
+	flush_work(&qdev->fb_work);
+	qxl_fb_imageblit_internal(info, image);
+}
 
-	/* ensure proper order of rendering operations - TODO: must do this
-	 * for everything. */
-	qxl_fb_image_init(&qxl_fb_image, qfbdev->qdev, info, image);
-	qxl_fb_imageblit_safe(&qxl_fb_image);
+static void qxl_fb_work(struct work_struct *work)
+{
+	struct qxl_device *qdev = container_of(work, struct qxl_device, fb_work);
+	unsigned long flags;
+	struct qxl_fb_op *entry, *tmp;
+	struct qxl_fbdev *qfbdev = qdev->mode_info.qfbdev;
+
+	/* since the irq context just adds entries to the end of the
+	   list dropping the lock should be fine, as entry isn't modified
+	   in the operation code */
+	spin_lock_irqsave(&qfbdev->delayed_ops_lock, flags);
+	list_for_each_entry_safe(entry, tmp, &qfbdev->delayed_ops, head) {
+		spin_unlock_irqrestore(&qfbdev->delayed_ops_lock, flags);
+		switch (entry->op_type) {
+		case QXL_FB_OP_FILLRECT:
+			qxl_fb_fillrect_internal(qfbdev->helper.fbdev, &entry->op.fr);
+			break;
+		case QXL_FB_OP_COPYAREA:
+			qxl_fb_copyarea_internal(qfbdev->helper.fbdev, &entry->op.ca);
+			break;
+		case QXL_FB_OP_IMAGEBLIT:
+			qxl_fb_imageblit_internal(qfbdev->helper.fbdev, &entry->op.ib);
+			break;
+		}
+		spin_lock_irqsave(&qfbdev->delayed_ops_lock, flags);
+		list_del(&entry->head);
+		kfree(entry);
+	}
+	spin_unlock_irqrestore(&qfbdev->delayed_ops_lock, flags);
 }
 
 int qxl_fb_init(struct qxl_device *qdev)
 {
+	INIT_WORK(&qdev->fb_work, qxl_fb_work);
 	return 0;
 }
 
@@ -536,7 +677,8 @@ int qxl_fbdev_init(struct qxl_device *qdev)
 	qfbdev->qdev = qdev;
 	qdev->mode_info.qfbdev = qfbdev;
 	qfbdev->helper.funcs = &qxl_fb_helper_funcs;
-
+	spin_lock_init(&qfbdev->delayed_ops_lock);
+	INIT_LIST_HEAD(&qfbdev->delayed_ops);
 	ret = drm_fb_helper_init(qdev->ddev, &qfbdev->helper,
 				 qxl_num_crtc /* num_crtc - QXL supports just 1 */,
 				 QXLFB_CONN_LIMIT);
diff --git a/drivers/gpu/drm/qxl/qxl_fence.c b/drivers/gpu/drm/qxl/qxl_fence.c
index 63c6715ad385..ae59e91cfb9a 100644
--- a/drivers/gpu/drm/qxl/qxl_fence.c
+++ b/drivers/gpu/drm/qxl/qxl_fence.c
@@ -49,17 +49,11 @@
 
    For some reason every so often qxl hw fails to release, things go wrong.
 */
-
-
-int qxl_fence_add_release(struct qxl_fence *qfence, uint32_t rel_id)
+/* must be called with the fence lock held */
+void qxl_fence_add_release_locked(struct qxl_fence *qfence, uint32_t rel_id)
 {
-	struct qxl_bo *bo = container_of(qfence, struct qxl_bo, fence);
-
-	spin_lock(&bo->tbo.bdev->fence_lock);
 	radix_tree_insert(&qfence->tree, rel_id, qfence);
 	qfence->num_active_releases++;
-	spin_unlock(&bo->tbo.bdev->fence_lock);
-	return 0;
 }
 
 int qxl_fence_remove_release(struct qxl_fence *qfence, uint32_t rel_id)
diff --git a/drivers/gpu/drm/qxl/qxl_gem.c b/drivers/gpu/drm/qxl/qxl_gem.c
index a235693aabba..25e1777fb0a2 100644
--- a/drivers/gpu/drm/qxl/qxl_gem.c
+++ b/drivers/gpu/drm/qxl/qxl_gem.c
@@ -55,7 +55,7 @@ int qxl_gem_object_create(struct qxl_device *qdev, int size,
 	/* At least align on page size */
 	if (alignment < PAGE_SIZE)
 		alignment = PAGE_SIZE;
-	r = qxl_bo_create(qdev, size, kernel, initial_domain, surf, &qbo);
+	r = qxl_bo_create(qdev, size, kernel, false, initial_domain, surf, &qbo);
 	if (r) {
 		if (r != -ERESTARTSYS)
 			DRM_ERROR(
diff --git a/drivers/gpu/drm/qxl/qxl_image.c b/drivers/gpu/drm/qxl/qxl_image.c
index cf856206996b..7fbcc35e8ad3 100644
--- a/drivers/gpu/drm/qxl/qxl_image.c
+++ b/drivers/gpu/drm/qxl/qxl_image.c
@@ -30,31 +30,100 @@
 #include "qxl_object.h"
 
 static int
-qxl_image_create_helper(struct qxl_device *qdev,
+qxl_allocate_chunk(struct qxl_device *qdev,
+		   struct qxl_release *release,
+		   struct qxl_drm_image *image,
+		   unsigned int chunk_size)
+{
+	struct qxl_drm_chunk *chunk;
+	int ret;
+
+	chunk = kmalloc(sizeof(struct qxl_drm_chunk), GFP_KERNEL);
+	if (!chunk)
+		return -ENOMEM;
+
+	ret = qxl_alloc_bo_reserved(qdev, release, chunk_size, &chunk->bo);
+	if (ret) {
+		kfree(chunk);
+		return ret;
+	}
+
+	list_add_tail(&chunk->head, &image->chunk_list);
+	return 0;
+}
+
+int
+qxl_image_alloc_objects(struct qxl_device *qdev,
 			struct qxl_release *release,
-			struct qxl_bo **image_bo,
-			const uint8_t *data,
-			int width, int height,
-			int depth, unsigned int hash,
-			int stride)
+			struct qxl_drm_image **image_ptr,
+			int height, int stride)
+{
+	struct qxl_drm_image *image;
+	int ret;
+
+	image = kmalloc(sizeof(struct qxl_drm_image), GFP_KERNEL);
+	if (!image)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&image->chunk_list);
+
+	ret = qxl_alloc_bo_reserved(qdev, release, sizeof(struct qxl_image), &image->bo);
+	if (ret) {
+		kfree(image);
+		return ret;
+	}
+
+	ret = qxl_allocate_chunk(qdev, release, image, sizeof(struct qxl_data_chunk) + stride * height);
+	if (ret) {
+		qxl_bo_unref(&image->bo);
+		kfree(image);
+		return ret;
+	}
+	*image_ptr = image;
+	return 0;
+}
+
+void qxl_image_free_objects(struct qxl_device *qdev, struct qxl_drm_image *dimage)
 {
+	struct qxl_drm_chunk *chunk, *tmp;
+
+	list_for_each_entry_safe(chunk, tmp, &dimage->chunk_list, head) {
+		qxl_bo_unref(&chunk->bo);
+		kfree(chunk);
+	}
+
+	qxl_bo_unref(&dimage->bo);
+	kfree(dimage);
+}
+
+static int
+qxl_image_init_helper(struct qxl_device *qdev,
+		      struct qxl_release *release,
+		      struct qxl_drm_image *dimage,
+		      const uint8_t *data,
+		      int width, int height,
+		      int depth, unsigned int hash,
+		      int stride)
+{
+	struct qxl_drm_chunk *drv_chunk;
 	struct qxl_image *image;
 	struct qxl_data_chunk *chunk;
 	int i;
 	int chunk_stride;
 	int linesize = width * depth / 8;
-	struct qxl_bo *chunk_bo;
-	int ret;
+	struct qxl_bo *chunk_bo, *image_bo;
 	void *ptr;
 	/* Chunk */
 	/* FIXME: Check integer overflow */
 	/* TODO: variable number of chunks */
+
+	drv_chunk = list_first_entry(&dimage->chunk_list, struct qxl_drm_chunk, head);
+
+	chunk_bo = drv_chunk->bo;
 	chunk_stride = stride; /* TODO: should use linesize, but it renders
 				  wrong (check the bitmaps are sent correctly
 				  first) */
-	ret = qxl_alloc_bo_reserved(qdev, sizeof(*chunk) + height * chunk_stride,
-				    &chunk_bo);
-	
+
 	ptr = qxl_bo_kmap_atomic_page(qdev, chunk_bo, 0);
 	chunk = ptr;
 	chunk->data_size = height * chunk_stride;
@@ -102,7 +171,6 @@ qxl_image_create_helper(struct qxl_device *qdev,
 				while (remain > 0) {
 					page_base = out_offset & PAGE_MASK;
 					page_offset = offset_in_page(out_offset);
-					
 					size = min((int)(PAGE_SIZE - page_offset), remain);
 
 					ptr = qxl_bo_kmap_atomic_page(qdev, chunk_bo, page_base);
@@ -116,14 +184,10 @@ qxl_image_create_helper(struct qxl_device *qdev,
 			}
 		}
 	}
-
-
 	qxl_bo_kunmap(chunk_bo);
 
-	/* Image */
-	ret = qxl_alloc_bo_reserved(qdev, sizeof(*image), image_bo);
-
-	ptr = qxl_bo_kmap_atomic_page(qdev, *image_bo, 0);
+	image_bo = dimage->bo;
+	ptr = qxl_bo_kmap_atomic_page(qdev, image_bo, 0);
 	image = ptr;
 
 	image->descriptor.id = 0;
@@ -154,23 +218,20 @@ qxl_image_create_helper(struct qxl_device *qdev,
 	image->u.bitmap.stride = chunk_stride;
 	image->u.bitmap.palette = 0;
 	image->u.bitmap.data = qxl_bo_physical_address(qdev, chunk_bo, 0);
-	qxl_release_add_res(qdev, release, chunk_bo);
-	qxl_bo_unreserve(chunk_bo);
-	qxl_bo_unref(&chunk_bo);
 
-	qxl_bo_kunmap_atomic_page(qdev, *image_bo, ptr);
+	qxl_bo_kunmap_atomic_page(qdev, image_bo, ptr);
 
 	return 0;
 }
 
-int qxl_image_create(struct qxl_device *qdev,
+int qxl_image_init(struct qxl_device *qdev,
 		     struct qxl_release *release,
-		     struct qxl_bo **image_bo,
+		     struct qxl_drm_image *dimage,
 		     const uint8_t *data,
 		     int x, int y, int width, int height,
 		     int depth, int stride)
 {
 	data += y * stride + x * (depth / 8);
-	return qxl_image_create_helper(qdev, release, image_bo, data,
+	return qxl_image_init_helper(qdev, release, dimage, data,
 				       width, height, depth, 0, stride);
 }
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 27f45e49250d..6de33563d6f1 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -68,55 +68,60 @@ static int qxl_map_ioctl(struct drm_device *dev, void *data,
 				  &qxl_map->offset);
 }
 
+struct qxl_reloc_info {
+	int type;
+	struct qxl_bo *dst_bo;
+	uint32_t dst_offset;
+	struct qxl_bo *src_bo;
+	int src_offset;
+};
+
 /*
  * dst must be validated, i.e. whole bo on vram/surfacesram (right now all bo's
  * are on vram).
  * *(dst + dst_off) = qxl_bo_physical_address(src, src_off)
  */
 static void
-apply_reloc(struct qxl_device *qdev, struct qxl_bo *dst, uint64_t dst_off,
-	    struct qxl_bo *src, uint64_t src_off)
+apply_reloc(struct qxl_device *qdev, struct qxl_reloc_info *info)
 {
 	void *reloc_page;
-
-	reloc_page = qxl_bo_kmap_atomic_page(qdev, dst, dst_off & PAGE_MASK);
-	*(uint64_t *)(reloc_page + (dst_off & ~PAGE_MASK)) = qxl_bo_physical_address(qdev,
-								     src, src_off);
-	qxl_bo_kunmap_atomic_page(qdev, dst, reloc_page);
+	reloc_page = qxl_bo_kmap_atomic_page(qdev, info->dst_bo, info->dst_offset & PAGE_MASK);
+	*(uint64_t *)(reloc_page + (info->dst_offset & ~PAGE_MASK)) = qxl_bo_physical_address(qdev,
+											      info->src_bo,
+											      info->src_offset);
+	qxl_bo_kunmap_atomic_page(qdev, info->dst_bo, reloc_page);
 }
 
 static void
-apply_surf_reloc(struct qxl_device *qdev, struct qxl_bo *dst, uint64_t dst_off,
-		 struct qxl_bo *src)
+apply_surf_reloc(struct qxl_device *qdev, struct qxl_reloc_info *info)
 {
 	uint32_t id = 0;
 	void *reloc_page;
 
-	if (src && !src->is_primary)
-		id = src->surface_id;
+	if (info->src_bo && !info->src_bo->is_primary)
+		id = info->src_bo->surface_id;
 
-	reloc_page = qxl_bo_kmap_atomic_page(qdev, dst, dst_off & PAGE_MASK);
-	*(uint32_t *)(reloc_page + (dst_off & ~PAGE_MASK)) = id;
-	qxl_bo_kunmap_atomic_page(qdev, dst, reloc_page);
+	reloc_page = qxl_bo_kmap_atomic_page(qdev, info->dst_bo, info->dst_offset & PAGE_MASK);
+	*(uint32_t *)(reloc_page + (info->dst_offset & ~PAGE_MASK)) = id;
+	qxl_bo_kunmap_atomic_page(qdev, info->dst_bo, reloc_page);
 }
 
 /* return holding the reference to this object */
 static struct qxl_bo *qxlhw_handle_to_bo(struct qxl_device *qdev,
 					 struct drm_file *file_priv, uint64_t handle,
-					 struct qxl_reloc_list *reloc_list)
+					 struct qxl_release *release)
 {
 	struct drm_gem_object *gobj;
 	struct qxl_bo *qobj;
 	int ret;
 
 	gobj = drm_gem_object_lookup(qdev->ddev, file_priv, handle);
-	if (!gobj) {
-		DRM_ERROR("bad bo handle %lld\n", handle);
+	if (!gobj)
 		return NULL;
-	}
+
 	qobj = gem_to_qxl_bo(gobj);
 
-	ret = qxl_bo_list_add(reloc_list, qobj);
+	ret = qxl_release_list_add(release, qobj);
 	if (ret)
 		return NULL;
 
@@ -129,151 +134,177 @@ static struct qxl_bo *qxlhw_handle_to_bo(struct qxl_device *qdev,
  * However, the command as passed from user space must *not* contain the initial
  * QXLReleaseInfo struct (first XXX bytes)
  */
-static int qxl_execbuffer_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *file_priv)
+static int qxl_process_single_command(struct qxl_device *qdev,
+				      struct drm_qxl_command *cmd,
+				      struct drm_file *file_priv)
 {
-	struct qxl_device *qdev = dev->dev_private;
-	struct drm_qxl_execbuffer *execbuffer = data;
-	struct drm_qxl_command user_cmd;
-	int cmd_num;
-	struct qxl_bo *reloc_src_bo;
-	struct qxl_bo *reloc_dst_bo;
-	struct drm_qxl_reloc reloc;
+	struct qxl_reloc_info *reloc_info;
+	int release_type;
+	struct qxl_release *release;
+	struct qxl_bo *cmd_bo;
 	void *fb_cmd;
-	int i, ret;
-	struct qxl_reloc_list reloc_list;
+	int i, j, ret, num_relocs;
 	int unwritten;
-	uint32_t reloc_dst_offset;
-	INIT_LIST_HEAD(&reloc_list.bos);
 
-	for (cmd_num = 0; cmd_num < execbuffer->commands_num; ++cmd_num) {
-		struct qxl_release *release;
-		struct qxl_bo *cmd_bo;
-		int release_type;
-		struct drm_qxl_command *commands =
-			(struct drm_qxl_command *)(uintptr_t)execbuffer->commands;
+	switch (cmd->type) {
+	case QXL_CMD_DRAW:
+		release_type = QXL_RELEASE_DRAWABLE;
+		break;
+	case QXL_CMD_SURFACE:
+	case QXL_CMD_CURSOR:
+	default:
+		DRM_DEBUG("Only draw commands in execbuffers\n");
+		return -EINVAL;
+		break;
+	}
 
-		if (DRM_COPY_FROM_USER(&user_cmd, &commands[cmd_num],
-				       sizeof(user_cmd)))
-			return -EFAULT;
-		switch (user_cmd.type) {
-		case QXL_CMD_DRAW:
-			release_type = QXL_RELEASE_DRAWABLE;
-			break;
-		case QXL_CMD_SURFACE:
-		case QXL_CMD_CURSOR:
-		default:
-			DRM_DEBUG("Only draw commands in execbuffers\n");
-			return -EINVAL;
-			break;
-		}
+	if (cmd->command_size > PAGE_SIZE - sizeof(union qxl_release_info))
+		return -EINVAL;
 
-		if (user_cmd.command_size > PAGE_SIZE - sizeof(union qxl_release_info))
-			return -EINVAL;
+	if (!access_ok(VERIFY_READ,
+		       (void *)(unsigned long)cmd->command,
+		       cmd->command_size))
+		return -EFAULT;
 
-		if (!access_ok(VERIFY_READ,
-			       (void *)(unsigned long)user_cmd.command,
-			       user_cmd.command_size))
-			return -EFAULT;
+	reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL);
+	if (!reloc_info)
+		return -ENOMEM;
 
-		ret = qxl_alloc_release_reserved(qdev,
-						 sizeof(union qxl_release_info) +
-						 user_cmd.command_size,
-						 release_type,
-						 &release,
-						 &cmd_bo);
-		if (ret)
-			return ret;
+	ret = qxl_alloc_release_reserved(qdev,
+					 sizeof(union qxl_release_info) +
+					 cmd->command_size,
+					 release_type,
+					 &release,
+					 &cmd_bo);
+	if (ret)
+		goto out_free_reloc;
 
-		/* TODO copy slow path code from i915 */
-		fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_SIZE));
-		unwritten = __copy_from_user_inatomic_nocache(fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_SIZE), (void *)(unsigned long)user_cmd.command, user_cmd.command_size);
+	/* TODO copy slow path code from i915 */
+	fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_SIZE));
+	unwritten = __copy_from_user_inatomic_nocache(fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_SIZE), (void *)(unsigned long)cmd->command, cmd->command_size);
 
-		{
-			struct qxl_drawable *draw = fb_cmd;
+	{
+		struct qxl_drawable *draw = fb_cmd;
+		draw->mm_time = qdev->rom->mm_clock;
+	}
 
-			draw->mm_time = qdev->rom->mm_clock;
-		}
-		qxl_bo_kunmap_atomic_page(qdev, cmd_bo, fb_cmd);
-		if (unwritten) {
-			DRM_ERROR("got unwritten %d\n", unwritten);
-			qxl_release_unreserve(qdev, release);
-			qxl_release_free(qdev, release);
-			return -EFAULT;
+	qxl_bo_kunmap_atomic_page(qdev, cmd_bo, fb_cmd);
+	if (unwritten) {
+		DRM_ERROR("got unwritten %d\n", unwritten);
+		ret = -EFAULT;
+		goto out_free_release;
+	}
+
+	/* fill out reloc info structs */
+	num_relocs = 0;
+	for (i = 0; i < cmd->relocs_num; ++i) {
+		struct drm_qxl_reloc reloc;
+
+		if (DRM_COPY_FROM_USER(&reloc,
+				       &((struct drm_qxl_reloc *)(uintptr_t)cmd->relocs)[i],
+				       sizeof(reloc))) {
+			ret = -EFAULT;
+			goto out_free_bos;
 		}
 
-		for (i = 0 ; i < user_cmd.relocs_num; ++i) {
-			if (DRM_COPY_FROM_USER(&reloc,
-					       &((struct drm_qxl_reloc *)(uintptr_t)user_cmd.relocs)[i],
-					       sizeof(reloc))) {
-				qxl_bo_list_unreserve(&reloc_list, true);
-				qxl_release_unreserve(qdev, release);
-				qxl_release_free(qdev, release);
-				return -EFAULT;
-			}
+		/* add the bos to the list of bos to validate -
+		   need to validate first then process relocs? */
+		if (reloc.reloc_type != QXL_RELOC_TYPE_BO && reloc.reloc_type != QXL_RELOC_TYPE_SURF) {
+			DRM_DEBUG("unknown reloc type %d\n", reloc_info[i].type);
 
-			/* add the bos to the list of bos to validate -
-			   need to validate first then process relocs? */
-			if (reloc.dst_handle) {
-				reloc_dst_bo = qxlhw_handle_to_bo(qdev, file_priv,
-								  reloc.dst_handle, &reloc_list);
-				if (!reloc_dst_bo) {
-					qxl_bo_list_unreserve(&reloc_list, true);
-					qxl_release_unreserve(qdev, release);
-					qxl_release_free(qdev, release);
-					return -EINVAL;
-				}
-				reloc_dst_offset = 0;
-			} else {
-				reloc_dst_bo = cmd_bo;
-				reloc_dst_offset = release->release_offset;
+			ret = -EINVAL;
+			goto out_free_bos;
+		}
+		reloc_info[i].type = reloc.reloc_type;
+
+		if (reloc.dst_handle) {
+			reloc_info[i].dst_bo = qxlhw_handle_to_bo(qdev, file_priv,
+								  reloc.dst_handle, release);
+			if (!reloc_info[i].dst_bo) {
+				ret = -EINVAL;
+				reloc_info[i].src_bo = NULL;
+				goto out_free_bos;
 			}
-
-			/* reserve and validate the reloc dst bo */
-			if (reloc.reloc_type == QXL_RELOC_TYPE_BO || reloc.src_handle > 0) {
-				reloc_src_bo =
-					qxlhw_handle_to_bo(qdev, file_priv,
-							   reloc.src_handle, &reloc_list);
-				if (!reloc_src_bo) {
-					if (reloc_dst_bo != cmd_bo)
-						drm_gem_object_unreference_unlocked(&reloc_dst_bo->gem_base);
-					qxl_bo_list_unreserve(&reloc_list, true);
-					qxl_release_unreserve(qdev, release);
-					qxl_release_free(qdev, release);
-					return -EINVAL;
-				}
-			} else
-				reloc_src_bo = NULL;
-			if (reloc.reloc_type == QXL_RELOC_TYPE_BO) {
-				apply_reloc(qdev, reloc_dst_bo, reloc_dst_offset + reloc.dst_offset,
-					    reloc_src_bo, reloc.src_offset);
-			} else if (reloc.reloc_type == QXL_RELOC_TYPE_SURF) {
-				apply_surf_reloc(qdev, reloc_dst_bo, reloc_dst_offset + reloc.dst_offset, reloc_src_bo);
-			} else {
-				DRM_ERROR("unknown reloc type %d\n", reloc.reloc_type);
-				return -EINVAL;
+			reloc_info[i].dst_offset = reloc.dst_offset;
+		} else {
+			reloc_info[i].dst_bo = cmd_bo;
+			reloc_info[i].dst_offset = reloc.dst_offset + release->release_offset;
+		}
+		num_relocs++;
+
+		/* reserve and validate the reloc dst bo */
+		if (reloc.reloc_type == QXL_RELOC_TYPE_BO || reloc.src_handle > 0) {
+			reloc_info[i].src_bo =
+				qxlhw_handle_to_bo(qdev, file_priv,
+						   reloc.src_handle, release);
+			if (!reloc_info[i].src_bo) {
+				if (reloc_info[i].dst_bo != cmd_bo)
+					drm_gem_object_unreference_unlocked(&reloc_info[i].dst_bo->gem_base);
+				ret = -EINVAL;
+				goto out_free_bos;
 			}
+			reloc_info[i].src_offset = reloc.src_offset;
+		} else {
+			reloc_info[i].src_bo = NULL;
+			reloc_info[i].src_offset = 0;
+		}
+	}
 
-			if (reloc_src_bo && reloc_src_bo != cmd_bo) {
-				qxl_release_add_res(qdev, release, reloc_src_bo);
-				drm_gem_object_unreference_unlocked(&reloc_src_bo->gem_base);
-			}
+	/* validate all buffers */
+	ret = qxl_release_reserve_list(release, false);
+	if (ret)
+		goto out_free_bos;
 
-			if (reloc_dst_bo != cmd_bo)
-				drm_gem_object_unreference_unlocked(&reloc_dst_bo->gem_base);
-		}
-		qxl_fence_releaseable(qdev, release);
+	for (i = 0; i < cmd->relocs_num; ++i) {
+		if (reloc_info[i].type == QXL_RELOC_TYPE_BO)
+			apply_reloc(qdev, &reloc_info[i]);
+		else if (reloc_info[i].type == QXL_RELOC_TYPE_SURF)
+			apply_surf_reloc(qdev, &reloc_info[i]);
+	}
 
-		ret = qxl_push_command_ring_release(qdev, release, user_cmd.type, true);
-		if (ret == -ERESTARTSYS) {
-			qxl_release_unreserve(qdev, release);
-			qxl_release_free(qdev, release);
-			qxl_bo_list_unreserve(&reloc_list, true);
+	ret = qxl_push_command_ring_release(qdev, release, cmd->type, true);
+	if (ret)
+		qxl_release_backoff_reserve_list(release);
+	else
+		qxl_release_fence_buffer_objects(release);
+
+out_free_bos:
+	for (j = 0; j < num_relocs; j++) {
+		if (reloc_info[j].dst_bo != cmd_bo)
+			drm_gem_object_unreference_unlocked(&reloc_info[j].dst_bo->gem_base);
+		if (reloc_info[j].src_bo && reloc_info[j].src_bo != cmd_bo)
+			drm_gem_object_unreference_unlocked(&reloc_info[j].src_bo->gem_base);
+	}
+out_free_release:
+	if (ret)
+		qxl_release_free(qdev, release);
+out_free_reloc:
+	kfree(reloc_info);
+	return ret;
+}
+
+static int qxl_execbuffer_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	struct qxl_device *qdev = dev->dev_private;
+	struct drm_qxl_execbuffer *execbuffer = data;
+	struct drm_qxl_command user_cmd;
+	int cmd_num;
+	int ret;
+
+	for (cmd_num = 0; cmd_num < execbuffer->commands_num; ++cmd_num) {
+
+		struct drm_qxl_command *commands =
+			(struct drm_qxl_command *)(uintptr_t)execbuffer->commands;
+
+		if (DRM_COPY_FROM_USER(&user_cmd, &commands[cmd_num],
+				       sizeof(user_cmd)))
+			return -EFAULT;
+
+		ret = qxl_process_single_command(qdev, &user_cmd, file_priv);
+		if (ret)
 			return ret;
-		}
-		qxl_release_unreserve(qdev, release);
 	}
-	qxl_bo_list_unreserve(&reloc_list, 0);
 	return 0;
 }
 
@@ -305,7 +336,7 @@ static int qxl_update_area_ioctl(struct drm_device *dev, void *data,
 		goto out;
 
 	if (!qobj->pin_count) {
-		qxl_ttm_placement_from_domain(qobj, qobj->type);
+		qxl_ttm_placement_from_domain(qobj, qobj->type, false);
 		ret = ttm_bo_validate(&qobj->tbo, &qobj->placement,
 				      true, false);
 		if (unlikely(ret))
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index 1191fe7788c9..aa161cddd87e 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -51,20 +51,21 @@ bool qxl_ttm_bo_is_qxl_bo(struct ttm_buffer_object *bo)
 	return false;
 }
 
-void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain)
+void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain, bool pinned)
 {
 	u32 c = 0;
+	u32 pflag = pinned ? TTM_PL_FLAG_NO_EVICT : 0;
 
 	qbo->placement.fpfn = 0;
 	qbo->placement.lpfn = 0;
 	qbo->placement.placement = qbo->placements;
 	qbo->placement.busy_placement = qbo->placements;
 	if (domain == QXL_GEM_DOMAIN_VRAM)
-		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM;
+		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM | pflag;
 	if (domain == QXL_GEM_DOMAIN_SURFACE)
-		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_PRIV0;
+		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_PRIV0 | pflag;
 	if (domain == QXL_GEM_DOMAIN_CPU)
-		qbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		qbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM | pflag;
 	if (!c)
 		qbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	qbo->placement.num_placement = c;
@@ -73,7 +74,7 @@ void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain)
 
 
 int qxl_bo_create(struct qxl_device *qdev,
-		  unsigned long size, bool kernel, u32 domain,
+		  unsigned long size, bool kernel, bool pinned, u32 domain,
 		  struct qxl_surface *surf,
 		  struct qxl_bo **bo_ptr)
 {
@@ -99,15 +100,15 @@ int qxl_bo_create(struct qxl_device *qdev,
 	}
 	bo->gem_base.driver_private = NULL;
 	bo->type = domain;
-	bo->pin_count = 0;
+	bo->pin_count = pinned ? 1 : 0;
 	bo->surface_id = 0;
 	qxl_fence_init(qdev, &bo->fence);
 	INIT_LIST_HEAD(&bo->list);
-	atomic_set(&bo->reserve_count, 0);
+
 	if (surf)
 		bo->surf = *surf;
 
-	qxl_ttm_placement_from_domain(bo, domain);
+	qxl_ttm_placement_from_domain(bo, domain, pinned);
 
 	r = ttm_bo_init(&qdev->mman.bdev, &bo->tbo, size, type,
 			&bo->placement, 0, !kernel, NULL, size,
@@ -228,7 +229,7 @@ struct qxl_bo *qxl_bo_ref(struct qxl_bo *bo)
 int qxl_bo_pin(struct qxl_bo *bo, u32 domain, u64 *gpu_addr)
 {
 	struct qxl_device *qdev = (struct qxl_device *)bo->gem_base.dev->dev_private;
-	int r, i;
+	int r;
 
 	if (bo->pin_count) {
 		bo->pin_count++;
@@ -236,9 +237,7 @@ int qxl_bo_pin(struct qxl_bo *bo, u32 domain, u64 *gpu_addr)
 			*gpu_addr = qxl_bo_gpu_offset(bo);
 		return 0;
 	}
-	qxl_ttm_placement_from_domain(bo, domain);
-	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+	qxl_ttm_placement_from_domain(bo, domain, true);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (likely(r == 0)) {
 		bo->pin_count = 1;
@@ -317,53 +316,6 @@ int qxl_bo_check_id(struct qxl_device *qdev, struct qxl_bo *bo)
 	return 0;
 }
 
-void qxl_bo_list_unreserve(struct qxl_reloc_list *reloc_list, bool failed)
-{
-	struct qxl_bo_list *entry, *sf;
-
-	list_for_each_entry_safe(entry, sf, &reloc_list->bos, lhead) {
-		qxl_bo_unreserve(entry->bo);
-		list_del(&entry->lhead);
-		kfree(entry);
-	}
-}
-
-int qxl_bo_list_add(struct qxl_reloc_list *reloc_list, struct qxl_bo *bo)
-{
-	struct qxl_bo_list *entry;
-	int ret;
-
-	list_for_each_entry(entry, &reloc_list->bos, lhead) {
-		if (entry->bo == bo)
-			return 0;
-	}
-
-	entry = kmalloc(sizeof(struct qxl_bo_list), GFP_KERNEL);
-	if (!entry)
-		return -ENOMEM;
-
-	entry->bo = bo;
-	list_add(&entry->lhead, &reloc_list->bos);
-
-	ret = qxl_bo_reserve(bo, false);
-	if (ret)
-		return ret;
-
-	if (!bo->pin_count) {
-		qxl_ttm_placement_from_domain(bo, bo->type);
-		ret = ttm_bo_validate(&bo->tbo, &bo->placement,
-				      true, false);
-		if (ret)
-			return ret;
-	}
-
-	/* allocate a surface for reserved + validated buffers */
-	ret = qxl_bo_check_id(bo->gem_base.dev->dev_private, bo);
-	if (ret)
-		return ret;
-	return 0;
-}
-
 int qxl_surf_evict(struct qxl_device *qdev)
 {
 	return ttm_bo_evict_mm(&qdev->mman.bdev, TTM_PL_PRIV0);
diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h
index ee7ad79ce781..8cb6167038e5 100644
--- a/drivers/gpu/drm/qxl/qxl_object.h
+++ b/drivers/gpu/drm/qxl/qxl_object.h
@@ -88,7 +88,7 @@ static inline int qxl_bo_wait(struct qxl_bo *bo, u32 *mem_type,
 
 extern int qxl_bo_create(struct qxl_device *qdev,
 			 unsigned long size,
-			 bool kernel, u32 domain,
+			 bool kernel, bool pinned, u32 domain,
 			 struct qxl_surface *surf,
 			 struct qxl_bo **bo_ptr);
 extern int qxl_bo_kmap(struct qxl_bo *bo, void **ptr);
@@ -99,9 +99,7 @@ extern struct qxl_bo *qxl_bo_ref(struct qxl_bo *bo);
 extern void qxl_bo_unref(struct qxl_bo **bo);
 extern int qxl_bo_pin(struct qxl_bo *bo, u32 domain, u64 *gpu_addr);
 extern int qxl_bo_unpin(struct qxl_bo *bo);
-extern void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain);
+extern void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain, bool pinned);
 extern bool qxl_ttm_bo_is_qxl_bo(struct ttm_buffer_object *bo);
 
-extern int qxl_bo_list_add(struct qxl_reloc_list *reloc_list, struct qxl_bo *bo);
-extern void qxl_bo_list_unreserve(struct qxl_reloc_list *reloc_list, bool failed);
 #endif
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index b443d6751d5f..b61449e52cd5 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -38,7 +38,8 @@
 
 static const int release_size_per_bo[] = { RELEASE_SIZE, SURFACE_RELEASE_SIZE, RELEASE_SIZE };
 static const int releases_per_bo[] = { RELEASES_PER_BO, SURFACE_RELEASES_PER_BO, RELEASES_PER_BO };
-uint64_t
+
+static uint64_t
 qxl_release_alloc(struct qxl_device *qdev, int type,
 		  struct qxl_release **ret)
 {
@@ -53,9 +54,9 @@ qxl_release_alloc(struct qxl_device *qdev, int type,
 		return 0;
 	}
 	release->type = type;
-	release->bo_count = 0;
 	release->release_offset = 0;
 	release->surface_release_id = 0;
+	INIT_LIST_HEAD(&release->bos);
 
 	idr_preload(GFP_KERNEL);
 	spin_lock(&qdev->release_idr_lock);
@@ -77,20 +78,20 @@ void
 qxl_release_free(struct qxl_device *qdev,
 		 struct qxl_release *release)
 {
-	int i;
-
-	QXL_INFO(qdev, "release %d, type %d, %d bos\n", release->id,
-		 release->type, release->bo_count);
+	struct qxl_bo_list *entry, *tmp;
+	QXL_INFO(qdev, "release %d, type %d\n", release->id,
+		 release->type);
 
 	if (release->surface_release_id)
 		qxl_surface_id_dealloc(qdev, release->surface_release_id);
 
-	for (i = 0 ; i < release->bo_count; ++i) {
+	list_for_each_entry_safe(entry, tmp, &release->bos, tv.head) {
+		struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
 		QXL_INFO(qdev, "release %llx\n",
-			release->bos[i]->tbo.addr_space_offset
+			entry->tv.bo->addr_space_offset
 						- DRM_FILE_OFFSET);
-		qxl_fence_remove_release(&release->bos[i]->fence, release->id);
-		qxl_bo_unref(&release->bos[i]);
+		qxl_fence_remove_release(&bo->fence, release->id);
+		qxl_bo_unref(&bo);
 	}
 	spin_lock(&qdev->release_idr_lock);
 	idr_remove(&qdev->release_idr, release->id);
@@ -98,83 +99,117 @@ qxl_release_free(struct qxl_device *qdev,
 	kfree(release);
 }
 
-void
-qxl_release_add_res(struct qxl_device *qdev, struct qxl_release *release,
-		    struct qxl_bo *bo)
-{
-	int i;
-	for (i = 0; i < release->bo_count; i++)
-		if (release->bos[i] == bo)
-			return;
-
-	if (release->bo_count >= QXL_MAX_RES) {
-		DRM_ERROR("exceeded max resource on a qxl_release item\n");
-		return;
-	}
-	release->bos[release->bo_count++] = qxl_bo_ref(bo);
-}
-
 static int qxl_release_bo_alloc(struct qxl_device *qdev,
 				struct qxl_bo **bo)
 {
 	int ret;
-	ret = qxl_bo_create(qdev, PAGE_SIZE, false, QXL_GEM_DOMAIN_VRAM, NULL,
+	/* pin releases bo's they are too messy to evict */
+	ret = qxl_bo_create(qdev, PAGE_SIZE, false, true,
+			    QXL_GEM_DOMAIN_VRAM, NULL,
 			    bo);
 	return ret;
 }
 
-int qxl_release_reserve(struct qxl_device *qdev,
-			struct qxl_release *release, bool no_wait)
+int qxl_release_list_add(struct qxl_release *release, struct qxl_bo *bo)
+{
+	struct qxl_bo_list *entry;
+
+	list_for_each_entry(entry, &release->bos, tv.head) {
+		if (entry->tv.bo == &bo->tbo)
+			return 0;
+	}
+
+	entry = kmalloc(sizeof(struct qxl_bo_list), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	qxl_bo_ref(bo);
+	entry->tv.bo = &bo->tbo;
+	list_add_tail(&entry->tv.head, &release->bos);
+	return 0;
+}
+
+static int qxl_release_validate_bo(struct qxl_bo *bo)
 {
 	int ret;
-	if (atomic_inc_return(&release->bos[0]->reserve_count) == 1) {
-		ret = qxl_bo_reserve(release->bos[0], no_wait);
+
+	if (!bo->pin_count) {
+		qxl_ttm_placement_from_domain(bo, bo->type, false);
+		ret = ttm_bo_validate(&bo->tbo, &bo->placement,
+				      true, false);
 		if (ret)
 			return ret;
 	}
+
+	/* allocate a surface for reserved + validated buffers */
+	ret = qxl_bo_check_id(bo->gem_base.dev->dev_private, bo);
+	if (ret)
+		return ret;
+	return 0;
+}
+
+int qxl_release_reserve_list(struct qxl_release *release, bool no_intr)
+{
+	int ret;
+	struct qxl_bo_list *entry;
+
+	/* if only one object on the release its the release itself
+	   since these objects are pinned no need to reserve */
+	if (list_is_singular(&release->bos))
+		return 0;
+
+	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(entry, &release->bos, tv.head) {
+		struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
+
+		ret = qxl_release_validate_bo(bo);
+		if (ret) {
+			ttm_eu_backoff_reservation(&release->ticket, &release->bos);
+			return ret;
+		}
+	}
 	return 0;
 }
 
-void qxl_release_unreserve(struct qxl_device *qdev,
-			  struct qxl_release *release)
+void qxl_release_backoff_reserve_list(struct qxl_release *release)
 {
-	if (atomic_dec_and_test(&release->bos[0]->reserve_count))
-		qxl_bo_unreserve(release->bos[0]);
+	/* if only one object on the release its the release itself
+	   since these objects are pinned no need to reserve */
+	if (list_is_singular(&release->bos))
+		return;
+
+	ttm_eu_backoff_reservation(&release->ticket, &release->bos);
 }
 
+
 int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
 				       enum qxl_surface_cmd_type surface_cmd_type,
 				       struct qxl_release *create_rel,
 				       struct qxl_release **release)
 {
-	int ret;
-
 	if (surface_cmd_type == QXL_SURFACE_CMD_DESTROY && create_rel) {
 		int idr_ret;
+		struct qxl_bo_list *entry = list_first_entry(&create_rel->bos, struct qxl_bo_list, tv.head);
 		struct qxl_bo *bo;
 		union qxl_release_info *info;
 
 		/* stash the release after the create command */
 		idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release);
-		bo = qxl_bo_ref(create_rel->bos[0]);
+		bo = qxl_bo_ref(to_qxl_bo(entry->tv.bo));
 
 		(*release)->release_offset = create_rel->release_offset + 64;
 
-		qxl_release_add_res(qdev, *release, bo);
+		qxl_release_list_add(*release, bo);
 
-		ret = qxl_release_reserve(qdev, *release, false);
-		if (ret) {
-			DRM_ERROR("release reserve failed\n");
-			goto out_unref;
-		}
 		info = qxl_release_map(qdev, *release);
 		info->id = idr_ret;
 		qxl_release_unmap(qdev, *release, info);
 
-
-out_unref:
 		qxl_bo_unref(&bo);
-		return ret;
+		return 0;
 	}
 
 	return qxl_alloc_release_reserved(qdev, sizeof(struct qxl_surface_cmd),
@@ -187,7 +222,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 {
 	struct qxl_bo *bo;
 	int idr_ret;
-	int ret;
+	int ret = 0;
 	union qxl_release_info *info;
 	int cur_idx;
 
@@ -216,11 +251,6 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 			mutex_unlock(&qdev->release_mutex);
 			return ret;
 		}
-
-		/* pin releases bo's they are too messy to evict */
-		ret = qxl_bo_reserve(qdev->current_release_bo[cur_idx], false);
-		qxl_bo_pin(qdev->current_release_bo[cur_idx], QXL_GEM_DOMAIN_VRAM, NULL);
-		qxl_bo_unreserve(qdev->current_release_bo[cur_idx]);
 	}
 
 	bo = qxl_bo_ref(qdev->current_release_bo[cur_idx]);
@@ -231,36 +261,18 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 	if (rbo)
 		*rbo = bo;
 
-	qxl_release_add_res(qdev, *release, bo);
-
-	ret = qxl_release_reserve(qdev, *release, false);
 	mutex_unlock(&qdev->release_mutex);
-	if (ret)
-		goto out_unref;
+
+	qxl_release_list_add(*release, bo);
 
 	info = qxl_release_map(qdev, *release);
 	info->id = idr_ret;
 	qxl_release_unmap(qdev, *release, info);
 
-out_unref:
 	qxl_bo_unref(&bo);
 	return ret;
 }
 
-int qxl_fence_releaseable(struct qxl_device *qdev,
-			  struct qxl_release *release)
-{
-	int i, ret;
-	for (i = 0; i < release->bo_count; i++) {
-		if (!release->bos[i]->tbo.sync_obj)
-			release->bos[i]->tbo.sync_obj = &release->bos[i]->fence;
-		ret = qxl_fence_add_release(&release->bos[i]->fence, release->id);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
 struct qxl_release *qxl_release_from_id_locked(struct qxl_device *qdev,
 						   uint64_t id)
 {
@@ -273,10 +285,7 @@ struct qxl_release *qxl_release_from_id_locked(struct qxl_device *qdev,
 		DRM_ERROR("failed to find id in release_idr\n");
 		return NULL;
 	}
-	if (release->bo_count < 1) {
-		DRM_ERROR("read a released resource with 0 bos\n");
-		return NULL;
-	}
+
 	return release;
 }
 
@@ -285,9 +294,12 @@ union qxl_release_info *qxl_release_map(struct qxl_device *qdev,
 {
 	void *ptr;
 	union qxl_release_info *info;
-	struct qxl_bo *bo = release->bos[0];
+	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
+	struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
 
 	ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_SIZE);
+	if (!ptr)
+		return NULL;
 	info = ptr + (release->release_offset & ~PAGE_SIZE);
 	return info;
 }
@@ -296,9 +308,51 @@ void qxl_release_unmap(struct qxl_device *qdev,
 		       struct qxl_release *release,
 		       union qxl_release_info *info)
 {
-	struct qxl_bo *bo = release->bos[0];
+	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
+	struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
 	void *ptr;
 
 	ptr = ((void *)info) - (release->release_offset & ~PAGE_SIZE);
 	qxl_bo_kunmap_atomic_page(qdev, bo, ptr);
 }
+
+void qxl_release_fence_buffer_objects(struct qxl_release *release)
+{
+	struct ttm_validate_buffer *entry;
+	struct ttm_buffer_object *bo;
+	struct ttm_bo_global *glob;
+	struct ttm_bo_device *bdev;
+	struct ttm_bo_driver *driver;
+	struct qxl_bo *qbo;
+
+	/* if only one object on the release its the release itself
+	   since these objects are pinned no need to reserve */
+	if (list_is_singular(&release->bos))
+		return;
+
+	bo = list_first_entry(&release->bos, struct ttm_validate_buffer, head)->bo;
+	bdev = bo->bdev;
+	driver = bdev->driver;
+	glob = bo->glob;
+
+	spin_lock(&glob->lru_lock);
+	spin_lock(&bdev->fence_lock);
+
+	list_for_each_entry(entry, &release->bos, head) {
+		bo = entry->bo;
+		qbo = to_qxl_bo(bo);
+
+		if (!entry->bo->sync_obj)
+			entry->bo->sync_obj = &qbo->fence;
+
+		qxl_fence_add_release_locked(&qbo->fence, release->id);
+
+		ttm_bo_add_to_lru(bo);
+		ww_mutex_unlock(&bo->resv->lock);
+		entry->reserved = false;
+	}
+	spin_unlock(&bdev->fence_lock);
+	spin_unlock(&glob->lru_lock);
+	ww_acquire_fini(&release->ticket);
+}
+
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 489cb8cece4d..1dfd84cda2a1 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -206,7 +206,7 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 		return;
 	}
 	qbo = container_of(bo, struct qxl_bo, tbo);
-	qxl_ttm_placement_from_domain(qbo, QXL_GEM_DOMAIN_CPU);
+	qxl_ttm_placement_from_domain(qbo, QXL_GEM_DOMAIN_CPU, false);
 	*placement = qbo->placement;
 }
 
diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c
index fb441a790f3d..15da7ef344a4 100644
--- a/drivers/gpu/drm/radeon/atom.c
+++ b/drivers/gpu/drm/radeon/atom.c
@@ -1222,12 +1222,17 @@ int atom_execute_table(struct atom_context *ctx, int index, uint32_t * params)
 	int r;
 
 	mutex_lock(&ctx->mutex);
+	/* reset data block */
+	ctx->data_block = 0;
 	/* reset reg block */
 	ctx->reg_block = 0;
 	/* reset fb window */
 	ctx->fb_base = 0;
 	/* reset io mode */
 	ctx->io_mode = ATOM_IO_MM;
+	/* reset divmul */
+	ctx->divmul[0] = 0;
+	ctx->divmul[1] = 0;
 	r = atom_execute_table_locked(ctx, index, params);
 	mutex_unlock(&ctx->mutex);
 	return r;
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 064023bed480..32501f6ec991 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -44,6 +44,41 @@ static char *pre_emph_names[] = {
 };
 
 /***** radeon AUX functions *****/
+
+/* Atom needs data in little endian format
+ * so swap as appropriate when copying data to
+ * or from atom. Note that atom operates on
+ * dw units.
+ */
+static void radeon_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
+{
+#ifdef __BIG_ENDIAN
+	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
+	u32 *dst32, *src32;
+	int i;
+
+	memcpy(src_tmp, src, num_bytes);
+	src32 = (u32 *)src_tmp;
+	dst32 = (u32 *)dst_tmp;
+	if (to_le) {
+		for (i = 0; i < ((num_bytes + 3) / 4); i++)
+			dst32[i] = cpu_to_le32(src32[i]);
+		memcpy(dst, dst_tmp, num_bytes);
+	} else {
+		u8 dws = num_bytes & ~3;
+		for (i = 0; i < ((num_bytes + 3) / 4); i++)
+			dst32[i] = le32_to_cpu(src32[i]);
+		memcpy(dst, dst_tmp, dws);
+		if (num_bytes % 4) {
+			for (i = 0; i < (num_bytes % 4); i++)
+				dst[dws+i] = dst_tmp[dws+i];
+		}
+	}
+#else
+	memcpy(dst, src, num_bytes);
+#endif
+}
+
 union aux_channel_transaction {
 	PROCESS_AUX_CHANNEL_TRANSACTION_PS_ALLOCATION v1;
 	PROCESS_AUX_CHANNEL_TRANSACTION_PARAMETERS_V2 v2;
@@ -65,10 +100,10 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 
 	base = (unsigned char *)(rdev->mode_info.atom_context->scratch + 1);
 
-	memcpy(base, send, send_bytes);
+	radeon_copy_swap(base, send, send_bytes, true);
 
-	args.v1.lpAuxRequest = 0 + 4;
-	args.v1.lpDataOut = 16 + 4;
+	args.v1.lpAuxRequest = cpu_to_le16((u16)(0 + 4));
+	args.v1.lpDataOut = cpu_to_le16((u16)(16 + 4));
 	args.v1.ucDataOutLen = 0;
 	args.v1.ucChannelID = chan->rec.i2c_id;
 	args.v1.ucDelay = delay / 10;
@@ -102,7 +137,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 		recv_bytes = recv_size;
 
 	if (recv && recv_size)
-		memcpy(recv, base + 16, recv_bytes);
+		radeon_copy_swap(recv, base + 16, recv_bytes, false);
 
 	return recv_bytes;
 }
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index 0bfd55e08820..9953e1fbc46d 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -2548,9 +2548,6 @@ int btc_dpm_init(struct radeon_device *rdev)
 {
 	struct rv7xx_power_info *pi;
 	struct evergreen_power_info *eg_pi;
-	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
-	u16 data_offset, size;
-	u8 frev, crev;
 	struct atom_clock_dividers dividers;
 	int ret;
 
@@ -2633,16 +2630,7 @@ int btc_dpm_init(struct radeon_device *rdev)
 	eg_pi->vddci_control =
 		radeon_atom_is_voltage_gpio(rdev, SET_VOLTAGE_TYPE_ASIC_VDDCI, 0);
 
-	if (atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
-                                   &frev, &crev, &data_offset)) {
-		pi->sclk_ss = true;
-		pi->mclk_ss = true;
-		pi->dynamic_ss = true;
-	} else {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
-		pi->dynamic_ss = true;
-	}
+	rv770_get_engine_memory_ss(rdev);
 
 	pi->asi = RV770_ASI_DFLT;
 	pi->pasi = CYPRESS_HASI_DFLT;
@@ -2659,8 +2647,7 @@ int btc_dpm_init(struct radeon_device *rdev)
 
 	pi->dynamic_pcie_gen2 = true;
 
-	if (pi->gfx_clock_gating &&
-	    (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE))
+	if (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE)
 		pi->thermal_protection = true;
 	else
 		pi->thermal_protection = false;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 6dacec4e2090..8928bd109c16 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -2587,9 +2587,11 @@ u32 cik_compute_ring_get_rptr(struct radeon_device *rdev,
 	if (rdev->wb.enabled) {
 		rptr = le32_to_cpu(rdev->wb.wb[ring->rptr_offs/4]);
 	} else {
+		mutex_lock(&rdev->srbm_mutex);
 		cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0);
 		rptr = RREG32(CP_HQD_PQ_RPTR);
 		cik_srbm_select(rdev, 0, 0, 0, 0);
+		mutex_unlock(&rdev->srbm_mutex);
 	}
 	rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
 
@@ -2604,9 +2606,11 @@ u32 cik_compute_ring_get_wptr(struct radeon_device *rdev,
 	if (rdev->wb.enabled) {
 		wptr = le32_to_cpu(rdev->wb.wb[ring->wptr_offs/4]);
 	} else {
+		mutex_lock(&rdev->srbm_mutex);
 		cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0);
 		wptr = RREG32(CP_HQD_PQ_WPTR);
 		cik_srbm_select(rdev, 0, 0, 0, 0);
+		mutex_unlock(&rdev->srbm_mutex);
 	}
 	wptr = (wptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
 
@@ -2897,6 +2901,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 	WREG32(CP_CPF_DEBUG, tmp);
 
 	/* init the pipes */
+	mutex_lock(&rdev->srbm_mutex);
 	for (i = 0; i < (rdev->mec.num_pipe * rdev->mec.num_mec); i++) {
 		int me = (i < 4) ? 1 : 2;
 		int pipe = (i < 4) ? i : (i - 4);
@@ -2919,6 +2924,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 		WREG32(CP_HPD_EOP_CONTROL, tmp);
 	}
 	cik_srbm_select(rdev, 0, 0, 0, 0);
+	mutex_unlock(&rdev->srbm_mutex);
 
 	/* init the queues.  Just two for now. */
 	for (i = 0; i < 2; i++) {
@@ -2972,6 +2978,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 		mqd->static_thread_mgmt23[0] = 0xffffffff;
 		mqd->static_thread_mgmt23[1] = 0xffffffff;
 
+		mutex_lock(&rdev->srbm_mutex);
 		cik_srbm_select(rdev, rdev->ring[idx].me,
 				rdev->ring[idx].pipe,
 				rdev->ring[idx].queue, 0);
@@ -3099,6 +3106,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 		WREG32(CP_HQD_ACTIVE, mqd->queue_state.cp_hqd_active);
 
 		cik_srbm_select(rdev, 0, 0, 0, 0);
+		mutex_unlock(&rdev->srbm_mutex);
 
 		radeon_bo_kunmap(rdev->ring[idx].mqd_obj);
 		radeon_bo_unreserve(rdev->ring[idx].mqd_obj);
@@ -4320,6 +4328,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
 
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
+	mutex_lock(&rdev->srbm_mutex);
 	for (i = 0; i < 16; i++) {
 		cik_srbm_select(rdev, 0, 0, 0, i);
 		/* CP and shaders */
@@ -4335,6 +4344,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
 		/* XXX SDMA RLC - todo */
 	}
 	cik_srbm_select(rdev, 0, 0, 0, 0);
+	mutex_unlock(&rdev->srbm_mutex);
 
 	cik_pcie_gart_tlb_flush(rdev);
 	DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
@@ -5954,6 +5964,8 @@ static int cik_startup(struct radeon_device *rdev)
 	struct radeon_ring *ring;
 	int r;
 
+	cik_mc_program(rdev);
+
 	if (rdev->flags & RADEON_IS_IGP) {
 		if (!rdev->me_fw || !rdev->pfp_fw || !rdev->ce_fw ||
 		    !rdev->mec_fw || !rdev->sdma_fw || !rdev->rlc_fw) {
@@ -5985,7 +5997,6 @@ static int cik_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	cik_mc_program(rdev);
 	r = cik_pcie_gart_enable(rdev);
 	if (r)
 		return r;
@@ -6194,7 +6205,7 @@ int cik_suspend(struct radeon_device *rdev)
 	radeon_vm_manager_fini(rdev);
 	cik_cp_enable(rdev, false);
 	cik_sdma_enable(rdev, false);
-	r600_uvd_rbc_stop(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_suspend(rdev);
 	cik_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
@@ -6358,6 +6369,7 @@ void cik_fini(struct radeon_device *rdev)
 	radeon_vm_manager_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_fini(rdev);
 	cik_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
@@ -6978,7 +6990,7 @@ int cik_uvd_resume(struct radeon_device *rdev)
 
 	/* programm the VCPU memory controller bits 0-27 */
 	addr = rdev->uvd.gpu_addr >> 3;
-	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd.fw_size + 4) >> 3;
+	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
 	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
 	WREG32(UVD_VCPU_CACHE_SIZE0, size);
 
diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c
index 9bcdd174780f..7e5d0b570a30 100644
--- a/drivers/gpu/drm/radeon/cypress_dpm.c
+++ b/drivers/gpu/drm/radeon/cypress_dpm.c
@@ -2038,9 +2038,6 @@ int cypress_dpm_init(struct radeon_device *rdev)
 {
 	struct rv7xx_power_info *pi;
 	struct evergreen_power_info *eg_pi;
-	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
-	uint16_t data_offset, size;
-	uint8_t frev, crev;
 	struct atom_clock_dividers dividers;
 	int ret;
 
@@ -2092,16 +2089,7 @@ int cypress_dpm_init(struct radeon_device *rdev)
 	eg_pi->vddci_control =
 		radeon_atom_is_voltage_gpio(rdev, SET_VOLTAGE_TYPE_ASIC_VDDCI, 0);
 
-	if (atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
-                                   &frev, &crev, &data_offset)) {
-		pi->sclk_ss = true;
-		pi->mclk_ss = true;
-		pi->dynamic_ss = true;
-	} else {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
-		pi->dynamic_ss = true;
-	}
+	rv770_get_engine_memory_ss(rdev);
 
 	pi->asi = RV770_ASI_DFLT;
 	pi->pasi = CYPRESS_HASI_DFLT;
@@ -2122,8 +2110,7 @@ int cypress_dpm_init(struct radeon_device *rdev)
 
 	pi->dynamic_pcie_gen2 = true;
 
-	if (pi->gfx_clock_gating &&
-	    (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE))
+	if (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE)
 		pi->thermal_protection = true;
 	else
 		pi->thermal_protection = false;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 038dcac7670c..d5b49e33315e 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -5106,6 +5106,8 @@ static int evergreen_startup(struct radeon_device *rdev)
 	/* enable aspm */
 	evergreen_program_aspm(rdev);
 
+	evergreen_mc_program(rdev);
+
 	if (ASIC_IS_DCE5(rdev)) {
 		if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw || !rdev->mc_fw) {
 			r = ni_init_microcode(rdev);
@@ -5133,7 +5135,6 @@ static int evergreen_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	evergreen_mc_program(rdev);
 	if (rdev->flags & RADEON_IS_AGP) {
 		evergreen_agp_enable(rdev);
 	} else {
@@ -5291,10 +5292,10 @@ int evergreen_resume(struct radeon_device *rdev)
 int evergreen_suspend(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_suspend(rdev);
 	r700_cp_stop(rdev);
 	r600_dma_stop(rdev);
-	r600_uvd_rbc_stop(rdev);
 	evergreen_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
 	evergreen_pcie_gart_disable(rdev);
@@ -5429,6 +5430,7 @@ void evergreen_fini(struct radeon_device *rdev)
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	evergreen_pcie_gart_fini(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index b0d3fb341417..b0e280058b9b 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -148,18 +148,40 @@ static void evergreen_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
 	u32 base_rate = 24000;
+	u32 max_ratio = clock / base_rate;
+	u32 dto_phase;
+	u32 dto_modulo = clock;
+	u32 wallclock_ratio;
+	u32 dto_cntl;
 
 	if (!dig || !dig->afmt)
 		return;
 
+	if (max_ratio >= 8) {
+		dto_phase = 192 * 1000;
+		wallclock_ratio = 3;
+	} else if (max_ratio >= 4) {
+		dto_phase = 96 * 1000;
+		wallclock_ratio = 2;
+	} else if (max_ratio >= 2) {
+		dto_phase = 48 * 1000;
+		wallclock_ratio = 1;
+	} else {
+		dto_phase = 24 * 1000;
+		wallclock_ratio = 0;
+	}
+	dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
+	dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
+	WREG32(DCCG_AUDIO_DTO0_CNTL, dto_cntl);
+
 	/* XXX two dtos; generally use dto0 for hdmi */
 	/* Express [24MHz / target pixel clock] as an exact rational
 	 * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
 	 * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
 	 */
-	WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
-	WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
 	WREG32(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL(radeon_crtc->crtc_id));
+	WREG32(DCCG_AUDIO_DTO0_PHASE, dto_phase);
+	WREG32(DCCG_AUDIO_DTO0_MODULE, dto_modulo);
 }
 
 
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index a7baf67aef6c..0d582ac1dc31 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -497,6 +497,9 @@
 #define DCCG_AUDIO_DTO0_MODULE            0x05b4
 #define DCCG_AUDIO_DTO0_LOAD              0x05b8
 #define DCCG_AUDIO_DTO0_CNTL              0x05bc
+#       define DCCG_AUDIO_DTO_WALLCLOCK_RATIO(x) (((x) & 7) << 0)
+#       define DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK 7
+#       define DCCG_AUDIO_DTO_WALLCLOCK_RATIO_SHIFT 0
 
 #define DCCG_AUDIO_DTO1_PHASE             0x05c0
 #define DCCG_AUDIO_DTO1_MODULE            0x05c4
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 56bd4f3be4fe..ccb4f8b54852 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -794,9 +794,13 @@ int ni_init_microcode(struct radeon_device *rdev)
 	if ((rdev->family >= CHIP_BARTS) && (rdev->family <= CHIP_CAYMAN)) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
 		err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
-		if (err)
-			goto out;
-		if (rdev->smc_fw->size != smc_req_size) {
+		if (err) {
+			printk(KERN_ERR
+			       "smc: error loading firmware \"%s\"\n",
+			       fw_name);
+			release_firmware(rdev->smc_fw);
+			rdev->smc_fw = NULL;
+		} else if (rdev->smc_fw->size != smc_req_size) {
 			printk(KERN_ERR
 			       "ni_mc: Bogus length %zu in firmware \"%s\"\n",
 			       rdev->mc_fw->size, fw_name);
@@ -2079,6 +2083,8 @@ static int cayman_startup(struct radeon_device *rdev)
 	/* enable aspm */
 	evergreen_program_aspm(rdev);
 
+	evergreen_mc_program(rdev);
+
 	if (rdev->flags & RADEON_IS_IGP) {
 		if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
 			r = ni_init_microcode(rdev);
@@ -2107,7 +2113,6 @@ static int cayman_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	evergreen_mc_program(rdev);
 	r = cayman_pcie_gart_enable(rdev);
 	if (r)
 		return r;
@@ -2286,7 +2291,7 @@ int cayman_suspend(struct radeon_device *rdev)
 	radeon_vm_manager_fini(rdev);
 	cayman_cp_enable(rdev, false);
 	cayman_dma_stop(rdev);
-	r600_uvd_rbc_stop(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_suspend(rdev);
 	evergreen_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
@@ -2418,6 +2423,7 @@ void cayman_fini(struct radeon_device *rdev)
 	radeon_vm_manager_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_fini(rdev);
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 559cf24d51af..f0f5f748938a 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -1054,10 +1054,6 @@ static int ni_restrict_performance_levels_before_switch(struct radeon_device *rd
 int ni_dpm_force_performance_level(struct radeon_device *rdev,
 				   enum radeon_dpm_forced_level level)
 {
-	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
-	struct ni_ps *ps = ni_get_ps(rps);
-	u32 levels;
-
 	if (level == RADEON_DPM_FORCED_LEVEL_HIGH) {
 		if (ni_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, 0) != PPSMC_Result_OK)
 			return -EINVAL;
@@ -1068,8 +1064,7 @@ int ni_dpm_force_performance_level(struct radeon_device *rdev,
 		if (ni_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetForcedLevels, 0) != PPSMC_Result_OK)
 			return -EINVAL;
 
-		levels = ps->performance_level_count - 1;
-		if (ni_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, levels) != PPSMC_Result_OK)
+		if (ni_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, 1) != PPSMC_Result_OK)
 			return -EINVAL;
 	} else if (level == RADEON_DPM_FORCED_LEVEL_AUTO) {
 		if (ni_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetForcedLevels, 0) != PPSMC_Result_OK)
@@ -4072,9 +4067,6 @@ int ni_dpm_init(struct radeon_device *rdev)
 	struct rv7xx_power_info *pi;
 	struct evergreen_power_info *eg_pi;
 	struct ni_power_info *ni_pi;
-	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
-	u16 data_offset, size;
-	u8 frev, crev;
 	struct atom_clock_dividers dividers;
 	int ret;
 
@@ -4167,16 +4159,7 @@ int ni_dpm_init(struct radeon_device *rdev)
 	eg_pi->vddci_control =
 		radeon_atom_is_voltage_gpio(rdev, SET_VOLTAGE_TYPE_ASIC_VDDCI, 0);
 
-	if (atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
-                                   &frev, &crev, &data_offset)) {
-		pi->sclk_ss = true;
-		pi->mclk_ss = true;
-		pi->dynamic_ss = true;
-	} else {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
-		pi->dynamic_ss = true;
-	}
+	rv770_get_engine_memory_ss(rdev);
 
 	pi->asi = RV770_ASI_DFLT;
 	pi->pasi = CYPRESS_HASI_DFLT;
@@ -4193,8 +4176,7 @@ int ni_dpm_init(struct radeon_device *rdev)
 
 	pi->dynamic_pcie_gen2 = true;
 
-	if (pi->gfx_clock_gating &&
-	    (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE))
+	if (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE)
 		pi->thermal_protection = true;
 	else
 		pi->thermal_protection = false;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 393880a09412..e66e72077350 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2299,9 +2299,13 @@ int r600_init_microcode(struct radeon_device *rdev)
 	if ((rdev->family >= CHIP_RV770) && (rdev->family <= CHIP_HEMLOCK)) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", smc_chip_name);
 		err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
-		if (err)
-			goto out;
-		if (rdev->smc_fw->size != smc_req_size) {
+		if (err) {
+			printk(KERN_ERR
+			       "smc: error loading firmware \"%s\"\n",
+			       fw_name);
+			release_firmware(rdev->smc_fw);
+			rdev->smc_fw = NULL;
+		} else if (rdev->smc_fw->size != smc_req_size) {
 			printk(KERN_ERR
 			       "smc: Bogus length %zu in firmware \"%s\"\n",
 			       rdev->smc_fw->size, fw_name);
@@ -2697,12 +2701,29 @@ int r600_uvd_rbc_start(struct radeon_device *rdev)
 	return 0;
 }
 
-void r600_uvd_rbc_stop(struct radeon_device *rdev)
+void r600_uvd_stop(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
 
 	/* force RBC into idle state */
 	WREG32(UVD_RBC_RB_CNTL, 0x11010101);
+
+	/* Stall UMC and register bus before resetting VCPU */
+	WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+	WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
+	mdelay(1);
+
+	/* put VCPU into reset */
+	WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
+	mdelay(5);
+
+	/* disable VCPU clock */
+	WREG32(UVD_VCPU_CNTL, 0x0);
+
+	/* Unstall UMC and register bus */
+	WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
+	WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
+
 	ring->ready = false;
 }
 
@@ -2722,6 +2743,11 @@ int r600_uvd_init(struct radeon_device *rdev)
 	/* disable interupt */
 	WREG32_P(UVD_MASTINT_EN, 0, ~(1 << 1));
 
+	/* Stall UMC and register bus before resetting VCPU */
+	WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+	WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
+	mdelay(1);
+
 	/* put LMI, VCPU, RBC etc... into reset */
 	WREG32(UVD_SOFT_RESET, LMI_SOFT_RESET | VCPU_SOFT_RESET |
 	       LBSI_SOFT_RESET | RBC_SOFT_RESET | CSM_SOFT_RESET |
@@ -2751,10 +2777,6 @@ int r600_uvd_init(struct radeon_device *rdev)
 	WREG32(UVD_MPC_SET_ALU, 0);
 	WREG32(UVD_MPC_SET_MUX, 0x88);
 
-	/* Stall UMC */
-	WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
-	WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
-
 	/* take all subblocks out of reset, except VCPU */
 	WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
 	mdelay(5);
@@ -3166,7 +3188,7 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 
 	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
 	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);
-	r = radeon_ring_lock(rdev, ring, num_loops * 6 + 21);
+	r = radeon_ring_lock(rdev, ring, num_loops * 6 + 24);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
@@ -3181,6 +3203,9 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 		radeon_semaphore_free(rdev, &sem, NULL);
 	}
 
+	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+	radeon_ring_write(ring, (WAIT_UNTIL - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
+	radeon_ring_write(ring, WAIT_3D_IDLE_bit);
 	for (i = 0; i < num_loops; i++) {
 		cur_size_in_bytes = size_in_bytes;
 		if (cur_size_in_bytes > 0x1fffff)
@@ -3309,6 +3334,8 @@ static int r600_startup(struct radeon_device *rdev)
 	/* enable pcie gen2 link */
 	r600_pcie_gen2_enable(rdev);
 
+	r600_mc_program(rdev);
+
 	if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
 		r = r600_init_microcode(rdev);
 		if (r) {
@@ -3321,7 +3348,6 @@ static int r600_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r600_mc_program(rdev);
 	if (rdev->flags & RADEON_IS_AGP) {
 		r600_agp_enable(rdev);
 	} else {
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index b88f54b134ab..e5c860f4ccbe 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -278,9 +278,9 @@ bool r600_dynamicpm_enabled(struct radeon_device *rdev)
 void r600_enable_sclk_control(struct radeon_device *rdev, bool enable)
 {
 	if (enable)
-		WREG32_P(GENERAL_PWRMGT, 0, ~SCLK_PWRMGT_OFF);
+		WREG32_P(SCLK_PWRMGT_CNTL, 0, ~SCLK_PWRMGT_OFF);
 	else
-		WREG32_P(GENERAL_PWRMGT, SCLK_PWRMGT_OFF, ~SCLK_PWRMGT_OFF);
+		WREG32_P(SCLK_PWRMGT_CNTL, SCLK_PWRMGT_OFF, ~SCLK_PWRMGT_OFF);
 }
 
 void r600_enable_mclk_control(struct radeon_device *rdev, bool enable)
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index f48240bb8c56..f264df5470f7 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -226,10 +226,29 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	u32 base_rate = 24000;
+	u32 max_ratio = clock / base_rate;
+	u32 dto_phase;
+	u32 dto_modulo = clock;
+	u32 wallclock_ratio;
+	u32 dto_cntl;
 
 	if (!dig || !dig->afmt)
 		return;
 
+	if (max_ratio >= 8) {
+		dto_phase = 192 * 1000;
+		wallclock_ratio = 3;
+	} else if (max_ratio >= 4) {
+		dto_phase = 96 * 1000;
+		wallclock_ratio = 2;
+	} else if (max_ratio >= 2) {
+		dto_phase = 48 * 1000;
+		wallclock_ratio = 1;
+	} else {
+		dto_phase = 24 * 1000;
+		wallclock_ratio = 0;
+	}
+
 	/* there are two DTOs selected by DCCG_AUDIO_DTO_SELECT.
 	 * doesn't matter which one you use.  Just use the first one.
 	 */
@@ -242,9 +261,21 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 		/* according to the reg specs, this should DCE3.2 only, but in
 		 * practice it seems to cover DCE3.0 as well.
 		 */
-		WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
-		WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
-		WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+		if (dig->dig_encoder == 0) {
+			dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
+			dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
+			WREG32(DCCG_AUDIO_DTO0_CNTL, dto_cntl);
+			WREG32(DCCG_AUDIO_DTO0_PHASE, dto_phase);
+			WREG32(DCCG_AUDIO_DTO0_MODULE, dto_modulo);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+		} else {
+			dto_cntl = RREG32(DCCG_AUDIO_DTO1_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
+			dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
+			WREG32(DCCG_AUDIO_DTO1_CNTL, dto_cntl);
+			WREG32(DCCG_AUDIO_DTO1_PHASE, dto_phase);
+			WREG32(DCCG_AUDIO_DTO1_MODULE, dto_modulo);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+		}
 	} else {
 		/* according to the reg specs, this should be DCE2.0 and DCE3.0 */
 		WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 8e3fe815edab..7c780839a7f4 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -933,6 +933,9 @@
 #define DCCG_AUDIO_DTO0_LOAD              0x051c
 #       define DTO_LOAD                   (1 << 31)
 #define DCCG_AUDIO_DTO0_CNTL              0x0520
+#       define DCCG_AUDIO_DTO_WALLCLOCK_RATIO(x) (((x) & 7) << 0)
+#       define DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK 7
+#       define DCCG_AUDIO_DTO_WALLCLOCK_RATIO_SHIFT 0
 
 #define DCCG_AUDIO_DTO1_PHASE             0x0524
 #define DCCG_AUDIO_DTO1_MODULE            0x0528
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 2f08219c39b6..9f19259667df 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1468,7 +1468,6 @@ struct radeon_uvd {
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
 	void			*saved_bo;
-	unsigned		fw_size;
 	atomic_t		handles[RADEON_MAX_UVD_HANDLES];
 	struct drm_file		*filp[RADEON_MAX_UVD_HANDLES];
 	struct delayed_work	idle_work;
@@ -2066,6 +2065,7 @@ struct radeon_device {
 	const struct firmware *mec_fw;	/* CIK MEC firmware */
 	const struct firmware *sdma_fw;	/* CIK SDMA firmware */
 	const struct firmware *smc_fw;	/* SMC firmware */
+	const struct firmware *uvd_fw;	/* UVD firmware */
 	struct r600_blit r600_blit;
 	struct r600_vram_scratch vram_scratch;
 	int msi_enabled; /* msi enabled */
@@ -2095,6 +2095,8 @@ struct radeon_device {
 	/* ACPI interface */
 	struct radeon_atif		atif;
 	struct radeon_atcs		atcs;
+	/* srbm instance registers */
+	struct mutex			srbm_mutex;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -2161,7 +2163,7 @@ void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v);
 		WREG32(reg, tmp_);				\
 	} while (0)
 #define WREG32_AND(reg, and) WREG32_P(reg, 0, and)
-#define WREG32_OR(reg, or) WREG32_P(reg, or, ~or)
+#define WREG32_OR(reg, or) WREG32_P(reg, or, ~(or))
 #define WREG32_PLL_P(reg, val, mask)				\
 	do {							\
 		uint32_t tmp_ = RREG32_PLL(reg);		\
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 78bec1a58ed1..f8f8b3113ddd 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1161,6 +1161,7 @@ static struct radeon_asic rv6xx_asic = {
 		.get_mclk = &rv6xx_dpm_get_mclk,
 		.print_power_state = &rv6xx_dpm_print_power_state,
 		.debugfs_print_current_performance_level = &rv6xx_dpm_debugfs_print_current_performance_level,
+		.force_performance_level = &rv6xx_dpm_force_performance_level,
 	},
 	.pflip = {
 		.pre_page_flip = &rs600_pre_page_flip,
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index ca1895709908..3d61d5aac18f 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -421,6 +421,8 @@ void rv6xx_dpm_print_power_state(struct radeon_device *rdev,
 				 struct radeon_ps *ps);
 void rv6xx_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
 						       struct seq_file *m);
+int rv6xx_dpm_force_performance_level(struct radeon_device *rdev,
+				      enum radeon_dpm_forced_level level);
 /* rs780 dpm */
 int rs780_dpm_init(struct radeon_device *rdev);
 int rs780_dpm_enable(struct radeon_device *rdev);
@@ -439,7 +441,7 @@ void rs780_dpm_debugfs_print_current_performance_level(struct radeon_device *rde
 /* uvd */
 int r600_uvd_init(struct radeon_device *rdev);
 int r600_uvd_rbc_start(struct radeon_device *rdev);
-void r600_uvd_rbc_stop(struct radeon_device *rdev);
+void r600_uvd_stop(struct radeon_device *rdev);
 int r600_uvd_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 void r600_uvd_fence_emit(struct radeon_device *rdev,
 			 struct radeon_fence *fence);
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index e3f3e8841789..4ccd61f60eb6 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -2782,7 +2782,7 @@ int radeon_atom_get_clock_dividers(struct radeon_device *rdev,
 							     ATOM_PLL_CNTL_FLAG_PLL_POST_DIV_EN) ? true : false;
 				dividers->enable_dithen = (args.v3.ucCntlFlag &
 							   ATOM_PLL_CNTL_FLAG_FRACTION_DISABLE) ? false : true;
-				dividers->fb_div = le16_to_cpu(args.v3.ulFbDiv.usFbDiv);
+				dividers->whole_fb_div = le16_to_cpu(args.v3.ulFbDiv.usFbDiv);
 				dividers->frac_fb_div = le16_to_cpu(args.v3.ulFbDiv.usFbDivFrac);
 				dividers->ref_div = args.v3.ucRefDiv;
 				dividers->vco_mode = (args.v3.ucCntlFlag &
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 78edadc9e86b..68ce36056019 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -147,7 +147,7 @@ static uint16_t combios_get_table_offset(struct drm_device *dev,
 					 enum radeon_combios_table_offset table)
 {
 	struct radeon_device *rdev = dev->dev_private;
-	int rev;
+	int rev, size;
 	uint16_t offset = 0, check_offset;
 
 	if (!rdev->bios)
@@ -156,174 +156,106 @@ static uint16_t combios_get_table_offset(struct drm_device *dev,
 	switch (table) {
 		/* absolute offset tables */
 	case COMBIOS_ASIC_INIT_1_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0xc);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0xc;
 		break;
 	case COMBIOS_BIOS_SUPPORT_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x14);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x14;
 		break;
 	case COMBIOS_DAC_PROGRAMMING_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x2a);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x2a;
 		break;
 	case COMBIOS_MAX_COLOR_DEPTH_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x2c);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x2c;
 		break;
 	case COMBIOS_CRTC_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x2e);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x2e;
 		break;
 	case COMBIOS_PLL_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x30);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x30;
 		break;
 	case COMBIOS_TV_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x32);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x32;
 		break;
 	case COMBIOS_DFP_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x34);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x34;
 		break;
 	case COMBIOS_HW_CONFIG_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x36);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x36;
 		break;
 	case COMBIOS_MULTIMEDIA_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x38);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x38;
 		break;
 	case COMBIOS_TV_STD_PATCH_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x3e);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x3e;
 		break;
 	case COMBIOS_LCD_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x40);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x40;
 		break;
 	case COMBIOS_MOBILE_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x42);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x42;
 		break;
 	case COMBIOS_PLL_INIT_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x46);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x46;
 		break;
 	case COMBIOS_MEM_CONFIG_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x48);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x48;
 		break;
 	case COMBIOS_SAVE_MASK_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x4a);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x4a;
 		break;
 	case COMBIOS_HARDCODED_EDID_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x4c);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x4c;
 		break;
 	case COMBIOS_ASIC_INIT_2_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x4e);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x4e;
 		break;
 	case COMBIOS_CONNECTOR_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x50);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x50;
 		break;
 	case COMBIOS_DYN_CLK_1_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x52);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x52;
 		break;
 	case COMBIOS_RESERVED_MEM_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x54);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x54;
 		break;
 	case COMBIOS_EXT_TMDS_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x58);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x58;
 		break;
 	case COMBIOS_MEM_CLK_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x5a);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x5a;
 		break;
 	case COMBIOS_EXT_DAC_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x5c);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x5c;
 		break;
 	case COMBIOS_MISC_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x5e);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x5e;
 		break;
 	case COMBIOS_CRT_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x60);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x60;
 		break;
 	case COMBIOS_INTEGRATED_SYSTEM_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x62);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x62;
 		break;
 	case COMBIOS_COMPONENT_VIDEO_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x64);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x64;
 		break;
 	case COMBIOS_FAN_SPEED_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x66);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x66;
 		break;
 	case COMBIOS_OVERDRIVE_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x68);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x68;
 		break;
 	case COMBIOS_OEM_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x6a);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x6a;
 		break;
 	case COMBIOS_DYN_CLK_2_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x6c);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x6c;
 		break;
 	case COMBIOS_POWER_CONNECTOR_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x6e);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x6e;
 		break;
 	case COMBIOS_I2C_INFO_TABLE:
-		check_offset = RBIOS16(rdev->bios_header_start + 0x70);
-		if (check_offset)
-			offset = check_offset;
+		check_offset = 0x70;
 		break;
 		/* relative offset tables */
 	case COMBIOS_ASIC_INIT_3_TABLE:	/* offset from misc info */
@@ -439,11 +371,16 @@ static uint16_t combios_get_table_offset(struct drm_device *dev,
 		}
 		break;
 	default:
+		check_offset = 0;
 		break;
 	}
 
-	return offset;
+	size = RBIOS8(rdev->bios_header_start + 0x6);
+	/* check absolute offset tables */
+	if (table < COMBIOS_ASIC_INIT_3_TABLE && check_offset && check_offset < size)
+		offset = RBIOS16(rdev->bios_header_start + check_offset);
 
+	return offset;
 }
 
 bool radeon_combios_check_hardcoded_edid(struct radeon_device *rdev)
@@ -965,16 +902,22 @@ struct radeon_encoder_primary_dac *radeon_combios_get_primary_dac_info(struct
 			dac = RBIOS8(dac_info + 0x3) & 0xf;
 			p_dac->ps2_pdac_adj = (bg << 8) | (dac);
 		}
-		/* if the values are all zeros, use the table */
-		if (p_dac->ps2_pdac_adj)
+		/* if the values are zeros, use the table */
+		if ((dac == 0) || (bg == 0))
+			found = 0;
+		else
 			found = 1;
 	}
 
 	/* quirks */
+	/* Radeon 7000 (RV100) */
+	if (((dev->pdev->device == 0x5159) &&
+	    (dev->pdev->subsystem_vendor == 0x174B) &&
+	    (dev->pdev->subsystem_device == 0x7c28)) ||
 	/* Radeon 9100 (R200) */
-	if ((dev->pdev->device == 0x514D) &&
+	   ((dev->pdev->device == 0x514D) &&
 	    (dev->pdev->subsystem_vendor == 0x174B) &&
-	    (dev->pdev->subsystem_device == 0x7149)) {
+	    (dev->pdev->subsystem_device == 0x7149))) {
 		/* vbios value is bad, use the default */
 		found = 0;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 82335e38ec4f..63398ae1dbf5 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1163,6 +1163,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	mutex_init(&rdev->gem.mutex);
 	mutex_init(&rdev->pm.mutex);
 	mutex_init(&rdev->gpu_clock_mutex);
+	mutex_init(&rdev->srbm_mutex);
 	init_rwsem(&rdev->pm.mclk_lock);
 	init_rwsem(&rdev->exclusive_lock);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
@@ -1519,6 +1520,7 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 	radeon_save_bios_scratch_regs(rdev);
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
+	radeon_pm_suspend(rdev);
 	radeon_suspend(rdev);
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
@@ -1564,6 +1566,7 @@ retry:
 		}
 	}
 
+	radeon_pm_resume(rdev);
 	drm_helper_resume_force_mode(rdev->ddev);
 
 	ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 7ddb0efe2408..ddb8f8e04eb5 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -782,7 +782,7 @@ int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring)
 
 		} else {
 			/* put fence directly behind firmware */
-			index = ALIGN(rdev->uvd.fw_size, 8);
+			index = ALIGN(rdev->uvd_fw->size, 8);
 			rdev->fence_drv[ring].cpu_addr = rdev->uvd.cpu_addr + index;
 			rdev->fence_drv[ring].gpu_addr = rdev->uvd.gpu_addr + index;
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index d9d31a383276..b990b1a2bd50 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -207,7 +207,6 @@ void radeon_gart_table_vram_free(struct radeon_device *rdev)
 	if (rdev->gart.robj == NULL) {
 		return;
 	}
-	radeon_gart_table_vram_unpin(rdev);
 	radeon_bo_unref(&rdev->gart.robj);
 }
 
@@ -466,7 +465,7 @@ int radeon_vm_manager_init(struct radeon_device *rdev)
 		size += rdev->vm_manager.max_pfn * 8;
 		size *= 2;
 		r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager,
-					      RADEON_VM_PTB_ALIGN(size),
+					      RADEON_GPU_PAGE_ALIGN(size),
 					      RADEON_VM_PTB_ALIGN_SIZE,
 					      RADEON_GEM_DOMAIN_VRAM);
 		if (r) {
@@ -621,7 +620,7 @@ int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
 	}
 
 retry:
-	pd_size = RADEON_VM_PTB_ALIGN(radeon_vm_directory_size(rdev));
+	pd_size = radeon_vm_directory_size(rdev);
 	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
 			     &vm->page_directory, pd_size,
 			     RADEON_VM_PTB_ALIGN_SIZE, false);
@@ -953,8 +952,8 @@ static int radeon_vm_update_pdes(struct radeon_device *rdev,
 retry:
 		r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
 				     &vm->page_tables[pt_idx],
-				     RADEON_VM_PTB_ALIGN(RADEON_VM_PTE_COUNT * 8),
-				     RADEON_VM_PTB_ALIGN_SIZE, false);
+				     RADEON_VM_PTE_COUNT * 8,
+				     RADEON_GPU_PAGE_SIZE, false);
 
 		if (r == -ENOMEM) {
 			r = radeon_vm_evict(rdev, vm);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index f374c467aaca..c557850cd345 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1176,7 +1176,14 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_VERDE:
 	case CHIP_OLAND:
 	case CHIP_HAINAN:
-		if (radeon_dpm == 1)
+		/* DPM requires the RLC, RV770+ dGPU requires SMC */
+		if (!rdev->rlc_fw)
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if ((rdev->family >= CHIP_RV770) &&
+			 (!(rdev->flags & RADEON_IS_IGP)) &&
+			 (!rdev->smc_fw))
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if (radeon_dpm == 1)
 			rdev->pm.pm_method = PM_METHOD_DPM;
 		else
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 414fd145d20e..b79f4f5cdd62 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -56,7 +56,6 @@ static void radeon_uvd_idle_work_handler(struct work_struct *work);
 
 int radeon_uvd_init(struct radeon_device *rdev)
 {
-	const struct firmware *fw;
 	unsigned long bo_size;
 	const char *fw_name;
 	int i, r;
@@ -105,14 +104,14 @@ int radeon_uvd_init(struct radeon_device *rdev)
 		return -EINVAL;
 	}
 
-	r = request_firmware(&fw, fw_name, rdev->dev);
+	r = request_firmware(&rdev->uvd_fw, fw_name, rdev->dev);
 	if (r) {
 		dev_err(rdev->dev, "radeon_uvd: Can't load firmware \"%s\"\n",
 			fw_name);
 		return r;
 	}
 
-	bo_size = RADEON_GPU_PAGE_ALIGN(fw->size + 8) +
+	bo_size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 8) +
 		  RADEON_UVD_STACK_SIZE + RADEON_UVD_HEAP_SIZE;
 	r = radeon_bo_create(rdev, bo_size, PAGE_SIZE, true,
 			     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->uvd.vcpu_bo);
@@ -145,12 +144,6 @@ int radeon_uvd_init(struct radeon_device *rdev)
 
 	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
 
-	rdev->uvd.fw_size = fw->size;
-	memset(rdev->uvd.cpu_addr, 0, bo_size);
-	memcpy(rdev->uvd.cpu_addr, fw->data, fw->size);
-
-	release_firmware(fw);
-
 	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
 		atomic_set(&rdev->uvd.handles[i], 0);
 		rdev->uvd.filp[i] = NULL;
@@ -174,33 +167,60 @@ void radeon_uvd_fini(struct radeon_device *rdev)
 	}
 
 	radeon_bo_unref(&rdev->uvd.vcpu_bo);
+
+	release_firmware(rdev->uvd_fw);
 }
 
 int radeon_uvd_suspend(struct radeon_device *rdev)
 {
 	unsigned size;
+	void *ptr;
+	int i;
 
 	if (rdev->uvd.vcpu_bo == NULL)
 		return 0;
 
+	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i)
+		if (atomic_read(&rdev->uvd.handles[i]))
+			break;
+
+	if (i == RADEON_MAX_UVD_HANDLES)
+		return 0;
+
 	size = radeon_bo_size(rdev->uvd.vcpu_bo);
+	size -= rdev->uvd_fw->size;
+
+	ptr = rdev->uvd.cpu_addr;
+	ptr += rdev->uvd_fw->size;
+
 	rdev->uvd.saved_bo = kmalloc(size, GFP_KERNEL);
-	memcpy(rdev->uvd.saved_bo, rdev->uvd.cpu_addr, size);
+	memcpy(rdev->uvd.saved_bo, ptr, size);
 
 	return 0;
 }
 
 int radeon_uvd_resume(struct radeon_device *rdev)
 {
+	unsigned size;
+	void *ptr;
+
 	if (rdev->uvd.vcpu_bo == NULL)
 		return -EINVAL;
 
+	memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);
+
+	size = radeon_bo_size(rdev->uvd.vcpu_bo);
+	size -= rdev->uvd_fw->size;
+
+	ptr = rdev->uvd.cpu_addr;
+	ptr += rdev->uvd_fw->size;
+
 	if (rdev->uvd.saved_bo != NULL) {
-		unsigned size = radeon_bo_size(rdev->uvd.vcpu_bo);
-		memcpy(rdev->uvd.cpu_addr, rdev->uvd.saved_bo, size);
+		memcpy(ptr, rdev->uvd.saved_bo, size);
 		kfree(rdev->uvd.saved_bo);
 		rdev->uvd.saved_bo = NULL;
-	}
+	} else
+		memset(ptr, 0, size);
 
 	return 0;
 }
@@ -215,8 +235,8 @@ void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp)
 {
 	int i, r;
 	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
-		if (rdev->uvd.filp[i] == filp) {
-			uint32_t handle = atomic_read(&rdev->uvd.handles[i]);
+		uint32_t handle = atomic_read(&rdev->uvd.handles[i]);
+		if (handle != 0 && rdev->uvd.filp[i] == filp) {
 			struct radeon_fence *fence;
 
 			r = radeon_uvd_get_destroy_msg(rdev,
@@ -336,9 +356,19 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 		return -EINVAL;
 	}
 
+	if (bo->tbo.sync_obj) {
+		r = radeon_fence_wait(bo->tbo.sync_obj, false);
+		if (r) {
+			DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
+			return r;
+		}
+	}
+
 	r = radeon_bo_kmap(bo, &ptr);
-	if (r)
+	if (r) {
+		DRM_ERROR("Failed mapping the UVD message (%d)!\n", r);
 		return r;
+	}
 
 	msg = ptr + offset;
 
@@ -364,8 +394,14 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 		radeon_bo_kunmap(bo);
 		return 0;
 	} else {
-		/* it's a create msg, no special handling needed */
 		radeon_bo_kunmap(bo);
+
+		if (msg_type != 0) {
+			DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+			return -EINVAL;
+		}
+
+		/* it's a create msg, no special handling needed */
 	}
 
 	/* create or decode, validate the handle */
@@ -388,7 +424,7 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 
 static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 			       int data0, int data1,
-			       unsigned buf_sizes[])
+			       unsigned buf_sizes[], bool *has_msg_cmd)
 {
 	struct radeon_cs_chunk *relocs_chunk;
 	struct radeon_cs_reloc *reloc;
@@ -417,7 +453,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 
 	if (cmd < 0x4) {
 		if ((end - start) < buf_sizes[cmd]) {
-			DRM_ERROR("buffer to small (%d / %d)!\n",
+			DRM_ERROR("buffer (%d) to small (%d / %d)!\n", cmd,
 				  (unsigned)(end - start), buf_sizes[cmd]);
 			return -EINVAL;
 		}
@@ -442,9 +478,17 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 	}
 
 	if (cmd == 0) {
+		if (*has_msg_cmd) {
+			DRM_ERROR("More than one message in a UVD-IB!\n");
+			return -EINVAL;
+		}
+		*has_msg_cmd = true;
 		r = radeon_uvd_cs_msg(p, reloc->robj, offset, buf_sizes);
 		if (r)
 			return r;
+	} else if (!*has_msg_cmd) {
+		DRM_ERROR("Message needed before other commands are send!\n");
+		return -EINVAL;
 	}
 
 	return 0;
@@ -453,7 +497,8 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 static int radeon_uvd_cs_reg(struct radeon_cs_parser *p,
 			     struct radeon_cs_packet *pkt,
 			     int *data0, int *data1,
-			     unsigned buf_sizes[])
+			     unsigned buf_sizes[],
+			     bool *has_msg_cmd)
 {
 	int i, r;
 
@@ -467,7 +512,8 @@ static int radeon_uvd_cs_reg(struct radeon_cs_parser *p,
 			*data1 = p->idx;
 			break;
 		case UVD_GPCOM_VCPU_CMD:
-			r = radeon_uvd_cs_reloc(p, *data0, *data1, buf_sizes);
+			r = radeon_uvd_cs_reloc(p, *data0, *data1,
+						buf_sizes, has_msg_cmd);
 			if (r)
 				return r;
 			break;
@@ -488,6 +534,9 @@ int radeon_uvd_cs_parse(struct radeon_cs_parser *p)
 	struct radeon_cs_packet pkt;
 	int r, data0 = 0, data1 = 0;
 
+	/* does the IB has a msg command */
+	bool has_msg_cmd = false;
+
 	/* minimum buffer sizes */
 	unsigned buf_sizes[] = {
 		[0x00000000]	=	2048,
@@ -514,8 +563,8 @@ int radeon_uvd_cs_parse(struct radeon_cs_parser *p)
 			return r;
 		switch (pkt.type) {
 		case RADEON_PACKET_TYPE0:
-			r = radeon_uvd_cs_reg(p, &pkt, &data0,
-					      &data1, buf_sizes);
+			r = radeon_uvd_cs_reg(p, &pkt, &data0, &data1,
+					      buf_sizes, &has_msg_cmd);
 			if (r)
 				return r;
 			break;
@@ -527,6 +576,12 @@ int radeon_uvd_cs_parse(struct radeon_cs_parser *p)
 			return -EINVAL;
 		}
 	} while (p->idx < p->chunks[p->chunk_ib_idx].length_dw);
+
+	if (!has_msg_cmd) {
+		DRM_ERROR("UVD-IBs need a msg command!\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/rv6xx_dpm.c b/drivers/gpu/drm/radeon/rv6xx_dpm.c
index 65e33f387341..bdd888b4db2b 100644
--- a/drivers/gpu/drm/radeon/rv6xx_dpm.c
+++ b/drivers/gpu/drm/radeon/rv6xx_dpm.c
@@ -819,7 +819,7 @@ static void rv6xx_program_memory_timing_parameters(struct radeon_device *rdev)
 		 POWERMODE1(calculate_memory_refresh_rate(rdev,
 							  pi->hw.sclks[R600_POWER_LEVEL_MEDIUM])) |
 		 POWERMODE2(calculate_memory_refresh_rate(rdev,
-							  pi->hw.sclks[R600_POWER_LEVEL_MEDIUM])) |
+							  pi->hw.sclks[R600_POWER_LEVEL_HIGH])) |
 		 POWERMODE3(calculate_memory_refresh_rate(rdev,
 							  pi->hw.sclks[R600_POWER_LEVEL_HIGH])));
 	WREG32(ARB_RFSH_RATE, arb_refresh_rate);
@@ -1182,10 +1182,10 @@ static void rv6xx_program_display_gap(struct radeon_device *rdev)
 	u32 tmp = RREG32(CG_DISPLAY_GAP_CNTL);
 
 	tmp &= ~(DISP1_GAP_MCHG_MASK | DISP2_GAP_MCHG_MASK);
-	if (RREG32(AVIVO_D1CRTC_CONTROL) & AVIVO_CRTC_EN) {
+	if (rdev->pm.dpm.new_active_crtcs & 1) {
 		tmp |= DISP1_GAP_MCHG(R600_PM_DISPLAY_GAP_VBLANK);
 		tmp |= DISP2_GAP_MCHG(R600_PM_DISPLAY_GAP_IGNORE);
-	} else if (RREG32(AVIVO_D2CRTC_CONTROL) & AVIVO_CRTC_EN) {
+	} else if (rdev->pm.dpm.new_active_crtcs & 2) {
 		tmp |= DISP1_GAP_MCHG(R600_PM_DISPLAY_GAP_IGNORE);
 		tmp |= DISP2_GAP_MCHG(R600_PM_DISPLAY_GAP_VBLANK);
 	} else {
@@ -1670,6 +1670,8 @@ int rv6xx_dpm_set_power_state(struct radeon_device *rdev)
 	struct radeon_ps *old_ps = rdev->pm.dpm.current_ps;
 	int ret;
 
+	pi->restricted_levels = 0;
+
 	rv6xx_set_uvd_clock_before_set_eng_clock(rdev, new_ps, old_ps);
 
 	rv6xx_clear_vc(rdev);
@@ -1756,6 +1758,8 @@ int rv6xx_dpm_set_power_state(struct radeon_device *rdev)
 
 	rv6xx_set_uvd_clock_after_set_eng_clock(rdev, new_ps, old_ps);
 
+	rdev->pm.dpm.forced_level = RADEON_DPM_FORCED_LEVEL_AUTO;
+
 	return 0;
 }
 
@@ -1940,9 +1944,7 @@ static int rv6xx_parse_power_table(struct radeon_device *rdev)
 
 int rv6xx_dpm_init(struct radeon_device *rdev)
 {
-	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
-	uint16_t data_offset, size;
-	uint8_t frev, crev;
+	struct radeon_atom_ss ss;
 	struct atom_clock_dividers dividers;
 	struct rv6xx_power_info *pi;
 	int ret;
@@ -1985,16 +1987,18 @@ int rv6xx_dpm_init(struct radeon_device *rdev)
 
 	pi->gfx_clock_gating = true;
 
-	if (atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
-                                   &frev, &crev, &data_offset)) {
-		pi->sclk_ss = true;
-		pi->mclk_ss = true;
+	pi->sclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
+						       ASIC_INTERNAL_ENGINE_SS, 0);
+	pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
+						       ASIC_INTERNAL_MEMORY_SS, 0);
+
+	/* Disable sclk ss, causes hangs on a lot of systems */
+	pi->sclk_ss = false;
+
+	if (pi->sclk_ss || pi->mclk_ss)
 		pi->dynamic_ss = true;
-	} else {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
+	else
 		pi->dynamic_ss = false;
-	}
 
 	pi->dynamic_pcie_gen2 = true;
 
@@ -2085,3 +2089,34 @@ u32 rv6xx_dpm_get_mclk(struct radeon_device *rdev, bool low)
 	else
 		return requested_state->high.mclk;
 }
+
+int rv6xx_dpm_force_performance_level(struct radeon_device *rdev,
+				      enum radeon_dpm_forced_level level)
+{
+	struct rv6xx_power_info *pi = rv6xx_get_pi(rdev);
+
+	if (level == RADEON_DPM_FORCED_LEVEL_HIGH) {
+		pi->restricted_levels = 3;
+	} else if (level == RADEON_DPM_FORCED_LEVEL_LOW) {
+		pi->restricted_levels = 2;
+	} else {
+		pi->restricted_levels = 0;
+	}
+
+	rv6xx_clear_vc(rdev);
+	r600_power_level_enable(rdev, R600_POWER_LEVEL_LOW, true);
+	r600_set_at(rdev, 0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF);
+	r600_wait_for_power_level(rdev, R600_POWER_LEVEL_LOW);
+	r600_power_level_enable(rdev, R600_POWER_LEVEL_HIGH, false);
+	r600_power_level_enable(rdev, R600_POWER_LEVEL_MEDIUM, false);
+	rv6xx_enable_medium(rdev);
+	rv6xx_enable_high(rdev);
+	if (pi->restricted_levels == 3)
+		r600_power_level_enable(rdev, R600_POWER_LEVEL_LOW, false);
+	rv6xx_program_vc(rdev);
+	rv6xx_program_at(rdev);
+
+	rdev->pm.dpm.forced_level = level;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 30ea14e8854c..f5e92cfcc140 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -744,10 +744,10 @@ static void rv770_init_golden_registers(struct radeon_device *rdev)
 						 (const u32)ARRAY_SIZE(r7xx_golden_dyn_gpr_registers));
 		radeon_program_register_sequence(rdev,
 						 rv730_golden_registers,
-						 (const u32)ARRAY_SIZE(rv770_golden_registers));
+						 (const u32)ARRAY_SIZE(rv730_golden_registers));
 		radeon_program_register_sequence(rdev,
 						 rv730_mgcg_init,
-						 (const u32)ARRAY_SIZE(rv770_mgcg_init));
+						 (const u32)ARRAY_SIZE(rv730_mgcg_init));
 		break;
 	case CHIP_RV710:
 		radeon_program_register_sequence(rdev,
@@ -758,18 +758,18 @@ static void rv770_init_golden_registers(struct radeon_device *rdev)
 						 (const u32)ARRAY_SIZE(r7xx_golden_dyn_gpr_registers));
 		radeon_program_register_sequence(rdev,
 						 rv710_golden_registers,
-						 (const u32)ARRAY_SIZE(rv770_golden_registers));
+						 (const u32)ARRAY_SIZE(rv710_golden_registers));
 		radeon_program_register_sequence(rdev,
 						 rv710_mgcg_init,
-						 (const u32)ARRAY_SIZE(rv770_mgcg_init));
+						 (const u32)ARRAY_SIZE(rv710_mgcg_init));
 		break;
 	case CHIP_RV740:
 		radeon_program_register_sequence(rdev,
 						 rv740_golden_registers,
-						 (const u32)ARRAY_SIZE(rv770_golden_registers));
+						 (const u32)ARRAY_SIZE(rv740_golden_registers));
 		radeon_program_register_sequence(rdev,
 						 rv740_mgcg_init,
-						 (const u32)ARRAY_SIZE(rv770_mgcg_init));
+						 (const u32)ARRAY_SIZE(rv740_mgcg_init));
 		break;
 	default:
 		break;
@@ -813,7 +813,7 @@ int rv770_uvd_resume(struct radeon_device *rdev)
 
 	/* programm the VCPU memory controller bits 0-27 */
 	addr = rdev->uvd.gpu_addr >> 3;
-	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd.fw_size + 4) >> 3;
+	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
 	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
 	WREG32(UVD_VCPU_CACHE_SIZE0, size);
 
@@ -1829,6 +1829,8 @@ static int rv770_startup(struct radeon_device *rdev)
 	/* enable pcie gen2 link */
 	rv770_pcie_gen2_enable(rdev);
 
+	rv770_mc_program(rdev);
+
 	if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
 		r = r600_init_microcode(rdev);
 		if (r) {
@@ -1841,7 +1843,6 @@ static int rv770_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	rv770_mc_program(rdev);
 	if (rdev->flags & RADEON_IS_AGP) {
 		rv770_agp_enable(rdev);
 	} else {
@@ -1983,6 +1984,7 @@ int rv770_resume(struct radeon_device *rdev)
 int rv770_suspend(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_suspend(rdev);
 	r700_cp_stop(rdev);
 	r600_dma_stop(rdev);
@@ -2098,6 +2100,7 @@ void rv770_fini(struct radeon_device *rdev)
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	rv770_pcie_gart_fini(rdev);
+	r600_uvd_stop(rdev);
 	radeon_uvd_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 2d347925f77d..094c67a29d0d 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2319,12 +2319,25 @@ int rv7xx_parse_power_table(struct radeon_device *rdev)
 	return 0;
 }
 
+void rv770_get_engine_memory_ss(struct radeon_device *rdev)
+{
+	struct rv7xx_power_info *pi = rv770_get_pi(rdev);
+	struct radeon_atom_ss ss;
+
+	pi->sclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
+						       ASIC_INTERNAL_ENGINE_SS, 0);
+	pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
+						       ASIC_INTERNAL_MEMORY_SS, 0);
+
+	if (pi->sclk_ss || pi->mclk_ss)
+		pi->dynamic_ss = true;
+	else
+		pi->dynamic_ss = false;
+}
+
 int rv770_dpm_init(struct radeon_device *rdev)
 {
 	struct rv7xx_power_info *pi;
-	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
-	uint16_t data_offset, size;
-	uint8_t frev, crev;
 	struct atom_clock_dividers dividers;
 	int ret;
 
@@ -2369,16 +2382,7 @@ int rv770_dpm_init(struct radeon_device *rdev)
 	pi->mvdd_control =
 		radeon_atom_is_voltage_gpio(rdev, SET_VOLTAGE_TYPE_ASIC_MVDDC, 0);
 
-	if (atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
-                                   &frev, &crev, &data_offset)) {
-		pi->sclk_ss = true;
-		pi->mclk_ss = true;
-		pi->dynamic_ss = true;
-	} else {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
-		pi->dynamic_ss = false;
-	}
+	rv770_get_engine_memory_ss(rdev);
 
 	pi->asi = RV770_ASI_DFLT;
 	pi->pasi = RV770_HASI_DFLT;
@@ -2393,8 +2397,7 @@ int rv770_dpm_init(struct radeon_device *rdev)
 
 	pi->dynamic_pcie_gen2 = true;
 
-	if (pi->gfx_clock_gating &&
-	    (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE))
+	if (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE)
 		pi->thermal_protection = true;
 	else
 		pi->thermal_protection = false;
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.h b/drivers/gpu/drm/radeon/rv770_dpm.h
index 96b1b2a62a8a..9244effc6b59 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.h
+++ b/drivers/gpu/drm/radeon/rv770_dpm.h
@@ -275,6 +275,7 @@ void rv770_set_uvd_clock_before_set_eng_clock(struct radeon_device *rdev,
 void rv770_set_uvd_clock_after_set_eng_clock(struct radeon_device *rdev,
 					     struct radeon_ps *new_ps,
 					     struct radeon_ps *old_ps);
+void rv770_get_engine_memory_ss(struct radeon_device *rdev);
 
 /* smc */
 int rv770_read_smc_soft_register(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index d325280e2f9f..daa8d2df8ec5 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1663,9 +1663,13 @@ static int si_init_microcode(struct radeon_device *rdev)
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
 	err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
-	if (err)
-		goto out;
-	if (rdev->smc_fw->size != smc_req_size) {
+	if (err) {
+		printk(KERN_ERR
+		       "smc: error loading firmware \"%s\"\n",
+		       fw_name);
+		release_firmware(rdev->smc_fw);
+		rdev->smc_fw = NULL;
+	} else if (rdev->smc_fw->size != smc_req_size) {
 		printk(KERN_ERR
 		       "si_smc: Bogus length %zu in firmware \"%s\"\n",
 		       rdev->smc_fw->size, fw_name);
@@ -5215,14 +5219,12 @@ static void si_enable_mc_ls(struct radeon_device *rdev,
 
 static void si_init_cg(struct radeon_device *rdev)
 {
-	bool has_uvd = true;
-
 	si_enable_mgcg(rdev, true);
-	si_enable_cgcg(rdev, true);
+	si_enable_cgcg(rdev, false);
 	/* disable MC LS on Tahiti */
 	if (rdev->family == CHIP_TAHITI)
 		si_enable_mc_ls(rdev, false);
-	if (has_uvd) {
+	if (rdev->has_uvd) {
 		si_enable_uvd_mgcg(rdev, true);
 		si_init_uvd_internal_cg(rdev);
 	}
@@ -5230,9 +5232,7 @@ static void si_init_cg(struct radeon_device *rdev)
 
 static void si_fini_cg(struct radeon_device *rdev)
 {
-	bool has_uvd = true;
-
-	if (has_uvd)
+	if (rdev->has_uvd)
 		si_enable_uvd_mgcg(rdev, false);
 	si_enable_cgcg(rdev, false);
 	si_enable_mgcg(rdev, false);
@@ -5241,11 +5241,11 @@ static void si_fini_cg(struct radeon_device *rdev)
 static void si_init_pg(struct radeon_device *rdev)
 {
 	bool has_pg = false;
-
+#if 0
 	/* only cape verde supports PG */
 	if (rdev->family == CHIP_VERDE)
 		has_pg = true;
-
+#endif
 	if (has_pg) {
 		si_init_ao_cu_mask(rdev);
 		si_init_dma_pg(rdev);
@@ -6422,6 +6422,8 @@ static int si_startup(struct radeon_device *rdev)
 	/* enable aspm */
 	si_program_aspm(rdev);
 
+	si_mc_program(rdev);
+
 	if (!rdev->me_fw || !rdev->pfp_fw || !rdev->ce_fw ||
 	    !rdev->rlc_fw || !rdev->mc_fw) {
 		r = si_init_microcode(rdev);
@@ -6441,7 +6443,6 @@ static int si_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	si_mc_program(rdev);
 	r = si_pcie_gart_enable(rdev);
 	if (r)
 		return r;
@@ -6625,7 +6626,7 @@ int si_suspend(struct radeon_device *rdev)
 	si_cp_enable(rdev, false);
 	cayman_dma_stop(rdev);
 	if (rdev->has_uvd) {
-		r600_uvd_rbc_stop(rdev);
+		r600_uvd_stop(rdev);
 		radeon_uvd_suspend(rdev);
 	}
 	si_irq_suspend(rdev);
@@ -6767,8 +6768,10 @@ void si_fini(struct radeon_device *rdev)
 	radeon_vm_manager_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
-	if (rdev->has_uvd)
+	if (rdev->has_uvd) {
+		r600_uvd_stop(rdev);
 		radeon_uvd_fini(rdev);
+	}
 	si_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 73aaa2e4c312..88699e3cd868 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -37,8 +37,6 @@
 
 #define SMC_RAM_END                 0x20000
 
-#define DDR3_DRAM_ROWS              0x2000
-
 #define SCLK_MIN_DEEPSLEEP_FREQ     1350
 
 static const struct si_cac_config_reg cac_weights_tahiti[] =
@@ -1767,8 +1765,9 @@ static void si_calculate_leakage_for_v_and_t_formula(const struct ni_leakage_coe
 {
 	s64 kt, kv, leakage_w, i_leakage, vddc;
 	s64 temperature, t_slope, t_intercept, av, bv, t_ref;
+	s64 tmp;
 
-	i_leakage = drm_int2fixp(ileakage / 100);
+	i_leakage = div64_s64(drm_int2fixp(ileakage), 100);
 	vddc = div64_s64(drm_int2fixp(v), 1000);
 	temperature = div64_s64(drm_int2fixp(t), 1000);
 
@@ -1778,8 +1777,9 @@ static void si_calculate_leakage_for_v_and_t_formula(const struct ni_leakage_coe
 	bv = div64_s64(drm_int2fixp(coeff->bv), 100000000);
 	t_ref = drm_int2fixp(coeff->t_ref);
 
-	kt = drm_fixp_div(drm_fixp_exp(drm_fixp_mul(drm_fixp_mul(t_slope, vddc) + t_intercept, temperature)),
-			  drm_fixp_exp(drm_fixp_mul(drm_fixp_mul(t_slope, vddc) + t_intercept, t_ref)));
+	tmp = drm_fixp_mul(t_slope, vddc) + t_intercept;
+	kt = drm_fixp_exp(drm_fixp_mul(tmp, temperature));
+	kt = drm_fixp_div(kt, drm_fixp_exp(drm_fixp_mul(tmp, t_ref)));
 	kv = drm_fixp_mul(av, drm_fixp_exp(drm_fixp_mul(bv, vddc)));
 
 	leakage_w = drm_fixp_mul(drm_fixp_mul(drm_fixp_mul(i_leakage, kt), kv), vddc);
@@ -1931,6 +1931,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 			si_pi->cac_override = cac_override_pitcairn;
 			si_pi->powertune_data = &powertune_data_pitcairn;
 			si_pi->dte_data = dte_data_pitcairn;
+			break;
 		}
 	} else if (rdev->family == CHIP_VERDE) {
 		si_pi->lcac_config = lcac_cape_verde;
@@ -1941,6 +1942,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 		case 0x683B:
 		case 0x683F:
 		case 0x6829:
+		case 0x6835:
 			si_pi->cac_weights = cac_weights_cape_verde_pro;
 			si_pi->dte_data = dte_data_cape_verde;
 			break;
@@ -2901,7 +2903,8 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 {
 	struct ni_ps *ps = ni_get_ps(rps);
 	struct radeon_clock_and_voltage_limits *max_limits;
-	bool disable_mclk_switching;
+	bool disable_mclk_switching = false;
+	bool disable_sclk_switching = false;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
 	int i;
@@ -2909,8 +2912,11 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
 	    ni_dpm_vblank_too_short(rdev))
 		disable_mclk_switching = true;
-	else
-		disable_mclk_switching = false;
+
+	if (rps->vclk || rps->dclk) {
+		disable_mclk_switching = true;
+		disable_sclk_switching = true;
+	}
 
 	if (rdev->pm.dpm.ac_power)
 		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
@@ -2938,27 +2944,43 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 
 	if (disable_mclk_switching) {
 		mclk  = ps->performance_levels[ps->performance_level_count - 1].mclk;
-		sclk = ps->performance_levels[0].sclk;
-		vddc = ps->performance_levels[0].vddc;
 		vddci = ps->performance_levels[ps->performance_level_count - 1].vddci;
 	} else {
-		sclk = ps->performance_levels[0].sclk;
 		mclk = ps->performance_levels[0].mclk;
-		vddc = ps->performance_levels[0].vddc;
 		vddci = ps->performance_levels[0].vddci;
 	}
 
+	if (disable_sclk_switching) {
+		sclk = ps->performance_levels[ps->performance_level_count - 1].sclk;
+		vddc = ps->performance_levels[ps->performance_level_count - 1].vddc;
+	} else {
+		sclk = ps->performance_levels[0].sclk;
+		vddc = ps->performance_levels[0].vddc;
+	}
+
 	/* adjusted low state */
 	ps->performance_levels[0].sclk = sclk;
 	ps->performance_levels[0].mclk = mclk;
 	ps->performance_levels[0].vddc = vddc;
 	ps->performance_levels[0].vddci = vddci;
 
-	for (i = 1; i < ps->performance_level_count; i++) {
-		if (ps->performance_levels[i].sclk < ps->performance_levels[i - 1].sclk)
-			ps->performance_levels[i].sclk = ps->performance_levels[i - 1].sclk;
-		if (ps->performance_levels[i].vddc < ps->performance_levels[i - 1].vddc)
-			ps->performance_levels[i].vddc = ps->performance_levels[i - 1].vddc;
+	if (disable_sclk_switching) {
+		sclk = ps->performance_levels[0].sclk;
+		for (i = 1; i < ps->performance_level_count; i++) {
+			if (sclk < ps->performance_levels[i].sclk)
+				sclk = ps->performance_levels[i].sclk;
+		}
+		for (i = 0; i < ps->performance_level_count; i++) {
+			ps->performance_levels[i].sclk = sclk;
+			ps->performance_levels[i].vddc = vddc;
+		}
+	} else {
+		for (i = 1; i < ps->performance_level_count; i++) {
+			if (ps->performance_levels[i].sclk < ps->performance_levels[i - 1].sclk)
+				ps->performance_levels[i].sclk = ps->performance_levels[i - 1].sclk;
+			if (ps->performance_levels[i].vddc < ps->performance_levels[i - 1].vddc)
+				ps->performance_levels[i].vddc = ps->performance_levels[i - 1].vddc;
+		}
 	}
 
 	if (disable_mclk_switching) {
@@ -3237,10 +3259,10 @@ int si_dpm_force_performance_level(struct radeon_device *rdev,
 {
 	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
 	struct ni_ps *ps = ni_get_ps(rps);
-	u32 levels;
+	u32 levels = ps->performance_level_count;
 
 	if (level == RADEON_DPM_FORCED_LEVEL_HIGH) {
-		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, 0) != PPSMC_Result_OK)
+		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, levels) != PPSMC_Result_OK)
 			return -EINVAL;
 
 		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetForcedLevels, 1) != PPSMC_Result_OK)
@@ -3249,14 +3271,13 @@ int si_dpm_force_performance_level(struct radeon_device *rdev,
 		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetForcedLevels, 0) != PPSMC_Result_OK)
 			return -EINVAL;
 
-		levels = ps->performance_level_count - 1;
-		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, levels) != PPSMC_Result_OK)
+		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, 1) != PPSMC_Result_OK)
 			return -EINVAL;
 	} else if (level == RADEON_DPM_FORCED_LEVEL_AUTO) {
 		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetForcedLevels, 0) != PPSMC_Result_OK)
 			return -EINVAL;
 
-		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, 0) != PPSMC_Result_OK)
+		if (si_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_SetEnabledLevels, levels) != PPSMC_Result_OK)
 			return -EINVAL;
 	}
 
@@ -3620,8 +3641,12 @@ static void si_enable_display_gap(struct radeon_device *rdev)
 {
 	u32 tmp = RREG32(CG_DISPLAY_GAP_CNTL);
 
+	tmp &= ~(DISP1_GAP_MASK | DISP2_GAP_MASK);
+	tmp |= (DISP1_GAP(R600_PM_DISPLAY_GAP_IGNORE) |
+		DISP2_GAP(R600_PM_DISPLAY_GAP_IGNORE));
+
 	tmp &= ~(DISP1_GAP_MCHG_MASK | DISP2_GAP_MCHG_MASK);
-	tmp |= (DISP1_GAP_MCHG(R600_PM_DISPLAY_GAP_IGNORE) |
+	tmp |= (DISP1_GAP_MCHG(R600_PM_DISPLAY_GAP_VBLANK) |
 		DISP2_GAP_MCHG(R600_PM_DISPLAY_GAP_IGNORE));
 	WREG32(CG_DISPLAY_GAP_CNTL, tmp);
 }
@@ -4036,16 +4061,15 @@ static int si_force_switch_to_arb_f0(struct radeon_device *rdev)
 static u32 si_calculate_memory_refresh_rate(struct radeon_device *rdev,
 					    u32 engine_clock)
 {
-	struct rv7xx_power_info *pi = rv770_get_pi(rdev);
 	u32 dram_rows;
 	u32 dram_refresh_rate;
 	u32 mc_arb_rfsh_rate;
 	u32 tmp = (RREG32(MC_ARB_RAMCFG) & NOOFROWS_MASK) >> NOOFROWS_SHIFT;
 
-	if (pi->mem_gddr5)
-		dram_rows = 1 << (tmp + 10);
+	if (tmp >= 4)
+		dram_rows = 16384;
 	else
-		dram_rows = DDR3_DRAM_ROWS;
+		dram_rows = 1 << (tmp + 10);
 
 	dram_refresh_rate = 1 << ((RREG32(MC_SEQ_MISC0) & 0x3) + 3);
 	mc_arb_rfsh_rate = ((engine_clock * 10) * dram_refresh_rate / dram_rows - 32) / 64;
@@ -6013,16 +6037,11 @@ int si_dpm_set_power_state(struct radeon_device *rdev)
 		return ret;
 	}
 
-#if 0
-	/* XXX */
 	ret = si_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
 	if (ret) {
 		DRM_ERROR("si_dpm_force_performance_level failed\n");
 		return ret;
 	}
-#else
-	rdev->pm.dpm.forced_level = RADEON_DPM_FORCED_LEVEL_AUTO;
-#endif
 
 	return 0;
 }
@@ -6254,9 +6273,6 @@ int si_dpm_init(struct radeon_device *rdev)
 	struct evergreen_power_info *eg_pi;
 	struct ni_power_info *ni_pi;
 	struct si_power_info *si_pi;
-	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
-	u16 data_offset, size;
-	u8 frev, crev;
 	struct atom_clock_dividers dividers;
 	int ret;
 	u32 mask;
@@ -6347,16 +6363,7 @@ int si_dpm_init(struct radeon_device *rdev)
 	si_pi->vddc_phase_shed_control =
 		radeon_atom_is_voltage_gpio(rdev, SET_VOLTAGE_TYPE_ASIC_VDDC, VOLTAGE_OBJ_PHASE_LUT);
 
-	if (atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
-                                   &frev, &crev, &data_offset)) {
-		pi->sclk_ss = true;
-		pi->mclk_ss = true;
-		pi->dynamic_ss = true;
-	} else {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
-		pi->dynamic_ss = true;
-	}
+	rv770_get_engine_memory_ss(rdev);
 
 	pi->asi = RV770_ASI_DFLT;
 	pi->pasi = CYPRESS_HASI_DFLT;
@@ -6367,8 +6374,7 @@ int si_dpm_init(struct radeon_device *rdev)
 	eg_pi->sclk_deep_sleep = true;
 	si_pi->sclk_deep_sleep_above_low = false;
 
-	if (pi->gfx_clock_gating &&
-	    (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE))
+	if (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE)
 		pi->thermal_protection = true;
 	else
 		pi->thermal_protection = false;
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 5207591a598c..cd33084c7860 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -192,6 +192,7 @@ static struct hid_ll_driver logi_dj_ll_driver;
 static int logi_dj_output_hidraw_report(struct hid_device *hid, u8 * buf,
 					size_t count,
 					unsigned char report_type);
+static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev);
 
 static void logi_dj_recv_destroy_djhid_device(struct dj_receiver_dev *djrcv_dev,
 						struct dj_report *dj_report)
@@ -232,6 +233,7 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev,
 	if (dj_report->report_params[DEVICE_PAIRED_PARAM_SPFUNCTION] &
 	    SPFUNCTION_DEVICE_LIST_EMPTY) {
 		dbg_hid("%s: device list is empty\n", __func__);
+		djrcv_dev->querying_devices = false;
 		return;
 	}
 
@@ -242,6 +244,12 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev,
 		return;
 	}
 
+	if (djrcv_dev->paired_dj_devices[dj_report->device_index]) {
+		/* The device is already known. No need to reallocate it. */
+		dbg_hid("%s: device is already known\n", __func__);
+		return;
+	}
+
 	dj_hiddev = hid_allocate_device();
 	if (IS_ERR(dj_hiddev)) {
 		dev_err(&djrcv_hdev->dev, "%s: hid_allocate_device failed\n",
@@ -305,6 +313,7 @@ static void delayedwork_callback(struct work_struct *work)
 	struct dj_report dj_report;
 	unsigned long flags;
 	int count;
+	int retval;
 
 	dbg_hid("%s\n", __func__);
 
@@ -337,6 +346,25 @@ static void delayedwork_callback(struct work_struct *work)
 		logi_dj_recv_destroy_djhid_device(djrcv_dev, &dj_report);
 		break;
 	default:
+	/* A normal report (i. e. not belonging to a pair/unpair notification)
+	 * arriving here, means that the report arrived but we did not have a
+	 * paired dj_device associated to the report's device_index, this
+	 * means that the original "device paired" notification corresponding
+	 * to this dj_device never arrived to this driver. The reason is that
+	 * hid-core discards all packets coming from a device while probe() is
+	 * executing. */
+	if (!djrcv_dev->paired_dj_devices[dj_report.device_index]) {
+		/* ok, we don't know the device, just re-ask the
+		 * receiver for the list of connected devices. */
+		retval = logi_dj_recv_query_paired_devices(djrcv_dev);
+		if (!retval) {
+			/* everything went fine, so just leave */
+			break;
+		}
+		dev_err(&djrcv_dev->hdev->dev,
+			"%s:logi_dj_recv_query_paired_devices "
+			"error:%d\n", __func__, retval);
+		}
 		dbg_hid("%s: unexpected report type\n", __func__);
 	}
 }
@@ -367,6 +395,12 @@ static void logi_dj_recv_forward_null_report(struct dj_receiver_dev *djrcv_dev,
 	if (!djdev) {
 		dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]"
 			" is NULL, index %d\n", dj_report->device_index);
+		kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report));
+
+		if (schedule_work(&djrcv_dev->work) == 0) {
+			dbg_hid("%s: did not schedule the work item, was already "
+			"queued\n", __func__);
+		}
 		return;
 	}
 
@@ -397,6 +431,12 @@ static void logi_dj_recv_forward_report(struct dj_receiver_dev *djrcv_dev,
 	if (dj_device == NULL) {
 		dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]"
 			" is NULL, index %d\n", dj_report->device_index);
+		kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report));
+
+		if (schedule_work(&djrcv_dev->work) == 0) {
+			dbg_hid("%s: did not schedule the work item, was already "
+			"queued\n", __func__);
+		}
 		return;
 	}
 
@@ -444,6 +484,10 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev)
 	struct dj_report *dj_report;
 	int retval;
 
+	/* no need to protect djrcv_dev->querying_devices */
+	if (djrcv_dev->querying_devices)
+		return 0;
+
 	dj_report = kzalloc(sizeof(struct dj_report), GFP_KERNEL);
 	if (!dj_report)
 		return -ENOMEM;
@@ -455,6 +499,7 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev)
 	return retval;
 }
 
+
 static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev,
 					  unsigned timeout)
 {
diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h
index fd28a5e0ca3b..4a4000340ce1 100644
--- a/drivers/hid/hid-logitech-dj.h
+++ b/drivers/hid/hid-logitech-dj.h
@@ -101,6 +101,7 @@ struct dj_receiver_dev {
 	struct work_struct work;
 	struct kfifo notif_fifo;
 	spinlock_t lock;
+	bool querying_devices;
 };
 
 struct dj_device {
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index ecbc74923d06..87fbe2924cfa 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -369,7 +369,8 @@ static int sony_mapping(struct hid_device *hdev, struct hid_input *hi,
 	if (sc->quirks & PS3REMOTE)
 		return ps3remote_mapping(hdev, hi, field, usage, bit, max);
 
-	return -1;
+	/* Let hid-core decide for the others */
+	return 0;
 }
 
 /*
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index a7451632ceb4..6f1feb2c2e97 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -518,7 +518,6 @@ int hidraw_connect(struct hid_device *hid)
 		goto out;
 	}
 
-	mutex_unlock(&minors_lock);
 	init_waitqueue_head(&dev->wait);
 	INIT_LIST_HEAD(&dev->list);
 
@@ -528,6 +527,7 @@ int hidraw_connect(struct hid_device *hid)
 	dev->exist = 1;
 	hid->hidraw = dev;
 
+	mutex_unlock(&minors_lock);
 out:
 	return result;
 
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 4c605c70ebf9..deb5c25305af 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -562,7 +562,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 				struct hv_hotadd_state *has)
 {
 	int ret = 0;
-	int i, nid, t;
+	int i, nid;
 	unsigned long start_pfn;
 	unsigned long processed_pfn;
 	unsigned long total_pfn = pfn_count;
@@ -607,14 +607,11 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 
 		/*
 		 * Wait for the memory block to be onlined.
+		 * Since the hot add has succeeded, it is ok to
+		 * proceed even if the pages in the hot added region
+		 * have not been "onlined" within the allowed time.
 		 */
-		t = wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
-		if (t == 0) {
-			pr_info("hot_add memory timedout\n");
-			has->ha_end_pfn -= HA_CHUNK;
-			has->covered_end_pfn -=  processed_pfn;
-			break;
-		}
+		wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
 
 	}
 
@@ -978,6 +975,14 @@ static void post_status(struct hv_dynmem_device *dm)
 				dm->num_pages_ballooned +
 				compute_balloon_floor();
 
+	/*
+	 * If our transaction ID is no longer current, just don't
+	 * send the status. This can happen if we were interrupted
+	 * after we picked our transaction ID.
+	 */
+	if (status.hdr.trans_id != atomic_read(&trans_id))
+		return;
+
 	vmbus_sendpacket(dm->dev->channel, &status,
 				sizeof(struct dm_status),
 				(unsigned long)NULL,
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index a2464bf07c49..e8e071fc1d6d 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -690,7 +690,7 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	if (ret)
 		pr_err("Unable to register child device\n");
 	else
-		pr_info("child device %s registered\n",
+		pr_debug("child device %s registered\n",
 			dev_name(&child_device_obj->device));
 
 	return ret;
@@ -702,14 +702,14 @@ int vmbus_device_register(struct hv_device *child_device_obj)
  */
 void vmbus_device_unregister(struct hv_device *device_obj)
 {
+	pr_debug("child device %s unregistered\n",
+		dev_name(&device_obj->device));
+
 	/*
 	 * Kick off the process of unregistering the device.
 	 * This will call vmbus_remove() and eventually vmbus_device_release()
 	 */
 	device_unregister(&device_obj->device);
-
-	pr_info("child device %s unregistered\n",
-		dev_name(&device_obj->device));
 }
 
 
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index 0f34bca9f5e5..6099f50b28aa 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -215,7 +215,7 @@ static inline int adt7470_write_word_data(struct i2c_client *client, u8 reg,
 					  u16 value)
 {
 	return i2c_smbus_write_byte_data(client, reg, value & 0xFF)
-	       && i2c_smbus_write_byte_data(client, reg + 1, value >> 8);
+	       || i2c_smbus_write_byte_data(client, reg + 1, value >> 8);
 }
 
 static void adt7470_init_client(struct i2c_client *client)
diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c
index 328fb0353c17..a41b5f3fc506 100644
--- a/drivers/hwmon/max6697.c
+++ b/drivers/hwmon/max6697.c
@@ -605,12 +605,12 @@ static int max6697_init_chip(struct i2c_client *client)
 		if (ret < 0)
 			return ret;
 		ret = i2c_smbus_write_byte_data(client, MAX6581_REG_IDEALITY,
-						pdata->ideality_mask >> 1);
+						pdata->ideality_value);
 		if (ret < 0)
 			return ret;
 		ret = i2c_smbus_write_byte_data(client,
 						MAX6581_REG_IDEALITY_SELECT,
-						pdata->ideality_value);
+						pdata->ideality_mask >> 1);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/drivers/i2c/busses/i2c-kempld.c b/drivers/i2c/busses/i2c-kempld.c
index ccec916bc3eb..af8f65fb1c05 100644
--- a/drivers/i2c/busses/i2c-kempld.c
+++ b/drivers/i2c/busses/i2c-kempld.c
@@ -246,9 +246,9 @@ static void kempld_i2c_device_init(struct kempld_i2c_data *i2c)
 		bus_frequency = KEMPLD_I2C_FREQ_MAX;
 
 	if (pld->info.spec_major == 1)
-		prescale = pld->pld_clock / bus_frequency * 5 - 1000;
+		prescale = pld->pld_clock / (bus_frequency * 5) - 1000;
 	else
-		prescale = pld->pld_clock / bus_frequency * 4 - 3000;
+		prescale = pld->pld_clock / (bus_frequency * 4) - 3000;
 
 	if (prescale < 0)
 		prescale = 0;
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index df8ff5aea5b5..e2e9a0dade96 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -493,7 +493,7 @@ static int mxs_i2c_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg,
 	 * based on this empirical measurement and a lot of previous frobbing.
 	 */
 	i2c->cmd_err = 0;
-	if (msg->len < 8) {
+	if (0) {	/* disable PIO mode until a proper fix is made */
 		ret = mxs_i2c_pio_setup_xfer(adap, msg, flags);
 		if (ret)
 			mxs_i2c_reset(i2c);
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index 0ad208a69c29..3ceac3e91dde 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -60,7 +60,6 @@ static void tiadc_step_config(struct tiadc_device *adc_dev)
 {
 	unsigned int stepconfig;
 	int i, steps;
-	u32 step_en;
 
 	/*
 	 * There are 16 configurable steps and 8 analog input
@@ -86,8 +85,7 @@ static void tiadc_step_config(struct tiadc_device *adc_dev)
 		adc_dev->channel_step[i] = steps;
 		steps++;
 	}
-	step_en = get_adc_step_mask(adc_dev);
-	am335x_tsc_se_set(adc_dev->mfd_tscadc, step_en);
+
 }
 
 static const char * const chan_name_ain[] = {
@@ -142,10 +140,22 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 		int *val, int *val2, long mask)
 {
 	struct tiadc_device *adc_dev = iio_priv(indio_dev);
-	int i;
-	unsigned int fifo1count, read;
+	int i, map_val;
+	unsigned int fifo1count, read, stepid;
 	u32 step = UINT_MAX;
 	bool found = false;
+	u32 step_en;
+	unsigned long timeout = jiffies + usecs_to_jiffies
+				(IDLE_TIMEOUT * adc_dev->channels);
+	step_en = get_adc_step_mask(adc_dev);
+	am335x_tsc_se_set(adc_dev->mfd_tscadc, step_en);
+
+	/* Wait for ADC sequencer to complete sampling */
+	while (tiadc_readl(adc_dev, REG_ADCFSM) & SEQ_STATUS) {
+		if (time_after(jiffies, timeout))
+			return -EAGAIN;
+		}
+	map_val = chan->channel + TOTAL_CHANNELS;
 
 	/*
 	 * When the sub-system is first enabled,
@@ -170,12 +180,16 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 	fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT);
 	for (i = 0; i < fifo1count; i++) {
 		read = tiadc_readl(adc_dev, REG_FIFO1);
-		if (read >> 16 == step) {
-			*val = read & 0xfff;
+		stepid = read & FIFOREAD_CHNLID_MASK;
+		stepid = stepid >> 0x10;
+
+		if (stepid == map_val) {
+			read = read & FIFOREAD_DATA_MASK;
 			found = true;
+			*val = read;
 		}
 	}
-	am335x_tsc_se_update(adc_dev->mfd_tscadc);
+
 	if (found == false)
 		return -EBUSY;
 	return IIO_VAL_INT;
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index ea8a4146620d..0dd9bb873130 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -127,12 +127,17 @@ static struct iio_trigger *iio_trigger_find_by_name(const char *name,
 void iio_trigger_poll(struct iio_trigger *trig, s64 time)
 {
 	int i;
-	if (!trig->use_count)
-		for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++)
-			if (trig->subirqs[i].enabled) {
-				trig->use_count++;
+
+	if (!atomic_read(&trig->use_count)) {
+		atomic_set(&trig->use_count, CONFIG_IIO_CONSUMERS_PER_TRIGGER);
+
+		for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++) {
+			if (trig->subirqs[i].enabled)
 				generic_handle_irq(trig->subirq_base + i);
-			}
+			else
+				iio_trigger_notify_done(trig);
+		}
+	}
 }
 EXPORT_SYMBOL(iio_trigger_poll);
 
@@ -146,19 +151,24 @@ EXPORT_SYMBOL(iio_trigger_generic_data_rdy_poll);
 void iio_trigger_poll_chained(struct iio_trigger *trig, s64 time)
 {
 	int i;
-	if (!trig->use_count)
-		for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++)
-			if (trig->subirqs[i].enabled) {
-				trig->use_count++;
+
+	if (!atomic_read(&trig->use_count)) {
+		atomic_set(&trig->use_count, CONFIG_IIO_CONSUMERS_PER_TRIGGER);
+
+		for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++) {
+			if (trig->subirqs[i].enabled)
 				handle_nested_irq(trig->subirq_base + i);
-			}
+			else
+				iio_trigger_notify_done(trig);
+		}
+	}
 }
 EXPORT_SYMBOL(iio_trigger_poll_chained);
 
 void iio_trigger_notify_done(struct iio_trigger *trig)
 {
-	trig->use_count--;
-	if (trig->use_count == 0 && trig->ops && trig->ops->try_reenable)
+	if (atomic_dec_and_test(&trig->use_count) && trig->ops &&
+		trig->ops->try_reenable)
 		if (trig->ops->try_reenable(trig))
 			/* Missed an interrupt so launch new poll now */
 			iio_trigger_poll(trig, 0);
diff --git a/drivers/iio/light/adjd_s311.c b/drivers/iio/light/adjd_s311.c
index 5f4749e60b04..c1cd5698b8ae 100644
--- a/drivers/iio/light/adjd_s311.c
+++ b/drivers/iio/light/adjd_s311.c
@@ -232,7 +232,8 @@ static int adjd_s311_read_raw(struct iio_dev *indio_dev,
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
-		ret = adjd_s311_read_data(indio_dev, chan->address, val);
+		ret = adjd_s311_read_data(indio_dev,
+			ADJD_S311_DATA_REG(chan->address), val);
 		if (ret < 0)
 			return ret;
 		return IIO_VAL_INT;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index f1c279fabe64..7c0f9535fb7d 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -423,7 +423,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 	struct sockaddr_ib *addr;
 	union ib_gid gid, sgid, *dgid;
 	u16 pkey, index;
-	u8 port, p;
+	u8 p;
 	int i;
 
 	cma_dev = NULL;
@@ -443,7 +443,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 				if (!memcmp(&gid, dgid, sizeof(gid))) {
 					cma_dev = cur_dev;
 					sgid = gid;
-					port = p;
+					id_priv->id.port_num = p;
 					goto found;
 				}
 
@@ -451,7 +451,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 						 dgid->global.subnet_prefix)) {
 					cma_dev = cur_dev;
 					sgid = gid;
-					port = p;
+					id_priv->id.port_num = p;
 				}
 			}
 		}
@@ -462,7 +462,6 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 
 found:
 	cma_attach_to_dev(id_priv, cma_dev);
-	id_priv->id.port_num = port;
 	addr = (struct sockaddr_ib *) cma_src_addr(id_priv);
 	memcpy(&addr->sib_addr, &sgid, sizeof sgid);
 	cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr);
@@ -880,7 +879,8 @@ static int cma_save_net_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id
 {
 	struct cma_hdr *hdr;
 
-	if (listen_id->route.addr.src_addr.ss_family == AF_IB) {
+	if ((listen_id->route.addr.src_addr.ss_family == AF_IB) &&
+	    (ib_event->event == IB_CM_REQ_RECEIVED)) {
 		cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path);
 		return 0;
 	}
@@ -2677,29 +2677,32 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
 {
 	struct ib_cm_sidr_req_param req;
 	struct ib_cm_id	*id;
+	void *private_data;
 	int offset, ret;
 
+	memset(&req, 0, sizeof req);
 	offset = cma_user_data_offset(id_priv);
 	req.private_data_len = offset + conn_param->private_data_len;
 	if (req.private_data_len < conn_param->private_data_len)
 		return -EINVAL;
 
 	if (req.private_data_len) {
-		req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
-		if (!req.private_data)
+		private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
+		if (!private_data)
 			return -ENOMEM;
 	} else {
-		req.private_data = NULL;
+		private_data = NULL;
 	}
 
 	if (conn_param->private_data && conn_param->private_data_len)
-		memcpy((void *) req.private_data + offset,
-		       conn_param->private_data, conn_param->private_data_len);
+		memcpy(private_data + offset, conn_param->private_data,
+		       conn_param->private_data_len);
 
-	if (req.private_data) {
-		ret = cma_format_hdr((void *) req.private_data, id_priv);
+	if (private_data) {
+		ret = cma_format_hdr(private_data, id_priv);
 		if (ret)
 			goto out;
+		req.private_data = private_data;
 	}
 
 	id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler,
@@ -2721,7 +2724,7 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
 		id_priv->cm_id.ib = NULL;
 	}
 out:
-	kfree(req.private_data);
+	kfree(private_data);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index dc3fd1e8af07..4c837e66516b 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -2663,6 +2663,7 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 	int ret, i;
 	struct ib_qp_attr *attr;
 	struct ib_qp *qp;
+	u16 pkey_index;
 
 	attr = kmalloc(sizeof *attr, GFP_KERNEL);
 	if (!attr) {
@@ -2670,6 +2671,11 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 		return -ENOMEM;
 	}
 
+	ret = ib_find_pkey(port_priv->device, port_priv->port_num,
+			   IB_DEFAULT_PKEY_FULL, &pkey_index);
+	if (ret)
+		pkey_index = 0;
+
 	for (i = 0; i < IB_MAD_QPS_CORE; i++) {
 		qp = port_priv->qp_info[i].qp;
 		if (!qp)
@@ -2680,7 +2686,7 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 		 * one is needed for the Reset to Init transition
 		 */
 		attr->qp_state = IB_QPS_INIT;
-		attr->pkey_index = 0;
+		attr->pkey_index = pkey_index;
 		attr->qkey = (qp->qp_num == 0) ? 0 : IB_QP1_QKEY;
 		ret = ib_modify_qp(qp, attr, IB_QP_STATE |
 					     IB_QP_PKEY_INDEX | IB_QP_QKEY);
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index e87f2201b220..d2283837d451 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -226,6 +226,7 @@ static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int ve
 			mm->len = PAGE_ALIGN(((1UL << uresp.size_log2) + 1) *
 					     sizeof(struct t3_cqe));
 			uresp.memsize = mm->len;
+			uresp.reserved = 0;
 			resplen = sizeof uresp;
 		}
 		if (ib_copy_to_udata(udata, &uresp, resplen)) {
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 232040447e8a..a4975e1654a6 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1657,6 +1657,8 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		if (mm5) {
 			uresp.ma_sync_key = ucontext->key;
 			ucontext->key += PAGE_SIZE;
+		} else {
+			uresp.ma_sync_key =  0;
 		}
 		uresp.sq_key = ucontext->key;
 		ucontext->key += PAGE_SIZE;
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 4d599cedbb0b..f2a3f48107e7 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -1511,8 +1511,14 @@ static int create_pv_sqp(struct mlx4_ib_demux_pv_ctx *ctx,
 
 	memset(&attr, 0, sizeof attr);
 	attr.qp_state = IB_QPS_INIT;
-	attr.pkey_index =
-		to_mdev(ctx->ib_dev)->pkeys.virt2phys_pkey[ctx->slave][ctx->port - 1][0];
+	ret = 0;
+	if (create_tun)
+		ret = find_slave_port_pkey_ix(to_mdev(ctx->ib_dev), ctx->slave,
+					      ctx->port, IB_DEFAULT_PKEY_FULL,
+					      &attr.pkey_index);
+	if (ret || !create_tun)
+		attr.pkey_index =
+			to_mdev(ctx->ib_dev)->pkeys.virt2phys_pkey[ctx->slave][ctx->port - 1][0];
 	attr.qkey = IB_QP1_QKEY;
 	attr.port_num = ctx->port;
 	ret = ib_modify_qp(tun_qp->qp, &attr, qp_attr_mask_INIT);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8000fff4d444..3f831de9a4d8 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -619,7 +619,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 
 	resp.tot_uuars = req.total_num_uuars;
 	resp.num_ports = dev->mdev.caps.num_ports;
-	err = ib_copy_to_udata(udata, &resp, sizeof(resp));
+	err = ib_copy_to_udata(udata, &resp,
+			       sizeof(resp) - sizeof(resp.reserved));
 	if (err)
 		goto out_uars;
 
@@ -1426,7 +1427,8 @@ static int init_one(struct pci_dev *pdev,
 	if (err)
 		goto err_eqs;
 
-	if (ib_register_device(&dev->ib_dev, NULL))
+	err = ib_register_device(&dev->ib_dev, NULL);
+	if (err)
 		goto err_rsrc;
 
 	err = create_umr_res(dev);
@@ -1434,8 +1436,9 @@ static int init_one(struct pci_dev *pdev,
 		goto err_dev;
 
 	for (i = 0; i < ARRAY_SIZE(mlx5_class_attributes); i++) {
-		if (device_create_file(&dev->ib_dev.dev,
-				       mlx5_class_attributes[i]))
+		err = device_create_file(&dev->ib_dev.dev,
+					 mlx5_class_attributes[i]);
+		if (err)
 			goto err_umrc;
 	}
 
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 16ac54c9819f..045f8cdbd303 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -199,7 +199,7 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 
 static int sq_overhead(enum ib_qp_type qp_type)
 {
-	int size;
+	int size = 0;
 
 	switch (qp_type) {
 	case IB_QPT_XRC_INI:
diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c
index 418004c93feb..90200245c5eb 100644
--- a/drivers/infiniband/hw/nes/nes_hw.c
+++ b/drivers/infiniband/hw/nes/nes_hw.c
@@ -3570,10 +3570,10 @@ static void nes_process_iwarp_aeqe(struct nes_device *nesdev,
 	tcp_state = (aeq_info & NES_AEQE_TCP_STATE_MASK) >> NES_AEQE_TCP_STATE_SHIFT;
 	iwarp_state = (aeq_info & NES_AEQE_IWARP_STATE_MASK) >> NES_AEQE_IWARP_STATE_SHIFT;
 	nes_debug(NES_DBG_AEQ, "aeid = 0x%04X, qp-cq id = %d, aeqe = %p,"
-			" Tcp state = %d, iWARP state = %d\n",
+			" Tcp state = %s, iWARP state = %s\n",
 			async_event_id,
 			le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX]), aeqe,
-			tcp_state, iwarp_state);
+			nes_tcp_state_str[tcp_state], nes_iwarp_state_str[iwarp_state]);
 
 	aeqe_cq_id = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX]);
 	if (aeq_info & NES_AEQE_QP) {
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 8f67fe2e91e6..5b53ca5a2284 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1384,6 +1384,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd,
 
 			if (ibpd->uobject) {
 				uresp.mmap_sq_db_index = nesqp->mmap_sq_db_index;
+				uresp.mmap_rq_db_index = 0;
 				uresp.actual_sq_size = sq_size;
 				uresp.actual_rq_size = rq_size;
 				uresp.qp_id = nesqp->hwqp.qp_id;
@@ -1767,7 +1768,7 @@ static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
 		resp.cq_id = nescq->hw_cq.cq_number;
 		resp.cq_size = nescq->hw_cq.cq_size;
 		resp.mmap_db_index = 0;
-		if (ib_copy_to_udata(udata, &resp, sizeof resp)) {
+		if (ib_copy_to_udata(udata, &resp, sizeof resp - sizeof resp.reserved)) {
 			nes_free_resource(nesadapter, nesadapter->allocated_cqs, cq_num);
 			kfree(nescq);
 			return ERR_PTR(-EFAULT);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index a877a8ed7907..f4c587c68f64 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -29,7 +29,6 @@
 #include <net/netevent.h>
 
 #include <rdma/ib_addr.h>
-#include <rdma/ib_cache.h>
 
 #include "ocrdma.h"
 #include "ocrdma_verbs.h"
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index dcfbab177faa..f36630e4b6be 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -242,6 +242,7 @@ struct ib_ucontext *ocrdma_alloc_ucontext(struct ib_device *ibdev,
 	memset(ctx->ah_tbl.va, 0, map_len);
 	ctx->ah_tbl.len = map_len;
 
+	memset(&resp, 0, sizeof(resp));
 	resp.ah_tbl_len = ctx->ah_tbl.len;
 	resp.ah_tbl_page = ctx->ah_tbl.pa;
 
@@ -253,7 +254,6 @@ struct ib_ucontext *ocrdma_alloc_ucontext(struct ib_device *ibdev,
 	resp.wqe_size = dev->attr.wqe_size;
 	resp.rqe_size = dev->attr.rqe_size;
 	resp.dpp_wqe_size = dev->attr.wqe_size;
-	resp.rsvd = 0;
 
 	memcpy(resp.fw_ver, dev->attr.fw_ver, sizeof(resp.fw_ver));
 	status = ib_copy_to_udata(udata, &resp, sizeof(resp));
@@ -338,6 +338,7 @@ static int ocrdma_copy_pd_uresp(struct ocrdma_pd *pd,
 	struct ocrdma_alloc_pd_uresp rsp;
 	struct ocrdma_ucontext *uctx = get_ocrdma_ucontext(ib_ctx);
 
+	memset(&rsp, 0, sizeof(rsp));
 	rsp.id = pd->id;
 	rsp.dpp_enabled = pd->dpp_enabled;
 	db_page_addr = pd->dev->nic_info.unmapped_db +
@@ -692,6 +693,7 @@ static int ocrdma_copy_cq_uresp(struct ocrdma_cq *cq, struct ib_udata *udata,
 	struct ocrdma_ucontext *uctx;
 	struct ocrdma_create_cq_uresp uresp;
 
+	memset(&uresp, 0, sizeof(uresp));
 	uresp.cq_id = cq->id;
 	uresp.page_size = cq->len;
 	uresp.num_pages = 1;
@@ -1460,6 +1462,7 @@ static int ocrdma_copy_srq_uresp(struct ocrdma_srq *srq, struct ib_udata *udata)
 	int status;
 	struct ocrdma_create_srq_uresp uresp;
 
+	memset(&uresp, 0, sizeof(uresp));
 	uresp.rq_dbid = srq->rq.dbid;
 	uresp.num_rq_pages = 1;
 	uresp.rq_page_addr[0] = srq->rq.pa;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 21e8b09d4bf8..016e7429adf6 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -1596,6 +1596,8 @@ static void sdma_7322_p_errors(struct qib_pportdata *ppd, u64 errs)
 	struct qib_devdata *dd = ppd->dd;
 
 	errs &= QIB_E_P_SDMAERRS;
+	err_decode(ppd->cpspec->sdmamsgbuf, sizeof(ppd->cpspec->sdmamsgbuf),
+		   errs, qib_7322p_error_msgs);
 
 	if (errs & QIB_E_P_SDMAUNEXPDATA)
 		qib_dev_err(dd, "IB%u:%u SDmaUnexpData\n", dd->unit,
diff --git a/drivers/infiniband/hw/qib/qib_sdma.c b/drivers/infiniband/hw/qib/qib_sdma.c
index 32162d355370..9b5322d8cd5a 100644
--- a/drivers/infiniband/hw/qib/qib_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_sdma.c
@@ -717,7 +717,7 @@ void dump_sdma_state(struct qib_pportdata *ppd)
 	struct qib_sdma_txreq *txp, *txpnext;
 	__le64 *descqp;
 	u64 desc[2];
-	dma_addr_t addr;
+	u64 addr;
 	u16 gen, dwlen, dwoffset;
 	u16 head, tail, cnt;
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 2cfa76f5d99e..196b1d13cbcb 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -932,12 +932,47 @@ int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
 	return 0;
 }
 
+/*
+ * Takes whatever value which is in pkey index 0 and updates priv->pkey
+ * returns 0 if the pkey value was changed.
+ */
+static inline int update_parent_pkey(struct ipoib_dev_priv *priv)
+{
+	int result;
+	u16 prev_pkey;
+
+	prev_pkey = priv->pkey;
+	result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
+	if (result) {
+		ipoib_warn(priv, "ib_query_pkey port %d failed (ret = %d)\n",
+			   priv->port, result);
+		return result;
+	}
+
+	priv->pkey |= 0x8000;
+
+	if (prev_pkey != priv->pkey) {
+		ipoib_dbg(priv, "pkey changed from 0x%x to 0x%x\n",
+			  prev_pkey, priv->pkey);
+		/*
+		 * Update the pkey in the broadcast address, while making sure to set
+		 * the full membership bit, so that we join the right broadcast group.
+		 */
+		priv->dev->broadcast[8] = priv->pkey >> 8;
+		priv->dev->broadcast[9] = priv->pkey & 0xff;
+		return 0;
+	}
+
+	return 1;
+}
+
 static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 				enum ipoib_flush_level level)
 {
 	struct ipoib_dev_priv *cpriv;
 	struct net_device *dev = priv->dev;
 	u16 new_index;
+	int result;
 
 	mutex_lock(&priv->vlan_mutex);
 
@@ -951,6 +986,10 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 	mutex_unlock(&priv->vlan_mutex);
 
 	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) {
+		/* for non-child devices must check/update the pkey value here */
+		if (level == IPOIB_FLUSH_HEAVY &&
+		    !test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags))
+			update_parent_pkey(priv);
 		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
 		return;
 	}
@@ -961,21 +1000,32 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 	}
 
 	if (level == IPOIB_FLUSH_HEAVY) {
-		if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
-			clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
-			ipoib_ib_dev_down(dev, 0);
-			ipoib_ib_dev_stop(dev, 0);
-			if (ipoib_pkey_dev_delay_open(dev))
+		/* child devices chase their origin pkey value, while non-child
+		 * (parent) devices should always takes what present in pkey index 0
+		 */
+		if (test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+			if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
+				clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+				ipoib_ib_dev_down(dev, 0);
+				ipoib_ib_dev_stop(dev, 0);
+				if (ipoib_pkey_dev_delay_open(dev))
+					return;
+			}
+			/* restart QP only if P_Key index is changed */
+			if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
+			    new_index == priv->pkey_index) {
+				ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
 				return;
+			}
+			priv->pkey_index = new_index;
+		} else {
+			result = update_parent_pkey(priv);
+			/* restart QP only if P_Key value changed */
+			if (result) {
+				ipoib_dbg(priv, "Not flushing - P_Key value not changed.\n");
+				return;
+			}
 		}
-
-		/* restart QP only if P_Key index is changed */
-		if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
-		    new_index == priv->pkey_index) {
-			ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
-			return;
-		}
-		priv->pkey_index = new_index;
 	}
 
 	if (level == IPOIB_FLUSH_LIGHT) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index b6e049a3c7a8..c6f71a88c55c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1461,7 +1461,7 @@ static ssize_t create_child(struct device *dev,
 	if (sscanf(buf, "%i", &pkey) != 1)
 		return -EINVAL;
 
-	if (pkey < 0 || pkey > 0xffff)
+	if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000)
 		return -EINVAL;
 
 	/*
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
index 74685936c948..f81abe16cf09 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -119,6 +119,15 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
 	} else
 		child_pkey  = nla_get_u16(data[IFLA_IPOIB_PKEY]);
 
+	if (child_pkey == 0 || child_pkey == 0x8000)
+		return -EINVAL;
+
+	/*
+	 * Set the full membership bit, so that we join the right
+	 * broadcast group, etc.
+	 */
+	child_pkey |= 0x8000;
+
 	err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, IPOIB_RTNL_CHILD);
 
 	if (!err && data)
diff --git a/drivers/macintosh/windfarm_rm31.c b/drivers/macintosh/windfarm_rm31.c
index 0b9a79b2f48a..82fc86a90c1a 100644
--- a/drivers/macintosh/windfarm_rm31.c
+++ b/drivers/macintosh/windfarm_rm31.c
@@ -439,15 +439,15 @@ static void backside_setup_pid(void)
 
 /* Slots fan */
 static const struct wf_pid_param slots_param = {
-	.interval	= 5,
-	.history_len	= 2,
-	.gd		= 30 << 20,
-	.gp		= 5 << 20,
-	.gr		= 0,
-	.itarget	= 40 << 16,
-	.additive	= 1,
-	.min		= 300,
-	.max		= 4000,
+	.interval	= 1,
+	.history_len	= 20,
+	.gd		= 0,
+	.gp		= 0,
+	.gr		= 0x00100000,
+	.itarget	= 3200000,
+	.additive	= 0,
+	.min		= 20,
+	.max		= 100,
 };
 
 static void slots_fan_tick(void)
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 048f2947e08b..e45f5575fd4d 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -63,7 +63,10 @@
 #include "bcache.h"
 #include "btree.h"
 
+#include <linux/freezer.h>
+#include <linux/kthread.h>
 #include <linux/random.h>
+#include <trace/events/bcache.h>
 
 #define MAX_IN_FLIGHT_DISCARDS		8U
 
@@ -151,7 +154,7 @@ static void discard_finish(struct work_struct *w)
 	mutex_unlock(&ca->set->bucket_lock);
 
 	closure_wake_up(&ca->set->bucket_wait);
-	wake_up(&ca->set->alloc_wait);
+	wake_up_process(ca->alloc_thread);
 
 	closure_put(&ca->set->cl);
 }
@@ -350,38 +353,30 @@ static void invalidate_buckets(struct cache *ca)
 		break;
 	}
 
-	pr_debug("free %zu/%zu free_inc %zu/%zu unused %zu/%zu",
-		 fifo_used(&ca->free), ca->free.size,
-		 fifo_used(&ca->free_inc), ca->free_inc.size,
-		 fifo_used(&ca->unused), ca->unused.size);
+	trace_bcache_alloc_invalidate(ca);
 }
 
 #define allocator_wait(ca, cond)					\
 do {									\
-	DEFINE_WAIT(__wait);						\
-									\
 	while (1) {							\
-		prepare_to_wait(&ca->set->alloc_wait,			\
-				&__wait, TASK_INTERRUPTIBLE);		\
+		set_current_state(TASK_INTERRUPTIBLE);			\
 		if (cond)						\
 			break;						\
 									\
 		mutex_unlock(&(ca)->set->bucket_lock);			\
-		if (test_bit(CACHE_SET_STOPPING_2, &ca->set->flags)) {	\
-			finish_wait(&ca->set->alloc_wait, &__wait);	\
-			closure_return(cl);				\
-		}							\
+		if (kthread_should_stop())				\
+			return 0;					\
 									\
+		try_to_freeze();					\
 		schedule();						\
 		mutex_lock(&(ca)->set->bucket_lock);			\
 	}								\
-									\
-	finish_wait(&ca->set->alloc_wait, &__wait);			\
+	__set_current_state(TASK_RUNNING);				\
 } while (0)
 
-void bch_allocator_thread(struct closure *cl)
+static int bch_allocator_thread(void *arg)
 {
-	struct cache *ca = container_of(cl, struct cache, alloc);
+	struct cache *ca = arg;
 
 	mutex_lock(&ca->set->bucket_lock);
 
@@ -442,7 +437,7 @@ long bch_bucket_alloc(struct cache *ca, unsigned watermark, struct closure *cl)
 {
 	long r = -1;
 again:
-	wake_up(&ca->set->alloc_wait);
+	wake_up_process(ca->alloc_thread);
 
 	if (fifo_used(&ca->free) > ca->watermark[watermark] &&
 	    fifo_pop(&ca->free, r)) {
@@ -476,9 +471,7 @@ again:
 		return r;
 	}
 
-	pr_debug("alloc failure: blocked %i free %zu free_inc %zu unused %zu",
-		 atomic_read(&ca->set->prio_blocked), fifo_used(&ca->free),
-		 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
+	trace_bcache_alloc_fail(ca);
 
 	if (cl) {
 		closure_wait(&ca->set->bucket_wait, cl);
@@ -552,6 +545,17 @@ int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
 
 /* Init */
 
+int bch_cache_allocator_start(struct cache *ca)
+{
+	struct task_struct *k = kthread_run(bch_allocator_thread,
+					    ca, "bcache_allocator");
+	if (IS_ERR(k))
+		return PTR_ERR(k);
+
+	ca->alloc_thread = k;
+	return 0;
+}
+
 void bch_cache_allocator_exit(struct cache *ca)
 {
 	struct discard *d;
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d3e15b42a4ab..b39f6f0b45f2 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -178,7 +178,6 @@
 #define pr_fmt(fmt) "bcache: %s() " fmt "\n", __func__
 
 #include <linux/bio.h>
-#include <linux/blktrace_api.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -388,8 +387,6 @@ struct keybuf_key {
 typedef bool (keybuf_pred_fn)(struct keybuf *, struct bkey *);
 
 struct keybuf {
-	keybuf_pred_fn		*key_predicate;
-
 	struct bkey		last_scanned;
 	spinlock_t		lock;
 
@@ -437,9 +434,12 @@ struct bcache_device {
 
 	/* If nonzero, we're detaching/unregistering from cache set */
 	atomic_t		detaching;
+	int			flush_done;
+
+	uint64_t		nr_stripes;
+	unsigned		stripe_size_bits;
+	atomic_t		*stripe_sectors_dirty;
 
-	atomic_long_t		sectors_dirty;
-	unsigned long		sectors_dirty_gc;
 	unsigned long		sectors_dirty_last;
 	long			sectors_dirty_derivative;
 
@@ -531,6 +531,7 @@ struct cached_dev {
 	unsigned		sequential_merge:1;
 	unsigned		verify:1;
 
+	unsigned		partial_stripes_expensive:1;
 	unsigned		writeback_metadata:1;
 	unsigned		writeback_running:1;
 	unsigned char		writeback_percent;
@@ -565,8 +566,7 @@ struct cache {
 
 	unsigned		watermark[WATERMARK_MAX];
 
-	struct closure		alloc;
-	struct workqueue_struct	*alloc_workqueue;
+	struct task_struct	*alloc_thread;
 
 	struct closure		prio;
 	struct prio_set		*disk_buckets;
@@ -664,13 +664,9 @@ struct gc_stat {
  * CACHE_SET_STOPPING always gets set first when we're closing down a cache set;
  * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e.
  * flushing dirty data).
- *
- * CACHE_SET_STOPPING_2 gets set at the last phase, when it's time to shut down
- * the allocation thread.
  */
 #define CACHE_SET_UNREGISTERING		0
 #define	CACHE_SET_STOPPING		1
-#define	CACHE_SET_STOPPING_2		2
 
 struct cache_set {
 	struct closure		cl;
@@ -703,9 +699,6 @@ struct cache_set {
 	/* For the btree cache */
 	struct shrinker		shrink;
 
-	/* For the allocator itself */
-	wait_queue_head_t	alloc_wait;
-
 	/* For the btree cache and anything allocation related */
 	struct mutex		bucket_lock;
 
@@ -823,10 +816,9 @@ struct cache_set {
 
 	/*
 	 * A btree node on disk could have too many bsets for an iterator to fit
-	 * on the stack - this is a single element mempool for btree_read_work()
+	 * on the stack - have to dynamically allocate them
 	 */
-	struct mutex		fill_lock;
-	struct btree_iter	*fill_iter;
+	mempool_t		*fill_iter;
 
 	/*
 	 * btree_sort() is a merge sort and requires temporary space - single
@@ -834,6 +826,7 @@ struct cache_set {
 	 */
 	struct mutex		sort_lock;
 	struct bset		*sort;
+	unsigned		sort_crit_factor;
 
 	/* List of buckets we're currently writing data to */
 	struct list_head	data_buckets;
@@ -906,8 +899,6 @@ static inline unsigned local_clock_us(void)
 	return local_clock() >> 10;
 }
 
-#define MAX_BSETS		4U
-
 #define BTREE_PRIO		USHRT_MAX
 #define INITIAL_PRIO		32768
 
@@ -1112,23 +1103,6 @@ static inline void __bkey_put(struct cache_set *c, struct bkey *k)
 		atomic_dec_bug(&PTR_BUCKET(c, k, i)->pin);
 }
 
-/* Blktrace macros */
-
-#define blktrace_msg(c, fmt, ...)					\
-do {									\
-	struct request_queue *q = bdev_get_queue(c->bdev);		\
-	if (q)								\
-		blk_add_trace_msg(q, fmt, ##__VA_ARGS__);		\
-} while (0)
-
-#define blktrace_msg_all(s, fmt, ...)					\
-do {									\
-	struct cache *_c;						\
-	unsigned i;							\
-	for_each_cache(_c, (s), i)					\
-		blktrace_msg(_c, fmt, ##__VA_ARGS__);			\
-} while (0)
-
 static inline void cached_dev_put(struct cached_dev *dc)
 {
 	if (atomic_dec_and_test(&dc->count))
@@ -1173,10 +1147,16 @@ static inline uint8_t bucket_disk_gen(struct bucket *b)
 	static struct kobj_attribute ksysfs_##n =			\
 		__ATTR(n, S_IWUSR|S_IRUSR, show, store)
 
-/* Forward declarations */
+static inline void wake_up_allocators(struct cache_set *c)
+{
+	struct cache *ca;
+	unsigned i;
+
+	for_each_cache(ca, c, i)
+		wake_up_process(ca->alloc_thread);
+}
 
-void bch_writeback_queue(struct cached_dev *);
-void bch_writeback_add(struct cached_dev *, unsigned);
+/* Forward declarations */
 
 void bch_count_io_errors(struct cache *, int, const char *);
 void bch_bbio_count_io_errors(struct cache_set *, struct bio *,
@@ -1193,7 +1173,6 @@ void bch_submit_bbio(struct bio *, struct cache_set *, struct bkey *, unsigned);
 uint8_t bch_inc_gen(struct cache *, struct bucket *);
 void bch_rescale_priorities(struct cache_set *, int);
 bool bch_bucket_add_unused(struct cache *, struct bucket *);
-void bch_allocator_thread(struct closure *);
 
 long bch_bucket_alloc(struct cache *, unsigned, struct closure *);
 void bch_bucket_free(struct cache_set *, struct bkey *);
@@ -1241,9 +1220,9 @@ void bch_cache_set_stop(struct cache_set *);
 struct cache_set *bch_cache_set_alloc(struct cache_sb *);
 void bch_btree_cache_free(struct cache_set *);
 int bch_btree_cache_alloc(struct cache_set *);
-void bch_cached_dev_writeback_init(struct cached_dev *);
 void bch_moving_init_cache_set(struct cache_set *);
 
+int bch_cache_allocator_start(struct cache *ca);
 void bch_cache_allocator_exit(struct cache *ca);
 int bch_cache_allocator_init(struct cache *ca);
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 1d27d3af3251..8010eed06a51 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -78,6 +78,7 @@ struct bkey *bch_keylist_pop(struct keylist *l)
 bool __bch_ptr_invalid(struct cache_set *c, int level, const struct bkey *k)
 {
 	unsigned i;
+	char buf[80];
 
 	if (level && (!KEY_PTRS(k) || !KEY_SIZE(k) || KEY_DIRTY(k)))
 		goto bad;
@@ -102,7 +103,8 @@ bool __bch_ptr_invalid(struct cache_set *c, int level, const struct bkey *k)
 
 	return false;
 bad:
-	cache_bug(c, "spotted bad key %s: %s", pkey(k), bch_ptr_status(c, k));
+	bch_bkey_to_text(buf, sizeof(buf), k);
+	cache_bug(c, "spotted bad key %s: %s", buf, bch_ptr_status(c, k));
 	return true;
 }
 
@@ -162,10 +164,16 @@ bool bch_ptr_bad(struct btree *b, const struct bkey *k)
 #ifdef CONFIG_BCACHE_EDEBUG
 bug:
 	mutex_unlock(&b->c->bucket_lock);
-	btree_bug(b,
+
+	{
+		char buf[80];
+
+		bch_bkey_to_text(buf, sizeof(buf), k);
+		btree_bug(b,
 "inconsistent pointer %s: bucket %zu pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
-		  pkey(k), PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
-		  g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
+			  buf, PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
+			  g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
+	}
 	return true;
 #endif
 }
@@ -1084,33 +1092,39 @@ void bch_btree_sort_into(struct btree *b, struct btree *new)
 	new->sets->size = 0;
 }
 
+#define SORT_CRIT	(4096 / sizeof(uint64_t))
+
 void bch_btree_sort_lazy(struct btree *b)
 {
-	if (b->nsets) {
-		unsigned i, j, keys = 0, total;
+	unsigned crit = SORT_CRIT;
+	int i;
 
-		for (i = 0; i <= b->nsets; i++)
-			keys += b->sets[i].data->keys;
-
-		total = keys;
+	/* Don't sort if nothing to do */
+	if (!b->nsets)
+		goto out;
 
-		for (j = 0; j < b->nsets; j++) {
-			if (keys * 2 < total ||
-			    keys < 1000) {
-				bch_btree_sort_partial(b, j);
-				return;
-			}
+	/* If not a leaf node, always sort */
+	if (b->level) {
+		bch_btree_sort(b);
+		return;
+	}
 
-			keys -= b->sets[j].data->keys;
-		}
+	for (i = b->nsets - 1; i >= 0; --i) {
+		crit *= b->c->sort_crit_factor;
 
-		/* Must sort if b->nsets == 3 or we'll overflow */
-		if (b->nsets >= (MAX_BSETS - 1) - b->level) {
-			bch_btree_sort(b);
+		if (b->sets[i].data->keys < crit) {
+			bch_btree_sort_partial(b, i);
 			return;
 		}
 	}
 
+	/* Sort if we'd overflow */
+	if (b->nsets + 1 == MAX_BSETS) {
+		bch_btree_sort(b);
+		return;
+	}
+
+out:
 	bset_build_written_tree(b);
 }
 
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index 57a9cff41546..ae115a253d73 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -1,6 +1,8 @@
 #ifndef _BCACHE_BSET_H
 #define _BCACHE_BSET_H
 
+#include <linux/slab.h>
+
 /*
  * BKEYS:
  *
@@ -142,6 +144,8 @@
 
 /* Btree key comparison/iteration */
 
+#define MAX_BSETS		4U
+
 struct btree_iter {
 	size_t size, used;
 	struct btree_iter_set {
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 7a5658f04e62..ee372884c405 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -24,6 +24,7 @@
 #include "btree.h"
 #include "debug.h"
 #include "request.h"
+#include "writeback.h"
 
 #include <linux/slab.h>
 #include <linux/bitops.h>
@@ -134,44 +135,17 @@ static uint64_t btree_csum_set(struct btree *b, struct bset *i)
 	return crc ^ 0xffffffffffffffffULL;
 }
 
-static void btree_bio_endio(struct bio *bio, int error)
+static void bch_btree_node_read_done(struct btree *b)
 {
-	struct closure *cl = bio->bi_private;
-	struct btree *b = container_of(cl, struct btree, io.cl);
-
-	if (error)
-		set_btree_node_io_error(b);
-
-	bch_bbio_count_io_errors(b->c, bio, error, (bio->bi_rw & WRITE)
-				 ? "writing btree" : "reading btree");
-	closure_put(cl);
-}
-
-static void btree_bio_init(struct btree *b)
-{
-	BUG_ON(b->bio);
-	b->bio = bch_bbio_alloc(b->c);
-
-	b->bio->bi_end_io	= btree_bio_endio;
-	b->bio->bi_private	= &b->io.cl;
-}
-
-void bch_btree_read_done(struct closure *cl)
-{
-	struct btree *b = container_of(cl, struct btree, io.cl);
-	struct bset *i = b->sets[0].data;
-	struct btree_iter *iter = b->c->fill_iter;
 	const char *err = "bad btree header";
-	BUG_ON(b->nsets || b->written);
-
-	bch_bbio_free(b->bio, b->c);
-	b->bio = NULL;
+	struct bset *i = b->sets[0].data;
+	struct btree_iter *iter;
 
-	mutex_lock(&b->c->fill_lock);
+	iter = mempool_alloc(b->c->fill_iter, GFP_NOWAIT);
+	iter->size = b->c->sb.bucket_size / b->c->sb.block_size;
 	iter->used = 0;
 
-	if (btree_node_io_error(b) ||
-	    !i->seq)
+	if (!i->seq)
 		goto err;
 
 	for (;
@@ -228,17 +202,8 @@ void bch_btree_read_done(struct closure *cl)
 	if (b->written < btree_blocks(b))
 		bch_bset_init_next(b);
 out:
-
-	mutex_unlock(&b->c->fill_lock);
-
-	spin_lock(&b->c->btree_read_time_lock);
-	bch_time_stats_update(&b->c->btree_read_time, b->io_start_time);
-	spin_unlock(&b->c->btree_read_time_lock);
-
-	smp_wmb(); /* read_done is our write lock */
-	set_btree_node_read_done(b);
-
-	closure_return(cl);
+	mempool_free(iter, b->c->fill_iter);
+	return;
 err:
 	set_btree_node_io_error(b);
 	bch_cache_set_error(b->c, "%s at bucket %zu, block %zu, %u keys",
@@ -247,48 +212,69 @@ err:
 	goto out;
 }
 
-void bch_btree_read(struct btree *b)
+static void btree_node_read_endio(struct bio *bio, int error)
+{
+	struct closure *cl = bio->bi_private;
+	closure_put(cl);
+}
+
+void bch_btree_node_read(struct btree *b)
 {
-	BUG_ON(b->nsets || b->written);
+	uint64_t start_time = local_clock();
+	struct closure cl;
+	struct bio *bio;
+
+	trace_bcache_btree_read(b);
+
+	closure_init_stack(&cl);
+
+	bio = bch_bbio_alloc(b->c);
+	bio->bi_rw	= REQ_META|READ_SYNC;
+	bio->bi_size	= KEY_SIZE(&b->key) << 9;
+	bio->bi_end_io	= btree_node_read_endio;
+	bio->bi_private	= &cl;
+
+	bch_bio_map(bio, b->sets[0].data);
+
+	bch_submit_bbio(bio, b->c, &b->key, 0);
+	closure_sync(&cl);
 
-	if (!closure_trylock(&b->io.cl, &b->c->cl))
-		BUG();
+	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+		set_btree_node_io_error(b);
 
-	b->io_start_time = local_clock();
+	bch_bbio_free(bio, b->c);
 
-	btree_bio_init(b);
-	b->bio->bi_rw	= REQ_META|READ_SYNC;
-	b->bio->bi_size	= KEY_SIZE(&b->key) << 9;
+	if (btree_node_io_error(b))
+		goto err;
 
-	bch_bio_map(b->bio, b->sets[0].data);
+	bch_btree_node_read_done(b);
 
-	pr_debug("%s", pbtree(b));
-	trace_bcache_btree_read(b->bio);
-	bch_submit_bbio(b->bio, b->c, &b->key, 0);
+	spin_lock(&b->c->btree_read_time_lock);
+	bch_time_stats_update(&b->c->btree_read_time, start_time);
+	spin_unlock(&b->c->btree_read_time_lock);
 
-	continue_at(&b->io.cl, bch_btree_read_done, system_wq);
+	return;
+err:
+	bch_cache_set_error(b->c, "io error reading bucket %lu",
+			    PTR_BUCKET_NR(b->c, &b->key, 0));
 }
 
 static void btree_complete_write(struct btree *b, struct btree_write *w)
 {
 	if (w->prio_blocked &&
 	    !atomic_sub_return(w->prio_blocked, &b->c->prio_blocked))
-		wake_up(&b->c->alloc_wait);
+		wake_up_allocators(b->c);
 
 	if (w->journal) {
 		atomic_dec_bug(w->journal);
 		__closure_wake_up(&b->c->journal.wait);
 	}
 
-	if (w->owner)
-		closure_put(w->owner);
-
 	w->prio_blocked	= 0;
 	w->journal	= NULL;
-	w->owner	= NULL;
 }
 
-static void __btree_write_done(struct closure *cl)
+static void __btree_node_write_done(struct closure *cl)
 {
 	struct btree *b = container_of(cl, struct btree, io.cl);
 	struct btree_write *w = btree_prev_write(b);
@@ -304,7 +290,7 @@ static void __btree_write_done(struct closure *cl)
 	closure_return(cl);
 }
 
-static void btree_write_done(struct closure *cl)
+static void btree_node_write_done(struct closure *cl)
 {
 	struct btree *b = container_of(cl, struct btree, io.cl);
 	struct bio_vec *bv;
@@ -313,10 +299,22 @@ static void btree_write_done(struct closure *cl)
 	__bio_for_each_segment(bv, b->bio, n, 0)
 		__free_page(bv->bv_page);
 
-	__btree_write_done(cl);
+	__btree_node_write_done(cl);
 }
 
-static void do_btree_write(struct btree *b)
+static void btree_node_write_endio(struct bio *bio, int error)
+{
+	struct closure *cl = bio->bi_private;
+	struct btree *b = container_of(cl, struct btree, io.cl);
+
+	if (error)
+		set_btree_node_io_error(b);
+
+	bch_bbio_count_io_errors(b->c, bio, error, "writing btree");
+	closure_put(cl);
+}
+
+static void do_btree_node_write(struct btree *b)
 {
 	struct closure *cl = &b->io.cl;
 	struct bset *i = b->sets[b->nsets].data;
@@ -325,15 +323,34 @@ static void do_btree_write(struct btree *b)
 	i->version	= BCACHE_BSET_VERSION;
 	i->csum		= btree_csum_set(b, i);
 
-	btree_bio_init(b);
-	b->bio->bi_rw	= REQ_META|WRITE_SYNC;
-	b->bio->bi_size	= set_blocks(i, b->c) * block_bytes(b->c);
+	BUG_ON(b->bio);
+	b->bio = bch_bbio_alloc(b->c);
+
+	b->bio->bi_end_io	= btree_node_write_endio;
+	b->bio->bi_private	= &b->io.cl;
+	b->bio->bi_rw		= REQ_META|WRITE_SYNC|REQ_FUA;
+	b->bio->bi_size		= set_blocks(i, b->c) * block_bytes(b->c);
 	bch_bio_map(b->bio, i);
 
+	/*
+	 * If we're appending to a leaf node, we don't technically need FUA -
+	 * this write just needs to be persisted before the next journal write,
+	 * which will be marked FLUSH|FUA.
+	 *
+	 * Similarly if we're writing a new btree root - the pointer is going to
+	 * be in the next journal entry.
+	 *
+	 * But if we're writing a new btree node (that isn't a root) or
+	 * appending to a non leaf btree node, we need either FUA or a flush
+	 * when we write the parent with the new pointer. FUA is cheaper than a
+	 * flush, and writes appending to leaf nodes aren't blocking anything so
+	 * just make all btree node writes FUA to keep things sane.
+	 */
+
 	bkey_copy(&k.key, &b->key);
 	SET_PTR_OFFSET(&k.key, 0, PTR_OFFSET(&k.key, 0) + bset_offset(b, i));
 
-	if (!bch_bio_alloc_pages(b->bio, GFP_NOIO)) {
+	if (!bio_alloc_pages(b->bio, GFP_NOIO)) {
 		int j;
 		struct bio_vec *bv;
 		void *base = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
@@ -342,40 +359,41 @@ static void do_btree_write(struct btree *b)
 			memcpy(page_address(bv->bv_page),
 			       base + j * PAGE_SIZE, PAGE_SIZE);
 
-		trace_bcache_btree_write(b->bio);
 		bch_submit_bbio(b->bio, b->c, &k.key, 0);
 
-		continue_at(cl, btree_write_done, NULL);
+		continue_at(cl, btree_node_write_done, NULL);
 	} else {
 		b->bio->bi_vcnt = 0;
 		bch_bio_map(b->bio, i);
 
-		trace_bcache_btree_write(b->bio);
 		bch_submit_bbio(b->bio, b->c, &k.key, 0);
 
 		closure_sync(cl);
-		__btree_write_done(cl);
+		__btree_node_write_done(cl);
 	}
 }
 
-static void __btree_write(struct btree *b)
+void bch_btree_node_write(struct btree *b, struct closure *parent)
 {
 	struct bset *i = b->sets[b->nsets].data;
 
+	trace_bcache_btree_write(b);
+
 	BUG_ON(current->bio_list);
+	BUG_ON(b->written >= btree_blocks(b));
+	BUG_ON(b->written && !i->keys);
+	BUG_ON(b->sets->data->seq != i->seq);
+	bch_check_key_order(b, i);
 
-	closure_lock(&b->io, &b->c->cl);
 	cancel_delayed_work(&b->work);
 
+	/* If caller isn't waiting for write, parent refcount is cache set */
+	closure_lock(&b->io, parent ?: &b->c->cl);
+
 	clear_bit(BTREE_NODE_dirty,	 &b->flags);
 	change_bit(BTREE_NODE_write_idx, &b->flags);
 
-	bch_check_key_order(b, i);
-	BUG_ON(b->written && !i->keys);
-
-	do_btree_write(b);
-
-	pr_debug("%s block %i keys %i", pbtree(b), b->written, i->keys);
+	do_btree_node_write(b);
 
 	b->written += set_blocks(i, b->c);
 	atomic_long_add(set_blocks(i, b->c) * b->c->sb.block_size,
@@ -387,37 +405,31 @@ static void __btree_write(struct btree *b)
 		bch_bset_init_next(b);
 }
 
-static void btree_write_work(struct work_struct *w)
+static void btree_node_write_work(struct work_struct *w)
 {
 	struct btree *b = container_of(to_delayed_work(w), struct btree, work);
 
-	down_write(&b->lock);
+	rw_lock(true, b, b->level);
 
 	if (btree_node_dirty(b))
-		__btree_write(b);
-	up_write(&b->lock);
+		bch_btree_node_write(b, NULL);
+	rw_unlock(true, b);
 }
 
-void bch_btree_write(struct btree *b, bool now, struct btree_op *op)
+static void bch_btree_leaf_dirty(struct btree *b, struct btree_op *op)
 {
 	struct bset *i = b->sets[b->nsets].data;
 	struct btree_write *w = btree_current_write(b);
 
-	BUG_ON(b->written &&
-	       (b->written >= btree_blocks(b) ||
-		i->seq != b->sets[0].data->seq ||
-		!i->keys));
+	BUG_ON(!b->written);
+	BUG_ON(!i->keys);
 
-	if (!btree_node_dirty(b)) {
-		set_btree_node_dirty(b);
-		queue_delayed_work(btree_io_wq, &b->work,
-				   msecs_to_jiffies(30000));
-	}
+	if (!btree_node_dirty(b))
+		queue_delayed_work(btree_io_wq, &b->work, 30 * HZ);
 
-	w->prio_blocked += b->prio_blocked;
-	b->prio_blocked = 0;
+	set_btree_node_dirty(b);
 
-	if (op && op->journal && !b->level) {
+	if (op && op->journal) {
 		if (w->journal &&
 		    journal_pin_cmp(b->c, w, op)) {
 			atomic_dec_bug(w->journal);
@@ -430,23 +442,10 @@ void bch_btree_write(struct btree *b, bool now, struct btree_op *op)
 		}
 	}
 
-	if (current->bio_list)
-		return;
-
 	/* Force write if set is too big */
-	if (now ||
-	    b->level ||
-	    set_bytes(i) > PAGE_SIZE - 48) {
-		if (op && now) {
-			/* Must wait on multiple writes */
-			BUG_ON(w->owner);
-			w->owner = &op->cl;
-			closure_get(&op->cl);
-		}
-
-		__btree_write(b);
-	}
-	BUG_ON(!b->written);
+	if (set_bytes(i) > PAGE_SIZE - 48 &&
+	    !current->bio_list)
+		bch_btree_node_write(b, NULL);
 }
 
 /*
@@ -559,7 +558,7 @@ static struct btree *mca_bucket_alloc(struct cache_set *c,
 	init_rwsem(&b->lock);
 	lockdep_set_novalidate_class(&b->lock);
 	INIT_LIST_HEAD(&b->list);
-	INIT_DELAYED_WORK(&b->work, btree_write_work);
+	INIT_DELAYED_WORK(&b->work, btree_node_write_work);
 	b->c = c;
 	closure_init_unlocked(&b->io);
 
@@ -582,7 +581,7 @@ static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order)
 	BUG_ON(btree_node_dirty(b) && !b->sets[0].data);
 
 	if (cl && btree_node_dirty(b))
-		bch_btree_write(b, true, NULL);
+		bch_btree_node_write(b, NULL);
 
 	if (cl)
 		closure_wait_event_async(&b->io.wait, cl,
@@ -623,6 +622,13 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
 	else if (!mutex_trylock(&c->bucket_lock))
 		return -1;
 
+	/*
+	 * It's _really_ critical that we don't free too many btree nodes - we
+	 * have to always leave ourselves a reserve. The reserve is how we
+	 * guarantee that allocating memory for a new btree node can always
+	 * succeed, so that inserting keys into the btree can always succeed and
+	 * IO can always make forward progress:
+	 */
 	nr /= c->btree_pages;
 	nr = min_t(unsigned long, nr, mca_can_free(c));
 
@@ -766,6 +772,8 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct bkey *k,
 	int ret = -ENOMEM;
 	struct btree *i;
 
+	trace_bcache_btree_cache_cannibalize(c);
+
 	if (!cl)
 		return ERR_PTR(-ENOMEM);
 
@@ -784,7 +792,6 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct bkey *k,
 		return ERR_PTR(-EAGAIN);
 	}
 
-	/* XXX: tracepoint */
 	c->try_harder = cl;
 	c->try_harder_start = local_clock();
 retry:
@@ -905,6 +912,9 @@ retry:
 	b = mca_find(c, k);
 
 	if (!b) {
+		if (current->bio_list)
+			return ERR_PTR(-EAGAIN);
+
 		mutex_lock(&c->bucket_lock);
 		b = mca_alloc(c, k, level, &op->cl);
 		mutex_unlock(&c->bucket_lock);
@@ -914,7 +924,7 @@ retry:
 		if (IS_ERR(b))
 			return b;
 
-		bch_btree_read(b);
+		bch_btree_node_read(b);
 
 		if (!write)
 			downgrade_write(&b->lock);
@@ -937,15 +947,12 @@ retry:
 	for (; i <= b->nsets; i++)
 		prefetch(b->sets[i].data);
 
-	if (!closure_wait_event(&b->io.wait, &op->cl,
-				btree_node_read_done(b))) {
-		rw_unlock(write, b);
-		b = ERR_PTR(-EAGAIN);
-	} else if (btree_node_io_error(b)) {
+	if (btree_node_io_error(b)) {
 		rw_unlock(write, b);
-		b = ERR_PTR(-EIO);
-	} else
-		BUG_ON(!b->written);
+		return ERR_PTR(-EIO);
+	}
+
+	BUG_ON(!b->written);
 
 	return b;
 }
@@ -959,7 +966,7 @@ static void btree_node_prefetch(struct cache_set *c, struct bkey *k, int level)
 	mutex_unlock(&c->bucket_lock);
 
 	if (!IS_ERR_OR_NULL(b)) {
-		bch_btree_read(b);
+		bch_btree_node_read(b);
 		rw_unlock(true, b);
 	}
 }
@@ -970,24 +977,19 @@ static void btree_node_free(struct btree *b, struct btree_op *op)
 {
 	unsigned i;
 
+	trace_bcache_btree_node_free(b);
+
 	/*
 	 * The BUG_ON() in btree_node_get() implies that we must have a write
 	 * lock on parent to free or even invalidate a node
 	 */
 	BUG_ON(op->lock <= b->level);
 	BUG_ON(b == b->c->root);
-	pr_debug("bucket %s", pbtree(b));
 
 	if (btree_node_dirty(b))
 		btree_complete_write(b, btree_current_write(b));
 	clear_bit(BTREE_NODE_dirty, &b->flags);
 
-	if (b->prio_blocked &&
-	    !atomic_sub_return(b->prio_blocked, &b->c->prio_blocked))
-		wake_up(&b->c->alloc_wait);
-
-	b->prio_blocked = 0;
-
 	cancel_delayed_work(&b->work);
 
 	mutex_lock(&b->c->bucket_lock);
@@ -1028,17 +1030,20 @@ retry:
 		goto retry;
 	}
 
-	set_btree_node_read_done(b);
 	b->accessed = 1;
 	bch_bset_init_next(b);
 
 	mutex_unlock(&c->bucket_lock);
+
+	trace_bcache_btree_node_alloc(b);
 	return b;
 err_free:
 	bch_bucket_free(c, &k.key);
 	__bkey_put(c, &k.key);
 err:
 	mutex_unlock(&c->bucket_lock);
+
+	trace_bcache_btree_node_alloc_fail(b);
 	return b;
 }
 
@@ -1137,11 +1142,8 @@ static int btree_gc_mark_node(struct btree *b, unsigned *keys,
 		gc->nkeys++;
 
 		gc->data += KEY_SIZE(k);
-		if (KEY_DIRTY(k)) {
+		if (KEY_DIRTY(k))
 			gc->dirty += KEY_SIZE(k);
-			if (d)
-				d->sectors_dirty_gc += KEY_SIZE(k);
-		}
 	}
 
 	for (t = b->sets; t <= &b->sets[b->nsets]; t++)
@@ -1166,14 +1168,11 @@ static struct btree *btree_gc_alloc(struct btree *b, struct bkey *k,
 
 	if (!IS_ERR_OR_NULL(n)) {
 		swap(b, n);
+		__bkey_put(b->c, &b->key);
 
 		memcpy(k->ptr, b->key.ptr,
 		       sizeof(uint64_t) * KEY_PTRS(&b->key));
 
-		__bkey_put(b->c, &b->key);
-		atomic_inc(&b->c->prio_blocked);
-		b->prio_blocked++;
-
 		btree_node_free(n, op);
 		up_write(&n->lock);
 	}
@@ -1278,7 +1277,7 @@ static void btree_gc_coalesce(struct btree *b, struct btree_op *op,
 	btree_node_free(r->b, op);
 	up_write(&r->b->lock);
 
-	pr_debug("coalesced %u nodes", nodes);
+	trace_bcache_btree_gc_coalesce(nodes);
 
 	gc->nodes--;
 	nodes--;
@@ -1293,14 +1292,9 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 	void write(struct btree *r)
 	{
 		if (!r->written)
-			bch_btree_write(r, true, op);
-		else if (btree_node_dirty(r)) {
-			BUG_ON(btree_current_write(r)->owner);
-			btree_current_write(r)->owner = writes;
-			closure_get(writes);
-
-			bch_btree_write(r, true, NULL);
-		}
+			bch_btree_node_write(r, &op->cl);
+		else if (btree_node_dirty(r))
+			bch_btree_node_write(r, writes);
 
 		up_write(&r->lock);
 	}
@@ -1386,9 +1380,7 @@ static int bch_btree_gc_root(struct btree *b, struct btree_op *op,
 		ret = btree_gc_recurse(b, op, writes, gc);
 
 	if (!b->written || btree_node_dirty(b)) {
-		atomic_inc(&b->c->prio_blocked);
-		b->prio_blocked++;
-		bch_btree_write(b, true, n ? op : NULL);
+		bch_btree_node_write(b, n ? &op->cl : NULL);
 	}
 
 	if (!IS_ERR_OR_NULL(n)) {
@@ -1405,7 +1397,6 @@ static void btree_gc_start(struct cache_set *c)
 {
 	struct cache *ca;
 	struct bucket *b;
-	struct bcache_device **d;
 	unsigned i;
 
 	if (!c->gc_mark_valid)
@@ -1419,16 +1410,12 @@ static void btree_gc_start(struct cache_set *c)
 	for_each_cache(ca, c, i)
 		for_each_bucket(b, ca) {
 			b->gc_gen = b->gen;
-			if (!atomic_read(&b->pin))
+			if (!atomic_read(&b->pin)) {
 				SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+				SET_GC_SECTORS_USED(b, 0);
+			}
 		}
 
-	for (d = c->devices;
-	     d < c->devices + c->nr_uuids;
-	     d++)
-		if (*d)
-			(*d)->sectors_dirty_gc = 0;
-
 	mutex_unlock(&c->bucket_lock);
 }
 
@@ -1437,7 +1424,6 @@ size_t bch_btree_gc_finish(struct cache_set *c)
 	size_t available = 0;
 	struct bucket *b;
 	struct cache *ca;
-	struct bcache_device **d;
 	unsigned i;
 
 	mutex_lock(&c->bucket_lock);
@@ -1480,22 +1466,6 @@ size_t bch_btree_gc_finish(struct cache_set *c)
 		}
 	}
 
-	for (d = c->devices;
-	     d < c->devices + c->nr_uuids;
-	     d++)
-		if (*d) {
-			unsigned long last =
-				atomic_long_read(&((*d)->sectors_dirty));
-			long difference = (*d)->sectors_dirty_gc - last;
-
-			pr_debug("sectors dirty off by %li", difference);
-
-			(*d)->sectors_dirty_last += difference;
-
-			atomic_long_set(&((*d)->sectors_dirty),
-					(*d)->sectors_dirty_gc);
-		}
-
 	mutex_unlock(&c->bucket_lock);
 	return available;
 }
@@ -1508,10 +1478,9 @@ static void bch_btree_gc(struct closure *cl)
 	struct gc_stat stats;
 	struct closure writes;
 	struct btree_op op;
-
 	uint64_t start_time = local_clock();
-	trace_bcache_gc_start(c->sb.set_uuid);
-	blktrace_msg_all(c, "Starting gc");
+
+	trace_bcache_gc_start(c);
 
 	memset(&stats, 0, sizeof(struct gc_stat));
 	closure_init_stack(&writes);
@@ -1520,14 +1489,14 @@ static void bch_btree_gc(struct closure *cl)
 
 	btree_gc_start(c);
 
+	atomic_inc(&c->prio_blocked);
+
 	ret = btree_root(gc_root, c, &op, &writes, &stats);
 	closure_sync(&op.cl);
 	closure_sync(&writes);
 
 	if (ret) {
-		blktrace_msg_all(c, "Stopped gc");
 		pr_warn("gc failed!");
-
 		continue_at(cl, bch_btree_gc, bch_gc_wq);
 	}
 
@@ -1537,6 +1506,9 @@ static void bch_btree_gc(struct closure *cl)
 
 	available = bch_btree_gc_finish(c);
 
+	atomic_dec(&c->prio_blocked);
+	wake_up_allocators(c);
+
 	bch_time_stats_update(&c->btree_gc_time, start_time);
 
 	stats.key_bytes *= sizeof(uint64_t);
@@ -1544,10 +1516,8 @@ static void bch_btree_gc(struct closure *cl)
 	stats.data	<<= 9;
 	stats.in_use	= (c->nbuckets - available) * 100 / c->nbuckets;
 	memcpy(&c->gc_stats, &stats, sizeof(struct gc_stat));
-	blktrace_msg_all(c, "Finished gc");
 
-	trace_bcache_gc_end(c->sb.set_uuid);
-	wake_up(&c->alloc_wait);
+	trace_bcache_gc_end(c);
 
 	continue_at(cl, bch_moving_gc, bch_gc_wq);
 }
@@ -1654,14 +1624,14 @@ static bool fix_overlapping_extents(struct btree *b,
 				    struct btree_iter *iter,
 				    struct btree_op *op)
 {
-	void subtract_dirty(struct bkey *k, int sectors)
+	void subtract_dirty(struct bkey *k, uint64_t offset, int sectors)
 	{
-		struct bcache_device *d = b->c->devices[KEY_INODE(k)];
-
-		if (KEY_DIRTY(k) && d)
-			atomic_long_sub(sectors, &d->sectors_dirty);
+		if (KEY_DIRTY(k))
+			bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
+						     offset, -sectors);
 	}
 
+	uint64_t old_offset;
 	unsigned old_size, sectors_found = 0;
 
 	while (1) {
@@ -1673,6 +1643,7 @@ static bool fix_overlapping_extents(struct btree *b,
 		if (bkey_cmp(k, &START_KEY(insert)) <= 0)
 			continue;
 
+		old_offset = KEY_START(k);
 		old_size = KEY_SIZE(k);
 
 		/*
@@ -1728,7 +1699,7 @@ static bool fix_overlapping_extents(struct btree *b,
 
 			struct bkey *top;
 
-			subtract_dirty(k, KEY_SIZE(insert));
+			subtract_dirty(k, KEY_START(insert), KEY_SIZE(insert));
 
 			if (bkey_written(b, k)) {
 				/*
@@ -1775,7 +1746,7 @@ static bool fix_overlapping_extents(struct btree *b,
 			}
 		}
 
-		subtract_dirty(k, old_size - KEY_SIZE(k));
+		subtract_dirty(k, old_offset, old_size - KEY_SIZE(k));
 	}
 
 check_failed:
@@ -1798,7 +1769,7 @@ static bool btree_insert_key(struct btree *b, struct btree_op *op,
 {
 	struct bset *i = b->sets[b->nsets].data;
 	struct bkey *m, *prev;
-	const char *status = "insert";
+	unsigned status = BTREE_INSERT_STATUS_INSERT;
 
 	BUG_ON(bkey_cmp(k, &b->key) > 0);
 	BUG_ON(b->level && !KEY_PTRS(k));
@@ -1831,17 +1802,17 @@ static bool btree_insert_key(struct btree *b, struct btree_op *op,
 			goto insert;
 
 		/* prev is in the tree, if we merge we're done */
-		status = "back merging";
+		status = BTREE_INSERT_STATUS_BACK_MERGE;
 		if (prev &&
 		    bch_bkey_try_merge(b, prev, k))
 			goto merged;
 
-		status = "overwrote front";
+		status = BTREE_INSERT_STATUS_OVERWROTE;
 		if (m != end(i) &&
 		    KEY_PTRS(m) == KEY_PTRS(k) && !KEY_SIZE(m))
 			goto copy;
 
-		status = "front merge";
+		status = BTREE_INSERT_STATUS_FRONT_MERGE;
 		if (m != end(i) &&
 		    bch_bkey_try_merge(b, k, m))
 			goto copy;
@@ -1851,21 +1822,21 @@ static bool btree_insert_key(struct btree *b, struct btree_op *op,
 insert:	shift_keys(b, m, k);
 copy:	bkey_copy(m, k);
 merged:
-	bch_check_keys(b, "%s for %s at %s: %s", status,
-		       op_type(op), pbtree(b), pkey(k));
-	bch_check_key_order_msg(b, i, "%s for %s at %s: %s", status,
-				op_type(op), pbtree(b), pkey(k));
+	if (KEY_DIRTY(k))
+		bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
+					     KEY_START(k), KEY_SIZE(k));
+
+	bch_check_keys(b, "%u for %s", status, op_type(op));
 
 	if (b->level && !KEY_OFFSET(k))
-		b->prio_blocked++;
+		btree_current_write(b)->prio_blocked++;
 
-	pr_debug("%s for %s at %s: %s", status,
-		 op_type(op), pbtree(b), pkey(k));
+	trace_bcache_btree_insert_key(b, k, op->type, status);
 
 	return true;
 }
 
-bool bch_btree_insert_keys(struct btree *b, struct btree_op *op)
+static bool bch_btree_insert_keys(struct btree *b, struct btree_op *op)
 {
 	bool ret = false;
 	struct bkey *k;
@@ -1896,7 +1867,7 @@ bool bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
 	    should_split(b))
 		goto out;
 
-	op->replace = KEY(op->inode, bio_end(bio), bio_sectors(bio));
+	op->replace = KEY(op->inode, bio_end_sector(bio), bio_sectors(bio));
 
 	SET_KEY_PTRS(&op->replace, 1);
 	get_random_bytes(&op->replace.ptr[0], sizeof(uint64_t));
@@ -1907,7 +1878,6 @@ bool bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
 
 	BUG_ON(op->type != BTREE_INSERT);
 	BUG_ON(!btree_insert_key(b, op, &tmp.k));
-	bch_btree_write(b, false, NULL);
 	ret = true;
 out:
 	downgrade_write(&b->lock);
@@ -1929,12 +1899,11 @@ static int btree_split(struct btree *b, struct btree_op *op)
 
 	split = set_blocks(n1->sets[0].data, n1->c) > (btree_blocks(b) * 4) / 5;
 
-	pr_debug("%ssplitting at %s keys %i", split ? "" : "not ",
-		 pbtree(b), n1->sets[0].data->keys);
-
 	if (split) {
 		unsigned keys = 0;
 
+		trace_bcache_btree_node_split(b, n1->sets[0].data->keys);
+
 		n2 = bch_btree_node_alloc(b->c, b->level, &op->cl);
 		if (IS_ERR(n2))
 			goto err_free1;
@@ -1967,18 +1936,21 @@ static int btree_split(struct btree *b, struct btree_op *op)
 		bkey_copy_key(&n2->key, &b->key);
 
 		bch_keylist_add(&op->keys, &n2->key);
-		bch_btree_write(n2, true, op);
+		bch_btree_node_write(n2, &op->cl);
 		rw_unlock(true, n2);
-	} else
+	} else {
+		trace_bcache_btree_node_compact(b, n1->sets[0].data->keys);
+
 		bch_btree_insert_keys(n1, op);
+	}
 
 	bch_keylist_add(&op->keys, &n1->key);
-	bch_btree_write(n1, true, op);
+	bch_btree_node_write(n1, &op->cl);
 
 	if (n3) {
 		bkey_copy_key(&n3->key, &MAX_KEY);
 		bch_btree_insert_keys(n3, op);
-		bch_btree_write(n3, true, op);
+		bch_btree_node_write(n3, &op->cl);
 
 		closure_sync(&op->cl);
 		bch_btree_set_root(n3);
@@ -2082,8 +2054,12 @@ static int bch_btree_insert_recurse(struct btree *b, struct btree_op *op,
 
 		BUG_ON(write_block(b) != b->sets[b->nsets].data);
 
-		if (bch_btree_insert_keys(b, op))
-			bch_btree_write(b, false, op);
+		if (bch_btree_insert_keys(b, op)) {
+			if (!b->level)
+				bch_btree_leaf_dirty(b, op);
+			else
+				bch_btree_node_write(b, &op->cl);
+		}
 	}
 
 	return 0;
@@ -2140,6 +2116,11 @@ int bch_btree_insert(struct btree_op *op, struct cache_set *c)
 void bch_btree_set_root(struct btree *b)
 {
 	unsigned i;
+	struct closure cl;
+
+	closure_init_stack(&cl);
+
+	trace_bcache_btree_set_root(b);
 
 	BUG_ON(!b->written);
 
@@ -2153,8 +2134,8 @@ void bch_btree_set_root(struct btree *b)
 	b->c->root = b;
 	__bkey_put(b->c, &b->key);
 
-	bch_journal_meta(b->c, NULL);
-	pr_debug("%s for %pf", pbtree(b), __builtin_return_address(0));
+	bch_journal_meta(b->c, &cl);
+	closure_sync(&cl);
 }
 
 /* Cache lookup */
@@ -2215,9 +2196,6 @@ static int submit_partial_cache_hit(struct btree *b, struct btree_op *op,
 					 KEY_OFFSET(k) - bio->bi_sector);
 
 		n = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
-		if (!n)
-			return -EAGAIN;
-
 		if (n == bio)
 			op->lookup_done = true;
 
@@ -2240,7 +2218,6 @@ static int submit_partial_cache_hit(struct btree *b, struct btree_op *op,
 		n->bi_end_io	= bch_cache_read_endio;
 		n->bi_private	= &s->cl;
 
-		trace_bcache_cache_hit(n);
 		__bch_submit_bbio(n, b->c);
 	}
 
@@ -2257,9 +2234,6 @@ int bch_btree_search_recurse(struct btree *b, struct btree_op *op)
 	struct btree_iter iter;
 	bch_btree_iter_init(b, &iter, &KEY(op->inode, bio->bi_sector, 0));
 
-	pr_debug("at %s searching for %u:%llu", pbtree(b), op->inode,
-		 (uint64_t) bio->bi_sector);
-
 	do {
 		k = bch_btree_iter_next_filter(&iter, b, bch_ptr_bad);
 		if (!k) {
@@ -2303,7 +2277,8 @@ static inline int keybuf_nonoverlapping_cmp(struct keybuf_key *l,
 }
 
 static int bch_btree_refill_keybuf(struct btree *b, struct btree_op *op,
-				   struct keybuf *buf, struct bkey *end)
+				   struct keybuf *buf, struct bkey *end,
+				   keybuf_pred_fn *pred)
 {
 	struct btree_iter iter;
 	bch_btree_iter_init(b, &iter, &buf->last_scanned);
@@ -2322,11 +2297,9 @@ static int bch_btree_refill_keybuf(struct btree *b, struct btree_op *op,
 			if (bkey_cmp(&buf->last_scanned, end) >= 0)
 				break;
 
-			if (buf->key_predicate(buf, k)) {
+			if (pred(buf, k)) {
 				struct keybuf_key *w;
 
-				pr_debug("%s", pkey(k));
-
 				spin_lock(&buf->lock);
 
 				w = array_alloc(&buf->freelist);
@@ -2343,7 +2316,7 @@ static int bch_btree_refill_keybuf(struct btree *b, struct btree_op *op,
 			if (!k)
 				break;
 
-			btree(refill_keybuf, k, b, op, buf, end);
+			btree(refill_keybuf, k, b, op, buf, end, pred);
 			/*
 			 * Might get an error here, but can't really do anything
 			 * and it'll get logged elsewhere. Just read what we
@@ -2361,7 +2334,7 @@ static int bch_btree_refill_keybuf(struct btree *b, struct btree_op *op,
 }
 
 void bch_refill_keybuf(struct cache_set *c, struct keybuf *buf,
-			  struct bkey *end)
+		       struct bkey *end, keybuf_pred_fn *pred)
 {
 	struct bkey start = buf->last_scanned;
 	struct btree_op op;
@@ -2369,7 +2342,7 @@ void bch_refill_keybuf(struct cache_set *c, struct keybuf *buf,
 
 	cond_resched();
 
-	btree_root(refill_keybuf, c, &op, buf, end);
+	btree_root(refill_keybuf, c, &op, buf, end, pred);
 	closure_sync(&op.cl);
 
 	pr_debug("found %s keys from %llu:%llu to %llu:%llu",
@@ -2455,7 +2428,8 @@ struct keybuf_key *bch_keybuf_next(struct keybuf *buf)
 
 struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *c,
 					     struct keybuf *buf,
-					     struct bkey *end)
+					     struct bkey *end,
+					     keybuf_pred_fn *pred)
 {
 	struct keybuf_key *ret;
 
@@ -2469,15 +2443,14 @@ struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *c,
 			break;
 		}
 
-		bch_refill_keybuf(c, buf, end);
+		bch_refill_keybuf(c, buf, end, pred);
 	}
 
 	return ret;
 }
 
-void bch_keybuf_init(struct keybuf *buf, keybuf_pred_fn *fn)
+void bch_keybuf_init(struct keybuf *buf)
 {
-	buf->key_predicate	= fn;
 	buf->last_scanned	= MAX_KEY;
 	buf->keys		= RB_ROOT;
 
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index af4a7092a28c..3333d3723633 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -102,7 +102,6 @@
 #include "debug.h"
 
 struct btree_write {
-	struct closure		*owner;
 	atomic_t		*journal;
 
 	/* If btree_split() frees a btree node, it writes a new pointer to that
@@ -142,16 +141,12 @@ struct btree {
 	 */
 	struct bset_tree	sets[MAX_BSETS];
 
-	/* Used to refcount bio splits, also protects b->bio */
+	/* For outstanding btree writes, used as a lock - protects write_idx */
 	struct closure_with_waitlist	io;
 
-	/* Gets transferred to w->prio_blocked - see the comment there */
-	int			prio_blocked;
-
 	struct list_head	list;
 	struct delayed_work	work;
 
-	uint64_t		io_start_time;
 	struct btree_write	writes[2];
 	struct bio		*bio;
 };
@@ -164,13 +159,11 @@ static inline void set_btree_node_ ## flag(struct btree *b)		\
 {	set_bit(BTREE_NODE_ ## flag, &b->flags); }			\
 
 enum btree_flags {
-	BTREE_NODE_read_done,
 	BTREE_NODE_io_error,
 	BTREE_NODE_dirty,
 	BTREE_NODE_write_idx,
 };
 
-BTREE_FLAG(read_done);
 BTREE_FLAG(io_error);
 BTREE_FLAG(dirty);
 BTREE_FLAG(write_idx);
@@ -278,6 +271,13 @@ struct btree_op {
 	BKEY_PADDED(replace);
 };
 
+enum {
+	BTREE_INSERT_STATUS_INSERT,
+	BTREE_INSERT_STATUS_BACK_MERGE,
+	BTREE_INSERT_STATUS_OVERWROTE,
+	BTREE_INSERT_STATUS_FRONT_MERGE,
+};
+
 void bch_btree_op_init_stack(struct btree_op *);
 
 static inline void rw_lock(bool w, struct btree *b, int level)
@@ -293,9 +293,7 @@ static inline void rw_unlock(bool w, struct btree *b)
 #ifdef CONFIG_BCACHE_EDEBUG
 	unsigned i;
 
-	if (w &&
-	    b->key.ptr[0] &&
-	    btree_node_read_done(b))
+	if (w && b->key.ptr[0])
 		for (i = 0; i <= b->nsets; i++)
 			bch_check_key_order(b, b->sets[i].data);
 #endif
@@ -370,9 +368,8 @@ static inline bool should_split(struct btree *b)
 		 > btree_blocks(b));
 }
 
-void bch_btree_read_done(struct closure *);
-void bch_btree_read(struct btree *);
-void bch_btree_write(struct btree *b, bool now, struct btree_op *op);
+void bch_btree_node_read(struct btree *);
+void bch_btree_node_write(struct btree *, struct closure *);
 
 void bch_cannibalize_unlock(struct cache_set *, struct closure *);
 void bch_btree_set_root(struct btree *);
@@ -380,7 +377,6 @@ struct btree *bch_btree_node_alloc(struct cache_set *, int, struct closure *);
 struct btree *bch_btree_node_get(struct cache_set *, struct bkey *,
 				int, struct btree_op *);
 
-bool bch_btree_insert_keys(struct btree *, struct btree_op *);
 bool bch_btree_insert_check_key(struct btree *, struct btree_op *,
 				   struct bio *);
 int bch_btree_insert(struct btree_op *, struct cache_set *);
@@ -393,13 +389,14 @@ void bch_moving_gc(struct closure *);
 int bch_btree_check(struct cache_set *, struct btree_op *);
 uint8_t __bch_btree_mark_key(struct cache_set *, int, struct bkey *);
 
-void bch_keybuf_init(struct keybuf *, keybuf_pred_fn *);
-void bch_refill_keybuf(struct cache_set *, struct keybuf *, struct bkey *);
+void bch_keybuf_init(struct keybuf *);
+void bch_refill_keybuf(struct cache_set *, struct keybuf *, struct bkey *,
+		       keybuf_pred_fn *);
 bool bch_keybuf_check_overlapping(struct keybuf *, struct bkey *,
 				  struct bkey *);
 void bch_keybuf_del(struct keybuf *, struct keybuf_key *);
 struct keybuf_key *bch_keybuf_next(struct keybuf *);
-struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *,
-					  struct keybuf *, struct bkey *);
+struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *, struct keybuf *,
+					  struct bkey *, keybuf_pred_fn *);
 
 #endif
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index bd05a9a8c7cf..9aba2017f0d1 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -66,16 +66,18 @@ static inline void closure_put_after_sub(struct closure *cl, int flags)
 		} else {
 			struct closure *parent = cl->parent;
 			struct closure_waitlist *wait = closure_waitlist(cl);
+			closure_fn *destructor = cl->fn;
 
 			closure_debug_destroy(cl);
 
+			smp_mb();
 			atomic_set(&cl->remaining, -1);
 
 			if (wait)
 				closure_wake_up(wait);
 
-			if (cl->fn)
-				cl->fn(cl);
+			if (destructor)
+				destructor(cl);
 
 			if (parent)
 				closure_put(parent);
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 89fd5204924e..88e6411eab4f 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -47,11 +47,10 @@ const char *bch_ptr_status(struct cache_set *c, const struct bkey *k)
 	return "";
 }
 
-struct keyprint_hack bch_pkey(const struct bkey *k)
+int bch_bkey_to_text(char *buf, size_t size, const struct bkey *k)
 {
 	unsigned i = 0;
-	struct keyprint_hack r;
-	char *out = r.s, *end = r.s + KEYHACK_SIZE;
+	char *out = buf, *end = buf + size;
 
 #define p(...)	(out += scnprintf(out, end - out, __VA_ARGS__))
 
@@ -75,16 +74,14 @@ struct keyprint_hack bch_pkey(const struct bkey *k)
 	if (KEY_CSUM(k))
 		p(" cs%llu %llx", KEY_CSUM(k), k->ptr[1]);
 #undef p
-	return r;
+	return out - buf;
 }
 
-struct keyprint_hack bch_pbtree(const struct btree *b)
+int bch_btree_to_text(char *buf, size_t size, const struct btree *b)
 {
-	struct keyprint_hack r;
-
-	snprintf(r.s, 40, "%zu level %i/%i", PTR_BUCKET_NR(b->c, &b->key, 0),
-		 b->level, b->c->root ? b->c->root->level : -1);
-	return r;
+	return scnprintf(buf, size, "%zu level %i/%i",
+			 PTR_BUCKET_NR(b->c, &b->key, 0),
+			 b->level, b->c->root ? b->c->root->level : -1);
 }
 
 #if defined(CONFIG_BCACHE_DEBUG) || defined(CONFIG_BCACHE_EDEBUG)
@@ -100,10 +97,12 @@ static void dump_bset(struct btree *b, struct bset *i)
 {
 	struct bkey *k;
 	unsigned j;
+	char buf[80];
 
 	for (k = i->start; k < end(i); k = bkey_next(k)) {
+		bch_bkey_to_text(buf, sizeof(buf), k);
 		printk(KERN_ERR "block %zu key %zi/%u: %s", index(i, b),
-		       (uint64_t *) k - i->d, i->keys, pkey(k));
+		       (uint64_t *) k - i->d, i->keys, buf);
 
 		for (j = 0; j < KEY_PTRS(k); j++) {
 			size_t n = PTR_BUCKET_NR(b->c, k, j);
@@ -144,7 +143,7 @@ void bch_btree_verify(struct btree *b, struct bset *new)
 	v->written = 0;
 	v->level = b->level;
 
-	bch_btree_read(v);
+	bch_btree_node_read(v);
 	closure_wait_event(&v->io.wait, &cl,
 			   atomic_read(&b->io.cl.remaining) == -1);
 
@@ -200,7 +199,7 @@ void bch_data_verify(struct search *s)
 	if (!check)
 		return;
 
-	if (bch_bio_alloc_pages(check, GFP_NOIO))
+	if (bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
 	check->bi_rw		= READ_SYNC;
@@ -252,6 +251,7 @@ static void vdump_bucket_and_panic(struct btree *b, const char *fmt,
 				   va_list args)
 {
 	unsigned i;
+	char buf[80];
 
 	console_lock();
 
@@ -262,7 +262,8 @@ static void vdump_bucket_and_panic(struct btree *b, const char *fmt,
 
 	console_unlock();
 
-	panic("at %s\n", pbtree(b));
+	bch_btree_to_text(buf, sizeof(buf), b);
+	panic("at %s\n", buf);
 }
 
 void bch_check_key_order_msg(struct btree *b, struct bset *i,
@@ -337,6 +338,7 @@ static ssize_t bch_dump_read(struct file *file, char __user *buf,
 {
 	struct dump_iterator *i = file->private_data;
 	ssize_t ret = 0;
+	char kbuf[80];
 
 	while (size) {
 		struct keybuf_key *w;
@@ -355,11 +357,12 @@ static ssize_t bch_dump_read(struct file *file, char __user *buf,
 		if (i->bytes)
 			break;
 
-		w = bch_keybuf_next_rescan(i->c, &i->keys, &MAX_KEY);
+		w = bch_keybuf_next_rescan(i->c, &i->keys, &MAX_KEY, dump_pred);
 		if (!w)
 			break;
 
-		i->bytes = snprintf(i->buf, PAGE_SIZE, "%s\n", pkey(&w->key));
+		bch_bkey_to_text(kbuf, sizeof(kbuf), &w->key);
+		i->bytes = snprintf(i->buf, PAGE_SIZE, "%s\n", kbuf);
 		bch_keybuf_del(&i->keys, w);
 	}
 
@@ -377,7 +380,7 @@ static int bch_dump_open(struct inode *inode, struct file *file)
 
 	file->private_data = i;
 	i->c = c;
-	bch_keybuf_init(&i->keys, dump_pred);
+	bch_keybuf_init(&i->keys);
 	i->keys.last_scanned = KEY(0, 0, 0);
 
 	return 0;
@@ -409,142 +412,6 @@ void bch_debug_init_cache_set(struct cache_set *c)
 
 #endif
 
-/* Fuzz tester has rotted: */
-#if 0
-
-static ssize_t btree_fuzz(struct kobject *k, struct kobj_attribute *a,
-			  const char *buffer, size_t size)
-{
-	void dump(struct btree *b)
-	{
-		struct bset *i;
-
-		for (i = b->sets[0].data;
-		     index(i, b) < btree_blocks(b) &&
-		     i->seq == b->sets[0].data->seq;
-		     i = ((void *) i) + set_blocks(i, b->c) * block_bytes(b->c))
-			dump_bset(b, i);
-	}
-
-	struct cache_sb *sb;
-	struct cache_set *c;
-	struct btree *all[3], *b, *fill, *orig;
-	int j;
-
-	struct btree_op op;
-	bch_btree_op_init_stack(&op);
-
-	sb = kzalloc(sizeof(struct cache_sb), GFP_KERNEL);
-	if (!sb)
-		return -ENOMEM;
-
-	sb->bucket_size = 128;
-	sb->block_size = 4;
-
-	c = bch_cache_set_alloc(sb);
-	if (!c)
-		return -ENOMEM;
-
-	for (j = 0; j < 3; j++) {
-		BUG_ON(list_empty(&c->btree_cache));
-		all[j] = list_first_entry(&c->btree_cache, struct btree, list);
-		list_del_init(&all[j]->list);
-
-		all[j]->key = KEY(0, 0, c->sb.bucket_size);
-		bkey_copy_key(&all[j]->key, &MAX_KEY);
-	}
-
-	b = all[0];
-	fill = all[1];
-	orig = all[2];
-
-	while (1) {
-		for (j = 0; j < 3; j++)
-			all[j]->written = all[j]->nsets = 0;
-
-		bch_bset_init_next(b);
-
-		while (1) {
-			struct bset *i = write_block(b);
-			struct bkey *k = op.keys.top;
-			unsigned rand;
-
-			bkey_init(k);
-			rand = get_random_int();
-
-			op.type = rand & 1
-				? BTREE_INSERT
-				: BTREE_REPLACE;
-			rand >>= 1;
-
-			SET_KEY_SIZE(k, bucket_remainder(c, rand));
-			rand >>= c->bucket_bits;
-			rand &= 1024 * 512 - 1;
-			rand += c->sb.bucket_size;
-			SET_KEY_OFFSET(k, rand);
-#if 0
-			SET_KEY_PTRS(k, 1);
-#endif
-			bch_keylist_push(&op.keys);
-			bch_btree_insert_keys(b, &op);
-
-			if (should_split(b) ||
-			    set_blocks(i, b->c) !=
-			    __set_blocks(i, i->keys + 15, b->c)) {
-				i->csum = csum_set(i);
-
-				memcpy(write_block(fill),
-				       i, set_bytes(i));
-
-				b->written += set_blocks(i, b->c);
-				fill->written = b->written;
-				if (b->written == btree_blocks(b))
-					break;
-
-				bch_btree_sort_lazy(b);
-				bch_bset_init_next(b);
-			}
-		}
-
-		memcpy(orig->sets[0].data,
-		       fill->sets[0].data,
-		       btree_bytes(c));
-
-		bch_btree_sort(b);
-		fill->written = 0;
-		bch_btree_read_done(&fill->io.cl);
-
-		if (b->sets[0].data->keys != fill->sets[0].data->keys ||
-		    memcmp(b->sets[0].data->start,
-			   fill->sets[0].data->start,
-			   b->sets[0].data->keys * sizeof(uint64_t))) {
-			struct bset *i = b->sets[0].data;
-			struct bkey *k, *l;
-
-			for (k = i->start,
-			     l = fill->sets[0].data->start;
-			     k < end(i);
-			     k = bkey_next(k), l = bkey_next(l))
-				if (bkey_cmp(k, l) ||
-				    KEY_SIZE(k) != KEY_SIZE(l))
-					pr_err("key %zi differs: %s != %s",
-					       (uint64_t *) k - i->d,
-					       pkey(k), pkey(l));
-
-			for (j = 0; j < 3; j++) {
-				pr_err("**** Set %i ****", j);
-				dump(all[j]);
-			}
-			panic("\n");
-		}
-
-		pr_info("fuzz complete: %i keys", b->sets[0].data->keys);
-	}
-}
-
-kobj_attribute_write(fuzz, btree_fuzz);
-#endif
-
 void bch_debug_exit(void)
 {
 	if (!IS_ERR_OR_NULL(debug))
@@ -554,11 +421,6 @@ void bch_debug_exit(void)
 int __init bch_debug_init(struct kobject *kobj)
 {
 	int ret = 0;
-#if 0
-	ret = sysfs_create_file(kobj, &ksysfs_fuzz.attr);
-	if (ret)
-		return ret;
-#endif
 
 	debug = debugfs_create_dir("bcache", NULL);
 	return ret;
diff --git a/drivers/md/bcache/debug.h b/drivers/md/bcache/debug.h
index f9378a218148..1c39b5a2489b 100644
--- a/drivers/md/bcache/debug.h
+++ b/drivers/md/bcache/debug.h
@@ -3,15 +3,8 @@
 
 /* Btree/bkey debug printing */
 
-#define KEYHACK_SIZE 80
-struct keyprint_hack {
-	char s[KEYHACK_SIZE];
-};
-
-struct keyprint_hack bch_pkey(const struct bkey *k);
-struct keyprint_hack bch_pbtree(const struct btree *b);
-#define pkey(k)		(&bch_pkey(k).s[0])
-#define pbtree(b)	(&bch_pbtree(b).s[0])
+int bch_bkey_to_text(char *buf, size_t size, const struct bkey *k);
+int bch_btree_to_text(char *buf, size_t size, const struct btree *b);
 
 #ifdef CONFIG_BCACHE_EDEBUG
 
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 48efd4dea645..9056632995b1 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -9,6 +9,8 @@
 #include "bset.h"
 #include "debug.h"
 
+#include <linux/blkdev.h>
+
 static void bch_bi_idx_hack_endio(struct bio *bio, int error)
 {
 	struct bio *p = bio->bi_private;
@@ -66,13 +68,6 @@ static void bch_generic_make_request_hack(struct bio *bio)
  * The newly allocated bio will point to @bio's bi_io_vec, if the split was on a
  * bvec boundry; it is the caller's responsibility to ensure that @bio is not
  * freed before the split.
- *
- * If bch_bio_split() is running under generic_make_request(), it's not safe to
- * allocate more than one bio from the same bio set. Therefore, if it is running
- * under generic_make_request() it masks out __GFP_WAIT when doing the
- * allocation. The caller must check for failure if there's any possibility of
- * it being called from under generic_make_request(); it is then the caller's
- * responsibility to retry from a safe context (by e.g. punting to workqueue).
  */
 struct bio *bch_bio_split(struct bio *bio, int sectors,
 			  gfp_t gfp, struct bio_set *bs)
@@ -83,20 +78,13 @@ struct bio *bch_bio_split(struct bio *bio, int sectors,
 
 	BUG_ON(sectors <= 0);
 
-	/*
-	 * If we're being called from underneath generic_make_request() and we
-	 * already allocated any bios from this bio set, we risk deadlock if we
-	 * use the mempool. So instead, we possibly fail and let the caller punt
-	 * to workqueue or somesuch and retry in a safe context.
-	 */
-	if (current->bio_list)
-		gfp &= ~__GFP_WAIT;
-
 	if (sectors >= bio_sectors(bio))
 		return bio;
 
 	if (bio->bi_rw & REQ_DISCARD) {
 		ret = bio_alloc_bioset(gfp, 1, bs);
+		if (!ret)
+			return NULL;
 		idx = 0;
 		goto out;
 	}
@@ -160,17 +148,18 @@ static unsigned bch_bio_max_sectors(struct bio *bio)
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	unsigned max_segments = min_t(unsigned, BIO_MAX_PAGES,
 				      queue_max_segments(q));
-	struct bio_vec *bv, *end = bio_iovec(bio) +
-		min_t(int, bio_segments(bio), max_segments);
 
 	if (bio->bi_rw & REQ_DISCARD)
 		return min(ret, q->limits.max_discard_sectors);
 
 	if (bio_segments(bio) > max_segments ||
 	    q->merge_bvec_fn) {
+		struct bio_vec *bv;
+		int i, seg = 0;
+
 		ret = 0;
 
-		for (bv = bio_iovec(bio); bv < end; bv++) {
+		bio_for_each_segment(bv, bio, i) {
 			struct bvec_merge_data bvm = {
 				.bi_bdev	= bio->bi_bdev,
 				.bi_sector	= bio->bi_sector,
@@ -178,10 +167,14 @@ static unsigned bch_bio_max_sectors(struct bio *bio)
 				.bi_rw		= bio->bi_rw,
 			};
 
+			if (seg == max_segments)
+				break;
+
 			if (q->merge_bvec_fn &&
 			    q->merge_bvec_fn(q, &bvm, bv) < (int) bv->bv_len)
 				break;
 
+			seg++;
 			ret += bv->bv_len >> 9;
 		}
 	}
@@ -218,30 +211,10 @@ static void bch_bio_submit_split_endio(struct bio *bio, int error)
 	closure_put(cl);
 }
 
-static void __bch_bio_submit_split(struct closure *cl)
-{
-	struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
-	struct bio *bio = s->bio, *n;
-
-	do {
-		n = bch_bio_split(bio, bch_bio_max_sectors(bio),
-				  GFP_NOIO, s->p->bio_split);
-		if (!n)
-			continue_at(cl, __bch_bio_submit_split, system_wq);
-
-		n->bi_end_io	= bch_bio_submit_split_endio;
-		n->bi_private	= cl;
-
-		closure_get(cl);
-		bch_generic_make_request_hack(n);
-	} while (n != bio);
-
-	continue_at(cl, bch_bio_submit_split_done, NULL);
-}
-
 void bch_generic_make_request(struct bio *bio, struct bio_split_pool *p)
 {
 	struct bio_split_hook *s;
+	struct bio *n;
 
 	if (!bio_has_data(bio) && !(bio->bi_rw & REQ_DISCARD))
 		goto submit;
@@ -250,6 +223,7 @@ void bch_generic_make_request(struct bio *bio, struct bio_split_pool *p)
 		goto submit;
 
 	s = mempool_alloc(p->bio_split_hook, GFP_NOIO);
+	closure_init(&s->cl, NULL);
 
 	s->bio		= bio;
 	s->p		= p;
@@ -257,8 +231,18 @@ void bch_generic_make_request(struct bio *bio, struct bio_split_pool *p)
 	s->bi_private	= bio->bi_private;
 	bio_get(bio);
 
-	closure_call(&s->cl, __bch_bio_submit_split, NULL, NULL);
-	return;
+	do {
+		n = bch_bio_split(bio, bch_bio_max_sectors(bio),
+				  GFP_NOIO, s->p->bio_split);
+
+		n->bi_end_io	= bch_bio_submit_split_endio;
+		n->bi_private	= &s->cl;
+
+		closure_get(&s->cl);
+		bch_generic_make_request_hack(n);
+	} while (n != bio);
+
+	continue_at(&s->cl, bch_bio_submit_split_done, NULL);
 submit:
 	bch_generic_make_request_hack(bio);
 }
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 8c8dfdcd9d4c..ba95ab84b2be 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -9,6 +9,8 @@
 #include "debug.h"
 #include "request.h"
 
+#include <trace/events/bcache.h>
+
 /*
  * Journal replay/recovery:
  *
@@ -182,9 +184,14 @@ bsearch:
 		pr_debug("starting binary search, l %u r %u", l, r);
 
 		while (l + 1 < r) {
+			seq = list_entry(list->prev, struct journal_replay,
+					 list)->j.seq;
+
 			m = (l + r) >> 1;
+			read_bucket(m);
 
-			if (read_bucket(m))
+			if (seq != list_entry(list->prev, struct journal_replay,
+					      list)->j.seq)
 				l = m;
 			else
 				r = m;
@@ -300,7 +307,8 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list,
 		for (k = i->j.start;
 		     k < end(&i->j);
 		     k = bkey_next(k)) {
-			pr_debug("%s", pkey(k));
+			trace_bcache_journal_replay_key(k);
+
 			bkey_copy(op->keys.top, k);
 			bch_keylist_push(&op->keys);
 
@@ -384,7 +392,7 @@ out:
 		return;
 found:
 	if (btree_node_dirty(best))
-		bch_btree_write(best, true, NULL);
+		bch_btree_node_write(best, NULL);
 	rw_unlock(true, best);
 }
 
@@ -617,7 +625,7 @@ static void journal_write_unlocked(struct closure *cl)
 		bio_reset(bio);
 		bio->bi_sector	= PTR_OFFSET(k, i);
 		bio->bi_bdev	= ca->bdev;
-		bio->bi_rw	= REQ_WRITE|REQ_SYNC|REQ_META|REQ_FLUSH;
+		bio->bi_rw	= REQ_WRITE|REQ_SYNC|REQ_META|REQ_FLUSH|REQ_FUA;
 		bio->bi_size	= sectors << 9;
 
 		bio->bi_end_io	= journal_write_endio;
@@ -712,7 +720,8 @@ void bch_journal(struct closure *cl)
 	spin_lock(&c->journal.lock);
 
 	if (journal_full(&c->journal)) {
-		/* XXX: tracepoint */
+		trace_bcache_journal_full(c);
+
 		closure_wait(&c->journal.wait, cl);
 
 		journal_reclaim(c);
@@ -728,13 +737,15 @@ void bch_journal(struct closure *cl)
 
 	if (b * c->sb.block_size > PAGE_SECTORS << JSET_BITS ||
 	    b > c->journal.blocks_free) {
-		/* XXX: If we were inserting so many keys that they won't fit in
+		trace_bcache_journal_entry_full(c);
+
+		/*
+		 * XXX: If we were inserting so many keys that they won't fit in
 		 * an _empty_ journal write, we'll deadlock. For now, handle
 		 * this in bch_keylist_realloc() - but something to think about.
 		 */
 		BUG_ON(!w->data->keys);
 
-		/* XXX: tracepoint */
 		BUG_ON(!closure_wait(&w->wait, cl));
 
 		closure_flush(&c->journal.io);
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 8589512c972e..1a3b4f4786c3 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -9,6 +9,8 @@
 #include "debug.h"
 #include "request.h"
 
+#include <trace/events/bcache.h>
+
 struct moving_io {
 	struct keybuf_key	*w;
 	struct search		s;
@@ -44,14 +46,14 @@ static void write_moving_finish(struct closure *cl)
 {
 	struct moving_io *io = container_of(cl, struct moving_io, s.cl);
 	struct bio *bio = &io->bio.bio;
-	struct bio_vec *bv = bio_iovec_idx(bio, bio->bi_vcnt);
+	struct bio_vec *bv;
+	int i;
 
-	while (bv-- != bio->bi_io_vec)
+	bio_for_each_segment_all(bv, bio, i)
 		__free_page(bv->bv_page);
 
-	pr_debug("%s %s", io->s.op.insert_collision
-		 ? "collision moving" : "moved",
-		 pkey(&io->w->key));
+	if (io->s.op.insert_collision)
+		trace_bcache_gc_copy_collision(&io->w->key);
 
 	bch_keybuf_del(&io->s.op.c->moving_gc_keys, io->w);
 
@@ -94,8 +96,6 @@ static void write_moving(struct closure *cl)
 	struct moving_io *io = container_of(s, struct moving_io, s);
 
 	if (!s->error) {
-		trace_bcache_write_moving(&io->bio.bio);
-
 		moving_init(io);
 
 		io->bio.bio.bi_sector	= KEY_START(&io->w->key);
@@ -122,7 +122,6 @@ static void read_moving_submit(struct closure *cl)
 	struct moving_io *io = container_of(s, struct moving_io, s);
 	struct bio *bio = &io->bio.bio;
 
-	trace_bcache_read_moving(bio);
 	bch_submit_bbio(bio, s->op.c, &io->w->key, 0);
 
 	continue_at(cl, write_moving, bch_gc_wq);
@@ -138,7 +137,8 @@ static void read_moving(struct closure *cl)
 	/* XXX: if we error, background writeback could stall indefinitely */
 
 	while (!test_bit(CACHE_SET_STOPPING, &c->flags)) {
-		w = bch_keybuf_next_rescan(c, &c->moving_gc_keys, &MAX_KEY);
+		w = bch_keybuf_next_rescan(c, &c->moving_gc_keys,
+					   &MAX_KEY, moving_pred);
 		if (!w)
 			break;
 
@@ -159,10 +159,10 @@ static void read_moving(struct closure *cl)
 		bio->bi_rw	= READ;
 		bio->bi_end_io	= read_moving_endio;
 
-		if (bch_bio_alloc_pages(bio, GFP_KERNEL))
+		if (bio_alloc_pages(bio, GFP_KERNEL))
 			goto err;
 
-		pr_debug("%s", pkey(&w->key));
+		trace_bcache_gc_copy(&w->key);
 
 		closure_call(&io->s.cl, read_moving_submit, NULL, &c->gc.cl);
 
@@ -250,5 +250,5 @@ void bch_moving_gc(struct closure *cl)
 
 void bch_moving_init_cache_set(struct cache_set *c)
 {
-	bch_keybuf_init(&c->moving_gc_keys, moving_pred);
+	bch_keybuf_init(&c->moving_gc_keys);
 }
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index e5ff12e52d5b..786a1a4f74d8 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -10,6 +10,7 @@
 #include "btree.h"
 #include "debug.h"
 #include "request.h"
+#include "writeback.h"
 
 #include <linux/cgroup.h>
 #include <linux/module.h>
@@ -21,8 +22,6 @@
 
 #define CUTOFF_CACHE_ADD	95
 #define CUTOFF_CACHE_READA	90
-#define CUTOFF_WRITEBACK	50
-#define CUTOFF_WRITEBACK_SYNC	75
 
 struct kmem_cache *bch_search_cache;
 
@@ -489,6 +488,12 @@ static void bch_insert_data_loop(struct closure *cl)
 		bch_queue_gc(op->c);
 	}
 
+	/*
+	 * Journal writes are marked REQ_FLUSH; if the original write was a
+	 * flush, it'll wait on the journal write.
+	 */
+	bio->bi_rw &= ~(REQ_FLUSH|REQ_FUA);
+
 	do {
 		unsigned i;
 		struct bkey *k;
@@ -510,10 +515,6 @@ static void bch_insert_data_loop(struct closure *cl)
 			goto err;
 
 		n = bch_bio_split(bio, KEY_SIZE(k), GFP_NOIO, split);
-		if (!n) {
-			__bkey_put(op->c, k);
-			continue_at(cl, bch_insert_data_loop, bcache_wq);
-		}
 
 		n->bi_end_io	= bch_insert_data_endio;
 		n->bi_private	= cl;
@@ -530,10 +531,9 @@ static void bch_insert_data_loop(struct closure *cl)
 		if (KEY_CSUM(k))
 			bio_csum(n, k);
 
-		pr_debug("%s", pkey(k));
+		trace_bcache_cache_insert(k);
 		bch_keylist_push(&op->keys);
 
-		trace_bcache_cache_insert(n, n->bi_sector, n->bi_bdev);
 		n->bi_rw |= REQ_WRITE;
 		bch_submit_bbio(n, op->c, k, 0);
 	} while (n != bio);
@@ -716,7 +716,7 @@ static struct search *search_alloc(struct bio *bio, struct bcache_device *d)
 	s->task			= current;
 	s->orig_bio		= bio;
 	s->write		= (bio->bi_rw & REQ_WRITE) != 0;
-	s->op.flush_journal	= (bio->bi_rw & REQ_FLUSH) != 0;
+	s->op.flush_journal	= (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0;
 	s->op.skip		= (bio->bi_rw & REQ_DISCARD) != 0;
 	s->recoverable		= 1;
 	s->start_time		= jiffies;
@@ -784,11 +784,8 @@ static void request_read_error(struct closure *cl)
 	int i;
 
 	if (s->recoverable) {
-		/* The cache read failed, but we can retry from the backing
-		 * device.
-		 */
-		pr_debug("recovering at sector %llu",
-			 (uint64_t) s->orig_bio->bi_sector);
+		/* Retry from the backing device: */
+		trace_bcache_read_retry(s->orig_bio);
 
 		s->error = 0;
 		bv = s->bio.bio.bi_io_vec;
@@ -806,7 +803,6 @@ static void request_read_error(struct closure *cl)
 
 		/* XXX: invalidate cache */
 
-		trace_bcache_read_retry(&s->bio.bio);
 		closure_bio_submit(&s->bio.bio, &s->cl, s->d);
 	}
 
@@ -827,53 +823,13 @@ static void request_read_done(struct closure *cl)
 	 */
 
 	if (s->op.cache_bio) {
-		struct bio_vec *src, *dst;
-		unsigned src_offset, dst_offset, bytes;
-		void *dst_ptr;
-
 		bio_reset(s->op.cache_bio);
 		s->op.cache_bio->bi_sector	= s->cache_miss->bi_sector;
 		s->op.cache_bio->bi_bdev	= s->cache_miss->bi_bdev;
 		s->op.cache_bio->bi_size	= s->cache_bio_sectors << 9;
 		bch_bio_map(s->op.cache_bio, NULL);
 
-		src = bio_iovec(s->op.cache_bio);
-		dst = bio_iovec(s->cache_miss);
-		src_offset = src->bv_offset;
-		dst_offset = dst->bv_offset;
-		dst_ptr = kmap(dst->bv_page);
-
-		while (1) {
-			if (dst_offset == dst->bv_offset + dst->bv_len) {
-				kunmap(dst->bv_page);
-				dst++;
-				if (dst == bio_iovec_idx(s->cache_miss,
-						s->cache_miss->bi_vcnt))
-					break;
-
-				dst_offset = dst->bv_offset;
-				dst_ptr = kmap(dst->bv_page);
-			}
-
-			if (src_offset == src->bv_offset + src->bv_len) {
-				src++;
-				if (src == bio_iovec_idx(s->op.cache_bio,
-						 s->op.cache_bio->bi_vcnt))
-					BUG();
-
-				src_offset = src->bv_offset;
-			}
-
-			bytes = min(dst->bv_offset + dst->bv_len - dst_offset,
-				    src->bv_offset + src->bv_len - src_offset);
-
-			memcpy(dst_ptr + dst_offset,
-			       page_address(src->bv_page) + src_offset,
-			       bytes);
-
-			src_offset	+= bytes;
-			dst_offset	+= bytes;
-		}
+		bio_copy_data(s->cache_miss, s->op.cache_bio);
 
 		bio_put(s->cache_miss);
 		s->cache_miss = NULL;
@@ -899,6 +855,7 @@ static void request_read_done_bh(struct closure *cl)
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	bch_mark_cache_accounting(s, !s->cache_miss, s->op.skip);
+	trace_bcache_read(s->orig_bio, !s->cache_miss, s->op.skip);
 
 	if (s->error)
 		continue_at_nobarrier(cl, request_read_error, bcache_wq);
@@ -917,9 +874,6 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	struct bio *miss;
 
 	miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
-	if (!miss)
-		return -EAGAIN;
-
 	if (miss == bio)
 		s->op.lookup_done = true;
 
@@ -938,8 +892,9 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 		reada = min(dc->readahead >> 9,
 			    sectors - bio_sectors(miss));
 
-		if (bio_end(miss) + reada > bdev_sectors(miss->bi_bdev))
-			reada = bdev_sectors(miss->bi_bdev) - bio_end(miss);
+		if (bio_end_sector(miss) + reada > bdev_sectors(miss->bi_bdev))
+			reada = bdev_sectors(miss->bi_bdev) -
+				bio_end_sector(miss);
 	}
 
 	s->cache_bio_sectors = bio_sectors(miss) + reada;
@@ -963,13 +918,12 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 		goto out_put;
 
 	bch_bio_map(s->op.cache_bio, NULL);
-	if (bch_bio_alloc_pages(s->op.cache_bio, __GFP_NOWARN|GFP_NOIO))
+	if (bio_alloc_pages(s->op.cache_bio, __GFP_NOWARN|GFP_NOIO))
 		goto out_put;
 
 	s->cache_miss = miss;
 	bio_get(s->op.cache_bio);
 
-	trace_bcache_cache_miss(s->orig_bio);
 	closure_bio_submit(s->op.cache_bio, &s->cl, s->d);
 
 	return ret;
@@ -1002,24 +956,13 @@ static void cached_dev_write_complete(struct closure *cl)
 	cached_dev_bio_complete(cl);
 }
 
-static bool should_writeback(struct cached_dev *dc, struct bio *bio)
-{
-	unsigned threshold = (bio->bi_rw & REQ_SYNC)
-		? CUTOFF_WRITEBACK_SYNC
-		: CUTOFF_WRITEBACK;
-
-	return !atomic_read(&dc->disk.detaching) &&
-		cache_mode(dc, bio) == CACHE_MODE_WRITEBACK &&
-		dc->disk.c->gc_stats.in_use < threshold;
-}
-
 static void request_write(struct cached_dev *dc, struct search *s)
 {
 	struct closure *cl = &s->cl;
 	struct bio *bio = &s->bio.bio;
 	struct bkey start, end;
 	start = KEY(dc->disk.id, bio->bi_sector, 0);
-	end = KEY(dc->disk.id, bio_end(bio), 0);
+	end = KEY(dc->disk.id, bio_end_sector(bio), 0);
 
 	bch_keybuf_check_overlapping(&s->op.c->moving_gc_keys, &start, &end);
 
@@ -1034,22 +977,37 @@ static void request_write(struct cached_dev *dc, struct search *s)
 	if (bio->bi_rw & REQ_DISCARD)
 		goto skip;
 
+	if (should_writeback(dc, s->orig_bio,
+			     cache_mode(dc, bio),
+			     s->op.skip)) {
+		s->op.skip = false;
+		s->writeback = true;
+	}
+
 	if (s->op.skip)
 		goto skip;
 
-	if (should_writeback(dc, s->orig_bio))
-		s->writeback = true;
+	trace_bcache_write(s->orig_bio, s->writeback, s->op.skip);
 
 	if (!s->writeback) {
 		s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO,
 						   dc->disk.bio_split);
 
-		trace_bcache_writethrough(s->orig_bio);
 		closure_bio_submit(bio, cl, s->d);
 	} else {
-		s->op.cache_bio = bio;
-		trace_bcache_writeback(s->orig_bio);
-		bch_writeback_add(dc, bio_sectors(bio));
+		bch_writeback_add(dc);
+
+		if (s->op.flush_journal) {
+			/* Also need to send a flush to the backing device */
+			s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO,
+							   dc->disk.bio_split);
+
+			bio->bi_size = 0;
+			bio->bi_vcnt = 0;
+			closure_bio_submit(bio, cl, s->d);
+		} else {
+			s->op.cache_bio = bio;
+		}
 	}
 out:
 	closure_call(&s->op.cl, bch_insert_data, NULL, cl);
@@ -1058,7 +1016,6 @@ skip:
 	s->op.skip = true;
 	s->op.cache_bio = s->orig_bio;
 	bio_get(s->op.cache_bio);
-	trace_bcache_write_skip(s->orig_bio);
 
 	if ((bio->bi_rw & REQ_DISCARD) &&
 	    !blk_queue_discard(bdev_get_queue(dc->bdev)))
@@ -1088,9 +1045,10 @@ static void request_nodata(struct cached_dev *dc, struct search *s)
 
 /* Cached devices - read & write stuff */
 
-int bch_get_congested(struct cache_set *c)
+unsigned bch_get_congested(struct cache_set *c)
 {
 	int i;
+	long rand;
 
 	if (!c->congested_read_threshold_us &&
 	    !c->congested_write_threshold_us)
@@ -1106,7 +1064,13 @@ int bch_get_congested(struct cache_set *c)
 
 	i += CONGESTED_MAX;
 
-	return i <= 0 ? 1 : fract_exp_two(i, 6);
+	if (i > 0)
+		i = fract_exp_two(i, 6);
+
+	rand = get_random_int();
+	i -= bitmap_weight(&rand, BITS_PER_LONG);
+
+	return i > 0 ? i : 1;
 }
 
 static void add_sequential(struct task_struct *t)
@@ -1126,10 +1090,8 @@ static void check_should_skip(struct cached_dev *dc, struct search *s)
 {
 	struct cache_set *c = s->op.c;
 	struct bio *bio = &s->bio.bio;
-
-	long rand;
-	int cutoff = bch_get_congested(c);
 	unsigned mode = cache_mode(dc, bio);
+	unsigned sectors, congested = bch_get_congested(c);
 
 	if (atomic_read(&dc->disk.detaching) ||
 	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
@@ -1147,17 +1109,14 @@ static void check_should_skip(struct cached_dev *dc, struct search *s)
 		goto skip;
 	}
 
-	if (!cutoff) {
-		cutoff = dc->sequential_cutoff >> 9;
+	if (!congested && !dc->sequential_cutoff)
+		goto rescale;
 
-		if (!cutoff)
-			goto rescale;
-
-		if (mode == CACHE_MODE_WRITEBACK &&
-		    (bio->bi_rw & REQ_WRITE) &&
-		    (bio->bi_rw & REQ_SYNC))
-			goto rescale;
-	}
+	if (!congested &&
+	    mode == CACHE_MODE_WRITEBACK &&
+	    (bio->bi_rw & REQ_WRITE) &&
+	    (bio->bi_rw & REQ_SYNC))
+		goto rescale;
 
 	if (dc->sequential_merge) {
 		struct io *i;
@@ -1177,7 +1136,7 @@ found:
 		if (i->sequential + bio->bi_size > i->sequential)
 			i->sequential	+= bio->bi_size;
 
-		i->last			 = bio_end(bio);
+		i->last			 = bio_end_sector(bio);
 		i->jiffies		 = jiffies + msecs_to_jiffies(5000);
 		s->task->sequential_io	 = i->sequential;
 
@@ -1192,12 +1151,19 @@ found:
 		add_sequential(s->task);
 	}
 
-	rand = get_random_int();
-	cutoff -= bitmap_weight(&rand, BITS_PER_LONG);
+	sectors = max(s->task->sequential_io,
+		      s->task->sequential_io_avg) >> 9;
 
-	if (cutoff <= (int) (max(s->task->sequential_io,
-				 s->task->sequential_io_avg) >> 9))
+	if (dc->sequential_cutoff &&
+	    sectors >= dc->sequential_cutoff >> 9) {
+		trace_bcache_bypass_sequential(s->orig_bio);
 		goto skip;
+	}
+
+	if (congested && sectors >= congested) {
+		trace_bcache_bypass_congested(s->orig_bio);
+		goto skip;
+	}
 
 rescale:
 	bch_rescale_priorities(c, bio_sectors(bio));
@@ -1288,30 +1254,25 @@ void bch_cached_dev_request_init(struct cached_dev *dc)
 static int flash_dev_cache_miss(struct btree *b, struct search *s,
 				struct bio *bio, unsigned sectors)
 {
+	struct bio_vec *bv;
+	int i;
+
 	/* Zero fill bio */
 
-	while (bio->bi_idx != bio->bi_vcnt) {
-		struct bio_vec *bv = bio_iovec(bio);
+	bio_for_each_segment(bv, bio, i) {
 		unsigned j = min(bv->bv_len >> 9, sectors);
 
 		void *p = kmap(bv->bv_page);
 		memset(p + bv->bv_offset, 0, j << 9);
 		kunmap(bv->bv_page);
 
-		bv->bv_len	-= j << 9;
-		bv->bv_offset	+= j << 9;
-
-		if (bv->bv_len)
-			return 0;
-
-		bio->bi_sector	+= j;
-		bio->bi_size	-= j << 9;
-
-		bio->bi_idx++;
-		sectors		-= j;
+		sectors	-= j;
 	}
 
-	s->op.lookup_done = true;
+	bio_advance(bio, min(sectors << 9, bio->bi_size));
+
+	if (!bio->bi_size)
+		s->op.lookup_done = true;
 
 	return 0;
 }
@@ -1338,8 +1299,8 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
 		closure_call(&s->op.cl, btree_read_async, NULL, cl);
 	} else if (bio_has_data(bio) || s->op.skip) {
 		bch_keybuf_check_overlapping(&s->op.c->moving_gc_keys,
-					     &KEY(d->id, bio->bi_sector, 0),
-					     &KEY(d->id, bio_end(bio), 0));
+					&KEY(d->id, bio->bi_sector, 0),
+					&KEY(d->id, bio_end_sector(bio), 0));
 
 		s->writeback	= true;
 		s->op.cache_bio	= bio;
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 254d9ab5707c..57dc4784f4f4 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -30,7 +30,7 @@ struct search {
 };
 
 void bch_cache_read_endio(struct bio *, int);
-int bch_get_congested(struct cache_set *);
+unsigned bch_get_congested(struct cache_set *);
 void bch_insert_data(struct closure *cl);
 void bch_btree_insert_async(struct closure *);
 void bch_cache_read_endio(struct bio *, int);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index f88e2b653a3f..547c4c57b052 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -10,10 +10,13 @@
 #include "btree.h"
 #include "debug.h"
 #include "request.h"
+#include "writeback.h"
 
+#include <linux/blkdev.h>
 #include <linux/buffer_head.h>
 #include <linux/debugfs.h>
 #include <linux/genhd.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/reboot.h>
@@ -342,6 +345,7 @@ static void uuid_io(struct cache_set *c, unsigned long rw,
 	struct closure *cl = &c->uuid_write.cl;
 	struct uuid_entry *u;
 	unsigned i;
+	char buf[80];
 
 	BUG_ON(!parent);
 	closure_lock(&c->uuid_write, parent);
@@ -362,8 +366,8 @@ static void uuid_io(struct cache_set *c, unsigned long rw,
 			break;
 	}
 
-	pr_debug("%s UUIDs at %s", rw & REQ_WRITE ? "wrote" : "read",
-		 pkey(&c->uuid_bucket));
+	bch_bkey_to_text(buf, sizeof(buf), k);
+	pr_debug("%s UUIDs at %s", rw & REQ_WRITE ? "wrote" : "read", buf);
 
 	for (u = c->uuids; u < c->uuids + c->nr_uuids; u++)
 		if (!bch_is_zero(u->uuid, 16))
@@ -543,7 +547,6 @@ void bch_prio_write(struct cache *ca)
 
 	pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
 		 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
-	blktrace_msg(ca, "Starting priorities: " buckets_free(ca));
 
 	for (i = prio_buckets(ca) - 1; i >= 0; --i) {
 		long bucket;
@@ -704,7 +707,8 @@ static void bcache_device_detach(struct bcache_device *d)
 		atomic_set(&d->detaching, 0);
 	}
 
-	bcache_device_unlink(d);
+	if (!d->flush_done)
+		bcache_device_unlink(d);
 
 	d->c->devices[d->id] = NULL;
 	closure_put(&d->c->caching);
@@ -743,13 +747,35 @@ static void bcache_device_free(struct bcache_device *d)
 		mempool_destroy(d->unaligned_bvec);
 	if (d->bio_split)
 		bioset_free(d->bio_split);
+	if (is_vmalloc_addr(d->stripe_sectors_dirty))
+		vfree(d->stripe_sectors_dirty);
+	else
+		kfree(d->stripe_sectors_dirty);
 
 	closure_debug_destroy(&d->cl);
 }
 
-static int bcache_device_init(struct bcache_device *d, unsigned block_size)
+static int bcache_device_init(struct bcache_device *d, unsigned block_size,
+			      sector_t sectors)
 {
 	struct request_queue *q;
+	size_t n;
+
+	if (!d->stripe_size_bits)
+		d->stripe_size_bits = 31;
+
+	d->nr_stripes = round_up(sectors, 1 << d->stripe_size_bits) >>
+		d->stripe_size_bits;
+
+	if (!d->nr_stripes || d->nr_stripes > SIZE_MAX / sizeof(atomic_t))
+		return -ENOMEM;
+
+	n = d->nr_stripes * sizeof(atomic_t);
+	d->stripe_sectors_dirty = n < PAGE_SIZE << 6
+		? kzalloc(n, GFP_KERNEL)
+		: vzalloc(n);
+	if (!d->stripe_sectors_dirty)
+		return -ENOMEM;
 
 	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
 	    !(d->unaligned_bvec = mempool_create_kmalloc_pool(1,
@@ -759,6 +785,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size)
 	    !(q = blk_alloc_queue(GFP_KERNEL)))
 		return -ENOMEM;
 
+	set_capacity(d->disk, sectors);
 	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", bcache_minor);
 
 	d->disk->major		= bcache_major;
@@ -781,6 +808,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size)
 	set_bit(QUEUE_FLAG_NONROT,	&d->disk->queue->queue_flags);
 	set_bit(QUEUE_FLAG_DISCARD,	&d->disk->queue->queue_flags);
 
+	blk_queue_flush(q, REQ_FLUSH|REQ_FUA);
+
 	return 0;
 }
 
@@ -800,6 +829,17 @@ static void calc_cached_dev_sectors(struct cache_set *c)
 void bch_cached_dev_run(struct cached_dev *dc)
 {
 	struct bcache_device *d = &dc->disk;
+	char buf[SB_LABEL_SIZE + 1];
+	char *env[] = {
+		"DRIVER=bcache",
+		kasprintf(GFP_KERNEL, "CACHED_UUID=%pU", dc->sb.uuid),
+		NULL,
+		NULL,
+	};
+
+	memcpy(buf, dc->sb.label, SB_LABEL_SIZE);
+	buf[SB_LABEL_SIZE] = '\0';
+	env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf);
 
 	if (atomic_xchg(&dc->running, 1))
 		return;
@@ -816,10 +856,12 @@ void bch_cached_dev_run(struct cached_dev *dc)
 
 	add_disk(d->disk);
 	bd_link_disk_holder(dc->bdev, dc->disk.disk);
-#if 0
-	char *env[] = { "SYMLINK=label" , NULL };
+	/* won't show up in the uevent file, use udevadm monitor -e instead
+	 * only class / kset properties are persistent */
 	kobject_uevent_env(&disk_to_dev(d->disk)->kobj, KOBJ_CHANGE, env);
-#endif
+	kfree(env[1]);
+	kfree(env[2]);
+
 	if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
 	    sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
 		pr_debug("error creating sysfs link");
@@ -960,6 +1002,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	atomic_set(&dc->count, 1);
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
+		bch_sectors_dirty_init(dc);
 		atomic_set(&dc->has_dirty, 1);
 		atomic_inc(&dc->count);
 		bch_writeback_queue(dc);
@@ -1014,6 +1057,14 @@ static void cached_dev_flush(struct closure *cl)
 	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
 	struct bcache_device *d = &dc->disk;
 
+	mutex_lock(&bch_register_lock);
+	d->flush_done = 1;
+
+	if (d->c)
+		bcache_device_unlink(d);
+
+	mutex_unlock(&bch_register_lock);
+
 	bch_cache_accounting_destroy(&dc->accounting);
 	kobject_del(&d->kobj);
 
@@ -1045,7 +1096,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
 		hlist_add_head(&io->hash, dc->io_hash + RECENT_IO);
 	}
 
-	ret = bcache_device_init(&dc->disk, block_size);
+	ret = bcache_device_init(&dc->disk, block_size,
+			 dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
 	if (ret)
 		return ret;
 
@@ -1144,11 +1196,10 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 
 	kobject_init(&d->kobj, &bch_flash_dev_ktype);
 
-	if (bcache_device_init(d, block_bytes(c)))
+	if (bcache_device_init(d, block_bytes(c), u->sectors))
 		goto err;
 
 	bcache_device_attach(d, c, u - c->uuids);
-	set_capacity(d->disk, u->sectors);
 	bch_flash_dev_request_init(d);
 	add_disk(d->disk);
 
@@ -1255,9 +1306,10 @@ static void cache_set_free(struct closure *cl)
 	free_pages((unsigned long) c->uuids, ilog2(bucket_pages(c)));
 	free_pages((unsigned long) c->sort, ilog2(bucket_pages(c)));
 
-	kfree(c->fill_iter);
 	if (c->bio_split)
 		bioset_free(c->bio_split);
+	if (c->fill_iter)
+		mempool_destroy(c->fill_iter);
 	if (c->bio_meta)
 		mempool_destroy(c->bio_meta);
 	if (c->search)
@@ -1278,11 +1330,9 @@ static void cache_set_free(struct closure *cl)
 static void cache_set_flush(struct closure *cl)
 {
 	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	struct cache *ca;
 	struct btree *b;
-
-	/* Shut down allocator threads */
-	set_bit(CACHE_SET_STOPPING_2, &c->flags);
-	wake_up(&c->alloc_wait);
+	unsigned i;
 
 	bch_cache_accounting_destroy(&c->accounting);
 
@@ -1295,7 +1345,11 @@ static void cache_set_flush(struct closure *cl)
 	/* Should skip this if we're unregistering because of an error */
 	list_for_each_entry(b, &c->btree_cache, list)
 		if (btree_node_dirty(b))
-			bch_btree_write(b, true, NULL);
+			bch_btree_node_write(b, NULL);
+
+	for_each_cache(ca, c, i)
+		if (ca->alloc_thread)
+			kthread_stop(ca->alloc_thread);
 
 	closure_return(cl);
 }
@@ -1303,18 +1357,22 @@ static void cache_set_flush(struct closure *cl)
 static void __cache_set_unregister(struct closure *cl)
 {
 	struct cache_set *c = container_of(cl, struct cache_set, caching);
-	struct cached_dev *dc, *t;
+	struct cached_dev *dc;
 	size_t i;
 
 	mutex_lock(&bch_register_lock);
 
-	if (test_bit(CACHE_SET_UNREGISTERING, &c->flags))
-		list_for_each_entry_safe(dc, t, &c->cached_devs, list)
-			bch_cached_dev_detach(dc);
-
 	for (i = 0; i < c->nr_uuids; i++)
-		if (c->devices[i] && UUID_FLASH_ONLY(&c->uuids[i]))
-			bcache_device_stop(c->devices[i]);
+		if (c->devices[i]) {
+			if (!UUID_FLASH_ONLY(&c->uuids[i]) &&
+			    test_bit(CACHE_SET_UNREGISTERING, &c->flags)) {
+				dc = container_of(c->devices[i],
+						  struct cached_dev, disk);
+				bch_cached_dev_detach(dc);
+			} else {
+				bcache_device_stop(c->devices[i]);
+			}
+		}
 
 	mutex_unlock(&bch_register_lock);
 
@@ -1373,9 +1431,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 		c->btree_pages = max_t(int, c->btree_pages / 4,
 				       BTREE_MAX_PAGES);
 
-	init_waitqueue_head(&c->alloc_wait);
+	c->sort_crit_factor = int_sqrt(c->btree_pages);
+
 	mutex_init(&c->bucket_lock);
-	mutex_init(&c->fill_lock);
 	mutex_init(&c->sort_lock);
 	spin_lock_init(&c->sort_time_lock);
 	closure_init_unlocked(&c->sb_write);
@@ -1401,8 +1459,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	    !(c->bio_meta = mempool_create_kmalloc_pool(2,
 				sizeof(struct bbio) + sizeof(struct bio_vec) *
 				bucket_pages(c))) ||
+	    !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
 	    !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
-	    !(c->fill_iter = kmalloc(iter_size, GFP_KERNEL)) ||
 	    !(c->sort = alloc_bucket_pages(GFP_KERNEL, c)) ||
 	    !(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
 	    bch_journal_alloc(c) ||
@@ -1410,8 +1468,6 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	    bch_open_buckets_alloc(c))
 		goto err;
 
-	c->fill_iter->size = sb->bucket_size / sb->block_size;
-
 	c->congested_read_threshold_us	= 2000;
 	c->congested_write_threshold_us	= 20000;
 	c->error_limit	= 8 << IO_ERROR_SHIFT;
@@ -1496,9 +1552,10 @@ static void run_cache_set(struct cache_set *c)
 		 */
 		bch_journal_next(&c->journal);
 
+		err = "error starting allocator thread";
 		for_each_cache(ca, c, i)
-			closure_call(&ca->alloc, bch_allocator_thread,
-				     system_wq, &c->cl);
+			if (bch_cache_allocator_start(ca))
+				goto err;
 
 		/*
 		 * First place it's safe to allocate: btree_check() and
@@ -1531,17 +1588,16 @@ static void run_cache_set(struct cache_set *c)
 
 		bch_btree_gc_finish(c);
 
+		err = "error starting allocator thread";
 		for_each_cache(ca, c, i)
-			closure_call(&ca->alloc, bch_allocator_thread,
-				     ca->alloc_workqueue, &c->cl);
+			if (bch_cache_allocator_start(ca))
+				goto err;
 
 		mutex_lock(&c->bucket_lock);
 		for_each_cache(ca, c, i)
 			bch_prio_write(ca);
 		mutex_unlock(&c->bucket_lock);
 
-		wake_up(&c->alloc_wait);
-
 		err = "cannot allocate new UUID bucket";
 		if (__uuid_write(c))
 			goto err_unlock_gc;
@@ -1552,7 +1608,7 @@ static void run_cache_set(struct cache_set *c)
 			goto err_unlock_gc;
 
 		bkey_copy_key(&c->root->key, &MAX_KEY);
-		bch_btree_write(c->root, true, &op);
+		bch_btree_node_write(c->root, &op.cl);
 
 		bch_btree_set_root(c->root);
 		rw_unlock(true, c->root);
@@ -1673,9 +1729,6 @@ void bch_cache_release(struct kobject *kobj)
 
 	bio_split_pool_free(&ca->bio_split_hook);
 
-	if (ca->alloc_workqueue)
-		destroy_workqueue(ca->alloc_workqueue);
-
 	free_pages((unsigned long) ca->disk_buckets, ilog2(bucket_pages(ca)));
 	kfree(ca->prio_buckets);
 	vfree(ca->buckets);
@@ -1723,7 +1776,6 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
 	    !(ca->prio_buckets	= kzalloc(sizeof(uint64_t) * prio_buckets(ca) *
 					  2, GFP_KERNEL)) ||
 	    !(ca->disk_buckets	= alloc_bucket_pages(GFP_KERNEL, ca)) ||
-	    !(ca->alloc_workqueue = alloc_workqueue("bch_allocator", 0, 1)) ||
 	    bio_split_pool_init(&ca->bio_split_hook))
 		return -ENOMEM;
 
@@ -1786,6 +1838,36 @@ static ssize_t register_bcache(struct kobject *, struct kobj_attribute *,
 kobj_attribute_write(register,		register_bcache);
 kobj_attribute_write(register_quiet,	register_bcache);
 
+static bool bch_is_open_backing(struct block_device *bdev) {
+	struct cache_set *c, *tc;
+	struct cached_dev *dc, *t;
+
+	list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
+		list_for_each_entry_safe(dc, t, &c->cached_devs, list)
+			if (dc->bdev == bdev)
+				return true;
+	list_for_each_entry_safe(dc, t, &uncached_devices, list)
+		if (dc->bdev == bdev)
+			return true;
+	return false;
+}
+
+static bool bch_is_open_cache(struct block_device *bdev) {
+	struct cache_set *c, *tc;
+	struct cache *ca;
+	unsigned i;
+
+	list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
+		for_each_cache(ca, c, i)
+			if (ca->bdev == bdev)
+				return true;
+	return false;
+}
+
+static bool bch_is_open(struct block_device *bdev) {
+	return bch_is_open_cache(bdev) || bch_is_open_backing(bdev);
+}
+
 static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			       const char *buffer, size_t size)
 {
@@ -1810,8 +1892,13 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 				  FMODE_READ|FMODE_WRITE|FMODE_EXCL,
 				  sb);
 	if (IS_ERR(bdev)) {
-		if (bdev == ERR_PTR(-EBUSY))
-			err = "device busy";
+		if (bdev == ERR_PTR(-EBUSY)) {
+			bdev = lookup_bdev(strim(path));
+			if (!IS_ERR(bdev) && bch_is_open(bdev))
+				err = "device already registered";
+			else
+				err = "device busy";
+		}
 		goto err;
 	}
 
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 4d9cca47e4c6..12a2c2846f99 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -9,7 +9,9 @@
 #include "sysfs.h"
 #include "btree.h"
 #include "request.h"
+#include "writeback.h"
 
+#include <linux/blkdev.h>
 #include <linux/sort.h>
 
 static const char * const cache_replacement_policies[] = {
@@ -79,6 +81,9 @@ rw_attribute(writeback_rate_p_term_inverse);
 rw_attribute(writeback_rate_d_smooth);
 read_attribute(writeback_rate_debug);
 
+read_attribute(stripe_size);
+read_attribute(partial_stripes_expensive);
+
 rw_attribute(synchronous);
 rw_attribute(journal_delay_ms);
 rw_attribute(discard);
@@ -127,7 +132,7 @@ SHOW(__bch_cached_dev)
 		char derivative[20];
 		char target[20];
 		bch_hprint(dirty,
-		       atomic_long_read(&dc->disk.sectors_dirty) << 9);
+			   bcache_dev_sectors_dirty(&dc->disk) << 9);
 		bch_hprint(derivative,	dc->writeback_rate_derivative << 9);
 		bch_hprint(target,	dc->writeback_rate_target << 9);
 
@@ -143,7 +148,10 @@ SHOW(__bch_cached_dev)
 	}
 
 	sysfs_hprint(dirty_data,
-		     atomic_long_read(&dc->disk.sectors_dirty) << 9);
+		     bcache_dev_sectors_dirty(&dc->disk) << 9);
+
+	sysfs_hprint(stripe_size,	(1 << dc->disk.stripe_size_bits) << 9);
+	var_printf(partial_stripes_expensive,	"%u");
 
 	var_printf(sequential_merge,	"%i");
 	var_hprint(sequential_cutoff);
@@ -170,6 +178,7 @@ STORE(__cached_dev)
 					     disk.kobj);
 	unsigned v = size;
 	struct cache_set *c;
+	struct kobj_uevent_env *env;
 
 #define d_strtoul(var)		sysfs_strtoul(var, dc->var)
 #define d_strtoi_h(var)		sysfs_hatoi(var, dc->var)
@@ -214,6 +223,7 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_label) {
+		/* note: endlines are preserved */
 		memcpy(dc->sb.label, buf, SB_LABEL_SIZE);
 		bch_write_bdev_super(dc, NULL);
 		if (dc->disk.c) {
@@ -221,6 +231,15 @@ STORE(__cached_dev)
 			       buf, SB_LABEL_SIZE);
 			bch_uuid_write(dc->disk.c);
 		}
+		env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL);
+		if (!env)
+			return -ENOMEM;
+		add_uevent_var(env, "DRIVER=bcache");
+		add_uevent_var(env, "CACHED_UUID=%pU", dc->sb.uuid),
+		add_uevent_var(env, "CACHED_LABEL=%s", buf);
+		kobject_uevent_env(
+			&disk_to_dev(dc->disk.disk)->kobj, KOBJ_CHANGE, env->envp);
+		kfree(env);
 	}
 
 	if (attr == &sysfs_attach) {
@@ -284,6 +303,8 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_writeback_rate_d_smooth,
 	&sysfs_writeback_rate_debug,
 	&sysfs_dirty_data,
+	&sysfs_stripe_size,
+	&sysfs_partial_stripes_expensive,
 	&sysfs_sequential_cutoff,
 	&sysfs_sequential_merge,
 	&sysfs_clear_stats,
@@ -665,12 +686,10 @@ SHOW(__bch_cache)
 		int cmp(const void *l, const void *r)
 		{	return *((uint16_t *) r) - *((uint16_t *) l); }
 
-		/* Number of quantiles we compute */
-		const unsigned nq = 31;
-
 		size_t n = ca->sb.nbuckets, i, unused, btree;
 		uint64_t sum = 0;
-		uint16_t q[nq], *p, *cached;
+		/* Compute 31 quantiles */
+		uint16_t q[31], *p, *cached;
 		ssize_t ret;
 
 		cached = p = vmalloc(ca->sb.nbuckets * sizeof(uint16_t));
@@ -703,26 +722,29 @@ SHOW(__bch_cache)
 		if (n)
 			do_div(sum, n);
 
-		for (i = 0; i < nq; i++)
-			q[i] = INITIAL_PRIO - cached[n * (i + 1) / (nq + 1)];
+		for (i = 0; i < ARRAY_SIZE(q); i++)
+			q[i] = INITIAL_PRIO - cached[n * (i + 1) /
+				(ARRAY_SIZE(q) + 1)];
 
 		vfree(p);
 
-		ret = snprintf(buf, PAGE_SIZE,
-			       "Unused:		%zu%%\n"
-			       "Metadata:	%zu%%\n"
-			       "Average:	%llu\n"
-			       "Sectors per Q:	%zu\n"
-			       "Quantiles:	[",
-			       unused * 100 / (size_t) ca->sb.nbuckets,
-			       btree * 100 / (size_t) ca->sb.nbuckets, sum,
-			       n * ca->sb.bucket_size / (nq + 1));
-
-		for (i = 0; i < nq && ret < (ssize_t) PAGE_SIZE; i++)
-			ret += snprintf(buf + ret, PAGE_SIZE - ret,
-					i < nq - 1 ? "%u " : "%u]\n", q[i]);
-
-		buf[PAGE_SIZE - 1] = '\0';
+		ret = scnprintf(buf, PAGE_SIZE,
+				"Unused:		%zu%%\n"
+				"Metadata:	%zu%%\n"
+				"Average:	%llu\n"
+				"Sectors per Q:	%zu\n"
+				"Quantiles:	[",
+				unused * 100 / (size_t) ca->sb.nbuckets,
+				btree * 100 / (size_t) ca->sb.nbuckets, sum,
+				n * ca->sb.bucket_size / (ARRAY_SIZE(q) + 1));
+
+		for (i = 0; i < ARRAY_SIZE(q); i++)
+			ret += scnprintf(buf + ret, PAGE_SIZE - ret,
+					 "%u ", q[i]);
+		ret--;
+
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "]\n");
+
 		return ret;
 	}
 
diff --git a/drivers/md/bcache/trace.c b/drivers/md/bcache/trace.c
index 983f9bb411bc..f7b6c197f90f 100644
--- a/drivers/md/bcache/trace.c
+++ b/drivers/md/bcache/trace.c
@@ -2,6 +2,7 @@
 #include "btree.h"
 #include "request.h"
 
+#include <linux/blktrace_api.h>
 #include <linux/module.h>
 
 #define CREATE_TRACE_POINTS
@@ -9,18 +10,44 @@
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_request_start);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_request_end);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_passthrough);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_cache_hit);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_cache_miss);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_bypass_sequential);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_bypass_congested);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_read);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_write);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_read_retry);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_writethrough);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_writeback);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_write_skip);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_cache_insert);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_journal_replay_key);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_journal_write);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_journal_full);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_journal_entry_full);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_cache_cannibalize);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_read);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_write);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_write_dirty);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_read_dirty);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_journal_write);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_cache_insert);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_node_alloc);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_node_alloc_fail);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_node_free);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_gc_coalesce);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_gc_start);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_gc_end);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_gc_copy);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_gc_copy_collision);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_insert_key);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_node_split);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_node_compact);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_btree_set_root);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_alloc_invalidate);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_alloc_fail);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_writeback);
+EXPORT_TRACEPOINT_SYMBOL_GPL(bcache_writeback_collision);
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index da3a99e85b1e..98eb81159a22 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -228,23 +228,6 @@ start:		bv->bv_len	= min_t(size_t, PAGE_SIZE - bv->bv_offset,
 	}
 }
 
-int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp)
-{
-	int i;
-	struct bio_vec *bv;
-
-	bio_for_each_segment(bv, bio, i) {
-		bv->bv_page = alloc_page(gfp);
-		if (!bv->bv_page) {
-			while (bv-- != bio->bi_io_vec + bio->bi_idx)
-				__free_page(bv->bv_page);
-			return -ENOMEM;
-		}
-	}
-
-	return 0;
-}
-
 /*
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group (Any
  * use permitted, subject to terms of PostgreSQL license; see.)
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 577393e38c3a..1ae2a73ad85f 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -15,8 +15,6 @@
 
 struct closure;
 
-#include <trace/events/bcache.h>
-
 #ifdef CONFIG_BCACHE_EDEBUG
 
 #define atomic_dec_bug(v)	BUG_ON(atomic_dec_return(v) < 0)
@@ -566,12 +564,8 @@ static inline unsigned fract_exp_two(unsigned x, unsigned fract_bits)
 	return x;
 }
 
-#define bio_end(bio)	((bio)->bi_sector + bio_sectors(bio))
-
 void bch_bio_map(struct bio *bio, void *base);
 
-int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp);
-
 static inline sector_t bdev_sectors(struct block_device *bdev)
 {
 	return bdev->bd_inode->i_size >> 9;
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 2714ed3991d1..22cbff551628 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -9,6 +9,9 @@
 #include "bcache.h"
 #include "btree.h"
 #include "debug.h"
+#include "writeback.h"
+
+#include <trace/events/bcache.h>
 
 static struct workqueue_struct *dirty_wq;
 
@@ -36,7 +39,7 @@ static void __update_writeback_rate(struct cached_dev *dc)
 
 	int change = 0;
 	int64_t error;
-	int64_t dirty = atomic_long_read(&dc->disk.sectors_dirty);
+	int64_t dirty = bcache_dev_sectors_dirty(&dc->disk);
 	int64_t derivative = dirty - dc->disk.sectors_dirty_last;
 
 	dc->disk.sectors_dirty_last = dirty;
@@ -105,6 +108,31 @@ static bool dirty_pred(struct keybuf *buf, struct bkey *k)
 	return KEY_DIRTY(k);
 }
 
+static bool dirty_full_stripe_pred(struct keybuf *buf, struct bkey *k)
+{
+	uint64_t stripe;
+	unsigned nr_sectors = KEY_SIZE(k);
+	struct cached_dev *dc = container_of(buf, struct cached_dev,
+					     writeback_keys);
+	unsigned stripe_size = 1 << dc->disk.stripe_size_bits;
+
+	if (!KEY_DIRTY(k))
+		return false;
+
+	stripe = KEY_START(k) >> dc->disk.stripe_size_bits;
+	while (1) {
+		if (atomic_read(dc->disk.stripe_sectors_dirty + stripe) !=
+		    stripe_size)
+			return false;
+
+		if (nr_sectors <= stripe_size)
+			return true;
+
+		nr_sectors -= stripe_size;
+		stripe++;
+	}
+}
+
 static void dirty_init(struct keybuf_key *w)
 {
 	struct dirty_io *io = w->private;
@@ -149,7 +177,22 @@ static void refill_dirty(struct closure *cl)
 		searched_from_start = true;
 	}
 
-	bch_refill_keybuf(dc->disk.c, buf, &end);
+	if (dc->partial_stripes_expensive) {
+		uint64_t i;
+
+		for (i = 0; i < dc->disk.nr_stripes; i++)
+			if (atomic_read(dc->disk.stripe_sectors_dirty + i) ==
+			    1 << dc->disk.stripe_size_bits)
+				goto full_stripes;
+
+		goto normal_refill;
+full_stripes:
+		bch_refill_keybuf(dc->disk.c, buf, &end,
+				  dirty_full_stripe_pred);
+	} else {
+normal_refill:
+		bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
+	}
 
 	if (bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start) {
 		/* Searched the entire btree  - delay awhile */
@@ -181,10 +224,8 @@ void bch_writeback_queue(struct cached_dev *dc)
 	}
 }
 
-void bch_writeback_add(struct cached_dev *dc, unsigned sectors)
+void bch_writeback_add(struct cached_dev *dc)
 {
-	atomic_long_add(sectors, &dc->disk.sectors_dirty);
-
 	if (!atomic_read(&dc->has_dirty) &&
 	    !atomic_xchg(&dc->has_dirty, 1)) {
 		atomic_inc(&dc->count);
@@ -203,6 +244,34 @@ void bch_writeback_add(struct cached_dev *dc, unsigned sectors)
 	}
 }
 
+void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
+				  uint64_t offset, int nr_sectors)
+{
+	struct bcache_device *d = c->devices[inode];
+	unsigned stripe_size, stripe_offset;
+	uint64_t stripe;
+
+	if (!d)
+		return;
+
+	stripe_size = 1 << d->stripe_size_bits;
+	stripe = offset >> d->stripe_size_bits;
+	stripe_offset = offset & (stripe_size - 1);
+
+	while (nr_sectors) {
+		int s = min_t(unsigned, abs(nr_sectors),
+			      stripe_size - stripe_offset);
+
+		if (nr_sectors < 0)
+			s = -s;
+
+		atomic_add(s, d->stripe_sectors_dirty + stripe);
+		nr_sectors -= s;
+		stripe_offset = 0;
+		stripe++;
+	}
+}
+
 /* Background writeback - IO loop */
 
 static void dirty_io_destructor(struct closure *cl)
@@ -216,9 +285,10 @@ static void write_dirty_finish(struct closure *cl)
 	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
-	struct bio_vec *bv = bio_iovec_idx(&io->bio, io->bio.bi_vcnt);
+	struct bio_vec *bv;
+	int i;
 
-	while (bv-- != io->bio.bi_io_vec)
+	bio_for_each_segment_all(bv, &io->bio, i)
 		__free_page(bv->bv_page);
 
 	/* This is kind of a dumb way of signalling errors. */
@@ -236,10 +306,12 @@ static void write_dirty_finish(struct closure *cl)
 		for (i = 0; i < KEY_PTRS(&w->key); i++)
 			atomic_inc(&PTR_BUCKET(dc->disk.c, &w->key, i)->pin);
 
-		pr_debug("clearing %s", pkey(&w->key));
 		bch_btree_insert(&op, dc->disk.c);
 		closure_sync(&op.cl);
 
+		if (op.insert_collision)
+			trace_bcache_writeback_collision(&w->key);
+
 		atomic_long_inc(op.insert_collision
 				? &dc->disk.c->writeback_keys_failed
 				: &dc->disk.c->writeback_keys_done);
@@ -275,7 +347,6 @@ static void write_dirty(struct closure *cl)
 	io->bio.bi_bdev		= io->dc->bdev;
 	io->bio.bi_end_io	= dirty_endio;
 
-	trace_bcache_write_dirty(&io->bio);
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
 	continue_at(cl, write_dirty_finish, dirty_wq);
@@ -296,7 +367,6 @@ static void read_dirty_submit(struct closure *cl)
 {
 	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
 
-	trace_bcache_read_dirty(&io->bio);
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
 	continue_at(cl, write_dirty, dirty_wq);
@@ -349,10 +419,10 @@ static void read_dirty(struct closure *cl)
 		io->bio.bi_rw		= READ;
 		io->bio.bi_end_io	= read_dirty_endio;
 
-		if (bch_bio_alloc_pages(&io->bio, GFP_KERNEL))
+		if (bio_alloc_pages(&io->bio, GFP_KERNEL))
 			goto err_free;
 
-		pr_debug("%s", pkey(&w->key));
+		trace_bcache_writeback(&w->key);
 
 		closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl);
 
@@ -375,12 +445,49 @@ err:
 	refill_dirty(cl);
 }
 
+/* Init */
+
+static int bch_btree_sectors_dirty_init(struct btree *b, struct btree_op *op,
+					struct cached_dev *dc)
+{
+	struct bkey *k;
+	struct btree_iter iter;
+
+	bch_btree_iter_init(b, &iter, &KEY(dc->disk.id, 0, 0));
+	while ((k = bch_btree_iter_next_filter(&iter, b, bch_ptr_bad)))
+		if (!b->level) {
+			if (KEY_INODE(k) > dc->disk.id)
+				break;
+
+			if (KEY_DIRTY(k))
+				bcache_dev_sectors_dirty_add(b->c, dc->disk.id,
+							     KEY_START(k),
+							     KEY_SIZE(k));
+		} else {
+			btree(sectors_dirty_init, k, b, op, dc);
+			if (KEY_INODE(k) > dc->disk.id)
+				break;
+
+			cond_resched();
+		}
+
+	return 0;
+}
+
+void bch_sectors_dirty_init(struct cached_dev *dc)
+{
+	struct btree_op op;
+
+	bch_btree_op_init_stack(&op);
+	btree_root(sectors_dirty_init, dc->disk.c, &op, dc);
+}
+
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
 {
 	closure_init_unlocked(&dc->writeback);
 	init_rwsem(&dc->writeback_lock);
 
-	bch_keybuf_init(&dc->writeback_keys, dirty_pred);
+	bch_keybuf_init(&dc->writeback_keys);
 
 	dc->writeback_metadata		= true;
 	dc->writeback_running		= true;
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
new file mode 100644
index 000000000000..c91f61bb95b6
--- /dev/null
+++ b/drivers/md/bcache/writeback.h
@@ -0,0 +1,64 @@
+#ifndef _BCACHE_WRITEBACK_H
+#define _BCACHE_WRITEBACK_H
+
+#define CUTOFF_WRITEBACK	40
+#define CUTOFF_WRITEBACK_SYNC	70
+
+static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
+{
+	uint64_t i, ret = 0;
+
+	for (i = 0; i < d->nr_stripes; i++)
+		ret += atomic_read(d->stripe_sectors_dirty + i);
+
+	return ret;
+}
+
+static inline bool bcache_dev_stripe_dirty(struct bcache_device *d,
+					   uint64_t offset,
+					   unsigned nr_sectors)
+{
+	uint64_t stripe = offset >> d->stripe_size_bits;
+
+	while (1) {
+		if (atomic_read(d->stripe_sectors_dirty + stripe))
+			return true;
+
+		if (nr_sectors <= 1 << d->stripe_size_bits)
+			return false;
+
+		nr_sectors -= 1 << d->stripe_size_bits;
+		stripe++;
+	}
+}
+
+static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
+				    unsigned cache_mode, bool would_skip)
+{
+	unsigned in_use = dc->disk.c->gc_stats.in_use;
+
+	if (cache_mode != CACHE_MODE_WRITEBACK ||
+	    atomic_read(&dc->disk.detaching) ||
+	    in_use > CUTOFF_WRITEBACK_SYNC)
+		return false;
+
+	if (dc->partial_stripes_expensive &&
+	    bcache_dev_stripe_dirty(&dc->disk, bio->bi_sector,
+				    bio_sectors(bio)))
+		return true;
+
+	if (would_skip)
+		return false;
+
+	return bio->bi_rw & REQ_SYNC ||
+		in_use <= CUTOFF_WRITEBACK;
+}
+
+void bcache_dev_sectors_dirty_add(struct cache_set *, unsigned, uint64_t, int);
+void bch_writeback_queue(struct cached_dev *);
+void bch_writeback_add(struct cached_dev *);
+
+void bch_sectors_dirty_init(struct cached_dev *dc);
+void bch_cached_dev_writeback_init(struct cached_dev *);
+
+#endif
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index dc112a7137fe..4296155090b2 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -959,23 +959,21 @@ out:
 	return r;
 }
 
-static void remove_mapping(struct mq_policy *mq, dm_oblock_t oblock)
+static void mq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock)
 {
-	struct entry *e = hash_lookup(mq, oblock);
+	struct mq_policy *mq = to_mq_policy(p);
+	struct entry *e;
+
+	mutex_lock(&mq->lock);
+
+	e = hash_lookup(mq, oblock);
 
 	BUG_ON(!e || !e->in_cache);
 
 	del(mq, e);
 	e->in_cache = false;
 	push(mq, e);
-}
 
-static void mq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	remove_mapping(mq, oblock);
 	mutex_unlock(&mq->lock);
 }
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 957a719e8c2f..df7b0a06b0ea 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2290,12 +2290,18 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	d = r10_bio->devs[1].devnum;
 	wbio = r10_bio->devs[1].bio;
 	wbio2 = r10_bio->devs[1].repl_bio;
+	/* Need to test wbio2->bi_end_io before we call
+	 * generic_make_request as if the former is NULL,
+	 * the latter is free to free wbio2.
+	 */
+	if (wbio2 && !wbio2->bi_end_io)
+		wbio2 = NULL;
 	if (wbio->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
 		generic_make_request(wbio);
 	}
-	if (wbio2 && wbio2->bi_end_io) {
+	if (wbio2) {
 		atomic_inc(&conf->mirrors[d].replacement->nr_pending);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
 			     bio_sectors(wbio2));
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2bf094a587cb..78ea44336e75 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3462,6 +3462,7 @@ static void handle_stripe(struct stripe_head *sh)
 		    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
 			set_bit(STRIPE_SYNCING, &sh->state);
 			clear_bit(STRIPE_INSYNC, &sh->state);
+			clear_bit(STRIPE_REPLACED, &sh->state);
 		}
 		spin_unlock(&sh->stripe_lock);
 	}
@@ -3607,19 +3608,23 @@ static void handle_stripe(struct stripe_head *sh)
 			handle_parity_checks5(conf, sh, &s, disks);
 	}
 
-	if (s.replacing && s.locked == 0
-	    && !test_bit(STRIPE_INSYNC, &sh->state)) {
+	if ((s.replacing || s.syncing) && s.locked == 0
+	    && !test_bit(STRIPE_COMPUTE_RUN, &sh->state)
+	    && !test_bit(STRIPE_REPLACED, &sh->state)) {
 		/* Write out to replacement devices where possible */
 		for (i = 0; i < conf->raid_disks; i++)
-			if (test_bit(R5_UPTODATE, &sh->dev[i].flags) &&
-			    test_bit(R5_NeedReplace, &sh->dev[i].flags)) {
+			if (test_bit(R5_NeedReplace, &sh->dev[i].flags)) {
+				WARN_ON(!test_bit(R5_UPTODATE, &sh->dev[i].flags));
 				set_bit(R5_WantReplace, &sh->dev[i].flags);
 				set_bit(R5_LOCKED, &sh->dev[i].flags);
 				s.locked++;
 			}
-		set_bit(STRIPE_INSYNC, &sh->state);
+		if (s.replacing)
+			set_bit(STRIPE_INSYNC, &sh->state);
+		set_bit(STRIPE_REPLACED, &sh->state);
 	}
 	if ((s.syncing || s.replacing) && s.locked == 0 &&
+	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
 	    test_bit(STRIPE_INSYNC, &sh->state)) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
 		clear_bit(STRIPE_SYNCING, &sh->state);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index b0b663b119a8..70c49329ca9a 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -306,6 +306,7 @@ enum {
 	STRIPE_SYNC_REQUESTED,
 	STRIPE_SYNCING,
 	STRIPE_INSYNC,
+	STRIPE_REPLACED,
 	STRIPE_PREREAD_ACTIVE,
 	STRIPE_DELAYED,
 	STRIPE_DEGRADED,
diff --git a/drivers/media/i2c/ml86v7667.c b/drivers/media/i2c/ml86v7667.c
index efdc873e58d1..a9857022f71d 100644
--- a/drivers/media/i2c/ml86v7667.c
+++ b/drivers/media/i2c/ml86v7667.c
@@ -117,7 +117,7 @@ static int ml86v7667_s_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct v4l2_subdev *sd = to_sd(ctrl);
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
-	int ret;
+	int ret = -EINVAL;
 
 	switch (ctrl->id) {
 	case V4L2_CID_BRIGHTNESS:
@@ -157,7 +157,7 @@ static int ml86v7667_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static int ml86v7667_querystd(struct v4l2_subdev *sd, v4l2_std_id *std)
diff --git a/drivers/media/platform/coda.c b/drivers/media/platform/coda.c
index df4ada880e42..bd9405df1bd6 100644
--- a/drivers/media/platform/coda.c
+++ b/drivers/media/platform/coda.c
@@ -1987,7 +1987,7 @@ MODULE_DEVICE_TABLE(platform, coda_platform_ids);
 
 #ifdef CONFIG_OF
 static const struct of_device_id coda_dt_ids[] = {
-	{ .compatible = "fsl,imx27-vpu", .data = &coda_platform_ids[CODA_IMX27] },
+	{ .compatible = "fsl,imx27-vpu", .data = &coda_devdata[CODA_IMX27] },
 	{ .compatible = "fsl,imx53-vpu", .data = &coda_devdata[CODA_IMX53] },
 	{ /* sentinel */ }
 };
diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 553d87e5ceab..fd6289d60cde 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -784,6 +784,7 @@ static int g2d_probe(struct platform_device *pdev)
 	}
 	*vfd = g2d_videodev;
 	vfd->lock = &dev->mutex;
+	vfd->v4l2_dev = &dev->v4l2_dev;
 	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
 	if (ret) {
 		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
index 5296385153d5..4f6dd42c9adb 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
@@ -344,7 +344,7 @@ static int vidioc_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
 		pix_mp->num_planes = 2;
 		/* Set pixelformat to the format in which MFC
 		   outputs the decoded frame */
-		pix_mp->pixelformat = V4L2_PIX_FMT_NV12MT;
+		pix_mp->pixelformat = ctx->dst_fmt->fourcc;
 		pix_mp->plane_fmt[0].bytesperline = ctx->buf_width;
 		pix_mp->plane_fmt[0].sizeimage = ctx->luma_size;
 		pix_mp->plane_fmt[1].bytesperline = ctx->buf_width;
@@ -382,10 +382,16 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
 			mfc_err("Unsupported format for source.\n");
 			return -EINVAL;
 		}
-		if (!IS_MFCV6(dev) && (fmt->fourcc == V4L2_PIX_FMT_VP8)) {
-			mfc_err("Not supported format.\n");
+		if (fmt->codec_mode == S5P_FIMV_CODEC_NONE) {
+			mfc_err("Unknown codec\n");
 			return -EINVAL;
 		}
+		if (!IS_MFCV6(dev)) {
+			if (fmt->fourcc == V4L2_PIX_FMT_VP8) {
+				mfc_err("Not supported format.\n");
+				return -EINVAL;
+			}
+		}
 	} else if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
 		fmt = find_format(f, MFC_FMT_RAW);
 		if (!fmt) {
@@ -411,7 +417,6 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 	struct s5p_mfc_ctx *ctx = fh_to_ctx(priv);
 	int ret = 0;
-	struct s5p_mfc_fmt *fmt;
 	struct v4l2_pix_format_mplane *pix_mp;
 
 	mfc_debug_enter();
@@ -425,54 +430,32 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 		goto out;
 	}
 	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		fmt = find_format(f, MFC_FMT_RAW);
-		if (!fmt) {
-			mfc_err("Unsupported format for source.\n");
-			return -EINVAL;
-		}
-		if (!IS_MFCV6(dev) && (fmt->fourcc != V4L2_PIX_FMT_NV12MT)) {
-			mfc_err("Not supported format.\n");
-			return -EINVAL;
-		} else if (IS_MFCV6(dev) &&
-				(fmt->fourcc == V4L2_PIX_FMT_NV12MT)) {
-			mfc_err("Not supported format.\n");
-			return -EINVAL;
-		}
-		ctx->dst_fmt = fmt;
-		mfc_debug_leave();
-		return ret;
-	} else if (f->type != V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
-		mfc_err("Wrong type error for S_FMT : %d", f->type);
-		return -EINVAL;
-	}
-	fmt = find_format(f, MFC_FMT_DEC);
-	if (!fmt || fmt->codec_mode == S5P_MFC_CODEC_NONE) {
-		mfc_err("Unknown codec\n");
-		ret = -EINVAL;
+		/* dst_fmt is validated by call to vidioc_try_fmt */
+		ctx->dst_fmt = find_format(f, MFC_FMT_RAW);
+		ret = 0;
 		goto out;
-	}
-	if (fmt->type != MFC_FMT_DEC) {
-		mfc_err("Wrong format selected, you should choose "
-					"format for decoding\n");
+	} else if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
+		/* src_fmt is validated by call to vidioc_try_fmt */
+		ctx->src_fmt = find_format(f, MFC_FMT_DEC);
+		ctx->codec_mode = ctx->src_fmt->codec_mode;
+		mfc_debug(2, "The codec number is: %d\n", ctx->codec_mode);
+		pix_mp->height = 0;
+		pix_mp->width = 0;
+		if (pix_mp->plane_fmt[0].sizeimage)
+			ctx->dec_src_buf_size = pix_mp->plane_fmt[0].sizeimage;
+		else
+			pix_mp->plane_fmt[0].sizeimage = ctx->dec_src_buf_size =
+								DEF_CPB_SIZE;
+		pix_mp->plane_fmt[0].bytesperline = 0;
+		ctx->state = MFCINST_INIT;
+		ret = 0;
+		goto out;
+	} else {
+		mfc_err("Wrong type error for S_FMT : %d", f->type);
 		ret = -EINVAL;
 		goto out;
 	}
-	if (!IS_MFCV6(dev) && (fmt->fourcc == V4L2_PIX_FMT_VP8)) {
-		mfc_err("Not supported format.\n");
-		return -EINVAL;
-	}
-	ctx->src_fmt = fmt;
-	ctx->codec_mode = fmt->codec_mode;
-	mfc_debug(2, "The codec number is: %d\n", ctx->codec_mode);
-	pix_mp->height = 0;
-	pix_mp->width = 0;
-	if (pix_mp->plane_fmt[0].sizeimage)
-		ctx->dec_src_buf_size = pix_mp->plane_fmt[0].sizeimage;
-	else
-		pix_mp->plane_fmt[0].sizeimage = ctx->dec_src_buf_size =
-								DEF_CPB_SIZE;
-	pix_mp->plane_fmt[0].bytesperline = 0;
-	ctx->state = MFCINST_INIT;
+
 out:
 	mfc_debug_leave();
 	return ret;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
index 2549967b2f85..59e56f4c8ce3 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
@@ -906,6 +906,7 @@ static int vidioc_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
 
 static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
 {
+	struct s5p_mfc_dev *dev = video_drvdata(file);
 	struct s5p_mfc_fmt *fmt;
 	struct v4l2_pix_format_mplane *pix_fmt_mp = &f->fmt.pix_mp;
 
@@ -930,6 +931,18 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
 			return -EINVAL;
 		}
 
+		if (!IS_MFCV6(dev)) {
+			if (fmt->fourcc == V4L2_PIX_FMT_NV12MT_16X16) {
+				mfc_err("Not supported format.\n");
+				return -EINVAL;
+			}
+		} else if (IS_MFCV6(dev)) {
+			if (fmt->fourcc == V4L2_PIX_FMT_NV12MT) {
+				mfc_err("Not supported format.\n");
+				return -EINVAL;
+			}
+		}
+
 		if (fmt->num_planes != pix_fmt_mp->num_planes) {
 			mfc_err("failed to try output format\n");
 			return -EINVAL;
@@ -947,7 +960,6 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 {
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 	struct s5p_mfc_ctx *ctx = fh_to_ctx(priv);
-	struct s5p_mfc_fmt *fmt;
 	struct v4l2_pix_format_mplane *pix_fmt_mp = &f->fmt.pix_mp;
 	int ret = 0;
 
@@ -960,13 +972,9 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 		goto out;
 	}
 	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		fmt = find_format(f, MFC_FMT_ENC);
-		if (!fmt) {
-			mfc_err("failed to set capture format\n");
-			return -EINVAL;
-		}
+		/* dst_fmt is validated by call to vidioc_try_fmt */
+		ctx->dst_fmt = find_format(f, MFC_FMT_ENC);
 		ctx->state = MFCINST_INIT;
-		ctx->dst_fmt = fmt;
 		ctx->codec_mode = ctx->dst_fmt->codec_mode;
 		ctx->enc_dst_buf_size =	pix_fmt_mp->plane_fmt[0].sizeimage;
 		pix_fmt_mp->plane_fmt[0].bytesperline = 0;
@@ -987,28 +995,8 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 		}
 		mfc_debug(2, "Got instance number: %d\n", ctx->inst_no);
 	} else if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
-		fmt = find_format(f, MFC_FMT_RAW);
-		if (!fmt) {
-			mfc_err("failed to set output format\n");
-			return -EINVAL;
-		}
-
-		if (!IS_MFCV6(dev) &&
-				(fmt->fourcc == V4L2_PIX_FMT_NV12MT_16X16)) {
-			mfc_err("Not supported format.\n");
-			return -EINVAL;
-		} else if (IS_MFCV6(dev) &&
-				(fmt->fourcc == V4L2_PIX_FMT_NV12MT)) {
-			mfc_err("Not supported format.\n");
-			return -EINVAL;
-		}
-
-		if (fmt->num_planes != pix_fmt_mp->num_planes) {
-			mfc_err("failed to set output format\n");
-			ret = -EINVAL;
-			goto out;
-		}
-		ctx->src_fmt = fmt;
+		/* src_fmt is validated by call to vidioc_try_fmt */
+		ctx->src_fmt = find_format(f, MFC_FMT_RAW);
 		ctx->img_width = pix_fmt_mp->width;
 		ctx->img_height = pix_fmt_mp->height;
 		mfc_debug(2, "codec number: %d\n", ctx->src_fmt->codec_mode);
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index 4851cc2e4a4d..c4ff9739a7ae 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -726,7 +726,7 @@ static int em28xx_i2c_eeprom(struct em28xx *dev, unsigned bus,
 
 	*eedata = data;
 	*eedata_len = len;
-	dev_config = (void *)eedata;
+	dev_config = (void *)*eedata;
 
 	switch (le16_to_cpu(dev_config->chip_conf) >> 4 & 0x3) {
 	case 0:
diff --git a/drivers/media/usb/hdpvr/hdpvr-core.c b/drivers/media/usb/hdpvr/hdpvr-core.c
index cb694055ba7d..6e5070774dc2 100644
--- a/drivers/media/usb/hdpvr/hdpvr-core.c
+++ b/drivers/media/usb/hdpvr/hdpvr-core.c
@@ -303,6 +303,11 @@ static int hdpvr_probe(struct usb_interface *interface,
 
 	dev->workqueue = 0;
 
+	/* init video transfer queues first of all */
+	/* to prevent oops in hdpvr_delete() on error paths */
+	INIT_LIST_HEAD(&dev->free_buff_list);
+	INIT_LIST_HEAD(&dev->rec_buff_list);
+
 	/* register v4l2_device early so it can be used for printks */
 	if (v4l2_device_register(&interface->dev, &dev->v4l2_dev)) {
 		dev_err(&interface->dev, "v4l2_device_register failed\n");
@@ -325,10 +330,6 @@ static int hdpvr_probe(struct usb_interface *interface,
 	if (!dev->workqueue)
 		goto error;
 
-	/* init video transfer queues */
-	INIT_LIST_HEAD(&dev->free_buff_list);
-	INIT_LIST_HEAD(&dev->rec_buff_list);
-
 	dev->options = hdpvr_default_options;
 
 	if (default_video_input < HDPVR_VIDEO_INPUTS)
@@ -405,7 +406,7 @@ static int hdpvr_probe(struct usb_interface *interface,
 				    video_nr[atomic_inc_return(&dev_nr)]);
 	if (retval < 0) {
 		v4l2_err(&dev->v4l2_dev, "registering videodev failed\n");
-		goto error;
+		goto reg_fail;
 	}
 
 	/* let the user know what node this device is now attached to */
diff --git a/drivers/media/usb/usbtv/Kconfig b/drivers/media/usb/usbtv/Kconfig
index 8864436464bf..7c5b86006ee6 100644
--- a/drivers/media/usb/usbtv/Kconfig
+++ b/drivers/media/usb/usbtv/Kconfig
@@ -1,6 +1,6 @@
 config VIDEO_USBTV
         tristate "USBTV007 video capture support"
-        depends on VIDEO_DEV
+        depends on VIDEO_V4L2
         select VIDEOBUF2_VMALLOC
 
         ---help---
diff --git a/drivers/media/usb/usbtv/usbtv.c b/drivers/media/usb/usbtv/usbtv.c
index bf43f874685e..91650173941a 100644
--- a/drivers/media/usb/usbtv/usbtv.c
+++ b/drivers/media/usb/usbtv/usbtv.c
@@ -57,7 +57,7 @@
 #define USBTV_CHUNK_SIZE	256
 #define USBTV_CHUNK		240
 #define USBTV_CHUNKS		(USBTV_WIDTH * USBTV_HEIGHT \
-					/ 2 / USBTV_CHUNK)
+					/ 4 / USBTV_CHUNK)
 
 /* Chunk header. */
 #define USBTV_MAGIC_OK(chunk)	((be32_to_cpu(chunk[0]) & 0xff000000) \
@@ -89,6 +89,7 @@ struct usbtv {
 	/* Number of currently processed frame, useful find
 	 * out when a new one begins. */
 	u32 frame_id;
+	int chunks_done;
 
 	int iso_size;
 	unsigned int sequence;
@@ -202,6 +203,26 @@ static int usbtv_setup_capture(struct usbtv *usbtv)
 	return 0;
 }
 
+/* Copy data from chunk into a frame buffer, deinterlacing the data
+ * into every second line. Unfortunately, they don't align nicely into
+ * 720 pixel lines, as the chunk is 240 words long, which is 480 pixels.
+ * Therefore, we break down the chunk into two halves before copyting,
+ * so that we can interleave a line if needed. */
+static void usbtv_chunk_to_vbuf(u32 *frame, u32 *src, int chunk_no, int odd)
+{
+	int half;
+
+	for (half = 0; half < 2; half++) {
+		int part_no = chunk_no * 2 + half;
+		int line = part_no / 3;
+		int part_index = (line * 2 + !odd) * 3 + (part_no % 3);
+
+		u32 *dst = &frame[part_index * USBTV_CHUNK/2];
+		memcpy(dst, src, USBTV_CHUNK/2 * sizeof(*src));
+		src += USBTV_CHUNK/2;
+	}
+}
+
 /* Called for each 256-byte image chunk.
  * First word identifies the chunk, followed by 240 words of image
  * data and padding. */
@@ -218,17 +239,17 @@ static void usbtv_image_chunk(struct usbtv *usbtv, u32 *chunk)
 	frame_id = USBTV_FRAME_ID(chunk);
 	odd = USBTV_ODD(chunk);
 	chunk_no = USBTV_CHUNK_NO(chunk);
-
-	/* Deinterlace. TODO: Use interlaced frame format. */
-	chunk_no = (chunk_no - chunk_no % 3) * 2 + chunk_no % 3;
-	chunk_no += !odd * 3;
-
 	if (chunk_no >= USBTV_CHUNKS)
 		return;
 
 	/* Beginning of a frame. */
-	if (chunk_no == 0)
+	if (chunk_no == 0) {
 		usbtv->frame_id = frame_id;
+		usbtv->chunks_done = 0;
+	}
+
+	if (usbtv->frame_id != frame_id)
+		return;
 
 	spin_lock_irqsave(&usbtv->buflock, flags);
 	if (list_empty(&usbtv->bufs)) {
@@ -241,19 +262,23 @@ static void usbtv_image_chunk(struct usbtv *usbtv, u32 *chunk)
 	buf = list_first_entry(&usbtv->bufs, struct usbtv_buf, list);
 	frame = vb2_plane_vaddr(&buf->vb, 0);
 
-	/* Copy the chunk. */
-	memcpy(&frame[chunk_no * USBTV_CHUNK], &chunk[1],
-			USBTV_CHUNK * sizeof(chunk[1]));
+	/* Copy the chunk data. */
+	usbtv_chunk_to_vbuf(frame, &chunk[1], chunk_no, odd);
+	usbtv->chunks_done++;
 
 	/* Last chunk in a frame, signalling an end */
-	if (usbtv->frame_id && chunk_no == USBTV_CHUNKS-1) {
+	if (odd && chunk_no == USBTV_CHUNKS-1) {
 		int size = vb2_plane_size(&buf->vb, 0);
+		enum vb2_buffer_state state = usbtv->chunks_done ==
+						USBTV_CHUNKS ?
+						VB2_BUF_STATE_DONE :
+						VB2_BUF_STATE_ERROR;
 
 		buf->vb.v4l2_buf.field = V4L2_FIELD_INTERLACED;
 		buf->vb.v4l2_buf.sequence = usbtv->sequence++;
 		v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
 		vb2_set_plane_payload(&buf->vb, 0, size);
-		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_DONE);
+		vb2_buffer_done(&buf->vb, state);
 		list_del(&buf->list);
 	}
 
@@ -518,7 +543,7 @@ static int usbtv_queue_setup(struct vb2_queue *vq,
 	if (*nbuffers < 2)
 		*nbuffers = 2;
 	*nplanes = 1;
-	sizes[0] = USBTV_CHUNK * USBTV_CHUNKS * sizeof(u32);
+	sizes[0] = USBTV_WIDTH * USBTV_HEIGHT / 2 * sizeof(u32);
 
 	return 0;
 }
diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c
index f7b90661e321..e068a76a5f6f 100644
--- a/drivers/misc/atmel-ssc.c
+++ b/drivers/misc/atmel-ssc.c
@@ -66,14 +66,19 @@ EXPORT_SYMBOL(ssc_request);
 
 void ssc_free(struct ssc_device *ssc)
 {
+	bool disable_clk = true;
+
 	spin_lock(&user_lock);
-	if (ssc->user) {
+	if (ssc->user)
 		ssc->user--;
-		clk_disable_unprepare(ssc->clk);
-	} else {
+	else {
+		disable_clk = false;
 		dev_dbg(&ssc->pdev->dev, "device already free\n");
 	}
 	spin_unlock(&user_lock);
+
+	if (disable_clk)
+		clk_disable_unprepare(ssc->clk);
 }
 EXPORT_SYMBOL(ssc_free);
 
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index f9296abcf02a..6127ab64bb39 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -167,7 +167,7 @@ int mei_hbm_start_req(struct mei_device *dev)
 
 	dev->hbm_state = MEI_HBM_IDLE;
 	if (mei_write_message(dev, mei_hdr, dev->wr_msg.data)) {
-		dev_err(&dev->pdev->dev, "version message writet failed\n");
+		dev_err(&dev->pdev->dev, "version message write failed\n");
 		dev->dev_state = MEI_DEV_RESETTING;
 		mei_reset(dev, 1);
 		return -ENODEV;
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index e4f8dec4dc3c..b22c7e247225 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -239,14 +239,18 @@ static int mei_me_hw_ready_wait(struct mei_device *dev)
 	if (mei_me_hw_is_ready(dev))
 		return 0;
 
+	dev->recvd_hw_ready = false;
 	mutex_unlock(&dev->device_lock);
 	err = wait_event_interruptible_timeout(dev->wait_hw_ready,
-			dev->recvd_hw_ready, MEI_INTEROP_TIMEOUT);
+			dev->recvd_hw_ready,
+			mei_secs_to_jiffies(MEI_INTEROP_TIMEOUT));
 	mutex_lock(&dev->device_lock);
 	if (!err && !dev->recvd_hw_ready) {
+		if (!err)
+			err = -ETIMEDOUT;
 		dev_err(&dev->pdev->dev,
-			"wait hw ready failed. status = 0x%x\n", err);
-		return -ETIMEDOUT;
+			"wait hw ready failed. status = %d\n", err);
+		return err;
 	}
 
 	dev->recvd_hw_ready = false;
@@ -483,7 +487,9 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	/* check if ME wants a reset */
 	if (!mei_hw_is_ready(dev) &&
 	    dev->dev_state != MEI_DEV_RESETTING &&
-	    dev->dev_state != MEI_DEV_INITIALIZING) {
+	    dev->dev_state != MEI_DEV_INITIALIZING &&
+	    dev->dev_state != MEI_DEV_POWER_DOWN &&
+	    dev->dev_state != MEI_DEV_POWER_UP) {
 		dev_dbg(&dev->pdev->dev, "FW not ready.\n");
 		mei_reset(dev, 1);
 		mutex_unlock(&dev->device_lock);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index ed1d75203af6..e6f16f83ecde 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -148,7 +148,8 @@ void mei_reset(struct mei_device *dev, int interrupts_enabled)
 
 	dev->hbm_state = MEI_HBM_IDLE;
 
-	if (dev->dev_state != MEI_DEV_INITIALIZING) {
+	if (dev->dev_state != MEI_DEV_INITIALIZING &&
+	    dev->dev_state != MEI_DEV_POWER_UP) {
 		if (dev->dev_state != MEI_DEV_DISABLED &&
 		    dev->dev_state != MEI_DEV_POWER_DOWN)
 			dev->dev_state = MEI_DEV_RESETTING;
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 847b1996ce8e..2c5a91bb8ec3 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -128,7 +128,7 @@ static inline int pxamci_set_power(struct pxamci_host *host,
 			       !!on ^ host->pdata->gpio_power_invert);
 	}
 	if (!host->vcc && host->pdata && host->pdata->setpower)
-		host->pdata->setpower(mmc_dev(host->mmc), vdd);
+		return host->pdata->setpower(mmc_dev(host->mmc), vdd);
 
 	return 0;
 }
diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index a746ba272f04..a956053608f9 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -1007,7 +1007,7 @@ static void arcnet_rx(struct net_device *dev, int bufnum)
 
 	soft = &pkt.soft.rfc1201;
 
-	lp->hw.copy_from_card(dev, bufnum, 0, &pkt, sizeof(ARC_HDR_SIZE));
+	lp->hw.copy_from_card(dev, bufnum, 0, &pkt, ARC_HDR_SIZE);
 	if (pkt.hard.offset[0]) {
 		ofs = pkt.hard.offset[0];
 		length = 256 - ofs;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 07f257d44a1e..e48cb339c0c6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3714,11 +3714,17 @@ static int bond_neigh_init(struct neighbour *n)
  * The bonding ndo_neigh_setup is called at init time beofre any
  * slave exists. So we must declare proxy setup function which will
  * be used at run time to resolve the actual slave neigh param setup.
+ *
+ * It's also called by master devices (such as vlans) to setup their
+ * underlying devices. In that case - do nothing, we're already set up from
+ * our init.
  */
 static int bond_neigh_setup(struct net_device *dev,
 			    struct neigh_parms *parms)
 {
-	parms->neigh_setup   = bond_neigh_init;
+	/* modify only our neigh_parms */
+	if (parms->dev == dev)
+		parms->neigh_setup = bond_neigh_init;
 
 	return 0;
 }
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 6aa7b3266c80..ac6177d3befc 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -412,10 +412,20 @@ static void esd_usb2_read_bulk_callback(struct urb *urb)
 
 		switch (msg->msg.hdr.cmd) {
 		case CMD_CAN_RX:
+			if (msg->msg.rx.net >= dev->net_count) {
+				dev_err(dev->udev->dev.parent, "format error\n");
+				break;
+			}
+
 			esd_usb2_rx_can_msg(dev->nets[msg->msg.rx.net], msg);
 			break;
 
 		case CMD_CAN_TX:
+			if (msg->msg.txdone.net >= dev->net_count) {
+				dev_err(dev->udev->dev.parent, "format error\n");
+				break;
+			}
+
 			esd_usb2_tx_done_msg(dev->nets[msg->msg.txdone.net],
 					     msg);
 			break;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 25723d8ee201..925ab8ec9329 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -649,7 +649,7 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 		if ((mc->ptr + rec_len) > mc->end)
 			goto decode_failed;
 
-		memcpy(cf->data, mc->ptr, rec_len);
+		memcpy(cf->data, mc->ptr, cf->can_dlc);
 		mc->ptr += rec_len;
 	}
 
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index cbd388eea682..8becd3d838b5 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -779,6 +779,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv)
 			usb_unanchor_urb(urb);
 			usb_free_coherent(priv->udev, RX_BUFFER_SIZE, buf,
 					  urb->transfer_dma);
+			usb_free_urb(urb);
 			break;
 		}
 
diff --git a/drivers/net/ethernet/allwinner/Kconfig b/drivers/net/ethernet/allwinner/Kconfig
index 53ad213e865b..d8d95d4cd45a 100644
--- a/drivers/net/ethernet/allwinner/Kconfig
+++ b/drivers/net/ethernet/allwinner/Kconfig
@@ -3,19 +3,20 @@
 #
 
 config NET_VENDOR_ALLWINNER
-       bool "Allwinner devices"
-       default y
-       depends on ARCH_SUNXI
-       ---help---
-         If you have a network (Ethernet) card belonging to this
-	 class, say Y and read the Ethernet-HOWTO, available from
-	 <http://www.tldp.org/docs.html#howto>.
+	bool "Allwinner devices"
+	default y
 
-	 Note that the answer to this question doesn't directly
-	 affect the kernel: saying N will just cause the configurator
-	 to skip all the questions about Allwinner cards. If you say Y,
-	 you will be asked for your specific card in the following
-	 questions.
+	depends on ARCH_SUNXI
+	---help---
+	  If you have a network (Ethernet) card belonging to this
+	  class, say Y and read the Ethernet-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>.
+
+	  Note that the answer to this question doesn't directly
+	  affect the kernel: saying N will just cause the configurator
+	  to skip all the questions about Allwinner cards. If you say Y,
+	  you will be asked for your specific card in the following
+	  questions.
 
 if NET_VENDOR_ALLWINNER
 
@@ -26,6 +27,7 @@ config SUN4I_EMAC
 	select CRC32
 	select MII
 	select PHYLIB
+	select MDIO_SUN4I
         ---help---
           Support for Allwinner A10 EMAC ethernet driver.
 
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index f1b121ee5525..55d79cb53a79 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -199,7 +199,7 @@ static int arc_emac_rx(struct net_device *ndev, int budget)
 	struct arc_emac_priv *priv = netdev_priv(ndev);
 	unsigned int work_done;
 
-	for (work_done = 0; work_done <= budget; work_done++) {
+	for (work_done = 0; work_done < budget; work_done++) {
 		unsigned int *last_rx_bd = &priv->last_rx_bd;
 		struct net_device_stats *stats = &priv->stats;
 		struct buffer_state *rx_buff = &priv->rx_buff[*last_rx_bd];
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h
index b2bf324631dc..0f0556526ba9 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h
@@ -520,6 +520,9 @@ struct atl1c_adapter {
 	struct net_device   *netdev;
 	struct pci_dev      *pdev;
 	struct napi_struct  napi;
+	struct page         *rx_page;
+	unsigned int	    rx_page_offset;
+	unsigned int	    rx_frag_size;
 	struct atl1c_hw        hw;
 	struct atl1c_hw_stats  hw_stats;
 	struct mii_if_info  mii;    /* MII interface info */
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 786a87483298..a36a760ada28 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -481,10 +481,15 @@ static int atl1c_set_mac_addr(struct net_device *netdev, void *p)
 static void atl1c_set_rxbufsize(struct atl1c_adapter *adapter,
 				struct net_device *dev)
 {
+	unsigned int head_size;
 	int mtu = dev->mtu;
 
 	adapter->rx_buffer_len = mtu > AT_RX_BUF_SIZE ?
 		roundup(mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN, 8) : AT_RX_BUF_SIZE;
+
+	head_size = SKB_DATA_ALIGN(adapter->rx_buffer_len + NET_SKB_PAD) +
+		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	adapter->rx_frag_size = roundup_pow_of_two(head_size);
 }
 
 static netdev_features_t atl1c_fix_features(struct net_device *netdev,
@@ -952,6 +957,10 @@ static void atl1c_free_ring_resources(struct atl1c_adapter *adapter)
 		kfree(adapter->tpd_ring[0].buffer_info);
 		adapter->tpd_ring[0].buffer_info = NULL;
 	}
+	if (adapter->rx_page) {
+		put_page(adapter->rx_page);
+		adapter->rx_page = NULL;
+	}
 }
 
 /**
@@ -1639,6 +1648,35 @@ static inline void atl1c_rx_checksum(struct atl1c_adapter *adapter,
 	skb_checksum_none_assert(skb);
 }
 
+static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter)
+{
+	struct sk_buff *skb;
+	struct page *page;
+
+	if (adapter->rx_frag_size > PAGE_SIZE)
+		return netdev_alloc_skb(adapter->netdev,
+					adapter->rx_buffer_len);
+
+	page = adapter->rx_page;
+	if (!page) {
+		adapter->rx_page = page = alloc_page(GFP_ATOMIC);
+		if (unlikely(!page))
+			return NULL;
+		adapter->rx_page_offset = 0;
+	}
+
+	skb = build_skb(page_address(page) + adapter->rx_page_offset,
+			adapter->rx_frag_size);
+	if (likely(skb)) {
+		adapter->rx_page_offset += adapter->rx_frag_size;
+		if (adapter->rx_page_offset >= PAGE_SIZE)
+			adapter->rx_page = NULL;
+		else
+			get_page(page);
+	}
+	return skb;
+}
+
 static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter)
 {
 	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
@@ -1660,7 +1698,7 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter)
 	while (next_info->flags & ATL1C_BUFFER_FREE) {
 		rfd_desc = ATL1C_RFD_DESC(rfd_ring, rfd_next_to_use);
 
-		skb = netdev_alloc_skb(adapter->netdev, adapter->rx_buffer_len);
+		skb = atl1c_alloc_skb(adapter);
 		if (unlikely(!skb)) {
 			if (netif_msg_rx_err(adapter))
 				dev_warn(&pdev->dev, "alloc rx buffer failed\n");
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index dedbd76c033e..00b88cbfde25 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -486,7 +486,7 @@ struct bnx2x_fastpath {
 
 	struct napi_struct	napi;
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int state;
 #define BNX2X_FP_STATE_IDLE		      0
 #define BNX2X_FP_STATE_NAPI		(1 << 0)    /* NAPI owns this FP */
@@ -498,7 +498,7 @@ struct bnx2x_fastpath {
 #define BNX2X_FP_USER_PEND (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_POLL_YIELD)
 	/* protect state */
 	spinlock_t lock;
-#endif /* CONFIG_NET_LL_RX_POLL */
+#endif /* CONFIG_NET_RX_BUSY_POLL */
 
 	union host_hc_status_block	status_blk;
 	/* chip independent shortcuts into sb structure */
@@ -572,7 +572,7 @@ struct bnx2x_fastpath {
 #define bnx2x_fp_stats(bp, fp)	(&((bp)->fp_stats[(fp)->index]))
 #define bnx2x_fp_qstats(bp, fp)	(&((bp)->fp_stats[(fp)->index].eth_q_stats))
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp)
 {
 	spin_lock_init(&fp->lock);
@@ -680,7 +680,7 @@ static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
 {
 	return false;
 }
-#endif /* CONFIG_NET_LL_RX_POLL */
+#endif /* CONFIG_NET_RX_BUSY_POLL */
 
 /* Use 2500 as a mini-jumbo MTU for FCoE */
 #define BNX2X_FCOE_MINI_JUMBO_MTU	2500
@@ -1333,6 +1333,8 @@ enum {
 	BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN,
 	BNX2X_SP_RTNL_VFPF_STORM_RX_MODE,
 	BNX2X_SP_RTNL_HYPERVISOR_VLAN,
+	BNX2X_SP_RTNL_TX_STOP,
+	BNX2X_SP_RTNL_TX_RESUME,
 };
 
 struct bnx2x_prev_path_list {
@@ -1502,6 +1504,7 @@ struct bnx2x {
 #define BC_SUPPORTS_DCBX_MSG_NON_PMF	(1 << 21)
 #define IS_VF_FLAG			(1 << 22)
 #define INTERRUPTS_ENABLED_FLAG		(1 << 23)
+#define BC_SUPPORTS_RMMOD_CMD		(1 << 24)
 
 #define BP_NOMCP(bp)			((bp)->flags & NO_MCP_FLAG)
 
@@ -1830,6 +1833,8 @@ struct bnx2x {
 
 	int fp_array_size;
 	u32 dump_preset_idx;
+	bool					stats_started;
+	struct semaphore			stats_sema;
 };
 
 /* Tx queues may be less or equal to Rx queues */
@@ -2451,4 +2456,6 @@ enum bnx2x_pci_bus_speed {
 	BNX2X_PCI_LINK_SPEED_5000 = 5000,
 	BNX2X_PCI_LINK_SPEED_8000 = 8000
 };
+
+void bnx2x_set_local_cmng(struct bnx2x *bp);
 #endif /* bnx2x.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ee350bde1818..f2d1ff10054b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3117,7 +3117,7 @@ int bnx2x_poll(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 /* must be called with local_bh_disable()d */
 int bnx2x_low_latency_recv(struct napi_struct *napi)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index 0c94df47e0e8..fcf2761d8828 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -30,10 +30,8 @@
 #include "bnx2x_dcb.h"
 
 /* forward declarations of dcbx related functions */
-static int bnx2x_dcbx_stop_hw_tx(struct bnx2x *bp);
 static void bnx2x_pfc_set_pfc(struct bnx2x *bp);
 static void bnx2x_dcbx_update_ets_params(struct bnx2x *bp);
-static int bnx2x_dcbx_resume_hw_tx(struct bnx2x *bp);
 static void bnx2x_dcbx_get_ets_pri_pg_tbl(struct bnx2x *bp,
 					  u32 *set_configuration_ets_pg,
 					  u32 *pri_pg_tbl);
@@ -425,30 +423,52 @@ static void bnx2x_pfc_set_pfc(struct bnx2x *bp)
 		bnx2x_pfc_clear(bp);
 }
 
-static int bnx2x_dcbx_stop_hw_tx(struct bnx2x *bp)
+int bnx2x_dcbx_stop_hw_tx(struct bnx2x *bp)
 {
 	struct bnx2x_func_state_params func_params = {NULL};
+	int rc;
 
 	func_params.f_obj = &bp->func_obj;
 	func_params.cmd = BNX2X_F_CMD_TX_STOP;
 
+	__set_bit(RAMROD_COMP_WAIT, &func_params.ramrod_flags);
+	__set_bit(RAMROD_RETRY, &func_params.ramrod_flags);
+
 	DP(BNX2X_MSG_DCB, "STOP TRAFFIC\n");
-	return bnx2x_func_state_change(bp, &func_params);
+
+	rc = bnx2x_func_state_change(bp, &func_params);
+	if (rc) {
+		BNX2X_ERR("Unable to hold traffic for HW configuration\n");
+		bnx2x_panic();
+	}
+
+	return rc;
 }
 
-static int bnx2x_dcbx_resume_hw_tx(struct bnx2x *bp)
+int bnx2x_dcbx_resume_hw_tx(struct bnx2x *bp)
 {
 	struct bnx2x_func_state_params func_params = {NULL};
 	struct bnx2x_func_tx_start_params *tx_params =
 		&func_params.params.tx_start;
+	int rc;
 
 	func_params.f_obj = &bp->func_obj;
 	func_params.cmd = BNX2X_F_CMD_TX_START;
 
+	__set_bit(RAMROD_COMP_WAIT, &func_params.ramrod_flags);
+	__set_bit(RAMROD_RETRY, &func_params.ramrod_flags);
+
 	bnx2x_dcbx_fw_struct(bp, tx_params);
 
 	DP(BNX2X_MSG_DCB, "START TRAFFIC\n");
-	return bnx2x_func_state_change(bp, &func_params);
+
+	rc = bnx2x_func_state_change(bp, &func_params);
+	if (rc) {
+		BNX2X_ERR("Unable to resume traffic after HW configuration\n");
+		bnx2x_panic();
+	}
+
+	return rc;
 }
 
 static void bnx2x_dcbx_2cos_limit_update_ets_config(struct bnx2x *bp)
@@ -744,7 +764,9 @@ void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state)
 			if (IS_MF(bp))
 				bnx2x_link_sync_notify(bp);
 
-			bnx2x_dcbx_stop_hw_tx(bp);
+			set_bit(BNX2X_SP_RTNL_TX_STOP, &bp->sp_rtnl_state);
+
+			schedule_delayed_work(&bp->sp_rtnl_task, 0);
 
 			return;
 		}
@@ -753,7 +775,13 @@ void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state)
 		bnx2x_pfc_set_pfc(bp);
 
 		bnx2x_dcbx_update_ets_params(bp);
-		bnx2x_dcbx_resume_hw_tx(bp);
+
+		/* ets may affect cmng configuration: reinit it in hw */
+		bnx2x_set_local_cmng(bp);
+
+		set_bit(BNX2X_SP_RTNL_TX_RESUME, &bp->sp_rtnl_state);
+
+		schedule_delayed_work(&bp->sp_rtnl_task, 0);
 
 		return;
 	case BNX2X_DCBX_STATE_TX_RELEASED:
@@ -2363,21 +2391,24 @@ static u8 bnx2x_dcbnl_get_featcfg(struct net_device *netdev, int featid,
 		case DCB_FEATCFG_ATTR_PG:
 			if (bp->dcbx_local_feat.ets.enabled)
 				*flags |= DCB_FEATCFG_ENABLE;
-			if (bp->dcbx_error & DCBX_LOCAL_ETS_ERROR)
+			if (bp->dcbx_error & (DCBX_LOCAL_ETS_ERROR |
+					      DCBX_REMOTE_MIB_ERROR))
 				*flags |= DCB_FEATCFG_ERROR;
 			break;
 		case DCB_FEATCFG_ATTR_PFC:
 			if (bp->dcbx_local_feat.pfc.enabled)
 				*flags |= DCB_FEATCFG_ENABLE;
 			if (bp->dcbx_error & (DCBX_LOCAL_PFC_ERROR |
-			    DCBX_LOCAL_PFC_MISMATCH))
+					      DCBX_LOCAL_PFC_MISMATCH |
+					      DCBX_REMOTE_MIB_ERROR))
 				*flags |= DCB_FEATCFG_ERROR;
 			break;
 		case DCB_FEATCFG_ATTR_APP:
 			if (bp->dcbx_local_feat.app.enabled)
 				*flags |= DCB_FEATCFG_ENABLE;
 			if (bp->dcbx_error & (DCBX_LOCAL_APP_ERROR |
-			    DCBX_LOCAL_APP_MISMATCH))
+					      DCBX_LOCAL_APP_MISMATCH |
+					      DCBX_REMOTE_MIB_ERROR))
 				*flags |= DCB_FEATCFG_ERROR;
 			break;
 		default:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
index 125bd1b6586f..804b8f64463e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
@@ -199,4 +199,7 @@ extern const struct dcbnl_rtnl_ops bnx2x_dcbnl_ops;
 int bnx2x_dcbnl_update_applist(struct bnx2x *bp, bool delall);
 #endif /* BCM_DCBNL */
 
+int bnx2x_dcbx_stop_hw_tx(struct bnx2x *bp);
+int bnx2x_dcbx_resume_hw_tx(struct bnx2x *bp);
+
 #endif /* BNX2X_DCB_H */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index 5018e52ae2ad..32767f6aa33f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -1300,6 +1300,9 @@ struct drv_func_mb {
 
 	#define DRV_MSG_CODE_EEE_RESULTS_ACK            0xda000000
 
+	#define DRV_MSG_CODE_RMMOD                      0xdb000000
+	#define REQ_BC_VER_4_RMMOD_CMD                  0x0007080f
+
 	#define DRV_MSG_CODE_SET_MF_BW                  0xe0000000
 	#define REQ_BC_VER_4_SET_MF_BW                  0x00060202
 	#define DRV_MSG_CODE_SET_MF_BW_ACK              0xe1000000
@@ -1372,6 +1375,8 @@ struct drv_func_mb {
 
 	#define FW_MSG_CODE_EEE_RESULS_ACK              0xda100000
 
+	#define FW_MSG_CODE_RMMOD_ACK                   0xdb100000
+
 	#define FW_MSG_CODE_SET_MF_BW_SENT              0xe0000000
 	#define FW_MSG_CODE_SET_MF_BW_DONE              0xe1000000
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index e5da07858a2f..8bdc8b973007 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -2261,6 +2261,23 @@ static void bnx2x_set_requested_fc(struct bnx2x *bp)
 		bp->link_params.req_fc_auto_adv = BNX2X_FLOW_CTRL_BOTH;
 }
 
+static void bnx2x_init_dropless_fc(struct bnx2x *bp)
+{
+	u32 pause_enabled = 0;
+
+	if (!CHIP_IS_E1(bp) && bp->dropless_fc && bp->link_vars.link_up) {
+		if (bp->link_vars.flow_ctrl & BNX2X_FLOW_CTRL_TX)
+			pause_enabled = 1;
+
+		REG_WR(bp, BAR_USTRORM_INTMEM +
+			   USTORM_ETH_PAUSE_ENABLED_OFFSET(BP_PORT(bp)),
+		       pause_enabled);
+	}
+
+	DP(NETIF_MSG_IFUP | NETIF_MSG_LINK, "dropless_fc is %s\n",
+	   pause_enabled ? "enabled" : "disabled");
+}
+
 int bnx2x_initial_phy_init(struct bnx2x *bp, int load_mode)
 {
 	int rc, cfx_idx = bnx2x_get_link_cfg_idx(bp);
@@ -2294,6 +2311,8 @@ int bnx2x_initial_phy_init(struct bnx2x *bp, int load_mode)
 
 		bnx2x_release_phy_lock(bp);
 
+		bnx2x_init_dropless_fc(bp);
+
 		bnx2x_calc_fc_adv(bp);
 
 		if (bp->link_vars.link_up) {
@@ -2315,6 +2334,8 @@ void bnx2x_link_set(struct bnx2x *bp)
 		bnx2x_phy_init(&bp->link_params, &bp->link_vars);
 		bnx2x_release_phy_lock(bp);
 
+		bnx2x_init_dropless_fc(bp);
+
 		bnx2x_calc_fc_adv(bp);
 	} else
 		BNX2X_ERR("Bootcode is missing - can not set link\n");
@@ -2476,7 +2497,7 @@ static void bnx2x_cmng_fns_init(struct bnx2x *bp, u8 read_cfg, u8 cmng_type)
 
 	input.port_rate = bp->link_vars.line_speed;
 
-	if (cmng_type == CMNG_FNS_MINMAX) {
+	if (cmng_type == CMNG_FNS_MINMAX && input.port_rate) {
 		int vn;
 
 		/* read mf conf from shmem */
@@ -2533,6 +2554,21 @@ static void storm_memset_cmng(struct bnx2x *bp,
 	}
 }
 
+/* init cmng mode in HW according to local configuration */
+void bnx2x_set_local_cmng(struct bnx2x *bp)
+{
+	int cmng_fns = bnx2x_get_cmng_fns_mode(bp);
+
+	if (cmng_fns != CMNG_FNS_NONE) {
+		bnx2x_cmng_fns_init(bp, false, cmng_fns);
+		storm_memset_cmng(bp, &bp->cmng, BP_PORT(bp));
+	} else {
+		/* rate shaping and fairness are disabled */
+		DP(NETIF_MSG_IFUP,
+		   "single function mode without fairness\n");
+	}
+}
+
 /* This function is called upon link interrupt */
 static void bnx2x_link_attn(struct bnx2x *bp)
 {
@@ -2541,20 +2577,9 @@ static void bnx2x_link_attn(struct bnx2x *bp)
 
 	bnx2x_link_update(&bp->link_params, &bp->link_vars);
 
-	if (bp->link_vars.link_up) {
+	bnx2x_init_dropless_fc(bp);
 
-		/* dropless flow control */
-		if (!CHIP_IS_E1(bp) && bp->dropless_fc) {
-			int port = BP_PORT(bp);
-			u32 pause_enabled = 0;
-
-			if (bp->link_vars.flow_ctrl & BNX2X_FLOW_CTRL_TX)
-				pause_enabled = 1;
-
-			REG_WR(bp, BAR_USTRORM_INTMEM +
-			       USTORM_ETH_PAUSE_ENABLED_OFFSET(port),
-			       pause_enabled);
-		}
+	if (bp->link_vars.link_up) {
 
 		if (bp->link_vars.mac_type != MAC_TYPE_EMAC) {
 			struct host_port_stats *pstats;
@@ -2568,17 +2593,8 @@ static void bnx2x_link_attn(struct bnx2x *bp)
 			bnx2x_stats_handle(bp, STATS_EVENT_LINK_UP);
 	}
 
-	if (bp->link_vars.link_up && bp->link_vars.line_speed) {
-		int cmng_fns = bnx2x_get_cmng_fns_mode(bp);
-
-		if (cmng_fns != CMNG_FNS_NONE) {
-			bnx2x_cmng_fns_init(bp, false, cmng_fns);
-			storm_memset_cmng(bp, &bp->cmng, BP_PORT(bp));
-		} else
-			/* rate shaping and fairness are disabled */
-			DP(NETIF_MSG_IFUP,
-			   "single function mode without fairness\n");
-	}
+	if (bp->link_vars.link_up && bp->link_vars.line_speed)
+		bnx2x_set_local_cmng(bp);
 
 	__bnx2x_link_report(bp);
 
@@ -9639,6 +9655,12 @@ sp_rtnl_not_reset:
 			       &bp->sp_rtnl_state))
 		bnx2x_pf_set_vfs_vlan(bp);
 
+	if (test_and_clear_bit(BNX2X_SP_RTNL_TX_STOP, &bp->sp_rtnl_state))
+		bnx2x_dcbx_stop_hw_tx(bp);
+
+	if (test_and_clear_bit(BNX2X_SP_RTNL_TX_RESUME, &bp->sp_rtnl_state))
+		bnx2x_dcbx_resume_hw_tx(bp);
+
 	/* work which needs rtnl lock not-taken (as it takes the lock itself and
 	 * can be called from other contexts as well)
 	 */
@@ -10362,6 +10384,10 @@ static void bnx2x_get_common_hwinfo(struct bnx2x *bp)
 
 	bp->flags |= (val >= REQ_BC_VER_4_DCBX_ADMIN_MSG_NON_PMF) ?
 			BC_SUPPORTS_DCBX_MSG_NON_PMF : 0;
+
+	bp->flags |= (val >= REQ_BC_VER_4_RMMOD_CMD) ?
+			BC_SUPPORTS_RMMOD_CMD : 0;
+
 	boot_mode = SHMEM_RD(bp,
 			dev_info.port_feature_config[BP_PORT(bp)].mba_config) &
 			PORT_FEATURE_MBA_BOOT_AGENT_TYPE_MASK;
@@ -11137,6 +11163,9 @@ static bool bnx2x_get_dropless_info(struct bnx2x *bp)
 	int tmp;
 	u32 cfg;
 
+	if (IS_VF(bp))
+		return 0;
+
 	if (IS_MF(bp) && !CHIP_IS_E1x(bp)) {
 		/* Take function: tmp = func */
 		tmp = BP_ABS_FUNC(bp);
@@ -11524,6 +11553,7 @@ static int bnx2x_init_bp(struct bnx2x *bp)
 	mutex_init(&bp->port.phy_mutex);
 	mutex_init(&bp->fw_mb_mutex);
 	spin_lock_init(&bp->stats_lock);
+	sema_init(&bp->stats_sema, 1);
 
 	INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task);
 	INIT_DELAYED_WORK(&bp->sp_rtnl_task, bnx2x_sp_rtnl_task);
@@ -12026,7 +12056,7 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_fcoe_get_wwn	= bnx2x_fcoe_get_wwn,
 #endif
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= bnx2x_low_latency_recv,
 #endif
 };
@@ -12817,13 +12847,17 @@ static void __bnx2x_remove(struct pci_dev *pdev,
 	bnx2x_dcbnl_update_applist(bp, true);
 #endif
 
+	if (IS_PF(bp) &&
+	    !BP_NOMCP(bp) &&
+	    (bp->flags & BC_SUPPORTS_RMMOD_CMD))
+		bnx2x_fw_command(bp, DRV_MSG_CODE_RMMOD, 0);
+
 	/* Close the interface - either directly or implicitly */
 	if (remove_netdev) {
 		unregister_netdev(dev);
 	} else {
 		rtnl_lock();
-		if (netif_running(dev))
-			bnx2x_close(dev);
+		dev_close(dev);
 		rtnl_unlock();
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 95861efb5051..ad83f4b48777 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1747,11 +1747,8 @@ void bnx2x_iov_init_dq(struct bnx2x *bp)
 
 void bnx2x_iov_init_dmae(struct bnx2x *bp)
 {
-	DP(BNX2X_MSG_IOV, "SRIOV is %s\n", IS_SRIOV(bp) ? "ON" : "OFF");
-	if (!IS_SRIOV(bp))
-		return;
-
-	REG_WR(bp, DMAE_REG_BACKWARD_COMP_EN, 0);
+	if (pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
+		REG_WR(bp, DMAE_REG_BACKWARD_COMP_EN, 0);
 }
 
 static int bnx2x_vf_bus(struct bnx2x *bp, int vfid)
@@ -3084,8 +3081,9 @@ void bnx2x_disable_sriov(struct bnx2x *bp)
 	pci_disable_sriov(bp->pdev);
 }
 
-static int bnx2x_vf_ndo_sanity(struct bnx2x *bp, int vfidx,
-			       struct bnx2x_virtf *vf)
+static int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx,
+			     struct bnx2x_virtf **vf,
+			     struct pf_vf_bulletin_content **bulletin)
 {
 	if (bp->state != BNX2X_STATE_OPEN) {
 		BNX2X_ERR("vf ndo called though PF is down\n");
@@ -3103,12 +3101,22 @@ static int bnx2x_vf_ndo_sanity(struct bnx2x *bp, int vfidx,
 		return -EINVAL;
 	}
 
-	if (!vf) {
+	/* init members */
+	*vf = BP_VF(bp, vfidx);
+	*bulletin = BP_VF_BULLETIN(bp, vfidx);
+
+	if (!*vf) {
 		BNX2X_ERR("vf ndo called but vf was null. vfidx was %d\n",
 			  vfidx);
 		return -EINVAL;
 	}
 
+	if (!*bulletin) {
+		BNX2X_ERR("vf ndo called but Bulletin Board struct is null. vfidx was %d\n",
+			  vfidx);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -3116,17 +3124,19 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx,
 			struct ifla_vf_info *ivi)
 {
 	struct bnx2x *bp = netdev_priv(dev);
-	struct bnx2x_virtf *vf = BP_VF(bp, vfidx);
-	struct bnx2x_vlan_mac_obj *mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
-	struct bnx2x_vlan_mac_obj *vlan_obj = &bnx2x_vfq(vf, 0, vlan_obj);
-	struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vfidx);
+	struct bnx2x_virtf *vf = NULL;
+	struct pf_vf_bulletin_content *bulletin = NULL;
+	struct bnx2x_vlan_mac_obj *mac_obj;
+	struct bnx2x_vlan_mac_obj *vlan_obj;
 	int rc;
 
-	/* sanity */
-	rc = bnx2x_vf_ndo_sanity(bp, vfidx, vf);
+	/* sanity and init */
+	rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
 	if (rc)
 		return rc;
-	if (!mac_obj || !vlan_obj || !bulletin) {
+	mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
+	vlan_obj = &bnx2x_vfq(vf, 0, vlan_obj);
+	if (!mac_obj || !vlan_obj) {
 		BNX2X_ERR("VF partially initialized\n");
 		return -EINVAL;
 	}
@@ -3183,11 +3193,11 @@ int bnx2x_set_vf_mac(struct net_device *dev, int vfidx, u8 *mac)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	int rc, q_logical_state;
-	struct bnx2x_virtf *vf = BP_VF(bp, vfidx);
-	struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vfidx);
+	struct bnx2x_virtf *vf = NULL;
+	struct pf_vf_bulletin_content *bulletin = NULL;
 
-	/* sanity */
-	rc = bnx2x_vf_ndo_sanity(bp, vfidx, vf);
+	/* sanity and init */
+	rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
 	if (rc)
 		return rc;
 	if (!is_valid_ether_addr(mac)) {
@@ -3249,11 +3259,11 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	int rc, q_logical_state;
-	struct bnx2x_virtf *vf = BP_VF(bp, vfidx);
-	struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vfidx);
+	struct bnx2x_virtf *vf = NULL;
+	struct pf_vf_bulletin_content *bulletin = NULL;
 
-	/* sanity */
-	rc = bnx2x_vf_ndo_sanity(bp, vfidx, vf);
+	/* sanity and init */
+	rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
 	if (rc)
 		return rc;
 
@@ -3463,7 +3473,7 @@ int bnx2x_vf_pci_alloc(struct bnx2x *bp)
 alloc_mem_err:
 	BNX2X_PCI_FREE(bp->vf2pf_mbox, bp->vf2pf_mbox_mapping,
 		       sizeof(struct bnx2x_vf_mbx_msg));
-	BNX2X_PCI_FREE(bp->vf2pf_mbox, bp->vf2pf_mbox_mapping,
+	BNX2X_PCI_FREE(bp->vf2pf_mbox, bp->pf2vf_bulletin_mapping,
 		       sizeof(union pf_vf_bulletin));
 	return -ENOMEM;
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 98366abd02bd..d63d1327b051 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -221,7 +221,8 @@ static int bnx2x_stats_comp(struct bnx2x *bp)
  * Statistics service functions
  */
 
-static void bnx2x_stats_pmf_update(struct bnx2x *bp)
+/* should be called under stats_sema */
+static void __bnx2x_stats_pmf_update(struct bnx2x *bp)
 {
 	struct dmae_command *dmae;
 	u32 opcode;
@@ -518,7 +519,8 @@ static void bnx2x_func_stats_init(struct bnx2x *bp)
 	*stats_comp = 0;
 }
 
-static void bnx2x_stats_start(struct bnx2x *bp)
+/* should be called under stats_sema */
+static void __bnx2x_stats_start(struct bnx2x *bp)
 {
 	/* vfs travel through here as part of the statistics FSM, but no action
 	 * is required
@@ -534,13 +536,34 @@ static void bnx2x_stats_start(struct bnx2x *bp)
 
 	bnx2x_hw_stats_post(bp);
 	bnx2x_storm_stats_post(bp);
+
+	bp->stats_started = true;
+}
+
+static void bnx2x_stats_start(struct bnx2x *bp)
+{
+	if (down_timeout(&bp->stats_sema, HZ/10))
+		BNX2X_ERR("Unable to acquire stats lock\n");
+	__bnx2x_stats_start(bp);
+	up(&bp->stats_sema);
 }
 
 static void bnx2x_stats_pmf_start(struct bnx2x *bp)
 {
+	if (down_timeout(&bp->stats_sema, HZ/10))
+		BNX2X_ERR("Unable to acquire stats lock\n");
 	bnx2x_stats_comp(bp);
-	bnx2x_stats_pmf_update(bp);
-	bnx2x_stats_start(bp);
+	__bnx2x_stats_pmf_update(bp);
+	__bnx2x_stats_start(bp);
+	up(&bp->stats_sema);
+}
+
+static void bnx2x_stats_pmf_update(struct bnx2x *bp)
+{
+	if (down_timeout(&bp->stats_sema, HZ/10))
+		BNX2X_ERR("Unable to acquire stats lock\n");
+	__bnx2x_stats_pmf_update(bp);
+	up(&bp->stats_sema);
 }
 
 static void bnx2x_stats_restart(struct bnx2x *bp)
@@ -550,8 +573,11 @@ static void bnx2x_stats_restart(struct bnx2x *bp)
 	 */
 	if (IS_VF(bp))
 		return;
+	if (down_timeout(&bp->stats_sema, HZ/10))
+		BNX2X_ERR("Unable to acquire stats lock\n");
 	bnx2x_stats_comp(bp);
-	bnx2x_stats_start(bp);
+	__bnx2x_stats_start(bp);
+	up(&bp->stats_sema);
 }
 
 static void bnx2x_bmac_stats_update(struct bnx2x *bp)
@@ -888,9 +914,7 @@ static int bnx2x_storm_stats_validate_counters(struct bnx2x *bp)
 	/* Make sure we use the value of the counter
 	 * used for sending the last stats ramrod.
 	 */
-	spin_lock_bh(&bp->stats_lock);
 	cur_stats_counter = bp->stats_counter - 1;
-	spin_unlock_bh(&bp->stats_lock);
 
 	/* are storm stats valid? */
 	if (le16_to_cpu(counters->xstats_counter) != cur_stats_counter) {
@@ -1227,12 +1251,18 @@ static void bnx2x_stats_update(struct bnx2x *bp)
 {
 	u32 *stats_comp = bnx2x_sp(bp, stats_comp);
 
-	if (bnx2x_edebug_stats_stopped(bp))
+	/* we run update from timer context, so give up
+	 * if somebody is in the middle of transition
+	 */
+	if (down_trylock(&bp->stats_sema))
 		return;
 
+	if (bnx2x_edebug_stats_stopped(bp) || !bp->stats_started)
+		goto out;
+
 	if (IS_PF(bp)) {
 		if (*stats_comp != DMAE_COMP_VAL)
-			return;
+			goto out;
 
 		if (bp->port.pmf)
 			bnx2x_hw_stats_update(bp);
@@ -1242,7 +1272,7 @@ static void bnx2x_stats_update(struct bnx2x *bp)
 				BNX2X_ERR("storm stats were not updated for 3 times\n");
 				bnx2x_panic();
 			}
-			return;
+			goto out;
 		}
 	} else {
 		/* vf doesn't collect HW statistics, and doesn't get completions
@@ -1256,7 +1286,7 @@ static void bnx2x_stats_update(struct bnx2x *bp)
 
 	/* vf is done */
 	if (IS_VF(bp))
-		return;
+		goto out;
 
 	if (netif_msg_timer(bp)) {
 		struct bnx2x_eth_stats *estats = &bp->eth_stats;
@@ -1267,6 +1297,9 @@ static void bnx2x_stats_update(struct bnx2x *bp)
 
 	bnx2x_hw_stats_post(bp);
 	bnx2x_storm_stats_post(bp);
+
+out:
+	up(&bp->stats_sema);
 }
 
 static void bnx2x_port_stats_stop(struct bnx2x *bp)
@@ -1332,6 +1365,11 @@ static void bnx2x_stats_stop(struct bnx2x *bp)
 {
 	int update = 0;
 
+	if (down_timeout(&bp->stats_sema, HZ/10))
+		BNX2X_ERR("Unable to acquire stats lock\n");
+
+	bp->stats_started = false;
+
 	bnx2x_stats_comp(bp);
 
 	if (bp->port.pmf)
@@ -1348,6 +1386,8 @@ static void bnx2x_stats_stop(struct bnx2x *bp)
 		bnx2x_hw_stats_post(bp);
 		bnx2x_stats_comp(bp);
 	}
+
+	up(&bp->stats_sema);
 }
 
 static void bnx2x_stats_do_nothing(struct bnx2x *bp)
@@ -1376,15 +1416,17 @@ static const struct {
 void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event)
 {
 	enum bnx2x_stats_state state;
+	void (*action)(struct bnx2x *bp);
 	if (unlikely(bp->panic))
 		return;
 
 	spin_lock_bh(&bp->stats_lock);
 	state = bp->stats_state;
 	bp->stats_state = bnx2x_stats_stm[state][event].next_state;
+	action = bnx2x_stats_stm[state][event].action;
 	spin_unlock_bh(&bp->stats_lock);
 
-	bnx2x_stats_stm[state][event].action(bp);
+	action(bp);
 
 	if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
 		DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index d964f302ac94..0da2214ef1b9 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -17625,7 +17625,8 @@ err_out_free_res:
 	pci_release_regions(pdev);
 
 err_out_disable_pdev:
-	pci_disable_device(pdev);
+	if (pci_is_enabled(pdev))
+		pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 	return err;
 }
@@ -17773,7 +17774,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	if (!netif_running(netdev))
+	/* We probably don't have netdev yet */
+	if (!netdev || !netif_running(netdev))
 		goto done;
 
 	tg3_phy_stop(tp);
@@ -17794,8 +17796,10 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 done:
 	if (state == pci_channel_io_perm_failure) {
-		tg3_napi_enable(tp);
-		dev_close(netdev);
+		if (netdev) {
+			tg3_napi_enable(tp);
+			dev_close(netdev);
+		}
 		err = PCI_ERS_RESULT_DISCONNECT;
 	} else {
 		pci_disable_device(pdev);
@@ -17825,7 +17829,8 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 	rtnl_lock();
 
 	if (pci_enable_device(pdev)) {
-		netdev_err(netdev, "Cannot re-enable PCI device after reset.\n");
+		dev_err(&pdev->dev,
+			"Cannot re-enable PCI device after reset.\n");
 		goto done;
 	}
 
@@ -17833,7 +17838,7 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 	pci_restore_state(pdev);
 	pci_save_state(pdev);
 
-	if (!netif_running(netdev)) {
+	if (!netdev || !netif_running(netdev)) {
 		rc = PCI_ERS_RESULT_RECOVERED;
 		goto done;
 	}
@@ -17845,7 +17850,7 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 	rc = PCI_ERS_RESULT_RECOVERED;
 
 done:
-	if (rc != PCI_ERS_RESULT_RECOVERED && netif_running(netdev)) {
+	if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) {
 		tg3_napi_enable(tp);
 		dev_close(netdev);
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 687ec4a8bb48..9c89dc8fe105 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -455,11 +455,6 @@ static int alloc_pg_chunk(struct adapter *adapter, struct sge_fl *q,
 		q->pg_chunk.offset = 0;
 		mapping = pci_map_page(adapter->pdev, q->pg_chunk.page,
 				       0, q->alloc_size, PCI_DMA_FROMDEVICE);
-		if (unlikely(pci_dma_mapping_error(adapter->pdev, mapping))) {
-			__free_pages(q->pg_chunk.page, order);
-			q->pg_chunk.page = NULL;
-			return -EIO;
-		}
 		q->pg_chunk.mapping = mapping;
 	}
 	sd->pg_chunk = q->pg_chunk;
@@ -954,75 +949,40 @@ static inline unsigned int calc_tx_descs(const struct sk_buff *skb)
 	return flits_to_desc(flits);
 }
 
-
-/*	map_skb - map a packet main body and its page fragments
- *	@pdev: the PCI device
- *	@skb: the packet
- *	@addr: placeholder to save the mapped addresses
- *
- *	map the main body of an sk_buff and its page fragments, if any.
- */
-static int map_skb(struct pci_dev *pdev, const struct sk_buff *skb,
-		   dma_addr_t *addr)
-{
-	const skb_frag_t *fp, *end;
-	const struct skb_shared_info *si;
-
-	*addr = pci_map_single(pdev, skb->data, skb_headlen(skb),
-			       PCI_DMA_TODEVICE);
-	if (pci_dma_mapping_error(pdev, *addr))
-		goto out_err;
-
-	si = skb_shinfo(skb);
-	end = &si->frags[si->nr_frags];
-
-	for (fp = si->frags; fp < end; fp++) {
-		*++addr = skb_frag_dma_map(&pdev->dev, fp, 0, skb_frag_size(fp),
-					   DMA_TO_DEVICE);
-		if (pci_dma_mapping_error(pdev, *addr))
-			goto unwind;
-	}
-	return 0;
-
-unwind:
-	while (fp-- > si->frags)
-		dma_unmap_page(&pdev->dev, *--addr, skb_frag_size(fp),
-			       DMA_TO_DEVICE);
-
-	pci_unmap_single(pdev, addr[-1], skb_headlen(skb), PCI_DMA_TODEVICE);
-out_err:
-	return -ENOMEM;
-}
-
 /**
- *	write_sgl - populate a scatter/gather list for a packet
+ *	make_sgl - populate a scatter/gather list for a packet
  *	@skb: the packet
  *	@sgp: the SGL to populate
  *	@start: start address of skb main body data to include in the SGL
  *	@len: length of skb main body data to include in the SGL
- *	@addr: the list of the mapped addresses
+ *	@pdev: the PCI device
  *
- *	Copies the scatter/gather list for the buffers that make up a packet
+ *	Generates a scatter/gather list for the buffers that make up a packet
  *	and returns the SGL size in 8-byte words.  The caller must size the SGL
  *	appropriately.
  */
-static inline unsigned int write_sgl(const struct sk_buff *skb,
+static inline unsigned int make_sgl(const struct sk_buff *skb,
 				    struct sg_ent *sgp, unsigned char *start,
-				    unsigned int len, const dma_addr_t *addr)
+				    unsigned int len, struct pci_dev *pdev)
 {
-	unsigned int i, j = 0, k = 0, nfrags;
+	dma_addr_t mapping;
+	unsigned int i, j = 0, nfrags;
 
 	if (len) {
+		mapping = pci_map_single(pdev, start, len, PCI_DMA_TODEVICE);
 		sgp->len[0] = cpu_to_be32(len);
-		sgp->addr[j++] = cpu_to_be64(addr[k++]);
+		sgp->addr[0] = cpu_to_be64(mapping);
+		j = 1;
 	}
 
 	nfrags = skb_shinfo(skb)->nr_frags;
 	for (i = 0; i < nfrags; i++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
+		mapping = skb_frag_dma_map(&pdev->dev, frag, 0, skb_frag_size(frag),
+					   DMA_TO_DEVICE);
 		sgp->len[j] = cpu_to_be32(skb_frag_size(frag));
-		sgp->addr[j] = cpu_to_be64(addr[k++]);
+		sgp->addr[j] = cpu_to_be64(mapping);
 		j ^= 1;
 		if (j == 0)
 			++sgp;
@@ -1178,7 +1138,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 			    const struct port_info *pi,
 			    unsigned int pidx, unsigned int gen,
 			    struct sge_txq *q, unsigned int ndesc,
-			    unsigned int compl, const dma_addr_t *addr)
+			    unsigned int compl)
 {
 	unsigned int flits, sgl_flits, cntrl, tso_info;
 	struct sg_ent *sgp, sgl[MAX_SKB_FRAGS / 2 + 1];
@@ -1236,7 +1196,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 	}
 
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
-	sgl_flits = write_sgl(skb, sgp, skb->data, skb_headlen(skb), addr);
+	sgl_flits = make_sgl(skb, sgp, skb->data, skb_headlen(skb), adap->pdev);
 
 	write_wr_hdr_sgl(ndesc, skb, d, pidx, q, sgl, flits, sgl_flits, gen,
 			 htonl(V_WR_OP(FW_WROPCODE_TUNNEL_TX_PKT) | compl),
@@ -1267,7 +1227,6 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct netdev_queue *txq;
 	struct sge_qset *qs;
 	struct sge_txq *q;
-	dma_addr_t addr[MAX_SKB_FRAGS + 1];
 
 	/*
 	 * The chip min packet length is 9 octets but play safe and reject
@@ -1296,11 +1255,6 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
-	if (unlikely(map_skb(adap->pdev, skb, addr) < 0)) {
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
 	q->in_use += ndesc;
 	if (unlikely(credits - ndesc < q->stop_thres)) {
 		t3_stop_tx_queue(txq, qs, q);
@@ -1358,7 +1312,7 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (likely(!skb_shared(skb)))
 		skb_orphan(skb);
 
-	write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl, addr);
+	write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl);
 	check_ring_tx_db(adap, q);
 	return NETDEV_TX_OK;
 }
@@ -1623,8 +1577,7 @@ static void setup_deferred_unmapping(struct sk_buff *skb, struct pci_dev *pdev,
  */
 static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
 			  struct sge_txq *q, unsigned int pidx,
-			  unsigned int gen, unsigned int ndesc,
-			  const dma_addr_t *addr)
+			  unsigned int gen, unsigned int ndesc)
 {
 	unsigned int sgl_flits, flits;
 	struct work_request_hdr *from;
@@ -1645,9 +1598,9 @@ static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
 
 	flits = skb_transport_offset(skb) / 8;
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
-	sgl_flits = write_sgl(skb, sgp, skb_transport_header(skb),
-			     skb_tail_pointer(skb) -
-			     skb_transport_header(skb), addr);
+	sgl_flits = make_sgl(skb, sgp, skb_transport_header(skb),
+			     skb->tail - skb->transport_header,
+			     adap->pdev);
 	if (need_skb_unmap()) {
 		setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits);
 		skb->destructor = deferred_unmap_destructor;
@@ -1705,11 +1658,6 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 		goto again;
 	}
 
-	if (map_skb(adap->pdev, skb, (dma_addr_t *)skb->head)) {
-		spin_unlock(&q->lock);
-		return NET_XMIT_SUCCESS;
-	}
-
 	gen = q->gen;
 	q->in_use += ndesc;
 	pidx = q->pidx;
@@ -1720,7 +1668,7 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 	}
 	spin_unlock(&q->lock);
 
-	write_ofld_wr(adap, skb, q, pidx, gen, ndesc, (dma_addr_t *)skb->head);
+	write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
 	check_ring_tx_db(adap, q);
 	return NET_XMIT_SUCCESS;
 }
@@ -1738,7 +1686,6 @@ static void restart_offloadq(unsigned long data)
 	struct sge_txq *q = &qs->txq[TXQ_OFLD];
 	const struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
-	unsigned int written = 0;
 
 	spin_lock(&q->lock);
 again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
@@ -1758,14 +1705,10 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 			break;
 		}
 
-		if (map_skb(adap->pdev, skb, (dma_addr_t *)skb->head))
-			break;
-
 		gen = q->gen;
 		q->in_use += ndesc;
 		pidx = q->pidx;
 		q->pidx += ndesc;
-		written += ndesc;
 		if (q->pidx >= q->size) {
 			q->pidx -= q->size;
 			q->gen ^= 1;
@@ -1773,8 +1716,7 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 		__skb_unlink(skb, &q->sendq);
 		spin_unlock(&q->lock);
 
-		write_ofld_wr(adap, skb, q, pidx, gen, ndesc,
-			     (dma_addr_t *)skb->head);
+		write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
 		spin_lock(&q->lock);
 	}
 	spin_unlock(&q->lock);
@@ -1784,9 +1726,8 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 	set_bit(TXQ_LAST_PKT_DB, &q->flags);
 #endif
 	wmb();
-	if (likely(written))
-		t3_write_reg(adap, A_SG_KDOORBELL,
-			     F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
+	t3_write_reg(adap, A_SG_KDOORBELL,
+		     F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
 }
 
 /**
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 6e6e0a117ee2..8ec5d74ad44d 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -3048,6 +3048,9 @@ int be_cmd_get_func_config(struct be_adapter *adapter)
 
 		adapter->max_event_queues = le16_to_cpu(desc->eq_count);
 		adapter->if_cap_flags = le32_to_cpu(desc->cap_flags);
+
+		/* Clear flags that driver is not interested in */
+		adapter->if_cap_flags &=  BE_IF_CAP_FLAGS_WANT;
 	}
 err:
 	mutex_unlock(&adapter->mbox_lock);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 5228d88c5a02..1b3b9e886412 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -563,6 +563,12 @@ enum be_if_flags {
 	BE_IF_FLAGS_MULTICAST = 0x1000
 };
 
+#define BE_IF_CAP_FLAGS_WANT (BE_IF_FLAGS_RSS | BE_IF_FLAGS_PROMISCUOUS |\
+			 BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_VLAN_PROMISCUOUS |\
+			 BE_IF_FLAGS_VLAN | BE_IF_FLAGS_MCAST_PROMISCUOUS |\
+			 BE_IF_FLAGS_PASS_L3L4_ERRORS | BE_IF_FLAGS_MULTICAST |\
+			 BE_IF_FLAGS_UNTAGGED)
+
 /* An RX interface is an object with one or more MAC addresses and
  * filtering capabilities. */
 struct be_cmd_req_if_create {
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 181edb522450..4559c35eea13 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2563,8 +2563,8 @@ static int be_close(struct net_device *netdev)
 	/* Wait for all pending tx completions to arrive so that
 	 * all tx skbs are freed.
 	 */
-	be_tx_compl_clean(adapter);
 	netif_tx_disable(netdev);
+	be_tx_compl_clean(adapter);
 
 	be_rx_qs_destroy(adapter);
 
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 2b0a0ea4f8e7..ae236009f1a8 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -259,6 +259,7 @@ struct bufdesc_ex {
 struct fec_enet_delayed_work {
 	struct delayed_work delay_work;
 	bool timeout;
+	bool trig_tx;
 };
 
 /* The FEC buffer descriptors track the ring buffers.  The rx_bd_base and
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d3ad5ea711d3..77ea0db0bbfc 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -93,6 +93,20 @@ static void set_multicast_list(struct net_device *ndev);
 #define FEC_QUIRK_HAS_CSUM		(1 << 5)
 /* Controller has hardware vlan support */
 #define FEC_QUIRK_HAS_VLAN		(1 << 6)
+/* ENET IP errata ERR006358
+ *
+ * If the ready bit in the transmit buffer descriptor (TxBD[R]) is previously
+ * detected as not set during a prior frame transmission, then the
+ * ENET_TDAR[TDAR] bit is cleared at a later time, even if additional TxBDs
+ * were added to the ring and the ENET_TDAR[TDAR] bit is set. This results in
+ * If the ready bit in the transmit buffer descriptor (TxBD[R]) is previously
+ * detected as not set during a prior frame transmission, then the
+ * ENET_TDAR[TDAR] bit is cleared at a later time, even if additional TxBDs
+ * were added to the ring and the ENET_TDAR[TDAR] bit is set. This results in
+ * frames not being transmitted until there is a 0-to-1 transition on
+ * ENET_TDAR[TDAR].
+ */
+#define FEC_QUIRK_ERR006358            (1 << 7)
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -112,7 +126,7 @@ static struct platform_device_id fec_devtype[] = {
 		.name = "imx6q-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN,
+				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358,
 	}, {
 		.name = "mvf600-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC,
@@ -275,16 +289,11 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	const struct platform_device_id *id_entry =
 				platform_get_device_id(fep->pdev);
-	struct bufdesc *bdp;
+	struct bufdesc *bdp, *bdp_pre;
 	void *bufaddr;
 	unsigned short	status;
 	unsigned int index;
 
-	if (!fep->link) {
-		/* Link is down or auto-negotiation is in progress. */
-		return NETDEV_TX_BUSY;
-	}
-
 	/* Fill in a Tx ring entry */
 	bdp = fep->cur_tx;
 
@@ -370,6 +379,15 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 				ebdp->cbd_esc |= BD_ENET_TX_PINS;
 		}
 	}
+
+	bdp_pre = fec_enet_get_prevdesc(bdp, fep->bufdesc_ex);
+	if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
+	    !(bdp_pre->cbd_sc & BD_ENET_TX_READY)) {
+		fep->delay_work.trig_tx = true;
+		schedule_delayed_work(&(fep->delay_work.delay_work),
+					msecs_to_jiffies(1));
+	}
+
 	/* If this was the last BD in the ring, start at the beginning again. */
 	if (status & BD_ENET_TX_WRAP)
 		bdp = fep->tx_bd_base;
@@ -689,6 +707,11 @@ static void fec_enet_work(struct work_struct *work)
 		fec_restart(fep->netdev, fep->full_duplex);
 		netif_wake_queue(fep->netdev);
 	}
+
+	if (fep->delay_work.trig_tx) {
+		fep->delay_work.trig_tx = false;
+		writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+	}
 }
 
 static void
@@ -2279,4 +2302,5 @@ static struct platform_driver fec_driver = {
 
 module_platform_driver(fec_driver);
 
+MODULE_ALIAS("platform:"DRIVER_NAME);
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 6a0c1b66ce54..c1d72c03cb59 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3739,9 +3739,8 @@ static void igb_set_rx_mode(struct net_device *netdev)
 	rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE | E1000_RCTL_VFE);
 
 	if (netdev->flags & IFF_PROMISC) {
-		u32 mrqc = rd32(E1000_MRQC);
 		/* retain VLAN HW filtering if in VT mode */
-		if (mrqc & E1000_MRQC_ENABLE_VMDQ)
+		if (adapter->vfs_allocated_count)
 			rctl |= E1000_RCTL_VFE;
 		rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
 		vmolr |= (E1000_VMOLR_ROPE | E1000_VMOLR_MPME);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 7be725cdfea8..a6494e5daffe 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -54,7 +54,7 @@
 
 #include <net/busy_poll.h>
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 #define LL_EXTENDED_STATS
 #endif
 /* common prefix used by pr_<> macros */
@@ -366,7 +366,7 @@ struct ixgbe_q_vector {
 	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[IFNAMSIZ + 9];
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int state;
 #define IXGBE_QV_STATE_IDLE        0
 #define IXGBE_QV_STATE_NAPI	   1    /* NAPI owns this QV */
@@ -377,12 +377,12 @@ struct ixgbe_q_vector {
 #define IXGBE_QV_YIELD (IXGBE_QV_STATE_NAPI_YIELD | IXGBE_QV_STATE_POLL_YIELD)
 #define IXGBE_QV_USER_PEND (IXGBE_QV_STATE_POLL | IXGBE_QV_STATE_POLL_YIELD)
 	spinlock_t lock;
-#endif  /* CONFIG_NET_LL_RX_POLL */
+#endif  /* CONFIG_NET_RX_BUSY_POLL */
 
 	/* for dynamic allocation of rings associated with this q_vector */
 	struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp;
 };
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector)
 {
 
@@ -462,7 +462,7 @@ static inline bool ixgbe_qv_ll_polling(struct ixgbe_q_vector *q_vector)
 	WARN_ON(!(q_vector->state & IXGBE_QV_LOCKED));
 	return q_vector->state & IXGBE_QV_USER_PEND;
 }
-#else /* CONFIG_NET_LL_RX_POLL */
+#else /* CONFIG_NET_RX_BUSY_POLL */
 static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector)
 {
 }
@@ -491,7 +491,7 @@ static inline bool ixgbe_qv_ll_polling(struct ixgbe_q_vector *q_vector)
 {
 	return false;
 }
-#endif /* CONFIG_NET_LL_RX_POLL */
+#endif /* CONFIG_NET_RX_BUSY_POLL */
 
 #ifdef CONFIG_IXGBE_HWMON
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
index ac780770863d..7a77f37a7cbc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
@@ -108,9 +108,8 @@ s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw,
 
 	/* Enable arbiter */
 	reg &= ~IXGBE_DPMCS_ARBDIS;
-	/* Enable DFP and Recycle mode */
-	reg |= (IXGBE_DPMCS_TDPAC | IXGBE_DPMCS_TRM);
 	reg |= IXGBE_DPMCS_TSOEF;
+
 	/* Configure Max TSO packet size 34KB including payload and headers */
 	reg |= (0x4 << IXGBE_DPMCS_MTSOS_SHIFT);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index bad8f14b1941..be4b1fb3d0d2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1998,7 +1998,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	return total_rx_packets;
 }
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 /* must be called with local_bh_disable()d */
 static int ixgbe_low_latency_recv(struct napi_struct *napi)
 {
@@ -2030,7 +2030,7 @@ static int ixgbe_low_latency_recv(struct napi_struct *napi)
 
 	return found;
 }
-#endif	/* CONFIG_NET_LL_RX_POLL */
+#endif	/* CONFIG_NET_RX_BUSY_POLL */
 
 /**
  * ixgbe_configure_msix - Configure MSI-X hardware
@@ -7227,7 +7227,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= ixgbe_netpoll,
 #endif
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= ixgbe_low_latency_recv,
 #endif
 #ifdef IXGBE_FCOE
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 712779fb12b7..b017818bccae 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -88,6 +88,8 @@
 #define      MVNETA_TX_IN_PRGRS                  BIT(1)
 #define      MVNETA_TX_FIFO_EMPTY                BIT(8)
 #define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
+#define MVNETA_SGMII_SERDES_CFG			 0x24A0
+#define      MVNETA_SGMII_SERDES_PROTO		 0x0cc7
 #define MVNETA_TYPE_PRIO                         0x24bc
 #define      MVNETA_FORCE_UNI                    BIT(21)
 #define MVNETA_TXQ_CMD_1                         0x24e4
@@ -655,6 +657,8 @@ static void mvneta_port_sgmii_config(struct mvneta_port *pp)
 	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
 	val |= MVNETA_GMAC2_PSC_ENABLE;
 	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+
+	mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
 }
 
 /* Start the Ethernet port RX and TX activity */
@@ -2728,28 +2732,24 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp = netdev_priv(dev);
 
-	pp->tx_done_timer.function = mvneta_tx_done_timer_callback;
-	init_timer(&pp->tx_done_timer);
-	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
-
 	pp->weight = MVNETA_RX_POLL_WEIGHT;
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
 
-	pp->base = of_iomap(dn, 0);
-	if (pp->base == NULL) {
-		err = -ENOMEM;
-		goto err_free_irq;
-	}
-
 	pp->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pp->clk)) {
 		err = PTR_ERR(pp->clk);
-		goto err_unmap;
+		goto err_free_irq;
 	}
 
 	clk_prepare_enable(pp->clk);
 
+	pp->base = of_iomap(dn, 0);
+	if (pp->base == NULL) {
+		err = -ENOMEM;
+		goto err_clk;
+	}
+
 	dt_mac_addr = of_get_mac_address(dn);
 	if (dt_mac_addr && is_valid_ether_addr(dt_mac_addr)) {
 		mac_from = "device tree";
@@ -2766,6 +2766,9 @@ static int mvneta_probe(struct platform_device *pdev)
 	}
 
 	pp->tx_done_timer.data = (unsigned long)dev;
+	pp->tx_done_timer.function = mvneta_tx_done_timer_callback;
+	init_timer(&pp->tx_done_timer);
+	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
 
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
@@ -2776,7 +2779,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	err = mvneta_init(pp, phy_addr);
 	if (err < 0) {
 		dev_err(&pdev->dev, "can't init eth hal\n");
-		goto err_clk;
+		goto err_unmap;
 	}
 	mvneta_port_power_up(pp, phy_mode);
 
@@ -2806,10 +2809,10 @@ static int mvneta_probe(struct platform_device *pdev)
 
 err_deinit:
 	mvneta_deinit(pp);
-err_clk:
-	clk_disable_unprepare(pp->clk);
 err_unmap:
 	iounmap(pp->base);
+err_clk:
+	clk_disable_unprepare(pp->clk);
 err_free_irq:
 	irq_dispose_mapping(dev->irq);
 err_free_netdev:
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index c896079728e1..ef94a591f9e5 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -931,17 +931,20 @@ static int skge_ring_alloc(struct skge_ring *ring, void *vaddr, u32 base)
 }
 
 /* Allocate and setup a new buffer for receiving */
-static void skge_rx_setup(struct skge_port *skge, struct skge_element *e,
-			  struct sk_buff *skb, unsigned int bufsize)
+static int skge_rx_setup(struct skge_port *skge, struct skge_element *e,
+			 struct sk_buff *skb, unsigned int bufsize)
 {
 	struct skge_rx_desc *rd = e->desc;
-	u64 map;
+	dma_addr_t map;
 
 	map = pci_map_single(skge->hw->pdev, skb->data, bufsize,
 			     PCI_DMA_FROMDEVICE);
 
-	rd->dma_lo = map;
-	rd->dma_hi = map >> 32;
+	if (pci_dma_mapping_error(skge->hw->pdev, map))
+		return -1;
+
+	rd->dma_lo = lower_32_bits(map);
+	rd->dma_hi = upper_32_bits(map);
 	e->skb = skb;
 	rd->csum1_start = ETH_HLEN;
 	rd->csum2_start = ETH_HLEN;
@@ -953,6 +956,7 @@ static void skge_rx_setup(struct skge_port *skge, struct skge_element *e,
 	rd->control = BMU_OWN | BMU_STF | BMU_IRQ_EOF | BMU_TCP_CHECK | bufsize;
 	dma_unmap_addr_set(e, mapaddr, map);
 	dma_unmap_len_set(e, maplen, bufsize);
+	return 0;
 }
 
 /* Resume receiving using existing skb,
@@ -1014,7 +1018,10 @@ static int skge_rx_fill(struct net_device *dev)
 			return -ENOMEM;
 
 		skb_reserve(skb, NET_IP_ALIGN);
-		skge_rx_setup(skge, e, skb, skge->rx_buf_size);
+		if (skge_rx_setup(skge, e, skb, skge->rx_buf_size) < 0) {
+			dev_kfree_skb(skb);
+			return -EIO;
+		}
 	} while ((e = e->next) != ring->start);
 
 	ring->to_clean = ring->start;
@@ -2544,7 +2551,7 @@ static int skge_up(struct net_device *dev)
 
 	BUG_ON(skge->dma & 7);
 
-	if ((u64)skge->dma >> 32 != ((u64) skge->dma + skge->mem_size) >> 32) {
+	if (upper_32_bits(skge->dma) != upper_32_bits(skge->dma + skge->mem_size)) {
 		dev_err(&hw->pdev->dev, "pci_alloc_consistent region crosses 4G boundary\n");
 		err = -EINVAL;
 		goto free_pci_mem;
@@ -2729,7 +2736,7 @@ static netdev_tx_t skge_xmit_frame(struct sk_buff *skb,
 	struct skge_tx_desc *td;
 	int i;
 	u32 control, len;
-	u64 map;
+	dma_addr_t map;
 
 	if (skb_padto(skb, ETH_ZLEN))
 		return NETDEV_TX_OK;
@@ -2743,11 +2750,14 @@ static netdev_tx_t skge_xmit_frame(struct sk_buff *skb,
 	e->skb = skb;
 	len = skb_headlen(skb);
 	map = pci_map_single(hw->pdev, skb->data, len, PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(hw->pdev, map))
+		goto mapping_error;
+
 	dma_unmap_addr_set(e, mapaddr, map);
 	dma_unmap_len_set(e, maplen, len);
 
-	td->dma_lo = map;
-	td->dma_hi = map >> 32;
+	td->dma_lo = lower_32_bits(map);
+	td->dma_hi = upper_32_bits(map);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		const int offset = skb_checksum_start_offset(skb);
@@ -2778,14 +2788,16 @@ static netdev_tx_t skge_xmit_frame(struct sk_buff *skb,
 
 			map = skb_frag_dma_map(&hw->pdev->dev, frag, 0,
 					       skb_frag_size(frag), DMA_TO_DEVICE);
+			if (dma_mapping_error(&hw->pdev->dev, map))
+				goto mapping_unwind;
 
 			e = e->next;
 			e->skb = skb;
 			tf = e->desc;
 			BUG_ON(tf->control & BMU_OWN);
 
-			tf->dma_lo = map;
-			tf->dma_hi = (u64) map >> 32;
+			tf->dma_lo = lower_32_bits(map);
+			tf->dma_hi = upper_32_bits(map);
 			dma_unmap_addr_set(e, mapaddr, map);
 			dma_unmap_len_set(e, maplen, skb_frag_size(frag));
 
@@ -2815,6 +2827,26 @@ static netdev_tx_t skge_xmit_frame(struct sk_buff *skb,
 	}
 
 	return NETDEV_TX_OK;
+
+mapping_unwind:
+	e = skge->tx_ring.to_use;
+	pci_unmap_single(hw->pdev,
+			 dma_unmap_addr(e, mapaddr),
+			 dma_unmap_len(e, maplen),
+			 PCI_DMA_TODEVICE);
+	while (i-- > 0) {
+		e = e->next;
+		pci_unmap_page(hw->pdev,
+			       dma_unmap_addr(e, mapaddr),
+			       dma_unmap_len(e, maplen),
+			       PCI_DMA_TODEVICE);
+	}
+
+mapping_error:
+	if (net_ratelimit())
+		dev_warn(&hw->pdev->dev, "%s: tx mapping error\n", dev->name);
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 
@@ -3045,11 +3077,13 @@ static struct sk_buff *skge_rx_get(struct net_device *dev,
 
 		pci_dma_sync_single_for_cpu(skge->hw->pdev,
 					    dma_unmap_addr(e, mapaddr),
-					    len, PCI_DMA_FROMDEVICE);
+					    dma_unmap_len(e, maplen),
+					    PCI_DMA_FROMDEVICE);
 		skb_copy_from_linear_data(e->skb, skb->data, len);
 		pci_dma_sync_single_for_device(skge->hw->pdev,
 					       dma_unmap_addr(e, mapaddr),
-					       len, PCI_DMA_FROMDEVICE);
+					       dma_unmap_len(e, maplen),
+					       PCI_DMA_FROMDEVICE);
 		skge_rx_reuse(e, skge->rx_buf_size);
 	} else {
 		struct sk_buff *nskb;
@@ -3058,13 +3092,17 @@ static struct sk_buff *skge_rx_get(struct net_device *dev,
 		if (!nskb)
 			goto resubmit;
 
+		if (skge_rx_setup(skge, e, nskb, skge->rx_buf_size) < 0) {
+			dev_kfree_skb(nskb);
+			goto resubmit;
+		}
+
 		pci_unmap_single(skge->hw->pdev,
 				 dma_unmap_addr(e, mapaddr),
 				 dma_unmap_len(e, maplen),
 				 PCI_DMA_FROMDEVICE);
 		skb = e->skb;
 		prefetch(skb->data);
-		skge_rx_setup(skge, e, nskb, skge->rx_buf_size);
 	}
 
 	skb_put(skb, len);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 727874f575ce..a28cd801a236 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -223,7 +223,7 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
 	case ETH_SS_STATS:
 		return (priv->stats_bitmap ? bit_count : NUM_ALL_STATS) +
 			(priv->tx_ring_num * 2) +
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 			(priv->rx_ring_num * 5);
 #else
 			(priv->rx_ring_num * 2);
@@ -276,7 +276,7 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		data[index++] = priv->rx_ring[i].packets;
 		data[index++] = priv->rx_ring[i].bytes;
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 		data[index++] = priv->rx_ring[i].yields;
 		data[index++] = priv->rx_ring[i].misses;
 		data[index++] = priv->rx_ring[i].cleaned;
@@ -344,7 +344,7 @@ static void mlx4_en_get_strings(struct net_device *dev,
 				"rx%d_packets", i);
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
 				"rx%d_bytes", i);
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
 				"rx%d_napi_yield", i);
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 5eac871399d8..fa37b7a61213 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -68,7 +68,7 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up)
 	return 0;
 }
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 /* must be called with local_bh_disable()d */
 static int mlx4_en_low_latency_recv(struct napi_struct *napi)
 {
@@ -94,7 +94,7 @@ static int mlx4_en_low_latency_recv(struct napi_struct *napi)
 
 	return done;
 }
-#endif	/* CONFIG_NET_LL_RX_POLL */
+#endif	/* CONFIG_NET_RX_BUSY_POLL */
 
 #ifdef CONFIG_RFS_ACCEL
 
@@ -2140,7 +2140,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= mlx4_en_low_latency_recv,
 #endif
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 8873d6802c80..6fc6dabc78d5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -845,16 +845,7 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			   MLX4_CMD_NATIVE);
 
 	if (!err && dev->caps.function != slave) {
-		/* if config MAC in DB use it */
-		if (priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac)
-			def_mac = priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac;
-		else {
-			/* set slave default_mac address */
-			MLX4_GET(def_mac, outbox->buf, QUERY_PORT_MAC_OFFSET);
-			def_mac += slave << 8;
-			priv->mfunc.master.vf_admin[slave].vport[vhcr->in_modifier].mac = def_mac;
-		}
-
+		def_mac = priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac;
 		MLX4_PUT(outbox->buf, def_mac, QUERY_PORT_MAC_OFFSET);
 
 		/* get port type - currently only eth is enabled */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index e85af922dcdc..36be3208786a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -371,7 +371,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 	dev->caps.sqp_demux = (mlx4_is_master(dev)) ? MLX4_MAX_NUM_SLAVES : 0;
 
-	if (!enable_64b_cqe_eqe) {
+	if (!enable_64b_cqe_eqe && !mlx4_is_slave(dev)) {
 		if (dev_cap->flags &
 		    (MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) {
 			mlx4_warn(dev, "64B EQEs/CQEs supported by the device but not enabled\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 35fb60e2320c..5e0aa569306a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -292,7 +292,7 @@ struct mlx4_en_rx_ring {
 	void *rx_info;
 	unsigned long bytes;
 	unsigned long packets;
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned long yields;
 	unsigned long misses;
 	unsigned long cleaned;
@@ -318,7 +318,7 @@ struct mlx4_en_cq {
 	struct mlx4_cqe *buf;
 #define MLX4_EN_OPCODE_ERROR	0x1e
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int state;
 #define MLX4_EN_CQ_STATE_IDLE        0
 #define MLX4_EN_CQ_STATE_NAPI     1    /* NAPI owns this CQ */
@@ -329,7 +329,7 @@ struct mlx4_en_cq {
 #define CQ_YIELD (MLX4_EN_CQ_STATE_NAPI_YIELD | MLX4_EN_CQ_STATE_POLL_YIELD)
 #define CQ_USER_PEND (MLX4_EN_CQ_STATE_POLL | MLX4_EN_CQ_STATE_POLL_YIELD)
 	spinlock_t poll_lock; /* protects from LLS/napi conflicts */
-#endif  /* CONFIG_NET_LL_RX_POLL */
+#endif  /* CONFIG_NET_RX_BUSY_POLL */
 };
 
 struct mlx4_en_port_profile {
@@ -580,7 +580,7 @@ struct mlx4_mac_entry {
 	struct rcu_head rcu;
 };
 
-#ifdef CONFIG_NET_LL_RX_POLL
+#ifdef CONFIG_NET_RX_BUSY_POLL
 static inline void mlx4_en_cq_init_lock(struct mlx4_en_cq *cq)
 {
 	spin_lock_init(&cq->poll_lock);
@@ -687,7 +687,7 @@ static inline bool mlx4_en_cq_ll_polling(struct mlx4_en_cq *cq)
 {
 	return false;
 }
-#endif /* CONFIG_NET_LL_RX_POLL */
+#endif /* CONFIG_NET_RX_BUSY_POLL */
 
 #define MLX4_EN_WOL_DO_MODIFY (1ULL << 63)
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 205753a04cfc..5472cbd34028 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -46,7 +46,7 @@
 #include "mlx5_core.h"
 
 enum {
-	CMD_IF_REV = 3,
+	CMD_IF_REV = 5,
 };
 
 enum {
@@ -282,6 +282,12 @@ const char *mlx5_command_str(int command)
 	case MLX5_CMD_OP_TEARDOWN_HCA:
 		return "TEARDOWN_HCA";
 
+	case MLX5_CMD_OP_ENABLE_HCA:
+		return "MLX5_CMD_OP_ENABLE_HCA";
+
+	case MLX5_CMD_OP_DISABLE_HCA:
+		return "MLX5_CMD_OP_DISABLE_HCA";
+
 	case MLX5_CMD_OP_QUERY_PAGES:
 		return "QUERY_PAGES";
 
@@ -1113,7 +1119,13 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector)
 
 	for (i = 0; i < (1 << cmd->log_sz); i++) {
 		if (test_bit(i, &vector)) {
+			struct semaphore *sem;
+
 			ent = cmd->ent_arr[i];
+			if (ent->page_queue)
+				sem = &cmd->pages_sem;
+			else
+				sem = &cmd->sem;
 			ktime_get_ts(&ent->ts2);
 			memcpy(ent->out->first.data, ent->lay->out, sizeof(ent->lay->out));
 			dump_command(dev, ent, 0);
@@ -1136,10 +1148,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector)
 			} else {
 				complete(&ent->done);
 			}
-			if (ent->page_queue)
-				up(&cmd->pages_sem);
-			else
-				up(&cmd->sem);
+			up(sem);
 		}
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c02cbcfd0fb8..443cc4d7b024 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -268,7 +268,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 		case MLX5_EVENT_TYPE_PAGE_REQUEST:
 			{
 				u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
-				s16 npages = be16_to_cpu(eqe->data.req_pages.num_pages);
+				s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages);
 
 				mlx5_core_dbg(dev, "page request for func 0x%x, napges %d\n", func_id, npages);
 				mlx5_core_req_pages_handler(dev, func_id, npages);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 72a5222447f5..f012658b6a92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -113,7 +113,7 @@ int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev,
 	caps->log_max_srq = out->hca_cap.log_max_srqs & 0x1f;
 	caps->local_ca_ack_delay = out->hca_cap.local_ca_ack_delay & 0x1f;
 	caps->log_max_mcg = out->hca_cap.log_max_mcg;
-	caps->max_qp_mcg = be16_to_cpu(out->hca_cap.max_qp_mcg);
+	caps->max_qp_mcg = be32_to_cpu(out->hca_cap.max_qp_mcg) & 0xffffff;
 	caps->max_ra_res_qp = 1 << (out->hca_cap.log_max_ra_res_qp & 0x3f);
 	caps->max_ra_req_qp = 1 << (out->hca_cap.log_max_ra_req_qp & 0x3f);
 	caps->max_srq_wqes = 1 << out->hca_cap.log_max_srq_sz;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 748f10a155c4..3e6670c4a7cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -55,33 +55,9 @@ enum {
 };
 
 static DEFINE_SPINLOCK(health_lock);
-
 static LIST_HEAD(health_list);
 static struct work_struct health_work;
 
-static health_handler_t reg_handler;
-int mlx5_register_health_report_handler(health_handler_t handler)
-{
-	spin_lock_irq(&health_lock);
-	if (reg_handler) {
-		spin_unlock_irq(&health_lock);
-		return -EEXIST;
-	}
-	reg_handler = handler;
-	spin_unlock_irq(&health_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(mlx5_register_health_report_handler);
-
-void mlx5_unregister_health_report_handler(void)
-{
-	spin_lock_irq(&health_lock);
-	reg_handler = NULL;
-	spin_unlock_irq(&health_lock);
-}
-EXPORT_SYMBOL(mlx5_unregister_health_report_handler);
-
 static void health_care(struct work_struct *work)
 {
 	struct mlx5_core_health *health, *n;
@@ -98,11 +74,8 @@ static void health_care(struct work_struct *work)
 		priv = container_of(health, struct mlx5_priv, health);
 		dev = container_of(priv, struct mlx5_core_dev, priv);
 		mlx5_core_warn(dev, "handling bad device here\n");
+		/* nothing yet */
 		spin_lock_irq(&health_lock);
-		if (reg_handler)
-			reg_handler(dev->pdev, health->health,
-				    sizeof(health->health));
-
 		list_del_init(&health->list);
 		spin_unlock_irq(&health_lock);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 12242de2b0e3..b47739b0b5f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -249,6 +249,44 @@ static int set_hca_ctrl(struct mlx5_core_dev *dev)
 	return err;
 }
 
+static int mlx5_core_enable_hca(struct mlx5_core_dev *dev)
+{
+	int err;
+	struct mlx5_enable_hca_mbox_in in;
+	struct mlx5_enable_hca_mbox_out out;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_ENABLE_HCA);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err)
+		return err;
+
+	if (out.hdr.status)
+		return mlx5_cmd_status_to_err(&out.hdr);
+
+	return 0;
+}
+
+static int mlx5_core_disable_hca(struct mlx5_core_dev *dev)
+{
+	int err;
+	struct mlx5_disable_hca_mbox_in in;
+	struct mlx5_disable_hca_mbox_out out;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DISABLE_HCA);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err)
+		return err;
+
+	if (out.hdr.status)
+		return mlx5_cmd_status_to_err(&out.hdr);
+
+	return 0;
+}
+
 int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -304,28 +342,41 @@ int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 	}
 
 	mlx5_pagealloc_init(dev);
+
+	err = mlx5_core_enable_hca(dev);
+	if (err) {
+		dev_err(&pdev->dev, "enable hca failed\n");
+		goto err_pagealloc_cleanup;
+	}
+
+	err = mlx5_satisfy_startup_pages(dev, 1);
+	if (err) {
+		dev_err(&pdev->dev, "failed to allocate boot pages\n");
+		goto err_disable_hca;
+	}
+
 	err = set_hca_ctrl(dev);
 	if (err) {
 		dev_err(&pdev->dev, "set_hca_ctrl failed\n");
-		goto err_pagealloc_cleanup;
+		goto reclaim_boot_pages;
 	}
 
 	err = handle_hca_cap(dev);
 	if (err) {
 		dev_err(&pdev->dev, "handle_hca_cap failed\n");
-		goto err_pagealloc_cleanup;
+		goto reclaim_boot_pages;
 	}
 
-	err = mlx5_satisfy_startup_pages(dev);
+	err = mlx5_satisfy_startup_pages(dev, 0);
 	if (err) {
-		dev_err(&pdev->dev, "failed to allocate startup pages\n");
-		goto err_pagealloc_cleanup;
+		dev_err(&pdev->dev, "failed to allocate init pages\n");
+		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_pagealloc_start(dev);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_pagealloc_start failed\n");
-		goto err_reclaim_pages;
+		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_cmd_init_hca(dev);
@@ -396,9 +447,12 @@ err_stop_poll:
 err_pagealloc_stop:
 	mlx5_pagealloc_stop(dev);
 
-err_reclaim_pages:
+reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
 
+err_disable_hca:
+	mlx5_core_disable_hca(dev);
+
 err_pagealloc_cleanup:
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_cmd_cleanup(dev);
@@ -434,6 +488,7 @@ void mlx5_dev_cleanup(struct mlx5_core_dev *dev)
 	mlx5_cmd_teardown_hca(dev);
 	mlx5_pagealloc_stop(dev);
 	mlx5_reclaim_startup_pages(dev);
+	mlx5_core_disable_hca(dev);
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_cmd_cleanup(dev);
 	iounmap(dev->iseg);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index f0bf46339b28..3a2408d44820 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -43,10 +43,16 @@ enum {
 	MLX5_PAGES_TAKE		= 2
 };
 
+enum {
+	MLX5_BOOT_PAGES		= 1,
+	MLX5_INIT_PAGES		= 2,
+	MLX5_POST_INIT_PAGES	= 3
+};
+
 struct mlx5_pages_req {
 	struct mlx5_core_dev *dev;
 	u32	func_id;
-	s16	npages;
+	s32	npages;
 	struct work_struct work;
 };
 
@@ -64,27 +70,23 @@ struct mlx5_query_pages_inbox {
 
 struct mlx5_query_pages_outbox {
 	struct mlx5_outbox_hdr	hdr;
-	u8			reserved[2];
+	__be16			rsvd;
 	__be16			func_id;
-	__be16			init_pages;
-	__be16			num_pages;
+	__be32			num_pages;
 };
 
 struct mlx5_manage_pages_inbox {
 	struct mlx5_inbox_hdr	hdr;
-	__be16			rsvd0;
+	__be16			rsvd;
 	__be16			func_id;
-	__be16			rsvd1;
-	__be16			num_entries;
-	u8			rsvd2[16];
+	__be32			num_entries;
 	__be64			pas[0];
 };
 
 struct mlx5_manage_pages_outbox {
 	struct mlx5_outbox_hdr	hdr;
-	u8			rsvd0[2];
-	__be16			num_entries;
-	u8			rsvd1[20];
+	__be32			num_entries;
+	u8			rsvd[4];
 	__be64			pas[0];
 };
 
@@ -146,7 +148,7 @@ static struct page *remove_page(struct mlx5_core_dev *dev, u64 addr)
 }
 
 static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
-				s16 *pages, s16 *init_pages)
+				s32 *npages, int boot)
 {
 	struct mlx5_query_pages_inbox	in;
 	struct mlx5_query_pages_outbox	out;
@@ -155,6 +157,8 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 	memset(&in, 0, sizeof(in));
 	memset(&out, 0, sizeof(out));
 	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_PAGES);
+	in.hdr.opmod = boot ? cpu_to_be16(MLX5_BOOT_PAGES) : cpu_to_be16(MLX5_INIT_PAGES);
+
 	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
 	if (err)
 		return err;
@@ -162,10 +166,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 	if (out.hdr.status)
 		return mlx5_cmd_status_to_err(&out.hdr);
 
-	if (pages)
-		*pages = be16_to_cpu(out.num_pages);
-	if (init_pages)
-		*init_pages = be16_to_cpu(out.init_pages);
+	*npages = be32_to_cpu(out.num_pages);
 	*func_id = be16_to_cpu(out.func_id);
 
 	return err;
@@ -219,7 +220,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES);
 	in->hdr.opmod = cpu_to_be16(MLX5_PAGES_GIVE);
 	in->func_id = cpu_to_be16(func_id);
-	in->num_entries = cpu_to_be16(npages);
+	in->num_entries = cpu_to_be32(npages);
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
 	mlx5_core_dbg(dev, "err %d\n", err);
 	if (err) {
@@ -287,7 +288,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES);
 	in.hdr.opmod = cpu_to_be16(MLX5_PAGES_TAKE);
 	in.func_id = cpu_to_be16(func_id);
-	in.num_entries = cpu_to_be16(npages);
+	in.num_entries = cpu_to_be32(npages);
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
 	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
 	if (err) {
@@ -301,7 +302,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 		goto out_free;
 	}
 
-	num_claimed = be16_to_cpu(out->num_entries);
+	num_claimed = be32_to_cpu(out->num_entries);
 	if (nclaimed)
 		*nclaimed = num_claimed;
 
@@ -340,7 +341,7 @@ static void pages_work_handler(struct work_struct *work)
 }
 
 void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
-				 s16 npages)
+				 s32 npages)
 {
 	struct mlx5_pages_req *req;
 
@@ -357,19 +358,20 @@ void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 	queue_work(dev->priv.pg_wq, &req->work);
 }
 
-int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev)
+int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
 {
-	s16 uninitialized_var(init_pages);
 	u16 uninitialized_var(func_id);
+	s32 uninitialized_var(npages);
 	int err;
 
-	err = mlx5_cmd_query_pages(dev, &func_id, NULL, &init_pages);
+	err = mlx5_cmd_query_pages(dev, &func_id, &npages, boot);
 	if (err)
 		return err;
 
-	mlx5_core_dbg(dev, "requested %d init pages for func_id 0x%x\n", init_pages, func_id);
+	mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
+		      npages, boot ? "boot" : "init", func_id);
 
-	return give_pages(dev, func_id, init_pages, 0);
+	return give_pages(dev, func_id, npages, 0);
 }
 
 static int optimal_reclaimed_pages(void)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 71d4a3937200..68f5d9c77c7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -164,6 +164,7 @@ int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari)
 		uuari->uars[i].map = ioremap(addr, PAGE_SIZE);
 		if (!uuari->uars[i].map) {
 			mlx5_cmd_free_uar(dev, uuari->uars[i].index);
+			err = -ENOMEM;
 			goto out_count;
 		}
 		mlx5_core_dbg(dev, "allocated uar index 0x%x, mmaped at %p\n",
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
index cb22341a14a8..a588ffde9700 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
@@ -4,7 +4,7 @@
 
 config PCH_GBE
 	tristate "OKI SEMICONDUCTOR IOH(ML7223/ML7831) GbE"
-	depends on PCI
+	depends on PCI && (X86 || COMPILE_TEST)
 	select MII
 	select PTP_1588_CLOCK_PCH
 	---help---
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index b00cf5665eab..221645e9f182 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1400,8 +1400,8 @@ void qlcnic_pci_camqm_write_2M(struct qlcnic_adapter *, u64, u64);
 #define ADDR_IN_RANGE(addr, low, high)	\
 	(((addr) < (high)) && ((addr) >= (low)))
 
-#define QLCRD32(adapter, off) \
-	(adapter->ahw->hw_ops->read_reg)(adapter, off)
+#define QLCRD32(adapter, off, err) \
+	(adapter->ahw->hw_ops->read_reg)(adapter, off, err)
 
 #define QLCWR32(adapter, off, val) \
 	adapter->ahw->hw_ops->write_reg(adapter, off, val)
@@ -1604,7 +1604,7 @@ struct qlcnic_nic_template {
 struct qlcnic_hardware_ops {
 	void (*read_crb) (struct qlcnic_adapter *, char *, loff_t, size_t);
 	void (*write_crb) (struct qlcnic_adapter *, char *, loff_t, size_t);
-	int (*read_reg) (struct qlcnic_adapter *, ulong);
+	int (*read_reg) (struct qlcnic_adapter *, ulong, int *);
 	int (*write_reg) (struct qlcnic_adapter *, ulong, u32);
 	void (*get_ocm_win) (struct qlcnic_hardware_context *);
 	int (*get_mac_address) (struct qlcnic_adapter *, u8 *);
@@ -1662,12 +1662,6 @@ static inline void qlcnic_write_crb(struct qlcnic_adapter *adapter, char *buf,
 	adapter->ahw->hw_ops->write_crb(adapter, buf, offset, size);
 }
 
-static inline int qlcnic_hw_read_wx_2M(struct qlcnic_adapter *adapter,
-				       ulong off)
-{
-	return adapter->ahw->hw_ops->read_reg(adapter, off);
-}
-
 static inline int qlcnic_hw_write_wx_2M(struct qlcnic_adapter *adapter,
 					ulong off, u32 data)
 {
@@ -1869,7 +1863,8 @@ static inline void qlcnic_free_mac_list(struct qlcnic_adapter *adapter)
 
 static inline void qlcnic_set_mac_filter_count(struct qlcnic_adapter *adapter)
 {
-	adapter->ahw->hw_ops->set_mac_filter_count(adapter);
+	if (adapter->ahw->hw_ops->set_mac_filter_count)
+		adapter->ahw->hw_ops->set_mac_filter_count(adapter);
 }
 
 static inline void qlcnic_dev_request_reset(struct qlcnic_adapter *adapter,
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 0913c623a67e..9d4bb7f83904 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -228,17 +228,17 @@ static int __qlcnic_set_win_base(struct qlcnic_adapter *adapter, u32 addr)
 	return 0;
 }
 
-int qlcnic_83xx_rd_reg_indirect(struct qlcnic_adapter *adapter, ulong addr)
+int qlcnic_83xx_rd_reg_indirect(struct qlcnic_adapter *adapter, ulong addr,
+				int *err)
 {
-	int ret;
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 
-	ret = __qlcnic_set_win_base(adapter, (u32) addr);
-	if (!ret) {
+	*err = __qlcnic_set_win_base(adapter, (u32) addr);
+	if (!*err) {
 		return QLCRDX(ahw, QLCNIC_WILDCARD);
 	} else {
 		dev_err(&adapter->pdev->dev,
-			"%s failed, addr = 0x%x\n", __func__, (int)addr);
+			"%s failed, addr = 0x%lx\n", __func__, addr);
 		return -EIO;
 	}
 }
@@ -561,7 +561,7 @@ void qlcnic_83xx_cam_unlock(struct qlcnic_adapter *adapter)
 void qlcnic_83xx_read_crb(struct qlcnic_adapter *adapter, char *buf,
 			  loff_t offset, size_t size)
 {
-	int ret;
+	int ret = 0;
 	u32 data;
 
 	if (qlcnic_api_lock(adapter)) {
@@ -571,7 +571,7 @@ void qlcnic_83xx_read_crb(struct qlcnic_adapter *adapter, char *buf,
 		return;
 	}
 
-	ret = qlcnic_83xx_rd_reg_indirect(adapter, (u32) offset);
+	data = QLCRD32(adapter, (u32) offset, &ret);
 	qlcnic_api_unlock(adapter);
 
 	if (ret == -EIO) {
@@ -580,7 +580,6 @@ void qlcnic_83xx_read_crb(struct qlcnic_adapter *adapter, char *buf,
 			__func__, (u32)offset);
 		return;
 	}
-	data = ret;
 	memcpy(buf, &data, size);
 }
 
@@ -2075,18 +2074,25 @@ void qlcnic_83xx_config_intr_coal(struct qlcnic_adapter *adapter)
 static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter,
 					u32 data[])
 {
+	struct qlcnic_hardware_context *ahw = adapter->ahw;
 	u8 link_status, duplex;
 	/* link speed */
 	link_status = LSB(data[3]) & 1;
-	adapter->ahw->link_speed = MSW(data[2]);
-	adapter->ahw->link_autoneg = MSB(MSW(data[3]));
-	adapter->ahw->module_type = MSB(LSW(data[3]));
-	duplex = LSB(MSW(data[3]));
-	if (duplex)
-		adapter->ahw->link_duplex = DUPLEX_FULL;
-	else
-		adapter->ahw->link_duplex = DUPLEX_HALF;
-	adapter->ahw->has_link_events = 1;
+	if (link_status) {
+		ahw->link_speed = MSW(data[2]);
+		duplex = LSB(MSW(data[3]));
+		if (duplex)
+			ahw->link_duplex = DUPLEX_FULL;
+		else
+			ahw->link_duplex = DUPLEX_HALF;
+	} else {
+		ahw->link_speed = SPEED_UNKNOWN;
+		ahw->link_duplex = DUPLEX_UNKNOWN;
+	}
+
+	ahw->link_autoneg = MSB(MSW(data[3]));
+	ahw->module_type = MSB(LSW(data[3]));
+	ahw->has_link_events = 1;
 	qlcnic_advert_link_change(adapter, link_status);
 }
 
@@ -2384,9 +2390,9 @@ int qlcnic_83xx_lockless_flash_read32(struct qlcnic_adapter *adapter,
 				      u32 flash_addr, u8 *p_data,
 				      int count)
 {
-	int i, ret;
-	u32 word, range, flash_offset, addr = flash_addr;
+	u32 word, range, flash_offset, addr = flash_addr, ret;
 	ulong indirect_add, direct_window;
+	int i, err = 0;
 
 	flash_offset = addr & (QLCNIC_FLASH_SECTOR_SIZE - 1);
 	if (addr & 0x3) {
@@ -2404,10 +2410,9 @@ int qlcnic_83xx_lockless_flash_read32(struct qlcnic_adapter *adapter,
 		/* Multi sector read */
 		for (i = 0; i < count; i++) {
 			indirect_add = QLC_83XX_FLASH_DIRECT_DATA(addr);
-			ret = qlcnic_83xx_rd_reg_indirect(adapter,
-							  indirect_add);
-			if (ret == -EIO)
-				return -EIO;
+			ret = QLCRD32(adapter, indirect_add, &err);
+			if (err == -EIO)
+				return err;
 
 			word = ret;
 			*(u32 *)p_data  = word;
@@ -2428,10 +2433,9 @@ int qlcnic_83xx_lockless_flash_read32(struct qlcnic_adapter *adapter,
 		/* Single sector read */
 		for (i = 0; i < count; i++) {
 			indirect_add = QLC_83XX_FLASH_DIRECT_DATA(addr);
-			ret = qlcnic_83xx_rd_reg_indirect(adapter,
-							  indirect_add);
-			if (ret == -EIO)
-				return -EIO;
+			ret = QLCRD32(adapter, indirect_add, &err);
+			if (err == -EIO)
+				return err;
 
 			word = ret;
 			*(u32 *)p_data  = word;
@@ -2447,10 +2451,13 @@ static int qlcnic_83xx_poll_flash_status_reg(struct qlcnic_adapter *adapter)
 {
 	u32 status;
 	int retries = QLC_83XX_FLASH_READ_RETRY_COUNT;
+	int err = 0;
 
 	do {
-		status = qlcnic_83xx_rd_reg_indirect(adapter,
-						     QLC_83XX_FLASH_STATUS);
+		status = QLCRD32(adapter, QLC_83XX_FLASH_STATUS, &err);
+		if (err == -EIO)
+			return err;
+
 		if ((status & QLC_83XX_FLASH_STATUS_READY) ==
 		    QLC_83XX_FLASH_STATUS_READY)
 			break;
@@ -2502,7 +2509,8 @@ int qlcnic_83xx_disable_flash_write(struct qlcnic_adapter *adapter)
 
 int qlcnic_83xx_read_flash_mfg_id(struct qlcnic_adapter *adapter)
 {
-	int ret, mfg_id;
+	int ret, err = 0;
+	u32 mfg_id;
 
 	if (qlcnic_83xx_lock_flash(adapter))
 		return -EIO;
@@ -2517,9 +2525,11 @@ int qlcnic_83xx_read_flash_mfg_id(struct qlcnic_adapter *adapter)
 		return -EIO;
 	}
 
-	mfg_id = qlcnic_83xx_rd_reg_indirect(adapter, QLC_83XX_FLASH_RDDATA);
-	if (mfg_id == -EIO)
-		return -EIO;
+	mfg_id = QLCRD32(adapter, QLC_83XX_FLASH_RDDATA, &err);
+	if (err == -EIO) {
+		qlcnic_83xx_unlock_flash(adapter);
+		return err;
+	}
 
 	adapter->flash_mfg_id = (mfg_id & 0xFF);
 	qlcnic_83xx_unlock_flash(adapter);
@@ -2636,7 +2646,7 @@ int qlcnic_83xx_flash_bulk_write(struct qlcnic_adapter *adapter, u32 addr,
 				 u32 *p_data, int count)
 {
 	u32 temp;
-	int ret = -EIO;
+	int ret = -EIO, err = 0;
 
 	if ((count < QLC_83XX_FLASH_WRITE_MIN) ||
 	    (count > QLC_83XX_FLASH_WRITE_MAX)) {
@@ -2645,8 +2655,10 @@ int qlcnic_83xx_flash_bulk_write(struct qlcnic_adapter *adapter, u32 addr,
 		return -EIO;
 	}
 
-	temp = qlcnic_83xx_rd_reg_indirect(adapter,
-					   QLC_83XX_FLASH_SPI_CONTROL);
+	temp = QLCRD32(adapter, QLC_83XX_FLASH_SPI_CONTROL, &err);
+	if (err == -EIO)
+		return err;
+
 	qlcnic_83xx_wrt_reg_indirect(adapter, QLC_83XX_FLASH_SPI_CONTROL,
 				     (temp | QLC_83XX_FLASH_SPI_CTRL));
 	qlcnic_83xx_wrt_reg_indirect(adapter, QLC_83XX_FLASH_ADDR,
@@ -2695,13 +2707,18 @@ int qlcnic_83xx_flash_bulk_write(struct qlcnic_adapter *adapter, u32 addr,
 		return -EIO;
 	}
 
-	ret = qlcnic_83xx_rd_reg_indirect(adapter, QLC_83XX_FLASH_SPI_STATUS);
+	ret = QLCRD32(adapter, QLC_83XX_FLASH_SPI_STATUS, &err);
+	if (err == -EIO)
+		return err;
+
 	if ((ret & QLC_83XX_FLASH_SPI_CTRL) == QLC_83XX_FLASH_SPI_CTRL) {
 		dev_err(&adapter->pdev->dev, "%s: failed at %d\n",
 			__func__, __LINE__);
 		/* Operation failed, clear error bit */
-		temp = qlcnic_83xx_rd_reg_indirect(adapter,
-						   QLC_83XX_FLASH_SPI_CONTROL);
+		temp = QLCRD32(adapter, QLC_83XX_FLASH_SPI_CONTROL, &err);
+		if (err == -EIO)
+			return err;
+
 		qlcnic_83xx_wrt_reg_indirect(adapter,
 					     QLC_83XX_FLASH_SPI_CONTROL,
 					     (temp | QLC_83XX_FLASH_SPI_CTRL));
@@ -2823,6 +2840,7 @@ int qlcnic_83xx_ms_mem_write128(struct qlcnic_adapter *adapter, u64 addr,
 {
 	int i, j, ret = 0;
 	u32 temp;
+	int err = 0;
 
 	/* Check alignment */
 	if (addr & 0xF)
@@ -2855,8 +2873,12 @@ int qlcnic_83xx_ms_mem_write128(struct qlcnic_adapter *adapter, u64 addr,
 					     QLCNIC_TA_WRITE_START);
 
 		for (j = 0; j < MAX_CTL_CHECK; j++) {
-			temp = qlcnic_83xx_rd_reg_indirect(adapter,
-							   QLCNIC_MS_CTRL);
+			temp = QLCRD32(adapter, QLCNIC_MS_CTRL, &err);
+			if (err == -EIO) {
+				mutex_unlock(&adapter->ahw->mem_lock);
+				return err;
+			}
+
 			if ((temp & TA_CTL_BUSY) == 0)
 				break;
 		}
@@ -2878,9 +2900,9 @@ int qlcnic_83xx_ms_mem_write128(struct qlcnic_adapter *adapter, u64 addr,
 int qlcnic_83xx_flash_read32(struct qlcnic_adapter *adapter, u32 flash_addr,
 			     u8 *p_data, int count)
 {
-	int i, ret;
-	u32 word, addr = flash_addr;
+	u32 word, addr = flash_addr, ret;
 	ulong  indirect_addr;
+	int i, err = 0;
 
 	if (qlcnic_83xx_lock_flash(adapter) != 0)
 		return -EIO;
@@ -2900,10 +2922,10 @@ int qlcnic_83xx_flash_read32(struct qlcnic_adapter *adapter, u32 flash_addr,
 		}
 
 		indirect_addr = QLC_83XX_FLASH_DIRECT_DATA(addr);
-		ret = qlcnic_83xx_rd_reg_indirect(adapter,
-						  indirect_addr);
-		if (ret == -EIO)
-			return -EIO;
+		ret = QLCRD32(adapter, indirect_addr, &err);
+		if (err == -EIO)
+			return err;
+
 		word = ret;
 		*(u32 *)p_data  = word;
 		p_data = p_data + 4;
@@ -3014,8 +3036,8 @@ int qlcnic_83xx_get_settings(struct qlcnic_adapter *adapter,
 	}
 
 	if (ahw->port_type == QLCNIC_XGBE) {
-		ecmd->supported = SUPPORTED_1000baseT_Full;
-		ecmd->advertising = ADVERTISED_1000baseT_Full;
+		ecmd->supported = SUPPORTED_10000baseT_Full;
+		ecmd->advertising = ADVERTISED_10000baseT_Full;
 	} else {
 		ecmd->supported = (SUPPORTED_10baseT_Half |
 				   SUPPORTED_10baseT_Full |
@@ -3244,6 +3266,11 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 	u8 val;
 	int ret, max_sds_rings = adapter->max_sds_rings;
 
+	if (test_bit(__QLCNIC_RESETTING, &adapter->state)) {
+		netdev_info(netdev, "Device is resetting\n");
+		return -EBUSY;
+	}
+
 	if (qlcnic_get_diag_lock(adapter)) {
 		netdev_info(netdev, "Device in diagnostics mode\n");
 		return -EBUSY;
@@ -3369,7 +3396,8 @@ int qlcnic_83xx_set_pauseparam(struct qlcnic_adapter *adapter,
 
 static int qlcnic_83xx_read_flash_status_reg(struct qlcnic_adapter *adapter)
 {
-	int ret;
+	int ret, err = 0;
+	u32 temp;
 
 	qlcnic_83xx_wrt_reg_indirect(adapter, QLC_83XX_FLASH_ADDR,
 				     QLC_83XX_FLASH_OEM_READ_SIG);
@@ -3379,8 +3407,11 @@ static int qlcnic_83xx_read_flash_status_reg(struct qlcnic_adapter *adapter)
 	if (ret)
 		return -EIO;
 
-	ret = qlcnic_83xx_rd_reg_indirect(adapter, QLC_83XX_FLASH_RDDATA);
-	return ret & 0xFF;
+	temp = QLCRD32(adapter, QLC_83XX_FLASH_RDDATA, &err);
+	if (err == -EIO)
+		return err;
+
+	return temp & 0xFF;
 }
 
 int qlcnic_83xx_flash_test(struct qlcnic_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index 2548d1403d75..272f56a2e14b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -508,7 +508,7 @@ void qlcnic_83xx_add_sysfs(struct qlcnic_adapter *);
 void qlcnic_83xx_remove_sysfs(struct qlcnic_adapter *);
 void qlcnic_83xx_write_crb(struct qlcnic_adapter *, char *, loff_t, size_t);
 void qlcnic_83xx_read_crb(struct qlcnic_adapter *, char *, loff_t, size_t);
-int qlcnic_83xx_rd_reg_indirect(struct qlcnic_adapter *, ulong);
+int qlcnic_83xx_rd_reg_indirect(struct qlcnic_adapter *, ulong, int *);
 int qlcnic_83xx_wrt_reg_indirect(struct qlcnic_adapter *, ulong, u32);
 void qlcnic_83xx_process_rcv_diag(struct qlcnic_adapter *, int, u64 []);
 int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *, u32);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index f41dfab1e9a3..345d987aede4 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -629,7 +629,8 @@ int qlcnic_83xx_idc_reattach_driver(struct qlcnic_adapter *adapter)
 		return -EIO;
 	}
 
-	qlcnic_set_drv_version(adapter);
+	if (adapter->portnum == 0)
+		qlcnic_set_drv_version(adapter);
 	qlcnic_83xx_idc_attach_driver(adapter);
 
 	return 0;
@@ -1303,8 +1304,11 @@ static void qlcnic_83xx_dump_pause_control_regs(struct qlcnic_adapter *adapter)
 {
 	int i, j;
 	u32 val = 0, val1 = 0, reg = 0;
+	int err = 0;
 
-	val = QLCRD32(adapter, QLC_83XX_SRE_SHIM_REG);
+	val = QLCRD32(adapter, QLC_83XX_SRE_SHIM_REG, &err);
+	if (err == -EIO)
+		return;
 	dev_info(&adapter->pdev->dev, "SRE-Shim Ctrl:0x%x\n", val);
 
 	for (j = 0; j < 2; j++) {
@@ -1318,7 +1322,9 @@ static void qlcnic_83xx_dump_pause_control_regs(struct qlcnic_adapter *adapter)
 			reg = QLC_83XX_PORT1_THRESHOLD;
 		}
 		for (i = 0; i < 8; i++) {
-			val = QLCRD32(adapter, reg + (i * 0x4));
+			val = QLCRD32(adapter, reg + (i * 0x4), &err);
+			if (err == -EIO)
+				return;
 			dev_info(&adapter->pdev->dev, "0x%x  ", val);
 		}
 		dev_info(&adapter->pdev->dev, "\n");
@@ -1335,8 +1341,10 @@ static void qlcnic_83xx_dump_pause_control_regs(struct qlcnic_adapter *adapter)
 			reg = QLC_83XX_PORT1_TC_MC_REG;
 		}
 		for (i = 0; i < 4; i++) {
-			val = QLCRD32(adapter, reg + (i * 0x4));
-			 dev_info(&adapter->pdev->dev, "0x%x  ", val);
+			val = QLCRD32(adapter, reg + (i * 0x4), &err);
+			if (err == -EIO)
+				return;
+			dev_info(&adapter->pdev->dev, "0x%x  ", val);
 		}
 		dev_info(&adapter->pdev->dev, "\n");
 	}
@@ -1352,17 +1360,25 @@ static void qlcnic_83xx_dump_pause_control_regs(struct qlcnic_adapter *adapter)
 			reg = QLC_83XX_PORT1_TC_STATS;
 		}
 		for (i = 7; i >= 0; i--) {
-			val = QLCRD32(adapter, reg);
+			val = QLCRD32(adapter, reg, &err);
+			if (err == -EIO)
+				return;
 			val &= ~(0x7 << 29);    /* Reset bits 29 to 31 */
 			QLCWR32(adapter, reg, (val | (i << 29)));
-			val = QLCRD32(adapter, reg);
+			val = QLCRD32(adapter, reg, &err);
+			if (err == -EIO)
+				return;
 			dev_info(&adapter->pdev->dev, "0x%x  ", val);
 		}
 		dev_info(&adapter->pdev->dev, "\n");
 	}
 
-	val = QLCRD32(adapter, QLC_83XX_PORT2_IFB_THRESHOLD);
-	val1 = QLCRD32(adapter, QLC_83XX_PORT3_IFB_THRESHOLD);
+	val = QLCRD32(adapter, QLC_83XX_PORT2_IFB_THRESHOLD, &err);
+	if (err == -EIO)
+		return;
+	val1 = QLCRD32(adapter, QLC_83XX_PORT3_IFB_THRESHOLD, &err);
+	if (err == -EIO)
+		return;
 	dev_info(&adapter->pdev->dev,
 		 "IFB-Pause Thresholds: Port 2:0x%x, Port 3:0x%x\n",
 		 val, val1);
@@ -1425,7 +1441,7 @@ static void qlcnic_83xx_take_eport_out_of_reset(struct qlcnic_adapter *adapter)
 static int qlcnic_83xx_check_heartbeat(struct qlcnic_adapter *p_dev)
 {
 	u32 heartbeat, peg_status;
-	int retries, ret = -EIO;
+	int retries, ret = -EIO, err = 0;
 
 	retries = QLCNIC_HEARTBEAT_CHECK_RETRY_COUNT;
 	p_dev->heartbeat = QLC_SHARED_REG_RD32(p_dev,
@@ -1453,11 +1469,11 @@ static int qlcnic_83xx_check_heartbeat(struct qlcnic_adapter *p_dev)
 			 "PEG_NET_2_PC: 0x%x, PEG_NET_3_PC: 0x%x,\n"
 			 "PEG_NET_4_PC: 0x%x\n", peg_status,
 			 QLC_SHARED_REG_RD32(p_dev, QLCNIC_PEG_HALT_STATUS2),
-			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_0),
-			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_1),
-			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_2),
-			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_3),
-			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_4));
+			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_0, &err),
+			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_1, &err),
+			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_2, &err),
+			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_3, &err),
+			 QLCRD32(p_dev, QLC_83XX_CRB_PEG_NET_4, &err));
 
 		if (QLCNIC_FWERROR_CODE(peg_status) == 0x67)
 			dev_err(&p_dev->pdev->dev,
@@ -1501,18 +1517,22 @@ int qlcnic_83xx_check_hw_status(struct qlcnic_adapter *p_dev)
 static int qlcnic_83xx_poll_reg(struct qlcnic_adapter *p_dev, u32 addr,
 				int duration, u32 mask, u32 status)
 {
+	int timeout_error, err = 0;
 	u32 value;
-	int timeout_error;
 	u8 retries;
 
-	value = qlcnic_83xx_rd_reg_indirect(p_dev, addr);
+	value = QLCRD32(p_dev, addr, &err);
+	if (err == -EIO)
+		return err;
 	retries = duration / 10;
 
 	do {
 		if ((value & mask) != status) {
 			timeout_error = 1;
 			msleep(duration / 10);
-			value = qlcnic_83xx_rd_reg_indirect(p_dev, addr);
+			value = QLCRD32(p_dev, addr, &err);
+			if (err == -EIO)
+				return err;
 		} else {
 			timeout_error = 0;
 			break;
@@ -1606,9 +1626,12 @@ int qlcnic_83xx_get_reset_instruction_template(struct qlcnic_adapter *p_dev)
 static void qlcnic_83xx_read_write_crb_reg(struct qlcnic_adapter *p_dev,
 					   u32 raddr, u32 waddr)
 {
-	int value;
+	int err = 0;
+	u32 value;
 
-	value = qlcnic_83xx_rd_reg_indirect(p_dev, raddr);
+	value = QLCRD32(p_dev, raddr, &err);
+	if (err == -EIO)
+		return;
 	qlcnic_83xx_wrt_reg_indirect(p_dev, waddr, value);
 }
 
@@ -1617,12 +1640,16 @@ static void qlcnic_83xx_rmw_crb_reg(struct qlcnic_adapter *p_dev,
 				    u32 raddr, u32 waddr,
 				    struct qlc_83xx_rmw *p_rmw_hdr)
 {
-	int value;
+	int err = 0;
+	u32 value;
 
-	if (p_rmw_hdr->index_a)
+	if (p_rmw_hdr->index_a) {
 		value = p_dev->ahw->reset.array[p_rmw_hdr->index_a];
-	else
-		value = qlcnic_83xx_rd_reg_indirect(p_dev, raddr);
+	} else {
+		value = QLCRD32(p_dev, raddr, &err);
+		if (err == -EIO)
+			return;
+	}
 
 	value &= p_rmw_hdr->mask;
 	value <<= p_rmw_hdr->shl;
@@ -1675,7 +1702,7 @@ static void qlcnic_83xx_poll_list(struct qlcnic_adapter *p_dev,
 	long delay;
 	struct qlc_83xx_entry *entry;
 	struct qlc_83xx_poll *poll;
-	int i;
+	int i, err = 0;
 	unsigned long arg1, arg2;
 
 	poll = (struct qlc_83xx_poll *)((char *)p_hdr +
@@ -1699,10 +1726,12 @@ static void qlcnic_83xx_poll_list(struct qlcnic_adapter *p_dev,
 							 arg1, delay,
 							 poll->mask,
 							 poll->status)){
-					qlcnic_83xx_rd_reg_indirect(p_dev,
-								    arg1);
-					qlcnic_83xx_rd_reg_indirect(p_dev,
-								    arg2);
+					QLCRD32(p_dev, arg1, &err);
+					if (err == -EIO)
+						return;
+					QLCRD32(p_dev, arg2, &err);
+					if (err == -EIO)
+						return;
 				}
 			}
 		}
@@ -1768,7 +1797,7 @@ static void qlcnic_83xx_poll_read_list(struct qlcnic_adapter *p_dev,
 				       struct qlc_83xx_entry_hdr *p_hdr)
 {
 	long delay;
-	int index, i, j;
+	int index, i, j, err;
 	struct qlc_83xx_quad_entry *entry;
 	struct qlc_83xx_poll *poll;
 	unsigned long addr;
@@ -1788,7 +1817,10 @@ static void qlcnic_83xx_poll_read_list(struct qlcnic_adapter *p_dev,
 						  poll->mask, poll->status)){
 				index = p_dev->ahw->reset.array_index;
 				addr = entry->dr_addr;
-				j = qlcnic_83xx_rd_reg_indirect(p_dev, addr);
+				j = QLCRD32(p_dev, addr, &err);
+				if (err == -EIO)
+					return;
+
 				p_dev->ahw->reset.array[index++] = j;
 
 				if (index == QLC_83XX_MAX_RESET_SEQ_ENTRIES)
@@ -2123,6 +2155,8 @@ int qlcnic_83xx_init(struct qlcnic_adapter *adapter, int pci_using_dac)
 	set_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status);
 	qlcnic_83xx_clear_function_resources(adapter);
 
+	INIT_DELAYED_WORK(&adapter->idc_aen_work, qlcnic_83xx_idc_aen_work);
+
 	/* register for NIC IDC AEN Events */
 	qlcnic_83xx_register_nic_idc_func(adapter, 1);
 
@@ -2140,8 +2174,6 @@ int qlcnic_83xx_init(struct qlcnic_adapter *adapter, int pci_using_dac)
 	if (adapter->nic_ops->init_driver(adapter))
 		return -EIO;
 
-	INIT_DELAYED_WORK(&adapter->idc_aen_work, qlcnic_83xx_idc_aen_work);
-
 	/* Periodically monitor device status */
 	qlcnic_83xx_idc_poll_dev_state(&adapter->fw_work.work);
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
index 0581a484ceb5..d09389b33474 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
@@ -104,7 +104,7 @@ static u32
 qlcnic_poll_rsp(struct qlcnic_adapter *adapter)
 {
 	u32 rsp;
-	int timeout = 0;
+	int timeout = 0, err = 0;
 
 	do {
 		/* give atleast 1ms for firmware to respond */
@@ -113,7 +113,7 @@ qlcnic_poll_rsp(struct qlcnic_adapter *adapter)
 		if (++timeout > QLCNIC_OS_CRB_RETRY_COUNT)
 			return QLCNIC_CDRP_RSP_TIMEOUT;
 
-		rsp = QLCRD32(adapter, QLCNIC_CDRP_CRB_OFFSET);
+		rsp = QLCRD32(adapter, QLCNIC_CDRP_CRB_OFFSET, &err);
 	} while (!QLCNIC_CDRP_IS_RSP(rsp));
 
 	return rsp;
@@ -122,7 +122,7 @@ qlcnic_poll_rsp(struct qlcnic_adapter *adapter)
 int qlcnic_82xx_issue_cmd(struct qlcnic_adapter *adapter,
 			  struct qlcnic_cmd_args *cmd)
 {
-	int i;
+	int i, err = 0;
 	u32 rsp;
 	u32 signature;
 	struct pci_dev *pdev = adapter->pdev;
@@ -148,7 +148,7 @@ int qlcnic_82xx_issue_cmd(struct qlcnic_adapter *adapter,
 		dev_err(&pdev->dev, "card response timeout.\n");
 		cmd->rsp.arg[0] = QLCNIC_RCODE_TIMEOUT;
 	} else if (rsp == QLCNIC_CDRP_RSP_FAIL) {
-		cmd->rsp.arg[0] = QLCRD32(adapter, QLCNIC_CDRP_ARG(1));
+		cmd->rsp.arg[0] = QLCRD32(adapter, QLCNIC_CDRP_ARG(1), &err);
 		switch (cmd->rsp.arg[0]) {
 		case QLCNIC_RCODE_INVALID_ARGS:
 			fmt = "CDRP invalid args: [%d]\n";
@@ -175,7 +175,7 @@ int qlcnic_82xx_issue_cmd(struct qlcnic_adapter *adapter,
 		cmd->rsp.arg[0] = QLCNIC_RCODE_SUCCESS;
 
 	for (i = 1; i < cmd->rsp.num; i++)
-		cmd->rsp.arg[i] = QLCRD32(adapter, QLCNIC_CDRP_ARG(i));
+		cmd->rsp.arg[i] = QLCRD32(adapter, QLCNIC_CDRP_ARG(i), &err);
 
 	/* Release semaphore */
 	qlcnic_api_unlock(adapter);
@@ -210,10 +210,10 @@ int qlcnic_fw_cmd_set_drv_version(struct qlcnic_adapter *adapter, u32 fw_cmd)
 	if (err) {
 		dev_info(&adapter->pdev->dev,
 			 "Failed to set driver version in firmware\n");
-		return -EIO;
+		err = -EIO;
 	}
-
-	return 0;
+	qlcnic_free_mbx_args(&cmd);
+	return err;
 }
 
 int
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 700a46324d09..7aac23ab31d1 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -150,6 +150,7 @@ static const char qlcnic_gstrings_test[][ETH_GSTRING_LEN] = {
 	"Link_Test_on_offline",
 	"Interrupt_Test_offline",
 	"Internal_Loopback_offline",
+	"External_Loopback_offline",
 	"EEPROM_Test_offline"
 };
 
@@ -266,7 +267,7 @@ int qlcnic_82xx_get_settings(struct qlcnic_adapter *adapter,
 {
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 	u32 speed, reg;
-	int check_sfp_module = 0;
+	int check_sfp_module = 0, err = 0;
 	u16 pcifn = ahw->pci_func;
 
 	/* read which mode */
@@ -289,7 +290,7 @@ int qlcnic_82xx_get_settings(struct qlcnic_adapter *adapter,
 
 	} else if (adapter->ahw->port_type == QLCNIC_XGBE) {
 		u32 val = 0;
-		val = QLCRD32(adapter, QLCNIC_PORT_MODE_ADDR);
+		val = QLCRD32(adapter, QLCNIC_PORT_MODE_ADDR, &err);
 
 		if (val == QLCNIC_PORT_MODE_802_3_AP) {
 			ecmd->supported = SUPPORTED_1000baseT_Full;
@@ -300,9 +301,13 @@ int qlcnic_82xx_get_settings(struct qlcnic_adapter *adapter,
 		}
 
 		if (netif_running(adapter->netdev) && ahw->has_link_events) {
-			reg = QLCRD32(adapter, P3P_LINK_SPEED_REG(pcifn));
-			speed = P3P_LINK_SPEED_VAL(pcifn, reg);
-			ahw->link_speed = speed * P3P_LINK_SPEED_MHZ;
+			if (ahw->linkup) {
+				reg = QLCRD32(adapter,
+					      P3P_LINK_SPEED_REG(pcifn), &err);
+				speed = P3P_LINK_SPEED_VAL(pcifn, reg);
+				ahw->link_speed = speed * P3P_LINK_SPEED_MHZ;
+			}
+
 			ethtool_cmd_speed_set(ecmd, ahw->link_speed);
 			ecmd->autoneg = ahw->link_autoneg;
 			ecmd->duplex = ahw->link_duplex;
@@ -463,13 +468,14 @@ static int qlcnic_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 static int qlcnic_82xx_get_registers(struct qlcnic_adapter *adapter,
 				     u32 *regs_buff)
 {
-	int i, j = 0;
+	int i, j = 0, err = 0;
 
 	for (i = QLCNIC_DEV_INFO_SIZE + 1; diag_registers[j] != -1; j++, i++)
 		regs_buff[i] = QLC_SHARED_REG_RD32(adapter, diag_registers[j]);
 	j = 0;
 	while (ext_diag_registers[j] != -1)
-		regs_buff[i++] = QLCRD32(adapter, ext_diag_registers[j++]);
+		regs_buff[i++] = QLCRD32(adapter, ext_diag_registers[j++],
+					 &err);
 	return i;
 }
 
@@ -519,13 +525,16 @@ qlcnic_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p)
 static u32 qlcnic_test_link(struct net_device *dev)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(dev);
+	int err = 0;
 	u32 val;
 
 	if (qlcnic_83xx_check(adapter)) {
 		val = qlcnic_83xx_test_link(adapter);
 		return (val & 1) ? 0 : 1;
 	}
-	val = QLCRD32(adapter, CRB_XG_STATE_P3P);
+	val = QLCRD32(adapter, CRB_XG_STATE_P3P, &err);
+	if (err == -EIO)
+		return err;
 	val = XG_LINK_STATE_P3P(adapter->ahw->pci_func, val);
 	return (val == XG_LINK_UP_P3P) ? 0 : 1;
 }
@@ -658,6 +667,7 @@ qlcnic_get_pauseparam(struct net_device *netdev,
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int port = adapter->ahw->physical_port;
+	int err = 0;
 	__u32 val;
 
 	if (qlcnic_83xx_check(adapter)) {
@@ -668,9 +678,13 @@ qlcnic_get_pauseparam(struct net_device *netdev,
 		if ((port < 0) || (port > QLCNIC_NIU_MAX_GBE_PORTS))
 			return;
 		/* get flow control settings */
-		val = QLCRD32(adapter, QLCNIC_NIU_GB_MAC_CONFIG_0(port));
+		val = QLCRD32(adapter, QLCNIC_NIU_GB_MAC_CONFIG_0(port), &err);
+		if (err == -EIO)
+			return;
 		pause->rx_pause = qlcnic_gb_get_rx_flowctl(val);
-		val = QLCRD32(adapter, QLCNIC_NIU_GB_PAUSE_CTL);
+		val = QLCRD32(adapter, QLCNIC_NIU_GB_PAUSE_CTL, &err);
+		if (err == -EIO)
+			return;
 		switch (port) {
 		case 0:
 			pause->tx_pause = !(qlcnic_gb_get_gb0_mask(val));
@@ -690,7 +704,9 @@ qlcnic_get_pauseparam(struct net_device *netdev,
 		if ((port < 0) || (port > QLCNIC_NIU_MAX_XG_PORTS))
 			return;
 		pause->rx_pause = 1;
-		val = QLCRD32(adapter, QLCNIC_NIU_XG_PAUSE_CTL);
+		val = QLCRD32(adapter, QLCNIC_NIU_XG_PAUSE_CTL, &err);
+		if (err == -EIO)
+			return;
 		if (port == 0)
 			pause->tx_pause = !(qlcnic_xg_get_xg0_mask(val));
 		else
@@ -707,6 +723,7 @@ qlcnic_set_pauseparam(struct net_device *netdev,
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int port = adapter->ahw->physical_port;
+	int err = 0;
 	__u32 val;
 
 	if (qlcnic_83xx_check(adapter))
@@ -717,7 +734,9 @@ qlcnic_set_pauseparam(struct net_device *netdev,
 		if ((port < 0) || (port > QLCNIC_NIU_MAX_GBE_PORTS))
 			return -EIO;
 		/* set flow control */
-		val = QLCRD32(adapter, QLCNIC_NIU_GB_MAC_CONFIG_0(port));
+		val = QLCRD32(adapter, QLCNIC_NIU_GB_MAC_CONFIG_0(port), &err);
+		if (err == -EIO)
+			return err;
 
 		if (pause->rx_pause)
 			qlcnic_gb_rx_flowctl(val);
@@ -728,7 +747,9 @@ qlcnic_set_pauseparam(struct net_device *netdev,
 				val);
 		QLCWR32(adapter, QLCNIC_NIU_GB_MAC_CONFIG_0(port), val);
 		/* set autoneg */
-		val = QLCRD32(adapter, QLCNIC_NIU_GB_PAUSE_CTL);
+		val = QLCRD32(adapter, QLCNIC_NIU_GB_PAUSE_CTL, &err);
+		if (err == -EIO)
+			return err;
 		switch (port) {
 		case 0:
 			if (pause->tx_pause)
@@ -764,7 +785,9 @@ qlcnic_set_pauseparam(struct net_device *netdev,
 		if ((port < 0) || (port > QLCNIC_NIU_MAX_XG_PORTS))
 			return -EIO;
 
-		val = QLCRD32(adapter, QLCNIC_NIU_XG_PAUSE_CTL);
+		val = QLCRD32(adapter, QLCNIC_NIU_XG_PAUSE_CTL, &err);
+		if (err == -EIO)
+			return err;
 		if (port == 0) {
 			if (pause->tx_pause)
 				qlcnic_xg_unset_xg0_mask(val);
@@ -788,11 +811,14 @@ static int qlcnic_reg_test(struct net_device *dev)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(dev);
 	u32 data_read;
+	int err = 0;
 
 	if (qlcnic_83xx_check(adapter))
 		return qlcnic_83xx_reg_test(adapter);
 
-	data_read = QLCRD32(adapter, QLCNIC_PCIX_PH_REG(0));
+	data_read = QLCRD32(adapter, QLCNIC_PCIX_PH_REG(0), &err);
+	if (err == -EIO)
+		return err;
 	if ((data_read & 0xffff) != adapter->pdev->vendor)
 		return 1;
 
@@ -1026,8 +1052,15 @@ qlcnic_diag_test(struct net_device *dev, struct ethtool_test *eth_test,
 		if (data[3])
 			eth_test->flags |= ETH_TEST_FL_FAILED;
 
-		data[4] = qlcnic_eeprom_test(dev);
-		if (data[4])
+		if (eth_test->flags & ETH_TEST_FL_EXTERNAL_LB) {
+			data[4] = qlcnic_loopback_test(dev, QLCNIC_ELB_MODE);
+			if (data[4])
+				eth_test->flags |= ETH_TEST_FL_FAILED;
+			eth_test->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE;
+		}
+
+		data[5] = qlcnic_eeprom_test(dev);
+		if (data[5])
 			eth_test->flags |= ETH_TEST_FL_FAILED;
 	}
 }
@@ -1257,17 +1290,20 @@ qlcnic_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(dev);
 	u32 wol_cfg;
+	int err = 0;
 
 	if (qlcnic_83xx_check(adapter))
 		return;
 	wol->supported = 0;
 	wol->wolopts = 0;
 
-	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG_NV);
+	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG_NV, &err);
+	if (err == -EIO)
+		return;
 	if (wol_cfg & (1UL << adapter->portnum))
 		wol->supported |= WAKE_MAGIC;
 
-	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG);
+	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG, &err);
 	if (wol_cfg & (1UL << adapter->portnum))
 		wol->wolopts |= WAKE_MAGIC;
 }
@@ -1277,17 +1313,22 @@ qlcnic_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(dev);
 	u32 wol_cfg;
+	int err = 0;
 
 	if (qlcnic_83xx_check(adapter))
 		return -EOPNOTSUPP;
 	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EINVAL;
 
-	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG_NV);
+	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG_NV, &err);
+	if (err == -EIO)
+		return err;
 	if (!(wol_cfg & (1 << adapter->portnum)))
 		return -EOPNOTSUPP;
 
-	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG);
+	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG, &err);
+	if (err == -EIO)
+		return err;
 	if (wol->wolopts & WAKE_MAGIC)
 		wol_cfg |= 1UL << adapter->portnum;
 	else
@@ -1540,7 +1581,7 @@ qlcnic_set_dump(struct net_device *netdev, struct ethtool_dump *val)
 		return 0;
 	case QLCNIC_SET_QUIESCENT:
 	case QLCNIC_RESET_QUIESCENT:
-		state = QLCRD32(adapter, QLCNIC_CRB_DEV_STATE);
+		state = QLC_SHARED_REG_RD32(adapter, QLCNIC_CRB_DEV_STATE);
 		if (state == QLCNIC_DEV_FAILED || (state == QLCNIC_DEV_BADBAD))
 			netdev_info(netdev, "Device in FAILED state\n");
 		return 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index 5b5d2edf125d..4d5f59b2d153 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -317,16 +317,20 @@ static void qlcnic_write_window_reg(u32 addr, void __iomem *bar0, u32 data)
 int
 qlcnic_pcie_sem_lock(struct qlcnic_adapter *adapter, int sem, u32 id_reg)
 {
-	int done = 0, timeout = 0;
+	int timeout = 0;
+	int err = 0;
+	u32 done = 0;
 
 	while (!done) {
-		done = QLCRD32(adapter, QLCNIC_PCIE_REG(PCIE_SEM_LOCK(sem)));
+		done = QLCRD32(adapter, QLCNIC_PCIE_REG(PCIE_SEM_LOCK(sem)),
+			       &err);
 		if (done == 1)
 			break;
 		if (++timeout >= QLCNIC_PCIE_SEM_TIMEOUT) {
 			dev_err(&adapter->pdev->dev,
 				"Failed to acquire sem=%d lock; holdby=%d\n",
-				sem, id_reg ? QLCRD32(adapter, id_reg) : -1);
+				sem,
+				id_reg ? QLCRD32(adapter, id_reg, &err) : -1);
 			return -EIO;
 		}
 		msleep(1);
@@ -341,19 +345,22 @@ qlcnic_pcie_sem_lock(struct qlcnic_adapter *adapter, int sem, u32 id_reg)
 void
 qlcnic_pcie_sem_unlock(struct qlcnic_adapter *adapter, int sem)
 {
-	QLCRD32(adapter, QLCNIC_PCIE_REG(PCIE_SEM_UNLOCK(sem)));
+	int err = 0;
+
+	QLCRD32(adapter, QLCNIC_PCIE_REG(PCIE_SEM_UNLOCK(sem)), &err);
 }
 
 int qlcnic_ind_rd(struct qlcnic_adapter *adapter, u32 addr)
 {
+	int err = 0;
 	u32 data;
 
 	if (qlcnic_82xx_check(adapter))
 		qlcnic_read_window_reg(addr, adapter->ahw->pci_base0, &data);
 	else {
-		data = qlcnic_83xx_rd_reg_indirect(adapter, addr);
-		if (data == -EIO)
-			return -EIO;
+		data = QLCRD32(adapter, addr, &err);
+		if (err == -EIO)
+			return err;
 	}
 	return data;
 }
@@ -516,20 +523,18 @@ void __qlcnic_set_multi(struct net_device *netdev, u16 vlan)
 	if (netdev->flags & IFF_PROMISC) {
 		if (!(adapter->flags & QLCNIC_PROMISC_DISABLED))
 			mode = VPORT_MISS_MODE_ACCEPT_ALL;
-	} else if (netdev->flags & IFF_ALLMULTI) {
-		if (netdev_mc_count(netdev) > ahw->max_mc_count) {
-			mode = VPORT_MISS_MODE_ACCEPT_MULTI;
-		} else if (!netdev_mc_empty(netdev) &&
-			   !qlcnic_sriov_vf_check(adapter)) {
-				netdev_for_each_mc_addr(ha, netdev)
-					qlcnic_nic_add_mac(adapter, ha->addr,
-							   vlan);
-		}
-		if (mode != VPORT_MISS_MODE_ACCEPT_MULTI &&
-		    qlcnic_sriov_vf_check(adapter))
-			qlcnic_vf_add_mc_list(netdev, vlan);
+	} else if ((netdev->flags & IFF_ALLMULTI) ||
+		   (netdev_mc_count(netdev) > ahw->max_mc_count)) {
+		mode = VPORT_MISS_MODE_ACCEPT_MULTI;
+	} else if (!netdev_mc_empty(netdev) &&
+		   !qlcnic_sriov_vf_check(adapter)) {
+		netdev_for_each_mc_addr(ha, netdev)
+			qlcnic_nic_add_mac(adapter, ha->addr, vlan);
 	}
 
+	if (qlcnic_sriov_vf_check(adapter))
+		qlcnic_vf_add_mc_list(netdev, vlan);
+
 	/* configure unicast MAC address, if there is not sufficient space
 	 * to store all the unicast addresses then enable promiscuous mode
 	 */
@@ -1161,7 +1166,8 @@ int qlcnic_82xx_hw_write_wx_2M(struct qlcnic_adapter *adapter, ulong off,
 	return -EIO;
 }
 
-int qlcnic_82xx_hw_read_wx_2M(struct qlcnic_adapter *adapter, ulong off)
+int qlcnic_82xx_hw_read_wx_2M(struct qlcnic_adapter *adapter, ulong off,
+			      int *err)
 {
 	unsigned long flags;
 	int rv;
@@ -1417,7 +1423,7 @@ int qlcnic_pci_mem_read_2M(struct qlcnic_adapter *adapter, u64 off, u64 *data)
 
 int qlcnic_82xx_get_board_info(struct qlcnic_adapter *adapter)
 {
-	int offset, board_type, magic;
+	int offset, board_type, magic, err = 0;
 	struct pci_dev *pdev = adapter->pdev;
 
 	offset = QLCNIC_FW_MAGIC_OFFSET;
@@ -1437,7 +1443,9 @@ int qlcnic_82xx_get_board_info(struct qlcnic_adapter *adapter)
 	adapter->ahw->board_type = board_type;
 
 	if (board_type == QLCNIC_BRDTYPE_P3P_4_GB_MM) {
-		u32 gpio = QLCRD32(adapter, QLCNIC_ROMUSB_GLB_PAD_GPIO_I);
+		u32 gpio = QLCRD32(adapter, QLCNIC_ROMUSB_GLB_PAD_GPIO_I, &err);
+		if (err == -EIO)
+			return err;
 		if ((gpio & 0x8000) == 0)
 			board_type = QLCNIC_BRDTYPE_P3P_10G_TP;
 	}
@@ -1477,10 +1485,13 @@ int
 qlcnic_wol_supported(struct qlcnic_adapter *adapter)
 {
 	u32 wol_cfg;
+	int err = 0;
 
-	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG_NV);
+	wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG_NV, &err);
 	if (wol_cfg & (1UL << adapter->portnum)) {
-		wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG);
+		wol_cfg = QLCRD32(adapter, QLCNIC_WOL_CONFIG, &err);
+		if (err == -EIO)
+			return err;
 		if (wol_cfg & (1 << adapter->portnum))
 			return 1;
 	}
@@ -1541,6 +1552,7 @@ void qlcnic_82xx_get_func_no(struct qlcnic_adapter *adapter)
 void qlcnic_82xx_read_crb(struct qlcnic_adapter *adapter, char *buf,
 			  loff_t offset, size_t size)
 {
+	int err = 0;
 	u32 data;
 	u64 qmdata;
 
@@ -1548,7 +1560,7 @@ void qlcnic_82xx_read_crb(struct qlcnic_adapter *adapter, char *buf,
 		qlcnic_pci_camqm_read_2M(adapter, offset, &qmdata);
 		memcpy(buf, &qmdata, size);
 	} else {
-		data = QLCRD32(adapter, offset);
+		data = QLCRD32(adapter, offset, &err);
 		memcpy(buf, &data, size);
 	}
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
index 2c22504f57aa..4a71b28effcb 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
@@ -154,7 +154,7 @@ struct qlcnic_hardware_context;
 struct qlcnic_adapter;
 
 int qlcnic_82xx_start_firmware(struct qlcnic_adapter *);
-int qlcnic_82xx_hw_read_wx_2M(struct qlcnic_adapter *adapter, ulong);
+int qlcnic_82xx_hw_read_wx_2M(struct qlcnic_adapter *adapter, ulong, int *);
 int qlcnic_82xx_hw_write_wx_2M(struct qlcnic_adapter *, ulong, u32);
 int qlcnic_82xx_config_hw_lro(struct qlcnic_adapter *adapter, int);
 int qlcnic_82xx_nic_set_promisc(struct qlcnic_adapter *adapter, u32);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
index d28336fc65ab..974d62607e13 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
@@ -142,7 +142,7 @@ void qlcnic_release_tx_buffers(struct qlcnic_adapter *adapter)
 					 buffrag->length, PCI_DMA_TODEVICE);
 			buffrag->dma = 0ULL;
 		}
-		for (j = 0; j < cmd_buf->frag_count; j++) {
+		for (j = 1; j < cmd_buf->frag_count; j++) {
 			buffrag++;
 			if (buffrag->dma) {
 				pci_unmap_page(adapter->pdev, buffrag->dma,
@@ -286,10 +286,11 @@ static int qlcnic_wait_rom_done(struct qlcnic_adapter *adapter)
 {
 	long timeout = 0;
 	long done = 0;
+	int err = 0;
 
 	cond_resched();
 	while (done == 0) {
-		done = QLCRD32(adapter, QLCNIC_ROMUSB_GLB_STATUS);
+		done = QLCRD32(adapter, QLCNIC_ROMUSB_GLB_STATUS, &err);
 		done &= 2;
 		if (++timeout >= QLCNIC_MAX_ROM_WAIT_USEC) {
 			dev_err(&adapter->pdev->dev,
@@ -304,6 +305,8 @@ static int qlcnic_wait_rom_done(struct qlcnic_adapter *adapter)
 static int do_rom_fast_read(struct qlcnic_adapter *adapter,
 			    u32 addr, u32 *valp)
 {
+	int err = 0;
+
 	QLCWR32(adapter, QLCNIC_ROMUSB_ROM_ADDRESS, addr);
 	QLCWR32(adapter, QLCNIC_ROMUSB_ROM_DUMMY_BYTE_CNT, 0);
 	QLCWR32(adapter, QLCNIC_ROMUSB_ROM_ABYTE_CNT, 3);
@@ -317,7 +320,9 @@ static int do_rom_fast_read(struct qlcnic_adapter *adapter,
 	udelay(10);
 	QLCWR32(adapter, QLCNIC_ROMUSB_ROM_DUMMY_BYTE_CNT, 0);
 
-	*valp = QLCRD32(adapter, QLCNIC_ROMUSB_ROM_RDATA);
+	*valp = QLCRD32(adapter, QLCNIC_ROMUSB_ROM_RDATA, &err);
+	if (err == -EIO)
+		return err;
 	return 0;
 }
 
@@ -369,11 +374,11 @@ int qlcnic_rom_fast_read(struct qlcnic_adapter *adapter, u32 addr, u32 *valp)
 
 int qlcnic_pinit_from_rom(struct qlcnic_adapter *adapter)
 {
-	int addr, val;
+	int addr, err = 0;
 	int i, n, init_delay;
 	struct crb_addr_pair *buf;
 	unsigned offset;
-	u32 off;
+	u32 off, val;
 	struct pci_dev *pdev = adapter->pdev;
 
 	QLC_SHARED_REG_WR32(adapter, QLCNIC_CMDPEG_STATE, 0);
@@ -402,7 +407,9 @@ int qlcnic_pinit_from_rom(struct qlcnic_adapter *adapter)
 	QLCWR32(adapter, QLCNIC_CRB_NIU + 0xb0000, 0x00);
 
 	/* halt sre */
-	val = QLCRD32(adapter, QLCNIC_CRB_SRE + 0x1000);
+	val = QLCRD32(adapter, QLCNIC_CRB_SRE + 0x1000, &err);
+	if (err == -EIO)
+		return err;
 	QLCWR32(adapter, QLCNIC_CRB_SRE + 0x1000, val & (~(0x1)));
 
 	/* halt epg */
@@ -719,10 +726,12 @@ qlcnic_check_flash_fw_ver(struct qlcnic_adapter *adapter)
 static int
 qlcnic_has_mn(struct qlcnic_adapter *adapter)
 {
-	u32 capability;
-	capability = 0;
+	u32 capability = 0;
+	int err = 0;
 
-	capability = QLCRD32(adapter, QLCNIC_PEG_TUNE_CAPABILITY);
+	capability = QLCRD32(adapter, QLCNIC_PEG_TUNE_CAPABILITY, &err);
+	if (err == -EIO)
+		return err;
 	if (capability & QLCNIC_PEG_TUNE_MN_PRESENT)
 		return 1;
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index d3f8797efcc3..6946d354f44f 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -161,36 +161,68 @@ static inline int qlcnic_82xx_is_lb_pkt(u64 sts_data)
 	return (qlcnic_get_sts_status(sts_data) == STATUS_CKSUM_LOOP) ? 1 : 0;
 }
 
+static void qlcnic_delete_rx_list_mac(struct qlcnic_adapter *adapter,
+				      struct qlcnic_filter *fil,
+				      void *addr, u16 vlan_id)
+{
+	int ret;
+	u8 op;
+
+	op = vlan_id ? QLCNIC_MAC_VLAN_ADD : QLCNIC_MAC_ADD;
+	ret = qlcnic_sre_macaddr_change(adapter, addr, vlan_id, op);
+	if (ret)
+		return;
+
+	op = vlan_id ? QLCNIC_MAC_VLAN_DEL : QLCNIC_MAC_DEL;
+	ret = qlcnic_sre_macaddr_change(adapter, addr, vlan_id, op);
+	if (!ret) {
+		hlist_del(&fil->fnode);
+		adapter->rx_fhash.fnum--;
+	}
+}
+
+static struct qlcnic_filter *qlcnic_find_mac_filter(struct hlist_head *head,
+						    void *addr, u16 vlan_id)
+{
+	struct qlcnic_filter *tmp_fil = NULL;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(tmp_fil, n, head, fnode) {
+		if (!memcmp(tmp_fil->faddr, addr, ETH_ALEN) &&
+		    tmp_fil->vlan_id == vlan_id)
+			return tmp_fil;
+	}
+
+	return NULL;
+}
+
 void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter, struct sk_buff *skb,
 			  int loopback_pkt, u16 vlan_id)
 {
 	struct ethhdr *phdr = (struct ethhdr *)(skb->data);
 	struct qlcnic_filter *fil, *tmp_fil;
-	struct hlist_node *n;
 	struct hlist_head *head;
 	unsigned long time;
 	u64 src_addr = 0;
-	u8 hindex, found = 0, op;
+	u8 hindex, op;
 	int ret;
 
 	memcpy(&src_addr, phdr->h_source, ETH_ALEN);
+	hindex = qlcnic_mac_hash(src_addr) &
+		 (adapter->fhash.fbucket_size - 1);
 
 	if (loopback_pkt) {
 		if (adapter->rx_fhash.fnum >= adapter->rx_fhash.fmax)
 			return;
 
-		hindex = qlcnic_mac_hash(src_addr) &
-			 (adapter->fhash.fbucket_size - 1);
 		head = &(adapter->rx_fhash.fhead[hindex]);
 
-		hlist_for_each_entry_safe(tmp_fil, n, head, fnode) {
-			if (!memcmp(tmp_fil->faddr, &src_addr, ETH_ALEN) &&
-			    tmp_fil->vlan_id == vlan_id) {
-				time = tmp_fil->ftime;
-				if (jiffies > (QLCNIC_READD_AGE * HZ + time))
-					tmp_fil->ftime = jiffies;
-				return;
-			}
+		tmp_fil = qlcnic_find_mac_filter(head, &src_addr, vlan_id);
+		if (tmp_fil) {
+			time = tmp_fil->ftime;
+			if (time_after(jiffies, QLCNIC_READD_AGE * HZ + time))
+				tmp_fil->ftime = jiffies;
+			return;
 		}
 
 		fil = kzalloc(sizeof(struct qlcnic_filter), GFP_ATOMIC);
@@ -205,36 +237,37 @@ void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter, struct sk_buff *skb,
 		adapter->rx_fhash.fnum++;
 		spin_unlock(&adapter->rx_mac_learn_lock);
 	} else {
-		hindex = qlcnic_mac_hash(src_addr) &
-			 (adapter->fhash.fbucket_size - 1);
-		head = &(adapter->rx_fhash.fhead[hindex]);
-		spin_lock(&adapter->rx_mac_learn_lock);
-		hlist_for_each_entry_safe(tmp_fil, n, head, fnode) {
-			if (!memcmp(tmp_fil->faddr, &src_addr, ETH_ALEN) &&
-			    tmp_fil->vlan_id == vlan_id) {
-				found = 1;
-				break;
-			}
-		}
+		head = &adapter->fhash.fhead[hindex];
 
-		if (!found) {
-			spin_unlock(&adapter->rx_mac_learn_lock);
-			return;
-		}
+		spin_lock(&adapter->mac_learn_lock);
 
-		op = vlan_id ? QLCNIC_MAC_VLAN_ADD : QLCNIC_MAC_ADD;
-		ret = qlcnic_sre_macaddr_change(adapter, (u8 *)&src_addr,
-						vlan_id, op);
-		if (!ret) {
+		tmp_fil = qlcnic_find_mac_filter(head, &src_addr, vlan_id);
+		if (tmp_fil) {
 			op = vlan_id ? QLCNIC_MAC_VLAN_DEL : QLCNIC_MAC_DEL;
 			ret = qlcnic_sre_macaddr_change(adapter,
 							(u8 *)&src_addr,
 							vlan_id, op);
 			if (!ret) {
-				hlist_del(&(tmp_fil->fnode));
-				adapter->rx_fhash.fnum--;
+				hlist_del(&tmp_fil->fnode);
+				adapter->fhash.fnum--;
 			}
+
+			spin_unlock(&adapter->mac_learn_lock);
+
+			return;
 		}
+
+		spin_unlock(&adapter->mac_learn_lock);
+
+		head = &adapter->rx_fhash.fhead[hindex];
+
+		spin_lock(&adapter->rx_mac_learn_lock);
+
+		tmp_fil = qlcnic_find_mac_filter(head, &src_addr, vlan_id);
+		if (tmp_fil)
+			qlcnic_delete_rx_list_mac(adapter, tmp_fil, &src_addr,
+						  vlan_id);
+
 		spin_unlock(&adapter->rx_mac_learn_lock);
 	}
 }
@@ -262,7 +295,7 @@ void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr,
 
 	mac_req = (struct qlcnic_mac_req *)&(req->words[0]);
 	mac_req->op = vlan_id ? QLCNIC_MAC_VLAN_ADD : QLCNIC_MAC_ADD;
-	memcpy(mac_req->mac_addr, &uaddr, ETH_ALEN);
+	memcpy(mac_req->mac_addr, uaddr, ETH_ALEN);
 
 	vlan_req = (struct qlcnic_vlan_req *)&req->words[1];
 	vlan_req->vlan_id = cpu_to_le16(vlan_id);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 4528f8ec333b..bc05d016c859 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -977,8 +977,8 @@ qlcnic_check_options(struct qlcnic_adapter *adapter)
 static int
 qlcnic_initialize_nic(struct qlcnic_adapter *adapter)
 {
-	int err;
 	struct qlcnic_info nic_info;
+	int err = 0;
 
 	memset(&nic_info, 0, sizeof(struct qlcnic_info));
 	err = qlcnic_get_nic_info(adapter, &nic_info, adapter->ahw->pci_func);
@@ -993,7 +993,9 @@ qlcnic_initialize_nic(struct qlcnic_adapter *adapter)
 
 	if (adapter->ahw->capabilities & QLCNIC_FW_CAPABILITY_MORE_CAPS) {
 		u32 temp;
-		temp = QLCRD32(adapter, CRB_FW_CAPABILITIES_2);
+		temp = QLCRD32(adapter, CRB_FW_CAPABILITIES_2, &err);
+		if (err == -EIO)
+			return err;
 		adapter->ahw->extra_capability[0] = temp;
 	}
 	adapter->ahw->max_mac_filters = nic_info.max_mac_filters;
@@ -1383,6 +1385,8 @@ qlcnic_request_irq(struct qlcnic_adapter *adapter)
 	if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST) {
 		if (qlcnic_82xx_check(adapter))
 			handler = qlcnic_tmp_intr;
+		else
+			handler = qlcnic_83xx_tmp_intr;
 		if (!QLCNIC_IS_MSI_FAMILY(adapter))
 			flags |= IRQF_SHARED;
 
@@ -1531,12 +1535,12 @@ int __qlcnic_up(struct qlcnic_adapter *adapter, struct net_device *netdev)
 	if (netdev->features & NETIF_F_LRO)
 		qlcnic_config_hw_lro(adapter, QLCNIC_LRO_ENABLED);
 
+	set_bit(__QLCNIC_DEV_UP, &adapter->state);
 	qlcnic_napi_enable(adapter);
 
 	qlcnic_linkevent_request(adapter, 1);
 
 	adapter->ahw->reset_context = 0;
-	set_bit(__QLCNIC_DEV_UP, &adapter->state);
 	return 0;
 }
 
@@ -2139,7 +2143,7 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (qlcnic_83xx_check(adapter) && !qlcnic_use_msi_x &&
 	    !!qlcnic_use_msi)
 		dev_warn(&pdev->dev,
-			 "83xx adapter do not support MSI interrupts\n");
+			 "Device does not support MSI interrupts\n");
 
 	err = qlcnic_setup_intr(adapter, 0);
 	if (err) {
@@ -2161,7 +2165,8 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_out_disable_mbx_intr;
 
-	qlcnic_set_drv_version(adapter);
+	if (adapter->portnum == 0)
+		qlcnic_set_drv_version(adapter);
 
 	pci_set_drvdata(pdev, adapter);
 
@@ -3081,7 +3086,8 @@ done:
 	adapter->fw_fail_cnt = 0;
 	adapter->flags &= ~QLCNIC_FW_HANG;
 	clear_bit(__QLCNIC_RESETTING, &adapter->state);
-	qlcnic_set_drv_version(adapter);
+	if (adapter->portnum == 0)
+		qlcnic_set_drv_version(adapter);
 
 	if (!qlcnic_clr_drv_state(adapter))
 		qlcnic_schedule_work(adapter, qlcnic_fw_poll_work,
@@ -3093,6 +3099,7 @@ qlcnic_check_health(struct qlcnic_adapter *adapter)
 {
 	u32 state = 0, heartbeat;
 	u32 peg_status;
+	int err = 0;
 
 	if (qlcnic_check_temp(adapter))
 		goto detach;
@@ -3139,11 +3146,11 @@ qlcnic_check_health(struct qlcnic_adapter *adapter)
 			"PEG_NET_4_PC: 0x%x\n",
 			peg_status,
 			QLC_SHARED_REG_RD32(adapter, QLCNIC_PEG_HALT_STATUS2),
-			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_0 + 0x3c),
-			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_1 + 0x3c),
-			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_2 + 0x3c),
-			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_3 + 0x3c),
-			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_4 + 0x3c));
+			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_0 + 0x3c, &err),
+			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_1 + 0x3c, &err),
+			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_2 + 0x3c, &err),
+			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_3 + 0x3c, &err),
+			QLCRD32(adapter, QLCNIC_CRB_PEG_NET_4 + 0x3c, &err));
 	if (QLCNIC_FWERROR_CODE(peg_status) == 0x67)
 		dev_err(&adapter->pdev->dev,
 			"Firmware aborted with error code 0x00006700. "
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
index ab8a6744d402..79e54efe07b9 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
@@ -1084,7 +1084,7 @@ flash_temp:
 	tmpl_hdr = ahw->fw_dump.tmpl_hdr;
 	tmpl_hdr->drv_cap_mask = QLCNIC_DUMP_MASK_DEF;
 
-	if ((tmpl_hdr->version & 0xffffff) >= 0x20001)
+	if ((tmpl_hdr->version & 0xfffff) >= 0x20001)
 		ahw->fw_dump.use_pex_dma = true;
 	else
 		ahw->fw_dump.use_pex_dma = false;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index 62380ce89905..5d40045b3cea 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -562,7 +562,7 @@ static int qlcnic_sriov_setup_vf(struct qlcnic_adapter *adapter,
 	INIT_LIST_HEAD(&adapter->vf_mc_list);
 	if (!qlcnic_use_msi_x && !!qlcnic_use_msi)
 		dev_warn(&adapter->pdev->dev,
-			 "83xx adapter do not support MSI interrupts\n");
+			 "Device does not support MSI interrupts\n");
 
 	err = qlcnic_setup_intr(adapter, 1);
 	if (err) {
@@ -762,6 +762,7 @@ static int qlcnic_sriov_alloc_bc_mbx_args(struct qlcnic_cmd_args *mbx, u32 type)
 			memset(mbx->rsp.arg, 0, sizeof(u32) * mbx->rsp.num);
 			mbx->req.arg[0] = (type | (mbx->req.num << 16) |
 					   (3 << 29));
+			mbx->rsp.arg[0] = (type & 0xffff) | mbx->rsp.num << 16;
 			return 0;
 		}
 	}
@@ -813,6 +814,7 @@ static int qlcnic_sriov_prepare_bc_hdr(struct qlcnic_bc_trans *trans,
 		cmd->req.num = trans->req_pay_size / 4;
 		cmd->rsp.num = trans->rsp_pay_size / 4;
 		hdr = trans->rsp_hdr;
+		cmd->op_type = trans->req_hdr->op_type;
 	}
 
 	trans->trans_id = seq;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index ee0c1d307966..eb49cd65378c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -635,12 +635,12 @@ static int qlcnic_sriov_pf_channel_cfg_cmd(struct qlcnic_bc_trans *trans,
 					   struct qlcnic_cmd_args *cmd)
 {
 	struct qlcnic_vf_info *vf = trans->vf;
-	struct qlcnic_adapter *adapter = vf->adapter;
-	int err;
+	struct qlcnic_vport *vp = vf->vp;
+	struct qlcnic_adapter *adapter;
 	u16 func = vf->pci_func;
+	int err;
 
-	cmd->rsp.arg[0] = trans->req_hdr->cmd_op;
-	cmd->rsp.arg[0] |= (1 << 16);
+	adapter = vf->adapter;
 
 	if (trans->req_hdr->cmd_op == QLCNIC_BC_CMD_CHANNEL_INIT) {
 		err = qlcnic_sriov_pf_config_vport(adapter, 1, func);
@@ -650,6 +650,8 @@ static int qlcnic_sriov_pf_channel_cfg_cmd(struct qlcnic_bc_trans *trans,
 				qlcnic_sriov_pf_config_vport(adapter, 0, func);
 		}
 	} else {
+		if (vp->vlan_mode == QLC_GUEST_VLAN_MODE)
+			vp->vlan = 0;
 		err = qlcnic_sriov_pf_config_vport(adapter, 0, func);
 	}
 
@@ -1183,7 +1185,7 @@ static int qlcnic_sriov_pf_get_acl_cmd(struct qlcnic_bc_trans *trans,
 	u8 cmd_op, mode = vp->vlan_mode;
 
 	cmd_op = trans->req_hdr->cmd_op;
-	cmd->rsp.arg[0] = (cmd_op & 0xffff) | 14 << 16 | 1 << 25;
+	cmd->rsp.arg[0] |= 1 << 25;
 
 	switch (mode) {
 	case QLC_GUEST_VLAN_MODE:
@@ -1561,6 +1563,7 @@ void qlcnic_sriov_pf_handle_flr(struct qlcnic_sriov *sriov,
 				struct qlcnic_vf_info *vf)
 {
 	struct net_device *dev = vf->adapter->netdev;
+	struct qlcnic_vport *vp = vf->vp;
 
 	if (!test_and_clear_bit(QLC_BC_VF_STATE, &vf->state)) {
 		clear_bit(QLC_BC_VF_FLR, &vf->state);
@@ -1573,6 +1576,9 @@ void qlcnic_sriov_pf_handle_flr(struct qlcnic_sriov *sriov,
 		return;
 	}
 
+	if (vp->vlan_mode == QLC_GUEST_VLAN_MODE)
+		vp->vlan = 0;
+
 	qlcnic_sriov_schedule_flr(sriov, vf, qlcnic_sriov_pf_process_flr);
 	netdev_info(dev, "FLR received for PCI func %d\n", vf->pci_func);
 }
@@ -1621,13 +1627,15 @@ int qlcnic_sriov_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
-	int i, num_vfs = sriov->num_vfs;
+	int i, num_vfs;
 	struct qlcnic_vf_info *vf_info;
 	u8 *curr_mac;
 
 	if (!qlcnic_sriov_pf_check(adapter))
 		return -EOPNOTSUPP;
 
+	num_vfs = sriov->num_vfs;
+
 	if (!is_valid_ether_addr(mac) || vf >= num_vfs)
 		return -EINVAL;
 
@@ -1741,6 +1749,7 @@ int qlcnic_sriov_set_vf_vlan(struct net_device *netdev, int vf,
 
 	switch (vlan) {
 	case 4095:
+		vp->vlan = 0;
 		vp->vlan_mode = QLC_GUEST_VLAN_MODE;
 		break;
 	case 0:
@@ -1759,6 +1768,29 @@ int qlcnic_sriov_set_vf_vlan(struct net_device *netdev, int vf,
 	return 0;
 }
 
+static inline __u32 qlcnic_sriov_get_vf_vlan(struct qlcnic_adapter *adapter,
+					     struct qlcnic_vport *vp, int vf)
+{
+	__u32 vlan = 0;
+
+	switch (vp->vlan_mode) {
+	case QLC_PVID_MODE:
+		vlan = vp->vlan;
+		break;
+	case QLC_GUEST_VLAN_MODE:
+		vlan = MAX_VLAN_ID;
+		break;
+	case QLC_NO_VLAN_MODE:
+		vlan = 0;
+		break;
+	default:
+		netdev_info(adapter->netdev, "Invalid VLAN mode = %d for VF %d\n",
+			    vp->vlan_mode, vf);
+	}
+
+	return vlan;
+}
+
 int qlcnic_sriov_get_vf_config(struct net_device *netdev,
 			       int vf, struct ifla_vf_info *ivi)
 {
@@ -1774,7 +1806,7 @@ int qlcnic_sriov_get_vf_config(struct net_device *netdev,
 
 	vp = sriov->vf_info[vf].vp;
 	memcpy(&ivi->mac, vp->mac, ETH_ALEN);
-	ivi->vlan = vp->vlan;
+	ivi->vlan = qlcnic_sriov_get_vf_vlan(adapter, vp, vf);
 	ivi->qos = vp->qos;
 	ivi->spoofchk = vp->spoofchk;
 	if (vp->max_tx_bw == MAX_BW)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 10ed82b3baca..660c3f5b2237 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -170,9 +170,9 @@ static int qlcnic_82xx_store_beacon(struct qlcnic_adapter *adapter,
 
 	if (ahw->extra_capability[0] & QLCNIC_FW_CAPABILITY_2_BEACON) {
 		err = qlcnic_get_beacon_state(adapter, &h_beacon_state);
-		if (!err) {
-			dev_info(&adapter->pdev->dev,
-				 "Failed to get current beacon state\n");
+		if (err) {
+			netdev_err(adapter->netdev,
+				   "Failed to get current beacon state\n");
 		} else {
 			if (h_beacon_state == QLCNIC_BEACON_DISABLE)
 				ahw->beacon_state = 0;
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index e6acb9fa5767..d2e591955bdd 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -478,7 +478,7 @@ rx_status_loop:
 
 	while (1) {
 		u32 status, len;
-		dma_addr_t mapping;
+		dma_addr_t mapping, new_mapping;
 		struct sk_buff *skb, *new_skb;
 		struct cp_desc *desc;
 		const unsigned buflen = cp->rx_buf_sz;
@@ -520,6 +520,14 @@ rx_status_loop:
 			goto rx_next;
 		}
 
+		new_mapping = dma_map_single(&cp->pdev->dev, new_skb->data, buflen,
+					 PCI_DMA_FROMDEVICE);
+		if (dma_mapping_error(&cp->pdev->dev, new_mapping)) {
+			dev->stats.rx_dropped++;
+			kfree_skb(new_skb);
+			goto rx_next;
+		}
+
 		dma_unmap_single(&cp->pdev->dev, mapping,
 				 buflen, PCI_DMA_FROMDEVICE);
 
@@ -531,12 +539,11 @@ rx_status_loop:
 
 		skb_put(skb, len);
 
-		mapping = dma_map_single(&cp->pdev->dev, new_skb->data, buflen,
-					 PCI_DMA_FROMDEVICE);
 		cp->rx_skb[rx_tail] = new_skb;
 
 		cp_rx_skb(cp, skb, desc);
 		rx++;
+		mapping = new_mapping;
 
 rx_next:
 		cp->rx_ring[rx_tail].opts2 = 0;
@@ -716,6 +723,22 @@ static inline u32 cp_tx_vlan_tag(struct sk_buff *skb)
 		TxVlanTag | swab16(vlan_tx_tag_get(skb)) : 0x00;
 }
 
+static void unwind_tx_frag_mapping(struct cp_private *cp, struct sk_buff *skb,
+				   int first, int entry_last)
+{
+	int frag, index;
+	struct cp_desc *txd;
+	skb_frag_t *this_frag;
+	for (frag = 0; frag+first < entry_last; frag++) {
+		index = first+frag;
+		cp->tx_skb[index] = NULL;
+		txd = &cp->tx_ring[index];
+		this_frag = &skb_shinfo(skb)->frags[frag];
+		dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr),
+				 skb_frag_size(this_frag), PCI_DMA_TODEVICE);
+	}
+}
+
 static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 					struct net_device *dev)
 {
@@ -749,6 +772,9 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 
 		len = skb->len;
 		mapping = dma_map_single(&cp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE);
+		if (dma_mapping_error(&cp->pdev->dev, mapping))
+			goto out_dma_error;
+
 		txd->opts2 = opts2;
 		txd->addr = cpu_to_le64(mapping);
 		wmb();
@@ -786,6 +812,9 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		first_len = skb_headlen(skb);
 		first_mapping = dma_map_single(&cp->pdev->dev, skb->data,
 					       first_len, PCI_DMA_TODEVICE);
+		if (dma_mapping_error(&cp->pdev->dev, first_mapping))
+			goto out_dma_error;
+
 		cp->tx_skb[entry] = skb;
 		entry = NEXT_TX(entry);
 
@@ -799,6 +828,11 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			mapping = dma_map_single(&cp->pdev->dev,
 						 skb_frag_address(this_frag),
 						 len, PCI_DMA_TODEVICE);
+			if (dma_mapping_error(&cp->pdev->dev, mapping)) {
+				unwind_tx_frag_mapping(cp, skb, first_entry, entry);
+				goto out_dma_error;
+			}
+
 			eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
 
 			ctrl = eor | len | DescOwn;
@@ -859,11 +893,16 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 	if (TX_BUFFS_AVAIL(cp) <= (MAX_SKB_FRAGS + 1))
 		netif_stop_queue(dev);
 
+out_unlock:
 	spin_unlock_irqrestore(&cp->lock, intr_flags);
 
 	cpw8(TxPoll, NormalTxPoll);
 
 	return NETDEV_TX_OK;
+out_dma_error:
+	kfree_skb(skb);
+	cp->dev->stats.tx_dropped++;
+	goto out_unlock;
 }
 
 /* Set or clear the multicast filter for this adaptor.
@@ -1054,6 +1093,10 @@ static int cp_refill_rx(struct cp_private *cp)
 
 		mapping = dma_map_single(&cp->pdev->dev, skb->data,
 					 cp->rx_buf_sz, PCI_DMA_FROMDEVICE);
+		if (dma_mapping_error(&cp->pdev->dev, mapping)) {
+			kfree_skb(skb);
+			goto err_out;
+		}
 		cp->rx_skb[i] = skb;
 
 		cp->rx_ring[i].opts2 = 0;
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 4106a743ca74..85e5c97191dd 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -3689,7 +3689,7 @@ static void rtl_phy_work(struct rtl8169_private *tp)
 	if (tp->link_ok(ioaddr))
 		return;
 
-	netif_warn(tp, link, tp->dev, "PHY reset until link up\n");
+	netif_dbg(tp, link, tp->dev, "PHY reset until link up\n");
 
 	tp->phy_reset_enable(tp);
 
@@ -6468,6 +6468,8 @@ static int rtl8169_close(struct net_device *dev)
 	rtl8169_down(dev);
 	rtl_unlock_work(tp);
 
+	cancel_work_sync(&tp->wk.work);
+
 	free_irq(pdev->irq, dev);
 
 	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
@@ -6793,8 +6795,6 @@ static void rtl_remove_one(struct pci_dev *pdev)
 		rtl8168_driver_stop(tp);
 	}
 
-	cancel_work_sync(&tp->wk.work);
-
 	netif_napi_del(&tp->napi);
 
 	unregister_netdev(dev);
@@ -7088,7 +7088,7 @@ rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	RTL_W8(Cfg9346, Cfg9346_Unlock);
 	RTL_W8(Config1, RTL_R8(Config1) | PMEnable);
-	RTL_W8(Config5, RTL_R8(Config5) & PMEStatus);
+	RTL_W8(Config5, RTL_R8(Config5) & (BWF | MWF | UWF | LanWake | PMEStatus));
 	if ((RTL_R8(Config3) & (LinkUp | MagicPacket)) != 0)
 		tp->features |= RTL_FEATURE_WOL;
 	if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0)
diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c
index b74a60ab9ac7..30d744235d27 100644
--- a/drivers/net/ethernet/sfc/filter.c
+++ b/drivers/net/ethernet/sfc/filter.c
@@ -675,7 +675,7 @@ s32 efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec,
 		BUILD_BUG_ON(EFX_FILTER_INDEX_UC_DEF != 0);
 		BUILD_BUG_ON(EFX_FILTER_INDEX_MC_DEF !=
 			     EFX_FILTER_MC_DEF - EFX_FILTER_UC_DEF);
-		rep_index = spec->type - EFX_FILTER_INDEX_UC_DEF;
+		rep_index = spec->type - EFX_FILTER_UC_DEF;
 		ins_index = rep_index;
 
 		spin_lock_bh(&state->lock);
@@ -1209,7 +1209,9 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 	EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4);
 	ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
 
-	efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT, 0, rxq_index);
+	efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT,
+			   efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
+			   rxq_index);
 	rc = efx_filter_set_ipv4_full(&spec, ip->protocol,
 				      ip->daddr, ports[1], ip->saddr, ports[0]);
 	if (rc)
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index eb4aea3fe793..f5d7ad75e479 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -1318,7 +1318,7 @@ static void sis900_timer(unsigned long data)
 		if (duplex){
 			sis900_set_mode(sis_priv, speed, duplex);
 			sis630_set_eq(net_dev, sis_priv->chipset_rev);
-			netif_start_queue(net_dev);
+			netif_carrier_on(net_dev);
 		}
 
 		sis_priv->timer.expires = jiffies + HZ;
@@ -1336,10 +1336,8 @@ static void sis900_timer(unsigned long data)
 		status = sis900_default_phy(net_dev);
 		mii_phy = sis_priv->mii;
 
-		if (status & MII_STAT_LINK){
+		if (status & MII_STAT_LINK)
 			sis900_check_mode(net_dev, mii_phy);
-			netif_carrier_on(net_dev);
-		}
 	} else {
 	/* Link ON -> OFF */
                 if (!(status & MII_STAT_LINK)){
@@ -1612,12 +1610,6 @@ sis900_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	unsigned int  index_cur_tx, index_dirty_tx;
 	unsigned int  count_dirty_tx;
 
-	/* Don't transmit data before the complete of auto-negotiation */
-	if(!sis_priv->autong_complete){
-		netif_stop_queue(net_dev);
-		return NETDEV_TX_BUSY;
-	}
-
 	spin_lock_irqsave(&sis_priv->lock, flags);
 
 	/* Calculate the next Tx descriptor entry. */
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index c9d942a5c335..1ef9d8a555aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -33,10 +33,15 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 	struct stmmac_priv *priv = (struct stmmac_priv *)p;
 	unsigned int txsize = priv->dma_tx_size;
 	unsigned int entry = priv->cur_tx % txsize;
-	struct dma_desc *desc = priv->dma_tx + entry;
+	struct dma_desc *desc;
 	unsigned int nopaged_len = skb_headlen(skb);
 	unsigned int bmax, len;
 
+	if (priv->extend_desc)
+		desc = (struct dma_desc *)(priv->dma_etx + entry);
+	else
+		desc = priv->dma_tx + entry;
+
 	if (priv->plat->enh_desc)
 		bmax = BUF_SIZE_8KiB;
 	else
@@ -54,7 +59,11 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 						STMMAC_RING_MODE);
 		wmb();
 		entry = (++priv->cur_tx) % txsize;
-		desc = priv->dma_tx + entry;
+
+		if (priv->extend_desc)
+			desc = (struct dma_desc *)(priv->dma_etx + entry);
+		else
+			desc = priv->dma_tx + entry;
 
 		desc->des2 = dma_map_single(priv->device, skb->data + bmax,
 					    len, DMA_TO_DEVICE);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f2ccb36e8685..0a9bb9d30c3f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -939,15 +939,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 
 	skb = __netdev_alloc_skb(priv->dev, priv->dma_buf_sz + NET_IP_ALIGN,
 				 GFP_KERNEL);
-	if (unlikely(skb == NULL)) {
+	if (!skb) {
 		pr_err("%s: Rx init fails; skb is NULL\n", __func__);
-		return 1;
+		return -ENOMEM;
 	}
 	skb_reserve(skb, NET_IP_ALIGN);
 	priv->rx_skbuff[i] = skb;
 	priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
 						priv->dma_buf_sz,
 						DMA_FROM_DEVICE);
+	if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) {
+		pr_err("%s: DMA mapping error\n", __func__);
+		dev_kfree_skb_any(skb);
+		return -EINVAL;
+	}
 
 	p->des2 = priv->rx_skbuff_dma[i];
 
@@ -958,6 +963,16 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 	return 0;
 }
 
+static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i)
+{
+	if (priv->rx_skbuff[i]) {
+		dma_unmap_single(priv->device, priv->rx_skbuff_dma[i],
+				 priv->dma_buf_sz, DMA_FROM_DEVICE);
+		dev_kfree_skb_any(priv->rx_skbuff[i]);
+	}
+	priv->rx_skbuff[i] = NULL;
+}
+
 /**
  * init_dma_desc_rings - init the RX/TX descriptor rings
  * @dev: net device structure
@@ -965,13 +980,14 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
  * and allocates the socket buffers. It suppors the chained and ring
  * modes.
  */
-static void init_dma_desc_rings(struct net_device *dev)
+static int init_dma_desc_rings(struct net_device *dev)
 {
 	int i;
 	struct stmmac_priv *priv = netdev_priv(dev);
 	unsigned int txsize = priv->dma_tx_size;
 	unsigned int rxsize = priv->dma_rx_size;
 	unsigned int bfsize = 0;
+	int ret = -ENOMEM;
 
 	/* Set the max buffer size according to the DESC mode
 	 * and the MTU. Note that RING mode allows 16KiB bsize.
@@ -992,34 +1008,60 @@ static void init_dma_desc_rings(struct net_device *dev)
 							  dma_extended_desc),
 						   &priv->dma_rx_phy,
 						   GFP_KERNEL);
+		if (!priv->dma_erx)
+			goto err_dma;
+
 		priv->dma_etx = dma_alloc_coherent(priv->device, txsize *
 						   sizeof(struct
 							  dma_extended_desc),
 						   &priv->dma_tx_phy,
 						   GFP_KERNEL);
-		if ((!priv->dma_erx) || (!priv->dma_etx))
-			return;
+		if (!priv->dma_etx) {
+			dma_free_coherent(priv->device, priv->dma_rx_size *
+					sizeof(struct dma_extended_desc),
+					priv->dma_erx, priv->dma_rx_phy);
+			goto err_dma;
+		}
 	} else {
 		priv->dma_rx = dma_alloc_coherent(priv->device, rxsize *
 						  sizeof(struct dma_desc),
 						  &priv->dma_rx_phy,
 						  GFP_KERNEL);
+		if (!priv->dma_rx)
+			goto err_dma;
+
 		priv->dma_tx = dma_alloc_coherent(priv->device, txsize *
 						  sizeof(struct dma_desc),
 						  &priv->dma_tx_phy,
 						  GFP_KERNEL);
-		if ((!priv->dma_rx) || (!priv->dma_tx))
-			return;
+		if (!priv->dma_tx) {
+			dma_free_coherent(priv->device, priv->dma_rx_size *
+					sizeof(struct dma_desc),
+					priv->dma_rx, priv->dma_rx_phy);
+			goto err_dma;
+		}
 	}
 
 	priv->rx_skbuff_dma = kmalloc_array(rxsize, sizeof(dma_addr_t),
 					    GFP_KERNEL);
+	if (!priv->rx_skbuff_dma)
+		goto err_rx_skbuff_dma;
+
 	priv->rx_skbuff = kmalloc_array(rxsize, sizeof(struct sk_buff *),
 					GFP_KERNEL);
+	if (!priv->rx_skbuff)
+		goto err_rx_skbuff;
+
 	priv->tx_skbuff_dma = kmalloc_array(txsize, sizeof(dma_addr_t),
 					    GFP_KERNEL);
+	if (!priv->tx_skbuff_dma)
+		goto err_tx_skbuff_dma;
+
 	priv->tx_skbuff = kmalloc_array(txsize, sizeof(struct sk_buff *),
 					GFP_KERNEL);
+	if (!priv->tx_skbuff)
+		goto err_tx_skbuff;
+
 	if (netif_msg_probe(priv)) {
 		pr_debug("(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n", __func__,
 			 (u32) priv->dma_rx_phy, (u32) priv->dma_tx_phy);
@@ -1034,8 +1076,9 @@ static void init_dma_desc_rings(struct net_device *dev)
 		else
 			p = priv->dma_rx + i;
 
-		if (stmmac_init_rx_buffers(priv, p, i))
-			break;
+		ret = stmmac_init_rx_buffers(priv, p, i);
+		if (ret)
+			goto err_init_rx_buffers;
 
 		if (netif_msg_probe(priv))
 			pr_debug("[%p]\t[%p]\t[%x]\n", priv->rx_skbuff[i],
@@ -1081,20 +1124,44 @@ static void init_dma_desc_rings(struct net_device *dev)
 
 	if (netif_msg_hw(priv))
 		stmmac_display_rings(priv);
+
+	return 0;
+err_init_rx_buffers:
+	while (--i >= 0)
+		stmmac_free_rx_buffers(priv, i);
+	kfree(priv->tx_skbuff);
+err_tx_skbuff:
+	kfree(priv->tx_skbuff_dma);
+err_tx_skbuff_dma:
+	kfree(priv->rx_skbuff);
+err_rx_skbuff:
+	kfree(priv->rx_skbuff_dma);
+err_rx_skbuff_dma:
+	if (priv->extend_desc) {
+		dma_free_coherent(priv->device, priv->dma_tx_size *
+				  sizeof(struct dma_extended_desc),
+				  priv->dma_etx, priv->dma_tx_phy);
+		dma_free_coherent(priv->device, priv->dma_rx_size *
+				  sizeof(struct dma_extended_desc),
+				  priv->dma_erx, priv->dma_rx_phy);
+	} else {
+		dma_free_coherent(priv->device,
+				priv->dma_tx_size * sizeof(struct dma_desc),
+				priv->dma_tx, priv->dma_tx_phy);
+		dma_free_coherent(priv->device,
+				priv->dma_rx_size * sizeof(struct dma_desc),
+				priv->dma_rx, priv->dma_rx_phy);
+	}
+err_dma:
+	return ret;
 }
 
 static void dma_free_rx_skbufs(struct stmmac_priv *priv)
 {
 	int i;
 
-	for (i = 0; i < priv->dma_rx_size; i++) {
-		if (priv->rx_skbuff[i]) {
-			dma_unmap_single(priv->device, priv->rx_skbuff_dma[i],
-					 priv->dma_buf_sz, DMA_FROM_DEVICE);
-			dev_kfree_skb_any(priv->rx_skbuff[i]);
-		}
-		priv->rx_skbuff[i] = NULL;
-	}
+	for (i = 0; i < priv->dma_rx_size; i++)
+		stmmac_free_rx_buffers(priv, i);
 }
 
 static void dma_free_tx_skbufs(struct stmmac_priv *priv)
@@ -1560,12 +1627,17 @@ static int stmmac_open(struct net_device *dev)
 	priv->dma_tx_size = STMMAC_ALIGN(dma_txsize);
 	priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize);
 	priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
-	init_dma_desc_rings(dev);
+
+	ret = init_dma_desc_rings(dev);
+	if (ret < 0) {
+		pr_err("%s: DMA descriptors initialization failed\n", __func__);
+		goto dma_desc_error;
+	}
 
 	/* DMA initialization and SW reset */
 	ret = stmmac_init_dma_engine(priv);
 	if (ret < 0) {
-		pr_err("%s: DMA initialization failed\n", __func__);
+		pr_err("%s: DMA engine initialization failed\n", __func__);
 		goto init_error;
 	}
 
@@ -1672,6 +1744,7 @@ wolirq_error:
 
 init_error:
 	free_dma_desc_resources(priv);
+dma_desc_error:
 	if (priv->phydev)
 		phy_disconnect(priv->phydev);
 phy_error:
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 05a1674e204f..22a7a4336211 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1867,7 +1867,7 @@ static int cpsw_probe(struct platform_device *pdev)
 
 	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) {
 		for (i = res->start; i <= res->end; i++) {
-			if (request_irq(i, cpsw_interrupt, IRQF_DISABLED,
+			if (request_irq(i, cpsw_interrupt, 0,
 					dev_name(&pdev->dev), priv)) {
 				dev_err(priv->dev, "error attaching irq\n");
 				goto clean_ale_ret;
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 07b176bcf929..1a222bce4bd7 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1568,8 +1568,7 @@ static int emac_dev_open(struct net_device *ndev)
 	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) {
 		for (i = res->start; i <= res->end; i++) {
 			if (devm_request_irq(&priv->pdev->dev, i, emac_irq,
-					     IRQF_DISABLED,
-					     ndev->name, ndev))
+					     0, ndev->name, ndev))
 				goto rollback;
 		}
 		k++;
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 1d6dc41f755d..d01cacf8a7c2 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -2100,7 +2100,7 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx)
 
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
 	}
-	netif_rx(skb);
+	netif_receive_skb(skb);
 
 	stats->rx_bytes += pkt_len;
 	stats->rx_packets++;
@@ -2884,6 +2884,7 @@ out:
 	return ret;
 
 err_iounmap:
+	netif_napi_del(&vptr->napi);
 	iounmap(regs);
 err_free_dev:
 	free_netdev(netdev);
@@ -2904,6 +2905,7 @@ static int velocity_remove(struct device *dev)
 	struct velocity_info *vptr = netdev_priv(netdev);
 
 	unregister_netdev(netdev);
+	netif_napi_del(&vptr->napi);
 	iounmap(vptr->mac_regs);
 	free_netdev(netdev);
 	velocity_nics--;
diff --git a/drivers/net/irda/via-ircc.c b/drivers/net/irda/via-ircc.c
index 51f2bc376101..2dcc60fb37f1 100644
--- a/drivers/net/irda/via-ircc.c
+++ b/drivers/net/irda/via-ircc.c
@@ -210,8 +210,7 @@ static int via_init_one(struct pci_dev *pcidev, const struct pci_device_id *id)
 			pci_write_config_byte(pcidev,0x42,(bTmp | 0xf0));
 			pci_write_config_byte(pcidev,0x5a,0xc0);
 			WriteLPCReg(0x28, 0x70 );
-			if (via_ircc_open(pcidev, &info, 0x3076) == 0)
-				rc=0;
+			rc = via_ircc_open(pcidev, &info, 0x3076);
 		} else
 			rc = -ENODEV; //IR not turn on	 
 	} else { //Not VT1211
@@ -249,8 +248,7 @@ static int via_init_one(struct pci_dev *pcidev, const struct pci_device_id *id)
 			info.irq=FirIRQ;
 			info.dma=FirDRQ1;
 			info.dma2=FirDRQ0;
-			if (via_ircc_open(pcidev, &info, 0x3096) == 0)
-				rc=0;
+			rc = via_ircc_open(pcidev, &info, 0x3096);
 		} else
 			rc = -ENODEV; //IR not turn on !!!!!
 	}//Not VT1211
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 18373b6ae37d..16b43bf544b7 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -337,8 +337,11 @@ static int macvlan_open(struct net_device *dev)
 	int err;
 
 	if (vlan->port->passthru) {
-		if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC))
-			dev_set_promiscuity(lowerdev, 1);
+		if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) {
+			err = dev_set_promiscuity(lowerdev, 1);
+			if (err < 0)
+				goto out;
+		}
 		goto hash_add;
 	}
 
@@ -736,6 +739,10 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[])
 			return -EADDRNOTAVAIL;
 	}
 
+	if (data && data[IFLA_MACVLAN_FLAGS] &&
+	    nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~MACVLAN_FLAG_NOPROMISC)
+		return -EINVAL;
+
 	if (data && data[IFLA_MACVLAN_MODE]) {
 		switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) {
 		case MACVLAN_MODE_PRIVATE:
@@ -863,6 +870,18 @@ static int macvlan_changelink(struct net_device *dev,
 		struct nlattr *tb[], struct nlattr *data[])
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
+	enum macvlan_mode mode;
+	bool set_mode = false;
+
+	/* Validate mode, but don't set yet: setting flags may fail. */
+	if (data && data[IFLA_MACVLAN_MODE]) {
+		set_mode = true;
+		mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);
+		/* Passthrough mode can't be set or cleared dynamically */
+		if ((mode == MACVLAN_MODE_PASSTHRU) !=
+		    (vlan->mode == MACVLAN_MODE_PASSTHRU))
+			return -EINVAL;
+	}
 
 	if (data && data[IFLA_MACVLAN_FLAGS]) {
 		__u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
@@ -879,8 +898,8 @@ static int macvlan_changelink(struct net_device *dev,
 		}
 		vlan->flags = flags;
 	}
-	if (data && data[IFLA_MACVLAN_MODE])
-		vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);
+	if (set_mode)
+		vlan->mode = mode;
 	return 0;
 }
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index a98fb0ed6aef..ea53abb20988 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -68,6 +68,8 @@ static const struct proto_ops macvtap_socket_ops;
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
 		      NETIF_F_TSO6 | NETIF_F_UFO)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
+#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
+
 /*
  * RCU usage:
  * The macvtap_queue and the macvlan_dev are loosely coupled, the
@@ -278,7 +280,8 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct macvtap_queue *q = macvtap_get_queue(dev, skb);
-	netdev_features_t features;
+	netdev_features_t features = TAP_FEATURES;
+
 	if (!q)
 		goto drop;
 
@@ -287,9 +290,11 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
 
 	skb->dev = dev;
 	/* Apply the forward feature mask so that we perform segmentation
-	 * according to users wishes.
+	 * according to users wishes.  This only works if VNET_HDR is
+	 * enabled.
 	 */
-	features = netif_skb_features(skb) & vlan->tap_features;
+	if (q->flags & IFF_VNET_HDR)
+		features |= vlan->tap_features;
 	if (netif_needs_gso(skb, features)) {
 		struct sk_buff *segs = __skb_gso_segment(skb, features, false);
 
@@ -818,10 +823,13 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 		skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
 	}
-	if (vlan)
+	if (vlan) {
+		local_bh_disable();
 		macvlan_start_xmit(skb, vlan->dev);
-	else
+		local_bh_enable();
+	} else {
 		kfree_skb(skb);
+	}
 	rcu_read_unlock();
 
 	return total_len;
@@ -912,8 +920,11 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 done:
 	rcu_read_lock();
 	vlan = rcu_dereference(q->vlan);
-	if (vlan)
+	if (vlan) {
+		preempt_disable();
 		macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
+		preempt_enable();
+	}
 	rcu_read_unlock();
 
 	return ret ? ret : copied;
@@ -1058,8 +1069,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg)
 	/* tap_features are the same as features on tun/tap and
 	 * reflect user expectations.
 	 */
-	vlan->tap_features = vlan->dev->features &
-			    (feature_mask | ~TUN_OFFLOADS);
+	vlan->tap_features = feature_mask;
 	vlan->set_features = features;
 	netdev_update_features(vlan->dev);
 
@@ -1155,10 +1165,6 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 			    TUN_F_TSO_ECN | TUN_F_UFO))
 			return -EINVAL;
 
-		/* TODO: only accept frames with the features that
-			 got enabled for forwarded frames */
-		if (!(q->flags & IFF_VNET_HDR))
-			return  -EINVAL;
 		rtnl_lock();
 		ret = set_offload(q, arg);
 		rtnl_unlock();
diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/phy/mdio-sun4i.c
index 61d3f4ebf52e..7f25e49ae37f 100644
--- a/drivers/net/phy/mdio-sun4i.c
+++ b/drivers/net/phy/mdio-sun4i.c
@@ -40,7 +40,7 @@ struct sun4i_mdio_data {
 static int sun4i_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct sun4i_mdio_data *data = bus->priv;
-	unsigned long start_jiffies;
+	unsigned long timeout_jiffies;
 	int value;
 
 	/* issue the phy address and reg */
@@ -49,10 +49,9 @@ static int sun4i_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	writel(0x1, data->membase + EMAC_MAC_MCMD_REG);
 
 	/* Wait read complete */
-	start_jiffies = jiffies;
+	timeout_jiffies = jiffies + MDIO_TIMEOUT;
 	while (readl(data->membase + EMAC_MAC_MIND_REG) & 0x1) {
-		if (time_after(start_jiffies,
-			       start_jiffies + MDIO_TIMEOUT))
+		if (time_is_before_jiffies(timeout_jiffies))
 			return -ETIMEDOUT;
 		msleep(1);
 	}
@@ -69,7 +68,7 @@ static int sun4i_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			    u16 value)
 {
 	struct sun4i_mdio_data *data = bus->priv;
-	unsigned long start_jiffies;
+	unsigned long timeout_jiffies;
 
 	/* issue the phy address and reg */
 	writel((mii_id << 8) | regnum, data->membase + EMAC_MAC_MADR_REG);
@@ -77,10 +76,9 @@ static int sun4i_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	writel(0x1, data->membase + EMAC_MAC_MCMD_REG);
 
 	/* Wait read complete */
-	start_jiffies = jiffies;
+	timeout_jiffies = jiffies + MDIO_TIMEOUT;
 	while (readl(data->membase + EMAC_MAC_MIND_REG) & 0x1) {
-		if (time_after(start_jiffies,
-			       start_jiffies + MDIO_TIMEOUT))
+		if (time_is_before_jiffies(timeout_jiffies))
 			return -ETIMEDOUT;
 		msleep(1);
 	}
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 8e7af8354342..138de837977f 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -23,7 +23,7 @@
 #define RTL821x_INER_INIT	0x6400
 #define RTL821x_INSR		0x13
 
-#define	RTL8211E_INER_LINK_STAT	0x10
+#define	RTL8211E_INER_LINK_STATUS	0x400
 
 MODULE_DESCRIPTION("Realtek PHY driver");
 MODULE_AUTHOR("Johnson Leung");
@@ -57,7 +57,7 @@ static int rtl8211e_config_intr(struct phy_device *phydev)
 
 	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
 		err = phy_write(phydev, RTL821x_INER,
-				RTL8211E_INER_LINK_STAT);
+				RTL8211E_INER_LINK_STATUS);
 	else
 		err = phy_write(phydev, RTL821x_INER, 0);
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index db690a372260..71af122edf2d 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1074,8 +1074,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	u32 rxhash;
 
 	if (!(tun->flags & TUN_NO_PI)) {
-		if ((len -= sizeof(pi)) > total_len)
+		if (len < sizeof(pi))
 			return -EINVAL;
+		len -= sizeof(pi);
 
 		if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi)))
 			return -EFAULT;
@@ -1083,8 +1084,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & TUN_VNET_HDR) {
-		if ((len -= tun->vnet_hdr_sz) > total_len)
+		if (len < tun->vnet_hdr_sz)
 			return -EINVAL;
+		len -= tun->vnet_hdr_sz;
 
 		if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
 			return -EFAULT;
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 1e3c302d94fe..2bc87e3a8141 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1029,10 +1029,10 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->mii.supports_gmii = 1;
 
 	dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			      NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+			      NETIF_F_RXCSUM;
 
 	dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-				 NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+				 NETIF_F_RXCSUM;
 
 	/* Enable checksum offload */
 	*tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP |
@@ -1173,7 +1173,6 @@ ax88179_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
 	if (((skb->len + 8) % frame_size) == 0)
 		tx_hdr2 |= 0x80008000;	/* Enable padding */
 
-	skb_linearize(skb);
 	headroom = skb_headroom(skb);
 	tailroom = skb_tailroom(skb);
 
@@ -1317,10 +1316,10 @@ static int ax88179_reset(struct usbnet *dev)
 			  1, 1, tmp);
 
 	dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			      NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+			      NETIF_F_RXCSUM;
 
 	dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-				 NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+				 NETIF_F_RXCSUM;
 
 	/* Enable checksum offload */
 	*tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP |
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index cba1d46e672e..86292e6aaf49 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2816,13 +2816,16 @@ exit:
 static int hso_get_config_data(struct usb_interface *interface)
 {
 	struct usb_device *usbdev = interface_to_usbdev(interface);
-	u8 config_data[17];
+	u8 *config_data = kmalloc(17, GFP_KERNEL);
 	u32 if_num = interface->altsetting->desc.bInterfaceNumber;
 	s32 result;
 
+	if (!config_data)
+		return -ENOMEM;
 	if (usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
 			    0x86, 0xC0, 0, 0, config_data, 17,
 			    USB_CTRL_SET_TIMEOUT) != 0x11) {
+		kfree(config_data);
 		return -EIO;
 	}
 
@@ -2873,6 +2876,7 @@ static int hso_get_config_data(struct usb_interface *interface)
 	if (config_data[16] & 0x1)
 		result |= HSO_INFO_CRC_BUG;
 
+	kfree(config_data);
 	return result;
 }
 
@@ -2886,6 +2890,11 @@ static int hso_probe(struct usb_interface *interface,
 	struct hso_shared_int *shared_int;
 	struct hso_device *tmp_dev = NULL;
 
+	if (interface->cur_altsetting->desc.bInterfaceClass != 0xFF) {
+		dev_err(&interface->dev, "Not our interface\n");
+		return -ENODEV;
+	}
+
 	if_num = interface->altsetting->desc.bInterfaceNumber;
 
 	/* Get the interface/port specification from either driver_info or from
@@ -2895,10 +2904,6 @@ static int hso_probe(struct usb_interface *interface,
 	else
 		port_spec = hso_get_config_data(interface);
 
-	if (interface->cur_altsetting->desc.bInterfaceClass != 0xFF) {
-		dev_err(&interface->dev, "Not our interface\n");
-		return -ENODEV;
-	}
 	/* Check if we need to switch to alt interfaces prior to port
 	 * configuration */
 	if (interface->num_altsetting > 1)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index ee13f9eb740c..11c51f275366 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -344,17 +344,41 @@ static const int multicast_filter_limit = 32;
 static
 int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 {
-	return usb_control_msg(tp->udev, usb_rcvctrlpipe(tp->udev, 0),
+	int ret;
+	void *tmp;
+
+	tmp = kmalloc(size, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	ret = usb_control_msg(tp->udev, usb_rcvctrlpipe(tp->udev, 0),
 			       RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
-			       value, index, data, size, 500);
+			       value, index, tmp, size, 500);
+
+	memcpy(data, tmp, size);
+	kfree(tmp);
+
+	return ret;
 }
 
 static
 int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 {
-	return usb_control_msg(tp->udev, usb_sndctrlpipe(tp->udev, 0),
+	int ret;
+	void *tmp;
+
+	tmp = kmalloc(size, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	memcpy(tmp, data, size);
+
+	ret = usb_control_msg(tp->udev, usb_sndctrlpipe(tp->udev, 0),
 			       RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE,
-			       value, index, data, size, 500);
+			       value, index, tmp, size, 500);
+
+	kfree(tmp);
+	return ret;
 }
 
 static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size,
@@ -490,37 +514,31 @@ int usb_ocp_write(struct r8152 *tp, u16 index, u16 byteen, u16 size, void *data)
 
 static u32 ocp_read_dword(struct r8152 *tp, u16 type, u16 index)
 {
-	u32 data;
+	__le32 data;
 
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_read(tp, index, sizeof(data), &data);
-	else
-		usb_ocp_read(tp, index, sizeof(data), &data);
+	generic_ocp_read(tp, index, sizeof(data), &data, type);
 
 	return __le32_to_cpu(data);
 }
 
 static void ocp_write_dword(struct r8152 *tp, u16 type, u16 index, u32 data)
 {
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_write(tp, index, BYTE_EN_DWORD, sizeof(data), &data);
-	else
-		usb_ocp_write(tp, index, BYTE_EN_DWORD, sizeof(data), &data);
+	__le32 tmp = __cpu_to_le32(data);
+
+	generic_ocp_write(tp, index, BYTE_EN_DWORD, sizeof(tmp), &tmp, type);
 }
 
 static u16 ocp_read_word(struct r8152 *tp, u16 type, u16 index)
 {
 	u32 data;
+	__le32 tmp;
 	u8 shift = index & 2;
 
 	index &= ~3;
 
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_read(tp, index, sizeof(data), &data);
-	else
-		usb_ocp_read(tp, index, sizeof(data), &data);
+	generic_ocp_read(tp, index, sizeof(tmp), &tmp, type);
 
-	data = __le32_to_cpu(data);
+	data = __le32_to_cpu(tmp);
 	data >>= (shift * 8);
 	data &= 0xffff;
 
@@ -529,7 +547,8 @@ static u16 ocp_read_word(struct r8152 *tp, u16 type, u16 index)
 
 static void ocp_write_word(struct r8152 *tp, u16 type, u16 index, u32 data)
 {
-	u32 tmp, mask = 0xffff;
+	u32 mask = 0xffff;
+	__le32 tmp;
 	u16 byen = BYTE_EN_WORD;
 	u8 shift = index & 2;
 
@@ -542,34 +561,25 @@ static void ocp_write_word(struct r8152 *tp, u16 type, u16 index, u32 data)
 		index &= ~3;
 	}
 
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_read(tp, index, sizeof(tmp), &tmp);
-	else
-		usb_ocp_read(tp, index, sizeof(tmp), &tmp);
+	generic_ocp_read(tp, index, sizeof(tmp), &tmp, type);
 
-	tmp = __le32_to_cpu(tmp) & ~mask;
-	tmp |= data;
-	tmp = __cpu_to_le32(tmp);
+	data |= __le32_to_cpu(tmp) & ~mask;
+	tmp = __cpu_to_le32(data);
 
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_write(tp, index, byen, sizeof(tmp), &tmp);
-	else
-		usb_ocp_write(tp, index, byen, sizeof(tmp), &tmp);
+	generic_ocp_write(tp, index, byen, sizeof(tmp), &tmp, type);
 }
 
 static u8 ocp_read_byte(struct r8152 *tp, u16 type, u16 index)
 {
 	u32 data;
+	__le32 tmp;
 	u8 shift = index & 3;
 
 	index &= ~3;
 
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_read(tp, index, sizeof(data), &data);
-	else
-		usb_ocp_read(tp, index, sizeof(data), &data);
+	generic_ocp_read(tp, index, sizeof(tmp), &tmp, type);
 
-	data = __le32_to_cpu(data);
+	data = __le32_to_cpu(tmp);
 	data >>= (shift * 8);
 	data &= 0xff;
 
@@ -578,7 +588,8 @@ static u8 ocp_read_byte(struct r8152 *tp, u16 type, u16 index)
 
 static void ocp_write_byte(struct r8152 *tp, u16 type, u16 index, u32 data)
 {
-	u32 tmp, mask = 0xff;
+	u32 mask = 0xff;
+	__le32 tmp;
 	u16 byen = BYTE_EN_BYTE;
 	u8 shift = index & 3;
 
@@ -591,19 +602,12 @@ static void ocp_write_byte(struct r8152 *tp, u16 type, u16 index, u32 data)
 		index &= ~3;
 	}
 
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_read(tp, index, sizeof(tmp), &tmp);
-	else
-		usb_ocp_read(tp, index, sizeof(tmp), &tmp);
+	generic_ocp_read(tp, index, sizeof(tmp), &tmp, type);
 
-	tmp = __le32_to_cpu(tmp) & ~mask;
-	tmp |= data;
-	tmp = __cpu_to_le32(tmp);
+	data |= __le32_to_cpu(tmp) & ~mask;
+	tmp = __cpu_to_le32(data);
 
-	if (type == MCU_TYPE_PLA)
-		pla_ocp_write(tp, index, byen, sizeof(tmp), &tmp);
-	else
-		usb_ocp_write(tp, index, byen, sizeof(tmp), &tmp);
+	generic_ocp_write(tp, index, byen, sizeof(tmp), &tmp, type);
 }
 
 static void r8152_mdio_write(struct r8152 *tp, u32 reg_addr, u32 value)
@@ -685,21 +689,14 @@ static void ocp_reg_write(struct r8152 *tp, u16 addr, u16 data)
 static inline void set_ethernet_addr(struct r8152 *tp)
 {
 	struct net_device *dev = tp->netdev;
-	u8 *node_id;
-
-	node_id = kmalloc(sizeof(u8) * 8, GFP_KERNEL);
-	if (!node_id) {
-		netif_err(tp, probe, dev, "out of memory");
-		return;
-	}
+	u8 node_id[8] = {0};
 
-	if (pla_ocp_read(tp, PLA_IDR, sizeof(u8) * 8, node_id) < 0)
+	if (pla_ocp_read(tp, PLA_IDR, sizeof(node_id), node_id) < 0)
 		netif_notice(tp, probe, dev, "inet addr fail\n");
 	else {
 		memcpy(dev->dev_addr, node_id, dev->addr_len);
 		memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
 	}
-	kfree(node_id);
 }
 
 static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
@@ -882,15 +879,10 @@ static void rtl8152_set_rx_mode(struct net_device *netdev)
 static void _rtl8152_set_rx_mode(struct net_device *netdev)
 {
 	struct r8152 *tp = netdev_priv(netdev);
-	u32 tmp, *mc_filter;	/* Multicast hash filter */
+	u32 mc_filter[2];	/* Multicast hash filter */
+	__le32 tmp[2];
 	u32 ocp_data;
 
-	mc_filter = kmalloc(sizeof(u32) * 2, GFP_KERNEL);
-	if (!mc_filter) {
-		netif_err(tp, link, netdev, "out of memory");
-		return;
-	}
-
 	clear_bit(RTL8152_SET_RX_MODE, &tp->flags);
 	netif_stop_queue(netdev);
 	ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
@@ -918,14 +910,12 @@ static void _rtl8152_set_rx_mode(struct net_device *netdev)
 		}
 	}
 
-	tmp = mc_filter[0];
-	mc_filter[0] = __cpu_to_le32(swab32(mc_filter[1]));
-	mc_filter[1] = __cpu_to_le32(swab32(tmp));
+	tmp[0] = __cpu_to_le32(swab32(mc_filter[1]));
+	tmp[1] = __cpu_to_le32(swab32(mc_filter[0]));
 
-	pla_ocp_write(tp, PLA_MAR, BYTE_EN_DWORD, sizeof(u32) * 2, mc_filter);
+	pla_ocp_write(tp, PLA_MAR, BYTE_EN_DWORD, sizeof(tmp), tmp);
 	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
 	netif_wake_queue(netdev);
-	kfree(mc_filter);
 }
 
 static netdev_tx_t rtl8152_start_xmit(struct sk_buff *skb,
diff --git a/drivers/net/usb/r815x.c b/drivers/net/usb/r815x.c
index 852392269718..2df2f4fb42a7 100644
--- a/drivers/net/usb/r815x.c
+++ b/drivers/net/usb/r815x.c
@@ -24,34 +24,43 @@
 
 static int pla_read_word(struct usb_device *udev, u16 index)
 {
-	int data, ret;
+	int ret;
 	u8 shift = index & 2;
-	__le32 ocp_data;
+	__le32 *tmp;
+
+	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
 
 	index &= ~3;
 
 	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
 			      RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
-			      index, MCU_TYPE_PLA, &ocp_data, sizeof(ocp_data),
-			      500);
+			      index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
 	if (ret < 0)
-		return ret;
+		goto out2;
 
-	data = __le32_to_cpu(ocp_data);
-	data >>= (shift * 8);
-	data &= 0xffff;
+	ret = __le32_to_cpu(*tmp);
+	ret >>= (shift * 8);
+	ret &= 0xffff;
 
-	return data;
+out2:
+	kfree(tmp);
+	return ret;
 }
 
 static int pla_write_word(struct usb_device *udev, u16 index, u32 data)
 {
-	__le32 ocp_data;
+	__le32 *tmp;
 	u32 mask = 0xffff;
 	u16 byen = BYTE_EN_WORD;
 	u8 shift = index & 2;
 	int ret;
 
+	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	data &= mask;
 
 	if (shift) {
@@ -63,19 +72,20 @@ static int pla_write_word(struct usb_device *udev, u16 index, u32 data)
 
 	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
 			      RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
-			      index, MCU_TYPE_PLA, &ocp_data, sizeof(ocp_data),
-			      500);
+			      index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
 	if (ret < 0)
-		return ret;
+		goto out3;
 
-	data |= __le32_to_cpu(ocp_data) & ~mask;
-	ocp_data = __cpu_to_le32(data);
+	data |= __le32_to_cpu(*tmp) & ~mask;
+	*tmp = __cpu_to_le32(data);
 
 	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
 			      RTL815x_REQ_SET_REGS, RTL815x_REQT_WRITE,
-			      index, MCU_TYPE_PLA | byen, &ocp_data,
-			      sizeof(ocp_data), 500);
+			      index, MCU_TYPE_PLA | byen, tmp, sizeof(*tmp),
+			      500);
 
+out3:
+	kfree(tmp);
 	return ret;
 }
 
@@ -116,11 +126,18 @@ out1:
 static int r815x_mdio_read(struct net_device *netdev, int phy_id, int reg)
 {
 	struct usbnet *dev = netdev_priv(netdev);
+	int ret;
 
 	if (phy_id != R815x_PHY_ID)
 		return -EINVAL;
 
-	return ocp_reg_read(dev, BASE_MII + reg * 2);
+	if (usb_autopm_get_interface(dev->intf) < 0)
+		return -ENODEV;
+
+	ret = ocp_reg_read(dev, BASE_MII + reg * 2);
+
+	usb_autopm_put_interface(dev->intf);
+	return ret;
 }
 
 static
@@ -131,7 +148,12 @@ void r815x_mdio_write(struct net_device *netdev, int phy_id, int reg, int val)
 	if (phy_id != R815x_PHY_ID)
 		return;
 
+	if (usb_autopm_get_interface(dev->intf) < 0)
+		return;
+
 	ocp_reg_write(dev, BASE_MII + reg * 2, val);
+
+	usb_autopm_put_interface(dev->intf);
 }
 
 static int r8153_bind(struct usbnet *dev, struct usb_interface *intf)
@@ -150,7 +172,7 @@ static int r8153_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->mii.phy_id = R815x_PHY_ID;
 	dev->mii.supports_gmii = 1;
 
-	return 0;
+	return status;
 }
 
 static int r8152_bind(struct usbnet *dev, struct usb_interface *intf)
@@ -169,7 +191,7 @@ static int r8152_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->mii.phy_id = R815x_PHY_ID;
 	dev->mii.supports_gmii = 0;
 
-	return 0;
+	return status;
 }
 
 static const struct driver_info r8152_info = {
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 75409748c774..66ebbacf066f 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -45,7 +45,6 @@
 #define EEPROM_MAC_OFFSET		(0x01)
 #define DEFAULT_TX_CSUM_ENABLE		(true)
 #define DEFAULT_RX_CSUM_ENABLE		(true)
-#define DEFAULT_TSO_ENABLE		(true)
 #define SMSC75XX_INTERNAL_PHY_ID	(1)
 #define SMSC75XX_TX_OVERHEAD		(8)
 #define MAX_RX_FIFO_SIZE		(20 * 1024)
@@ -1410,17 +1409,14 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	INIT_WORK(&pdata->set_multicast, smsc75xx_deferred_multicast_write);
 
-	if (DEFAULT_TX_CSUM_ENABLE) {
+	if (DEFAULT_TX_CSUM_ENABLE)
 		dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-		if (DEFAULT_TSO_ENABLE)
-			dev->net->features |= NETIF_F_SG |
-				NETIF_F_TSO | NETIF_F_TSO6;
-	}
+
 	if (DEFAULT_RX_CSUM_ENABLE)
 		dev->net->features |= NETIF_F_RXCSUM;
 
 	dev->net->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_RXCSUM;
+				NETIF_F_RXCSUM;
 
 	ret = smsc75xx_wait_ready(dev, 0);
 	if (ret < 0) {
@@ -2200,8 +2196,6 @@ static struct sk_buff *smsc75xx_tx_fixup(struct usbnet *dev,
 {
 	u32 tx_cmd_a, tx_cmd_b;
 
-	skb_linearize(skb);
-
 	if (skb_headroom(skb) < SMSC75XX_TX_OVERHEAD) {
 		struct sk_buff *skb2 =
 			skb_copy_expand(skb, SMSC75XX_TX_OVERHEAD, 0, flags);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index da866523cf20..eee1f19ef1e9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -269,6 +269,7 @@ static void veth_setup(struct net_device *dev)
 	dev->ethtool_ops = &veth_ethtool_ops;
 	dev->features |= NETIF_F_LLTX;
 	dev->features |= VETH_FEATURES;
+	dev->vlan_features = dev->features;
 	dev->destructor = veth_dev_free;
 
 	dev->hw_features = VETH_FEATURES;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a5ba8dd7e6be..767f7af3bd40 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -136,7 +136,8 @@ struct vxlan_dev {
 	u32		  flags;	/* VXLAN_F_* below */
 
 	struct work_struct sock_work;
-	struct work_struct igmp_work;
+	struct work_struct igmp_join;
+	struct work_struct igmp_leave;
 
 	unsigned long	  age_interval;
 	struct timer_list age_timer;
@@ -736,7 +737,6 @@ static bool vxlan_snoop(struct net_device *dev,
 	return false;
 }
 
-
 /* See if multicast group is already in use by other ID */
 static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip)
 {
@@ -770,12 +770,13 @@ static void vxlan_sock_release(struct vxlan_net *vn, struct vxlan_sock *vs)
 	queue_work(vxlan_wq, &vs->del_work);
 }
 
-/* Callback to update multicast group membership.
- * Scheduled when vxlan goes up/down.
+/* Callback to update multicast group membership when first VNI on
+ * multicast asddress is brought up
+ * Done as workqueue because ip_mc_join_group acquires RTNL.
  */
-static void vxlan_igmp_work(struct work_struct *work)
+static void vxlan_igmp_join(struct work_struct *work)
 {
-	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_work);
+	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join);
 	struct vxlan_net *vn = net_generic(dev_net(vxlan->dev), vxlan_net_id);
 	struct vxlan_sock *vs = vxlan->vn_sock;
 	struct sock *sk = vs->sock->sk;
@@ -785,10 +786,27 @@ static void vxlan_igmp_work(struct work_struct *work)
 	};
 
 	lock_sock(sk);
-	if (vxlan_group_used(vn, vxlan->default_dst.remote_ip))
-		ip_mc_join_group(sk, &mreq);
-	else
-		ip_mc_leave_group(sk, &mreq);
+	ip_mc_join_group(sk, &mreq);
+	release_sock(sk);
+
+	vxlan_sock_release(vn, vs);
+	dev_put(vxlan->dev);
+}
+
+/* Inverse of vxlan_igmp_join when last VNI is brought down */
+static void vxlan_igmp_leave(struct work_struct *work)
+{
+	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave);
+	struct vxlan_net *vn = net_generic(dev_net(vxlan->dev), vxlan_net_id);
+	struct vxlan_sock *vs = vxlan->vn_sock;
+	struct sock *sk = vs->sock->sk;
+	struct ip_mreqn mreq = {
+		.imr_multiaddr.s_addr	= vxlan->default_dst.remote_ip,
+		.imr_ifindex		= vxlan->default_dst.remote_ifindex,
+	};
+
+	lock_sock(sk);
+	ip_mc_leave_group(sk, &mreq);
 	release_sock(sk);
 
 	vxlan_sock_release(vn, vs);
@@ -1359,6 +1377,7 @@ static void vxlan_uninit(struct net_device *dev)
 /* Start ageing timer and join group when device is brought up */
 static int vxlan_open(struct net_device *dev)
 {
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_sock *vs = vxlan->vn_sock;
 
@@ -1366,10 +1385,11 @@ static int vxlan_open(struct net_device *dev)
 	if (!vs)
 		return -ENOTCONN;
 
-	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
+	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) &&
+	    vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
 		vxlan_sock_hold(vs);
 		dev_hold(dev);
-		queue_work(vxlan_wq, &vxlan->igmp_work);
+		queue_work(vxlan_wq, &vxlan->igmp_join);
 	}
 
 	if (vxlan->age_interval)
@@ -1400,13 +1420,15 @@ static void vxlan_flush(struct vxlan_dev *vxlan)
 /* Cleanup timer and forwarding table on shutdown */
 static int vxlan_stop(struct net_device *dev)
 {
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_sock *vs = vxlan->vn_sock;
 
-	if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
+	if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) &&
+	    ! vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
 		vxlan_sock_hold(vs);
 		dev_hold(dev);
-		queue_work(vxlan_wq, &vxlan->igmp_work);
+		queue_work(vxlan_wq, &vxlan->igmp_leave);
 	}
 
 	del_timer_sync(&vxlan->age_timer);
@@ -1471,7 +1493,8 @@ static void vxlan_setup(struct net_device *dev)
 
 	INIT_LIST_HEAD(&vxlan->next);
 	spin_lock_init(&vxlan->hash_lock);
-	INIT_WORK(&vxlan->igmp_work, vxlan_igmp_work);
+	INIT_WORK(&vxlan->igmp_join, vxlan_igmp_join);
+	INIT_WORK(&vxlan->igmp_leave, vxlan_igmp_leave);
 	INIT_WORK(&vxlan->sock_work, vxlan_sock_work);
 
 	init_timer_deferrable(&vxlan->age_timer);
@@ -1770,8 +1793,6 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 
-	flush_workqueue(vxlan_wq);
-
 	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vxlan->hlist);
 	spin_unlock(&vn->sock_lock);
@@ -1878,10 +1899,12 @@ static __net_exit void vxlan_exit_net(struct net *net)
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan;
+	LIST_HEAD(list);
 
 	rtnl_lock();
 	list_for_each_entry(vxlan, &vn->vxlan_list, next)
-		dev_close(vxlan->dev);
+		unregister_netdevice_queue(vxlan->dev, &list);
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig
index cde58fe96254..82e8088ca9b4 100644
--- a/drivers/net/wireless/ath/ath10k/Kconfig
+++ b/drivers/net/wireless/ath/ath10k/Kconfig
@@ -1,6 +1,6 @@
 config ATH10K
         tristate "Atheros 802.11ac wireless cards support"
-        depends on MAC80211
+        depends on MAC80211 && HAS_DMA
 	select ATH_COMMON
         ---help---
           This module adds support for wireless adapters based on
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index 81b686c6a376..40825d43322e 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -325,7 +325,7 @@ ath5k_prepare_multicast(struct ieee80211_hw *hw,
 	struct netdev_hw_addr *ha;
 
 	mfilt[0] = 0;
-	mfilt[1] = 1;
+	mfilt[1] = 0;
 
 	netdev_hw_addr_list_for_each(ha, mc_list) {
 		/* calculate XOR of eight 6-bit values */
diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
index d1acfe98918a..1576d58291d4 100644
--- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
@@ -610,7 +610,15 @@ static void ar5008_hw_override_ini(struct ath_hw *ah,
 	REG_SET_BIT(ah, AR_DIAG_SW, (AR_DIAG_RX_DIS | AR_DIAG_RX_ABORT));
 
 	if (AR_SREV_9280_20_OR_LATER(ah)) {
-		val = REG_READ(ah, AR_PCU_MISC_MODE2);
+		/*
+		 * For AR9280 and above, there is a new feature that allows
+		 * Multicast search based on both MAC Address and Key ID.
+		 * By default, this feature is enabled. But since the driver
+		 * is not using this feature, we switch it off; otherwise
+		 * multicast search based on MAC addr only will fail.
+		 */
+		val = REG_READ(ah, AR_PCU_MISC_MODE2) &
+			(~AR_ADHOC_MCAST_KEYID_ENABLE);
 
 		if (!AR_SREV_9271(ah))
 			val &= ~AR_PCU_MISC_MODE2_HWWAR1;
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 9e582e14da74..5205a3625e84 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -1082,7 +1082,7 @@ static void ath9k_hif_usb_firmware_fail(struct hif_device_usb *hif_dev)
 	struct device *dev = &hif_dev->udev->dev;
 	struct device *parent = dev->parent;
 
-	complete(&hif_dev->fw_done);
+	complete_all(&hif_dev->fw_done);
 
 	if (parent)
 		device_lock(parent);
@@ -1131,7 +1131,7 @@ static void ath9k_hif_usb_firmware_cb(const struct firmware *fw, void *context)
 
 	release_firmware(fw);
 	hif_dev->flags |= HIF_USB_READY;
-	complete(&hif_dev->fw_done);
+	complete_all(&hif_dev->fw_done);
 
 	return;
 
@@ -1295,7 +1295,9 @@ static void ath9k_hif_usb_disconnect(struct usb_interface *interface)
 
 	usb_set_intfdata(interface, NULL);
 
-	if (!unplugged && (hif_dev->flags & HIF_USB_START))
+	/* If firmware was loaded we should drop it
+	 * go back to first stage bootloader. */
+	if (!unplugged && (hif_dev->flags & HIF_USB_READY))
 		ath9k_hif_usb_reboot(udev);
 
 	kfree(hif_dev);
@@ -1316,7 +1318,10 @@ static int ath9k_hif_usb_suspend(struct usb_interface *interface,
 	if (!(hif_dev->flags & HIF_USB_START))
 		ath9k_htc_suspend(hif_dev->htc_handle);
 
-	ath9k_hif_usb_dealloc_urbs(hif_dev);
+	wait_for_completion(&hif_dev->fw_done);
+
+	if (hif_dev->flags & HIF_USB_READY)
+		ath9k_hif_usb_dealloc_urbs(hif_dev);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index 71a183ffc77f..c3676bf1d6c4 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -861,6 +861,7 @@ static int ath9k_init_device(struct ath9k_htc_priv *priv,
 	if (error != 0)
 		goto err_rx;
 
+	ath9k_hw_disable(priv->ah);
 #ifdef CONFIG_MAC80211_LEDS
 	/* must be initialized before ieee80211_register_hw */
 	priv->led_cdev.default_trigger = ieee80211_create_tpt_led_trigger(priv->hw,
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index c59ae43b9b35..927992732620 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -146,6 +146,28 @@ static void ath_set_rates(struct ieee80211_vif *vif, struct ieee80211_sta *sta,
 			       ARRAY_SIZE(bf->rates));
 }
 
+static void ath_txq_skb_done(struct ath_softc *sc, struct ath_txq *txq,
+			     struct sk_buff *skb)
+{
+	int q;
+
+	q = skb_get_queue_mapping(skb);
+	if (txq == sc->tx.uapsdq)
+		txq = sc->tx.txq_map[q];
+
+	if (txq != sc->tx.txq_map[q])
+		return;
+
+	if (WARN_ON(--txq->pending_frames < 0))
+		txq->pending_frames = 0;
+
+	if (txq->stopped &&
+	    txq->pending_frames < sc->tx.txq_max_pending[q]) {
+		ieee80211_wake_queue(sc->hw, q);
+		txq->stopped = false;
+	}
+}
+
 static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
 {
 	struct ath_txq *txq = tid->ac->txq;
@@ -167,6 +189,7 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
 		if (!bf) {
 			bf = ath_tx_setup_buffer(sc, txq, tid, skb);
 			if (!bf) {
+				ath_txq_skb_done(sc, txq, skb);
 				ieee80211_free_txskb(sc->hw, skb);
 				continue;
 			}
@@ -811,6 +834,7 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 
 		if (!bf) {
 			__skb_unlink(skb, &tid->buf_q);
+			ath_txq_skb_done(sc, txq, skb);
 			ieee80211_free_txskb(sc->hw, skb);
 			continue;
 		}
@@ -1824,6 +1848,7 @@ static void ath_tx_send_ampdu(struct ath_softc *sc, struct ath_txq *txq,
 
 	bf = ath_tx_setup_buffer(sc, txq, tid, skb);
 	if (!bf) {
+		ath_txq_skb_done(sc, txq, skb);
 		ieee80211_free_txskb(sc->hw, skb);
 		return;
 	}
@@ -2090,6 +2115,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 
 	bf = ath_tx_setup_buffer(sc, txq, tid, skb);
 	if (!bf) {
+		ath_txq_skb_done(sc, txq, skb);
 		if (txctl->paprd)
 			dev_kfree_skb_any(skb);
 		else
@@ -2189,7 +2215,7 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb,
 	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb);
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ieee80211_hdr * hdr = (struct ieee80211_hdr *)skb->data;
-	int q, padpos, padsize;
+	int padpos, padsize;
 	unsigned long flags;
 
 	ath_dbg(common, XMIT, "TX complete: skb: %p\n", skb);
@@ -2225,21 +2251,7 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb,
 	spin_unlock_irqrestore(&sc->sc_pm_lock, flags);
 
 	__skb_queue_tail(&txq->complete_q, skb);
-
-	q = skb_get_queue_mapping(skb);
-	if (txq == sc->tx.uapsdq)
-		txq = sc->tx.txq_map[q];
-
-	if (txq == sc->tx.txq_map[q]) {
-		if (WARN_ON(--txq->pending_frames < 0))
-			txq->pending_frames = 0;
-
-		if (txq->stopped &&
-		    txq->pending_frames < sc->tx.txq_max_pending[q]) {
-			ieee80211_wake_queue(sc->hw, q);
-			txq->stopped = false;
-		}
-	}
+	ath_txq_skb_done(sc, txq, skb);
 }
 
 static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf,
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index e8308ec30970..ab636767fbde 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -145,7 +145,7 @@ static void wil_print_ring(struct seq_file *s, const char *prefix,
 				   le16_to_cpu(hdr.type), hdr.flags);
 			if (len <= MAX_MBOXITEM_SIZE) {
 				int n = 0;
-				unsigned char printbuf[16 * 3 + 2];
+				char printbuf[16 * 3 + 2];
 				unsigned char databuf[MAX_MBOXITEM_SIZE];
 				void __iomem *src = wmi_buffer(wil, d.addr) +
 					sizeof(struct wil6210_mbox_hdr);
@@ -416,7 +416,7 @@ static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
 		seq_printf(s, "  SKB = %p\n", skb);
 
 		if (skb) {
-			unsigned char printbuf[16 * 3 + 2];
+			char printbuf[16 * 3 + 2];
 			int i = 0;
 			int len = le16_to_cpu(d->dma.length);
 			void *p = skb->data;
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
index 8e8975562ec3..80099016d21f 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
@@ -242,7 +242,7 @@ void brcmf_txflowblock_if(struct brcmf_if *ifp,
 {
 	unsigned long flags;
 
-	if (!ifp)
+	if (!ifp || !ifp->ndev)
 		return;
 
 	brcmf_dbg(TRACE, "enter: idx=%d stop=0x%X reason=%d state=%d\n",
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
index f0d9f7f6c83d..29b1f24c2d0f 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
@@ -1744,13 +1744,14 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 	ulong flags;
 	int fifo = BRCMF_FWS_FIFO_BCMC;
 	bool multicast = is_multicast_ether_addr(eh->h_dest);
+	bool pae = eh->h_proto == htons(ETH_P_PAE);
 
 	/* determine the priority */
 	if (!skb->priority)
 		skb->priority = cfg80211_classify8021d(skb);
 
 	drvr->tx_multicast += !!multicast;
-	if (ntohs(eh->h_proto) == ETH_P_PAE)
+	if (pae)
 		atomic_inc(&ifp->pend_8021x_cnt);
 
 	if (!brcmf_fws_fc_active(fws)) {
@@ -1781,6 +1782,11 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 		brcmf_fws_schedule_deq(fws);
 	} else {
 		brcmf_err("drop skb: no hanger slot\n");
+		if (pae) {
+			atomic_dec(&ifp->pend_8021x_cnt);
+			if (waitqueue_active(&ifp->pend_8021x_wait))
+				wake_up(&ifp->pend_8021x_wait);
+		}
 		brcmu_pkt_buf_free_skb(skb);
 	}
 	brcmf_fws_unlock(drvr, flags);
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index 277b37ae7126..7fa71f73cfe8 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -1093,8 +1093,11 @@ static void brcmf_link_down(struct brcmf_cfg80211_vif *vif)
 		brcmf_dbg(INFO, "Call WLC_DISASSOC to stop excess roaming\n ");
 		err = brcmf_fil_cmd_data_set(vif->ifp,
 					     BRCMF_C_DISASSOC, NULL, 0);
-		if (err)
+		if (err) {
 			brcmf_err("WLC_DISASSOC failed (%d)\n", err);
+			cfg80211_disconnected(vif->wdev.netdev, 0,
+					      NULL, 0, GFP_KERNEL);
+		}
 		clear_bit(BRCMF_VIF_STATUS_CONNECTED, &vif->sme_state);
 	}
 	clear_bit(BRCMF_VIF_STATUS_CONNECTING, &vif->sme_state);
diff --git a/drivers/net/wireless/cw1200/sta.c b/drivers/net/wireless/cw1200/sta.c
index 7365674366f4..010b252be584 100644
--- a/drivers/net/wireless/cw1200/sta.c
+++ b/drivers/net/wireless/cw1200/sta.c