Merge tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux

Pull clk fixes from Stephen Boyd:

 - build fix to export the clk_bulk_prepare() symbol

 - suspend fix for Samsung Exynos SoCs where we need to keep clks on
   across suspend

 - two critical clk markings for clks that shouldn't ever turn off on
   Rockchip SoCs

 - a fix for a copy-paste mistake on Rockchip rk3128 causing some clks
   to touch the same bit and trample over one another

* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
  clk: samsung: exynos4: Enable VPLL and EPLL clocks for suspend/resume cycle
  clk: Export clk_bulk_prepare()
  clk: rockchip: add sclk_timer5 as critical clock on rk3128
  clk: rockchip: fix up rk3128 pvtm and mipi_24m gate regs error
  clk: rockchip: add pclk_pmu as critical clock on rk3128
diff --git a/.mailmap b/.mailmap
index 5273cfd..c7b10ca 100644
--- a/.mailmap
+++ b/.mailmap
@@ -68,6 +68,8 @@
 James Bottomley <jejb@mulgrave.(none)>
 James Bottomley <jejb@titanic.il.steeleye.com>
 James E Wilson <wilson@specifix.com>
+James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
+James Hogan <jhogan@kernel.org> <james@albanarts.com>
 James Ketrenos <jketreno@io.(none)>
 Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 713cab1..a1d1612 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -127,7 +127,7 @@
 
 What;		/sys/power/pm_trace_dev_match
 Date:		October 2010
-Contact:	James Hogan <james@albanarts.com>
+Contact:	James Hogan <jhogan@kernel.org>
 Description:
 		The /sys/power/pm_trace_dev_match file contains the name of the
 		device associated with the last PM event point saved in the RTC
diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index 3943b5b..00a5ba5 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -39,8 +39,8 @@
 Although MT wq wasted a lot of resource, the level of concurrency
 provided was unsatisfactory.  The limitation was common to both ST and
 MT wq albeit less severe on MT.  Each wq maintained its own separate
-worker pool.  A MT wq could provide only one execution context per CPU
-while a ST wq one for the whole system.  Work items had to compete for
+worker pool.  An MT wq could provide only one execution context per CPU
+while an ST wq one for the whole system.  Work items had to compete for
 those very limited execution contexts leading to various problems
 including proneness to deadlocks around the single execution context.
 
@@ -151,7 +151,7 @@
 
 ``alloc_workqueue()`` allocates a wq.  The original
 ``create_*workqueue()`` functions are deprecated and scheduled for
-removal.  ``alloc_workqueue()`` takes three arguments - @``name``,
+removal.  ``alloc_workqueue()`` takes three arguments - ``@name``,
 ``@flags`` and ``@max_active``.  ``@name`` is the name of the wq and
 also used as the name of the rescuer thread if there is one.
 
@@ -197,7 +197,7 @@
   served by worker threads with elevated nice level.
 
   Note that normal and highpri worker-pools don't interact with
-  each other.  Each maintain its separate pool of workers and
+  each other.  Each maintains its separate pool of workers and
   implements concurrency management among its workers.
 
 ``WQ_CPU_INTENSIVE``
@@ -249,8 +249,8 @@
 time thus achieving the same ordering property as ST wq.
 
 In the current implementation the above configuration only guarantees
-ST behavior within a given NUMA node. Instead alloc_ordered_queue should
-be used to achieve system wide ST behavior.
+ST behavior within a given NUMA node. Instead ``alloc_ordered_queue()`` should
+be used to achieve system-wide ST behavior.
 
 
 Example Execution Scenarios
diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt
index 03a7cee..c15e753 100644
--- a/Documentation/cpu-freq/index.txt
+++ b/Documentation/cpu-freq/index.txt
@@ -32,8 +32,6 @@
 
 index.txt	-	File index, Mailing list and Links (this document)
 
-intel-pstate.txt -	Intel pstate cpufreq driver specific file.
-
 pcc-cpufreq.txt -	PCC cpufreq driver specific file.
 
 
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index 4a0a746..32df07e 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -344,3 +344,4 @@
 	(wrong raid10_copies/raid10_format sequence)
 1.11.1  Add raid4/5/6 journal write-back support via journal_mode option
 1.12.1  fix for MD deadlock between mddev_suspend() and md_write_start() available
+1.13.0  Fix dev_health status at end of "recover" (was 'a', now 'A')
diff --git a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt
index a135504..cac24ee 100644
--- a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt
+++ b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt
@@ -32,7 +32,7 @@
 		compatible = "st,stm32h743-rcc", "st,stm32-rcc";
 		reg = <0x58024400 0x400>;
 		#reset-cells = <1>;
-		#clock-cells = <2>;
+		#clock-cells = <1>;
 		clocks = <&clk_hse>, <&clk_lse>, <&clk_i2s_ckin>;
 
 		st,syscfg = <&pwrcfg>;
diff --git a/Documentation/devicetree/bindings/leds/ams,as3645a.txt b/Documentation/devicetree/bindings/leds/ams,as3645a.txt
index 12c5ef2..fdc40e3 100644
--- a/Documentation/devicetree/bindings/leds/ams,as3645a.txt
+++ b/Documentation/devicetree/bindings/leds/ams,as3645a.txt
@@ -15,11 +15,14 @@
 
 compatible	: Must be "ams,as3645a".
 reg		: The I2C address of the device. Typically 0x30.
+#address-cells	: 1
+#size-cells	: 0
 
 
-Required properties of the "flash" child node
-=============================================
+Required properties of the flash child node (0)
+===============================================
 
+reg: 0
 flash-timeout-us: Flash timeout in microseconds. The value must be in
 		  the range [100000, 850000] and divisible by 50000.
 flash-max-microamp: Maximum flash current in microamperes. Has to be
@@ -33,20 +36,21 @@
 			and divisible by 50000.
 
 
-Optional properties of the "flash" child node
-=============================================
+Optional properties of the flash child node
+===========================================
 
 label		: The label of the flash LED.
 
 
-Required properties of the "indicator" child node
-=================================================
+Required properties of the indicator child node (1)
+===================================================
 
+reg: 1
 led-max-microamp: Maximum indicator current. The allowed values are
 		  2500, 5000, 7500 and 10000.
 
-Optional properties of the "indicator" child node
-=================================================
+Optional properties of the indicator child node
+===============================================
 
 label		: The label of the indicator LED.
 
@@ -55,16 +59,20 @@
 =======
 
 	as3645a@30 {
+		#address-cells: 1
+		#size-cells: 0
 		reg = <0x30>;
 		compatible = "ams,as3645a";
-		flash {
+		flash@0 {
+			reg = <0x0>;
 			flash-timeout-us = <150000>;
 			flash-max-microamp = <320000>;
 			led-max-microamp = <60000>;
 			ams,input-max-microamp = <1750000>;
 			label = "as3645a:flash";
 		};
-		indicator {
+		indicator@1 {
+			reg = <0x1>;
 			led-max-microamp = <10000>;
 			label = "as3645a:indicator";
 		};
diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
index 7e2dad0..1814fa1 100644
--- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
+++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
@@ -21,8 +21,9 @@
 	- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
 	- GOP clock (for both armada-375-pp2 and armada-7k-pp2)
 	- MG clock (only for armada-7k-pp2)
-- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and
-  "mg_clk" (the latter only for armada-7k-pp2).
+	- AXI clock (only for armada-7k-pp2)
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk"
+  and "axi_clk" (the 2 latter only for armada-7k-pp2).
 
 The ethernet ports are represented by subnodes. At least one port is
 required.
@@ -78,8 +79,9 @@
 cpm_ethernet: ethernet@0 {
 	compatible = "marvell,armada-7k-pp22";
 	reg = <0x0 0x100000>, <0x129000 0xb000>;
-	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>;
-	clock-names = "pp_clk", "gop_clk", "gp_clk";
+	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>,
+		 <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>;
+	clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk";
 
 	eth0: eth0 {
 		interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
index 6af8eed..9c16ee2 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
@@ -4,6 +4,7 @@
 
 Required properties:
  - compatible: should be "rockchip,<name>-gamc"
+   "rockchip,rk3128-gmac": found on RK312x SoCs
    "rockchip,rk3228-gmac": found on RK322x SoCs
    "rockchip,rk3288-gmac": found on RK3288 SoCs
    "rockchip,rk3328-gmac": found on RK3328 SoCs
diff --git a/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt b/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt
new file mode 100644
index 0000000..830069b
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt
@@ -0,0 +1,28 @@
+Binding for the Synopsys HSDK reset controller
+
+This binding uses the common reset binding[1].
+
+[1] Documentation/devicetree/bindings/reset/reset.txt
+
+Required properties:
+- compatible: should be "snps,hsdk-reset".
+- reg: should always contain 2 pairs address - length: first for reset
+  configuration register and second for corresponding SW reset and status bits
+  register.
+- #reset-cells: from common reset binding; Should always be set to 1.
+
+Example:
+	reset: reset@880 {
+		compatible = "snps,hsdk-reset";
+		#reset-cells = <1>;
+		reg = <0x8A0 0x4>, <0xFF0 0x4>;
+	};
+
+Specifying reset lines connected to IP modules:
+	ethernet@.... {
+		....
+		resets = <&reset HSDK_V1_ETH_RESET>;
+		....
+	};
+
+The index could be found in <dt-bindings/reset/snps,hsdk-reset.h>
diff --git a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
index 3eca6de..a65d7b7 100644
--- a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
+++ b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
@@ -8,6 +8,12 @@
                    the firmware event log
 - linux,sml-size : size of the memory allocated for the firmware event log
 
+Optional properties:
+
+- powered-while-suspended: present when the TPM is left powered on between
+                           suspend and resume (makes the suspend/resume
+                           callbacks do nothing).
+
 Example (for OpenPower Systems with Nuvoton TPM 2.0 on I2C)
 ----------------------------------------------------------
 
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index 4fc9694..cf504d0 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -41,6 +41,8 @@
     - "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART.
     - "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART.
     - "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART.
+    - "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART.
+    - "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART.
     - "renesas,scif-r8a77995" for R8A77995 (R-Car D3) SCIF compatible UART.
     - "renesas,hscif-r8a77995" for R8A77995 (R-Car D3) HSCIF compatible UART.
     - "renesas,scifa-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFA compatible UART.
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 1ea1fd4..1afd298 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -3,8 +3,8 @@
 This isn't an exhaustive list, but you should add new prefixes to it before
 using them to avoid name-space collisions.
 
-abcn	Abracon Corporation
 abilis	Abilis Systems
+abracon	Abracon Corporation
 actions	Actions Semiconductor Co., Ltd.
 active-semi	Active-Semi International Inc
 ad	Avionic Design GmbH
diff --git a/Documentation/driver-api/pm/devices.rst b/Documentation/driver-api/pm/devices.rst
index bedd323..a0dc287 100644
--- a/Documentation/driver-api/pm/devices.rst
+++ b/Documentation/driver-api/pm/devices.rst
@@ -675,7 +675,7 @@
 
 Support for power domains is provided through the :c:member:`pm_domain` field of
 |struct device|.  This field is a pointer to an object of type
-|struct dev_pm_domain|, defined in :file:`include/linux/pm.h``, providing a set
+|struct dev_pm_domain|, defined in :file:`include/linux/pm.h`, providing a set
 of power management callbacks analogous to the subsystem-level and device driver
 callbacks that are executed for the given device during all power transitions,
 instead of the respective subsystem-level callbacks.  Specifically, if a
diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt
index 4421135..d661e6f 100644
--- a/Documentation/driver-model/driver.txt
+++ b/Documentation/driver-model/driver.txt
@@ -196,12 +196,13 @@
 };
 
 Device drivers can export attributes via their sysfs directories. 
-Drivers can declare attributes using a DRIVER_ATTR macro that works
-identically to the DEVICE_ATTR macro. 
+Drivers can declare attributes using a DRIVER_ATTR_RW and DRIVER_ATTR_RO
+macro that works identically to the DEVICE_ATTR_RW and DEVICE_ATTR_RO
+macros.
 
 Example:
 
-DRIVER_ATTR(debug,0644,show_debug,store_debug);
+DRIVER_ATTR_RW(debug);
 
 This is equivalent to declaring:
 
diff --git a/Documentation/filesystems/cifs/AUTHORS b/Documentation/filesystems/cifs/AUTHORS
index c98800d..9f4f87e 100644
--- a/Documentation/filesystems/cifs/AUTHORS
+++ b/Documentation/filesystems/cifs/AUTHORS
@@ -41,6 +41,11 @@
 Jeff Layton (many, many fixes, as well as great work on the cifs Kerberos code)
 Scott Lovenberg
 Pavel Shilovsky (for great work adding SMB2 support, and various SMB3 features)
+Aurelien Aptel (for DFS SMB3 work and some key bug fixes)
+Ronnie Sahlberg (for SMB3 xattr work and bug fixes)
+Shirish Pargaonkar (for many ACL patches over the years)
+Sachin Prabhu (many bug fixes, including for reconnect, copy offload and security)
+
 
 Test case and Bug Report contributors
 -------------------------------------
diff --git a/Documentation/filesystems/cifs/README b/Documentation/filesystems/cifs/README
index a5478840..a9da515 100644
--- a/Documentation/filesystems/cifs/README
+++ b/Documentation/filesystems/cifs/README
@@ -1,10 +1,14 @@
-The CIFS VFS support for Linux supports many advanced network filesystem 
-features such as hierarchical dfs like namespace, hardlinks, locking and more.  
+This module supports the SMB3 family of advanced network protocols (as well
+as older dialects, originally called "CIFS" or SMB1).
+
+The CIFS VFS module for Linux supports many advanced network filesystem
+features such as hierarchical DFS like namespace, hardlinks, locking and more.
 It was designed to comply with the SNIA CIFS Technical Reference (which 
 supersedes the 1992 X/Open SMB Standard) as well as to perform best practice 
 practical interoperability with Windows 2000, Windows XP, Samba and equivalent 
 servers.  This code was developed in participation with the Protocol Freedom
-Information Foundation.
+Information Foundation.  CIFS and now SMB3 has now become a defacto
+standard for interoperating between Macs and Windows and major NAS appliances.
 
 Please see
   http://protocolfreedom.org/ and
@@ -15,30 +19,11 @@
 For questions or bug reports please contact:
     sfrench@samba.org (sfrench@us.ibm.com) 
 
+See the project page at: https://wiki.samba.org/index.php/LinuxCIFS_utils
+
 Build instructions:
 ==================
-For Linux 2.4:
-1) Get the kernel source (e.g.from http://www.kernel.org)
-and download the cifs vfs source (see the project page
-at http://us1.samba.org/samba/Linux_CIFS_client.html)
-and change directory into the top of the kernel directory
-then patch the kernel (e.g. "patch -p1 < cifs_24.patch") 
-to add the cifs vfs to your kernel configure options if
-it has not already been added (e.g. current SuSE and UL
-users do not need to apply the cifs_24.patch since the cifs vfs is
-already in the kernel configure menu) and then
-mkdir linux/fs/cifs and then copy the current cifs vfs files from
-the cifs download to your kernel build directory e.g.
-
-	cp <cifs_download_dir>/fs/cifs/* to <kernel_download_dir>/fs/cifs
-	
-2) make menuconfig (or make xconfig)
-3) select cifs from within the network filesystem choices
-4) save and exit
-5) make dep
-6) make modules (or "make" if CIFS VFS not to be built as a module)
-
-For Linux 2.6:
+For Linux:
 1) Download the kernel (e.g. from http://www.kernel.org)
 and change directory into the top of the kernel directory tree
 (e.g. /usr/src/linux-2.5.73)
@@ -61,16 +46,13 @@
 If you do not have the utility mount.cifs (in the Samba 3.0 source tree and on 
 the CIFS VFS web site) copy it to the same directory in which mount.smbfs and 
 similar files reside (usually /sbin).  Although the helper software is not  
-required, mount.cifs is recommended.  Eventually the Samba 3.0 utility program 
-"net" may also be helpful since it may someday provide easier mount syntax for
-users who are used to Windows e.g.
-	net use <mount point> <UNC name or cifs URL>
+required, mount.cifs is recommended.  Most distros include a "cifs-utils"
+package that includes this utility so it is recommended to install this.
+
 Note that running the Winbind pam/nss module (logon service) on all of your
 Linux clients is useful in mapping Uids and Gids consistently across the
 domain to the proper network user.  The mount.cifs mount helper can be
-trivially built from Samba 3.0 or later source e.g. by executing:
-
-	gcc samba/source/client/mount.cifs.c -o mount.cifs
+found at cifs-utils.git on git.samba.org
 
 If cifs is built as a module, then the size and number of network buffers
 and maximum number of simultaneous requests to one server can be configured.
@@ -79,6 +61,18 @@
 on kernel/fs/cifs/cifs.ko the list of configuration changes that can be made
 at module initialization time (by running insmod cifs.ko) can be seen.
 
+Recommendations
+===============
+To improve security the SMB2.1 dialect or later (usually will get SMB3) is now
+the new default. To use old dialects (e.g. to mount Windows XP) use "vers=1.0"
+on mount (or vers=2.0 for Windows Vista).  Note that the CIFS (vers=1.0) is
+much older and less secure than the default dialect SMB3 which includes
+many advanced security features such as downgrade attack detection
+and encrypted shares and stronger signing and authentication algorithms.
+There are additional mount options that may be helpful for SMB3 to get
+improved POSIX behavior (NB: can use vers=3.0 to force only SMB3, never 2.1):
+     "mfsymlinks" and "cifsacl" and "idsfromsid"
+
 Allowing User Mounts
 ====================
 To permit users to mount and unmount over directories they own is possible
@@ -98,9 +92,7 @@
 by default. This can be changed, as with nfs and other filesystems, 
 by simply specifying "nosuid" among the mount options. For user mounts 
 though to be able to pass the suid flag to mount requires rebuilding 
-mount.cifs with the following flag: 
- 
-        gcc samba/source/client/mount.cifs.c -DCIFS_ALLOW_USR_SUID -o mount.cifs
+mount.cifs with the following flag: CIFS_ALLOW_USR_SUID
 
 There is a corresponding manual page for cifs mounting in the Samba 3.0 and
 later source tree in docs/manpages/mount.cifs.8 
@@ -189,18 +181,18 @@
 Use instructions:
 ================
 Once the CIFS VFS support is built into the kernel or installed as a module 
-(cifs.o), you can use mount syntax like the following to access Samba or Windows 
-servers: 
+(cifs.ko), you can use mount syntax like the following to access Samba or
+Mac or Windows servers:
 
-  mount -t cifs //9.53.216.11/e$ /mnt -o user=myname,pass=mypassword
+  mount -t cifs //9.53.216.11/e$ /mnt -o username=myname,password=mypassword
 
 Before -o the option -v may be specified to make the mount.cifs
 mount helper display the mount steps more verbosely.  
 After -o the following commonly used cifs vfs specific options
 are supported:
 
-  user=<username>
-  pass=<password>
+  username=<username>
+  password=<password>
   domain=<domain name>
   
 Other cifs mount options are described below.  Use of TCP names (in addition to
@@ -246,13 +238,16 @@
 filenames (ie those which contain valid Linux characters, which normally
 would be forbidden for Windows/CIFS semantics) as long as the server is
 configured for Unix Extensions (and the client has not disabled
-/proc/fs/cifs/LinuxExtensionsEnabled).
-  
+/proc/fs/cifs/LinuxExtensionsEnabled). In addition the mount option
+"mapposix" can be used on CIFS (vers=1.0) to force the mapping of
+illegal Windows/NTFS/SMB characters to a remap range (this mount parm
+is the default for SMB3). This remap ("mapposix") range is also
+compatible with Mac (and "Services for Mac" on some older Windows).
 
 CIFS VFS Mount Options
 ======================
 A partial list of the supported mount options follows:
-  user		The user name to use when trying to establish
+  username	The user name to use when trying to establish
 		the CIFS session.
   password	The user password.  If the mount helper is
 		installed, the user will be prompted for password
diff --git a/Documentation/filesystems/cifs/TODO b/Documentation/filesystems/cifs/TODO
index 066ffdd..396ecfd 100644
--- a/Documentation/filesystems/cifs/TODO
+++ b/Documentation/filesystems/cifs/TODO
@@ -1,4 +1,4 @@
-Version 2.03 August 1, 2014
+Version 2.04 September 13, 2017
 
 A Partial List of Missing Features
 ==================================
@@ -8,73 +8,69 @@
 is a partial list of the known problems and missing features:
 
 a) SMB3 (and SMB3.02) missing optional features:
-   - RDMA
+   - RDMA (started)
    - multichannel (started)
    - directory leases (improved metadata caching)
    - T10 copy offload (copy chunk is only mechanism supported)
-   - encrypted shares
 
 b) improved sparse file support
 
 c) Directory entry caching relies on a 1 second timer, rather than
-using FindNotify or equivalent.  - (started)
+using Directory Leases
 
 d) quota support (needs minor kernel change since quota calls
 to make it to network filesystems or deviceless filesystems)
 
-e) improve support for very old servers (OS/2 and Win9x for example)
-Including support for changing the time remotely (utimes command).
+e) Better optimize open to reduce redundant opens (using reference
+counts more) and to improve use of compounding in SMB3 to reduce
+number of roundtrips.
 
-f) hook lower into the sockets api (as NFS/SunRPC does) to avoid the
-extra copy in/out of the socket buffers in some cases.
-
-g) Better optimize open (and pathbased setfilesize) to reduce the
-oplock breaks coming from windows srv.  Piggyback identical file
-opens on top of each other by incrementing reference count rather
-than resending (helps reduce server resource utilization and avoid
-spurious oplock breaks).
-
-h) Add support for storing symlink info to Windows servers
-in the Extended Attribute format their SFU clients would recognize.
-
-i) Finish inotify support so kde and gnome file list windows
+f) Finish inotify support so kde and gnome file list windows
 will autorefresh (partially complete by Asser). Needs minor kernel
 vfs change to support removing D_NOTIFY on a file.   
 
-j) Add GUI tool to configure /proc/fs/cifs settings and for display of
+g) Add GUI tool to configure /proc/fs/cifs settings and for display of
 the CIFS statistics (started)
 
-k) implement support for security and trusted categories of xattrs
+h) implement support for security and trusted categories of xattrs
 (requires minor protocol extension) to enable better support for SELINUX
 
-l) Implement O_DIRECT flag on open (already supported on mount)
+i) Implement O_DIRECT flag on open (already supported on mount)
 
-m) Create UID mapping facility so server UIDs can be mapped on a per
+j) Create UID mapping facility so server UIDs can be mapped on a per
 mount or a per server basis to client UIDs or nobody if no mapping
-exists.  This is helpful when Unix extensions are negotiated to
-allow better permission checking when UIDs differ on the server
-and client.  Add new protocol request to the CIFS protocol 
-standard for asking the server for the corresponding name of a
-particular uid.
+exists. Also better integration with winbind for resolving SID owners
 
-n) DOS attrs - returned as pseudo-xattr in Samba format (check VFAT and NTFS for this too)
+k) Add tools to take advantage of more smb3 specific ioctls and features
 
-o) mount check for unmatched uids
+l) encrypted file support
 
-p) Add support for new vfs entry point for fallocate
+m) improved stats gathering, tools (perhaps integration with nfsometer?)
 
-q) Add tools to take advantage of cifs/smb3 specific ioctls and features
-such as "CopyChunk" (fast server side file copy)
+n) allow setting more NTFS/SMB3 file attributes remotely (currently limited to compressed
+file attribute via chflags) and improve user space tools for managing and
+viewing them.
 
-r) encrypted file support
+o) mount helper GUI (to simplify the various configuration options on mount)
 
-s) improved stats gathering, tools (perhaps integration with nfsometer?)
+p) autonegotiation of dialects (offering more than one dialect ie SMB3.02,
+SMB3, SMB2.1 not just SMB3).
 
-t) allow setting more NTFS/SMB3 file attributes remotely (currently limited to compressed
-file attribute via chflags)
+q) Allow mount.cifs to be more verbose in reporting errors with dialect
+or unsupported feature errors.
 
-u) mount helper GUI (to simplify the various configuration options on mount)
+r) updating cifs documentation, and user guid.
 
+s) Addressing bugs found by running a broader set of xfstests in standard
+file system xfstest suite.
+
+t) split cifs and smb3 support into separate modules so legacy (and less
+secure) CIFS dialect can be disabled in environments that don't need it
+and simplify the code.
+
+u) Finish up SMB3.1.1 dialect support
+
+v) POSIX Extensions for SMB3.1.1
 
 KNOWN BUGS
 ====================================
diff --git a/Documentation/filesystems/cifs/cifs.txt b/Documentation/filesystems/cifs/cifs.txt
index 2fac91a..6775660 100644
--- a/Documentation/filesystems/cifs/cifs.txt
+++ b/Documentation/filesystems/cifs/cifs.txt
@@ -1,24 +1,28 @@
-  This is the client VFS module for the Common Internet File System
-  (CIFS) protocol which is the successor to the Server Message Block 
+  This is the client VFS module for the SMB3 NAS protocol as well
+  older dialects such as the Common Internet File System (CIFS)
+  protocol which was the successor to the Server Message Block
   (SMB) protocol, the native file sharing mechanism for most early
   PC operating systems. New and improved versions of CIFS are now
   called SMB2 and SMB3. These dialects are also supported by the
   CIFS VFS module. CIFS is fully supported by network
-  file servers such as Windows 2000, 2003, 2008 and 2012
+  file servers such as Windows 2000, 2003, 2008, 2012 and 2016
   as well by Samba (which provides excellent CIFS
-  server support for Linux and many other operating systems), so
+  server support for Linux and many other operating systems), Apple
+  systems, as well as most Network Attached Storage vendors, so
   this network filesystem client can mount to a wide variety of
   servers.
 
   The intent of this module is to provide the most advanced network
-  file system function for CIFS compliant servers, including better
-  POSIX compliance, secure per-user session establishment, high
-  performance safe distributed caching (oplock), optional packet
+  file system function for SMB3 compliant servers, including advanced
+  security features, excellent parallelized high performance i/o, better
+  POSIX compliance, secure per-user session establishment, encryption,
+  high performance safe distributed caching (leases/oplocks), optional packet
   signing, large files, Unicode support and other internationalization
   improvements. Since both Samba server and this filesystem client support
-  the CIFS Unix extensions, the combination can provide a reasonable 
-  alternative to NFSv4 for fileserving in some Linux to Linux environments,
-  not just in Linux to Windows environments.
+  the CIFS Unix extensions (and in the future SMB3 POSIX extensions),
+  the combination can provide a reasonable alternative to other network and
+  cluster file systems for fileserving in some Linux to Linux environments,
+  not just in Linux to Windows (or Linux to Mac) environments.
 
   This filesystem has an mount utility (mount.cifs) that can be obtained from
 
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index 36f528a..8caa607 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -210,8 +210,11 @@
 beneath or above the path of another overlay lower layer path.
 
 Using an upper layer path and/or a workdir path that are already used by
-another overlay mount is not allowed and will fail with EBUSY.  Using
+another overlay mount is not allowed and may fail with EBUSY.  Using
 partially overlapping paths is not allowed but will not fail with EBUSY.
+If files are accessed from two overlayfs mounts which share or overlap the
+upper layer and/or workdir path the behavior of the overlay is undefined,
+though it will not result in a crash or deadlock.
 
 Mounting an overlay using an upper layer path, where the upper layer path
 was previously used by another mounted overlay in combination with a
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 24da7b3..9a3658c 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -366,7 +366,8 @@
 
 Declaring:
 
-DRIVER_ATTR(_name, _mode, _show, _store)
+DRIVER_ATTR_RO(_name)
+DRIVER_ATTR_RW(_name)
 
 Creation/Removal:
 
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 789b74d..8781485 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -337,7 +337,7 @@
   jeq #14, good           /* __NR_rt_sigprocmask */
   jeq #13, good           /* __NR_rt_sigaction */
   jeq #35, good           /* __NR_nanosleep */
-  bad: ret #0             /* SECCOMP_RET_KILL */
+  bad: ret #0             /* SECCOMP_RET_KILL_THREAD */
   good: ret #0x7fff0000   /* SECCOMP_RET_ALLOW */
 
 The above example code can be placed into a file (here called "foo"), and
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index b3345d0..77f4de5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1680,6 +1680,9 @@
 	2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
 	   link-local address has been found.
 
+	DAD operation and mode on a given interface will be selected according
+	to the maximum value of conf/{all,interface}/accept_dad.
+
 force_tllao - BOOLEAN
 	Enable sending the target link-layer address option even when
 	responding to a unicast neighbor solicitation.
@@ -1727,16 +1730,23 @@
 
 optimistic_dad - BOOLEAN
 	Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
-		0: disabled (default)
-		1: enabled
+	0: disabled (default)
+	1: enabled
+
+	Optimistic Duplicate Address Detection for the interface will be enabled
+	if at least one of conf/{all,interface}/optimistic_dad is set to 1,
+	it will be disabled otherwise.
 
 use_optimistic - BOOLEAN
 	If enabled, do not classify optimistic addresses as deprecated during
 	source address selection.  Preferred addresses will still be chosen
 	before optimistic addresses, subject to other ranking in the source
 	address selection algorithm.
-		0: disabled (default)
-		1: enabled
+	0: disabled (default)
+	1: enabled
+
+	This will be enabled if at least one of
+	conf/{all,interface}/use_optimistic is set to 1, disabled otherwise.
 
 stable_secret - IPv6 address
 	This IPv6 address will be used as a secret to generate IPv6
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index 5e40e1f..82236a1 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -13,42 +13,42 @@
 with SR-IOV or soft switches, such as OVS, are possible.
 
 
-                             User-space tools
+                             User-space tools
 
-       user space                   |
-      +-------------------------------------------------------------------+
-       kernel                       | Netlink
-                                    |
-                     +--------------+-------------------------------+
-                     |         Network stack                        |
-                     |           (Linux)                            |
-                     |                                              |
-                     +----------------------------------------------+
+       user space                   |
+      +-------------------------------------------------------------------+
+       kernel                       | Netlink
+                                    |
+                     +--------------+-------------------------------+
+                     |         Network stack                        |
+                     |           (Linux)                            |
+                     |                                              |
+                     +----------------------------------------------+
 
                            sw1p2     sw1p4     sw1p6
-                      sw1p1  +  sw1p3  +  sw1p5  +          eth1
-                        +    |    +    |    +    |            +
-                        |    |    |    |    |    |            |
-                     +--+----+----+----+-+--+----+---+  +-----+-----+
-                     |         Switch driver         |  |    mgmt   |
-                     |        (this document)        |  |   driver  |
-                     |                               |  |           |
-                     +--------------+----------------+  +-----------+
-                                    |
-       kernel                       | HW bus (eg PCI)
-      +-------------------------------------------------------------------+
-       hardware                     |
-                     +--------------+---+------------+
-                     |         Switch device (sw1)   |
-                     |  +----+                       +--------+
-                     |  |    v offloaded data path   | mgmt port
-                     |  |    |                       |
-                     +--|----|----+----+----+----+---+
-                        |    |    |    |    |    |
-                        +    +    +    +    +    +
-                       p1   p2   p3   p4   p5   p6
+                      sw1p1  +  sw1p3  +  sw1p5  +          eth1
+                        +    |    +    |    +    |            +
+                        |    |    |    |    |    |            |
+                     +--+----+----+----+----+----+---+  +-----+-----+
+                     |         Switch driver         |  |    mgmt   |
+                     |        (this document)        |  |   driver  |
+                     |                               |  |           |
+                     +--------------+----------------+  +-----------+
+                                    |
+       kernel                       | HW bus (eg PCI)
+      +-------------------------------------------------------------------+
+       hardware                     |
+                     +--------------+----------------+
+                     |         Switch device (sw1)   |
+                     |  +----+                       +--------+
+                     |  |    v offloaded data path   | mgmt port
+                     |  |    |                       |
+                     +--|----|----+----+----+----+---+
+                        |    |    |    |    |    |
+                        +    +    +    +    +    +
+                       p1   p2   p3   p4   p5   p6
 
-                             front-panel ports
+                             front-panel ports
 
 
                                     Fig 1.
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index ce61d1f..694968c 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -75,6 +75,7 @@
 - reboot-cmd                  [ SPARC only ]
 - rtsig-max
 - rtsig-nr
+- seccomp/                    ==> Documentation/userspace-api/seccomp_filter.rst
 - sem
 - sem_next_id		      [ sysv ipc ]
 - sg-big-buff                 [ generic SCSI device (sg) ]
diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst
index f71eb5e..099c412 100644
--- a/Documentation/userspace-api/seccomp_filter.rst
+++ b/Documentation/userspace-api/seccomp_filter.rst
@@ -87,11 +87,16 @@
 A seccomp filter may return any of the following values. If multiple
 filters exist, the return value for the evaluation of a given system
 call will always use the highest precedent value. (For example,
-``SECCOMP_RET_KILL`` will always take precedence.)
+``SECCOMP_RET_KILL_PROCESS`` will always take precedence.)
 
 In precedence order, they are:
 
-``SECCOMP_RET_KILL``:
+``SECCOMP_RET_KILL_PROCESS``:
+	Results in the entire process exiting immediately without executing
+	the system call.  The exit status of the task (``status & 0x7f``)
+	will be ``SIGSYS``, not ``SIGKILL``.
+
+``SECCOMP_RET_KILL_THREAD``:
 	Results in the task exiting immediately without executing the
 	system call.  The exit status of the task (``status & 0x7f``) will
 	be ``SIGSYS``, not ``SIGKILL``.
@@ -141,6 +146,15 @@
 	allow use of ptrace, even of other sandboxed processes, without
 	extreme care; ptracers can use this mechanism to escape.)
 
+``SECCOMP_RET_LOG``:
+	Results in the system call being executed after it is logged. This
+	should be used by application developers to learn which syscalls their
+	application needs without having to iterate through multiple test and
+	development cycles to build the list.
+
+	This action will only be logged if "log" is present in the
+	actions_logged sysctl string.
+
 ``SECCOMP_RET_ALLOW``:
 	Results in the system call being executed.
 
@@ -169,7 +183,41 @@
 and a more generic example of a higher level macro interface for BPF
 program generation.
 
+Sysctls
+=======
 
+Seccomp's sysctl files can be found in the ``/proc/sys/kernel/seccomp/``
+directory. Here's a description of each file in that directory:
+
+``actions_avail``:
+	A read-only ordered list of seccomp return values (refer to the
+	``SECCOMP_RET_*`` macros above) in string form. The ordering, from
+	left-to-right, is the least permissive return value to the most
+	permissive return value.
+
+	The list represents the set of seccomp return values supported
+	by the kernel. A userspace program may use this list to
+	determine if the actions found in the ``seccomp.h``, when the
+	program was built, differs from the set of actions actually
+	supported in the current running kernel.
+
+``actions_logged``:
+	A read-write ordered list of seccomp return values (refer to the
+	``SECCOMP_RET_*`` macros above) that are allowed to be logged. Writes
+	to the file do not need to be in ordered form but reads from the file
+	will be ordered in the same way as the actions_avail sysctl.
+
+	It is important to note that the value of ``actions_logged`` does not
+	prevent certain actions from being logged when the audit subsystem is
+	configured to audit a task. If the action is not found in
+	``actions_logged`` list, the final decision on whether to audit the
+	action for that task is ultimately left up to the audit subsystem to
+	decide for all seccomp return values other than ``SECCOMP_RET_ALLOW``.
+
+	The ``allow`` string is not accepted in the ``actions_logged`` sysctl
+	as it is not possible to log ``SECCOMP_RET_ALLOW`` actions. Attempting
+	to write ``allow`` to the sysctl will result in an EINVAL being
+	returned.
 
 Adding architecture support
 ===========================
diff --git a/MAINTAINERS b/MAINTAINERS
index 2281af4..2d3d750 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -352,6 +352,18 @@
 S:	Maintained
 F:	drivers/acpi/arm64
 
+ACPI PMIC DRIVERS
+M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	Len Brown <lenb@kernel.org>
+R:	Andy Shevchenko <andy@infradead.org>
+R:	Mika Westerberg <mika.westerberg@linux.intel.com>
+L:	linux-acpi@vger.kernel.org
+Q:	https://patchwork.kernel.org/project/linux-acpi/list/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
+B:	https://bugzilla.kernel.org
+S:	Supported
+F:	drivers/acpi/pmic/
+
 ACPI THERMAL DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
@@ -2853,7 +2865,6 @@
 F:	drivers/scsi/bnx2i/
 
 BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M:	Yuval Mintz <Yuval.Mintz@cavium.com>
 M:	Ariel Elior <ariel.elior@cavium.com>
 M:	everest-linux-l2@cavium.com
 L:	netdev@vger.kernel.org
@@ -5248,7 +5259,8 @@
 F:	drivers/iommu/exynos-iommu.c
 
 EZchip NPS platform support
-M:	Noam Camus <noamc@ezchip.com>
+M:	Elad Kanfi <eladkan@mellanox.com>
+M:	Vineet Gupta <vgupta@synopsys.com>
 S:	Supported
 F:	arch/arc/plat-eznps
 F:	arch/arc/boot/dts/eznps.dts
@@ -6643,8 +6655,8 @@
 M:	Stefan Schmidt <stefan@osg.samsung.com>
 L:	linux-wpan@vger.kernel.org
 W:	http://wpan.cakelab.org/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan-next.git
 S:	Maintained
 F:	net/ieee802154/
 F:	net/mac802154/
@@ -6727,7 +6739,7 @@
 F:	drivers/auxdisplay/img-ascii-lcd.c
 
 IMGTEC IR DECODER DRIVER
-M:	James Hogan <james.hogan@imgtec.com>
+M:	James Hogan <jhogan@kernel.org>
 S:	Maintained
 F:	drivers/media/rc/img-ir/
 
@@ -7551,7 +7563,7 @@
 F:	arch/arm64/kvm/
 
 KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
-M:	James Hogan <james.hogan@imgtec.com>
+M:	James Hogan <jhogan@kernel.org>
 L:	linux-mips@linux-mips.org
 S:	Supported
 F:	arch/mips/include/uapi/asm/kvm*
@@ -8253,6 +8265,12 @@
 S:	Orphan
 F:	drivers/net/wireless/marvell/libertas/
 
+MARVELL MACCHIATOBIN SUPPORT
+M:	Russell King <rmk@armlinux.org.uk>
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts
+
 MARVELL MV643XX ETHERNET DRIVER
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	netdev@vger.kernel.org
@@ -8586,6 +8604,12 @@
 S:	Maintained
 F:	drivers/media/rc/mtk-cir.c
 
+MEDIATEK PMIC LED DRIVER
+M:	Sean Wang <sean.wang@mediatek.com>
+S:	Maintained
+F:	drivers/leds/leds-mt6323.c
+F:	Documentation/devicetree/bindings/leds/leds-mt6323.txt
+
 MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@openwrt.org>
 M:	John Crispin <john@phrozen.org>
@@ -8868,7 +8892,7 @@
 T:	git git://linuxtv.org/media_tree.git
 
 METAG ARCHITECTURE
-M:	James Hogan <james.hogan@imgtec.com>
+M:	James Hogan <jhogan@kernel.org>
 L:	linux-metag@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/metag.git
 S:	Odd Fixes
@@ -9337,7 +9361,7 @@
 M:	Josef Bacik <jbacik@fb.com>
 S:	Maintained
 L:	linux-block@vger.kernel.org
-L:	nbd-general@lists.sourceforge.net
+L:	nbd@other.debian.org
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/uapi/linux/nbd.h
@@ -11047,7 +11071,6 @@
 F:	drivers/scsi/qedi/
 
 QLOGIC QL4xxx ETHERNET DRIVER
-M:	Yuval Mintz <Yuval.Mintz@cavium.com>
 M:	Ariel Elior <Ariel.Elior@cavium.com>
 M:	everest-linux-l2@cavium.com
 L:	netdev@vger.kernel.org
@@ -12915,9 +12938,9 @@
 SYNOPSYS HSDK RESET CONTROLLER DRIVER
 M:	Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
 S:	Supported
-F:	drivers/reset/reset-hsdk-v1.c
-F:	include/dt-bindings/reset/snps,hsdk-v1-reset.h
-F:	Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt
+F:	drivers/reset/reset-hsdk.c
+F:	include/dt-bindings/reset/snps,hsdk-reset.h
+F:	Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt
 
 SYSTEM CONFIGURATION (SYSCON)
 M:	Lee Jones <lee.jones@linaro.org>
diff --git a/Makefile b/Makefile
index 64cbc66..cf007a3 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -1172,11 +1172,11 @@
 
 PHONY += kselftest
 kselftest:
-	$(Q)$(MAKE) -C tools/testing/selftests run_tests
+	$(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests
 
 PHONY += kselftest-clean
 kselftest-clean:
-	$(Q)$(MAKE) -C tools/testing/selftests clean
+	$(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean
 
 PHONY += kselftest-merge
 kselftest-merge:
diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h
index 384bd47..45c020a 100644
--- a/arch/alpha/include/asm/mmu_context.h
+++ b/arch/alpha/include/asm/mmu_context.h
@@ -8,6 +8,7 @@
  */
 
 #include <linux/mm_types.h>
+#include <linux/sched.h>
 
 #include <asm/machvec.h>
 #include <asm/compiler.h>
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index a598641..c84e67f 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -24,7 +24,7 @@
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_FUTEX_CMPXCHG
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 3a4b52b..d37f49d 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -6,8 +6,6 @@
 # published by the Free Software Foundation.
 #
 
-UTS_MACHINE := arc
-
 ifeq ($(CROSS_COMPILE),)
 ifndef CONFIG_CPU_BIG_ENDIAN
 CROSS_COMPILE := arc-linux-
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 2367a67..e114000 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -44,7 +44,14 @@
 
 			mmcclk: mmcclk {
 				compatible = "fixed-clock";
-				clock-frequency = <50000000>;
+				/*
+				 * DW sdio controller has external ciu clock divider
+				 * controlled via register in SDIO IP. It divides
+				 * sdio_ref_clk (which comes from CGU) by 16 for
+				 * default. So default mmcclk clock (which comes
+				 * to sdk_in) is 25000000 Hz.
+				 */
+				clock-frequency = <25000000>;
 				#clock-cells = <0>;
 			};
 
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 229d13a..8adde1b 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -12,6 +12,7 @@
 /dts-v1/;
 
 #include <dt-bindings/net/ti-dp83867.h>
+#include <dt-bindings/reset/snps,hsdk-reset.h>
 
 / {
 	model = "snps,hsdk";
@@ -57,10 +58,10 @@
 		};
 	};
 
-	core_clk: core-clk {
+	input_clk: input-clk {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
-		clock-frequency = <500000000>;
+		clock-frequency = <33333333>;
 	};
 
 	cpu_intc: cpu-interrupt-controller {
@@ -102,6 +103,19 @@
 
 		ranges = <0x00000000 0xf0000000 0x10000000>;
 
+		cgu_rst: reset-controller@8a0 {
+			compatible = "snps,hsdk-reset";
+			#reset-cells = <1>;
+			reg = <0x8A0 0x4>, <0xFF0 0x4>;
+		};
+
+		core_clk: core-clk@0 {
+			compatible = "snps,hsdk-core-pll-clock";
+			reg = <0x00 0x10>, <0x14B8 0x4>;
+			#clock-cells = <0>;
+			clocks = <&input_clk>;
+		};
+
 		serial: serial@5000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x5000 0x100>;
@@ -120,7 +134,17 @@
 
 		mmcclk_ciu: mmcclk-ciu {
 			compatible = "fixed-clock";
-			clock-frequency = <100000000>;
+			/*
+			 * DW sdio controller has external ciu clock divider
+			 * controlled via register in SDIO IP. Due to its
+			 * unexpected default value (it should devide by 1
+			 * but it devides by 8) SDIO IP uses wrong clock and
+			 * works unstable (see STAR 9001204800)
+			 * So add temporary fix and change clock frequency
+			 * from 100000000 to 12500000 Hz until we fix dw sdio
+			 * driver itself.
+			 */
+			clock-frequency = <12500000>;
 			#clock-cells = <0>;
 		};
 
@@ -141,6 +165,8 @@
 			clocks = <&gmacclk>;
 			clock-names = "stmmaceth";
 			phy-handle = <&phy0>;
+			resets = <&cgu_rst HSDK_ETH_RESET>;
+			reset-names = "stmmaceth";
 
 			mdio {
 				#address-cells = <1>;
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 6980b96..ec7c849 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -105,7 +105,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 2233f57..63d3cf6 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -104,7 +104,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 30a3d4c..f613eca 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -107,7 +107,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index 821a2e5..3507be2 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -84,5 +84,5 @@
 CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 9a3fcf4..15f0f6b 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -63,6 +63,7 @@
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_RESET_HSDK=y
 CONFIG_EXT3_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
@@ -72,7 +73,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index c0d6a01..4fcf4f2 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -94,7 +94,7 @@
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_SHIRQ=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 5c09717..7b71464 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -98,7 +98,7 @@
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_SHIRQ=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index ba8e802..b1c56d3 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -98,6 +98,7 @@
 
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
+#define AUX_EXEC_CTRL		8
 #define AUX_INTR_VEC_BASE	0x25
 #define AUX_VOL			0x5e
 
@@ -135,12 +136,12 @@
 #endif
 };
 
-struct bcr_isa {
+struct bcr_isa_arcv2 {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1,
-		     pad1:11, atomic1:1, ver:8;
+		     pad1:12, ver:8;
 #else
-	unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1,
+	unsigned int ver:8, pad1:12, be:1, atomic:1, unalign:1,
 		     ldd:1, pad2:4, div_rem:4;
 #endif
 };
@@ -263,13 +264,13 @@
 	struct cpuinfo_arc_mmu mmu;
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
-	struct bcr_isa isa;
+	struct bcr_isa_arcv2 isa;
 	const char *details, *name;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
-			     fpu_sp:1, fpu_dp:1, pad2:6,
+			     fpu_sp:1, fpu_dp:1, dual_iss_enb:1, dual_iss_exist:1, pad2:4,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index d400a21..8ee41e9 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -78,9 +78,6 @@
 
 #endif
 
-#define copy_segments(tsk, mm)      do { } while (0)
-#define release_segments(mm)        do { } while (0)
-
 #define KSTK_EIP(tsk)   (task_pt_regs(tsk)->ret)
 #define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 877cec8..fb83844 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -51,6 +51,7 @@
 	{ 0x51, "R2.0" },
 	{ 0x52, "R2.1" },
 	{ 0x53, "R3.0" },
+	{ 0x54, "R4.0" },
 #endif
 	{ 0x00, NULL   }
 };
@@ -62,6 +63,7 @@
 #else
 	{ 0x40, "ARC EM"  },
 	{ 0x50, "ARC HS38"  },
+	{ 0x54, "ARC HS48"  },
 #endif
 	{ 0x00, "Unknown"   }
 };
@@ -119,11 +121,11 @@
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	const struct id_to_str *tbl;
+	struct bcr_isa_arcv2 isa;
 
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
-	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
 	for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
 		if (cpu->core.family == tbl->id) {
@@ -133,7 +135,7 @@
 	}
 
 	for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
-		if ((cpu->core.family & 0xF0) == tbl->id)
+		if ((cpu->core.family & 0xF4) == tbl->id)
 			break;
 	}
 	cpu->name = tbl->str;
@@ -192,6 +194,14 @@
 		cpu->bpu.full = bpu.ft;
 		cpu->bpu.num_cache = 256 << bpu.bce;
 		cpu->bpu.num_pred = 2048 << bpu.pte;
+
+		if (cpu->core.family >= 0x54) {
+			unsigned int exec_ctrl;
+
+			READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
+			cpu->extn.dual_iss_exist = 1;
+			cpu->extn.dual_iss_enb = exec_ctrl & 1;
+		}
 	}
 
 	READ_BCR(ARC_REG_AP_BCR, bcr);
@@ -205,18 +215,25 @@
 
 	cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
 
+	READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
+
 	/* some hacks for lack of feature BCR info in old ARC700 cores */
 	if (is_isa_arcompact()) {
-		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
+		if (!isa.ver)	/* ISA BCR absent, use Kconfig info */
 			cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
-		else
-			cpu->isa.atomic = cpu->isa.atomic1;
+		else {
+			/* ARC700_BUILD only has 2 bits of isa info */
+			struct bcr_generic bcr = *(struct bcr_generic *)&isa;
+			cpu->isa.atomic = bcr.info & 1;
+		}
 
 		cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
 
 		 /* there's no direct way to distinguish 750 vs. 770 */
 		if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3))
 			cpu->name = "ARC750";
+	} else {
+		cpu->isa = isa;
 	}
 }
 
@@ -232,10 +249,11 @@
 		       "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n",
 		       core->family, core->cpu_id, core->chip_id);
 
-	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n",
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n",
 		       cpu_id, cpu->name, cpu->details,
 		       is_isa_arcompact() ? "ARCompact" : "ARCv2",
-		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"));
+		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"),
+		       IS_AVAIL3(cpu->extn.dual_iss_exist, cpu->extn.dual_iss_enb, " Dual-Issue"));
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s%s%s\nISA Extn\t: ",
 		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index f1ac679..cf14ebc 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -111,6 +111,13 @@
 
 	axs10x_enable_gpio_intc_wire();
 
+	/*
+	 * Reset ethernet IP core.
+	 * TODO: get rid of this quirk after axs10x reset driver (or simple
+	 * reset driver) will be available in upstream.
+	 */
+	iowrite32((1 << 5), (void __iomem *) CREG_MB_SW_RESET);
+
 	scnprintf(mb, 32, "MainBoard v%d", mb_rev);
 	axs10x_print_board_ver(CREG_MB_VER, mb);
 }
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index 5a6ed5a..bd08de4 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -6,4 +6,5 @@
 #
 
 menuconfig ARC_SOC_HSDK
-       bool "ARC HS Development Kit SOC"
+	bool "ARC HS Development Kit SOC"
+	select CLK_HSDK
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index a2e7fd1..744e62e 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -38,6 +38,42 @@
 #define CREG_PAE		(CREG_BASE + 0x180)
 #define CREG_PAE_UPDATE		(CREG_BASE + 0x194)
 
+#define CREG_CORE_IF_CLK_DIV	(CREG_BASE + 0x4B8)
+#define CREG_CORE_IF_CLK_DIV_2	0x1
+#define CGU_BASE		ARC_PERIPHERAL_BASE
+#define CGU_PLL_STATUS		(ARC_PERIPHERAL_BASE + 0x4)
+#define CGU_PLL_CTRL		(ARC_PERIPHERAL_BASE + 0x0)
+#define CGU_PLL_STATUS_LOCK	BIT(0)
+#define CGU_PLL_STATUS_ERR	BIT(1)
+#define CGU_PLL_CTRL_1GHZ	0x3A10
+#define HSDK_PLL_LOCK_TIMEOUT	500
+
+#define HSDK_PLL_LOCKED() \
+	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK)
+
+#define HSDK_PLL_ERR() \
+	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR)
+
+static void __init hsdk_set_cpu_freq_1ghz(void)
+{
+	u32 timeout = HSDK_PLL_LOCK_TIMEOUT;
+
+	/*
+	 * As we set cpu clock which exceeds 500MHz, the divider for the interface
+	 * clock must be programmed to div-by-2.
+	 */
+	iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV);
+
+	/* Set cpu clock to 1GHz */
+	iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL);
+
+	while (!HSDK_PLL_LOCKED() && timeout--)
+		cpu_relax();
+
+	if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR())
+		pr_err("Failed to setup CPU frequency to 1GHz!");
+}
+
 static void __init hsdk_init_early(void)
 {
 	/*
@@ -52,6 +88,12 @@
 
 	/* Really apply settings made above */
 	writel(1, (void __iomem *) CREG_PAE_UPDATE);
+
+	/*
+	 * Setup CPU frequency to 1GHz.
+	 * TODO: remove it after smart hsdk pll driver will be introduced.
+	 */
+	hsdk_set_cpu_freq_1ghz();
 }
 
 static const char *hsdk_compat[] __initconst = {
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 7d7ca05..e58fab8 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -36,6 +36,8 @@
 		phy1 = &usb1_phy;
 		ethernet0 = &cpsw_emac0;
 		ethernet1 = &cpsw_emac1;
+		spi0 = &spi0;
+		spi1 = &spi1;
 	};
 
 	cpus {
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 9d276af..081fa68 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -388,6 +388,7 @@
 	pinctrl-0 = <&cpsw_default>;
 	pinctrl-1 = <&cpsw_sleep>;
 	status = "okay";
+	slaves = <1>;
 };
 
 &davinci_mdio {
@@ -402,11 +403,6 @@
 	phy-mode = "rmii";
 };
 
-&cpsw_emac1 {
-	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "rmii";
-};
-
 &phy_sel {
 	rmii-clock-ext;
 };
diff --git a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts
index 9c9088c..60cb084 100644
--- a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts
@@ -67,7 +67,10 @@
 
 		usb1: ohci@00400000 {
 			num-ports = <3>;
-			atmel,vbus-gpio = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>;
+			atmel,vbus-gpio = <0 /* &pioA PIN_PD20 GPIO_ACTIVE_HIGH */
+					   &pioA PIN_PA27 GPIO_ACTIVE_HIGH
+					   0
+					  >;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb_default>;
 			status = "okay";
@@ -120,7 +123,7 @@
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_mikrobus2_uart>;
 				atmel,use-dma-rx;
-				atmel-use-dma-tx;
+				atmel,use-dma-tx;
 				status = "okay";
 			};
 
@@ -178,7 +181,7 @@
 			uart4: serial@fc00c000 {
 				atmel,use-dma-rx;
 				atmel,use-dma-tx;
-				pinctrl-name = "default";
+				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_mikrobus1_uart>;
 				status = "okay";
 			};
@@ -330,7 +333,7 @@
 				};
 
 				pinctrl_led_gpio_default: led_gpio_default {
-					pinmux = <PIN_PA27__GPIO>,
+					pinmux = <PIN_PA10__GPIO>,
 						 <PIN_PB1__GPIO>,
 						 <PIN_PA31__GPIO>;
 					bias-pull-up;
@@ -396,7 +399,7 @@
 				};
 
 				pinctrl_usb_default: usb_default {
-					pinmux = <PIN_PA10__GPIO>,
+					pinmux = <PIN_PA27__GPIO>,
 						 <PIN_PD19__GPIO>;
 					bias-disable;
 				};
@@ -520,17 +523,17 @@
 
 		red {
 			label = "red";
-			gpios = <&pioA PIN_PA27 GPIO_ACTIVE_LOW>;
+			gpios = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>;
 		};
 
 		green {
 			label = "green";
-			gpios = <&pioA PIN_PB1 GPIO_ACTIVE_LOW>;
+			gpios = <&pioA PIN_PB1 GPIO_ACTIVE_HIGH>;
 		};
 
 		blue {
 			label = "blue";
-			gpios = <&pioA PIN_PA31 GPIO_ACTIVE_LOW>;
+			gpios = <&pioA PIN_PA31 GPIO_ACTIVE_HIGH>;
 			linux,default-trigger = "heartbeat";
 		};
 	};
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index 67e72bc..c755079 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -15,6 +15,13 @@
 	compatible = "ti,da850-evm", "ti,da850";
 	model = "DA850/AM1808/OMAP-L138 EVM";
 
+	aliases {
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		ethernet0 = &eth0;
+	};
+
 	soc@1c00000 {
 		pmx_core: pinmux@14120 {
 			status = "okay";
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index cf229df..e62b628 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -1817,6 +1817,8 @@
 		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1868>;
+		assigned-clocks = <&mcasp3_ahclkx_mux>;
+		assigned-clock-parents = <&abe_24m_fclk>;
 	};
 
 	mcasp3_aux_gfclk_mux: mcasp3_aux_gfclk_mux@1868 {
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 26c20e1..4acd32a 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -144,15 +144,6 @@
 		io-channel-names = "temp", "bsi", "vbat";
 	};
 
-	rear_camera: camera@0 {
-		compatible = "linux,camera";
-
-		module {
-			model = "TCM8341MD";
-			sensor = <&cam1>;
-		};
-	};
-
 	pwm9: dmtimer-pwm {
 		compatible = "ti,omap-dmtimer-pwm";
 		#pwm-cells = <3>;
@@ -189,10 +180,8 @@
 				clock-lanes = <1>;
 				data-lanes = <0>;
 				lane-polarity = <0 0>;
-				clock-inv = <0>;
 				/* Select strobe = <1> for back camera, <0> for front camera */
 				strobe = <1>;
-				crc = <0>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index cb47ae7..1b0bd72 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -267,15 +267,19 @@
 	clock-frequency = <400000>;
 
 	as3645a@30 {
+		#address-cells = <1>;
+		#size-cells = <0>;
 		reg = <0x30>;
 		compatible = "ams,as3645a";
-		flash {
+		flash@0 {
+			reg = <0x0>;
 			flash-timeout-us = <150000>;
 			flash-max-microamp = <320000>;
 			led-max-microamp = <60000>;
-			peak-current-limit = <1750000>;
+			ams,input-max-microamp = <1750000>;
 		};
-		indicator {
+		indicator@1 {
+			reg = <0x1>;
 			led-max-microamp = <10000>;
 		};
 	};
diff --git a/arch/arm/boot/dts/stm32429i-eval.dts b/arch/arm/boot/dts/stm32429i-eval.dts
index 97b1c23..293ecb9 100644
--- a/arch/arm/boot/dts/stm32429i-eval.dts
+++ b/arch/arm/boot/dts/stm32429i-eval.dts
@@ -47,6 +47,7 @@
 
 /dts-v1/;
 #include "stm32f429.dtsi"
+#include "stm32f429-pinctrl.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/gpio/gpio.h>
 
@@ -202,10 +203,8 @@
 	stmpe1600: stmpe1600@42 {
 		compatible = "st,stmpe1600";
 		reg = <0x42>;
-		irq-gpio = <&gpioi 8 0>;
-		irq-trigger = <3>;
 		interrupts = <8 3>;
-		interrupt-parent = <&exti>;
+		interrupt-parent = <&gpioi>;
 		interrupt-controller;
 		wakeup-source;
 
diff --git a/arch/arm/boot/dts/stm32f4-pinctrl.dtsi b/arch/arm/boot/dts/stm32f4-pinctrl.dtsi
new file mode 100644
index 0000000..7f3560c
--- /dev/null
+++ b/arch/arm/boot/dts/stm32f4-pinctrl.dtsi
@@ -0,0 +1,343 @@
+/*
+ * Copyright 2017 - Alexandre Torgue <alexandre.torgue@st.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file 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 file 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.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     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 <dt-bindings/pinctrl/stm32f429-pinfunc.h>
+#include <dt-bindings/mfd/stm32f4-rcc.h>
+
+/ {
+	soc {
+		pinctrl: pin-controller {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x40020000 0x3000>;
+			interrupt-parent = <&exti>;
+			st,syscfg = <&syscfg 0x8>;
+			pins-are-numbered;
+
+			gpioa: gpio@40020000 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x0 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)>;
+				st,bank-name = "GPIOA";
+			};
+
+			gpiob: gpio@40020400 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x400 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOB)>;
+				st,bank-name = "GPIOB";
+			};
+
+			gpioc: gpio@40020800 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x800 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOC)>;
+				st,bank-name = "GPIOC";
+			};
+
+			gpiod: gpio@40020c00 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0xc00 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOD)>;
+				st,bank-name = "GPIOD";
+			};
+
+			gpioe: gpio@40021000 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x1000 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOE)>;
+				st,bank-name = "GPIOE";
+			};
+
+			gpiof: gpio@40021400 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x1400 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOF)>;
+				st,bank-name = "GPIOF";
+			};
+
+			gpiog: gpio@40021800 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x1800 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOG)>;
+				st,bank-name = "GPIOG";
+			};
+
+			gpioh: gpio@40021c00 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x1c00 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOH)>;
+				st,bank-name = "GPIOH";
+			};
+
+			gpioi: gpio@40022000 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x2000 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOI)>;
+				st,bank-name = "GPIOI";
+			};
+
+			gpioj: gpio@40022400 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x2400 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOJ)>;
+				st,bank-name = "GPIOJ";
+			};
+
+			gpiok: gpio@40022800 {
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				reg = <0x2800 0x400>;
+				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOK)>;
+				st,bank-name = "GPIOK";
+			};
+
+			usart1_pins_a: usart1@0 {
+				pins1 {
+					pinmux = <STM32F429_PA9_FUNC_USART1_TX>;
+					bias-disable;
+					drive-push-pull;
+					slew-rate = <0>;
+				};
+				pins2 {
+					pinmux = <STM32F429_PA10_FUNC_USART1_RX>;
+					bias-disable;
+				};
+			};
+
+			usart3_pins_a: usart3@0 {
+				pins1 {
+					pinmux = <STM32F429_PB10_FUNC_USART3_TX>;
+					bias-disable;
+					drive-push-pull;
+					slew-rate = <0>;
+				};
+				pins2 {
+					pinmux = <STM32F429_PB11_FUNC_USART3_RX>;
+					bias-disable;
+				};
+			};
+
+			usbotg_fs_pins_a: usbotg_fs@0 {
+				pins {
+					pinmux = <STM32F429_PA10_FUNC_OTG_FS_ID>,
+						 <STM32F429_PA11_FUNC_OTG_FS_DM>,
+						 <STM32F429_PA12_FUNC_OTG_FS_DP>;
+					bias-disable;
+					drive-push-pull;
+					slew-rate = <2>;
+				};
+			};
+
+			usbotg_fs_pins_b: usbotg_fs@1 {
+				pins {
+					pinmux = <STM32F429_PB12_FUNC_OTG_HS_ID>,
+						 <STM32F429_PB14_FUNC_OTG_HS_DM>,
+						 <STM32F429_PB15_FUNC_OTG_HS_DP>;
+					bias-disable;
+					drive-push-pull;
+					slew-rate = <2>;
+				};
+			};
+
+			usbotg_hs_pins_a: usbotg_hs@0 {
+				pins {
+					pinmux = <STM32F429_PH4_FUNC_OTG_HS_ULPI_NXT>,
+						 <STM32F429_PI11_FUNC_OTG_HS_ULPI_DIR>,
+						 <STM32F429_PC0_FUNC_OTG_HS_ULPI_STP>,
+						 <STM32F429_PA5_FUNC_OTG_HS_ULPI_CK>,
+						 <STM32F429_PA3_FUNC_OTG_HS_ULPI_D0>,
+						 <STM32F429_PB0_FUNC_OTG_HS_ULPI_D1>,
+						 <STM32F429_PB1_FUNC_OTG_HS_ULPI_D2>,
+						 <STM32F429_PB10_FUNC_OTG_HS_ULPI_D3>,
+						 <STM32F429_PB11_FUNC_OTG_HS_ULPI_D4>,
+						 <STM32F429_PB12_FUNC_OTG_HS_ULPI_D5>,
+						 <STM32F429_PB13_FUNC_OTG_HS_ULPI_D6>,
+						 <STM32F429_PB5_FUNC_OTG_HS_ULPI_D7>;
+					bias-disable;
+					drive-push-pull;
+					slew-rate = <2>;
+				};
+			};
+
+			ethernet_mii: mii@0 {
+				pins {
+					pinmux = <STM32F429_PG13_FUNC_ETH_MII_TXD0_ETH_RMII_TXD0>,
+						 <STM32F429_PG14_FUNC_ETH_MII_TXD1_ETH_RMII_TXD1>,
+						 <STM32F429_PC2_FUNC_ETH_MII_TXD2>,
+						 <STM32F429_PB8_FUNC_ETH_MII_TXD3>,
+						 <STM32F429_PC3_FUNC_ETH_MII_TX_CLK>,
+						 <STM32F429_PG11_FUNC_ETH_MII_TX_EN_ETH_RMII_TX_EN>,
+						 <STM32F429_PA2_FUNC_ETH_MDIO>,
+						 <STM32F429_PC1_FUNC_ETH_MDC>,
+						 <STM32F429_PA1_FUNC_ETH_MII_RX_CLK_ETH_RMII_REF_CLK>,
+						 <STM32F429_PA7_FUNC_ETH_MII_RX_DV_ETH_RMII_CRS_DV>,
+						 <STM32F429_PC4_FUNC_ETH_MII_RXD0_ETH_RMII_RXD0>,
+						 <STM32F429_PC5_FUNC_ETH_MII_RXD1_ETH_RMII_RXD1>,
+						 <STM32F429_PH6_FUNC_ETH_MII_RXD2>,
+						 <STM32F429_PH7_FUNC_ETH_MII_RXD3>;
+					slew-rate = <2>;
+				};
+			};
+
+			adc3_in8_pin: adc@200 {
+				pins {
+					pinmux = <STM32F429_PF10_FUNC_ANALOG>;
+				};
+			};
+
+			pwm1_pins: pwm@1 {
+				pins {
+					pinmux = <STM32F429_PA8_FUNC_TIM1_CH1>,
+						 <STM32F429_PB13_FUNC_TIM1_CH1N>,
+						 <STM32F429_PB12_FUNC_TIM1_BKIN>;
+				};
+			};
+
+			pwm3_pins: pwm@3 {
+				pins {
+					pinmux = <STM32F429_PB4_FUNC_TIM3_CH1>,
+						 <STM32F429_PB5_FUNC_TIM3_CH2>;
+				};
+			};
+
+			i2c1_pins: i2c1@0 {
+				pins {
+					pinmux = <STM32F429_PB9_FUNC_I2C1_SDA>,
+						 <STM32F429_PB6_FUNC_I2C1_SCL>;
+					bias-disable;
+					drive-open-drain;
+					slew-rate = <3>;
+				};
+			};
+
+			ltdc_pins: ltdc@0 {
+				pins {
+					pinmux = <STM32F429_PI12_FUNC_LCD_HSYNC>,
+						 <STM32F429_PI13_FUNC_LCD_VSYNC>,
+						 <STM32F429_PI14_FUNC_LCD_CLK>,
+						 <STM32F429_PI15_FUNC_LCD_R0>,
+						 <STM32F429_PJ0_FUNC_LCD_R1>,
+						 <STM32F429_PJ1_FUNC_LCD_R2>,
+						 <STM32F429_PJ2_FUNC_LCD_R3>,
+						 <STM32F429_PJ3_FUNC_LCD_R4>,
+						 <STM32F429_PJ4_FUNC_LCD_R5>,
+						 <STM32F429_PJ5_FUNC_LCD_R6>,
+						 <STM32F429_PJ6_FUNC_LCD_R7>,
+						 <STM32F429_PJ7_FUNC_LCD_G0>,
+						 <STM32F429_PJ8_FUNC_LCD_G1>,
+						 <STM32F429_PJ9_FUNC_LCD_G2>,
+						 <STM32F429_PJ10_FUNC_LCD_G3>,
+						 <STM32F429_PJ11_FUNC_LCD_G4>,
+						 <STM32F429_PJ12_FUNC_LCD_B0>,
+						 <STM32F429_PJ13_FUNC_LCD_B1>,
+						 <STM32F429_PJ14_FUNC_LCD_B2>,
+						 <STM32F429_PJ15_FUNC_LCD_B3>,
+						 <STM32F429_PK0_FUNC_LCD_G5>,
+						 <STM32F429_PK1_FUNC_LCD_G6>,
+						 <STM32F429_PK2_FUNC_LCD_G7>,
+						 <STM32F429_PK3_FUNC_LCD_B4>,
+						 <STM32F429_PK4_FUNC_LCD_B5>,
+						 <STM32F429_PK5_FUNC_LCD_B6>,
+						 <STM32F429_PK6_FUNC_LCD_B7>,
+						 <STM32F429_PK7_FUNC_LCD_DE>;
+					slew-rate = <2>;
+				};
+			};
+
+			dcmi_pins: dcmi@0 {
+				pins {
+					pinmux = <STM32F429_PA4_FUNC_DCMI_HSYNC>,
+						 <STM32F429_PB7_FUNC_DCMI_VSYNC>,
+						 <STM32F429_PA6_FUNC_DCMI_PIXCLK>,
+						 <STM32F429_PC6_FUNC_DCMI_D0>,
+						 <STM32F429_PC7_FUNC_DCMI_D1>,
+						 <STM32F429_PC8_FUNC_DCMI_D2>,
+						 <STM32F429_PC9_FUNC_DCMI_D3>,
+						 <STM32F429_PC11_FUNC_DCMI_D4>,
+						 <STM32F429_PD3_FUNC_DCMI_D5>,
+						 <STM32F429_PB8_FUNC_DCMI_D6>,
+						 <STM32F429_PE6_FUNC_DCMI_D7>,
+						 <STM32F429_PC10_FUNC_DCMI_D8>,
+						 <STM32F429_PC12_FUNC_DCMI_D9>,
+						 <STM32F429_PD6_FUNC_DCMI_D10>,
+						 <STM32F429_PD2_FUNC_DCMI_D11>;
+					bias-disable;
+					drive-push-pull;
+					slew-rate = <3>;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/stm32f429-disco.dts b/arch/arm/boot/dts/stm32f429-disco.dts
index c66d617..5ceb2cf 100644
--- a/arch/arm/boot/dts/stm32f429-disco.dts
+++ b/arch/arm/boot/dts/stm32f429-disco.dts
@@ -47,6 +47,7 @@
 
 /dts-v1/;
 #include "stm32f429.dtsi"
+#include "stm32f429-pinctrl.dtsi"
 #include <dt-bindings/input/input.h>
 
 / {
diff --git a/arch/arm/boot/dts/stm32f429-pinctrl.dtsi b/arch/arm/boot/dts/stm32f429-pinctrl.dtsi
new file mode 100644
index 0000000..3e7a17d
--- /dev/null
+++ b/arch/arm/boot/dts/stm32f429-pinctrl.dtsi
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2017 - Alexandre Torgue <alexandre.torgue@st.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file 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 file 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.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     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 "stm32f4-pinctrl.dtsi"
+
+/ {
+	soc {
+		pinctrl: pin-controller {
+			compatible = "st,stm32f429-pinctrl";
+
+			gpioa: gpio@40020000 {
+				gpio-ranges = <&pinctrl 0 0 16>;
+			};
+
+			gpiob: gpio@40020400 {
+				gpio-ranges = <&pinctrl 0 16 16>;
+			};
+
+			gpioc: gpio@40020800 {
+				gpio-ranges = <&pinctrl 0 32 16>;
+			};
+
+			gpiod: gpio@40020c00 {
+				gpio-ranges = <&pinctrl 0 48 16>;
+			};
+
+			gpioe: gpio@40021000 {
+				gpio-ranges = <&pinctrl 0 64 16>;
+			};
+
+			gpiof: gpio@40021400 {
+				gpio-ranges = <&pinctrl 0 80 16>;
+			};
+
+			gpiog: gpio@40021800 {
+				gpio-ranges = <&pinctrl 0 96 16>;
+			};
+
+			gpioh: gpio@40021c00 {
+				gpio-ranges = <&pinctrl 0 112 16>;
+			};
+
+			gpioi: gpio@40022000 {
+				gpio-ranges = <&pinctrl 0 128 16>;
+			};
+
+			gpioj: gpio@40022400 {
+				gpio-ranges = <&pinctrl 0 144 16>;
+			};
+
+			gpiok: gpio@40022800 {
+				gpio-ranges = <&pinctrl 0 160 8>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi
index dd7e99b..5b36eb1 100644
--- a/arch/arm/boot/dts/stm32f429.dtsi
+++ b/arch/arm/boot/dts/stm32f429.dtsi
@@ -47,7 +47,6 @@
 
 #include "skeleton.dtsi"
 #include "armv7-m.dtsi"
-#include <dt-bindings/pinctrl/stm32f429-pinfunc.h>
 #include <dt-bindings/clock/stm32fx-clock.h>
 #include <dt-bindings/mfd/stm32f4-rcc.h>
 
@@ -591,302 +590,6 @@
 			status = "disabled";
 		};
 
-		pinctrl: pin-controller {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "st,stm32f429-pinctrl";
-			ranges = <0 0x40020000 0x3000>;
-			interrupt-parent = <&exti>;
-			st,syscfg = <&syscfg 0x8>;
-			pins-are-numbered;
-
-			gpioa: gpio@40020000 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x0 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)>;
-				st,bank-name = "GPIOA";
-			};
-
-			gpiob: gpio@40020400 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x400 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOB)>;
-				st,bank-name = "GPIOB";
-			};
-
-			gpioc: gpio@40020800 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x800 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOC)>;
-				st,bank-name = "GPIOC";
-			};
-
-			gpiod: gpio@40020c00 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0xc00 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOD)>;
-				st,bank-name = "GPIOD";
-			};
-
-			gpioe: gpio@40021000 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x1000 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOE)>;
-				st,bank-name = "GPIOE";
-			};
-
-			gpiof: gpio@40021400 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x1400 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOF)>;
-				st,bank-name = "GPIOF";
-			};
-
-			gpiog: gpio@40021800 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x1800 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOG)>;
-				st,bank-name = "GPIOG";
-			};
-
-			gpioh: gpio@40021c00 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x1c00 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOH)>;
-				st,bank-name = "GPIOH";
-			};
-
-			gpioi: gpio@40022000 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x2000 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOI)>;
-				st,bank-name = "GPIOI";
-			};
-
-			gpioj: gpio@40022400 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x2400 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOJ)>;
-				st,bank-name = "GPIOJ";
-			};
-
-			gpiok: gpio@40022800 {
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				reg = <0x2800 0x400>;
-				clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOK)>;
-				st,bank-name = "GPIOK";
-			};
-
-			usart1_pins_a: usart1@0 {
-				pins1 {
-					pinmux = <STM32F429_PA9_FUNC_USART1_TX>;
-					bias-disable;
-					drive-push-pull;
-					slew-rate = <0>;
-				};
-				pins2 {
-					pinmux = <STM32F429_PA10_FUNC_USART1_RX>;
-					bias-disable;
-				};
-			};
-
-			usart3_pins_a: usart3@0 {
-				pins1 {
-					pinmux = <STM32F429_PB10_FUNC_USART3_TX>;
-					bias-disable;
-					drive-push-pull;
-					slew-rate = <0>;
-				};
-				pins2 {
-					pinmux = <STM32F429_PB11_FUNC_USART3_RX>;
-					bias-disable;
-				};
-			};
-
-			usbotg_fs_pins_a: usbotg_fs@0 {
-				pins {
-					pinmux = <STM32F429_PA10_FUNC_OTG_FS_ID>,
-						 <STM32F429_PA11_FUNC_OTG_FS_DM>,
-						 <STM32F429_PA12_FUNC_OTG_FS_DP>;
-					bias-disable;
-					drive-push-pull;
-					slew-rate = <2>;
-				};
-			};
-
-			usbotg_fs_pins_b: usbotg_fs@1 {
-				pins {
-					pinmux = <STM32F429_PB12_FUNC_OTG_HS_ID>,
-						 <STM32F429_PB14_FUNC_OTG_HS_DM>,
-						 <STM32F429_PB15_FUNC_OTG_HS_DP>;
-					bias-disable;
-					drive-push-pull;
-					slew-rate = <2>;
-				};
-			};
-
-			usbotg_hs_pins_a: usbotg_hs@0 {
-				pins {
-					pinmux = <STM32F429_PH4_FUNC_OTG_HS_ULPI_NXT>,
-						 <STM32F429_PI11_FUNC_OTG_HS_ULPI_DIR>,
-						 <STM32F429_PC0_FUNC_OTG_HS_ULPI_STP>,
-						 <STM32F429_PA5_FUNC_OTG_HS_ULPI_CK>,
-						 <STM32F429_PA3_FUNC_OTG_HS_ULPI_D0>,
-						 <STM32F429_PB0_FUNC_OTG_HS_ULPI_D1>,
-						 <STM32F429_PB1_FUNC_OTG_HS_ULPI_D2>,
-						 <STM32F429_PB10_FUNC_OTG_HS_ULPI_D3>,
-						 <STM32F429_PB11_FUNC_OTG_HS_ULPI_D4>,
-						 <STM32F429_PB12_FUNC_OTG_HS_ULPI_D5>,
-						 <STM32F429_PB13_FUNC_OTG_HS_ULPI_D6>,
-						 <STM32F429_PB5_FUNC_OTG_HS_ULPI_D7>;
-					bias-disable;
-					drive-push-pull;
-					slew-rate = <2>;
-				};
-			};
-
-			ethernet_mii: mii@0 {
-				pins {
-					pinmux = <STM32F429_PG13_FUNC_ETH_MII_TXD0_ETH_RMII_TXD0>,
-						 <STM32F429_PG14_FUNC_ETH_MII_TXD1_ETH_RMII_TXD1>,
-						 <STM32F429_PC2_FUNC_ETH_MII_TXD2>,
-						 <STM32F429_PB8_FUNC_ETH_MII_TXD3>,
-						 <STM32F429_PC3_FUNC_ETH_MII_TX_CLK>,
-						 <STM32F429_PG11_FUNC_ETH_MII_TX_EN_ETH_RMII_TX_EN>,
-						 <STM32F429_PA2_FUNC_ETH_MDIO>,
-						 <STM32F429_PC1_FUNC_ETH_MDC>,
-						 <STM32F429_PA1_FUNC_ETH_MII_RX_CLK_ETH_RMII_REF_CLK>,
-						 <STM32F429_PA7_FUNC_ETH_MII_RX_DV_ETH_RMII_CRS_DV>,
-						 <STM32F429_PC4_FUNC_ETH_MII_RXD0_ETH_RMII_RXD0>,
-						 <STM32F429_PC5_FUNC_ETH_MII_RXD1_ETH_RMII_RXD1>,
-						 <STM32F429_PH6_FUNC_ETH_MII_RXD2>,
-						 <STM32F429_PH7_FUNC_ETH_MII_RXD3>;
-					slew-rate = <2>;
-				};
-			};
-
-			adc3_in8_pin: adc@200 {
-				pins {
-					pinmux = <STM32F429_PF10_FUNC_ANALOG>;
-				};
-			};
-
-			pwm1_pins: pwm@1 {
-				pins {
-					pinmux = <STM32F429_PA8_FUNC_TIM1_CH1>,
-						 <STM32F429_PB13_FUNC_TIM1_CH1N>,
-						 <STM32F429_PB12_FUNC_TIM1_BKIN>;
-				};
-			};
-
-			pwm3_pins: pwm@3 {
-				pins {
-					pinmux = <STM32F429_PB4_FUNC_TIM3_CH1>,
-						 <STM32F429_PB5_FUNC_TIM3_CH2>;
-				};
-			};
-
-			i2c1_pins: i2c1@0 {
-				pins {
-					pinmux = <STM32F429_PB9_FUNC_I2C1_SDA>,
-						 <STM32F429_PB6_FUNC_I2C1_SCL>;
-					bias-disable;
-					drive-open-drain;
-					slew-rate = <3>;
-				};
-			};
-
-			ltdc_pins: ltdc@0 {
-				pins {
-					pinmux = <STM32F429_PI12_FUNC_LCD_HSYNC>,
-						 <STM32F429_PI13_FUNC_LCD_VSYNC>,
-						 <STM32F429_PI14_FUNC_LCD_CLK>,
-						 <STM32F429_PI15_FUNC_LCD_R0>,
-						 <STM32F429_PJ0_FUNC_LCD_R1>,
-						 <STM32F429_PJ1_FUNC_LCD_R2>,
-						 <STM32F429_PJ2_FUNC_LCD_R3>,
-						 <STM32F429_PJ3_FUNC_LCD_R4>,
-						 <STM32F429_PJ4_FUNC_LCD_R5>,
-						 <STM32F429_PJ5_FUNC_LCD_R6>,
-						 <STM32F429_PJ6_FUNC_LCD_R7>,
-						 <STM32F429_PJ7_FUNC_LCD_G0>,
-						 <STM32F429_PJ8_FUNC_LCD_G1>,
-						 <STM32F429_PJ9_FUNC_LCD_G2>,
-						 <STM32F429_PJ10_FUNC_LCD_G3>,
-						 <STM32F429_PJ11_FUNC_LCD_G4>,
-						 <STM32F429_PJ12_FUNC_LCD_B0>,
-						 <STM32F429_PJ13_FUNC_LCD_B1>,
-						 <STM32F429_PJ14_FUNC_LCD_B2>,
-						 <STM32F429_PJ15_FUNC_LCD_B3>,
-						 <STM32F429_PK0_FUNC_LCD_G5>,
-						 <STM32F429_PK1_FUNC_LCD_G6>,
-						 <STM32F429_PK2_FUNC_LCD_G7>,
-						 <STM32F429_PK3_FUNC_LCD_B4>,
-						 <STM32F429_PK4_FUNC_LCD_B5>,
-						 <STM32F429_PK5_FUNC_LCD_B6>,
-						 <STM32F429_PK6_FUNC_LCD_B7>,
-						 <STM32F429_PK7_FUNC_LCD_DE>;
-					slew-rate = <2>;
-				};
-			};
-
-			dcmi_pins: dcmi@0 {
-				pins {
-					pinmux = <STM32F429_PA4_FUNC_DCMI_HSYNC>,
-						 <STM32F429_PB7_FUNC_DCMI_VSYNC>,
-						 <STM32F429_PA6_FUNC_DCMI_PIXCLK>,
-						 <STM32F429_PC6_FUNC_DCMI_D0>,
-						 <STM32F429_PC7_FUNC_DCMI_D1>,
-						 <STM32F429_PC8_FUNC_DCMI_D2>,
-						 <STM32F429_PC9_FUNC_DCMI_D3>,
-						 <STM32F429_PC11_FUNC_DCMI_D4>,
-						 <STM32F429_PD3_FUNC_DCMI_D5>,
-						 <STM32F429_PB8_FUNC_DCMI_D6>,
-						 <STM32F429_PE6_FUNC_DCMI_D7>,
-						 <STM32F429_PC10_FUNC_DCMI_D8>,
-						 <STM32F429_PC12_FUNC_DCMI_D9>,
-						 <STM32F429_PD6_FUNC_DCMI_D10>,
-						 <STM32F429_PD2_FUNC_DCMI_D11>;
-					bias-disable;
-					drive-push-pull;
-					slew-rate = <3>;
-				};
-			};
-		};
-
 		crc: crc@40023000 {
 			compatible = "st,stm32f4-crc";
 			reg = <0x40023000 0x400>;
diff --git a/arch/arm/boot/dts/stm32f469-disco.dts b/arch/arm/boot/dts/stm32f469-disco.dts
index 6ae1f03..c18acbe 100644
--- a/arch/arm/boot/dts/stm32f469-disco.dts
+++ b/arch/arm/boot/dts/stm32f469-disco.dts
@@ -47,6 +47,7 @@
 
 /dts-v1/;
 #include "stm32f429.dtsi"
+#include "stm32f469-pinctrl.dtsi"
 
 / {
 	model = "STMicroelectronics STM32F469i-DISCO board";
diff --git a/arch/arm/boot/dts/stm32f469-pinctrl.dtsi b/arch/arm/boot/dts/stm32f469-pinctrl.dtsi
new file mode 100644
index 0000000..fff54266
--- /dev/null
+++ b/arch/arm/boot/dts/stm32f469-pinctrl.dtsi
@@ -0,0 +1,96 @@
+/*
+ * Copyright 2017 - Alexandre Torgue <alexandre.torgue@st.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file 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 file 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.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     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 "stm32f4-pinctrl.dtsi"
+
+/ {
+	soc {
+		pinctrl: pin-controller {
+			compatible = "st,stm32f469-pinctrl";
+
+			gpioa: gpio@40020000 {
+				gpio-ranges = <&pinctrl 0 0 16>;
+			};
+
+			gpiob: gpio@40020400 {
+				gpio-ranges = <&pinctrl 0 16 16>;
+			};
+
+			gpioc: gpio@40020800 {
+				gpio-ranges = <&pinctrl 0 32 16>;
+			};
+
+			gpiod: gpio@40020c00 {
+				gpio-ranges = <&pinctrl 0 48 16>;
+			};
+
+			gpioe: gpio@40021000 {
+				gpio-ranges = <&pinctrl 0 64 16>;
+			};
+
+			gpiof: gpio@40021400 {
+				gpio-ranges = <&pinctrl 0 80 16>;
+			};
+
+			gpiog: gpio@40021800 {
+				gpio-ranges = <&pinctrl 0 96 16>;
+			};
+
+			gpioh: gpio@40021c00 {
+				gpio-ranges = <&pinctrl 0 112 16>;
+			};
+
+			gpioi: gpio@40022000 {
+				gpio-ranges = <&pinctrl 0 128 16>;
+			};
+
+			gpioj: gpio@40022400 {
+				gpio-ranges = <&pinctrl 0 144 6>,
+					      <&pinctrl 12 156 4>;
+			};
+
+			gpiok: gpio@40022800 {
+				gpio-ranges = <&pinctrl 3 163 5>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig
index d2d75fa..2a63fa1 100644
--- a/arch/arm/configs/gemini_defconfig
+++ b/arch/arm/configs/gemini_defconfig
@@ -32,6 +32,7 @@
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_ATA=y
+CONFIG_PATA_FTIDE010=y
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
@@ -55,8 +56,8 @@
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_GEMINI=y
 CONFIG_DMADEVICES=y
+CONFIG_AMBA_PL08X=y
 # CONFIG_DNOTIFY is not set
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 64e3a2a..d5e1370 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -471,7 +471,7 @@
 CONFIG_LCD_TOSA=m
 CONFIG_BACKLIGHT_PWM=m
 CONFIG_BACKLIGHT_TOSA=m
-CONFIG_FRAMEBUFFER_CONSOLE=m
+CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig
index 44d4fa5..070e507 100644
--- a/arch/arm/configs/viper_defconfig
+++ b/arch/arm/configs/viper_defconfig
@@ -113,7 +113,7 @@
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_BACKLIGHT_PWM=m
 # CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=m
+CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig
index 8d4c0c9..09e7050 100644
--- a/arch/arm/configs/zeus_defconfig
+++ b/arch/arm/configs/zeus_defconfig
@@ -112,7 +112,7 @@
 CONFIG_FB_PXA_PARAMETERS=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=m
+CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 1d468b5..776757d 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -139,11 +139,10 @@
 #define TIF_NEED_RESCHED	1	/* rescheduling necessary */
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_UPROBE		3	/* breakpointed or singlestepping */
-#define TIF_FSCHECK		4	/* Check FS is USER_DS on return */
-#define TIF_SYSCALL_TRACE	5	/* syscall trace active */
-#define TIF_SYSCALL_AUDIT	6	/* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT	7	/* syscall tracepoint instrumentation */
-#define TIF_SECCOMP		8	/* seccomp syscall filtering active */
+#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
 
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
@@ -154,7 +153,6 @@
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
-#define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
@@ -168,9 +166,8 @@
 /*
  * Change these and you break ASM code in entry-common.S
  */
-#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING |	\
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
-				 _TIF_FSCHECK)
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 87936dd..0bf2347 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -70,8 +70,6 @@
 {
 	current_thread_info()->addr_limit = fs;
 	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
-	/* On user-mode return, check fs is correct */
-	set_thread_flag(TIF_FSCHECK);
 }
 
 #define segment_eq(a, b)	((a) == (b))
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index ca3614d..99c9082 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -12,6 +12,7 @@
 #include <asm/unistd.h>
 #include <asm/ftrace.h>
 #include <asm/unwind.h>
+#include <asm/memory.h>
 #ifdef CONFIG_AEABI
 #include <asm/unistd-oabi.h>
 #endif
@@ -48,11 +49,13 @@
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
+	ldr	r2, [tsk, #TI_ADDR_LIMIT]
+	cmp	r2, #TASK_SIZE
+	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	bne	fast_work_pending
-	tst	r1, #_TIF_WORK_MASK
-	bne	fast_work_pending
+
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
@@ -76,16 +79,16 @@
  UNWIND(.cantunwind	)
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
 	disable_irq_notrace			@ disable interrupts
+	ldr	r2, [tsk, #TI_ADDR_LIMIT]
+	cmp	r2, #TASK_SIZE
+	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK
-	bne	fast_work_pending
-	tst	r1, #_TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	beq	no_work_pending
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
 
 	/* Slower path - fall through to work_pending */
-fast_work_pending:
 #endif
 
 	tst	r1, #_TIF_SYSCALL_WORK
@@ -111,6 +114,9 @@
 ret_slow_syscall:
 	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
+	ldr	r2, [tsk, #TI_ADDR_LIMIT]
+	cmp	r2, #TASK_SIZE
+	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
 	bne	slow_work_pending
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index e2de50b..b67ae12 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -614,10 +614,6 @@
 	 * Update the trace code with the current status.
 	 */
 	trace_hardirqs_off();
-
-	/* Check valid user FS if needed */
-	addr_limit_user_check();
-
 	do {
 		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
 			schedule();
@@ -678,3 +674,9 @@
 
 	return page;
 }
+
+/* Defer to generic check */
+asmlinkage void addr_limit_check_failed(void)
+{
+	addr_limit_user_check();
+}
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 5036f99..849014c 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -533,8 +533,8 @@
 	}
 
 	pm_bu->suspended = 0;
-	pm_bu->canary = virt_to_phys(&canary);
-	pm_bu->resume = virt_to_phys(cpu_resume);
+	pm_bu->canary = __pa_symbol(&canary);
+	pm_bu->resume = __pa_symbol(cpu_resume);
 
 	return;
 
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 5b61438..6d28aa2 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -58,10 +58,10 @@
 	struct platform_device *pdev;
 	int res;
 
-	if (omap_hsmmc_done != 1)
+	if (omap_hsmmc_done)
 		return;
 
-	omap_hsmmc_done++;
+	omap_hsmmc_done = 1;
 
 	for (; c->mmc; c++) {
 		pdev = c->pdev;
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index f040244..2f4f700 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -839,6 +839,7 @@
 	.name		= "gpio1",
 	.class		= &dra7xx_gpio_hwmod_class,
 	.clkdm_name	= "wkupaon_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.main_clk	= "wkupaon_iclk_mux",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 9b41f1e..939b310 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -50,17 +50,22 @@
 KBUILD_CFLAGS	+= $(call cc-option, -mpc-relative-literal-loads)
 KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst)
 
+KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
+KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)
+
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
 AS		+= -EB
 LD		+= -EB
+LDFLAGS		+= -maarch64linuxb
 UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__AARCH64EL__
 AS		+= -EL
 LD		+= -EL
+LDFLAGS		+= -maarch64linux
 UTS_MACHINE	:= aarch64
 endif
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index c89010e..4157987 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -168,7 +168,8 @@
 &sd_emmc_a {
 	status = "okay";
 	pinctrl-0 = <&sdio_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 	#address-cells = <1>;
 	#size-cells = <0>;
 
@@ -194,7 +195,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -212,10 +214,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
index 9697a7a..4b17a76 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
@@ -107,6 +107,9 @@
 
 		states = <3300000 0>,
 		         <1800000 1>;
+
+		regulator-settling-time-up-us = <100>;
+		regulator-settling-time-down-us = <5000>;
 	};
 
 	wifi_32k: wifi-32k {
@@ -250,7 +253,8 @@
 &sd_emmc_a {
 	status = "okay";
 	pinctrl-0 = <&sdio_pins>, <&sdio_irq_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 	#address-cells = <1>;
 	#size-cells = <0>;
 
@@ -276,11 +280,16 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
-	max-frequency = <100000000>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	max-frequency = <200000000>;
 	disable-wp;
 
 	cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>;
@@ -294,10 +303,10 @@
 &sd_emmc_c {
 	status = "disabled";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
 	disable-wp;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
index 9c59c3c..38dfdde 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
@@ -51,7 +51,7 @@
 / {
 	compatible = "nexbox,a95x", "amlogic,meson-gxbb";
 	model = "NEXBOX A95X";
-	
+
 	aliases {
 		serial0 = &uart_AO;
 	};
@@ -232,7 +232,8 @@
 &sd_emmc_a {
 	status = "okay";
 	pinctrl-0 = <&sdio_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 	#address-cells = <1>;
 	#size-cells = <0>;
 
@@ -253,7 +254,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -271,10 +273,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index d147c85..1ffa1c2 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -50,7 +50,7 @@
 / {
 	compatible = "hardkernel,odroid-c2", "amlogic,meson-gxbb";
 	model = "Hardkernel ODROID-C2";
-	
+
 	aliases {
 		serial0 = &uart_AO;
 	};
@@ -253,7 +253,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -271,10 +272,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
 	disable-wp;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
index 81ffc689..23c08c3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
@@ -194,7 +194,8 @@
 &sd_emmc_a {
 	status = "okay";
 	pinctrl-0 = <&sdio_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 	#address-cells = <1>;
 	#size-cells = <0>;
 
@@ -220,10 +221,14 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
 	max-frequency = <100000000>;
 	disable-wp;
 
@@ -238,10 +243,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
index 346753f..f2bc6de 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
@@ -155,7 +155,8 @@
 &sd_emmc_a {
 	status = "okay";
 	pinctrl-0 = <&sdio_pins &sdio_irq_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 	#address-cells = <1>;
 	#size-cells = <0>;
 
@@ -181,7 +182,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -198,10 +200,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 52f1687..af834cd 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -392,6 +392,17 @@
 			};
 		};
 
+		emmc_clk_gate_pins: emmc_clk_gate {
+			mux {
+				groups = "BOOT_8";
+				function = "gpio_periphs";
+			};
+			cfg-pull-down {
+				pins = "BOOT_8";
+				bias-pull-down;
+			};
+		};
+
 		nor_pins: nor {
 			mux {
 				groups = "nor_d",
@@ -430,6 +441,17 @@
 			};
 		};
 
+		sdcard_clk_gate_pins: sdcard_clk_gate {
+			mux {
+				groups = "CARD_2";
+				function = "gpio_periphs";
+			};
+			cfg-pull-down {
+				pins = "CARD_2";
+				bias-pull-down;
+			};
+		};
+
 		sdio_pins: sdio {
 			mux {
 				groups = "sdio_d0",
@@ -442,6 +464,17 @@
 			};
 		};
 
+		sdio_clk_gate_pins: sdio_clk_gate {
+			mux {
+				groups = "GPIOX_4";
+				function = "gpio_periphs";
+			};
+			cfg-pull-down {
+				pins = "GPIOX_4";
+				bias-pull-down;
+			};
+		};
+
 		sdio_irq_pins: sdio_irq {
 			mux {
 				groups = "sdio_irq";
@@ -661,21 +694,21 @@
 
 &sd_emmc_a {
 	clocks = <&clkc CLKID_SD_EMMC_A>,
-		 <&xtal>,
+		 <&clkc CLKID_SD_EMMC_A_CLK0>,
 		 <&clkc CLKID_FCLK_DIV2>;
 	clock-names = "core", "clkin0", "clkin1";
 };
 
 &sd_emmc_b {
 	clocks = <&clkc CLKID_SD_EMMC_B>,
-		 <&xtal>,
+		 <&clkc CLKID_SD_EMMC_B_CLK0>,
 		 <&clkc CLKID_FCLK_DIV2>;
 	clock-names = "core", "clkin0", "clkin1";
 };
 
 &sd_emmc_c {
 	clocks = <&clkc CLKID_SD_EMMC_C>,
-		 <&xtal>,
+		 <&clkc CLKID_SD_EMMC_C_CLK0>,
 		 <&clkc CLKID_FCLK_DIV2>;
 	clock-names = "core", "clkin0", "clkin1";
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
index 2a5804c..977b424 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
@@ -123,7 +123,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -141,10 +142,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <100000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index 69ca14a..64c54c9 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -91,6 +91,9 @@
 
 		states = <3300000 0>,
 			 <1800000 1>;
+
+		regulator-settling-time-up-us = <200>;
+		regulator-settling-time-down-us = <50000>;
 	};
 
 	vddio_boot: regulator-vddio_boot {
@@ -197,10 +200,14 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
 	max-frequency = <100000000>;
 	disable-wp;
 
@@ -215,10 +222,12 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
 	cap-mmc-highspeed;
+	mmc-ddr-3_3v;
 	max-frequency = <50000000>;
 	non-removable;
 	disable-wp;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
index 4c2ac76..1b8f328 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
@@ -189,7 +189,8 @@
 &sd_emmc_a {
 	status = "okay";
 	pinctrl-0 = <&sdio_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 	#address-cells = <1>;
 	#size-cells = <0>;
 
@@ -210,7 +211,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -228,10 +230,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index f3eea8e..129af90 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -95,7 +95,8 @@
 &sd_emmc_a {
 	status = "okay";
 	pinctrl-0 = <&sdio_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 	#address-cells = <1>;
 	#size-cells = <0>;
 
@@ -116,7 +117,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -134,10 +136,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index d6876e6..d8dd329 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -281,6 +281,17 @@
 			};
 		};
 
+		emmc_clk_gate_pins: emmc_clk_gate {
+			mux {
+				groups = "BOOT_8";
+				function = "gpio_periphs";
+			};
+			cfg-pull-down {
+				pins = "BOOT_8";
+				bias-pull-down;
+			};
+		};
+
 		nor_pins: nor {
 			mux {
 				groups = "nor_d",
@@ -319,6 +330,17 @@
 			};
 		};
 
+		sdcard_clk_gate_pins: sdcard_clk_gate {
+			mux {
+				groups = "CARD_2";
+				function = "gpio_periphs";
+			};
+			cfg-pull-down {
+				pins = "CARD_2";
+				bias-pull-down;
+			};
+		};
+
 		sdio_pins: sdio {
 			mux {
 				groups = "sdio_d0",
@@ -331,6 +353,17 @@
 			};
 		};
 
+		sdio_clk_gate_pins: sdio_clk_gate {
+			mux {
+				groups = "GPIOX_4";
+				function = "gpio_periphs";
+			};
+			cfg-pull-down {
+				pins = "GPIOX_4";
+				bias-pull-down;
+			};
+		};
+
 		sdio_irq_pins: sdio_irq {
 			mux {
 				groups = "sdio_irq";
@@ -603,21 +636,21 @@
 
 &sd_emmc_a {
 	clocks = <&clkc CLKID_SD_EMMC_A>,
-		 <&xtal>,
+		 <&clkc CLKID_SD_EMMC_A_CLK0>,
 		 <&clkc CLKID_FCLK_DIV2>;
 	clock-names = "core", "clkin0", "clkin1";
 };
 
 &sd_emmc_b {
 	clocks = <&clkc CLKID_SD_EMMC_B>,
-		 <&xtal>,
+		 <&clkc CLKID_SD_EMMC_B_CLK0>,
 		 <&clkc CLKID_FCLK_DIV2>;
        clock-names = "core", "clkin0", "clkin1";
 };
 
 &sd_emmc_c {
 	clocks = <&clkc CLKID_SD_EMMC_C>,
-		 <&xtal>,
+		 <&clkc CLKID_SD_EMMC_C_CLK0>,
 		 <&clkc CLKID_FCLK_DIV2>;
 	clock-names = "core", "clkin0", "clkin1";
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
index 9b10c5f..22c6977 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
@@ -175,7 +175,8 @@
 &sd_emmc_b {
 	status = "okay";
 	pinctrl-0 = <&sdcard_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&sdcard_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <4>;
 	cap-sd-highspeed;
@@ -193,10 +194,10 @@
 &sd_emmc_c {
 	status = "okay";
 	pinctrl-0 = <&emmc_pins>;
-	pinctrl-names = "default";
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
index 08f1dd6..470f72b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
@@ -220,7 +220,6 @@
 	pinctrl-names = "default";
 
 	bus-width = <8>;
-	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	max-frequency = <200000000>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index 4d36071..30d48ec 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -254,7 +254,7 @@
 
 			ap_syscon: system-controller@6f4000 {
 				compatible = "syscon", "simple-mfd";
-				reg = <0x6f4000 0x1000>;
+				reg = <0x6f4000 0x2000>;
 
 				ap_clk: clock {
 					compatible = "marvell,ap806-clock";
@@ -265,7 +265,7 @@
 					compatible = "marvell,ap806-pinctrl";
 				};
 
-				ap_gpio: gpio {
+				ap_gpio: gpio@1040 {
 					compatible = "marvell,armada-8k-gpio";
 					offset = <0x1040>;
 					ngpios = <20>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index e0518b4..19fbaa5 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -113,8 +113,7 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x0>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKL>;
-			operating-points-v2 = <&cluster0_opp>;
+
 			#cooling-cells = <2>; /* min followed by max */
 		};
 
@@ -123,8 +122,6 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x1>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKL>;
-			operating-points-v2 = <&cluster0_opp>;
 		};
 
 		cpu_l2: cpu@2 {
@@ -132,8 +129,6 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x2>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKL>;
-			operating-points-v2 = <&cluster0_opp>;
 		};
 
 		cpu_l3: cpu@3 {
@@ -141,8 +136,6 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x3>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKL>;
-			operating-points-v2 = <&cluster0_opp>;
 		};
 
 		cpu_b0: cpu@100 {
@@ -150,8 +143,7 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x100>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKB>;
-			operating-points-v2 = <&cluster1_opp>;
+
 			#cooling-cells = <2>; /* min followed by max */
 		};
 
@@ -160,8 +152,6 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x101>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKB>;
-			operating-points-v2 = <&cluster1_opp>;
 		};
 
 		cpu_b2: cpu@102 {
@@ -169,8 +159,6 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x102>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKB>;
-			operating-points-v2 = <&cluster1_opp>;
 		};
 
 		cpu_b3: cpu@103 {
@@ -178,62 +166,6 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x103>;
 			enable-method = "psci";
-			clocks = <&cru ARMCLKB>;
-			operating-points-v2 = <&cluster1_opp>;
-		};
-	};
-
-	cluster0_opp: opp-table0 {
-		compatible = "operating-points-v2";
-		opp-shared;
-
-		opp00 {
-			opp-hz = /bits/ 64 <312000000>;
-			opp-microvolt = <950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <408000000>;
-			opp-microvolt = <950000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <600000000>;
-			opp-microvolt = <950000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <816000000>;
-			opp-microvolt = <1025000>;
-		};
-		opp04 {
-			opp-hz = /bits/ 64 <1008000000>;
-			opp-microvolt = <1125000>;
-		};
-	};
-
-	cluster1_opp: opp-table1 {
-		compatible = "operating-points-v2";
-		opp-shared;
-
-		opp00 {
-			opp-hz = /bits/ 64 <312000000>;
-			opp-microvolt = <950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <408000000>;
-			opp-microvolt = <950000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <600000000>;
-			opp-microvolt = <950000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <816000000>;
-			opp-microvolt = <975000>;
-		};
-		opp04 {
-			opp-hz = /bits/ 64 <1008000000>;
-			opp-microvolt = <1050000>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index d79e9b3..ab7629c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -1629,9 +1629,9 @@
 		compatible = "rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi";
 		reg = <0x0 0xff960000 0x0 0x8000>;
 		interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH 0>;
-		clocks = <&cru SCLK_MIPIDPHY_REF>, <&cru PCLK_MIPI_DSI0>,
-			 <&cru SCLK_DPHY_TX0_CFG>;
-		clock-names = "ref", "pclk", "phy_cfg";
+		clocks = <&cru SCLK_DPHY_PLL>, <&cru PCLK_MIPI_DSI0>,
+			 <&cru SCLK_DPHY_TX0_CFG>, <&cru PCLK_VIO_GRF>;
+		clock-names = "ref", "pclk", "phy_cfg", "grf";
 		power-domains = <&power RK3399_PD_VIO>;
 		rockchip,grf = <&grf>;
 		status = "disabled";
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index 636c1bc..1b26629 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
-#define __ALIGN		.align 4
-#define __ALIGN_STR	".align 4"
+#define __ALIGN		.align 2
+#define __ALIGN_STR	".align 2"
 
 #endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 3585a5e..f7c4d21 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -95,16 +95,19 @@
 #define KERNEL_END        _end
 
 /*
- * The size of the KASAN shadow region. This should be 1/8th of the
- * size of the entire kernel virtual address space.
+ * KASAN requires 1/8th of the kernel virtual address space for the shadow
+ * region. KASAN can bloat the stack significantly, so double the (minimum)
+ * stack size when KASAN is in use.
  */
 #ifdef CONFIG_KASAN
 #define KASAN_SHADOW_SIZE	(UL(1) << (VA_BITS - 3))
+#define KASAN_THREAD_SHIFT	1
 #else
 #define KASAN_SHADOW_SIZE	(0)
+#define KASAN_THREAD_SHIFT	0
 #endif
 
-#define MIN_THREAD_SHIFT	14
+#define MIN_THREAD_SHIFT	(14 + KASAN_THREAD_SHIFT)
 
 /*
  * VMAP'd stacks are allocated at page granularity, so we must ensure that such
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index bc4e923..b46e54c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -401,7 +401,7 @@
 /* Find an entry in the third-level page table. */
 #define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
-#define pte_offset_phys(dir,addr)	(pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t))
+#define pte_offset_phys(dir,addr)	(pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t))
 #define pte_offset_kernel(dir,addr)	((pte_t *)__va(pte_offset_phys((dir), (addr))))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index f0e6d71..d06fbe4 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -649,4 +649,4 @@
 	return 0;
 }
 
-late_initcall(armv8_deprecated_init);
+core_initcall(armv8_deprecated_init);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index cd52d36..21e2c95 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1307,4 +1307,4 @@
 	return 0;
 }
 
-late_initcall(enable_mrs_emulation);
+core_initcall(enable_mrs_emulation);
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 3a68cf3..5d547de 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -321,6 +321,8 @@
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
+#ifdef CONFIG_EFI
+
 static DEFINE_PER_CPU(struct fpsimd_state, efi_fpsimd_state);
 static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
 
@@ -370,6 +372,8 @@
 		kernel_neon_end();
 }
 
+#endif /* CONFIG_EFI */
+
 #endif /* CONFIG_KERNEL_MODE_NEON */
 
 #ifdef CONFIG_CPU_PM
@@ -440,4 +444,4 @@
 
 	return 0;
 }
-late_initcall(fpsimd_init);
+core_initcall(fpsimd_init);
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 7434ec0..0b243ec 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -384,6 +384,7 @@
  * booted in EL1 or EL2 respectively.
  */
 ENTRY(el2_setup)
+	msr	SPsel, #1			// We want to use SP_EL{1,2}
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
 	b.eq	1f
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index c45214f..0bdc96c 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -751,10 +751,10 @@
 	 */
 	trace_hardirqs_off();
 
-	/* Check valid user FS if needed */
-	addr_limit_user_check();
-
 	do {
+		/* Check valid user FS if needed */
+		addr_limit_user_check();
+
 		if (thread_flags & _TIF_NEED_RESCHED) {
 			schedule();
 		} else {
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 89993c4..b64958b 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -97,7 +97,7 @@
 			 (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
 			 (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
 	} else {
-		pr_alert("  ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK);
+		pr_alert("  ISV = 0, ISS = 0x%08lx\n", esr & ESR_ELx_ISS_MASK);
 	}
 
 	pr_alert("  CM = %lu, WnR = %lu\n",
@@ -651,7 +651,7 @@
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h
index 7c87b5b..8f7cce8 100644
--- a/arch/c6x/include/asm/processor.h
+++ b/arch/c6x/include/asm/processor.h
@@ -92,9 +92,6 @@
 {
 }
 
-#define copy_segments(tsk, mm)		do { } while (0)
-#define release_segments(mm)		do { } while (0)
-
 /*
  * saved kernel SP and DP of a blocked thread.
  */
diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h
index e4d08d7..021cce7 100644
--- a/arch/frv/include/asm/processor.h
+++ b/arch/frv/include/asm/processor.h
@@ -92,10 +92,6 @@
 extern asmlinkage void save_user_regs(struct user_context *target);
 extern asmlinkage void *restore_user_regs(const struct user_context *target, ...);
 
-#define copy_segments(tsk, mm)		do { } while (0)
-#define release_segments(mm)		do { } while (0)
-#define forget_segments()		do { } while (0)
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define	KSTK_EIP(tsk)	((tsk)->thread.frame0->pc)
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 87cde1e..0777f3a 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -194,6 +194,10 @@
 	int "Timer divider (integer)"
 	default "128"
 
+config CPU_BIG_ENDIAN
+        bool "Generate big endian code"
+	default n
+
 config CPU_LITTLE_ENDIAN
         bool "Generate little endian code"
 	default n
diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h
index 657874e..c70fa9a 100644
--- a/arch/m32r/include/asm/processor.h
+++ b/arch/m32r/include/asm/processor.h
@@ -118,14 +118,6 @@
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/* Copy and release all segment info associated with a VM */
-extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
-extern void release_segments(struct mm_struct * mm);
-
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm)  do { } while (0)
-#define release_segments(mm)  do { } while (0)
-
 unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)  ((tsk)->thread.lr)
 #define KSTK_ESP(tsk)  ((tsk)->thread.sp)
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index 647dd94..72b96f2 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -114,6 +114,15 @@
 	_flush_cache_copyback_all();
 }
 
+void abort(void)
+{
+	BUG();
+
+	/* if that doesn't kill us, halt */
+	panic("Oops failed to kill thread");
+}
+EXPORT_SYMBOL(abort);
+
 void __init trap_init(void)
 {
 	set_eit_vector_entries();
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index ec6a490..8ae92d6 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -131,9 +131,6 @@
 {
 }
 
-#define copy_segments(tsk, mm)		do { } while (0)
-#define release_segments(mm)		do { } while (0)
-
 /*
  * Return saved PC of a blocked thread.
  */
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 9d26abd..4f798aa 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -39,7 +39,7 @@
 # Endianness selection
 choice
 	prompt "Endianness selection"
-	default CPU_BIG_ENDIAN
+	default CPU_LITTLE_ENDIAN
 	help
 	  microblaze architectures can be configured for either little or
 	  big endian formats. Be sure to select the appropriate mode.
diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild
index e77a596..06609ca 100644
--- a/arch/microblaze/include/uapi/asm/Kbuild
+++ b/arch/microblaze/include/uapi/asm/Kbuild
@@ -7,6 +7,7 @@
 generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
+generic-y += kvm_para.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index e45ada8..94700c5 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -165,7 +165,7 @@
 			     unsigned long attrs)
 {
 #ifdef CONFIG_MMU
-	unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 	unsigned long pfn;
diff --git a/arch/mips/ath79/pci.c b/arch/mips/ath79/pci.c
index 730c0b0..b816cb4 100644
--- a/arch/mips/ath79/pci.c
+++ b/arch/mips/ath79/pci.c
@@ -22,10 +22,10 @@
 #include "pci.h"
 
 static int (*ath79_pci_plat_dev_init)(struct pci_dev *dev);
-static const struct ath79_pci_irq *ath79_pci_irq_map __initdata;
-static unsigned ath79_pci_nr_irqs __initdata;
+static const struct ath79_pci_irq *ath79_pci_irq_map;
+static unsigned ath79_pci_nr_irqs;
 
-static const struct ath79_pci_irq ar71xx_pci_irq_map[] __initconst = {
+static const struct ath79_pci_irq ar71xx_pci_irq_map[] = {
 	{
 		.slot	= 17,
 		.pin	= 1,
@@ -41,7 +41,7 @@
 	}
 };
 
-static const struct ath79_pci_irq ar724x_pci_irq_map[] __initconst = {
+static const struct ath79_pci_irq ar724x_pci_irq_map[] = {
 	{
 		.slot	= 0,
 		.pin	= 1,
@@ -49,7 +49,7 @@
 	}
 };
 
-static const struct ath79_pci_irq qca955x_pci_irq_map[] __initconst = {
+static const struct ath79_pci_irq qca955x_pci_irq_map[] = {
 	{
 		.bus	= 0,
 		.slot	= 0,
@@ -64,7 +64,7 @@
 	},
 };
 
-int __init pcibios_map_irq(const struct pci_dev *dev, uint8_t slot, uint8_t pin)
+int pcibios_map_irq(const struct pci_dev *dev, uint8_t slot, uint8_t pin)
 {
 	int irq = -1;
 	int i;
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index e4ed1bc..a681092 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1377,29 +1377,32 @@
 
 #define __write_64bit_c0_split(source, sel, val)			\
 do {									\
+	unsigned long long __tmp;					\
 	unsigned long __flags;						\
 									\
 	local_irq_save(__flags);					\
 	if (sel == 0)							\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L0, 32\n\t"			\
+			"dsll\t%L0, %L1, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M0, 32\n\t"			\
+			"dsll\t%M0, %M1, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source "\n\t"			\
 			".set\tmips0"					\
-			: : "r" (val));					\
+			: "=&r,r" (__tmp)				\
+			: "r,0" (val));					\
 	else								\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L0, 32\n\t"			\
+			"dsll\t%L0, %L1, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M0, 32\n\t"			\
+			"dsll\t%M0, %M1, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
 			".set\tmips0"					\
-			: : "r" (val));					\
+			: "=&r,r" (__tmp)				\
+			: "r,0" (val));					\
 	local_irq_restore(__flags);					\
 } while (0)
 
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 9e6c74b..6668f67 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -618,8 +618,7 @@
 		return -ENOENT;
 	}
 
-	if ((unsigned int)event->cpu >= nr_cpumask_bits ||
-	    (event->cpu >= 0 && !cpu_online(event->cpu)))
+	if (event->cpu >= 0 && !cpu_online(event->cpu))
 		return -ENODEV;
 
 	if (!atomic_inc_not_zero(&active_events)) {
diff --git a/arch/mips/pci/fixup-capcella.c b/arch/mips/pci/fixup-capcella.c
index 1c02f57..b4c263f 100644
--- a/arch/mips/pci/fixup-capcella.c
+++ b/arch/mips/pci/fixup-capcella.c
@@ -32,13 +32,13 @@
 #define INTC	PC104PLUS_INTC_IRQ
 #define INTD	PC104PLUS_INTD_IRQ
 
-static char irq_tab_capcella[][5] __initdata = {
+static char irq_tab_capcella[][5] = {
  [11] = { -1, INT1, INT1, INT1, INT1 },
  [12] = { -1, INT2, INT2, INT2, INT2 },
  [14] = { -1, INTA, INTB, INTC, INTD }
 };
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	return irq_tab_capcella[slot][pin];
 }
diff --git a/arch/mips/pci/fixup-cobalt.c b/arch/mips/pci/fixup-cobalt.c
index b3ab593..44be65c 100644
--- a/arch/mips/pci/fixup-cobalt.c
+++ b/arch/mips/pci/fixup-cobalt.c
@@ -147,7 +147,7 @@
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C586_0,
 	 qube_raq_via_board_id_fixup);
 
-static char irq_tab_qube1[] __initdata = {
+static char irq_tab_qube1[] = {
   [COBALT_PCICONF_CPU]	   = 0,
   [COBALT_PCICONF_ETH0]	   = QUBE1_ETH0_IRQ,
   [COBALT_PCICONF_RAQSCSI] = SCSI_IRQ,
@@ -156,7 +156,7 @@
   [COBALT_PCICONF_ETH1]	   = 0
 };
 
-static char irq_tab_cobalt[] __initdata = {
+static char irq_tab_cobalt[] = {
   [COBALT_PCICONF_CPU]	   = 0,
   [COBALT_PCICONF_ETH0]	   = ETH0_IRQ,
   [COBALT_PCICONF_RAQSCSI] = SCSI_IRQ,
@@ -165,7 +165,7 @@
   [COBALT_PCICONF_ETH1]	   = ETH1_IRQ
 };
 
-static char irq_tab_raq2[] __initdata = {
+static char irq_tab_raq2[] = {
   [COBALT_PCICONF_CPU]	   = 0,
   [COBALT_PCICONF_ETH0]	   = ETH0_IRQ,
   [COBALT_PCICONF_RAQSCSI] = RAQ2_SCSI_IRQ,
@@ -174,7 +174,7 @@
   [COBALT_PCICONF_ETH1]	   = ETH1_IRQ
 };
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	if (cobalt_board_id <= COBALT_BRD_ID_QUBE1)
 		return irq_tab_qube1[slot];
diff --git a/arch/mips/pci/fixup-emma2rh.c b/arch/mips/pci/fixup-emma2rh.c
index 19caf77..c31cb6a 100644
--- a/arch/mips/pci/fixup-emma2rh.c
+++ b/arch/mips/pci/fixup-emma2rh.c
@@ -43,7 +43,7 @@
  */
 
 #define MAX_SLOT_NUM 10
-static unsigned char irq_map[][5] __initdata = {
+static unsigned char irq_map[][5] = {
 	[3] = {0, MARKEINS_PCI_IRQ_INTB, MARKEINS_PCI_IRQ_INTC,
 	       MARKEINS_PCI_IRQ_INTD, 0,},
 	[4] = {0, MARKEINS_PCI_IRQ_INTA, 0, 0, 0,},
@@ -85,7 +85,7 @@
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_EMMA2RH,
 			 emma2rh_pci_host_fixup);
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	return irq_map[slot][pin];
 }
diff --git a/arch/mips/pci/fixup-fuloong2e.c b/arch/mips/pci/fixup-fuloong2e.c
index 50da773..b47c277 100644
--- a/arch/mips/pci/fixup-fuloong2e.c
+++ b/arch/mips/pci/fixup-fuloong2e.c
@@ -19,7 +19,7 @@
 /* South bridge slot number is set by the pci probe process */
 static u8 sb_slot = 5;
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq = 0;
 
diff --git a/arch/mips/pci/fixup-ip32.c b/arch/mips/pci/fixup-ip32.c
index 133685e..c6ec18a 100644
--- a/arch/mips/pci/fixup-ip32.c
+++ b/arch/mips/pci/fixup-ip32.c
@@ -21,7 +21,7 @@
 #define INTB   MACEPCI_SHARED0_IRQ
 #define INTC   MACEPCI_SHARED1_IRQ
 #define INTD   MACEPCI_SHARED2_IRQ
-static char irq_tab_mace[][5] __initdata = {
+static char irq_tab_mace[][5] = {
       /* Dummy	INT#A  INT#B  INT#C  INT#D */
 	{0,	    0,	   0,	  0,	 0}, /* This is placeholder row - never used */
 	{0,	SCSI0, SCSI0, SCSI0, SCSI0},
@@ -39,7 +39,7 @@
  * irqs.  I suppose a device without a pin A will thank us for doing it
  * right if there exists such a broken piece of crap.
  */
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	return irq_tab_mace[slot][pin];
 }
diff --git a/arch/mips/pci/fixup-jmr3927.c b/arch/mips/pci/fixup-jmr3927.c
index 0f10695..d3102ee 100644
--- a/arch/mips/pci/fixup-jmr3927.c
+++ b/arch/mips/pci/fixup-jmr3927.c
@@ -31,7 +31,7 @@
 #include <asm/txx9/pci.h>
 #include <asm/txx9/jmr3927.h>
 
-int __init jmr3927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int jmr3927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	unsigned char irq = pin;
 
diff --git a/arch/mips/pci/fixup-lantiq.c b/arch/mips/pci/fixup-lantiq.c
index 2b5427d..81530a1 100644
--- a/arch/mips/pci/fixup-lantiq.c
+++ b/arch/mips/pci/fixup-lantiq.c
@@ -23,7 +23,7 @@
 	return 0;
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	return of_irq_parse_and_map_pci(dev, slot, pin);
 }
diff --git a/arch/mips/pci/fixup-lemote2f.c b/arch/mips/pci/fixup-lemote2f.c
index 95ab9a1..20cdfdc 100644
--- a/arch/mips/pci/fixup-lemote2f.c
+++ b/arch/mips/pci/fixup-lemote2f.c
@@ -30,7 +30,7 @@
 #define PCID		7
 
 /* all the pci device has the PCIA pin, check the datasheet. */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
 	/*	INTA	INTB	INTC	INTD */
 	{0, 0, 0, 0, 0},	/*  11: Unused */
 	{0, 0, 0, 0, 0},	/*  12: Unused */
@@ -51,7 +51,7 @@
 	{0, 0, 0, 0, 0},	/*  27: Unused */
 };
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int virq;
 
diff --git a/arch/mips/pci/fixup-loongson3.c b/arch/mips/pci/fixup-loongson3.c
index 2b6d5e1..8a741c2 100644
--- a/arch/mips/pci/fixup-loongson3.c
+++ b/arch/mips/pci/fixup-loongson3.c
@@ -32,7 +32,7 @@
 			pdev->vendor, pdev->device, pdev->irq);
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	print_fixup_info(dev);
 	return dev->irq;
diff --git a/arch/mips/pci/fixup-malta.c b/arch/mips/pci/fixup-malta.c
index 40e920c..3ec8533 100644
--- a/arch/mips/pci/fixup-malta.c
+++ b/arch/mips/pci/fixup-malta.c
@@ -12,7 +12,7 @@
 static char pci_irq[5] = {
 };
 
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
 	/*	INTA	INTB	INTC	INTD */
 	{0,	0,	0,	0,	0 },	/*  0: GT64120 PCI bridge */
 	{0,	0,	0,	0,	0 },	/*  1: Unused */
@@ -38,7 +38,7 @@
 	{0,	PCID,	PCIA,	PCIB,	PCIC }	/* 21: PCI Slot 4 */
 };
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int virq;
 	virq = irq_tab[slot][pin];
diff --git a/arch/mips/pci/fixup-mpc30x.c b/arch/mips/pci/fixup-mpc30x.c
index 8e4f828..66eaf45 100644
--- a/arch/mips/pci/fixup-mpc30x.c
+++ b/arch/mips/pci/fixup-mpc30x.c
@@ -22,19 +22,19 @@
 
 #include <asm/vr41xx/mpc30x.h>
 
-static const int internal_func_irqs[] __initconst = {
+static const int internal_func_irqs[] = {
 	VRC4173_CASCADE_IRQ,
 	VRC4173_AC97_IRQ,
 	VRC4173_USB_IRQ,
 };
 
-static const int irq_tab_mpc30x[] __initconst = {
+static const int irq_tab_mpc30x[] = {
  [12] = VRC4173_PCMCIA1_IRQ,
  [13] = VRC4173_PCMCIA2_IRQ,
  [29] = MQ200_IRQ,
 };
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	if (slot == 30)
 		return internal_func_irqs[PCI_FUNC(dev->devfn)];
diff --git a/arch/mips/pci/fixup-pmcmsp.c b/arch/mips/pci/fixup-pmcmsp.c
index fab405c..4ad2ef0 100644
--- a/arch/mips/pci/fixup-pmcmsp.c
+++ b/arch/mips/pci/fixup-pmcmsp.c
@@ -47,7 +47,7 @@
 
 #if defined(CONFIG_PMC_MSP7120_GW)
 /* Garibaldi Board IRQ wiring to PCI slots */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
 	/* INTA	   INTB	   INTC	   INTD */
 	{0,	0,	0,	0,	0 },	/*    (AD[0]): Unused */
 	{0,	0,	0,	0,	0 },	/*    (AD[1]): Unused */
@@ -86,7 +86,7 @@
 #elif defined(CONFIG_PMC_MSP7120_EVAL)
 
 /* MSP7120 Eval Board IRQ wiring to PCI slots */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
 	/* INTA	   INTB	   INTC	   INTD */
 	{0,	0,	0,	0,	0 },	/*    (AD[0]): Unused */
 	{0,	0,	0,	0,	0 },	/*    (AD[1]): Unused */
@@ -125,7 +125,7 @@
 #else
 
 /* Unknown board -- don't assign any IRQs */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
 	/* INTA	   INTB	   INTC	   INTD */
 	{0,	0,	0,	0,	0 },	/*    (AD[0]): Unused */
 	{0,	0,	0,	0,	0 },	/*    (AD[1]): Unused */
@@ -202,7 +202,7 @@
  *  RETURNS:	 IRQ number
  *
  ****************************************************************************/
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 #if !defined(CONFIG_PMC_MSP7120_GW) && !defined(CONFIG_PMC_MSP7120_EVAL)
 	printk(KERN_WARNING "PCI: unknown board, no PCI IRQs assigned.\n");
diff --git a/arch/mips/pci/fixup-rbtx4927.c b/arch/mips/pci/fixup-rbtx4927.c
index 321db26..d6aaed1 100644
--- a/arch/mips/pci/fixup-rbtx4927.c
+++ b/arch/mips/pci/fixup-rbtx4927.c
@@ -36,7 +36,7 @@
 #include <asm/txx9/pci.h>
 #include <asm/txx9/rbtx4927.h>
 
-int __init rbtx4927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int rbtx4927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	unsigned char irq = pin;
 
diff --git a/arch/mips/pci/fixup-rbtx4938.c b/arch/mips/pci/fixup-rbtx4938.c
index a80579a..ff22a22 100644
--- a/arch/mips/pci/fixup-rbtx4938.c
+++ b/arch/mips/pci/fixup-rbtx4938.c
@@ -13,7 +13,7 @@
 #include <asm/txx9/pci.h>
 #include <asm/txx9/rbtx4938.h>
 
-int __init rbtx4938_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int rbtx4938_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq = tx4938_pcic1_map_irq(dev, slot);
 
diff --git a/arch/mips/pci/fixup-sni.c b/arch/mips/pci/fixup-sni.c
index f67ebee..adb9a58 100644
--- a/arch/mips/pci/fixup-sni.c
+++ b/arch/mips/pci/fixup-sni.c
@@ -40,7 +40,7 @@
  * seem to be a documentation error.  At least on my RM200C the Cirrus
  * Logic CL-GD5434 VGA is device 3.
  */
-static char irq_tab_rm200[8][5] __initdata = {
+static char irq_tab_rm200[8][5] = {
 	/*	 INTA  INTB  INTC  INTD */
 	{     0,    0,	  0,	0,    0 },	/* EISA bridge */
 	{  SCSI, SCSI, SCSI, SCSI, SCSI },	/* SCSI */
@@ -57,7 +57,7 @@
  *
  * The VGA card is optional for RM300 systems.
  */
-static char irq_tab_rm300d[8][5] __initdata = {
+static char irq_tab_rm300d[8][5] = {
 	/*	 INTA  INTB  INTC  INTD */
 	{     0,    0,	  0,	0,    0 },	/* EISA bridge */
 	{  SCSI, SCSI, SCSI, SCSI, SCSI },	/* SCSI */
@@ -69,7 +69,7 @@
 	{     0, INTD, INTA, INTB, INTC },	/* Slot 4 */
 };
 
-static char irq_tab_rm300e[5][5] __initdata = {
+static char irq_tab_rm300e[5][5] = {
 	/*	 INTA  INTB  INTC  INTD */
 	{     0,    0,	  0,	0,    0 },	/* HOST bridge */
 	{  SCSI, SCSI, SCSI, SCSI, SCSI },	/* SCSI */
@@ -96,7 +96,7 @@
 #define INTC	PCIT_IRQ_INTC
 #define INTD	PCIT_IRQ_INTD
 
-static char irq_tab_pcit[13][5] __initdata = {
+static char irq_tab_pcit[13][5] = {
 	/*	 INTA  INTB  INTC  INTD */
 	{     0,     0,	    0,	   0,	  0 },	/* HOST bridge */
 	{ SCSI0, SCSI0, SCSI0, SCSI0, SCSI0 },	/* SCSI */
@@ -113,7 +113,7 @@
 	{     0,  INTA,	 INTB,	INTC,  INTD },	/* Slot 5 */
 };
 
-static char irq_tab_pcit_cplus[13][5] __initdata = {
+static char irq_tab_pcit_cplus[13][5] = {
 	/*	 INTA  INTB  INTC  INTD */
 	{     0,     0,	    0,	   0,	  0 },	/* HOST bridge */
 	{     0,  INTB,	 INTC,	INTD,  INTA },	/* PCI Slot 9 */
@@ -130,7 +130,7 @@
 	return (csmsr & 0xa0) == 0x20;
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	switch (sni_brd_type) {
 	case SNI_BRD_PCI_TOWER_CPLUS:
diff --git a/arch/mips/pci/fixup-tb0219.c b/arch/mips/pci/fixup-tb0219.c
index d0b0083..cc58153 100644
--- a/arch/mips/pci/fixup-tb0219.c
+++ b/arch/mips/pci/fixup-tb0219.c
@@ -23,7 +23,7 @@
 
 #include <asm/vr41xx/tb0219.h>
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq = -1;
 
diff --git a/arch/mips/pci/fixup-tb0226.c b/arch/mips/pci/fixup-tb0226.c
index 4196ccf..b827b5c 100644
--- a/arch/mips/pci/fixup-tb0226.c
+++ b/arch/mips/pci/fixup-tb0226.c
@@ -23,7 +23,7 @@
 #include <asm/vr41xx/giu.h>
 #include <asm/vr41xx/tb0226.h>
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq = -1;
 
diff --git a/arch/mips/pci/fixup-tb0287.c b/arch/mips/pci/fixup-tb0287.c
index 8c5039e..98f2628 100644
--- a/arch/mips/pci/fixup-tb0287.c
+++ b/arch/mips/pci/fixup-tb0287.c
@@ -22,7 +22,7 @@
 
 #include <asm/vr41xx/tb0287.h>
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	unsigned char bus;
 	int irq = -1;
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
index e99ca77..f15ec98 100644
--- a/arch/mips/pci/pci-alchemy.c
+++ b/arch/mips/pci/pci-alchemy.c
@@ -522,7 +522,7 @@
 arch_initcall(alchemy_pci_init);
 
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	struct alchemy_pci_context *ctx = dev->sysdata;
 	if (ctx && ctx->board_map_irq)
diff --git a/arch/mips/pci/pci-bcm47xx.c b/arch/mips/pci/pci-bcm47xx.c
index 76f16ea..230d7dd 100644
--- a/arch/mips/pci/pci-bcm47xx.c
+++ b/arch/mips/pci/pci-bcm47xx.c
@@ -28,7 +28,7 @@
 #include <linux/bcma/bcma.h>
 #include <bcm47xx.h>
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	return 0;
 }
diff --git a/arch/mips/pci/pci-lasat.c b/arch/mips/pci/pci-lasat.c
index 40d2797..47f4ee6 100644
--- a/arch/mips/pci/pci-lasat.c
+++ b/arch/mips/pci/pci-lasat.c
@@ -61,7 +61,7 @@
 #define LASAT_IRQ_PCIC	 (LASAT_IRQ_BASE + 7)
 #define LASAT_IRQ_PCID	 (LASAT_IRQ_BASE + 8)
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	switch (slot) {
 	case 1:
diff --git a/arch/mips/pci/pci-mt7620.c b/arch/mips/pci/pci-mt7620.c
index 4e633c1..90fba9b 100644
--- a/arch/mips/pci/pci-mt7620.c
+++ b/arch/mips/pci/pci-mt7620.c
@@ -361,7 +361,7 @@
 	return 0;
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	u16 cmd;
 	u32 val;
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 9ee0193..3e92a06 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -59,8 +59,7 @@
 	} s;
 };
 
-int __initconst (*octeon_pcibios_map_irq)(const struct pci_dev *dev,
-					 u8 slot, u8 pin);
+int (*octeon_pcibios_map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
 enum octeon_dma_bar_type octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_INVALID;
 
 /**
@@ -74,7 +73,7 @@
  *		 as it goes through each bridge.
  * Returns Interrupt number for the device
  */
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	if (octeon_pcibios_map_irq)
 		return octeon_pcibios_map_irq(dev, slot, pin);
diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c
index d6360fe..711cdcc 100644
--- a/arch/mips/pci/pci-rt2880.c
+++ b/arch/mips/pci/pci-rt2880.c
@@ -181,7 +181,7 @@
 	spin_unlock_irqrestore(&rt2880_pci_lock, flags);
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	u16 cmd;
 	int irq = -1;
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index 04f8ea9..958899f 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -564,7 +564,7 @@
 	return err;
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	return of_irq_parse_and_map_pci(dev, slot, pin);
 }
diff --git a/arch/mips/pci/pci-tx4938.c b/arch/mips/pci/pci-tx4938.c
index 000c0e1..a641846 100644
--- a/arch/mips/pci/pci-tx4938.c
+++ b/arch/mips/pci/pci-tx4938.c
@@ -112,7 +112,7 @@
 	return pciclk;
 }
 
-int __init tx4938_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
+int tx4938_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
 {
 	if (get_tx4927_pcicptr(dev->bus->sysdata) == tx4938_pcic1ptr) {
 		switch (slot) {
diff --git a/arch/mips/pci/pci-tx4939.c b/arch/mips/pci/pci-tx4939.c
index 9d6acc0..09a65f7 100644
--- a/arch/mips/pci/pci-tx4939.c
+++ b/arch/mips/pci/pci-tx4939.c
@@ -48,7 +48,7 @@
 		((pciclk + 50000) / 100000) % 10);
 }
 
-int __init tx4939_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
+int tx4939_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
 {
 	if (get_tx4927_pcicptr(dev->bus->sysdata) == tx4939_pcic1ptr) {
 		switch (slot) {
@@ -68,7 +68,7 @@
 	return -1;
 }
 
-int __init tx4939_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int tx4939_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq = tx4939_pcic1_map_irq(dev, slot);
 
diff --git a/arch/mips/pci/pci-xlp.c b/arch/mips/pci/pci-xlp.c
index 7babf01..9eff913 100644
--- a/arch/mips/pci/pci-xlp.c
+++ b/arch/mips/pci/pci-xlp.c
@@ -205,7 +205,7 @@
 		return PCI_SLOT(lnkdev->devfn) / 8;
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	struct pci_dev *lnkdev;
 	int lnkfunc, node;
diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c
index 26d2dab..2a1c81a 100644
--- a/arch/mips/pci/pci-xlr.c
+++ b/arch/mips/pci/pci-xlr.c
@@ -315,7 +315,7 @@
 	}
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	return get_irq_vector(dev);
 }
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index ad3584d..fd28874 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -1464,8 +1464,7 @@
  *		 as it goes through each bridge.
  * Returns Interrupt number for the device
  */
-int __init octeon_pcie_pcibios_map_irq(const struct pci_dev *dev,
-				       u8 slot, u8 pin)
+int octeon_pcie_pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	/*
 	 * The EBH5600 board with the PCI to PCIe bridge mistakenly
diff --git a/arch/mips/pmcs-msp71xx/msp_smp.c b/arch/mips/pmcs-msp71xx/msp_smp.c
index ffa0f71..2b08242 100644
--- a/arch/mips/pmcs-msp71xx/msp_smp.c
+++ b/arch/mips/pmcs-msp71xx/msp_smp.c
@@ -22,6 +22,8 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 
+#include <asm/setup.h>
+
 #ifdef CONFIG_MIPS_MT_SMP
 #define MIPS_CPU_IPI_RESCHED_IRQ 0	/* SW int 0 for resched */
 #define MIPS_CPU_IPI_CALL_IRQ 1		/* SW int 1 for call */
diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index 0bd2a1e..fb99872 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -386,9 +386,10 @@
 	return 0;
 }
 
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int (*txx9_pci_map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	return txx9_board_vec->pci_map_irq(dev, slot, pin);
+	return txx9_pci_map_irq(dev, slot, pin);
 }
 
 char * (*txx9_board_pcibios_setup)(char *str) __initdata;
@@ -424,5 +425,8 @@
 			txx9_pci_err_action = TXX9_PCI_ERR_IGNORE;
 		return NULL;
 	}
+
+	txx9_pci_map_irq = txx9_board_vec->pci_map_irq;
+
 	return str;
 }
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 89e8027..7c475fd 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -59,10 +59,6 @@
 }
 #endif
 
-void release_segments(struct mm_struct *mm)
-{
-}
-
 void machine_restart(char *cmd)
 {
 #ifdef CONFIG_KERNEL_DEBUGGER
@@ -113,14 +109,6 @@
 }
 
 /*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
- */
-void copy_segments(struct task_struct *p, struct mm_struct *new_mm)
-{
-}
-
-/*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
  */
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index ba7b7dd..a57dedb 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -257,6 +257,18 @@
 
 endchoice
 
+config PARISC_SELF_EXTRACT
+	bool "Build kernel as self-extracting executable"
+	default y
+	help
+	  Say Y if you want to build the parisc kernel as a kind of
+	  self-extracting executable.
+
+	  If you say N here, the kernel will be compressed with gzip
+	  which can be loaded by the palo bootloader directly too.
+
+	  If you don't know what to do here, say Y.
+
 config SMP
 	bool "Symmetric multi-processing support"
 	---help---
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 58fae5d..01946eb 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -129,8 +129,13 @@
 bzImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
+ifdef CONFIG_PARISC_SELF_EXTRACT
 vmlinuz: bzImage
 	$(OBJCOPY) $(boot)/bzImage $@
+else
+vmlinuz: vmlinux
+	@gzip -cf -9 $< > $@
+endif
 
 install:
 	$(CONFIG_SHELL) $(src)/arch/parisc/install.sh \
diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile
index 5450a11..7d7e594 100644
--- a/arch/parisc/boot/compressed/Makefile
+++ b/arch/parisc/boot/compressed/Makefile
@@ -15,7 +15,7 @@
 KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks
-KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs
+KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs -Os
 ifndef CONFIG_64BIT
 KBUILD_CFLAGS += -mfast-indirect-calls
 endif
diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c
index 13a4bf9..9345b44 100644
--- a/arch/parisc/boot/compressed/misc.c
+++ b/arch/parisc/boot/compressed/misc.c
@@ -24,7 +24,8 @@
 /* Symbols defined by linker scripts */
 extern char input_data[];
 extern int input_len;
-extern __le32 output_len;	/* at unaligned address, little-endian */
+/* output_len is inserted by the linker possibly at an unaligned address */
+extern __le32 output_len __aligned(1);
 extern char _text, _end;
 extern char _bss, _ebss;
 extern char _startcode_end;
diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h
index 26b4455..510341f 100644
--- a/arch/parisc/include/asm/pdc.h
+++ b/arch/parisc/include/asm/pdc.h
@@ -280,6 +280,7 @@
 /* wrapper-functions from pdc.c */
 
 int pdc_add_valid(unsigned long address);
+int pdc_instr(unsigned int *instr);
 int pdc_chassis_info(struct pdc_chassis_info *chassis_info, void *led_info, unsigned long len);
 int pdc_chassis_disp(unsigned long disp);
 int pdc_chassis_warn(unsigned long *warn);
diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h
index a5dc906..ad9c9c3 100644
--- a/arch/parisc/include/asm/smp.h
+++ b/arch/parisc/include/asm/smp.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_SMP_H
 #define __ASM_SMP_H
 
+extern int init_per_cpu(int cpuid);
 
 #if defined(CONFIG_SMP)
 
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index ab80e5c..6d471c0 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -233,6 +233,26 @@
 EXPORT_SYMBOL(pdc_add_valid);
 
 /**
+ * pdc_instr - Get instruction that invokes PDCE_CHECK in HPMC handler.
+ * @instr: Pointer to variable which will get instruction opcode.
+ *
+ * The return value is PDC_OK (0) in case call succeeded.
+ */
+int __init pdc_instr(unsigned int *instr)
+{
+	int retval;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdc_lock, flags);
+	retval = mem_pdc_call(PDC_INSTR, 0UL, __pa(pdc_result));
+	convert_to_wide(pdc_result);
+	*instr = pdc_result[0];
+	spin_unlock_irqrestore(&pdc_lock, flags);
+
+	return retval;
+}
+
+/**
  * pdc_chassis_info - Return chassis information.
  * @result: The return buffer.
  * @chassis_info: The memory buffer address.
diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
index 05730a8..00aed08 100644
--- a/arch/parisc/kernel/pdt.c
+++ b/arch/parisc/kernel/pdt.c
@@ -15,6 +15,7 @@
 #include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/kthread.h>
+#include <linux/initrd.h>
 
 #include <asm/pdc.h>
 #include <asm/pdcpat.h>
@@ -216,8 +217,16 @@
 	}
 
 	for (i = 0; i < pdt_status.pdt_entries; i++) {
+		unsigned long addr;
+
 		report_mem_err(pdt_entry[i]);
 
+		addr = pdt_entry[i] & PDT_ADDR_PHYS_MASK;
+		if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) &&
+			addr >= initrd_start && addr < initrd_end)
+			pr_crit("CRITICAL: initrd possibly broken "
+				"due to bad memory!\n");
+
 		/* mark memory page bad */
 		memblock_reserve(pdt_entry[i] & PAGE_MASK, PAGE_SIZE);
 	}
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index a45a67d..30f9239 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -146,7 +146,7 @@
 
 	/* prevent soft lockup/stalled CPU messages for endless loop. */
 	rcu_sysrq_start();
-	lockup_detector_suspend();
+	lockup_detector_soft_poweroff();
 	for (;;);
 }
 
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index a778bd3..e120d63 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -317,7 +317,7 @@
  *
  * o Enable CPU profiling hooks.
  */
-int init_per_cpu(int cpunum)
+int __init init_per_cpu(int cpunum)
 {
 	int ret;
 	struct pdc_coproc_cfg coproc_cfg;
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index dee6f9d..f7d0c3b3 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -38,6 +38,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/start_kernel.h>
 
 #include <asm/processor.h>
 #include <asm/sections.h>
@@ -48,6 +49,7 @@
 #include <asm/io.h>
 #include <asm/setup.h>
 #include <asm/unwind.h>
+#include <asm/smp.h>
 
 static char __initdata command_line[COMMAND_LINE_SIZE];
 
@@ -115,7 +117,6 @@
 }
 #endif
 
-extern int init_per_cpu(int cpuid);
 extern void collect_boot_cpu_data(void);
 
 void __init setup_arch(char **cmdline_p)
@@ -398,9 +399,8 @@
 }
 arch_initcall(parisc_init);
 
-void start_parisc(void)
+void __init start_parisc(void)
 {
-	extern void start_kernel(void);
 	extern void early_trap_init(void);
 
 	int ret, cpunum;
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 6336510..30c28ab 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -255,12 +255,11 @@
 static void __init
 smp_cpu_init(int cpunum)
 {
-	extern int init_per_cpu(int);  /* arch/parisc/kernel/processor.c */
 	extern void init_IRQ(void);    /* arch/parisc/kernel/irq.c */
 	extern void start_cpu_itimer(void); /* arch/parisc/kernel/time.c */
 
 	/* Set modes and Enable floating point coprocessor */
-	(void) init_per_cpu(cpunum);
+	init_per_cpu(cpunum);
 
 	disable_sr_hashing();
 
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 991654c..23033315 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -817,7 +817,7 @@
 	u32 check = 0;
 	u32 *ivap;
 	u32 *hpmcp;
-	u32 length;
+	u32 length, instr;
 
 	if (strcmp((const char *)iva, "cows can fly"))
 		panic("IVT invalid");
@@ -827,6 +827,14 @@
 	for (i = 0; i < 8; i++)
 	    *ivap++ = 0;
 
+	/*
+	 * Use PDC_INSTR firmware function to get instruction that invokes
+	 * PDCE_CHECK in HPMC handler.  See programming note at page 1-31 of
+	 * the PA 1.1 Firmware Architecture document.
+	 */
+	if (pdc_instr(&instr) == PDC_OK)
+		ivap[0] = instr;
+
 	/* Compute Checksum for HPMC handler */
 	length = os_hpmc_size;
 	ivap[7] = length;
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 48dc7d4..caab39d 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/kallsyms.h>
 #include <linux/sort.h>
+#include <linux/sched.h>
 
 #include <linux/uaccess.h>
 #include <asm/assembly.h>
@@ -279,6 +280,17 @@
 
 			info->prev_sp = sp - 64;
 			info->prev_ip = 0;
+
+			/* The stack is at the end inside the thread_union
+			 * struct. If we reach data, we have reached the
+			 * beginning of the stack and should stop unwinding. */
+			if (info->prev_sp >= (unsigned long) task_thread_info(info->t) &&
+			    info->prev_sp < ((unsigned long) task_thread_info(info->t)
+						+ THREAD_SZ_ALGN)) {
+				info->prev_sp = 0;
+				break;
+			}
+
 			if (get_user(tmp, (unsigned long *)(info->prev_sp - RP_OFFSET))) 
 				break;
 			info->prev_ip = tmp;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 5b101f6..e247edb 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
+#include <linux/hugetlb.h>
 
 #include <asm/traps.h>
 
@@ -261,7 +262,7 @@
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	unsigned long acc_type;
-	int fault;
+	int fault = 0;
 	unsigned int flags;
 
 	if (faulthandler_disabled())
@@ -315,7 +316,8 @@
 			goto out_of_memory;
 		else if (fault & VM_FAULT_SIGSEGV)
 			goto bad_area;
-		else if (fault & VM_FAULT_SIGBUS)
+		else if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
+				  VM_FAULT_HWPOISON_LARGE))
 			goto bad_area;
 		BUG();
 	}
@@ -352,8 +354,7 @@
 
 	if (user_mode(regs)) {
 		struct siginfo si;
-
-		show_signal_msg(regs, code, address, tsk, vma);
+		unsigned int lsb = 0;
 
 		switch (code) {
 		case 15:	/* Data TLB miss fault/Data page fault */
@@ -386,6 +387,30 @@
 			si.si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR;
 			break;
 		}
+
+#ifdef CONFIG_MEMORY_FAILURE
+		if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+			printk(KERN_ERR
+	"MCE: Killing %s:%d due to hardware memory corruption fault at %08lx\n",
+			tsk->comm, tsk->pid, address);
+			si.si_signo = SIGBUS;
+			si.si_code = BUS_MCEERR_AR;
+		}
+#endif
+
+		/*
+		 * Either small page or large page may be poisoned.
+		 * In other words, VM_FAULT_HWPOISON_LARGE and
+		 * VM_FAULT_HWPOISON are mutually exclusive.
+		 */
+		if (fault & VM_FAULT_HWPOISON_LARGE)
+			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+		else if (fault & VM_FAULT_HWPOISON)
+			lsb = PAGE_SHIFT;
+		else
+			show_signal_msg(regs, code, address, tsk, vma);
+		si.si_addr_lsb = lsb;
+
 		si.si_errno = 0;
 		si.si_addr = (void __user *) address;
 		force_sig_info(si.si_signo, &si, current);
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index e084fa5..063817f 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -138,10 +138,11 @@
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQUENCER_OSS=m
 CONFIG_SND_POWERMAC=m
 CONFIG_SND_AOA=m
 CONFIG_SND_AOA_FABRIC_LAYOUT=m
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index 79bbc82..805b0f8 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -64,11 +64,12 @@
 # CONFIG_LOGO_LINUX_CLUT224 is not set
 CONFIG_SOUND=y
 CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=y
 CONFIG_SND_PCM_OSS=y
-CONFIG_SND_SEQUENCER_OSS=y
 # CONFIG_SND_VERBOSE_PROCFS is not set
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQUENCER_OSS=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 8cf4a46..6daa56f 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -115,9 +115,10 @@
 CONFIG_LOGO=y
 CONFIG_SOUND=y
 CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=y
 CONFIG_SND_PCM_OSS=y
+CONFIG_SND_SEQUENCER=y
 CONFIG_SND_SEQUENCER_OSS=y
 CONFIG_SND_USB_AUDIO=y
 CONFIG_SND_USB_USX2Y=y
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 8e798b1..1aab9a6 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -227,11 +227,12 @@
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
 CONFIG_SND_DUMMY=m
 CONFIG_SND_POWERMAC=m
 CONFIG_SND_AOA=m
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 791db77..6ddca80 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -222,11 +222,12 @@
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
 CONFIG_SND_POWERMAC=m
 CONFIG_SND_AOA=m
 CONFIG_SND_AOA_FABRIC_LAYOUT=m
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index d0fe0f8..41d85cb 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -141,11 +141,12 @@
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
 CONFIG_HID_DRAGONRISE=y
 CONFIG_HID_GYRATION=y
 CONFIG_HID_TWINHAN=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index ae6eba4..da0e8d5 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -789,17 +789,18 @@
 # CONFIG_LOGO_LINUX_VGA16 is not set
 CONFIG_SOUND=m
 CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
 CONFIG_SND_DYNAMIC_MINORS=y
 # CONFIG_SND_SUPPORT_OLD_API is not set
 CONFIG_SND_VERBOSE_PRINTK=y
 CONFIG_SND_DEBUG=y
 CONFIG_SND_DEBUG_VERBOSE=y
 CONFIG_SND_PCM_XRUN_DEBUG=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
 CONFIG_SND_DUMMY=m
 CONFIG_SND_VIRMIDI=m
 CONFIG_SND_MTPAV=m
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index aef41b1..9c7400a 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -79,11 +79,12 @@
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_SOUND=y
 CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
+CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=y
 CONFIG_SND_PCM_OSS=y
-CONFIG_SND_SEQUENCER_OSS=y
 # CONFIG_SND_VERBOSE_PROCFS is not set
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQUENCER_OSS=y
 CONFIG_HID_APPLE=m
 CONFIG_HID_WACOM=m
 CONFIG_MMC=y
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 1df770e..7275fed 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -102,10 +102,10 @@
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
-		__flush_tlb_power8(POWER8_TLB_SETS);
+		__flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL);
 		break;
 	case PVR_POWER9:
-		__flush_tlb_power9(POWER9_TLB_SETS_HASH);
+		__flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL);
 		break;
 	default:
 		pr_err("unknown CPU version for boot TLB flush\n");
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 9e81678..116000b 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1019,6 +1019,10 @@
 	} else if ((ret = eeh_ops->init()))
 		return ret;
 
+	/* Initialize PHB PEs */
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+		eeh_dev_phb_init_dynamic(hose);
+
 	/* Initialize EEH event */
 	ret = eeh_event_init();
 	if (ret)
diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
index ad04ecd..a34e691 100644
--- a/arch/powerpc/kernel/eeh_dev.c
+++ b/arch/powerpc/kernel/eeh_dev.c
@@ -78,21 +78,3 @@
 	/* EEH PE for PHB */
 	eeh_phb_pe_create(phb);
 }
-
-/**
- * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs
- *
- * Scan all the existing PHBs and create EEH devices for their OF
- * nodes and their children OF nodes
- */
-static int __init eeh_dev_phb_init(void)
-{
-	struct pci_controller *phb, *tmp;
-
-	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
-		eeh_dev_phb_init_dynamic(phb);
-
-	return 0;
-}
-
-core_initcall(eeh_dev_phb_init);
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index b76ca19..72f153c6 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -624,5 +624,18 @@
 
 long __machine_check_early_realmode_p9(struct pt_regs *regs)
 {
+	/*
+	 * On POWER9 DD2.1 and below, it's possible to get a machine check
+	 * caused by a paste instruction where only DSISR bit 25 is set. This
+	 * will result in the MCE handler seeing an unknown event and the kernel
+	 * crashing. An MCE that occurs like this is spurious, so we don't need
+	 * to do anything in terms of servicing it. If there is something that
+	 * needs to be serviced, the CPU will raise the MCE again with the
+	 * correct DSISR so that it can be serviced properly. So detect this
+	 * case and mark it as handled.
+	 */
+	if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000)
+		return 1;
+
 	return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
 }
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 6f8273f..91e037a 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -104,8 +104,10 @@
 	 * and that can be emulated.
 	 */
 	if (!is_conditional_branch(*p->ainsn.insn) &&
-			analyse_instr(&op, &regs, *p->ainsn.insn))
+			analyse_instr(&op, &regs, *p->ainsn.insn) == 1) {
+		emulate_update_regs(&regs, &op);
 		nip = regs.nip;
+	}
 
 	return nip;
 }
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 07cd22e..f52ad5b 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -131,7 +131,7 @@
 	 * in the appropriate thread structures from live.
 	 */
 
-	if (tsk != current)
+	if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current))
 		return;
 
 	if (MSR_TM_SUSPENDED(mfmsr())) {
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 0ac741f..2e3bc16 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -904,9 +904,6 @@
 #endif
 #endif
 
-#ifdef CONFIG_PPC_64K_PAGES
-	init_mm.context.pte_frag = NULL;
-#endif
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 	mm_iommu_init(&init_mm);
 #endif
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index ec74e20..13c9dcd 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -437,6 +437,7 @@
 int machine_check_e500mc(struct pt_regs *regs)
 {
 	unsigned long mcsr = mfspr(SPRN_MCSR);
+	unsigned long pvr = mfspr(SPRN_PVR);
 	unsigned long reason = mcsr;
 	int recoverable = 1;
 
@@ -478,8 +479,15 @@
 		 * may still get logged and cause a machine check.  We should
 		 * only treat the non-write shadow case as non-recoverable.
 		 */
-		if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS))
-			recoverable = 0;
+		/* On e6500 core, L1 DCWS (Data cache write shadow mode) bit
+		 * is not implemented but L1 data cache always runs in write
+		 * shadow mode. Hence on data cache parity errors HW will
+		 * automatically invalidate the L1 Data Cache.
+		 */
+		if (PVR_VER(pvr) != PVR_VER_E6500) {
+			if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS))
+				recoverable = 0;
+		}
 	}
 
 	if (reason & MCSR_L2MMU_MHIT) {
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 2f6eadd..c702a89 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -310,9 +310,6 @@
 	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
 		return 0;
 
-	if (watchdog_suspended)
-		return 0;
-
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
@@ -358,36 +355,39 @@
 	wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5;
 }
 
-void watchdog_nmi_reconfigure(void)
+void watchdog_nmi_stop(void)
+{
+	int cpu;
+
+	for_each_cpu(cpu, &wd_cpus_enabled)
+		stop_wd_on_cpu(cpu);
+}
+
+void watchdog_nmi_start(void)
 {
 	int cpu;
 
 	watchdog_calc_timeouts();
-
-	for_each_cpu(cpu, &wd_cpus_enabled)
-		stop_wd_on_cpu(cpu);
-
 	for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask)
 		start_wd_on_cpu(cpu);
 }
 
 /*
- * This runs after lockup_detector_init() which sets up watchdog_cpumask.
+ * Invoked from core watchdog init.
  */
-static int __init powerpc_watchdog_init(void)
+int __init watchdog_nmi_probe(void)
 {
 	int err;
 
-	watchdog_calc_timeouts();
-
-	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online",
-				start_wd_on_cpu, stop_wd_on_cpu);
-	if (err < 0)
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"powerpc/watchdog:online",
+					start_wd_on_cpu, stop_wd_on_cpu);
+	if (err < 0) {
 		pr_warn("Watchdog could not be initialized");
-
+		return err;
+	}
 	return 0;
 }
-arch_initcall(powerpc_watchdog_init);
 
 static void handle_backtrace_ipi(struct pt_regs *regs)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 17936f8..ec69fa4 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1121,6 +1121,13 @@
 BEGIN_FTR_SECTION
 	mtspr	SPRN_PPR, r0
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+/* Move canary into DSISR to check for later */
+BEGIN_FTR_SECTION
+	li	r0, 0x7fff
+	mtspr	SPRN_HDSISR, r0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
 	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
 
@@ -1956,9 +1963,14 @@
 kvmppc_hdsi:
 	ld	r3, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r3)
-	cmpwi	r0, 0
 	mfspr	r4, SPRN_HDAR
 	mfspr	r6, SPRN_HDSISR
+BEGIN_FTR_SECTION
+	/* Look for DSISR canary. If we find it, retry instruction */
+	cmpdi	r6, 0x7fff
+	beq	6f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+	cmpwi	r0, 0
 	bne	.Lradix_hdsi		/* on radix, just save DAR/DSISR/ASDR */
 	/* HPTE not found fault or protection fault? */
 	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 1330462..bf45784 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -622,7 +622,7 @@
 		return -EINVAL;
 	state = &sb->irq_state[idx];
 	arch_spin_lock(&sb->lock);
-	*server = state->guest_server;
+	*server = state->act_server;
 	*priority = state->guest_priority;
 	arch_spin_unlock(&sb->lock);
 
@@ -1331,7 +1331,7 @@
 	xive->saved_src_count++;
 
 	/* Convert saved state into something compatible with xics */
-	val = state->guest_server;
+	val = state->act_server;
 	prio = state->saved_scan_prio;
 
 	if (prio == MASKED) {
@@ -1507,7 +1507,6 @@
 	/* First convert prio and mark interrupt as untargetted */
 	act_prio = xive_prio_from_guest(guest_prio);
 	state->act_priority = MASKED;
-	state->guest_server = server;
 
 	/*
 	 * We need to drop the lock due to the mutex below. Hopefully
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 5938f76..6ba63f8 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -35,7 +35,6 @@
 	struct xive_irq_data *pt_data;	/* XIVE Pass-through associated data */
 
 	/* Targetting as set by guest */
-	u32 guest_server;		/* Current guest selected target */
 	u8 guest_priority;		/* Guest set priority */
 	u8 saved_priority;		/* Saved priority when masking */
 
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index fb9f58b..5e8418c 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -944,9 +944,9 @@
 		: "r" (addr), "i" (-EFAULT), "0" (err))
 
 static nokprobe_inline void set_cr0(const struct pt_regs *regs,
-				    struct instruction_op *op, int rd)
+				    struct instruction_op *op)
 {
-	long val = regs->gpr[rd];
+	long val = op->val;
 
 	op->type |= SETCC;
 	op->ccval = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000);
@@ -1326,7 +1326,7 @@
 	case 13:	/* addic. */
 		imm = (short) instr;
 		add_with_carry(regs, op, rd, regs->gpr[ra], imm, 0);
-		set_cr0(regs, op, rd);
+		set_cr0(regs, op);
 		return 1;
 
 	case 14:	/* addi */
@@ -1397,13 +1397,13 @@
 
 	case 28:	/* andi. */
 		op->val = regs->gpr[rd] & (unsigned short) instr;
-		set_cr0(regs, op, ra);
+		set_cr0(regs, op);
 		goto logical_done_nocc;
 
 	case 29:	/* andis. */
 		imm = (unsigned short) instr;
 		op->val = regs->gpr[rd] & (imm << 16);
-		set_cr0(regs, op, ra);
+		set_cr0(regs, op);
 		goto logical_done_nocc;
 
 #ifdef __powerpc64__
@@ -1513,10 +1513,10 @@
 			op->type = COMPUTE + SETCC;
 			imm = 0xf0000000UL;
 			val = regs->gpr[rd];
-			op->val = regs->ccr;
+			op->ccval = regs->ccr;
 			for (sh = 0; sh < 8; ++sh) {
 				if (instr & (0x80000 >> sh))
-					op->val = (op->val & ~imm) |
+					op->ccval = (op->ccval & ~imm) |
 						(val & imm);
 				imm >>= 4;
 			}
@@ -1651,8 +1651,9 @@
 			goto arith_done;
 
 		case 235:	/* mullw */
-			op->val = (unsigned int) regs->gpr[ra] *
-				(unsigned int) regs->gpr[rb];
+			op->val = (long)(int) regs->gpr[ra] *
+				(int) regs->gpr[rb];
+
 			goto arith_done;
 
 		case 266:	/* add */
@@ -2526,7 +2527,7 @@
 
  logical_done:
 	if (instr & 1)
-		set_cr0(regs, op, ra);
+		set_cr0(regs, op);
  logical_done_nocc:
 	op->reg = ra;
 	op->type |= SETREG;
@@ -2534,7 +2535,7 @@
 
  arith_done:
 	if (instr & 1)
-		set_cr0(regs, op, rd);
+		set_cr0(regs, op);
  compute_done:
 	op->reg = rd;
 	op->type |= SETREG;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 65eda19..f6c7f54 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -361,9 +361,9 @@
 			break;
 	}
 	wmb();
+	local_irq_restore(flags);
 	flush_tlb_kernel_range((unsigned long)page_address(start),
 			       (unsigned long)page_address(page));
-	local_irq_restore(flags);
 	return err;
 }
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 2e3eb74..9e3da16 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -793,6 +793,11 @@
 	u32 pmcs[MAX_HWEVENTS];
 	int i;
 
+	if (!ppmu) {
+		pr_info("Performance monitor hardware not registered.\n");
+		return;
+	}
+
 	if (!ppmu->n_counter)
 		return;
 
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 9f59041..443d5ca 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -393,7 +393,13 @@
 	u64 pir = get_hard_smp_processor_id(cpu);
 
 	mtspr(SPRN_LPCR, lpcr_val);
-	opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
+
+	/*
+	 * Program the LPCR via stop-api only if the deepest stop state
+	 * can lose hypervisor context.
+	 */
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
+		opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
 }
 
 /*
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 897aa14..bbb73aa 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -272,7 +272,15 @@
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 static unsigned long pnv_memory_block_size(void)
 {
-	return 256UL * 1024 * 1024;
+	/*
+	 * We map the kernel linear region with 1GB large pages on radix. For
+	 * memory hot unplug to work our memory block size must be at least
+	 * this size.
+	 */
+	if (radix_enabled())
+		return 1UL * 1024 * 1024 * 1024;
+	else
+		return 256UL * 1024 * 1024;
 }
 #endif
 
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 783f363..e45b5f1 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -266,7 +266,6 @@
 		return rc;
 	}
 
-	of_node_put(dn->parent);
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index fc0d8f9..fadb95e 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -462,15 +462,19 @@
 	}
 
 	dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent);
-	of_node_put(parent);
 	if (!dn) {
 		pr_warn("Failed call to configure-connector, drc index: %x\n",
 			drc_index);
 		dlpar_release_drc(drc_index);
+		of_node_put(parent);
 		return -EINVAL;
 	}
 
 	rc = dlpar_attach_node(dn, parent);
+
+	/* Regardless we are done with parent now */
+	of_node_put(parent);
+
 	if (rc) {
 		saved_rc = rc;
 		pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n",
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 210ce63..f7042ad 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -226,8 +226,10 @@
 		return -ENOENT;
 
 	dn = dlpar_configure_connector(drc_index, parent_dn);
-	if (!dn)
+	if (!dn) {
+		of_node_put(parent_dn);
 		return -ENOENT;
+	}
 
 	rc = dlpar_attach_node(dn, parent_dn);
 	if (rc)
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 9234be1..5011ffe 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -71,6 +71,8 @@
 #define RIWAR_WRTYP_ALLOC	0x00006000
 #define RIWAR_SIZE_MASK		0x0000003F
 
+static DEFINE_SPINLOCK(fsl_rio_config_lock);
+
 #define __fsl_read_rio_config(x, addr, err, op)		\
 	__asm__ __volatile__(				\
 		"1:	"op" %1,0(%2)\n"		\
@@ -184,6 +186,7 @@
 			u8 hopcount, u32 offset, int len, u32 *val)
 {
 	struct rio_priv *priv = mport->priv;
+	unsigned long flags;
 	u8 *data;
 	u32 rval, err = 0;
 
@@ -197,6 +200,8 @@
 	if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len))
 		return -EINVAL;
 
+	spin_lock_irqsave(&fsl_rio_config_lock, flags);
+
 	out_be32(&priv->maint_atmu_regs->rowtar,
 		 (destid << 22) | (hopcount << 12) | (offset >> 12));
 	out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10));
@@ -213,6 +218,7 @@
 		__fsl_read_rio_config(rval, data, err, "lwz");
 		break;
 	default:
+		spin_unlock_irqrestore(&fsl_rio_config_lock, flags);
 		return -EINVAL;
 	}
 
@@ -221,6 +227,7 @@
 			 err, destid, hopcount, offset);
 	}
 
+	spin_unlock_irqrestore(&fsl_rio_config_lock, flags);
 	*val = rval;
 
 	return err;
@@ -244,7 +251,10 @@
 			u8 hopcount, u32 offset, int len, u32 val)
 {
 	struct rio_priv *priv = mport->priv;
+	unsigned long flags;
 	u8 *data;
+	int ret = 0;
+
 	pr_debug
 		("fsl_rio_config_write:"
 		" index %d destid %d hopcount %d offset %8.8x len %d val %8.8x\n",
@@ -255,6 +265,8 @@
 	if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len))
 		return -EINVAL;
 
+	spin_lock_irqsave(&fsl_rio_config_lock, flags);
+
 	out_be32(&priv->maint_atmu_regs->rowtar,
 		 (destid << 22) | (hopcount << 12) | (offset >> 12));
 	out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10));
@@ -271,10 +283,11 @@
 		out_be32((u32 *) data, val);
 		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
 	}
+	spin_unlock_irqrestore(&fsl_rio_config_lock, flags);
 
-	return 0;
+	return ret;
 }
 
 static void fsl_rio_inbound_mem_init(struct rio_priv *priv)
diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c
index ab7a74c..88b35a3d 100644
--- a/arch/powerpc/sysdev/fsl_rmu.c
+++ b/arch/powerpc/sysdev/fsl_rmu.c
@@ -104,6 +104,8 @@
 
 #define DOORBELL_MESSAGE_SIZE	0x08
 
+static DEFINE_SPINLOCK(fsl_rio_doorbell_lock);
+
 struct rio_msg_regs {
 	u32 omr;
 	u32 osr;
@@ -626,9 +628,13 @@
 int fsl_rio_doorbell_send(struct rio_mport *mport,
 				int index, u16 destid, u16 data)
 {
+	unsigned long flags;
+
 	pr_debug("fsl_doorbell_send: index %d destid %4.4x data %4.4x\n",
 		 index, destid, data);
 
+	spin_lock_irqsave(&fsl_rio_doorbell_lock, flags);
+
 	/* In the serial version silicons, such as MPC8548, MPC8641,
 	 * below operations is must be.
 	 */
@@ -638,6 +644,8 @@
 	out_be32(&dbell->dbell_regs->oddatr, (index << 20) | data);
 	out_be32(&dbell->dbell_regs->odmr, 0x00000001);
 
+	spin_unlock_irqrestore(&fsl_rio_doorbell_lock, flags);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index f387318..a3b8d7d 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -1402,6 +1402,14 @@
 
 	if (xive_ops->teardown_cpu)
 		xive_ops->teardown_cpu(cpu, xc);
+
+#ifdef CONFIG_SMP
+	/* Get rid of IPI */
+	xive_cleanup_cpu_ipi(cpu, xc);
+#endif
+
+	/* Disable and free the queues */
+	xive_cleanup_cpu_queues(cpu, xc);
 }
 
 void xive_kexec_teardown_cpu(int secondary)
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index f24a70b..d9c4c93 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -431,7 +431,11 @@
 
 static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc)
 {
+	if (!xc->hw_ipi)
+		return;
+
 	xive_irq_bitmap_free(xc->hw_ipi);
+	xc->hw_ipi = 0;
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index dce708e..20e75a2 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1507,7 +1507,9 @@
 static inline void pmdp_invalidate(struct vm_area_struct *vma,
 				   unsigned long addr, pmd_t *pmdp)
 {
-	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
+	pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
+
+	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd);
 }
 
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index ca8cd80..60181ca 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -404,18 +404,6 @@
 #endif
 }
 
-static int __init topology_setup(char *str)
-{
-	bool enabled;
-	int rc;
-
-	rc = kstrtobool(str, &enabled);
-	if (!rc && !enabled)
-		S390_lowcore.machine_flags &= ~MACHINE_FLAG_TOPOLOGY;
-	return rc;
-}
-early_param("topology", topology_setup);
-
 static int __init disable_vector_extension(char *str)
 {
 	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index c1bf75f..7e1e403 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -823,9 +823,12 @@
 	}
 
 	/* Check online status of the CPU to which the event is pinned */
-	if ((unsigned int)event->cpu >= nr_cpumask_bits ||
-	    (event->cpu >= 0 && !cpu_online(event->cpu)))
-		return -ENODEV;
+	if (event->cpu >= 0) {
+		if ((unsigned int)event->cpu >= nr_cpumask_bits)
+			return -ENODEV;
+		if (!cpu_online(event->cpu))
+			return -ENODEV;
+	}
 
 	/* Force reset of idle/hv excludes regardless of what the
 	 * user requested.
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index bb47c92..ed0bdd2 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -8,6 +8,8 @@
 
 #include <linux/workqueue.h>
 #include <linux/bootmem.h>
+#include <linux/uaccess.h>
+#include <linux/sysctl.h>
 #include <linux/cpuset.h>
 #include <linux/device.h>
 #include <linux/export.h>
@@ -29,12 +31,20 @@
 #define PTF_VERTICAL	(1UL)
 #define PTF_CHECK	(2UL)
 
+enum {
+	TOPOLOGY_MODE_HW,
+	TOPOLOGY_MODE_SINGLE,
+	TOPOLOGY_MODE_PACKAGE,
+	TOPOLOGY_MODE_UNINITIALIZED
+};
+
 struct mask_info {
 	struct mask_info *next;
 	unsigned char id;
 	cpumask_t mask;
 };
 
+static int topology_mode = TOPOLOGY_MODE_UNINITIALIZED;
 static void set_topology_timer(void);
 static void topology_work_fn(struct work_struct *work);
 static struct sysinfo_15_1_x *tl_info;
@@ -59,11 +69,26 @@
 	cpumask_t mask;
 
 	cpumask_copy(&mask, cpumask_of(cpu));
-	if (!MACHINE_HAS_TOPOLOGY)
-		return mask;
-	for (; info; info = info->next) {
-		if (cpumask_test_cpu(cpu, &info->mask))
-			return info->mask;
+	switch (topology_mode) {
+	case TOPOLOGY_MODE_HW:
+		while (info) {
+			if (cpumask_test_cpu(cpu, &info->mask)) {
+				mask = info->mask;
+				break;
+			}
+			info = info->next;
+		}
+		if (cpumask_empty(&mask))
+			cpumask_copy(&mask, cpumask_of(cpu));
+		break;
+	case TOPOLOGY_MODE_PACKAGE:
+		cpumask_copy(&mask, cpu_present_mask);
+		break;
+	default:
+		/* fallthrough */
+	case TOPOLOGY_MODE_SINGLE:
+		cpumask_copy(&mask, cpumask_of(cpu));
+		break;
 	}
 	return mask;
 }
@@ -74,7 +99,7 @@
 	int i;
 
 	cpumask_copy(&mask, cpumask_of(cpu));
-	if (!MACHINE_HAS_TOPOLOGY)
+	if (topology_mode != TOPOLOGY_MODE_HW)
 		return mask;
 	cpu -= cpu % (smp_cpu_mtid + 1);
 	for (i = 0; i <= smp_cpu_mtid; i++)
@@ -184,10 +209,8 @@
 {
 	int cpu;
 
-	mutex_lock(&smp_cpu_state_mutex);
 	for_each_possible_cpu(cpu)
 		smp_cpu_set_polarization(cpu, POLARIZATION_HRZ);
-	mutex_unlock(&smp_cpu_state_mutex);
 }
 
 static int ptf(unsigned long fc)
@@ -223,7 +246,7 @@
 static void update_cpu_masks(void)
 {
 	struct cpu_topology_s390 *topo;
-	int cpu;
+	int cpu, id;
 
 	for_each_possible_cpu(cpu) {
 		topo = &cpu_topology[cpu];
@@ -231,12 +254,13 @@
 		topo->core_mask = cpu_group_map(&socket_info, cpu);
 		topo->book_mask = cpu_group_map(&book_info, cpu);
 		topo->drawer_mask = cpu_group_map(&drawer_info, cpu);
-		if (!MACHINE_HAS_TOPOLOGY) {
+		if (topology_mode != TOPOLOGY_MODE_HW) {
+			id = topology_mode == TOPOLOGY_MODE_PACKAGE ? 0 : cpu;
 			topo->thread_id = cpu;
 			topo->core_id = cpu;
-			topo->socket_id = cpu;
-			topo->book_id = cpu;
-			topo->drawer_id = cpu;
+			topo->socket_id = id;
+			topo->book_id = id;
+			topo->drawer_id = id;
 			if (cpu_present(cpu))
 				cpumask_set_cpu(cpu, &cpus_with_topology);
 		}
@@ -254,6 +278,7 @@
 	struct sysinfo_15_1_x *info = tl_info;
 	int rc = 0;
 
+	mutex_lock(&smp_cpu_state_mutex);
 	cpumask_clear(&cpus_with_topology);
 	if (MACHINE_HAS_TOPOLOGY) {
 		rc = 1;
@@ -263,6 +288,7 @@
 	update_cpu_masks();
 	if (!MACHINE_HAS_TOPOLOGY)
 		topology_update_polarization_simple();
+	mutex_unlock(&smp_cpu_state_mutex);
 	return rc;
 }
 
@@ -289,6 +315,11 @@
 	schedule_work(&topology_work);
 }
 
+static void topology_flush_work(void)
+{
+	flush_work(&topology_work);
+}
+
 static void topology_timer_fn(unsigned long ignored)
 {
 	if (ptf(PTF_CHECK))
@@ -459,6 +490,12 @@
 	struct sysinfo_15_1_x *info;
 
 	set_sched_topology(s390_topology);
+	if (topology_mode == TOPOLOGY_MODE_UNINITIALIZED) {
+		if (MACHINE_HAS_TOPOLOGY)
+			topology_mode = TOPOLOGY_MODE_HW;
+		else
+			topology_mode = TOPOLOGY_MODE_SINGLE;
+	}
 	if (!MACHINE_HAS_TOPOLOGY)
 		goto out;
 	tl_info = memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE);
@@ -474,12 +511,97 @@
 	__arch_update_cpu_topology();
 }
 
+static inline int topology_get_mode(int enabled)
+{
+	if (!enabled)
+		return TOPOLOGY_MODE_SINGLE;
+	return MACHINE_HAS_TOPOLOGY ? TOPOLOGY_MODE_HW : TOPOLOGY_MODE_PACKAGE;
+}
+
+static inline int topology_is_enabled(void)
+{
+	return topology_mode != TOPOLOGY_MODE_SINGLE;
+}
+
+static int __init topology_setup(char *str)
+{
+	bool enabled;
+	int rc;
+
+	rc = kstrtobool(str, &enabled);
+	if (rc)
+		return rc;
+	topology_mode = topology_get_mode(enabled);
+	return 0;
+}
+early_param("topology", topology_setup);
+
+static int topology_ctl_handler(struct ctl_table *ctl, int write,
+				void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	unsigned int len;
+	int new_mode;
+	char buf[2];
+
+	if (!*lenp || *ppos) {
+		*lenp = 0;
+		return 0;
+	}
+	if (!write) {
+		strncpy(buf, topology_is_enabled() ? "1\n" : "0\n",
+			ARRAY_SIZE(buf));
+		len = strnlen(buf, ARRAY_SIZE(buf));
+		if (len > *lenp)
+			len = *lenp;
+		if (copy_to_user(buffer, buf, len))
+			return -EFAULT;
+		goto out;
+	}
+	len = *lenp;
+	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
+		return -EFAULT;
+	if (buf[0] != '0' && buf[0] != '1')
+		return -EINVAL;
+	mutex_lock(&smp_cpu_state_mutex);
+	new_mode = topology_get_mode(buf[0] == '1');
+	if (topology_mode != new_mode) {
+		topology_mode = new_mode;
+		topology_schedule_update();
+	}
+	mutex_unlock(&smp_cpu_state_mutex);
+	topology_flush_work();
+out:
+	*lenp = len;
+	*ppos += len;
+	return 0;
+}
+
+static struct ctl_table topology_ctl_table[] = {
+	{
+		.procname	= "topology",
+		.mode		= 0644,
+		.proc_handler	= topology_ctl_handler,
+	},
+	{ },
+};
+
+static struct ctl_table topology_dir_table[] = {
+	{
+		.procname	= "s390",
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= topology_ctl_table,
+	},
+	{ },
+};
+
 static int __init topology_init(void)
 {
 	if (MACHINE_HAS_TOPOLOGY)
 		set_topology_timer();
 	else
 		topology_update_polarization_simple();
+	register_sysctl_table(topology_dir_table);
 	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 8ecc25e..98ffe3e 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -56,13 +56,12 @@
 static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	unsigned long mask, result;
 	struct page *head, *page;
+	unsigned long mask;
 	int refs;
 
-	result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
-	mask = result | _SEGMENT_ENTRY_INVALID;
-	if ((pmd_val(pmd) & mask) != result)
+	mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
+	if ((pmd_val(pmd) & mask) != 0)
 		return 0;
 	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
 
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index 18e0377..88ce1e2 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -136,10 +136,6 @@
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm)	do { } while(0)
-#define release_segments(mm)	do { } while(0)
-
 /*
  * FPU lazy state save handling.
  */
diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h
index eedd4f6..777a163 100644
--- a/arch/sh/include/asm/processor_64.h
+++ b/arch/sh/include/asm/processor_64.h
@@ -170,10 +170,6 @@
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm)	do { } while (0)
-#define release_segments(mm)	do { } while (0)
-#define forget_segments()	do { } while (0)
 /*
  * FPU lazy state save handling.
  */
diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7264.h b/arch/sh/include/cpu-sh2a/cpu/sh7264.h
index 4d1ef6d..2ae0e93 100644
--- a/arch/sh/include/cpu-sh2a/cpu/sh7264.h
+++ b/arch/sh/include/cpu-sh2a/cpu/sh7264.h
@@ -43,9 +43,7 @@
 	GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4,
 	GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0,
 
-	/* Port H */
-	GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4,
-	GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0,
+	/* Port H - Port H does not have a Data Register */
 
 	/* Port I - not on device */
 
diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7269.h b/arch/sh/include/cpu-sh2a/cpu/sh7269.h
index 2a0ca87..13c495a 100644
--- a/arch/sh/include/cpu-sh2a/cpu/sh7269.h
+++ b/arch/sh/include/cpu-sh2a/cpu/sh7269.h
@@ -45,9 +45,7 @@
 	GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4,
 	GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0,
 
-	/* Port H */
-	GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4,
-	GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0,
+	/* Port H - Port H does not have a Data Register */
 
 	/* Port I - not on device */
 
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h
index 3bb74e5..78961ab 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7722.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h
@@ -67,7 +67,7 @@
 	GPIO_PTN3, GPIO_PTN2, GPIO_PTN1, GPIO_PTN0,
 
 	/* PTQ */
-	GPIO_PTQ7, GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4,
+	GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4,
 	GPIO_PTQ3, GPIO_PTQ2, GPIO_PTQ1, GPIO_PTQ0,
 
 	/* PTR */
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7757.h b/arch/sh/include/cpu-sh4/cpu/sh7757.h
index 5340f3b..b40fb54 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7757.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7757.h
@@ -40,7 +40,7 @@
 
 	/* PTJ */
 	GPIO_PTJ0, GPIO_PTJ1, GPIO_PTJ2, GPIO_PTJ3,
-	GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, GPIO_PTJ7_RESV,
+	GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6,
 
 	/* PTK */
 	GPIO_PTK0, GPIO_PTK1, GPIO_PTK2, GPIO_PTK3,
@@ -48,7 +48,7 @@
 
 	/* PTL */
 	GPIO_PTL0, GPIO_PTL1, GPIO_PTL2, GPIO_PTL3,
-	GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, GPIO_PTL7_RESV,
+	GPIO_PTL4, GPIO_PTL5, GPIO_PTL6,
 
 	/* PTM */
 	GPIO_PTM0, GPIO_PTM1, GPIO_PTM2, GPIO_PTM3,
@@ -56,7 +56,7 @@
 
 	/* PTN */
 	GPIO_PTN0, GPIO_PTN1, GPIO_PTN2, GPIO_PTN3,
-	GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, GPIO_PTN7_RESV,
+	GPIO_PTN4, GPIO_PTN5, GPIO_PTN6,
 
 	/* PTO */
 	GPIO_PTO0, GPIO_PTO1, GPIO_PTO2, GPIO_PTO3,
@@ -68,7 +68,7 @@
 
 	/* PTQ */
 	GPIO_PTQ0, GPIO_PTQ1, GPIO_PTQ2, GPIO_PTQ3,
-	GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, GPIO_PTQ7_RESV,
+	GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6,
 
 	/* PTR */
 	GPIO_PTR0, GPIO_PTR1, GPIO_PTR2, GPIO_PTR3,
diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
index 0d925fa..9f94435 100644
--- a/arch/tile/configs/tilegx_defconfig
+++ b/arch/tile/configs/tilegx_defconfig
@@ -409,5 +409,4 @@
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
index 149d8e8..1c5bd4f 100644
--- a/arch/tile/configs/tilepro_defconfig
+++ b/arch/tile/configs/tilepro_defconfig
@@ -189,7 +189,6 @@
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=y
 CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
@@ -521,7 +520,6 @@
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
 CONFIG_CRC_CCITT=m
 CONFIG_CRC7=m
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 6becb96..ad83c1e 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -140,7 +140,7 @@
 {
 	char *endp;
 	unsigned long long maxnodemem;
-	long node;
+	unsigned long node;
 
 	node = str ? simple_strtoul(str, &endp, 0) : INT_MAX;
 	if (node >= MAX_NUMNODES || *endp != ':')
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index f6d1a3f..86942a4 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -58,11 +58,6 @@
 {
 }
 
-static inline void mm_copy_segments(struct mm_struct *from_mm,
-				    struct mm_struct *new_mm)
-{
-}
-
 #define init_stack	(init_thread_union.stack)
 
 /*
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index 0b034eb..7f69d17 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -98,7 +98,7 @@
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static void __init timer_setup(void)
+static void __init um_timer_setup(void)
 {
 	int err;
 
@@ -132,5 +132,5 @@
 void __init time_init(void)
 {
 	timer_set_signal_handler();
-	late_time_init = timer_setup;
+	late_time_init = um_timer_setup;
 }
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 246c670..8c1fcb6 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -33,7 +33,7 @@
 #define s3	((16 + 2 + (3 * 256)) * 4)
 
 /* register macros */
-#define CTX %rdi
+#define CTX %r12
 #define RIO %rsi
 
 #define RX0 %rax
@@ -56,12 +56,12 @@
 #define RX2bh %ch
 #define RX3bh %dh
 
-#define RT0 %rbp
+#define RT0 %rdi
 #define RT1 %rsi
 #define RT2 %r8
 #define RT3 %r9
 
-#define RT0d %ebp
+#define RT0d %edi
 #define RT1d %esi
 #define RT2d %r8d
 #define RT3d %r9d
@@ -120,13 +120,14 @@
 
 ENTRY(__blowfish_enc_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -142,7 +143,7 @@
 	round_enc(14);
 	add_roundkey_enc(16);
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	movq %r10, RIO;
 	test %cl, %cl;
@@ -157,12 +158,13 @@
 
 ENTRY(blowfish_dec_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -181,7 +183,7 @@
 	movq %r10, RIO;
 	write_block();
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk)
@@ -298,20 +300,21 @@
 
 ENTRY(__blowfish_enc_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
 	pushq %rcx;
 
-	preload_roundkey_enc(0);
-
+	movq %rdi, CTX
 	movq %rsi, %r11;
 	movq %rdx, RIO;
 
+	preload_roundkey_enc(0);
+
 	read_block4();
 
 	round_enc4(0);
@@ -324,39 +327,40 @@
 	round_enc4(14);
 	add_preloaded_roundkey4();
 
-	popq %rbp;
+	popq %r12;
 	movq %r11, RIO;
 
-	test %bpl, %bpl;
+	test %r12b, %r12b;
 	jnz .L__enc_xor4;
 
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 
 .L__enc_xor4:
 	xor_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 ENDPROC(__blowfish_enc_blk_4way)
 
 ENTRY(blowfish_dec_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
-	preload_roundkey_dec(17);
 
-	movq %rsi, %r11;
+	movq %rdi, CTX;
+	movq %rsi, %r11
 	movq %rdx, RIO;
 
+	preload_roundkey_dec(17);
 	read_block4();
 
 	round_dec4(17);
@@ -373,7 +377,7 @@
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk_4way)
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 310319c..95ba695 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -75,17 +75,17 @@
 #define RCD1bh %dh
 
 #define RT0 %rsi
-#define RT1 %rbp
+#define RT1 %r12
 #define RT2 %r8
 
 #define RT0d %esi
-#define RT1d %ebp
+#define RT1d %r12d
 #define RT2d %r8d
 
 #define RT2bl %r8b
 
 #define RXOR %r9
-#define RRBP %r10
+#define RR12 %r10
 #define RDST %r11
 
 #define RXORd %r9d
@@ -197,7 +197,7 @@
 	 *	%rdx: src
 	 *	%rcx: bool xor
 	 */
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 
 	movq %rcx, RXOR;
 	movq %rsi, RDST;
@@ -227,13 +227,13 @@
 
 	enc_outunpack(mov, RT1);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 
 .L__enc_xor:
 	enc_outunpack(xor, RT1);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 ENDPROC(__camellia_enc_blk)
 
@@ -248,7 +248,7 @@
 	movl $24, RXORd;
 	cmovel RXORd, RT2d; /* max */
 
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
 
@@ -271,7 +271,7 @@
 
 	dec_outunpack();
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 ENDPROC(camellia_dec_blk)
 
@@ -433,7 +433,7 @@
 	 */
 	pushq %rbx;
 
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rcx, RXOR;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
@@ -461,14 +461,14 @@
 
 	enc_outunpack2(mov, RT2);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	popq %rbx;
 	ret;
 
 .L__enc2_xor:
 	enc_outunpack2(xor, RT2);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	popq %rbx;
 	ret;
 ENDPROC(__camellia_enc_blk_2way)
@@ -485,7 +485,7 @@
 	cmovel RXORd, RT2d; /* max */
 
 	movq %rbx, RXOR;
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
 
@@ -508,7 +508,7 @@
 
 	dec_outunpack2();
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	movq RXOR, %rbx;
 	ret;
 ENDPROC(camellia_dec_blk_2way)
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index b4a8806..86107c9 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -47,7 +47,7 @@
 /**********************************************************************
   16-way AVX cast5
  **********************************************************************/
-#define CTX %rdi
+#define CTX %r15
 
 #define RL1 %xmm0
 #define RR1 %xmm1
@@ -70,8 +70,8 @@
 
 #define RTMP %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %rdi
+#define RID1d %edi
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -226,7 +226,7 @@
 .align 16
 __cast5_enc_blk16:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RL1: blocks 1 and 2
 	 *	RR1: blocks 3 and 4
 	 *	RL2: blocks 5 and 6
@@ -246,9 +246,11 @@
 	 *	RR4: encrypted blocks 15 and 16
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -283,7 +285,7 @@
 
 .L__skip_enc:
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 
@@ -298,7 +300,7 @@
 .align 16
 __cast5_dec_blk16:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RL1: encrypted blocks 1 and 2
 	 *	RR1: encrypted blocks 3 and 4
 	 *	RL2: encrypted blocks 5 and 6
@@ -318,9 +320,11 @@
 	 *	RR4: decrypted blocks 15 and 16
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -356,7 +360,7 @@
 
 	vmovdqa .Lbswap_mask, RKM;
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
 	outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
@@ -372,12 +376,14 @@
 
 ENTRY(cast5_ecb_enc_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	vmovdqu (0*4*4)(%rdx), RL1;
@@ -400,18 +406,22 @@
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_enc_16way)
 
 ENTRY(cast5_ecb_dec_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 
 	FRAME_BEGIN
+	pushq %r15;
+
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	vmovdqu (0*4*4)(%rdx), RL1;
@@ -434,20 +444,22 @@
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_dec_16way)
 
 ENTRY(cast5_cbc_dec_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -483,23 +495,24 @@
 	vmovdqu RR4, (6*16)(%r11);
 	vmovdqu RL4, (7*16)(%r11);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast5_cbc_dec_16way)
 
 ENTRY(cast5_ctr_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: iv (big endian, 64bit)
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -558,8 +571,8 @@
 	vmovdqu RR4, (6*16)(%r11);
 	vmovdqu RL4, (7*16)(%r11);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast5_ctr_16way)
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 952d315..7f30b6f 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -47,7 +47,7 @@
 /**********************************************************************
   8-way AVX cast6
  **********************************************************************/
-#define CTX %rdi
+#define CTX %r15
 
 #define RA1 %xmm0
 #define RB1 %xmm1
@@ -70,8 +70,8 @@
 
 #define RTMP %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %rdi
+#define RID1d %edi
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -264,15 +264,17 @@
 .align 8
 __cast6_enc_blk8:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
 	 * output:
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -297,7 +299,7 @@
 	QBAR(11);
 
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 
@@ -310,15 +312,17 @@
 .align 8
 __cast6_dec_blk8:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
 	 * output:
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -343,7 +347,7 @@
 	QBAR(0);
 
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
@@ -354,12 +358,14 @@
 
 ENTRY(cast6_ecb_enc_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
@@ -368,18 +374,21 @@
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_enc_8way)
 
 ENTRY(cast6_ecb_dec_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
@@ -388,20 +397,22 @@
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_dec_8way)
 
 ENTRY(cast6_cbc_dec_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -411,8 +422,8 @@
 
 	store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast6_cbc_dec_8way)
@@ -425,9 +436,10 @@
 	 *	%rcx: iv (little endian, 128bit)
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -438,8 +450,8 @@
 
 	store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast6_ctr_8way)
@@ -452,7 +464,9 @@
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX
 	movq %rsi, %r11;
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
@@ -464,6 +478,7 @@
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_xts_enc_8way)
@@ -476,7 +491,9 @@
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX
 	movq %rsi, %r11;
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
@@ -488,6 +505,7 @@
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_xts_dec_8way)
diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S
index f3e9164..8e49ce1 100644
--- a/arch/x86/crypto/des3_ede-asm_64.S
+++ b/arch/x86/crypto/des3_ede-asm_64.S
@@ -64,12 +64,12 @@
 #define RW2bh %ch
 
 #define RT0 %r15
-#define RT1 %rbp
+#define RT1 %rsi
 #define RT2 %r14
 #define RT3 %rdx
 
 #define RT0d %r15d
-#define RT1d %ebp
+#define RT1d %esi
 #define RT2d %r14d
 #define RT3d %edx
 
@@ -177,13 +177,14 @@
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	pushq %rbp;
 	pushq %rbx;
 	pushq %r12;
 	pushq %r13;
 	pushq %r14;
 	pushq %r15;
 
+	pushq %rsi; /* dst */
+
 	read_block(%rdx, RL0, RR0);
 	initial_permutation(RL0, RR0);
 
@@ -241,6 +242,8 @@
 	round1(32+15, RL0, RR0, dummy2);
 
 	final_permutation(RR0, RL0);
+
+	popq %rsi /* dst */
 	write_block(%rsi, RR0, RL0);
 
 	popq %r15;
@@ -248,7 +251,6 @@
 	popq %r13;
 	popq %r12;
 	popq %rbx;
-	popq %rbp;
 
 	ret;
 ENDPROC(des3_ede_x86_64_crypt_blk)
@@ -432,13 +434,14 @@
 	 *	%rdx: src (3 blocks)
 	 */
 
-	pushq %rbp;
 	pushq %rbx;
 	pushq %r12;
 	pushq %r13;
 	pushq %r14;
 	pushq %r15;
 
+	pushq %rsi /* dst */
+
 	/* load input */
 	movl 0 * 4(%rdx), RL0d;
 	movl 1 * 4(%rdx), RR0d;
@@ -520,6 +523,7 @@
 	bswapl RR2d;
 	bswapl RL2d;
 
+	popq %rsi /* dst */
 	movl RR0d, 0 * 4(%rsi);
 	movl RL0d, 1 * 4(%rsi);
 	movl RR1d, 2 * 4(%rsi);
@@ -532,7 +536,6 @@
 	popq %r13;
 	popq %r12;
 	popq %rbx;
-	popq %rbp;
 
 	ret;
 ENDPROC(des3_ede_x86_64_crypt_blk_3way)
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1eab79c..9f712a7 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -89,7 +89,7 @@
 #define	REG_RE	%rdx
 #define	REG_RTA	%r12
 #define	REG_RTB	%rbx
-#define	REG_T1	%ebp
+#define	REG_T1	%r11d
 #define	xmm_mov	vmovups
 #define	avx2_zeroupper	vzeroupper
 #define	RND_F1	1
@@ -637,7 +637,6 @@
 	ENTRY(\name)
 
 	push	%rbx
-	push	%rbp
 	push	%r12
 	push	%r13
 	push	%r14
@@ -673,7 +672,6 @@
 	pop	%r14
 	pop	%r13
 	pop	%r12
-	pop	%rbp
 	pop	%rbx
 
 	ret
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index a410950..6204bd5 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -37,7 +37,7 @@
 #define REG_A	%ecx
 #define REG_B	%esi
 #define REG_C	%edi
-#define REG_D	%ebp
+#define REG_D	%r12d
 #define REG_E	%edx
 
 #define REG_T1	%eax
@@ -74,10 +74,10 @@
 	ENTRY(\name)
 
 	push	%rbx
-	push	%rbp
 	push	%r12
+	push	%rbp
+	mov	%rsp, %rbp
 
-	mov	%rsp, %r12
 	sub	$64, %rsp		# allocate workspace
 	and	$~15, %rsp		# align stack
 
@@ -99,10 +99,9 @@
 	xor	%rax, %rax
 	rep stosq
 
-	mov	%r12, %rsp		# deallocate workspace
-
-	pop	%r12
+	mov	%rbp, %rsp		# deallocate workspace
 	pop	%rbp
+	pop	%r12
 	pop	%rbx
 	ret
 
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index e08888a..001bbcf 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -103,7 +103,7 @@
 c = %ecx
 d = %r8d
 e = %edx
-TBL = %rbp
+TBL = %r12
 a = %eax
 b = %ebx
 
@@ -350,13 +350,13 @@
 ENTRY(sha256_transform_avx)
 .align 32
 	pushq   %rbx
-	pushq   %rbp
+	pushq   %r12
 	pushq   %r13
 	pushq   %r14
 	pushq   %r15
-	pushq   %r12
+	pushq	%rbp
+	movq	%rsp, %rbp
 
-	mov	%rsp, %r12
 	subq    $STACK_SIZE, %rsp	# allocate stack space
 	and	$~15, %rsp		# align stack pointer
 
@@ -452,13 +452,12 @@
 
 done_hash:
 
-	mov	%r12, %rsp
-
-	popq	%r12
+	mov	%rbp, %rsp
+	popq	%rbp
 	popq    %r15
 	popq    %r14
 	popq    %r13
-	popq    %rbp
+	popq	%r12
 	popq    %rbx
 	ret
 ENDPROC(sha256_transform_avx)
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 89c8f09..1420db1 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -98,8 +98,6 @@
 e       = %edx	# clobbers NUM_BLKS
 y3	= %esi	# clobbers INP
 
-
-TBL	= %rbp
 SRND	= CTX	# SRND is same register as CTX
 
 a = %eax
@@ -531,7 +529,6 @@
 ENTRY(sha256_transform_rorx)
 .align 32
 	pushq	%rbx
-	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
@@ -568,8 +565,6 @@
 	mov	CTX, _CTX(%rsp)
 
 loop0:
-	lea     K256(%rip), TBL
-
 	## Load first 16 dwords from two blocks
 	VMOVDQ	0*32(INP),XTMP0
 	VMOVDQ	1*32(INP),XTMP1
@@ -597,19 +592,19 @@
 
 .align 16
 loop1:
-	vpaddd	0*32(TBL, SRND), X0, XFER
+	vpaddd	K256+0*32(SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 0*32
 
-	vpaddd	1*32(TBL, SRND), X0, XFER
+	vpaddd	K256+1*32(SRND), X0, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 1*32
 
-	vpaddd	2*32(TBL, SRND), X0, XFER
+	vpaddd	K256+2*32(SRND), X0, XFER
 	vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 2*32
 
-	vpaddd	3*32(TBL, SRND), X0, XFER
+	vpaddd	K256+3*32(SRND), X0, XFER
 	vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 3*32
 
@@ -619,10 +614,11 @@
 
 loop2:
 	## Do last 16 rounds with no scheduling
-	vpaddd	0*32(TBL, SRND), X0, XFER
+	vpaddd	K256+0*32(SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 0*32
-	vpaddd	1*32(TBL, SRND), X1, XFER
+
+	vpaddd	K256+1*32(SRND), X1, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 1*32
 	add	$2*32, SRND
@@ -676,9 +672,6 @@
 	ja	done_hash
 
 do_last_block:
-	#### do last block
-	lea	K256(%rip), TBL
-
 	VMOVDQ	0*16(INP),XWORD0
 	VMOVDQ	1*16(INP),XWORD1
 	VMOVDQ	2*16(INP),XWORD2
@@ -718,7 +711,6 @@
 	popq	%r14
 	popq	%r13
 	popq	%r12
-	popq	%rbp
 	popq	%rbx
 	ret
 ENDPROC(sha256_transform_rorx)
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 39b83c9..c6c05ed 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -95,7 +95,7 @@
 c = %ecx
 d = %r8d
 e = %edx
-TBL = %rbp
+TBL = %r12
 a = %eax
 b = %ebx
 
@@ -356,13 +356,13 @@
 ENTRY(sha256_transform_ssse3)
 .align 32
 	pushq   %rbx
-	pushq   %rbp
+	pushq   %r12
 	pushq   %r13
 	pushq   %r14
 	pushq   %r15
-	pushq   %r12
+	pushq   %rbp
+	mov	%rsp, %rbp
 
-	mov	%rsp, %r12
 	subq    $STACK_SIZE, %rsp
 	and	$~15, %rsp
 
@@ -462,13 +462,12 @@
 
 done_hash:
 
-	mov	%r12, %rsp
-
-	popq    %r12
+	mov	%rbp, %rsp
+	popq	%rbp
 	popq    %r15
 	popq    %r14
 	popq    %r13
-	popq    %rbp
+	popq    %r12
 	popq    %rbx
 
 	ret
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index 7f5f6c6..b16d560 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -69,8 +69,9 @@
 
 BYTE_FLIP_MASK  = %ymm9
 
-# 1st arg
-CTX         = %rdi
+# 1st arg is %rdi, which is saved to the stack and accessed later via %r12
+CTX1        = %rdi
+CTX2        = %r12
 # 2nd arg
 INP         = %rsi
 # 3rd arg
@@ -81,7 +82,7 @@
 e           = %rdx
 y3          = %rsi
 
-TBL   = %rbp
+TBL   = %rdi # clobbers CTX1
 
 a     = %rax
 b     = %rbx
@@ -91,26 +92,26 @@
 h     = %r11
 old_h = %r11
 
-T1    = %r12
+T1    = %r12 # clobbers CTX2
 y0    = %r13
 y1    = %r14
 y2    = %r15
 
-y4    = %r12
-
 # Local variables (stack frame)
 XFER_SIZE = 4*8
 SRND_SIZE = 1*8
 INP_SIZE = 1*8
 INPEND_SIZE = 1*8
+CTX_SIZE = 1*8
 RSPSAVE_SIZE = 1*8
-GPRSAVE_SIZE = 6*8
+GPRSAVE_SIZE = 5*8
 
 frame_XFER = 0
 frame_SRND = frame_XFER + XFER_SIZE
 frame_INP = frame_SRND + SRND_SIZE
 frame_INPEND = frame_INP + INP_SIZE
-frame_RSPSAVE = frame_INPEND + INPEND_SIZE
+frame_CTX = frame_INPEND + INPEND_SIZE
+frame_RSPSAVE = frame_CTX + CTX_SIZE
 frame_GPRSAVE = frame_RSPSAVE + RSPSAVE_SIZE
 frame_size = frame_GPRSAVE + GPRSAVE_SIZE
 
@@ -576,12 +577,11 @@
 	mov	%rax, frame_RSPSAVE(%rsp)
 
 	# Save GPRs
-	mov	%rbp, frame_GPRSAVE(%rsp)
-	mov	%rbx, 8*1+frame_GPRSAVE(%rsp)
-	mov	%r12, 8*2+frame_GPRSAVE(%rsp)
-	mov	%r13, 8*3+frame_GPRSAVE(%rsp)
-	mov	%r14, 8*4+frame_GPRSAVE(%rsp)
-	mov	%r15, 8*5+frame_GPRSAVE(%rsp)
+	mov	%rbx, 8*0+frame_GPRSAVE(%rsp)
+	mov	%r12, 8*1+frame_GPRSAVE(%rsp)
+	mov	%r13, 8*2+frame_GPRSAVE(%rsp)
+	mov	%r14, 8*3+frame_GPRSAVE(%rsp)
+	mov	%r15, 8*4+frame_GPRSAVE(%rsp)
 
 	shl	$7, NUM_BLKS	# convert to bytes
 	jz	done_hash
@@ -589,14 +589,17 @@
 	mov	NUM_BLKS, frame_INPEND(%rsp)
 
 	## load initial digest
-	mov	8*0(CTX),a
-	mov	8*1(CTX),b
-	mov	8*2(CTX),c
-	mov	8*3(CTX),d
-	mov	8*4(CTX),e
-	mov	8*5(CTX),f
-	mov	8*6(CTX),g
-	mov	8*7(CTX),h
+	mov	8*0(CTX1), a
+	mov	8*1(CTX1), b
+	mov	8*2(CTX1), c
+	mov	8*3(CTX1), d
+	mov	8*4(CTX1), e
+	mov	8*5(CTX1), f
+	mov	8*6(CTX1), g
+	mov	8*7(CTX1), h
+
+	# save %rdi (CTX) before it gets clobbered
+	mov	%rdi, frame_CTX(%rsp)
 
 	vmovdqa	PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
 
@@ -652,14 +655,15 @@
 	subq	$1, frame_SRND(%rsp)
 	jne	loop2
 
-	addm	8*0(CTX),a
-	addm	8*1(CTX),b
-	addm	8*2(CTX),c
-	addm	8*3(CTX),d
-	addm	8*4(CTX),e
-	addm	8*5(CTX),f
-	addm	8*6(CTX),g
-	addm	8*7(CTX),h
+	mov	frame_CTX(%rsp), CTX2
+	addm	8*0(CTX2), a
+	addm	8*1(CTX2), b
+	addm	8*2(CTX2), c
+	addm	8*3(CTX2), d
+	addm	8*4(CTX2), e
+	addm	8*5(CTX2), f
+	addm	8*6(CTX2), g
+	addm	8*7(CTX2), h
 
 	mov	frame_INP(%rsp), INP
 	add	$128, INP
@@ -669,12 +673,11 @@
 done_hash:
 
 # Restore GPRs
-	mov	frame_GPRSAVE(%rsp)     ,%rbp
-	mov	8*1+frame_GPRSAVE(%rsp) ,%rbx
-	mov	8*2+frame_GPRSAVE(%rsp) ,%r12
-	mov	8*3+frame_GPRSAVE(%rsp) ,%r13
-	mov	8*4+frame_GPRSAVE(%rsp) ,%r14
-	mov	8*5+frame_GPRSAVE(%rsp) ,%r15
+	mov	8*0+frame_GPRSAVE(%rsp), %rbx
+	mov	8*1+frame_GPRSAVE(%rsp), %r12
+	mov	8*2+frame_GPRSAVE(%rsp), %r13
+	mov	8*3+frame_GPRSAVE(%rsp), %r14
+	mov	8*4+frame_GPRSAVE(%rsp), %r15
 
 	# Restore Stack Pointer
 	mov	frame_RSPSAVE(%rsp), %rsp
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index b3f49d2..73b471d 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -76,8 +76,8 @@
 #define RT %xmm14
 #define RR %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %r13
+#define RID1d %r13d
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -259,7 +259,7 @@
 
 	vmovdqu w(CTX), RK1;
 
-	pushq %rbp;
+	pushq %r13;
 	pushq %rbx;
 	pushq %rcx;
 
@@ -282,7 +282,7 @@
 
 	popq %rcx;
 	popq %rbx;
-	popq %rbp;
+	popq %r13;
 
 	outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
@@ -301,7 +301,7 @@
 
 	vmovdqu (w+4*4)(CTX), RK1;
 
-	pushq %rbp;
+	pushq %r13;
 	pushq %rbx;
 
 	inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
@@ -322,7 +322,7 @@
 	vmovdqu (w)(CTX), RK1;
 
 	popq %rbx;
-	popq %rbp;
+	popq %r13;
 
 	outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 829e89c..9fb9a1f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4409,10 +4409,9 @@
 		return 0;
 	}
 
-	if (lockup_detector_suspend() != 0) {
-		pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
-		return 0;
-	}
+	cpus_read_lock();
+
+	hardlockup_detector_perf_stop();
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
@@ -4420,9 +4419,7 @@
 	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
-	lockup_detector_resume();
-
-	cpus_read_lock();
+	hardlockup_detector_perf_restart();
 
 	for_each_online_cpu(c)
 		free_excl_cntrs(c);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4cf100f..72db066 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -552,6 +552,7 @@
 
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
@@ -560,6 +561,9 @@
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 8e2457c..005908e 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,9 @@
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index db1fe37..a719681 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3462,7 +3462,7 @@
 static struct intel_uncore_type skx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IIO0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IIO0_MSR_PMON_CTR0,
@@ -3492,7 +3492,7 @@
 static struct intel_uncore_type skx_uncore_irp = {
 	.name			= "irp",
 	.num_counters		= 2,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IRP0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IRP0_MSR_PMON_CTR0,
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 4bb3ec6..0672367 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -63,6 +63,14 @@
 	case INTEL_FAM6_ATOM_SILVERMONT1:
 	case INTEL_FAM6_ATOM_SILVERMONT2:
 	case INTEL_FAM6_ATOM_AIRMONT:
+
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_DENVERTON:
+
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
 		if (idx == PERF_MSR_SMI)
 			return true;
 		break;
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index e0bb46c..0e2a5ed 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -231,7 +231,7 @@
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (fpu->fpstate_active) {
+	if (fpu->initialized) {
 		unsigned long fx_aligned, math_size;
 
 		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 1b02038..c096624 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -218,10 +218,9 @@
 #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2,   \
 			   output, input...)				      \
 {									      \
-	register void *__sp asm(_ASM_SP);				      \
 	asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
 		"call %P[new2]", feature2)				      \
-		: output, "+r" (__sp)					      \
+		: output, ASM_CALL_CONSTRAINT				      \
 		: [old] "i" (oldfunc), [new1] "i" (newfunc1),		      \
 		  [new2] "i" (newfunc2), ## input);			      \
 }
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 676ee58..b0dc91f 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -11,10 +11,12 @@
 # define __ASM_FORM_COMMA(x) " " #x ","
 #endif
 
-#ifdef CONFIG_X86_32
+#ifndef __x86_64__
+/* 32 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(a)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
 #else
+/* 64 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(b)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
 #endif
@@ -132,4 +134,15 @@
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 
+#ifndef __ASSEMBLY__
+/*
+ * This output constraint should be used for any inline asm which has a "call"
+ * instruction.  Otherwise the asm may be inserted before the frame pointer
+ * gets set up by the containing function.  If you forget to do this, objtool
+ * may print a "call without frame pointer save/setup" warning.
+ */
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
+#endif
+
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 554cdb2..e3221ff 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -23,11 +23,9 @@
 /*
  * High level FPU state handling functions:
  */
-extern void fpu__activate_curr(struct fpu *fpu);
-extern void fpu__activate_fpstate_read(struct fpu *fpu);
-extern void fpu__activate_fpstate_write(struct fpu *fpu);
-extern void fpu__current_fpstate_write_begin(void);
-extern void fpu__current_fpstate_write_end(void);
+extern void fpu__initialize(struct fpu *fpu);
+extern void fpu__prepare_read(struct fpu *fpu);
+extern void fpu__prepare_write(struct fpu *fpu);
 extern void fpu__save(struct fpu *fpu);
 extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
@@ -120,20 +118,11 @@
 	err;								\
 })
 
-#define check_insn(insn, output, input...)				\
-({									\
-	int err;							\
+#define kernel_insn(insn, output, input...)				\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore)	\
+		     : output : input)
 
 static inline int copy_fregs_to_user(struct fregs_state __user *fx)
 {
@@ -153,20 +142,16 @@
 
 static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
 {
-	int err;
-
 	if (IS_ENABLED(CONFIG_X86_32)) {
-		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+		kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 	} else {
 		if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) {
-			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+			kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 		} else {
 			/* See comment in copy_fxregs_to_kernel() below. */
-			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+			kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
 		}
 	}
-	/* Copying from a kernel buffer to FPU registers should never fail: */
-	WARN_ON_FPU(err);
 }
 
 static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
@@ -183,9 +168,7 @@
 
 static inline void copy_kernel_to_fregs(struct fregs_state *fx)
 {
-	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	WARN_ON_FPU(err);
+	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
 static inline int copy_user_to_fregs(struct fregs_state __user *fx)
@@ -281,18 +264,13 @@
  * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
  * XSAVE area format.
  */
-#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+#define XSTATE_XRESTORE(st, lmask, hmask)				\
 	asm volatile(ALTERNATIVE(XRSTOR,				\
 				 XRSTORS, X86_FEATURE_XSAVES)		\
 		     "\n"						\
-		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     ".pushsection .fixup,\"ax\"\n"			\
-		     "4: movl $-2, %[err]\n"				\
-		     "jmp 3b\n"						\
-		     ".popsection\n"					\
-		     _ASM_EXTABLE(661b, 4b)				\
-		     : [err] "=r" (err)					\
+		     _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
+		     :							\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
@@ -336,7 +314,10 @@
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
+	/*
+	 * We should never fault when copying from a kernel buffer, and the FPU
+	 * state we set at boot time should be valid.
+	 */
 	WARN_ON_FPU(err);
 }
 
@@ -350,7 +331,7 @@
 	u32 hmask = mask >> 32;
 	int err;
 
-	WARN_ON(!alternatives_patched);
+	WARN_ON_FPU(!alternatives_patched);
 
 	XSTATE_XSAVE(xstate, lmask, hmask, err);
 
@@ -365,12 +346,8 @@
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err;
 
-	XSTATE_XRESTORE(xstate, lmask, hmask, err);
-
-	/* We should never fault when copying from a kernel buffer: */
-	WARN_ON_FPU(err);
+	XSTATE_XRESTORE(xstate, lmask, hmask);
 }
 
 /*
@@ -526,38 +503,17 @@
  */
 static inline void fpregs_deactivate(struct fpu *fpu)
 {
-	WARN_ON_FPU(!fpu->fpregs_active);
-
-	fpu->fpregs_active = 0;
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
 	trace_x86_fpu_regs_deactivated(fpu);
 }
 
 static inline void fpregs_activate(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu->fpregs_active);
-
-	fpu->fpregs_active = 1;
 	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
 	trace_x86_fpu_regs_activated(fpu);
 }
 
 /*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int fpregs_active(void)
-{
-	return current->thread.fpu.fpregs_active;
-}
-
-/*
  * FPU state switching for scheduling.
  *
  * This is a two-stage process:
@@ -571,14 +527,13 @@
 static inline void
 switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (old_fpu->fpregs_active) {
+	if (old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
 			old_fpu->last_cpu = cpu;
 
 		/* But leave fpu_fpregs_owner_ctx! */
-		old_fpu->fpregs_active = 0;
 		trace_x86_fpu_regs_deactivated(old_fpu);
 	} else
 		old_fpu->last_cpu = -1;
@@ -595,7 +550,7 @@
 static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 {
 	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
-		       new_fpu->fpstate_active;
+		       new_fpu->initialized;
 
 	if (preload) {
 		if (!fpregs_state_valid(new_fpu, cpu))
@@ -617,8 +572,7 @@
 	struct fpu *fpu = &current->thread.fpu;
 
 	preempt_disable();
-	if (!fpregs_active())
-		fpregs_activate(fpu);
+	fpregs_activate(fpu);
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 3c80f5b..a152057 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -68,6 +68,9 @@
 /* Default value for fxregs_state.mxcsr: */
 #define MXCSR_DEFAULT		0x1f80
 
+/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */
+#define MXCSR_AND_FLAGS_SIZE sizeof(u64)
+
 /*
  * Software based FPU emulation state. This is arbitrary really,
  * it matches the x87 format to make it easier to understand:
@@ -290,36 +293,13 @@
 	unsigned int			last_cpu;
 
 	/*
-	 * @fpstate_active:
+	 * @initialized:
 	 *
-	 * This flag indicates whether this context is active: if the task
+	 * This flag indicates whether this context is initialized: if the task
 	 * is not running then we can restore from this context, if the task
 	 * is running then we should save into this context.
 	 */
-	unsigned char			fpstate_active;
-
-	/*
-	 * @fpregs_active:
-	 *
-	 * This flag determines whether a given context is actively
-	 * loaded into the FPU's registers and that those registers
-	 * represent the task's current FPU state.
-	 *
-	 * Note the interaction with fpstate_active:
-	 *
-	 *   # task does not use the FPU:
-	 *   fpstate_active == 0
-	 *
-	 *   # task uses the FPU and regs are active:
-	 *   fpstate_active == 1 && fpregs_active == 1
-	 *
-	 *   # the regs are inactive but still match fpstate:
-	 *   fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
-	 *
-	 * The third state is what we use for the lazy restore optimization
-	 * on lazy-switching CPUs.
-	 */
-	unsigned char			fpregs_active;
+	unsigned char			initialized;
 
 	/*
 	 * @state:
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 1b2799e..83fee24 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -48,8 +48,12 @@
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
 int using_compacted_format(void);
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
-			void __user *ubuf, struct xregs_state *xsave);
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
-		     struct xregs_state *xsave);
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+extern int validate_xstate_header(const struct xstate_header *hdr);
+
 #endif
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index bc62e7c..59ad3d1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -88,7 +88,7 @@
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
 void __init kvm_guest_init(void);
-void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
@@ -103,7 +103,7 @@
 
 #else /* CONFIG_KVM_GUEST */
 #define kvm_guest_init() do {} while (0)
-#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wait(T, I) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 
 static inline bool kvm_para_available(void)
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 7ae318c..c120b5d 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -286,6 +286,32 @@
 	return __pkru_allows_pkey(vma_pkey(vma), write);
 }
 
+/*
+ * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
+ * bits.  This serves two purposes.  It prevents a nasty situation in
+ * which PCID-unaware code saves CR3, loads some other value (with PCID
+ * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
+ * the saved ASID was nonzero.  It also means that any bugs involving
+ * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
+ * deterministically.
+ */
+
+static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
+{
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		VM_WARN_ON_ONCE(asid > 4094);
+		return __sme_pa(mm->pgd) | (asid + 1);
+	} else {
+		VM_WARN_ON_ONCE(asid != 0);
+		return __sme_pa(mm->pgd);
+	}
+}
+
+static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
+{
+	VM_WARN_ON_ONCE(asid > 4094);
+	return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
+}
 
 /*
  * This can be used from process context to figure out what the value of
@@ -296,10 +322,8 @@
  */
 static inline unsigned long __get_current_cr3_fast(void)
 {
-	unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd);
-
-	if (static_cpu_has(X86_FEATURE_PCID))
-		cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+		this_cpu_read(cpu_tlbstate.loaded_mm_asid));
 
 	/* For now, be very restrictive about when this can be called. */
 	VM_WARN_ON(in_nmi() || preemptible());
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 63cc96f..738503e 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -179,7 +179,6 @@
 	u64 input_address = input ? virt_to_phys(input) : 0;
 	u64 output_address = output ? virt_to_phys(output) : 0;
 	u64 hv_status;
-	register void *__sp asm(_ASM_SP);
 
 #ifdef CONFIG_X86_64
 	if (!hv_hypercall_pg)
@@ -187,7 +186,7 @@
 
 	__asm__ __volatile__("mov %4, %%r8\n"
 			     "call *%5"
-			     : "=a" (hv_status), "+r" (__sp),
+			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
 			     :  "r" (output_address), "m" (hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
@@ -202,7 +201,7 @@
 
 	__asm__ __volatile__("call *%7"
 			     : "=A" (hv_status),
-			       "+c" (input_address_lo), "+r" (__sp)
+			       "+c" (input_address_lo), ASM_CALL_CONSTRAINT
 			     : "A" (control),
 			       "b" (input_address_hi),
 			       "D"(output_address_hi), "S"(output_address_lo),
@@ -224,12 +223,11 @@
 static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 {
 	u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
-	register void *__sp asm(_ASM_SP);
 
 #ifdef CONFIG_X86_64
 	{
 		__asm__ __volatile__("call *%4"
-				     : "=a" (hv_status), "+r" (__sp),
+				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
 				     : "m" (hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
@@ -242,7 +240,7 @@
 		__asm__ __volatile__ ("call *%5"
 				      : "=A"(hv_status),
 					"+c"(input1_lo),
-					"+r"(__sp)
+					ASM_CALL_CONSTRAINT
 				      :	"A" (control),
 					"b" (input1_hi),
 					"m" (hv_hypercall_pg)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 42873ed..280d94c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -459,8 +459,8 @@
  */
 #ifdef CONFIG_X86_32
 #define PVOP_VCALL_ARGS							\
-	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;	\
-	register void *__sp asm("esp")
+	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
+
 #define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)		"a" ((unsigned long)(x))
@@ -480,8 +480,8 @@
 /* [re]ax isn't an arg, but the return val */
 #define PVOP_VCALL_ARGS						\
 	unsigned long __edi = __edi, __esi = __esi,		\
-		__edx = __edx, __ecx = __ecx, __eax = __eax;	\
-	register void *__sp asm("rsp")
+		__edx = __edx, __ecx = __ecx, __eax = __eax;
+
 #define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
@@ -532,7 +532,7 @@
 			asm volatile(pre				\
 				     paravirt_alt(PARAVIRT_CALL)	\
 				     post				\
-				     : call_clbr, "+r" (__sp)		\
+				     : call_clbr, ASM_CALL_CONSTRAINT	\
 				     : paravirt_type(op),		\
 				       paravirt_clobber(clbr),		\
 				       ##__VA_ARGS__			\
@@ -542,7 +542,7 @@
 			asm volatile(pre				\
 				     paravirt_alt(PARAVIRT_CALL)	\
 				     post				\
-				     : call_clbr, "+r" (__sp)		\
+				     : call_clbr, ASM_CALL_CONSTRAINT	\
 				     : paravirt_type(op),		\
 				       paravirt_clobber(clbr),		\
 				       ##__VA_ARGS__			\
@@ -569,7 +569,7 @@
 		asm volatile(pre					\
 			     paravirt_alt(PARAVIRT_CALL)		\
 			     post					\
-			     : call_clbr, "+r" (__sp)			\
+			     : call_clbr, ASM_CALL_CONSTRAINT		\
 			     : paravirt_type(op),			\
 			       paravirt_clobber(clbr),			\
 			       ##__VA_ARGS__				\
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index ec1f3c6..4f44505 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -100,19 +100,14 @@
 
 #ifdef CONFIG_PREEMPT
   extern asmlinkage void ___preempt_schedule(void);
-# define __preempt_schedule()					\
-({								\
-	register void *__sp asm(_ASM_SP);			\
-	asm volatile ("call ___preempt_schedule" : "+r"(__sp));	\
-})
+# define __preempt_schedule() \
+	asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT)
 
   extern asmlinkage void preempt_schedule(void);
   extern asmlinkage void ___preempt_schedule_notrace(void);
-# define __preempt_schedule_notrace()					\
-({									\
-	register void *__sp asm(_ASM_SP);				\
-	asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp));	\
-})
+# define __preempt_schedule_notrace() \
+	asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT)
+
   extern asmlinkage void preempt_schedule_notrace(void);
 #endif
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3fa26a6..b390ff7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -677,8 +677,6 @@
 	 * Like all of Linux's memory ordering operations, this is a
 	 * compiler barrier as well.
 	 */
-	register void *__sp asm(_ASM_SP);
-
 #ifdef CONFIG_X86_32
 	asm volatile (
 		"pushfl\n\t"
@@ -686,7 +684,7 @@
 		"pushl $1f\n\t"
 		"iret\n\t"
 		"1:"
-		: "+r" (__sp) : : "memory");
+		: ASM_CALL_CONSTRAINT : : "memory");
 #else
 	unsigned int tmp;
 
@@ -703,7 +701,7 @@
 		"iretq\n\t"
 		UNWIND_HINT_RESTORE
 		"1:"
-		: "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
+		: "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
 #endif
 }
 
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index a34e0d4..7116b79 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -103,7 +103,6 @@
 ({							\
 	long tmp;					\
 	struct rw_semaphore* ret;			\
-	register void *__sp asm(_ASM_SP);		\
 							\
 	asm volatile("# beginning down_write\n\t"	\
 		     LOCK_PREFIX "  xadd      %1,(%4)\n\t"	\
@@ -114,7 +113,8 @@
 		     "  call " slow_path "\n"		\
 		     "1:\n"				\
 		     "# ending down_write"		\
-		     : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \
+		     : "+m" (sem->count), "=d" (tmp),	\
+		       "=a" (ret), ASM_CALL_CONSTRAINT	\
 		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
 		     : "memory", "cc");			\
 	ret;						\
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 5161da1a..89e7eeb 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -158,17 +158,6 @@
  */
 #ifndef __ASSEMBLY__
 
-static inline unsigned long current_stack_pointer(void)
-{
-	unsigned long sp;
-#ifdef CONFIG_X86_64
-	asm("mov %%rsp,%0" : "=g" (sp));
-#else
-	asm("mov %%esp,%0" : "=g" (sp));
-#endif
-	return sp;
-}
-
 /*
  * Walks up the stack frames to make sure that the specified object is
  * entirely contained by a single stack frame.
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 342e597..39f7a27 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -12,25 +12,22 @@
 
 	TP_STRUCT__entry(
 		__field(struct fpu *, fpu)
-		__field(bool, fpregs_active)
-		__field(bool, fpstate_active)
+		__field(bool, initialized)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
 
 	TP_fast_assign(
 		__entry->fpu		= fpu;
-		__entry->fpregs_active	= fpu->fpregs_active;
-		__entry->fpstate_active	= fpu->fpstate_active;
+		__entry->initialized	= fpu->initialized;
 		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
 			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
 		}
 	),
-	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
-			__entry->fpregs_active,
-			__entry->fpstate_active,
+			__entry->initialized,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 184eb98..4b89291 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -166,11 +166,11 @@
 ({									\
 	int __ret_gu;							\
 	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
-	register void *__sp asm(_ASM_SP);				\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
 	asm volatile("call __get_user_%P4"				\
-		     : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp)	\
+		     : "=a" (__ret_gu), "=r" (__val_gu),		\
+			ASM_CALL_CONSTRAINT				\
 		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
 	__builtin_expect(__ret_gu, 0);					\
@@ -337,7 +337,7 @@
 		     _ASM_EXTABLE(1b, 4b)				\
 		     _ASM_EXTABLE(2b, 4b)				\
 		     : "=r" (retval), "=&A"(x)				\
-		     : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1),	\
+		     : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1),	\
 		       "i" (errret), "0" (retval));			\
 })
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 9606688..7cb282e 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -113,10 +113,9 @@
 	register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
 	register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
 	register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
-	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \
-	register void *__sp asm(_ASM_SP);
+	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
 
-#define __HYPERCALL_0PARAM	"=r" (__res), "+r" (__sp)
+#define __HYPERCALL_0PARAM	"=r" (__res), ASM_CALL_CONSTRAINT
 #define __HYPERCALL_1PARAM	__HYPERCALL_0PARAM, "+r" (__arg1)
 #define __HYPERCALL_2PARAM	__HYPERCALL_1PARAM, "+r" (__arg2)
 #define __HYPERCALL_3PARAM	__HYPERCALL_2PARAM, "+r" (__arg3)
@@ -552,13 +551,13 @@
 MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
 			struct desc_struct desc)
 {
-	u32 *p = (u32 *) &desc;
-
 	mcl->op = __HYPERVISOR_update_descriptor;
 	if (sizeof(maddr) == sizeof(long)) {
 		mcl->args[0] = maddr;
 		mcl->args[1] = *(unsigned long *)&desc;
 	} else {
+		u32 *p = (u32 *)&desc;
+
 		mcl->args[0] = maddr;
 		mcl->args[1] = maddr >> 32;
 		mcl->args[2] = *p++;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9862e2c..d58184b 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -763,6 +763,16 @@
 	}
 }
 
+static void init_amd_zn(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
+	 * all up to and including B1.
+	 */
+	if (c->x86_model <= 1 && c->x86_mask <= 1)
+		set_cpu_cap(c, X86_FEATURE_CPB);
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	early_init_amd(c);
@@ -791,6 +801,7 @@
 	case 0x10: init_amd_gh(c); break;
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
+	case 0x17: init_amd_zn(c); break;
 	}
 
 	/* Enable workaround for FXSAVE leak */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index db68488..0af86d9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -21,14 +21,6 @@
 
 void __init check_bugs(void)
 {
-#ifdef CONFIG_X86_32
-	/*
-	 * Regardless of whether PCID is enumerated, the SDM says
-	 * that it can't be enabled in 32-bit mode.
-	 */
-	setup_clear_cpu_cap(X86_FEATURE_PCID);
-#endif
-
 	identify_boot_cpu();
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 775f101..c9176ba 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -904,6 +904,14 @@
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 	fpu__init_system(c);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Regardless of whether PCID is enumerated, the SDM says
+	 * that it can't be enabled in 32-bit mode.
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
 }
 
 void __init early_cpu_init(void)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e1114f0..f92a659 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -100,7 +100,7 @@
 
 	kernel_fpu_disable();
 
-	if (fpu->fpregs_active) {
+	if (fpu->initialized) {
 		/*
 		 * Ignore return value -- we don't care if reg state
 		 * is clobbered.
@@ -116,7 +116,7 @@
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (fpu->fpregs_active)
+	if (fpu->initialized)
 		copy_kernel_to_fpregs(&fpu->state);
 
 	kernel_fpu_enable();
@@ -148,7 +148,7 @@
 
 	preempt_disable();
 	trace_x86_fpu_before_save(fpu);
-	if (fpu->fpregs_active) {
+	if (fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(fpu)) {
 			copy_kernel_to_fpregs(&fpu->state);
 		}
@@ -189,10 +189,9 @@
 
 int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 {
-	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
-	if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU))
+	if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -206,26 +205,14 @@
 	/*
 	 * Save current FPU registers directly into the child
 	 * FPU context, without any memory-to-memory copying.
-	 * In lazy mode, if the FPU context isn't loaded into
-	 * fpregs, CR0.TS will be set and do_device_not_available
-	 * will load the FPU context.
 	 *
-	 * We have to do all this with preemption disabled,
-	 * mostly because of the FNSAVE case, because in that
-	 * case we must not allow preemption in the window
-	 * between the FNSAVE and us marking the context lazy.
-	 *
-	 * It shouldn't be an issue as even FNSAVE is plenty
-	 * fast in terms of critical section length.
+	 * ( The function 'fails' in the FNSAVE case, which destroys
+	 *   register contents so we have to copy them back. )
 	 */
-	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
-		memcpy(&src_fpu->state, &dst_fpu->state,
-		       fpu_kernel_xstate_size);
-
+		memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size);
 		copy_kernel_to_fpregs(&src_fpu->state);
 	}
-	preempt_enable();
 
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
@@ -237,45 +224,48 @@
  * Activate the current task's in-memory FPU context,
  * if it has not been used before:
  */
-void fpu__activate_curr(struct fpu *fpu)
+void fpu__initialize(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	if (!fpu->fpstate_active) {
+	if (!fpu->initialized) {
 		fpstate_init(&fpu->state);
 		trace_x86_fpu_init_state(fpu);
 
 		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for the current task: */
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 	}
 }
-EXPORT_SYMBOL_GPL(fpu__activate_curr);
+EXPORT_SYMBOL_GPL(fpu__initialize);
 
 /*
  * This function must be called before we read a task's fpstate.
  *
- * If the task has not used the FPU before then initialize its
- * fpstate.
+ * There's two cases where this gets called:
+ *
+ * - for the current task (when coredumping), in which case we have
+ *   to save the latest FPU registers into the fpstate,
+ *
+ * - or it's called for stopped tasks (ptrace), in which case the
+ *   registers were already saved by the context-switch code when
+ *   the task scheduled out - we only have to initialize the registers
+ *   if they've never been initialized.
  *
  * If the task has used the FPU before then save it.
  */
-void fpu__activate_fpstate_read(struct fpu *fpu)
+void fpu__prepare_read(struct fpu *fpu)
 {
-	/*
-	 * If fpregs are active (in the current CPU), then
-	 * copy them to the fpstate:
-	 */
-	if (fpu->fpregs_active) {
+	if (fpu == &current->thread.fpu) {
 		fpu__save(fpu);
 	} else {
-		if (!fpu->fpstate_active) {
+		if (!fpu->initialized) {
 			fpstate_init(&fpu->state);
 			trace_x86_fpu_init_state(fpu);
 
 			trace_x86_fpu_activate_state(fpu);
 			/* Safe to do for current and for stopped child tasks: */
-			fpu->fpstate_active = 1;
+			fpu->initialized = 1;
 		}
 	}
 }
@@ -283,17 +273,17 @@
 /*
  * This function must be called before we write a task's fpstate.
  *
- * If the task has used the FPU before then unlazy it.
+ * If the task has used the FPU before then invalidate any cached FPU registers.
  * If the task has not used the FPU before then initialize its fpstate.
  *
  * After this function call, after registers in the fpstate are
  * modified and the child task has woken up, the child task will
  * restore the modified FPU state from the modified context. If we
- * didn't clear its lazy status here then the lazy in-registers
+ * didn't clear its cached status here then the cached in-registers
  * state pending on its former CPU could be restored, corrupting
  * the modifications.
  */
-void fpu__activate_fpstate_write(struct fpu *fpu)
+void fpu__prepare_write(struct fpu *fpu)
 {
 	/*
 	 * Only stopped child tasks can be used to modify the FPU
@@ -301,8 +291,8 @@
 	 */
 	WARN_ON_FPU(fpu == &current->thread.fpu);
 
-	if (fpu->fpstate_active) {
-		/* Invalidate any lazy state: */
+	if (fpu->initialized) {
+		/* Invalidate any cached state: */
 		__fpu_invalidate_fpregs_state(fpu);
 	} else {
 		fpstate_init(&fpu->state);
@@ -310,74 +300,11 @@
 
 		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for stopped child tasks: */
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 	}
 }
 
 /*
- * This function must be called before we write the current
- * task's fpstate.
- *
- * This call gets the current FPU register state and moves
- * it in to the 'fpstate'.  Preemption is disabled so that
- * no writes to the 'fpstate' can occur from context
- * swiches.
- *
- * Must be followed by a fpu__current_fpstate_write_end().
- */
-void fpu__current_fpstate_write_begin(void)
-{
-	struct fpu *fpu = &current->thread.fpu;
-
-	/*
-	 * Ensure that the context-switching code does not write
-	 * over the fpstate while we are doing our update.
-	 */
-	preempt_disable();
-
-	/*
-	 * Move the fpregs in to the fpu's 'fpstate'.
-	 */
-	fpu__activate_fpstate_read(fpu);
-
-	/*
-	 * The caller is about to write to 'fpu'.  Ensure that no
-	 * CPU thinks that its fpregs match the fpstate.  This
-	 * ensures we will not be lazy and skip a XRSTOR in the
-	 * future.
-	 */
-	__fpu_invalidate_fpregs_state(fpu);
-}
-
-/*
- * This function must be paired with fpu__current_fpstate_write_begin()
- *
- * This will ensure that the modified fpstate gets placed back in
- * the fpregs if necessary.
- *
- * Note: This function may be called whether or not an _actual_
- * write to the fpstate occurred.
- */
-void fpu__current_fpstate_write_end(void)
-{
-	struct fpu *fpu = &current->thread.fpu;
-
-	/*
-	 * 'fpu' now has an updated copy of the state, but the
-	 * registers may still be out of date.  Update them with
-	 * an XRSTOR if they are active.
-	 */
-	if (fpregs_active())
-		copy_kernel_to_fpregs(&fpu->state);
-
-	/*
-	 * Our update is done and the fpregs/fpstate are in sync
-	 * if necessary.  Context switches can happen again.
-	 */
-	preempt_enable();
-}
-
-/*
  * 'fpu__restore()' is called to copy FPU registers from
  * the FPU fpstate to the live hw registers and to activate
  * access to the hardware registers, so that FPU instructions
@@ -389,7 +316,7 @@
  */
 void fpu__restore(struct fpu *fpu)
 {
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
 	kernel_fpu_disable();
@@ -414,15 +341,17 @@
 {
 	preempt_disable();
 
-	if (fpu->fpregs_active) {
-		/* Ignore delayed exceptions from user space */
-		asm volatile("1: fwait\n"
-			     "2:\n"
-			     _ASM_EXTABLE(1b, 2b));
-		fpregs_deactivate(fpu);
+	if (fpu == &current->thread.fpu) {
+		if (fpu->initialized) {
+			/* Ignore delayed exceptions from user space */
+			asm volatile("1: fwait\n"
+				     "2:\n"
+				     _ASM_EXTABLE(1b, 2b));
+			fpregs_deactivate(fpu);
+		}
 	}
 
-	fpu->fpstate_active = 0;
+	fpu->initialized = 0;
 
 	trace_x86_fpu_dropped(fpu);
 
@@ -462,9 +391,11 @@
 	 * Make sure fpstate is cleared and initialized.
 	 */
 	if (static_cpu_has(X86_FEATURE_FPU)) {
-		fpu__activate_curr(fpu);
+		preempt_disable();
+		fpu__initialize(fpu);
 		user_fpu_begin();
 		copy_init_fpstate_to_fpregs();
+		preempt_enable();
 	}
 }
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index d5d44c4..7affb7e 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -240,7 +240,7 @@
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
-	WARN_ON_FPU(current->thread.fpu.fpstate_active);
+	WARN_ON_FPU(current->thread.fpu.initialized);
 }
 
 /*
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index b188b16..3ea1513 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -16,14 +16,14 @@
 {
 	struct fpu *target_fpu = &target->thread.fpu;
 
-	return target_fpu->fpstate_active ? regset->n : 0;
+	return target_fpu->initialized ? regset->n : 0;
 }
 
 int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
 	struct fpu *target_fpu = &target->thread.fpu;
 
-	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active)
+	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized)
 		return regset->n;
 	else
 		return 0;
@@ -38,7 +38,7 @@
 	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
-	fpu__activate_fpstate_read(fpu);
+	fpu__prepare_read(fpu);
 	fpstate_sanitize_xstate(fpu);
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
@@ -55,7 +55,7 @@
 	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
-	fpu__activate_fpstate_write(fpu);
+	fpu__prepare_write(fpu);
 	fpstate_sanitize_xstate(fpu);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
@@ -89,10 +89,13 @@
 
 	xsave = &fpu->state.xsave;
 
-	fpu__activate_fpstate_read(fpu);
+	fpu__prepare_read(fpu);
 
 	if (using_compacted_format()) {
-		ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave);
+		if (kbuf)
+			ret = copy_xstate_to_kernel(kbuf, xsave, pos, count);
+		else
+			ret = copy_xstate_to_user(ubuf, xsave, pos, count);
 	} else {
 		fpstate_sanitize_xstate(fpu);
 		/*
@@ -129,12 +132,23 @@
 
 	xsave = &fpu->state.xsave;
 
-	fpu__activate_fpstate_write(fpu);
+	fpu__prepare_write(fpu);
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		ret = copyin_to_xsaves(kbuf, ubuf, xsave);
-	else
+	if (using_compacted_format()) {
+		if (kbuf)
+			ret = copy_kernel_to_xstate(xsave, kbuf);
+		else
+			ret = copy_user_to_xstate(xsave, ubuf);
+	} else {
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+		if (!ret)
+			ret = validate_xstate_header(&xsave->header);
+	}
+
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	xsave->i387.mxcsr &= mxcsr_feature_mask;
 
 	/*
 	 * In case of failure, mark all states as init:
@@ -142,16 +156,6 @@
 	if (ret)
 		fpstate_init(&fpu->state);
 
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	xsave->i387.mxcsr &= mxcsr_feature_mask;
-	xsave->header.xfeatures &= xfeatures_mask;
-	/*
-	 * These bits must be zero.
-	 */
-	memset(&xsave->header.reserved, 0, 48);
-
 	return ret;
 }
 
@@ -299,7 +303,7 @@
 	struct fpu *fpu = &target->thread.fpu;
 	struct user_i387_ia32_struct env;
 
-	fpu__activate_fpstate_read(fpu);
+	fpu__prepare_read(fpu);
 
 	if (!boot_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
@@ -329,7 +333,7 @@
 	struct user_i387_ia32_struct env;
 	int ret;
 
-	fpu__activate_fpstate_write(fpu);
+	fpu__prepare_write(fpu);
 	fpstate_sanitize_xstate(fpu);
 
 	if (!boot_cpu_has(X86_FEATURE_FPU))
@@ -369,7 +373,7 @@
 	struct fpu *fpu = &tsk->thread.fpu;
 	int fpvalid;
 
-	fpvalid = fpu->fpstate_active;
+	fpvalid = fpu->initialized;
 	if (fpvalid)
 		fpvalid = !fpregs_get(tsk, NULL,
 				      0, sizeof(struct user_i387_ia32_struct),
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 83c23c2..fb639e7 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -155,7 +155,8 @@
  */
 int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 {
-	struct xregs_state *xsave = &current->thread.fpu.state.xsave;
+	struct fpu *fpu = &current->thread.fpu;
+	struct xregs_state *xsave = &fpu->state.xsave;
 	struct task_struct *tsk = current;
 	int ia32_fxstate = (buf != buf_fx);
 
@@ -170,13 +171,13 @@
 			sizeof(struct user_i387_ia32_struct), NULL,
 			(struct _fpstate_32 __user *) buf) ? -1 : 1;
 
-	if (fpregs_active() || using_compacted_format()) {
+	if (fpu->initialized || using_compacted_format()) {
 		/* Save the live register state to the user directly. */
 		if (copy_fpregs_to_sigframe(buf_fx))
 			return -1;
 		/* Update the thread's fxstate to save the fsave header. */
 		if (ia32_fxstate)
-			copy_fxregs_to_kernel(&tsk->thread.fpu);
+			copy_fxregs_to_kernel(fpu);
 	} else {
 		/*
 		 * It is a *bug* if kernel uses compacted-format for xsave
@@ -189,7 +190,7 @@
 			return -1;
 		}
 
-		fpstate_sanitize_xstate(&tsk->thread.fpu);
+		fpstate_sanitize_xstate(fpu);
 		if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
 			return -1;
 	}
@@ -213,8 +214,11 @@
 	struct xstate_header *header = &xsave->header;
 
 	if (use_xsave()) {
-		/* These bits must be zero. */
-		memset(header->reserved, 0, 48);
+		/*
+		 * Note: we don't need to zero the reserved bits in the
+		 * xstate_header here because we either didn't copy them at all,
+		 * or we checked earlier that they aren't set.
+		 */
 
 		/*
 		 * Init the state that is not present in the memory
@@ -223,7 +227,7 @@
 		if (fx_only)
 			header->xfeatures = XFEATURE_MASK_FPSSE;
 		else
-			header->xfeatures &= (xfeatures_mask & xfeatures);
+			header->xfeatures &= xfeatures;
 	}
 
 	if (use_fxsr()) {
@@ -279,7 +283,7 @@
 	if (!access_ok(VERIFY_READ, buf, size))
 		return -EACCES;
 
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 	if (!static_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_set(current, NULL,
@@ -307,28 +311,29 @@
 		/*
 		 * For 32-bit frames with fxstate, copy the user state to the
 		 * thread's fpu state, reconstruct fxstate from the fsave
-		 * header. Sanitize the copied state etc.
+		 * header. Validate and sanitize the copied state.
 		 */
 		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 
 		/*
-		 * Drop the current fpu which clears fpu->fpstate_active. This ensures
+		 * Drop the current fpu which clears fpu->initialized. This ensures
 		 * that any context-switch during the copy of the new state,
 		 * avoids the intermediate state from getting restored/saved.
 		 * Thus avoiding the new restored state from getting corrupted.
 		 * We will be ready to restore/save the state only after
-		 * fpu->fpstate_active is again set.
+		 * fpu->initialized is again set.
 		 */
 		fpu__drop(fpu);
 
 		if (using_compacted_format()) {
-			err = copyin_to_xsaves(NULL, buf_fx,
-					       &fpu->state.xsave);
+			err = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
 		} else {
-			err = __copy_from_user(&fpu->state.xsave,
-					       buf_fx, state_size);
+			err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
+
+			if (!err && state_size > offsetof(struct xregs_state, header))
+				err = validate_xstate_header(&fpu->state.xsave.header);
 		}
 
 		if (err || __copy_from_user(&env, buf, sizeof(env))) {
@@ -339,7 +344,7 @@
 			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
 		}
 
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 		preempt_disable();
 		fpu__restore(fpu);
 		preempt_enable();
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c24ac1e..f1d5476 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -483,6 +483,30 @@
 	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
 
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+int validate_xstate_header(const struct xstate_header *hdr)
+{
+	/* No unknown or supervisor features may be set */
+	if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR))
+		return -EINVAL;
+
+	/* Userspace must use the uncompacted format */
+	if (hdr->xcomp_bv)
+		return -EINVAL;
+
+	/*
+	 * If 'reserved' is shrunken to add a new field, make sure to validate
+	 * that new field here!
+	 */
+	BUILD_BUG_ON(sizeof(hdr->reserved) != 48);
+
+	/* No reserved bits may be set */
+	if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved)))
+		return -EINVAL;
+
+	return 0;
+}
+
 static void __xstate_dump_leaves(void)
 {
 	int i;
@@ -867,7 +891,7 @@
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (!fpu->fpstate_active)
+	if (!fpu->initialized)
 		return NULL;
 	/*
 	 * fpu__save() takes the CPU's xstate registers
@@ -921,47 +945,54 @@
 #endif /* ! CONFIG_ARCH_HAS_PKEYS */
 
 /*
+ * Weird legacy quirk: SSE and YMM states store information in the
+ * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP
+ * area is marked as unused in the xfeatures header, we need to copy
+ * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use.
+ */
+static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
+{
+	if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM)))
+		return false;
+
+	if (xfeatures & XFEATURE_MASK_FP)
+		return false;
+
+	return true;
+}
+
+/*
  * This is similar to user_regset_copyout(), but will not add offset to
  * the source data pointer or increment pos, count, kbuf, and ubuf.
  */
-static inline int xstate_copyout(unsigned int pos, unsigned int count,
-				 void *kbuf, void __user *ubuf,
-				 const void *data, const int start_pos,
-				 const int end_pos)
+static inline void
+__copy_xstate_to_kernel(void *kbuf, const void *data,
+			unsigned int offset, unsigned int size, unsigned int size_total)
 {
-	if ((count == 0) || (pos < start_pos))
-		return 0;
+	if (offset < size_total) {
+		unsigned int copy = min(size, size_total - offset);
 
-	if (end_pos < 0 || pos < end_pos) {
-		unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos));
-
-		if (kbuf) {
-			memcpy(kbuf + pos, data, copy);
-		} else {
-			if (__copy_to_user(ubuf + pos, data, copy))
-				return -EFAULT;
-		}
+		memcpy(kbuf + offset, data, copy);
 	}
-	return 0;
 }
 
 /*
  * Convert from kernel XSAVES compacted format to standard format and copy
- * to a ptrace buffer. It supports partial copy but pos always starts from
- * zero. This is called from xstateregs_get() and there we check the CPU
- * has XSAVES.
+ * to a kernel-space ptrace buffer.
+ *
+ * It supports partial copy but pos always starts from zero. This is called
+ * from xstateregs_get() and there we check the CPU has XSAVES.
  */
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
-			void __user *ubuf, struct xregs_state *xsave)
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
 {
 	unsigned int offset, size;
-	int ret, i;
 	struct xstate_header header;
+	int i;
 
 	/*
 	 * Currently copy_regset_to_user() starts from pos 0:
 	 */
-	if (unlikely(pos != 0))
+	if (unlikely(offset_start != 0))
 		return -EFAULT;
 
 	/*
@@ -977,8 +1008,91 @@
 	offset = offsetof(struct xregs_state, header);
 	size = sizeof(header);
 
-	ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count);
+	__copy_xstate_to_kernel(kbuf, &header, offset, size, size_total);
 
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		/*
+		 * Copy only in-use xstates:
+		 */
+		if ((header.xfeatures >> i) & 1) {
+			void *src = __raw_xsave_addr(xsave, 1 << i);
+
+			offset = xstate_offsets[i];
+			size = xstate_sizes[i];
+
+			/* The next component has to fit fully into the output buffer: */
+			if (offset + size > size_total)
+				break;
+
+			__copy_xstate_to_kernel(kbuf, src, offset, size, size_total);
+		}
+
+	}
+
+	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		__copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total);
+	}
+
+	/*
+	 * Fill xsave->i387.sw_reserved value for ptrace frame:
+	 */
+	offset = offsetof(struct fxregs_state, sw_reserved);
+	size = sizeof(xstate_fx_sw_bytes);
+
+	__copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total);
+
+	return 0;
+}
+
+static inline int
+__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total)
+{
+	if (!size)
+		return 0;
+
+	if (offset < size_total) {
+		unsigned int copy = min(size, size_total - offset);
+
+		if (__copy_to_user(ubuf + offset, data, copy))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+/*
+ * Convert from kernel XSAVES compacted format to standard format and copy
+ * to a user-space buffer. It supports partial copy but pos always starts from
+ * zero. This is called from xstateregs_get() and there we check the CPU
+ * has XSAVES.
+ */
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
+{
+	unsigned int offset, size;
+	int ret, i;
+	struct xstate_header header;
+
+	/*
+	 * Currently copy_regset_to_user() starts from pos 0:
+	 */
+	if (unlikely(offset_start != 0))
+		return -EFAULT;
+
+	/*
+	 * The destination is a ptrace buffer; we put in only user xstates:
+	 */
+	memset(&header, 0, sizeof(header));
+	header.xfeatures = xsave->header.xfeatures;
+	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+
+	/*
+	 * Copy xregs_state->header:
+	 */
+	offset = offsetof(struct xregs_state, header);
+	size = sizeof(header);
+
+	ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total);
 	if (ret)
 		return ret;
 
@@ -992,25 +1106,30 @@
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
 
-			ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count);
+			/* The next component has to fit fully into the output buffer: */
+			if (offset + size > size_total)
+				break;
 
+			ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total);
 			if (ret)
 				return ret;
-
-			if (offset + size >= count)
-				break;
 		}
 
 	}
 
+	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		__copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total);
+	}
+
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
 	 */
 	offset = offsetof(struct fxregs_state, sw_reserved);
 	size = sizeof(xstate_fx_sw_bytes);
 
-	ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count);
-
+	ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total);
 	if (ret)
 		return ret;
 
@@ -1018,55 +1137,42 @@
 }
 
 /*
- * Convert from a ptrace standard-format buffer to kernel XSAVES format
- * and copy to the target thread. This is called from xstateregs_set() and
- * there we check the CPU has XSAVES and a whole standard-sized buffer
- * exists.
+ * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format
+ * and copy to the target thread. This is called from xstateregs_set().
  */
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
-		     struct xregs_state *xsave)
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
 {
 	unsigned int offset, size;
 	int i;
-	u64 xfeatures;
-	u64 allowed_features;
+	struct xstate_header hdr;
 
 	offset = offsetof(struct xregs_state, header);
-	size = sizeof(xfeatures);
+	size = sizeof(hdr);
 
-	if (kbuf) {
-		memcpy(&xfeatures, kbuf + offset, size);
-	} else {
-		if (__copy_from_user(&xfeatures, ubuf + offset, size))
-			return -EFAULT;
-	}
+	memcpy(&hdr, kbuf + offset, size);
 
-	/*
-	 * Reject if the user sets any disabled or supervisor features:
-	 */
-	allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR;
-
-	if (xfeatures & ~allowed_features)
+	if (validate_xstate_header(&hdr))
 		return -EINVAL;
 
 	for (i = 0; i < XFEATURE_MAX; i++) {
 		u64 mask = ((u64)1 << i);
 
-		if (xfeatures & mask) {
+		if (hdr.xfeatures & mask) {
 			void *dst = __raw_xsave_addr(xsave, 1 << i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
 
-			if (kbuf) {
-				memcpy(dst, kbuf + offset, size);
-			} else {
-				if (__copy_from_user(dst, ubuf + offset, size))
-					return -EFAULT;
-			}
+			memcpy(dst, kbuf + offset, size);
 		}
 	}
 
+	if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		memcpy(&xsave->i387.mxcsr, kbuf + offset, size);
+	}
+
 	/*
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
@@ -1076,7 +1182,63 @@
 	/*
 	 * Add back in the features that came in from userspace:
 	 */
-	xsave->header.xfeatures |= xfeatures;
+	xsave->header.xfeatures |= hdr.xfeatures;
+
+	return 0;
+}
+
+/*
+ * Convert from a ptrace or sigreturn standard-format user-space buffer to
+ * kernel XSAVES format and copy to the target thread. This is called from
+ * xstateregs_set(), as well as potentially from the sigreturn() and
+ * rt_sigreturn() system calls.
+ */
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
+{
+	unsigned int offset, size;
+	int i;
+	struct xstate_header hdr;
+
+	offset = offsetof(struct xregs_state, header);
+	size = sizeof(hdr);
+
+	if (__copy_from_user(&hdr, ubuf + offset, size))
+		return -EFAULT;
+
+	if (validate_xstate_header(&hdr))
+		return -EINVAL;
+
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		u64 mask = ((u64)1 << i);
+
+		if (hdr.xfeatures & mask) {
+			void *dst = __raw_xsave_addr(xsave, 1 << i);
+
+			offset = xstate_offsets[i];
+			size = xstate_sizes[i];
+
+			if (__copy_from_user(dst, ubuf + offset, size))
+				return -EFAULT;
+		}
+	}
+
+	if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size))
+			return -EFAULT;
+	}
+
+	/*
+	 * The state that came in from userspace was user-state only.
+	 * Mask all the user states out of 'xfeatures':
+	 */
+	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+
+	/*
+	 * Add back in the features that came in from userspace:
+	 */
+	xsave->header.xfeatures |= hdr.xfeatures;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 1f38d9a..d4eb450 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -64,7 +64,7 @@
 
 static inline void *current_stack(void)
 {
-	return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
@@ -88,7 +88,7 @@
 
 	/* Save the next esp at the bottom of the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -139,7 +139,7 @@
 
 	/* Push the previous esp onto the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	call_on_stack(__do_softirq, isp);
 }
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index 4b0592c..8c1cc08 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -299,7 +299,7 @@
 	return 0;
 
 out_clean_nodes:
-	for (j = i - 1; j > 0; j--)
+	for (j = i - 1; j >= 0; j--)
 		cleanup_setup_data_node(*(kobjp + j));
 	kfree(kobjp);
 out_setup_data_kobj:
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index aa60a08..8bb9594 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -117,7 +117,11 @@
 	return NULL;
 }
 
-void kvm_async_pf_task_wait(u32 token)
+/*
+ * @interrupt_kernel: Is this called from a routine which interrupts the kernel
+ * 		      (other than user space)?
+ */
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
 {
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
@@ -140,7 +144,10 @@
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.halted = is_idle_task(current) || preempt_count() > 1;
+	n.halted = is_idle_task(current) ||
+		   (IS_ENABLED(CONFIG_PREEMPT_COUNT)
+		    ? preempt_count() > 1 || rcu_preempt_depth()
+		    : interrupt_kernel);
 	init_swait_queue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	raw_spin_unlock(&b->lock);
@@ -268,7 +275,7 @@
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
 		prev_state = exception_enter();
-		kvm_async_pf_task_wait((u32)read_cr2());
+		kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs));
 		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index e044423..4e188fd 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -263,7 +263,7 @@
 		sp = (unsigned long) ka->sa.sa_restorer;
 	}
 
-	if (fpu->fpstate_active) {
+	if (fpu->initialized) {
 		sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
 					  &buf_fx, &math_size);
 		*fpstate = (void __user *)sp;
@@ -279,7 +279,7 @@
 		return (void __user *)-1L;
 
 	/* save i387 and extended state */
-	if (fpu->fpstate_active &&
+	if (fpu->initialized &&
 	    copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
 		return (void __user *)-1L;
 
@@ -755,7 +755,7 @@
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		if (fpu->fpstate_active)
+		if (fpu->initialized)
 			fpu__clear(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0854ff1..ad59edd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -232,12 +232,6 @@
 	 */
 	if (boot_cpu_has(X86_FEATURE_PCID))
 		__write_cr4(__read_cr4() | X86_CR4_PCIDE);
-	cpu_init();
-	x86_cpuinit.early_percpu_clock_init();
-	preempt_disable();
-	smp_callin();
-
-	enable_start_cpu0 = 0;
 
 #ifdef CONFIG_X86_32
 	/* switch away from the initial page table */
@@ -245,6 +239,13 @@
 	__flush_tlb_all();
 #endif
 
+	cpu_init();
+	x86_cpuinit.early_percpu_clock_init();
+	preempt_disable();
+	smp_callin();
+
+	enable_start_cpu0 = 0;
+
 	/* otherwise gcc will move up smp_processor_id before the cpu_init */
 	barrier();
 	/*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 34ea365..67db4f4 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -142,7 +142,7 @@
 	 * from double_fault.
 	 */
 	BUG_ON((unsigned long)(current_top_of_stack() -
-			       current_stack_pointer()) >= THREAD_SIZE);
+			       current_stack_pointer) >= THREAD_SIZE);
 
 	preempt_enable_no_resched();
 }
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3ea6244..3c48bc8 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,6 +23,7 @@
 	depends on HIGH_RES_TIMERS
 	# for TASKSTATS/TASK_DELAY_ACCT:
 	depends on NET && MULTIUSER
+	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 16bf665..d90cdc7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -425,8 +425,10 @@
 	#op " %al \n\t" \
 	FOP_RET
 
-asm(".global kvm_fastop_exception \n"
-    "kvm_fastop_exception: xor %esi, %esi; ret");
+asm(".pushsection .fixup, \"ax\"\n"
+    ".global kvm_fastop_exception \n"
+    "kvm_fastop_exception: xor %esi, %esi; ret\n"
+    ".popsection");
 
 FOP_START(setcc)
 FOP_SETCC(seto)
@@ -4102,10 +4104,12 @@
 		ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
 		if (efer & EFER_LMA) {
 			u64 maxphyaddr;
-			u32 eax = 0x80000008;
+			u32 eax, ebx, ecx, edx;
 
-			if (ctxt->ops->get_cpuid(ctxt, &eax, NULL, NULL,
-						 NULL, false))
+			eax = 0x80000008;
+			ecx = 0;
+			if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx,
+						 &edx, false))
 				maxphyaddr = eax & 0xff;
 			else
 				maxphyaddr = 36;
@@ -5296,7 +5300,6 @@
 
 static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
 {
-	register void *__sp asm(_ASM_SP);
 	ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
 
 	if (!(ctxt->d & ByteOp))
@@ -5304,7 +5307,7 @@
 
 	asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
 	    : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
-	      [fastop]"+S"(fop), "+r"(__sp)
+	      [fastop]"+S"(fop), ASM_CALL_CONSTRAINT
 	    : "c"(ctxt->src2.val));
 
 	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eca30c1..106d4a0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3837,7 +3837,7 @@
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		vcpu->arch.apf.host_apf_reason = 0;
 		local_irq_disable();
-		kvm_async_pf_task_wait(fault_address);
+		kvm_async_pf_task_wait(fault_address, 0);
 		local_irq_enable();
 		break;
 	case KVM_PV_REASON_PAGE_READY:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 06c0c6d..a2b804e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -200,6 +200,8 @@
 	int cpu;
 	bool launched;
 	bool nmi_known_unmasked;
+	unsigned long vmcs_host_cr3;	/* May not match real cr3 */
+	unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	struct list_head loaded_vmcss_on_cpu_link;
 };
 
@@ -600,8 +602,6 @@
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
-		unsigned long vmcs_host_cr3;	/* May not match real cr3 */
-		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
 		int vm86_active;
@@ -2202,46 +2202,44 @@
 	struct pi_desc old, new;
 	unsigned int dest;
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	/*
+	 * In case of hot-plug or hot-unplug, we may have to undo
+	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
+	 * always keep PI.NDST up to date for simplicity: it makes the
+	 * code easier, and CPU migration is not a fast path.
+	 */
+	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
 		return;
 
+	/*
+	 * First handle the simple case where no cmpxchg is necessary; just
+	 * allow posting non-urgent interrupts.
+	 *
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+	 * expects the VCPU to be on the blocked_vcpu_list that matches
+	 * PI.NDST.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+	    vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
+		return;
+	}
+
+	/* The full case.  */
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
-		 * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
-		 * are two possible cases:
-		 * 1. After running 'pre_block', context switch
-		 *    happened. For this case, 'sn' was set in
-		 *    vmx_vcpu_put(), so we need to clear it here.
-		 * 2. After running 'pre_block', we were blocked,
-		 *    and woken up by some other guy. For this case,
-		 *    we don't need to do anything, 'pi_post_block'
-		 *    will do everything for us. However, we cannot
-		 *    check whether it is case #1 or case #2 here
-		 *    (maybe, not needed), so we also clear sn here,
-		 *    I think it is not a big deal.
-		 */
-		if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
-			if (vcpu->cpu != cpu) {
-				dest = cpu_physical_id(cpu);
+		dest = cpu_physical_id(cpu);
 
-				if (x2apic_enabled())
-					new.ndst = dest;
-				else
-					new.ndst = (dest << 8) & 0xFF00;
-			}
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
 
-			/* set 'NV' to 'notification vector' */
-			new.nv = POSTED_INTR_VECTOR;
-		}
-
-		/* Allow posting non-urgent interrupts */
 		new.sn = 0;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 }
 
 static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
@@ -5077,21 +5075,30 @@
 	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
 
 	if (vcpu->mode == IN_GUEST_MODE) {
-		struct vcpu_vmx *vmx = to_vmx(vcpu);
-
 		/*
-		 * Currently, we don't support urgent interrupt,
-		 * all interrupts are recognized as non-urgent
-		 * interrupt, so we cannot post interrupts when
-		 * 'SN' is set.
+		 * The vector of interrupt to be delivered to vcpu had
+		 * been set in PIR before this function.
 		 *
-		 * If the vcpu is in guest mode, it means it is
-		 * running instead of being scheduled out and
-		 * waiting in the run queue, and that's the only
-		 * case when 'SN' is set currently, warning if
-		 * 'SN' is set.
+		 * Following cases will be reached in this block, and
+		 * we always send a notification event in all cases as
+		 * explained below.
+		 *
+		 * Case 1: vcpu keeps in non-root mode. Sending a
+		 * notification event posts the interrupt to vcpu.
+		 *
+		 * Case 2: vcpu exits to root mode and is still
+		 * runnable. PIR will be synced to vIRR before the
+		 * next vcpu entry. Sending a notification event in
+		 * this case has no effect, as vcpu is not in root
+		 * mode.
+		 *
+		 * Case 3: vcpu exits to root mode and is blocked.
+		 * vcpu_block() has already synced PIR to vIRR and
+		 * never blocks vcpu if vIRR is not cleared. Therefore,
+		 * a blocked vcpu here does not wait for any requested
+		 * interrupts in PIR, and sending a notification event
+		 * which has no effect is safe here.
 		 */
-		WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
 
 		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
 		return true;
@@ -5169,12 +5176,12 @@
 	 */
 	cr3 = __read_cr3();
 	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
-	vmx->host_state.vmcs_host_cr3 = cr3;
+	vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
 	cr4 = cr4_read_shadow();
 	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
-	vmx->host_state.vmcs_host_cr4 = cr4;
+	vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
@@ -9036,7 +9043,6 @@
 static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 {
 	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-	register void *__sp asm(_ASM_SP);
 
 	if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
 			== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
@@ -9065,7 +9071,7 @@
 #ifdef CONFIG_X86_64
 			[sp]"=&r"(tmp),
 #endif
-			"+r"(__sp)
+			ASM_CALL_CONSTRAINT
 			:
 			[entry]"r"(entry),
 			[ss]"i"(__KERNEL_DS),
@@ -9265,15 +9271,15 @@
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
 	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+	if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
 		vmcs_writel(HOST_CR3, cr3);
-		vmx->host_state.vmcs_host_cr3 = cr3;
+		vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 	}
 
 	cr4 = cr4_read_shadow();
-	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+	if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
-		vmx->host_state.vmcs_host_cr4 = cr4;
+		vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 	}
 
 	/* When single-stepping over STI and MOV SS, we must clear the
@@ -9583,6 +9589,13 @@
 
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
+	/*
+	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+	 * or POSTED_INTR_WAKEUP_VECTOR.
+	 */
+	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+	vmx->pi_desc.sn = 1;
+
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -9831,7 +9844,8 @@
 
 	WARN_ON(!is_guest_mode(vcpu));
 
-	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
+		!to_vmx(vcpu)->nested.nested_run_pending) {
 		vmcs12->vm_exit_intr_error_code = fault->error_code;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
@@ -11696,6 +11710,37 @@
 	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
 }
 
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	do {
+		old.control = new.control = pi_desc->control;
+		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+		     "Wakeup handler not enabled while the VCPU is blocked\n");
+
+		dest = cpu_physical_id(vcpu->cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'notification vector' */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_del(&vcpu->blocked_vcpu_list);
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		vcpu->pre_pcpu = -1;
+	}
+}
+
 /*
  * This routine does the following things for vCPU which is going
  * to be blocked if VT-d PI is enabled.
@@ -11711,7 +11756,6 @@
  */
 static int pi_pre_block(struct kvm_vcpu *vcpu)
 {
-	unsigned long flags;
 	unsigned int dest;
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -11721,34 +11765,20 @@
 		!kvm_vcpu_apicv_active(vcpu))
 		return 0;
 
-	vcpu->pre_pcpu = vcpu->cpu;
-	spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
-			  vcpu->pre_pcpu), flags);
-	list_add_tail(&vcpu->blocked_vcpu_list,
-		      &per_cpu(blocked_vcpu_on_cpu,
-		      vcpu->pre_pcpu));
-	spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
-			       vcpu->pre_pcpu), flags);
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+		vcpu->pre_pcpu = vcpu->cpu;
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_add_tail(&vcpu->blocked_vcpu_list,
+			      &per_cpu(blocked_vcpu_on_cpu,
+				       vcpu->pre_pcpu));
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+	}
 
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
-		 * We should not block the vCPU if
-		 * an interrupt is posted for it.
-		 */
-		if (pi_test_on(pi_desc) == 1) {
-			spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
-					  vcpu->pre_pcpu), flags);
-			list_del(&vcpu->blocked_vcpu_list);
-			spin_unlock_irqrestore(
-					&per_cpu(blocked_vcpu_on_cpu_lock,
-					vcpu->pre_pcpu), flags);
-			vcpu->pre_pcpu = -1;
-
-			return 1;
-		}
-
 		WARN((pi_desc->sn == 1),
 		     "Warning: SN field of posted-interrupts "
 		     "is set before blocking\n");
@@ -11770,10 +11800,15 @@
 
 		/* set 'NV' to 'wakeup vector' */
 		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 
-	return 0;
+	/* We should not block the vCPU if an interrupt is posted for it.  */
+	if (pi_test_on(pi_desc) == 1)
+		__pi_post_block(vcpu);
+
+	local_irq_enable();
+	return (vcpu->pre_pcpu == -1);
 }
 
 static int vmx_pre_block(struct kvm_vcpu *vcpu)
@@ -11789,44 +11824,13 @@
 
 static void pi_post_block(struct kvm_vcpu *vcpu)
 {
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-	unsigned long flags;
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (vcpu->pre_pcpu == -1)
 		return;
 
-	do {
-		old.control = new.control = pi_desc->control;
-
-		dest = cpu_physical_id(vcpu->cpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* Allow posting non-urgent interrupts */
-		new.sn = 0;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
-
-	if(vcpu->pre_pcpu != -1) {
-		spin_lock_irqsave(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		list_del(&vcpu->blocked_vcpu_list);
-		spin_unlock_irqrestore(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		vcpu->pre_pcpu = -1;
-	}
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	__pi_post_block(vcpu);
+	local_irq_enable();
 }
 
 static void vmx_post_block(struct kvm_vcpu *vcpu)
@@ -11911,12 +11915,8 @@
 
 		if (set)
 			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else {
-			/* suppress notification event before unposting */
-			pi_set_sn(vcpu_to_pi_desc(vcpu));
+		else
 			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			pi_clear_sn(vcpu_to_pi_desc(vcpu));
-		}
 
 		if (ret < 0) {
 			printk(KERN_INFO "%s: failed to update PI IRTE\n",
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cd17b7d..03869eb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7225,7 +7225,7 @@
 	int r;
 	sigset_t sigsaved;
 
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index d4a7df2..220638a 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -114,7 +114,7 @@
 	struct desc_struct code_descriptor;
 	struct fpu *fpu = &current->thread.fpu;
 
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index c076f71..c3521e2 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -2,6 +2,7 @@
 #include <linux/uaccess.h>
 #include <linux/sched/debug.h>
 
+#include <asm/fpu/internal.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
 
@@ -78,6 +79,29 @@
 }
 EXPORT_SYMBOL_GPL(ex_handler_refcount);
 
+/*
+ * Handler for when we fail to restore a task's FPU state.  We should never get
+ * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * should always be valid.  However, past bugs have allowed userspace to set
+ * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
+ * These caused XRSTOR to fail when switching to the task, leaking the FPU
+ * registers of the task previously executing on the CPU.  Mitigate this class
+ * of vulnerability by restoring from the initial state (essentially, zeroing
+ * out all the FPU registers) if we can't restore from the task's FPU state.
+ */
+bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+			  struct pt_regs *regs, int trapnr)
+{
+	regs->ip = ex_fixup_addr(fixup);
+
+	WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
+		  (void *)instruction_pointer(regs));
+
+	__copy_kernel_to_fpregs(&init_fpstate, -1);
+	return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_fprestore);
+
 bool ex_handler_ext(const struct exception_table_entry *fixup,
 		   struct pt_regs *regs, int trapnr)
 {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b836a72..e2baeaa 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -192,8 +192,7 @@
  * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
  *	     faulted on a pte with its pkey=4.
  */
-static void fill_sig_info_pkey(int si_code, siginfo_t *info,
-		struct vm_area_struct *vma)
+static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
 {
 	/* This is effectively an #ifdef */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
@@ -209,7 +208,7 @@
 	 * valid VMA, so we should never reach this without a
 	 * valid VMA.
 	 */
-	if (!vma) {
+	if (!pkey) {
 		WARN_ONCE(1, "PKU fault with no VMA passed in");
 		info->si_pkey = 0;
 		return;
@@ -219,13 +218,12 @@
 	 * absolutely guranteed to be 100% accurate because of
 	 * the race explained above.
 	 */
-	info->si_pkey = vma_pkey(vma);
+	info->si_pkey = *pkey;
 }
 
 static void
 force_sig_info_fault(int si_signo, int si_code, unsigned long address,
-		     struct task_struct *tsk, struct vm_area_struct *vma,
-		     int fault)
+		     struct task_struct *tsk, u32 *pkey, int fault)
 {
 	unsigned lsb = 0;
 	siginfo_t info;
@@ -240,7 +238,7 @@
 		lsb = PAGE_SHIFT;
 	info.si_addr_lsb = lsb;
 
-	fill_sig_info_pkey(si_code, &info, vma);
+	fill_sig_info_pkey(si_code, &info, pkey);
 
 	force_sig_info(si_signo, &info, tsk);
 }
@@ -762,8 +760,6 @@
 	struct task_struct *tsk = current;
 	unsigned long flags;
 	int sig;
-	/* No context means no VMA to pass down */
-	struct vm_area_struct *vma = NULL;
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs, X86_TRAP_PF)) {
@@ -788,7 +784,7 @@
 
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address,
-					     tsk, vma, 0);
+					     tsk, NULL, 0);
 		}
 
 		/*
@@ -806,7 +802,6 @@
 	if (is_vmalloc_addr((void *)address) &&
 	    (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
 	     address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
-		register void *__sp asm("rsp");
 		unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
 		/*
 		 * We're likely to be running with very little stack space
@@ -821,7 +816,7 @@
 		asm volatile ("movq %[stack], %%rsp\n\t"
 			      "call handle_stack_overflow\n\t"
 			      "1: jmp 1b"
-			      : "+r" (__sp)
+			      : ASM_CALL_CONSTRAINT
 			      : "D" ("kernel stack overflow (page fault)"),
 				"S" (regs), "d" (address),
 				[stack] "rm" (stack));
@@ -897,8 +892,7 @@
 
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		       unsigned long address, struct vm_area_struct *vma,
-		       int si_code)
+		       unsigned long address, u32 *pkey, int si_code)
 {
 	struct task_struct *tsk = current;
 
@@ -946,7 +940,7 @@
 		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_nr	= X86_TRAP_PF;
 
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0);
+		force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);
 
 		return;
 	}
@@ -959,9 +953,9 @@
 
 static noinline void
 bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		     unsigned long address, struct vm_area_struct *vma)
+		     unsigned long address, u32 *pkey)
 {
-	__bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR);
+	__bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
 }
 
 static void
@@ -969,6 +963,10 @@
 	   unsigned long address,  struct vm_area_struct *vma, int si_code)
 {
 	struct mm_struct *mm = current->mm;
+	u32 pkey;
+
+	if (vma)
+		pkey = vma_pkey(vma);
 
 	/*
 	 * Something tried to access memory that isn't in our memory map..
@@ -976,7 +974,8 @@
 	 */
 	up_read(&mm->mmap_sem);
 
-	__bad_area_nosemaphore(regs, error_code, address, vma, si_code);
+	__bad_area_nosemaphore(regs, error_code, address,
+			       (vma) ? &pkey : NULL, si_code);
 }
 
 static noinline void
@@ -1019,7 +1018,7 @@
 
 static void
 do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
-	  struct vm_area_struct *vma, unsigned int fault)
+	  u32 *pkey, unsigned int fault)
 {
 	struct task_struct *tsk = current;
 	int code = BUS_ADRERR;
@@ -1046,13 +1045,12 @@
 		code = BUS_MCEERR_AR;
 	}
 #endif
-	force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault);
+	force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
 }
 
 static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
-	       unsigned long address, struct vm_area_struct *vma,
-	       unsigned int fault)
+	       unsigned long address, u32 *pkey, unsigned int fault)
 {
 	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
 		no_context(regs, error_code, address, 0, 0);
@@ -1076,9 +1074,9 @@
 	} else {
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
-			do_sigbus(regs, error_code, address, vma, fault);
+			do_sigbus(regs, error_code, address, pkey, fault);
 		else if (fault & VM_FAULT_SIGSEGV)
-			bad_area_nosemaphore(regs, error_code, address, vma);
+			bad_area_nosemaphore(regs, error_code, address, pkey);
 		else
 			BUG();
 	}
@@ -1268,6 +1266,7 @@
 	struct mm_struct *mm;
 	int fault, major = 0;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	u32 pkey;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1468,9 +1467,10 @@
 		return;
 	}
 
+	pkey = vma_pkey(vma);
 	up_read(&mm->mmap_sem);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
-		mm_fault_error(regs, error_code, address, vma, fault);
+		mm_fault_error(regs, error_code, address, &pkey, fault);
 		return;
 	}
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 3fcc8e0..16c5f37 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
  */
 
+#define DISABLE_BRANCH_PROFILING
+
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/mm.h>
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index 2dab69a..d7bc0eea 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -18,7 +18,6 @@
 
 #include <asm/cpufeature.h>             /* boot_cpu_has, ...            */
 #include <asm/mmu_context.h>            /* vma_pkey()                   */
-#include <asm/fpu/internal.h>           /* fpregs_active()              */
 
 int __execute_only_pkey(struct mm_struct *mm)
 {
@@ -45,7 +44,7 @@
 	 */
 	preempt_disable();
 	if (!need_to_set_mm_pkey &&
-	    fpregs_active() &&
+	    current->thread.fpu.initialized &&
 	    !__pkru_allows_read(read_pkru(), execute_only_pkey)) {
 		preempt_enable();
 		return execute_only_pkey;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1ab3821..49d9778 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -126,8 +126,7 @@
 	 * isn't free.
 	 */
 #ifdef CONFIG_DEBUG_VM
-	if (WARN_ON_ONCE(__read_cr3() !=
-			 (__sme_pa(real_prev->pgd) | prev_asid))) {
+	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) {
 		/*
 		 * If we were to BUG here, we'd be very likely to kill
 		 * the system so hard that we don't see the call trace.
@@ -172,7 +171,7 @@
 			 */
 			this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen,
 				       next_tlb_gen);
-			write_cr3(__sme_pa(next->pgd) | prev_asid);
+			write_cr3(build_cr3(next, prev_asid));
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
 					TLB_FLUSH_ALL);
 		}
@@ -192,7 +191,7 @@
 			 * mapped in the new pgd, we'll double-fault.  Forcibly
 			 * map it.
 			 */
-			unsigned int index = pgd_index(current_stack_pointer());
+			unsigned int index = pgd_index(current_stack_pointer);
 			pgd_t *pgd = next->pgd + index;
 
 			if (unlikely(pgd_none(*pgd)))
@@ -216,12 +215,12 @@
 		if (need_flush) {
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			write_cr3(__sme_pa(next->pgd) | new_asid);
+			write_cr3(build_cr3(next, new_asid));
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
 					TLB_FLUSH_ALL);
 		} else {
 			/* The new ASID is already up to date. */
-			write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH);
+			write_cr3(build_cr3_noflush(next, new_asid));
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
 		}
 
@@ -265,7 +264,7 @@
 		!(cr4_read_shadow() & X86_CR4_PCIDE));
 
 	/* Force ASID 0 and force a TLB flush. */
-	write_cr3(cr3 & ~CR3_PCID_MASK);
+	write_cr3(build_cr3(mm, 0));
 
 	/* Reinitialize tlbstate. */
 	this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8c95736..0554e8a 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -284,9 +284,9 @@
 	/* if (index >= array->map.max_entries)
 	 *   goto out;
 	 */
-	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
+	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
+	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
 #define OFFSET1 43 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 509f560..71495f1 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1238,21 +1238,16 @@
 	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
 	 * the ramdisk). We continue on, erasing PMD entries that point to page
 	 * tables - do note that they are accessible at this stage via __va.
-	 * For good measure we also round up to the PMD - which means that if
+	 * As Xen is aligning the memory end to a 4MB boundary, for good
+	 * measure we also round up to PMD_SIZE * 2 - which means that if
 	 * anybody is using __ka address to the initial boot-stack - and try
 	 * to use it - they are going to crash. The xen_start_info has been
 	 * taken care of already in xen_setup_kernel_pagetable. */
 	addr = xen_start_info->pt_base;
-	size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+	size = xen_start_info->nr_pt_frames * PAGE_SIZE;
 
-	xen_cleanhighmap(addr, addr + size);
+	xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2));
 	xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
-#ifdef DEBUG
-	/* This is superfluous and is not necessary, but you know what
-	 * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
-	 * anything at this stage. */
-	xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
-#endif
 }
 #endif
 
@@ -2220,7 +2215,7 @@
  * not the first page table in the page table pool.
  * Iterate through the initial page tables to find the real page table base.
  */
-static phys_addr_t xen_find_pt_base(pmd_t *pmd)
+static phys_addr_t __init xen_find_pt_base(pmd_t *pmd)
 {
 	phys_addr_t pt_base, paddr;
 	unsigned pmdidx;
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 30ee8c6..5b0027d 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -208,11 +208,6 @@
 /* Free all resources held by a thread. */
 #define release_thread(thread) do { } while(0)
 
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm)	do { } while(0)
-#define release_segments(mm)	do { } while(0)
-#define forget_segments()	do { } while (0)
-
 extern unsigned long get_wchan(struct task_struct *p);
 
 #define KSTK_EIP(tsk)		(task_pt_regs(tsk)->pc)
diff --git a/block/blk-core.c b/block/blk-core.c
index aebe676..048be4a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -854,6 +854,9 @@
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
 
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	mutex_init(&q->blk_trace_mutex);
+#endif
 	mutex_init(&q->sysfs_lock);
 	spin_lock_init(&q->__queue_lock);
 
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 980e730..de294d7 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -815,10 +815,14 @@
 		goto err;
 
 	/*
-	 * blk_mq_init_hctx() attempted to do this already, but q->debugfs_dir
+	 * blk_mq_init_sched() attempted to do this already, but q->debugfs_dir
 	 * didn't exist yet (because we don't know what to name the directory
 	 * until the queue is registered to a gendisk).
 	 */
+	if (q->elevator && !q->sched_debugfs_dir)
+		blk_mq_debugfs_register_sched(q);
+
+	/* Similarly, blk_mq_init_hctx() couldn't do this previously. */
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx->debugfs_dir && blk_mq_debugfs_register_hctx(q, hctx))
 			goto err;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 0fea76a..17816a0 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1911,11 +1911,11 @@
 
 		tg->disptime = jiffies - 1;
 		throtl_select_dispatch(sq);
-		throtl_schedule_next_dispatch(sq, false);
+		throtl_schedule_next_dispatch(sq, true);
 	}
 	rcu_read_unlock();
 	throtl_select_dispatch(&td->service_queue);
-	throtl_schedule_next_dispatch(&td->service_queue, false);
+	throtl_schedule_next_dispatch(&td->service_queue, true);
 	queue_work(kthrotld_workqueue, &td->dispatch_work);
 }
 
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index c82408c..15d25cc 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -154,7 +154,6 @@
 failjob_rls_rqst_payload:
 	kfree(job->request_payload.sg_list);
 failjob_rls_job:
-	kfree(job);
 	return -ENOMEM;
 }
 
@@ -208,20 +207,34 @@
 	struct bsg_job *job = blk_mq_rq_to_pdu(req);
 	struct scsi_request *sreq = &job->sreq;
 
-	memset(job, 0, sizeof(*job));
+	/* called right after the request is allocated for the request_queue */
 
-	scsi_req_init(sreq);
-	sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
-	sreq->sense = kzalloc(sreq->sense_len, gfp);
+	sreq->sense = kzalloc(SCSI_SENSE_BUFFERSIZE, gfp);
 	if (!sreq->sense)
 		return -ENOMEM;
 
+	return 0;
+}
+
+static void bsg_initialize_rq(struct request *req)
+{
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
+	struct scsi_request *sreq = &job->sreq;
+	void *sense = sreq->sense;
+
+	/* called right before the request is given to the request_queue user */
+
+	memset(job, 0, sizeof(*job));
+
+	scsi_req_init(sreq);
+
+	sreq->sense = sense;
+	sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
+
 	job->req = req;
-	job->reply = sreq->sense;
+	job->reply = sense;
 	job->reply_len = sreq->sense_len;
 	job->dd_data = job + 1;
-
-	return 0;
 }
 
 static void bsg_exit_rq(struct request_queue *q, struct request *req)
@@ -252,6 +265,7 @@
 	q->cmd_size = sizeof(struct bsg_job) + dd_job_size;
 	q->init_rq_fn = bsg_init_rq;
 	q->exit_rq_fn = bsg_exit_rq;
+	q->initialize_rq_fn = bsg_initialize_rq;
 	q->request_fn = bsg_request_fn;
 
 	ret = blk_init_allocated_queue(q);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 86e8fe1..88c555d 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -112,7 +112,7 @@
 		       struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	struct request_queue *q = dev_to_disk(dev)->queue;
+	struct request_queue *q = part_to_disk(p)->queue;
 	unsigned int inflight[2];
 	int cpu;
 
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index ffa9f4c..337cf38 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -619,14 +619,14 @@
 	struct af_alg_ctx *ctx = ask->private;
 	struct af_alg_tsgl *sgl;
 	struct scatterlist *sg;
-	unsigned int i, j;
+	unsigned int i, j = 0;
 
 	while (!list_empty(&ctx->tsgl_list)) {
 		sgl = list_first_entry(&ctx->tsgl_list, struct af_alg_tsgl,
 				       list);
 		sg = sgl->sg;
 
-		for (i = 0, j = 0; i < sgl->cur; i++) {
+		for (i = 0; i < sgl->cur; i++) {
 			size_t plen = min_t(size_t, used, sg[i].length);
 			struct page *page = sg_page(sg + i);
 
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 633a88e..7001839 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1133,10 +1133,10 @@
 {
 	if (!drbg)
 		return;
-	kzfree(drbg->V);
-	drbg->Vbuf = NULL;
-	kzfree(drbg->C);
-	drbg->Cbuf = NULL;
+	kzfree(drbg->Vbuf);
+	drbg->V = NULL;
+	kzfree(drbg->Cbuf);
+	drbg->C = NULL;
 	kzfree(drbg->scratchpadbuf);
 	drbg->scratchpadbuf = NULL;
 	drbg->reseed_ctr = 0;
diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c
index bf22c29..11b113f 100644
--- a/drivers/acpi/acpi_watchdog.c
+++ b/drivers/acpi/acpi_watchdog.c
@@ -66,7 +66,7 @@
 	for (i = 0; i < wdat->entries; i++) {
 		const struct acpi_generic_address *gas;
 		struct resource_entry *rentry;
-		struct resource res;
+		struct resource res = {};
 		bool found;
 
 		gas = &entries[i].register_region;
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 077f9ba..3c3a37b 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -743,17 +743,19 @@
 	}
 	ghes_do_proc(ghes, ghes->estatus);
 
+out:
+	ghes_clear_estatus(ghes);
+
+	if (rc == -ENOENT)
+		return rc;
+
 	/*
 	 * GHESv2 type HEST entries introduce support for error acknowledgment,
 	 * so only acknowledge the error if this support is present.
 	 */
-	if (is_hest_type_generic_v2(ghes)) {
-		rc = ghes_ack_error(ghes->generic_v2);
-		if (rc)
-			return rc;
-	}
-out:
-	ghes_clear_estatus(ghes);
+	if (is_hest_type_generic_v2(ghes))
+		return ghes_ack_error(ghes->generic_v2);
+
 	return rc;
 }
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 9565d57..de56394 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1178,12 +1178,44 @@
 	return ret;
 }
 
+static bool __init iort_enable_acs(struct acpi_iort_node *iort_node)
+{
+	if (iort_node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) {
+		struct acpi_iort_node *parent;
+		struct acpi_iort_id_mapping *map;
+		int i;
+
+		map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, iort_node,
+				   iort_node->mapping_offset);
+
+		for (i = 0; i < iort_node->mapping_count; i++, map++) {
+			if (!map->output_reference)
+				continue;
+
+			parent = ACPI_ADD_PTR(struct acpi_iort_node,
+					iort_table,  map->output_reference);
+			/*
+			 * If we detect a RC->SMMU mapping, make sure
+			 * we enable ACS on the system.
+			 */
+			if ((parent->type == ACPI_IORT_NODE_SMMU) ||
+				(parent->type == ACPI_IORT_NODE_SMMU_V3)) {
+				pci_request_acs();
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
 static void __init iort_init_platform_devices(void)
 {
 	struct acpi_iort_node *iort_node, *iort_end;
 	struct acpi_table_iort *iort;
 	struct fwnode_handle *fwnode;
 	int i, ret;
+	bool acs_enabled = false;
 
 	/*
 	 * iort_table and iort both point to the start of IORT table, but
@@ -1203,6 +1235,9 @@
 			return;
 		}
 
+		if (!acs_enabled)
+			acs_enabled = iort_enable_acs(iort_node);
+
 		if ((iort_node->type == ACPI_IORT_NODE_SMMU) ||
 			(iort_node->type == ACPI_IORT_NODE_SMMU_V3)) {
 
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index c1c2161..3fb8ff5 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -908,11 +908,12 @@
 					    struct fwnode_handle *child)
 {
 	const struct acpi_device *adev = to_acpi_device_node(fwnode);
-	struct acpi_device *child_adev = NULL;
 	const struct list_head *head;
 	struct list_head *next;
 
 	if (!child || is_acpi_device_node(child)) {
+		struct acpi_device *child_adev;
+
 		if (adev)
 			head = &adev->children;
 		else
@@ -922,8 +923,8 @@
 			goto nondev;
 
 		if (child) {
-			child_adev = to_acpi_device_node(child);
-			next = child_adev->node.next;
+			adev = to_acpi_device_node(child);
+			next = adev->node.next;
 			if (next == head) {
 				child = NULL;
 				goto nondev;
@@ -941,8 +942,8 @@
 		const struct acpi_data_node *data = to_acpi_data_node(fwnode);
 		struct acpi_data_node *dn;
 
-		if (child_adev)
-			head = &child_adev->data.subnodes;
+		if (adev)
+			head = &adev->data.subnodes;
 		else if (data)
 			head = &data->data.subnodes;
 		else
@@ -1293,3 +1294,16 @@
 DECLARE_ACPI_FWNODE_OPS(acpi_device_fwnode_ops);
 DECLARE_ACPI_FWNODE_OPS(acpi_data_fwnode_ops);
 const struct fwnode_operations acpi_static_fwnode_ops;
+
+bool is_acpi_device_node(const struct fwnode_handle *fwnode)
+{
+	return !IS_ERR_OR_NULL(fwnode) &&
+		fwnode->ops == &acpi_device_fwnode_ops;
+}
+EXPORT_SYMBOL(is_acpi_device_node);
+
+bool is_acpi_data_node(const struct fwnode_handle *fwnode)
+{
+	return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops;
+}
+EXPORT_SYMBOL(is_acpi_data_node);
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index d055b3f..ab34239 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2217,7 +2217,7 @@
 				       debug_id, (u64)fda->num_fds);
 				continue;
 			}
-			fd_array = (u32 *)(parent_buffer + fda->parent_offset);
+			fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset);
 			for (fd_index = 0; fd_index < fda->num_fds; fd_index++)
 				task_close_fd(proc, fd_array[fd_index]);
 		} break;
@@ -2326,7 +2326,6 @@
 			     (u64)node->ptr);
 		binder_node_unlock(node);
 	} else {
-		int ret;
 		struct binder_ref_data dest_rdata;
 
 		binder_node_unlock(node);
@@ -2442,7 +2441,7 @@
 	 */
 	parent_buffer = parent->buffer -
 		binder_alloc_get_user_buffer_offset(&target_proc->alloc);
-	fd_array = (u32 *)(parent_buffer + fda->parent_offset);
+	fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset);
 	if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) {
 		binder_user_error("%d:%d parent offset not aligned correctly.\n",
 				  proc->pid, thread->pid);
@@ -2508,7 +2507,7 @@
 				  proc->pid, thread->pid);
 		return -EINVAL;
 	}
-	parent_buffer = (u8 *)(parent->buffer -
+	parent_buffer = (u8 *)((uintptr_t)parent->buffer -
 			binder_alloc_get_user_buffer_offset(
 				&target_proc->alloc));
 	*(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer;
@@ -3083,6 +3082,7 @@
 err_dead_proc_or_thread:
 	return_error = BR_DEAD_REPLY;
 	return_error_line = __LINE__;
+	binder_dequeue_work(proc, tcomplete);
 err_translate_failed:
 err_bad_object_type:
 err_bad_offset:
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 8fe1658..064f5e3 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -913,6 +913,7 @@
 	struct binder_alloc *alloc;
 	uintptr_t page_addr;
 	size_t index;
+	struct vm_area_struct *vma;
 
 	alloc = page->alloc;
 	if (!mutex_trylock(&alloc->mutex))
@@ -923,16 +924,22 @@
 
 	index = page - alloc->pages;
 	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
-	if (alloc->vma) {
+	vma = alloc->vma;
+	if (vma) {
 		mm = get_task_mm(alloc->tsk);
 		if (!mm)
 			goto err_get_task_mm_failed;
 		if (!down_write_trylock(&mm->mmap_sem))
 			goto err_down_write_mmap_sem_failed;
+	}
 
+	list_lru_isolate(lru, item);
+	spin_unlock(lock);
+
+	if (vma) {
 		trace_binder_unmap_user_start(alloc, index);
 
-		zap_page_range(alloc->vma,
+		zap_page_range(vma,
 			       page_addr + alloc->user_buffer_offset,
 			       PAGE_SIZE);
 
@@ -950,13 +957,12 @@
 
 	trace_binder_unmap_kernel_end(alloc, index);
 
-	list_lru_isolate(lru, item);
-
+	spin_lock(lock);
 	mutex_unlock(&alloc->mutex);
-	return LRU_REMOVED;
+	return LRU_REMOVED_RETRY;
 
 err_down_write_mmap_sem_failed:
-	mmput(mm);
+	mmput_async(mm);
 err_get_task_mm_failed:
 err_page_already_freed:
 	mutex_unlock(&alloc->mutex);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index cb9b0e9..9f78bb0 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -621,8 +621,11 @@
 static int ahci_pci_reset_controller(struct ata_host *host)
 {
 	struct pci_dev *pdev = to_pci_dev(host->dev);
+	int rc;
 
-	ahci_reset_controller(host);
+	rc = ahci_reset_controller(host);
+	if (rc)
+		return rc;
 
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
 		struct ahci_host_priv *hpriv = host->private_data;
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 8401c3b..b702c20 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -492,6 +492,7 @@
 	{ 0x27DF, 0x152D, 0x0778 },	/* ICH7 on unknown Intel */
 	{ 0x24CA, 0x1025, 0x0061 },	/* ICH4 on ACER Aspire 2023WLMi */
 	{ 0x24CA, 0x1025, 0x003d },	/* ICH4 on ACER TM290 */
+	{ 0x24CA, 0x10CF, 0x11AB },	/* ICH4M on Fujitsu-Siemens Lifebook S6120 */
 	{ 0x266F, 0x1025, 0x0066 },	/* ICH6 on ACER Aspire 1694WLMi */
 	{ 0x2653, 0x1043, 0x82D8 },	/* ICH6M on Asus Eee 701 */
 	{ 0x27df, 0x104d, 0x900e },	/* ICH7 on Sony TZ-90 */
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 1945a8e..ee4c1ec 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -3234,19 +3234,19 @@
 };
 
 #define ENOUGH(v, unit)		(((v)-1)/(unit)+1)
-#define EZ(v, unit)		((v)?ENOUGH(v, unit):0)
+#define EZ(v, unit)		((v)?ENOUGH(((v) * 1000), unit):0)
 
 static void ata_timing_quantize(const struct ata_timing *t, struct ata_timing *q, int T, int UT)
 {
-	q->setup	= EZ(t->setup      * 1000,  T);
-	q->act8b	= EZ(t->act8b      * 1000,  T);
-	q->rec8b	= EZ(t->rec8b      * 1000,  T);
-	q->cyc8b	= EZ(t->cyc8b      * 1000,  T);
-	q->active	= EZ(t->active     * 1000,  T);
-	q->recover	= EZ(t->recover    * 1000,  T);
-	q->dmack_hold	= EZ(t->dmack_hold * 1000,  T);
-	q->cycle	= EZ(t->cycle      * 1000,  T);
-	q->udma		= EZ(t->udma       * 1000, UT);
+	q->setup	= EZ(t->setup,       T);
+	q->act8b	= EZ(t->act8b,       T);
+	q->rec8b	= EZ(t->rec8b,       T);
+	q->cyc8b	= EZ(t->cyc8b,       T);
+	q->active	= EZ(t->active,      T);
+	q->recover	= EZ(t->recover,     T);
+	q->dmack_hold	= EZ(t->dmack_hold,  T);
+	q->cycle	= EZ(t->cycle,       T);
+	q->udma		= EZ(t->udma,       UT);
 }
 
 void ata_timing_merge(const struct ata_timing *a, const struct ata_timing *b,
diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index cfeb049..642afd8 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -647,18 +647,25 @@
 static int charlcd_open(struct inode *inode, struct file *file)
 {
 	struct charlcd_priv *priv = to_priv(the_charlcd);
+	int ret;
 
+	ret = -EBUSY;
 	if (!atomic_dec_and_test(&charlcd_available))
-		return -EBUSY;	/* open only once at a time */
+		goto fail;	/* open only once at a time */
 
+	ret = -EPERM;
 	if (file->f_mode & FMODE_READ)	/* device is write-only */
-		return -EPERM;
+		goto fail;
 
 	if (priv->must_clear) {
 		charlcd_clear_display(&priv->lcd);
 		priv->must_clear = false;
 	}
 	return nonseekable_open(inode, file);
+
+ fail:
+	atomic_inc(&charlcd_available);
+	return ret;
 }
 
 static int charlcd_release(struct inode *inode, struct file *file)
diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c
index df126dc..6911acd 100644
--- a/drivers/auxdisplay/panel.c
+++ b/drivers/auxdisplay/panel.c
@@ -1105,14 +1105,21 @@
 
 static int keypad_open(struct inode *inode, struct file *file)
 {
-	if (!atomic_dec_and_test(&keypad_available))
-		return -EBUSY;	/* open only once at a time */
+	int ret;
 
+	ret = -EBUSY;
+	if (!atomic_dec_and_test(&keypad_available))
+		goto fail;	/* open only once at a time */
+
+	ret = -EPERM;
 	if (file->f_mode & FMODE_WRITE)	/* device is read-only */
-		return -EPERM;
+		goto fail;
 
 	keypad_buflen = 0;	/* flush the buffer on opening */
 	return 0;
+ fail:
+	atomic_inc(&keypad_available);
+	return ret;
 }
 
 static int keypad_release(struct inode *inode, struct file *file)
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 41be9ff..6df7d66 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -166,11 +166,11 @@
 }
 
 #ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
+static cpumask_var_t cpus_to_visit __initdata;
+static void __init parsing_done_workfn(struct work_struct *work);
+static __initdata DECLARE_WORK(parsing_done_work, parsing_done_workfn);
 
-static int
+static int __init
 init_cpu_capacity_callback(struct notifier_block *nb,
 			   unsigned long val,
 			   void *data)
@@ -206,7 +206,7 @@
 	return 0;
 }
 
-static struct notifier_block init_cpu_capacity_notifier = {
+static struct notifier_block init_cpu_capacity_notifier __initdata = {
 	.notifier_call = init_cpu_capacity_callback,
 };
 
@@ -232,7 +232,7 @@
 }
 core_initcall(register_cpufreq_notifier);
 
-static void parsing_done_workfn(struct work_struct *work)
+static void __init parsing_done_workfn(struct work_struct *work)
 {
 	cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
 					 CPUFREQ_POLICY_NOTIFIER);
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index a39b216..744f64f 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -348,16 +348,15 @@
 	struct dma_coherent_mem *mem = rmem->priv;
 	int ret;
 
-	if (!mem)
-		return -ENODEV;
-
-	ret = dma_init_coherent_memory(rmem->base, rmem->base, rmem->size,
-				       DMA_MEMORY_EXCLUSIVE, &mem);
-
-	if (ret) {
-		pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
-			&rmem->base, (unsigned long)rmem->size / SZ_1M);
-		return ret;
+	if (!mem) {
+		ret = dma_init_coherent_memory(rmem->base, rmem->base,
+					       rmem->size,
+					       DMA_MEMORY_EXCLUSIVE, &mem);
+		if (ret) {
+			pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
+				&rmem->base, (unsigned long)rmem->size / SZ_1M);
+			return ret;
+		}
 	}
 	mem->use_dev_dma_pfn_offset = true;
 	rmem->priv = mem;
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index d1bd992..9045c5f 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -868,7 +868,8 @@
 	struct platform_device *pdev = to_platform_device(dev);
 	char *driver_override, *old, *cp;
 
-	if (count > PATH_MAX)
+	/* We need to keep extra room for a newline */
+	if (count >= (PAGE_SIZE - 1))
 		return -EINVAL;
 
 	driver_override = kstrndup(buf, count, GFP_KERNEL);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index ea1732e..770b153 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1860,10 +1860,13 @@
 {
 	spin_lock_irq(&dev->power.lock);
 	dev->power.no_pm_callbacks =
-		(!dev->bus || pm_ops_is_empty(dev->bus->pm)) &&
-		(!dev->class || pm_ops_is_empty(dev->class->pm)) &&
+		(!dev->bus || (pm_ops_is_empty(dev->bus->pm) &&
+		 !dev->bus->suspend && !dev->bus->resume)) &&
+		(!dev->class || (pm_ops_is_empty(dev->class->pm) &&
+		 !dev->class->suspend && !dev->class->resume)) &&
 		(!dev->type || pm_ops_is_empty(dev->type->pm)) &&
 		(!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) &&
-		(!dev->driver || pm_ops_is_empty(dev->driver->pm));
+		(!dev->driver || (pm_ops_is_empty(dev->driver->pm) &&
+		 !dev->driver->suspend && !dev->driver->resume));
 	spin_unlock_irq(&dev->power.lock);
 }
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index a8cc14f..a6de325 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -1581,6 +1581,9 @@
 
 	opp->available = availability_req;
 
+	dev_pm_opp_get(opp);
+	mutex_unlock(&opp_table->lock);
+
 	/* Notify the change of the OPP availability */
 	if (availability_req)
 		blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE,
@@ -1589,8 +1592,12 @@
 		blocking_notifier_call_chain(&opp_table->head,
 					     OPP_EVENT_DISABLE, opp);
 
+	dev_pm_opp_put(opp);
+	goto put_table;
+
 unlock:
 	mutex_unlock(&opp_table->lock);
+put_table:
 	dev_pm_opp_put_opp_table(opp_table);
 	return r;
 }
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index f850dae..277d43a 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -277,11 +277,11 @@
 	mutex_unlock(&dev_pm_qos_sysfs_mtx);
 }
 
-static bool dev_pm_qos_invalid_request(struct device *dev,
-				       struct dev_pm_qos_request *req)
+static bool dev_pm_qos_invalid_req_type(struct device *dev,
+					enum dev_pm_qos_req_type type)
 {
-	return !req || (req->type == DEV_PM_QOS_LATENCY_TOLERANCE
-			&& !dev->power.set_latency_tolerance);
+	return type == DEV_PM_QOS_LATENCY_TOLERANCE &&
+	       !dev->power.set_latency_tolerance;
 }
 
 static int __dev_pm_qos_add_request(struct device *dev,
@@ -290,7 +290,7 @@
 {
 	int ret = 0;
 
-	if (!dev || dev_pm_qos_invalid_request(dev, req))
+	if (!dev || !req || dev_pm_qos_invalid_req_type(dev, type))
 		return -EINVAL;
 
 	if (WARN(dev_pm_qos_request_active(req),
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 4a438b8..2dfe99b 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -17,7 +17,7 @@
 
 config BLK_DEV_NULL_BLK
 	tristate "Null test block driver"
-	depends on CONFIGFS_FS
+	select CONFIGFS_FS
 
 config BLK_DEV_FD
 	tristate "Normal floppy disk support"
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bbd0d18..2d7178f 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -342,7 +342,7 @@
 
 	if (!brd)
 		return -ENODEV;
-	page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512);
+	page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index f68c1d5..1f39567 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -67,10 +67,8 @@
 struct loop_cmd {
 	struct kthread_work work;
 	struct request *rq;
-	union {
-		bool use_aio; /* use AIO interface to handle I/O */
-		atomic_t ref; /* only for aio */
-	};
+	bool use_aio; /* use AIO interface to handle I/O */
+	atomic_t ref; /* only for aio */
 	long ret;
 	struct kiocb iocb;
 	struct bio_vec *bvec;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 2aa87cb..883dfeb 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -820,9 +820,13 @@
 	 * appropriate.
 	 */
 	ret = nbd_handle_cmd(cmd, hctx->queue_num);
+	if (ret < 0)
+		ret = BLK_STS_IOERR;
+	else if (!ret)
+		ret = BLK_STS_OK;
 	complete(&cmd->send_complete);
 
-	return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK;
+	return ret;
 }
 
 static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
@@ -1194,6 +1198,12 @@
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	/* The block layer will pass back some non-nbd ioctls in case we have
+	 * special handling for them, but we don't so just return an error.
+	 */
+	if (_IOC_TYPE(cmd) != 0xab)
+		return -EINVAL;
+
 	mutex_lock(&nbd->config_lock);
 
 	/* Don't allow ioctl operations on a nbd device that was created with
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 2981c27..f149d3e 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -766,27 +766,6 @@
 	bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value);
 }
 
-static bool zram_same_page_read(struct zram *zram, u32 index,
-				struct page *page,
-				unsigned int offset, unsigned int len)
-{
-	zram_slot_lock(zram, index);
-	if (unlikely(!zram_get_handle(zram, index) ||
-			zram_test_flag(zram, index, ZRAM_SAME))) {
-		void *mem;
-
-		zram_slot_unlock(zram, index);
-		mem = kmap_atomic(page);
-		zram_fill_page(mem + offset, len,
-					zram_get_element(zram, index));
-		kunmap_atomic(mem);
-		return true;
-	}
-	zram_slot_unlock(zram, index);
-
-	return false;
-}
-
 static void zram_meta_free(struct zram *zram, u64 disksize)
 {
 	size_t num_pages = disksize >> PAGE_SHIFT;
@@ -884,11 +863,20 @@
 		zram_slot_unlock(zram, index);
 	}
 
-	if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE))
-		return 0;
-
 	zram_slot_lock(zram, index);
 	handle = zram_get_handle(zram, index);
+	if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
+		unsigned long value;
+		void *mem;
+
+		value = handle ? zram_get_element(zram, index) : 0;
+		mem = kmap_atomic(page);
+		zram_fill_page(mem, PAGE_SIZE, value);
+		kunmap_atomic(mem);
+		zram_slot_unlock(zram, index);
+		return 0;
+	}
+
 	size = zram_get_obj_size(zram, index);
 
 	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index fe597e6..1d6729b 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -455,7 +455,7 @@
 			goto out;
 		}
 
-		msleep(TPM_TIMEOUT);	/* CHECK */
+		tpm_msleep(TPM_TIMEOUT);
 		rmb();
 	} while (time_before(jiffies, stop));
 
@@ -970,7 +970,7 @@
 			dev_info(
 			    &chip->dev, HW_ERR
 			    "TPM command timed out during continue self test");
-			msleep(delay_msec);
+			tpm_msleep(delay_msec);
 			continue;
 		}
 
@@ -985,7 +985,7 @@
 		}
 		if (rc != TPM_WARN_DOING_SELFTEST)
 			return rc;
-		msleep(delay_msec);
+		tpm_msleep(delay_msec);
 	} while (--loops > 0);
 
 	return rc;
@@ -1085,7 +1085,7 @@
 		}
 	} else {
 		do {
-			msleep(TPM_TIMEOUT);
+			tpm_msleep(TPM_TIMEOUT);
 			status = chip->ops->status(chip);
 			if ((status & mask) == mask)
 				return 0;
@@ -1150,7 +1150,7 @@
 		 */
 		if (rc != TPM_WARN_RETRY)
 			break;
-		msleep(TPM_TIMEOUT_RETRY);
+		tpm_msleep(TPM_TIMEOUT_RETRY);
 	}
 
 	if (rc)
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 04fbff2..2d5466a 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -50,7 +50,8 @@
 
 enum tpm_timeout {
 	TPM_TIMEOUT = 5,	/* msecs */
-	TPM_TIMEOUT_RETRY = 100 /* msecs */
+	TPM_TIMEOUT_RETRY = 100, /* msecs */
+	TPM_TIMEOUT_RANGE_US = 300	/* usecs */
 };
 
 /* TPM addresses */
@@ -527,6 +528,12 @@
 int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
 		      wait_queue_head_t *queue, bool check_cancel);
 
+static inline void tpm_msleep(unsigned int delay_msec)
+{
+	usleep_range(delay_msec * 1000,
+		     (delay_msec * 1000) + TPM_TIMEOUT_RANGE_US);
+};
+
 struct tpm_chip *tpm_chip_find_get(int chip_num);
 __must_check int tpm_try_get_ops(struct tpm_chip *chip);
 void tpm_put_ops(struct tpm_chip *chip);
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index f7f34b2a..e1a41b7 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -899,7 +899,7 @@
 		if (rc != TPM2_RC_TESTING)
 			break;
 
-		msleep(delay_msec);
+		tpm_msleep(delay_msec);
 	}
 
 	return rc;
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index a4ac63a..8f0a98d 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -665,7 +665,7 @@
 	SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL)
 };
 
-static struct acpi_device_id crb_device_ids[] = {
+static const struct acpi_device_id crb_device_ids[] = {
 	{"MSFT0101", 0},
 	{"", 0},
 };
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index f01d083..25f6e26 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -32,26 +32,70 @@
 
 static const char tpm_ibmvtpm_driver_name[] = "tpm_ibmvtpm";
 
-static struct vio_device_id tpm_ibmvtpm_device_table[] = {
+static const struct vio_device_id tpm_ibmvtpm_device_table[] = {
 	{ "IBM,vtpm", "IBM,vtpm"},
 	{ "", "" }
 };
 MODULE_DEVICE_TABLE(vio, tpm_ibmvtpm_device_table);
 
 /**
+ *
+ * ibmvtpm_send_crq_word - Send a CRQ request
+ * @vdev:	vio device struct
+ * @w1:		pre-constructed first word of tpm crq (second word is reserved)
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvtpm_send_crq_word(struct vio_dev *vdev, u64 w1)
+{
+	return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, 0);
+}
+
+/**
+ *
  * ibmvtpm_send_crq - Send a CRQ request
  *
  * @vdev:	vio device struct
- * @w1:		first word
- * @w2:		second word
+ * @valid:	Valid field
+ * @msg:	Type field
+ * @len:	Length field
+ * @data:	Data field
+ *
+ * The ibmvtpm crq is defined as follows:
+ *
+ * Byte  |   0   |   1   |   2   |   3   |   4   |   5   |   6   |   7
+ * -----------------------------------------------------------------------
+ * Word0 | Valid | Type  |     Length    |              Data
+ * -----------------------------------------------------------------------
+ * Word1 |                Reserved
+ * -----------------------------------------------------------------------
+ *
+ * Which matches the following structure (on bigendian host):
+ *
+ * struct ibmvtpm_crq {
+ *         u8 valid;
+ *         u8 msg;
+ *         __be16 len;
+ *         __be32 data;
+ *         __be64 reserved;
+ * } __attribute__((packed, aligned(8)));
+ *
+ * However, the value is passed in a register so just compute the numeric value
+ * to load into the register avoiding byteswap altogether. Endian only affects
+ * memory loads and stores - registers are internally represented the same.
  *
  * Return:
- *	0 -Sucess
+ *	0 (H_SUCCESS) - Success
  *	Non-zero - Failure
  */
-static int ibmvtpm_send_crq(struct vio_dev *vdev, u64 w1, u64 w2)
+static int ibmvtpm_send_crq(struct vio_dev *vdev,
+		u8 valid, u8 msg, u16 len, u32 data)
 {
-	return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, w2);
+	u64 w1 = ((u64)valid << 56) | ((u64)msg << 48) | ((u64)len << 32) |
+		(u64)data;
+	return ibmvtpm_send_crq_word(vdev, w1);
 }
 
 /**
@@ -109,8 +153,6 @@
 static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
-	struct ibmvtpm_crq crq;
-	__be64 *word = (__be64 *)&crq;
 	int rc, sig;
 
 	if (!ibmvtpm->rtce_buf) {
@@ -137,10 +179,6 @@
 	spin_lock(&ibmvtpm->rtce_lock);
 	ibmvtpm->res_len = 0;
 	memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count);
-	crq.valid = (u8)IBMVTPM_VALID_CMD;
-	crq.msg = (u8)VTPM_TPM_COMMAND;
-	crq.len = cpu_to_be16(count);
-	crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle);
 
 	/*
 	 * set the processing flag before the Hcall, since we may get the
@@ -148,8 +186,9 @@
 	 */
 	ibmvtpm->tpm_processing_cmd = true;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]),
-			      be64_to_cpu(word[1]));
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+			IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND,
+			count, ibmvtpm->rtce_dma_handle);
 	if (rc != H_SUCCESS) {
 		dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
 		rc = 0;
@@ -182,15 +221,10 @@
  */
 static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm)
 {
-	struct ibmvtpm_crq crq;
-	u64 *buf = (u64 *) &crq;
 	int rc;
 
-	crq.valid = (u8)IBMVTPM_VALID_CMD;
-	crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE;
-
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
-			      cpu_to_be64(buf[1]));
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+			IBMVTPM_VALID_CMD, VTPM_GET_RTCE_BUFFER_SIZE, 0, 0);
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc);
@@ -210,15 +244,10 @@
  */
 static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm)
 {
-	struct ibmvtpm_crq crq;
-	u64 *buf = (u64 *) &crq;
 	int rc;
 
-	crq.valid = (u8)IBMVTPM_VALID_CMD;
-	crq.msg = (u8)VTPM_GET_VERSION;
-
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
-			      cpu_to_be64(buf[1]));
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+			IBMVTPM_VALID_CMD, VTPM_GET_VERSION, 0, 0);
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_get_version failed rc=%d\n", rc);
@@ -238,7 +267,7 @@
 {
 	int rc;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_COMP_CMD, 0);
+	rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_COMP_CMD);
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_send_init_complete failed rc=%d\n", rc);
@@ -258,7 +287,7 @@
 {
 	int rc;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_CMD, 0);
+	rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD);
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_send_init failed rc=%d\n", rc);
@@ -340,15 +369,10 @@
 {
 	struct tpm_chip *chip = dev_get_drvdata(dev);
 	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
-	struct ibmvtpm_crq crq;
-	u64 *buf = (u64 *) &crq;
 	int rc = 0;
 
-	crq.valid = (u8)IBMVTPM_VALID_CMD;
-	crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND;
-
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
-			      cpu_to_be64(buf[1]));
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+			IBMVTPM_VALID_CMD, VTPM_PREPARE_TO_SUSPEND, 0, 0);
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"tpm_ibmvtpm_suspend failed rc=%d\n", rc);
diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c
index 3b1b9f9..d8f1004 100644
--- a/drivers/char/tpm/tpm_infineon.c
+++ b/drivers/char/tpm/tpm_infineon.c
@@ -191,7 +191,7 @@
 		/* check the status-register if wait_for_bit is set */
 		if (status & 1 << wait_for_bit)
 			break;
-		msleep(TPM_MSLEEP_TIME);
+		tpm_msleep(TPM_MSLEEP_TIME);
 	}
 	if (i == TPM_MAX_TRIES) {	/* timeout occurs */
 		if (wait_for_bit == STAT_XFE)
@@ -226,7 +226,7 @@
 	wait_and_send(chip, TPM_CTRL_WTX);
 	wait_and_send(chip, 0x00);
 	wait_and_send(chip, 0x00);
-	msleep(TPM_WTX_MSLEEP_TIME);
+	tpm_msleep(TPM_WTX_MSLEEP_TIME);
 }
 
 static void tpm_wtx_abort(struct tpm_chip *chip)
@@ -237,7 +237,7 @@
 	wait_and_send(chip, 0x00);
 	wait_and_send(chip, 0x00);
 	number_of_wtx = 0;
-	msleep(TPM_WTX_MSLEEP_TIME);
+	tpm_msleep(TPM_WTX_MSLEEP_TIME);
 }
 
 static int tpm_inf_recv(struct tpm_chip *chip, u8 * buf, size_t count)
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index b617b2e..63bc6c3 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -51,7 +51,7 @@
 
 		if (access & TPM_ACCESS_VALID)
 			return 0;
-		msleep(TPM_TIMEOUT);
+		tpm_msleep(TPM_TIMEOUT);
 	} while (time_before(jiffies, stop));
 	return -1;
 }
@@ -117,7 +117,7 @@
 		do {
 			if (check_locality(chip, l))
 				return l;
-			msleep(TPM_TIMEOUT);
+			tpm_msleep(TPM_TIMEOUT);
 		} while (time_before(jiffies, stop));
 	}
 	return -1;
@@ -164,7 +164,7 @@
 		burstcnt = (value >> 8) & 0xFFFF;
 		if (burstcnt)
 			return burstcnt;
-		msleep(TPM_TIMEOUT);
+		tpm_msleep(TPM_TIMEOUT);
 	} while (time_before(jiffies, stop));
 	return -EBUSY;
 }
@@ -396,7 +396,7 @@
 	priv->irq = irq;
 	chip->flags |= TPM_CHIP_FLAG_IRQ;
 	if (!priv->irq_tested)
-		msleep(1);
+		tpm_msleep(1);
 	if (!priv->irq_tested)
 		disable_interrupts(chip);
 	priv->irq_tested = true;
diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c
index 6a20dc8..9a7d7f0 100644
--- a/drivers/clocksource/numachip.c
+++ b/drivers/clocksource/numachip.c
@@ -43,7 +43,7 @@
 	return 0;
 }
 
-static struct clock_event_device numachip2_clockevent = {
+static const struct clock_event_device numachip2_clockevent __initconst = {
 	.name            = "numachip2",
 	.rating          = 400,
 	.set_next_event  = numachip2_set_next_event,
diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c
index 2ff64d9..62d2469 100644
--- a/drivers/clocksource/timer-integrator-ap.c
+++ b/drivers/clocksource/timer-integrator-ap.c
@@ -36,8 +36,8 @@
 	return -readl(sched_clk_base + TIMER_VALUE);
 }
 
-static int integrator_clocksource_init(unsigned long inrate,
-				       void __iomem *base)
+static int __init integrator_clocksource_init(unsigned long inrate,
+					      void __iomem *base)
 {
 	u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC;
 	unsigned long rate = inrate;
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index a020da7..a753c50 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -106,6 +106,22 @@
  * platforms using "operating-points-v2" property.
  */
 static const struct of_device_id blacklist[] __initconst = {
+	{ .compatible = "calxeda,highbank", },
+	{ .compatible = "calxeda,ecx-2000", },
+
+	{ .compatible = "marvell,armadaxp", },
+
+	{ .compatible = "nvidia,tegra124", },
+
+	{ .compatible = "st,stih407", },
+	{ .compatible = "st,stih410", },
+
+	{ .compatible = "sigma,tango4", },
+
+	{ .compatible = "ti,am33xx", },
+	{ .compatible = "ti,am43", },
+	{ .compatible = "ti,dra7", },
+
 	{ }
 };
 
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index b29cd33..4bf47de 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -190,7 +190,7 @@
 
 static const struct of_device_id ti_cpufreq_of_match[] = {
 	{ .compatible = "ti,am33xx", .data = &am3x_soc_data, },
-	{ .compatible = "ti,am4372", .data = &am4x_soc_data, },
+	{ .compatible = "ti,am43", .data = &am4x_soc_data, },
 	{ .compatible = "ti,dra7", .data = &dra7_soc_data },
 	{},
 };
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index 7080c38..52a7505 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -104,13 +104,13 @@
 		ret = dt_init_idle_driver(drv, arm_idle_state_match, 1);
 		if (ret <= 0) {
 			ret = ret ? : -ENODEV;
-			goto out_fail;
+			goto init_fail;
 		}
 
 		ret = cpuidle_register_driver(drv);
 		if (ret) {
 			pr_err("Failed to register cpuidle driver\n");
-			goto out_fail;
+			goto init_fail;
 		}
 
 		/*
@@ -149,6 +149,8 @@
 	}
 
 	return 0;
+init_fail:
+	kfree(drv);
 out_fail:
 	while (--cpu >= 0) {
 		dev = per_cpu(cpuidle_devices, cpu);
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index e36aeac..1eb8527 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -1,6 +1,7 @@
 config CRYPTO_DEV_FSL_CAAM
 	tristate "Freescale CAAM-Multicore driver backend"
 	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE
+	select SOC_BUS
 	help
 	  Enables the driver module for Freescale's Cryptographic Accelerator
 	  and Assurance Module (CAAM), also known as the SEC version 4 (SEC4).
@@ -141,10 +142,6 @@
 	  To compile this as a module, choose M here: the module
 	  will be called caamrng.
 
-config CRYPTO_DEV_FSL_CAAM_IMX
-	def_bool SOC_IMX6 || SOC_IMX7D
-	depends on CRYPTO_DEV_FSL_CAAM
-
 config CRYPTO_DEV_FSL_CAAM_DEBUG
 	bool "Enable debug output in CAAM driver"
 	depends on CRYPTO_DEV_FSL_CAAM
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index dacb53f..027e121 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -7,6 +7,7 @@
 #include <linux/device.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sys_soc.h>
 
 #include "compat.h"
 #include "regs.h"
@@ -19,6 +20,8 @@
 EXPORT_SYMBOL(caam_little_end);
 bool caam_dpaa2;
 EXPORT_SYMBOL(caam_dpaa2);
+bool caam_imx;
+EXPORT_SYMBOL(caam_imx);
 
 #ifdef CONFIG_CAAM_QI
 #include "qi.h"
@@ -28,19 +31,11 @@
  * i.MX targets tend to have clock control subsystems that can
  * enable/disable clocking to our device.
  */
-#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
 static inline struct clk *caam_drv_identify_clk(struct device *dev,
 						char *clk_name)
 {
-	return devm_clk_get(dev, clk_name);
+	return caam_imx ? devm_clk_get(dev, clk_name) : NULL;
 }
-#else
-static inline struct clk *caam_drv_identify_clk(struct device *dev,
-						char *clk_name)
-{
-	return NULL;
-}
-#endif
 
 /*
  * Descriptor to instantiate RNG State Handle 0 in normal mode and
@@ -430,6 +425,10 @@
 {
 	int ret, ring, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
 	u64 caam_id;
+	static const struct soc_device_attribute imx_soc[] = {
+		{.family = "Freescale i.MX"},
+		{},
+	};
 	struct device *dev;
 	struct device_node *nprop, *np;
 	struct caam_ctrl __iomem *ctrl;
@@ -451,6 +450,8 @@
 	dev_set_drvdata(dev, ctrlpriv);
 	nprop = pdev->dev.of_node;
 
+	caam_imx = (bool)soc_device_match(imx_soc);
+
 	/* Enable clocking */
 	clk = caam_drv_identify_clk(&pdev->dev, "ipg");
 	if (IS_ERR(clk)) {
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index 2b5efff..17cfd23 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -67,6 +67,7 @@
  */
 
 extern bool caam_little_end;
+extern bool caam_imx;
 
 #define caam_to_cpu(len)				\
 static inline u##len caam##len ## _to_cpu(u##len val)	\
@@ -154,13 +155,10 @@
 #else /* CONFIG_64BIT */
 static inline void wr_reg64(void __iomem *reg, u64 data)
 {
-#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
-	if (caam_little_end) {
+	if (!caam_imx && caam_little_end) {
 		wr_reg32((u32 __iomem *)(reg) + 1, data >> 32);
 		wr_reg32((u32 __iomem *)(reg), data);
-	} else
-#endif
-	{
+	} else {
 		wr_reg32((u32 __iomem *)(reg), data >> 32);
 		wr_reg32((u32 __iomem *)(reg) + 1, data);
 	}
@@ -168,41 +166,40 @@
 
 static inline u64 rd_reg64(void __iomem *reg)
 {
-#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
-	if (caam_little_end)
+	if (!caam_imx && caam_little_end)
 		return ((u64)rd_reg32((u32 __iomem *)(reg) + 1) << 32 |
 			(u64)rd_reg32((u32 __iomem *)(reg)));
-	else
-#endif
-		return ((u64)rd_reg32((u32 __iomem *)(reg)) << 32 |
-			(u64)rd_reg32((u32 __iomem *)(reg) + 1));
+
+	return ((u64)rd_reg32((u32 __iomem *)(reg)) << 32 |
+		(u64)rd_reg32((u32 __iomem *)(reg) + 1));
 }
 #endif /* CONFIG_64BIT  */
 
+static inline u64 cpu_to_caam_dma64(dma_addr_t value)
+{
+	if (caam_imx)
+		return (((u64)cpu_to_caam32(lower_32_bits(value)) << 32) |
+			 (u64)cpu_to_caam32(upper_32_bits(value)));
+
+	return cpu_to_caam64(value);
+}
+
+static inline u64 caam_dma64_to_cpu(u64 value)
+{
+	if (caam_imx)
+		return (((u64)caam32_to_cpu(lower_32_bits(value)) << 32) |
+			 (u64)caam32_to_cpu(upper_32_bits(value)));
+
+	return caam64_to_cpu(value);
+}
+
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-#ifdef CONFIG_SOC_IMX7D
-#define cpu_to_caam_dma(value) \
-		(((u64)cpu_to_caam32(lower_32_bits(value)) << 32) | \
-		  (u64)cpu_to_caam32(upper_32_bits(value)))
-#define caam_dma_to_cpu(value) \
-		(((u64)caam32_to_cpu(lower_32_bits(value)) << 32) | \
-		  (u64)caam32_to_cpu(upper_32_bits(value)))
-#else
-#define cpu_to_caam_dma(value) cpu_to_caam64(value)
-#define caam_dma_to_cpu(value) caam64_to_cpu(value)
-#endif /* CONFIG_SOC_IMX7D */
+#define cpu_to_caam_dma(value) cpu_to_caam_dma64(value)
+#define caam_dma_to_cpu(value) caam_dma64_to_cpu(value)
 #else
 #define cpu_to_caam_dma(value) cpu_to_caam32(value)
 #define caam_dma_to_cpu(value) caam32_to_cpu(value)
-#endif /* CONFIG_ARCH_DMA_ADDR_T_64BIT  */
-
-#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
-#define cpu_to_caam_dma64(value) \
-		(((u64)cpu_to_caam32(lower_32_bits(value)) << 32) | \
-		 (u64)cpu_to_caam32(upper_32_bits(value)))
-#else
-#define cpu_to_caam_dma64(value) cpu_to_caam64(value)
-#endif
+#endif /* CONFIG_ARCH_DMA_ADDR_T_64BIT */
 
 /*
  * jr_outentry
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index d2207ac..5438552 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -386,7 +386,7 @@
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct skcipher_request req;
-	struct safexcel_inv_result result = { 0 };
+	struct safexcel_inv_result result = {};
 	int ring = ctx->base.ring;
 
 	memset(&req, 0, sizeof(struct skcipher_request));
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 3f81939..3980f94 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -419,7 +419,7 @@
 	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct ahash_request req;
-	struct safexcel_inv_result result = { 0 };
+	struct safexcel_inv_result result = {};
 	int ring = ctx->base.ring;
 
 	memset(&req, 0, sizeof(struct ahash_request));
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 79791c6..dff8883 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -1756,9 +1756,9 @@
 		req_ctx->swinit = 0;
 	} else {
 		desc->ptr[1] = zero_entry;
-		/* Indicate next op is not the first. */
-		req_ctx->first = 0;
 	}
+	/* Indicate next op is not the first. */
+	req_ctx->first = 0;
 
 	/* HMAC key */
 	if (ctx->keylen)
@@ -1769,7 +1769,7 @@
 
 	sg_count = edesc->src_nents ?: 1;
 	if (is_sec1 && sg_count > 1)
-		sg_copy_to_buffer(areq->src, sg_count, edesc->buf, length);
+		sg_copy_to_buffer(req_ctx->psrc, sg_count, edesc->buf, length);
 	else
 		sg_count = dma_map_sg(dev, req_ctx->psrc, sg_count,
 				      DMA_TO_DEVICE);
@@ -3057,7 +3057,8 @@
 		t_alg->algt.alg.hash.final = ahash_final;
 		t_alg->algt.alg.hash.finup = ahash_finup;
 		t_alg->algt.alg.hash.digest = ahash_digest;
-		t_alg->algt.alg.hash.setkey = ahash_setkey;
+		if (!strncmp(alg->cra_name, "hmac", 4))
+			t_alg->algt.alg.hash.setkey = ahash_setkey;
 		t_alg->algt.alg.hash.import = ahash_import;
 		t_alg->algt.alg.hash.export = ahash_export;
 
diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c
index 08629ee..00e73d2 100644
--- a/drivers/fpga/altera-cvp.c
+++ b/drivers/fpga/altera-cvp.c
@@ -361,12 +361,12 @@
 	.write_complete	= altera_cvp_write_complete,
 };
 
-static ssize_t show_chkcfg(struct device_driver *dev, char *buf)
+static ssize_t chkcfg_show(struct device_driver *dev, char *buf)
 {
 	return snprintf(buf, 3, "%d\n", altera_cvp_chkcfg);
 }
 
-static ssize_t store_chkcfg(struct device_driver *drv, const char *buf,
+static ssize_t chkcfg_store(struct device_driver *drv, const char *buf,
 			    size_t count)
 {
 	int ret;
@@ -378,7 +378,7 @@
 	return count;
 }
 
-static DRIVER_ATTR(chkcfg, 0600, show_chkcfg, store_chkcfg);
+static DRIVER_ATTR_RW(chkcfg);
 
 static int altera_cvp_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *dev_id);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index d228f5a..dbbe986 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -636,7 +636,194 @@
 				NUM_BANKS(ADDR_SURF_2_BANK);
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++)
 			WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]);
-	} else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) {
+	} else if (adev->asic_type == CHIP_OLAND) {
+		tilemode[0] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[1] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[2] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[3] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[4] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[5] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[6] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[7] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[8] =   MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[9] =   MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[10] =  MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[11] =  MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[12] =  MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[13] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[14] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[15] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[16] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[17] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[21] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[22] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[23] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[24] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[25] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+				NUM_BANKS(ADDR_SURF_8_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1);
+		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++)
+			WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]);
+	} else if (adev->asic_type == CHIP_HAINAN) {
 		tilemode[0] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
 				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 				PIPE_CONFIG(ADDR_SURF_P2) |
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index e4a8c2e..660b3fb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -892,6 +892,8 @@
 	int err = 0;
 
 	dev = kfd_device_by_id(args->gpu_id);
+	if (!dev)
+		return -EINVAL;
 
 	dev->kfd2kgd->get_tile_config(dev->kgd, &config);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 5979158..944abfa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -292,7 +292,10 @@
 				struct kfd_event *ev)
 {
 	if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) {
-		pr_warn("Signal event wasn't created because limit was reached\n");
+		if (!p->signal_event_limit_reached) {
+			pr_warn("Signal event wasn't created because limit was reached\n");
+			p->signal_event_limit_reached = true;
+		}
 		return -ENOMEM;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 681b639..ed71ad4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -183,8 +183,8 @@
 {
 	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
 		kq->mqd->destroy_mqd(kq->mqd,
-					NULL,
-					false,
+					kq->queue->mqd,
+					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 					QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS,
 					kq->queue->pipe,
 					kq->queue->queue);
@@ -210,6 +210,11 @@
 	uint32_t wptr, rptr;
 	unsigned int *queue_address;
 
+	/* When rptr == wptr, the buffer is empty.
+	 * When rptr == wptr + 1, the buffer is full.
+	 * It is always rptr that advances to the position of wptr, rather than
+	 * the opposite. So we can only use up to queue_size_dwords - 1 dwords.
+	 */
 	rptr = *kq->rptr_kernel;
 	wptr = *kq->wptr_kernel;
 	queue_address = (unsigned int *)kq->pq_kernel_addr;
@@ -219,11 +224,10 @@
 	pr_debug("wptr: %d\n", wptr);
 	pr_debug("queue_address 0x%p\n", queue_address);
 
-	available_size = (rptr - 1 - wptr + queue_size_dwords) %
+	available_size = (rptr + queue_size_dwords - 1 - wptr) %
 							queue_size_dwords;
 
-	if (packet_size_in_dwords >= queue_size_dwords ||
-			packet_size_in_dwords >= available_size) {
+	if (packet_size_in_dwords > available_size) {
 		/*
 		 * make sure calling functions know
 		 * acquire_packet_buffer() failed
@@ -233,6 +237,14 @@
 	}
 
 	if (wptr + packet_size_in_dwords >= queue_size_dwords) {
+		/* make sure after rolling back to position 0, there is
+		 * still enough space.
+		 */
+		if (packet_size_in_dwords >= rptr) {
+			*buffer_ptr = NULL;
+			return -ENOMEM;
+		}
+		/* fill nops, roll back and start at position 0 */
 		while (wptr > 0) {
 			queue_address[wptr] = kq->nop_packet;
 			wptr = (wptr + 1) % queue_size_dwords;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index b397ec7..b87e96c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -521,6 +521,7 @@
 	struct list_head signal_event_pages;
 	u32 next_nonsignal_event_id;
 	size_t signal_event_count;
+	bool signal_event_limit_reached;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 1cae95e..03bec76 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -143,7 +143,6 @@
 	int num_queues = 0;
 	struct queue *cur;
 
-	memset(&q_properties, 0, sizeof(struct queue_properties));
 	memcpy(&q_properties, properties, sizeof(struct queue_properties));
 	q = NULL;
 	kq = NULL;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 5a63459..5788116 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -551,12 +551,15 @@
 void etnaviv_gem_free_object(struct drm_gem_object *obj)
 {
 	struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
+	struct etnaviv_drm_private *priv = obj->dev->dev_private;
 	struct etnaviv_vram_mapping *mapping, *tmp;
 
 	/* object should not be active */
 	WARN_ON(is_active(etnaviv_obj));
 
+	mutex_lock(&priv->gem_lock);
 	list_del(&etnaviv_obj->gem_node);
+	mutex_unlock(&priv->gem_lock);
 
 	list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list,
 				 obj_node) {
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 026ef4e..46dfe07 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -445,8 +445,10 @@
 	cmdbuf->user_size = ALIGN(args->stream_size, 8);
 
 	ret = etnaviv_gpu_submit(gpu, submit, cmdbuf);
-	if (ret == 0)
-		cmdbuf = NULL;
+	if (ret)
+		goto out;
+
+	cmdbuf = NULL;
 
 	if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) {
 		/*
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 730b8d9..6be5b53 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -14,6 +14,7 @@
 #include <linux/clk.h>
 #include <linux/component.h>
 #include <linux/iopoll.h>
+#include <linux/irq.h>
 #include <linux/mfd/syscon.h>
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index b1f7299..e651a58 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -168,23 +168,19 @@
 static int exynos_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct drm_connector *connector;
-	struct drm_connector_list_iter conn_iter;
+	struct exynos_drm_private *private = drm_dev->dev_private;
 
 	if (pm_runtime_suspended(dev) || !drm_dev)
 		return 0;
 
-	drm_connector_list_iter_begin(drm_dev, &conn_iter);
-	drm_for_each_connector_iter(connector, &conn_iter) {
-		int old_dpms = connector->dpms;
-
-		if (connector->funcs->dpms)
-			connector->funcs->dpms(connector, DRM_MODE_DPMS_OFF);
-
-		/* Set the old mode back to the connector for resume */
-		connector->dpms = old_dpms;
+	drm_kms_helper_poll_disable(drm_dev);
+	exynos_drm_fbdev_suspend(drm_dev);
+	private->suspend_state = drm_atomic_helper_suspend(drm_dev);
+	if (IS_ERR(private->suspend_state)) {
+		exynos_drm_fbdev_resume(drm_dev);
+		drm_kms_helper_poll_enable(drm_dev);
+		return PTR_ERR(private->suspend_state);
 	}
-	drm_connector_list_iter_end(&conn_iter);
 
 	return 0;
 }
@@ -192,22 +188,14 @@
 static int exynos_drm_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct drm_connector *connector;
-	struct drm_connector_list_iter conn_iter;
+	struct exynos_drm_private *private = drm_dev->dev_private;
 
 	if (pm_runtime_suspended(dev) || !drm_dev)
 		return 0;
 
-	drm_connector_list_iter_begin(drm_dev, &conn_iter);
-	drm_for_each_connector_iter(connector, &conn_iter) {
-		if (connector->funcs->dpms) {
-			int dpms = connector->dpms;
-
-			connector->dpms = DRM_MODE_DPMS_OFF;
-			connector->funcs->dpms(connector, dpms);
-		}
-	}
-	drm_connector_list_iter_end(&conn_iter);
+	drm_atomic_helper_resume(drm_dev, private->suspend_state);
+	exynos_drm_fbdev_resume(drm_dev);
+	drm_kms_helper_poll_enable(drm_dev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index cf131c2..f8bae4cb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -202,6 +202,7 @@
  */
 struct exynos_drm_private {
 	struct drm_fb_helper *fb_helper;
+	struct drm_atomic_state *suspend_state;
 
 	struct device *dma_dev;
 	void *mapping;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index c3a0684..dfb66ec 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -18,6 +18,8 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/exynos_drm.h>
 
+#include <linux/console.h>
+
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
 #include "exynos_drm_fbdev.h"
@@ -285,3 +287,21 @@
 
 	drm_fb_helper_hotplug_event(fb_helper);
 }
+
+void exynos_drm_fbdev_suspend(struct drm_device *dev)
+{
+	struct exynos_drm_private *private = dev->dev_private;
+
+	console_lock();
+	drm_fb_helper_set_suspend(private->fb_helper, 1);
+	console_unlock();
+}
+
+void exynos_drm_fbdev_resume(struct drm_device *dev)
+{
+	struct exynos_drm_private *private = dev->dev_private;
+
+	console_lock();
+	drm_fb_helper_set_suspend(private->fb_helper, 0);
+	console_unlock();
+}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.h b/drivers/gpu/drm/exynos/exynos_drm_fbdev.h
index 330eef8..645d1bb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.h
@@ -21,6 +21,8 @@
 void exynos_drm_fbdev_fini(struct drm_device *dev);
 void exynos_drm_fbdev_restore_mode(struct drm_device *dev);
 void exynos_drm_output_poll_changed(struct drm_device *dev);
+void exynos_drm_fbdev_suspend(struct drm_device *drm);
+void exynos_drm_fbdev_resume(struct drm_device *drm);
 
 #else
 
@@ -39,6 +41,14 @@
 
 #define exynos_drm_output_poll_changed (NULL)
 
+static inline void exynos_drm_fbdev_suspend(struct drm_device *drm)
+{
+}
+
+static inline void exynos_drm_fbdev_resume(struct drm_device *drm)
+{
+}
+
 #endif
 
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 214fa5e..0109ff4 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -944,22 +944,27 @@
 	struct drm_device *dev = encoder->dev;
 	struct drm_connector *connector;
 	struct drm_display_mode *m;
+	struct drm_connector_list_iter conn_iter;
 	int mode_ok;
 
 	drm_mode_set_crtcinfo(adjusted_mode, 0);
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
 		if (connector->encoder == encoder)
 			break;
 	}
+	if (connector)
+		drm_connector_get(connector);
+	drm_connector_list_iter_end(&conn_iter);
 
-	if (connector->encoder != encoder)
+	if (!connector)
 		return true;
 
 	mode_ok = hdmi_mode_valid(connector, adjusted_mode);
 
 	if (mode_ok == MODE_OK)
-		return true;
+		goto cleanup;
 
 	/*
 	 * Find the most suitable mode and copy it to adjusted_mode.
@@ -979,6 +984,9 @@
 		}
 	}
 
+cleanup:
+	drm_connector_put(connector);
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 40af17e..ff3154f 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -197,78 +197,65 @@
 static int emulate_pci_bar_write(struct intel_vgpu *vgpu, unsigned int offset,
 	void *p_data, unsigned int bytes)
 {
-	unsigned int bar_index =
-		(rounddown(offset, 8) % PCI_BASE_ADDRESS_0) / 8;
 	u32 new = *(u32 *)(p_data);
 	bool lo = IS_ALIGNED(offset, 8);
 	u64 size;
 	int ret = 0;
 	bool mmio_enabled =
 		vgpu_cfg_space(vgpu)[PCI_COMMAND] & PCI_COMMAND_MEMORY;
+	struct intel_vgpu_pci_bar *bars = vgpu->cfg_space.bar;
 
-	if (WARN_ON(bar_index >= INTEL_GVT_PCI_BAR_MAX))
-		return -EINVAL;
-
+	/*
+	 * Power-up software can determine how much address
+	 * space the device requires by writing a value of
+	 * all 1's to the register and then reading the value
+	 * back. The device will return 0's in all don't-care
+	 * address bits.
+	 */
 	if (new == 0xffffffff) {
-		/*
-		 * Power-up software can determine how much address
-		 * space the device requires by writing a value of
-		 * all 1's to the register and then reading the value
-		 * back. The device will return 0's in all don't-care
-		 * address bits.
-		 */
-		size = vgpu->cfg_space.bar[bar_index].size;
-		if (lo) {
-			new = rounddown(new, size);
-		} else {
-			u32 val = vgpu_cfg_space(vgpu)[rounddown(offset, 8)];
-			/* for 32bit mode bar it returns all-0 in upper 32
-			 * bit, for 64bit mode bar it will calculate the
-			 * size with lower 32bit and return the corresponding
-			 * value
+		switch (offset) {
+		case PCI_BASE_ADDRESS_0:
+		case PCI_BASE_ADDRESS_1:
+			size = ~(bars[INTEL_GVT_PCI_BAR_GTTMMIO].size -1);
+			intel_vgpu_write_pci_bar(vgpu, offset,
+						size >> (lo ? 0 : 32), lo);
+			/*
+			 * Untrap the BAR, since guest hasn't configured a
+			 * valid GPA
 			 */
-			if (val & PCI_BASE_ADDRESS_MEM_TYPE_64)
-				new &= (~(size-1)) >> 32;
-			else
-				new = 0;
-		}
-		/*
-		 * Unmapp & untrap the BAR, since guest hasn't configured a
-		 * valid GPA
-		 */
-		switch (bar_index) {
-		case INTEL_GVT_PCI_BAR_GTTMMIO:
 			ret = trap_gttmmio(vgpu, false);
 			break;
-		case INTEL_GVT_PCI_BAR_APERTURE:
+		case PCI_BASE_ADDRESS_2:
+		case PCI_BASE_ADDRESS_3:
+			size = ~(bars[INTEL_GVT_PCI_BAR_APERTURE].size -1);
+			intel_vgpu_write_pci_bar(vgpu, offset,
+						size >> (lo ? 0 : 32), lo);
 			ret = map_aperture(vgpu, false);
 			break;
+		default:
+			/* Unimplemented BARs */
+			intel_vgpu_write_pci_bar(vgpu, offset, 0x0, false);
 		}
-		intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
 	} else {
-		/*
-		 * Unmapp & untrap the old BAR first, since guest has
-		 * re-configured the BAR
-		 */
-		switch (bar_index) {
-		case INTEL_GVT_PCI_BAR_GTTMMIO:
-			ret = trap_gttmmio(vgpu, false);
+		switch (offset) {
+		case PCI_BASE_ADDRESS_0:
+		case PCI_BASE_ADDRESS_1:
+			/*
+			 * Untrap the old BAR first, since guest has
+			 * re-configured the BAR
+			 */
+			trap_gttmmio(vgpu, false);
+			intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
+			ret = trap_gttmmio(vgpu, mmio_enabled);
 			break;
-		case INTEL_GVT_PCI_BAR_APERTURE:
-			ret = map_aperture(vgpu, false);
+		case PCI_BASE_ADDRESS_2:
+		case PCI_BASE_ADDRESS_3:
+			map_aperture(vgpu, false);
+			intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
+			ret = map_aperture(vgpu, mmio_enabled);
 			break;
-		}
-		intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
-		/* Track the new BAR */
-		if (mmio_enabled) {
-			switch (bar_index) {
-			case INTEL_GVT_PCI_BAR_GTTMMIO:
-				ret = trap_gttmmio(vgpu, true);
-				break;
-			case INTEL_GVT_PCI_BAR_APERTURE:
-				ret = map_aperture(vgpu, true);
-				break;
-			}
+		default:
+			intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
 		}
 	}
 	return ret;
@@ -299,10 +286,7 @@
 	}
 
 	switch (rounddown(offset, 4)) {
-	case PCI_BASE_ADDRESS_0:
-	case PCI_BASE_ADDRESS_1:
-	case PCI_BASE_ADDRESS_2:
-	case PCI_BASE_ADDRESS_3:
+	case PCI_BASE_ADDRESS_0 ... PCI_BASE_ADDRESS_5:
 		if (WARN_ON(!IS_ALIGNED(offset, 4)))
 			return -EINVAL;
 		return emulate_pci_bar_write(vgpu, offset, p_data, bytes);
@@ -344,7 +328,6 @@
 	struct intel_gvt *gvt = vgpu->gvt;
 	const struct intel_gvt_device_info *info = &gvt->device_info;
 	u16 *gmch_ctl;
-	int i;
 
 	memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
 	       info->cfg_space_size);
@@ -371,13 +354,13 @@
 	 */
 	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
 	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
+	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_4, 0, 8);
 	memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
 
-	for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
-		vgpu->cfg_space.bar[i].size = pci_resource_len(
-					      gvt->dev_priv->drm.pdev, i * 2);
-		vgpu->cfg_space.bar[i].tracked = false;
-	}
+	vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_GTTMMIO].size =
+				pci_resource_len(gvt->dev_priv->drm.pdev, 0);
+	vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].size =
+				pci_resource_len(gvt->dev_priv->drm.pdev, 2);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e21ce9c..b63893e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -839,7 +839,6 @@
 								pipe);
 	int position;
 	int vbl_start, vbl_end, hsync_start, htotal, vtotal;
-	bool in_vbl = true;
 	unsigned long irqflags;
 
 	if (WARN_ON(!mode->crtc_clock)) {
@@ -922,8 +921,6 @@
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
-	in_vbl = position >= vbl_start && position < vbl_end;
-
 	/*
 	 * While in vblank, position will be negative
 	 * counting up towards 0 at vbl_end. And outside
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index d805b6e..27743be 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -606,11 +606,6 @@
 			 connector->encoder->base.id,
 			 connector->encoder->name);
 
-	/* ELD Conn_Type */
-	connector->eld[5] &= ~(3 << 2);
-	if (intel_crtc_has_dp_encoder(crtc_state))
-		connector->eld[5] |= (1 << 2);
-
 	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
 
 	if (dev_priv->display.audio_codec_enable)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 183e87e..00c6aee 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1163,6 +1163,13 @@
 	is_hdmi = is_dvi && (child->common.device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0;
 	is_edp = is_dp && (child->common.device_type & DEVICE_TYPE_INTERNAL_CONNECTOR);
 
+	if (port == PORT_A && is_dvi) {
+		DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n",
+			      is_hdmi ? "/HDMI" : "");
+		is_dvi = false;
+		is_hdmi = false;
+	}
+
 	info->supports_dvi = is_dvi;
 	info->supports_hdmi = is_hdmi;
 	info->supports_dp = is_dp;
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 965988f..92c1f8e 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -216,7 +216,7 @@
 
 	mask = DC_STATE_DEBUG_MASK_MEMORY_UP;
 
-	if (IS_BROXTON(dev_priv))
+	if (IS_GEN9_LP(dev_priv))
 		mask |= DC_STATE_DEBUG_MASK_CORES;
 
 	/* The below bit doesn't need to be cleared ever afterwards */
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 4b4fd1f..476681d 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1655,7 +1655,8 @@
 out:
 	if (ret && IS_GEN9_LP(dev_priv)) {
 		tmp = I915_READ(BXT_PHY_CTL(port));
-		if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK |
+		if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK |
+			    BXT_PHY_LANE_POWERDOWN_ACK |
 			    BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED)
 			DRM_ERROR("Port %c enabled but PHY powered down? "
 				  "(PHY_CTL %08x)\n", port_name(port), tmp);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f172755..64f7b51 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12359,7 +12359,6 @@
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct drm_crtc *crtc;
 	struct intel_crtc_state *intel_cstate;
-	bool hw_check = intel_state->modeset;
 	u64 put_domains[I915_MAX_PIPES] = {};
 	unsigned crtc_vblank_mask = 0;
 	int i;
@@ -12376,7 +12375,6 @@
 
 		if (needs_modeset(new_crtc_state) ||
 		    to_intel_crtc_state(new_crtc_state)->update_pipe) {
-			hw_check = true;
 
 			put_domains[to_intel_crtc(crtc)->pipe] =
 				modeset_get_crtc_power_domains(crtc,
@@ -14030,7 +14028,7 @@
 
 		if (mode_cmd->handles[i] != mode_cmd->handles[0]) {
 			DRM_DEBUG_KMS("bad plane %d handle\n", i);
-			return -EINVAL;
+			goto err;
 		}
 
 		stride_alignment = intel_fb_stride_alignment(fb, i);
diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c
index 09b6709..de38d01 100644
--- a/drivers/gpu/drm/i915/intel_dpio_phy.c
+++ b/drivers/gpu/drm/i915/intel_dpio_phy.c
@@ -208,12 +208,6 @@
 	},
 };
 
-static u32 bxt_phy_port_mask(const struct bxt_ddi_phy_info *phy_info)
-{
-	return (phy_info->dual_channel * BIT(phy_info->channel[DPIO_CH1].port)) |
-		BIT(phy_info->channel[DPIO_CH0].port);
-}
-
 static const struct bxt_ddi_phy_info *
 bxt_get_phy_list(struct drm_i915_private *dev_priv, int *count)
 {
@@ -313,7 +307,6 @@
 			    enum dpio_phy phy)
 {
 	const struct bxt_ddi_phy_info *phy_info;
-	enum port port;
 
 	phy_info = bxt_get_phy_info(dev_priv, phy);
 
@@ -335,19 +328,6 @@
 		return false;
 	}
 
-	for_each_port_masked(port, bxt_phy_port_mask(phy_info)) {
-		u32 tmp = I915_READ(BXT_PHY_CTL(port));
-
-		if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) {
-			DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane "
-					 "for port %c powered down "
-					 "(PHY_CTL %08x)\n",
-					 phy, port_name(port), tmp);
-
-			return false;
-		}
-	}
-
 	return true;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index f0c11ae..7442891 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -892,8 +892,6 @@
 			      struct intel_crtc_state *old_crtc_state,
 			      struct drm_connector_state *old_conn_state)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 
@@ -903,15 +901,6 @@
 	intel_panel_disable_backlight(old_conn_state);
 
 	/*
-	 * Disable Device ready before the port shutdown in order
-	 * to avoid split screen
-	 */
-	if (IS_BROXTON(dev_priv)) {
-		for_each_dsi_port(port, intel_dsi->ports)
-			I915_WRITE(MIPI_DEVICE_READY(port), 0);
-	}
-
-	/*
 	 * According to the spec we should send SHUTDOWN before
 	 * MIPI_SEQ_DISPLAY_OFF only for v3+ VBTs, but field testing
 	 * has shown that the v3 sequence works for v2 VBTs too
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index 951e834..28a778b 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -30,6 +30,21 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
+static void intel_connector_update_eld_conn_type(struct drm_connector *connector)
+{
+	u8 conn_type;
+
+	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort ||
+	    connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+		conn_type = DRM_ELD_CONN_TYPE_DP;
+	} else {
+		conn_type = DRM_ELD_CONN_TYPE_HDMI;
+	}
+
+	connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] &= ~DRM_ELD_CONN_TYPE_MASK;
+	connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] |= conn_type;
+}
+
 /**
  * intel_connector_update_modes - update connector from edid
  * @connector: DRM connector device to use
@@ -44,6 +59,8 @@
 	ret = drm_add_edid_modes(connector, edid);
 	drm_edid_to_eld(connector, edid);
 
+	intel_connector_update_eld_conn_type(connector);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index a17b1de..3b1c5d7 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1699,6 +1699,8 @@
 	if (!panel->backlight.max)
 		return -ENODEV;
 
+	panel->backlight.min = get_backlight_min_vbt(connector);
+
 	val = bxt_get_backlight(connector);
 	val = intel_panel_compute_brightness(connector, val);
 	panel->backlight.level = clamp(val, panel->backlight.min,
@@ -1735,6 +1737,8 @@
 	if (!panel->backlight.max)
 		return -ENODEV;
 
+	panel->backlight.min = get_backlight_min_vbt(connector);
+
 	val = bxt_get_backlight(connector);
 	val = intel_panel_compute_brightness(connector, val);
 	panel->backlight.level = clamp(val, panel->backlight.min,
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index b66d8e1..b3a087c 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -2782,6 +2782,9 @@
 
 	/* 6. Enable DBUF */
 	gen9_dbuf_enable(dev_priv);
+
+	if (resume && dev_priv->csr.dmc_payload)
+		intel_csr_load_program(dev_priv);
 }
 
 #undef CNL_PROCMON_IDX
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 14c5613..afbf50d 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -509,23 +509,25 @@
 	    .y2 = qfb->base.height
 	};
 
-	if (!old_state->fb) {
-		qxl_io_log(qdev,
-			   "create primary fb: %dx%d,%d,%d\n",
-			   bo->surf.width, bo->surf.height,
-			   bo->surf.stride, bo->surf.format);
-
-		qxl_io_create_primary(qdev, 0, bo);
-		bo->is_primary = true;
-		return;
-
-	} else {
+	if (old_state->fb) {
 		qfb_old = to_qxl_framebuffer(old_state->fb);
 		bo_old = gem_to_qxl_bo(qfb_old->obj);
+	} else {
+		bo_old = NULL;
+	}
+
+	if (bo == bo_old)
+		return;
+
+	if (bo_old && bo_old->is_primary) {
+		qxl_io_destroy_primary(qdev);
 		bo_old->is_primary = false;
 	}
 
-	bo->is_primary = true;
+	if (!bo->is_primary) {
+		qxl_io_create_primary(qdev, 0, bo);
+		bo->is_primary = true;
+	}
 	qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1);
 }
 
@@ -534,13 +536,15 @@
 {
 	struct qxl_device *qdev = plane->dev->dev_private;
 
-	if (old_state->fb)
-	{	struct qxl_framebuffer *qfb =
+	if (old_state->fb) {
+		struct qxl_framebuffer *qfb =
 			to_qxl_framebuffer(old_state->fb);
 		struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj);
 
-		qxl_io_destroy_primary(qdev);
-		bo->is_primary = false;
+		if (bo->is_primary) {
+			qxl_io_destroy_primary(qdev);
+			bo->is_primary = false;
+		}
 	}
 }
 
@@ -698,14 +702,15 @@
 	struct drm_gem_object *obj;
 	struct qxl_bo *user_bo;
 
-	if (!plane->state->fb) {
-		/* we never executed prepare_fb, so there's nothing to
+	if (!old_state->fb) {
+		/*
+		 * we never executed prepare_fb, so there's nothing to
 		 * unpin.
 		 */
 		return;
 	}
 
-	obj = to_qxl_framebuffer(plane->state->fb)->obj;
+	obj = to_qxl_framebuffer(old_state->fb)->obj;
 	user_bo = gem_to_qxl_bo(obj);
 	qxl_bo_unpin(user_bo);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 997131d..ffc10ca 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1663,7 +1663,7 @@
 	radeon_agp_suspend(rdev);
 
 	pci_save_state(dev->pdev);
-	if (freeze && rdev->family >= CHIP_CEDAR) {
+	if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) {
 		rdev->asic->asic_reset(rdev, true);
 		pci_restore_state(dev->pdev);
 	} else if (suspend) {
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 06f0530..882d85d 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -26,7 +26,7 @@
        bool "Allwinner A10 HDMI CEC Support"
        depends on DRM_SUN4I_HDMI
        select CEC_CORE
-       depends on CEC_PIN
+       select CEC_PIN
        help
 	  Choose this option if you have an Allwinner SoC with an HDMI
 	  controller and want to use CEC.
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
index 1457750..a1f8cba 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
@@ -15,7 +15,7 @@
 #include <drm/drm_connector.h>
 #include <drm/drm_encoder.h>
 
-#include <media/cec.h>
+#include <media/cec-pin.h>
 
 #define SUN4I_HDMI_CTRL_REG		0x004
 #define SUN4I_HDMI_CTRL_ENABLE			BIT(31)
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index 9ea6cd5..3cf1a69 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -302,26 +302,29 @@
 	hdmi->mod_clk = devm_clk_get(dev, "mod");
 	if (IS_ERR(hdmi->mod_clk)) {
 		dev_err(dev, "Couldn't get the HDMI mod clock\n");
-		return PTR_ERR(hdmi->mod_clk);
+		ret = PTR_ERR(hdmi->mod_clk);
+		goto err_disable_bus_clk;
 	}
 	clk_prepare_enable(hdmi->mod_clk);
 
 	hdmi->pll0_clk = devm_clk_get(dev, "pll-0");
 	if (IS_ERR(hdmi->pll0_clk)) {
 		dev_err(dev, "Couldn't get the HDMI PLL 0 clock\n");
-		return PTR_ERR(hdmi->pll0_clk);
+		ret = PTR_ERR(hdmi->pll0_clk);
+		goto err_disable_mod_clk;
 	}
 
 	hdmi->pll1_clk = devm_clk_get(dev, "pll-1");
 	if (IS_ERR(hdmi->pll1_clk)) {
 		dev_err(dev, "Couldn't get the HDMI PLL 1 clock\n");
-		return PTR_ERR(hdmi->pll1_clk);
+		ret = PTR_ERR(hdmi->pll1_clk);
+		goto err_disable_mod_clk;
 	}
 
 	ret = sun4i_tmds_create(hdmi);
 	if (ret) {
 		dev_err(dev, "Couldn't create the TMDS clock\n");
-		return ret;
+		goto err_disable_mod_clk;
 	}
 
 	writel(SUN4I_HDMI_CTRL_ENABLE, hdmi->base + SUN4I_HDMI_CTRL_REG);
@@ -362,7 +365,7 @@
 	ret = sun4i_hdmi_i2c_create(dev, hdmi);
 	if (ret) {
 		dev_err(dev, "Couldn't create the HDMI I2C adapter\n");
-		return ret;
+		goto err_disable_mod_clk;
 	}
 
 	drm_encoder_helper_add(&hdmi->encoder,
@@ -422,6 +425,10 @@
 	drm_encoder_cleanup(&hdmi->encoder);
 err_del_i2c_adapter:
 	i2c_del_adapter(hdmi->i2c);
+err_disable_mod_clk:
+	clk_disable_unprepare(hdmi->mod_clk);
+err_disable_bus_clk:
+	clk_disable_unprepare(hdmi->bus_clk);
 	return ret;
 }
 
@@ -434,6 +441,8 @@
 	drm_connector_cleanup(&hdmi->connector);
 	drm_encoder_cleanup(&hdmi->encoder);
 	i2c_del_adapter(hdmi->i2c);
+	clk_disable_unprepare(hdmi->mod_clk);
+	clk_disable_unprepare(hdmi->bus_clk);
 }
 
 static const struct component_ops sun4i_hdmi_ops = {
diff --git a/drivers/gpu/drm/tegra/trace.h b/drivers/gpu/drm/tegra/trace.h
index e9b7cdad..5a1ab40 100644
--- a/drivers/gpu/drm/tegra/trace.h
+++ b/drivers/gpu/drm/tegra/trace.h
@@ -63,6 +63,6 @@
 
 /* This part must be outside protection */
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra
 #define TRACE_INCLUDE_FILE trace
 #include <trace/define_trace.h>
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index b397a14..a989191 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -533,6 +533,7 @@
 #define USB_VENDOR_ID_IDEACOM		0x1cb6
 #define USB_DEVICE_ID_IDEACOM_IDC6650	0x6650
 #define USB_DEVICE_ID_IDEACOM_IDC6651	0x6651
+#define USB_DEVICE_ID_IDEACOM_IDC6680	0x6680
 
 #define USB_VENDOR_ID_ILITEK		0x222a
 #define USB_DEVICE_ID_ILITEK_MULTITOUCH	0x0001
@@ -660,6 +661,7 @@
 #define USB_DEVICE_ID_LENOVO_CBTKBD	0x6048
 #define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
 #define USB_DEVICE_ID_LENOVO_X1_COVER	0x6085
+#define USB_DEVICE_ID_LENOVO_X1_TAB	0x60a3
 
 #define USB_VENDOR_ID_LG		0x1fd2
 #define USB_DEVICE_ID_LG_MULTITOUCH	0x0064
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 440b999..9e8c4d2 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -930,6 +930,7 @@
 	    field->application != HID_DG_PEN &&
 	    field->application != HID_DG_TOUCHPAD &&
 	    field->application != HID_GD_KEYBOARD &&
+	    field->application != HID_GD_SYSTEM_CONTROL &&
 	    field->application != HID_CP_CONSUMER_CONTROL &&
 	    field->application != HID_GD_WIRELESS_RADIO_CTLS &&
 	    !(field->application == HID_VD_ASUS_CUSTOM_MEDIA_KEYS &&
@@ -1419,6 +1420,12 @@
 			USB_VENDOR_ID_ALPS_JP,
 			HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP) },
 
+	/* Lenovo X1 TAB Gen 2 */
+	{ .driver_data = MT_CLS_WIN_8_DUAL,
+		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
+			   USB_VENDOR_ID_LENOVO,
+			   USB_DEVICE_ID_LENOVO_X1_TAB) },
+
 	/* Anton devices */
 	{ .driver_data = MT_CLS_EXPORT_ALL_INPUTS,
 		MT_USB_DEVICE(USB_VENDOR_ID_ANTON,
diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index 5b40c26..ef241d6 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -436,17 +436,24 @@
 	if (!(data->device_flags & RMI_DEVICE))
 		return 0;
 
-	ret = rmi_reset_attn_mode(hdev);
+	/* Make sure the HID device is ready to receive events */
+	ret = hid_hw_open(hdev);
 	if (ret)
 		return ret;
 
+	ret = rmi_reset_attn_mode(hdev);
+	if (ret)
+		goto out;
+
 	ret = rmi_driver_resume(rmi_dev, false);
 	if (ret) {
 		hid_warn(hdev, "Failed to resume device: %d\n", ret);
-		return ret;
+		goto out;
 	}
 
-	return 0;
+out:
+	hid_hw_close(hdev);
+	return ret;
 }
 #endif /* CONFIG_PM */
 
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index ec53045..5fbe0f8 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -337,8 +337,8 @@
 			kfree(hidraw);
 		} else {
 			/* close device for last reader */
-			hid_hw_power(hidraw->hid, PM_HINT_NORMAL);
 			hid_hw_close(hidraw->hid);
+			hid_hw_power(hidraw->hid, PM_HINT_NORMAL);
 		}
 	}
 }
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 7739614..9145c21 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -543,7 +543,8 @@
 {
 	/* the worst case is computed from the set_report command with a
 	 * reportID > 15 and the maximum report length */
-	int args_len = sizeof(__u8) + /* optional ReportID byte */
+	int args_len = sizeof(__u8) + /* ReportID */
+		       sizeof(__u8) + /* optional ReportID byte */
 		       sizeof(__u16) + /* data register */
 		       sizeof(__u16) + /* size of the report */
 		       report_size; /* report */
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index a83fa76..f489a5c 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -99,6 +99,7 @@
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C007, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS, HID_QUIRK_NOGET },
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index e82a696..906e654 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -668,8 +668,10 @@
 
 	/* Try to find an already-probed interface from the same device */
 	list_for_each_entry(data, &wacom_udev_list, list) {
-		if (compare_device_paths(hdev, data->dev, '/'))
+		if (compare_device_paths(hdev, data->dev, '/')) {
+			kref_get(&data->kref);
 			return data;
+		}
 	}
 
 	/* Fallback to finding devices that appear to be "siblings" */
@@ -766,6 +768,9 @@
 	if (!wacom->led.groups)
 		return -ENOTSUPP;
 
+	if (wacom->wacom_wac.features.type == REMOTE)
+		return -ENOTSUPP;
+
 	if (wacom->wacom_wac.pid) { /* wireless connected */
 		report_id = WAC_CMD_WL_LED_CONTROL;
 		buf_size = 13;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index bb17d7b..aa692e2 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -567,8 +567,8 @@
 				keys = data[9] & 0x07;
 			}
 		} else {
-			buttons = ((data[6] & 0x10) << 10) |
-			          ((data[5] & 0x10) << 9)  |
+			buttons = ((data[6] & 0x10) << 5)  |
+			          ((data[5] & 0x10) << 4)  |
 			          ((data[6] & 0x0F) << 4)  |
 			          (data[5] & 0x0F);
 		}
@@ -1227,11 +1227,17 @@
 			continue;
 
 		if (range) {
+			/* Fix rotation alignment: userspace expects zero at left */
+			int16_t rotation = (int16_t)get_unaligned_le16(&frame[9]);
+			rotation += 1800/4;
+			if (rotation > 899)
+				rotation -= 1800;
+
 			input_report_abs(pen_input, ABS_X, get_unaligned_le16(&frame[1]));
 			input_report_abs(pen_input, ABS_Y, get_unaligned_le16(&frame[3]));
-			input_report_abs(pen_input, ABS_TILT_X, frame[7]);
-			input_report_abs(pen_input, ABS_TILT_Y, frame[8]);
-			input_report_abs(pen_input, ABS_Z, get_unaligned_le16(&frame[9]));
+			input_report_abs(pen_input, ABS_TILT_X, (char)frame[7]);
+			input_report_abs(pen_input, ABS_TILT_Y, (char)frame[8]);
+			input_report_abs(pen_input, ABS_Z, rotation);
 			input_report_abs(pen_input, ABS_WHEEL, get_unaligned_le16(&frame[11]));
 		}
 		input_report_abs(pen_input, ABS_PRESSURE, get_unaligned_le16(&frame[5]));
@@ -1319,12 +1325,19 @@
 	unsigned char *data = wacom->data;
 
 	int buttons = (data[282] << 1) | ((data[281] >> 6) & 0x01);
-	int ring = data[285];
-	int prox = buttons | (ring & 0x80);
+	int ring = data[285] & 0x7F;
+	bool ringstatus = data[285] & 0x80;
+	bool prox = buttons || ringstatus;
+
+	/* Fix touchring data: userspace expects 0 at left and increasing clockwise */
+	ring = 71 - ring;
+	ring += 3*72/16;
+	if (ring > 71)
+		ring -= 72;
 
 	wacom_report_numbered_buttons(pad_input, 9, buttons);
 
-	input_report_abs(pad_input, ABS_WHEEL, (ring & 0x80) ? (ring & 0x7f) : 0);
+	input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0);
 
 	input_report_key(pad_input, wacom->tool[1], prox ? 1 : 0);
 	input_report_abs(pad_input, ABS_MISC, prox ? PAD_DEVICE_ID : 0);
@@ -1616,6 +1629,20 @@
 	return 0;
 }
 
+static int wacom_offset_rotation(struct input_dev *input, struct hid_usage *usage,
+				 int value, int num, int denom)
+{
+	struct input_absinfo *abs = &input->absinfo[usage->code];
+	int range = (abs->maximum - abs->minimum + 1);
+
+	value += num*range/denom;
+	if (value > abs->maximum)
+		value -= range;
+	else if (value < abs->minimum)
+		value += range;
+	return value;
+}
+
 int wacom_equivalent_usage(int usage)
 {
 	if ((usage & HID_USAGE_PAGE) == WACOM_HID_UP_WACOMDIGITIZER) {
@@ -1898,6 +1925,7 @@
 	unsigned equivalent_usage = wacom_equivalent_usage(usage->hid);
 	int i;
 	bool is_touch_on = value;
+	bool do_report = false;
 
 	/*
 	 * Avoid reporting this event and setting inrange_state if this usage
@@ -1912,6 +1940,29 @@
 	}
 
 	switch (equivalent_usage) {
+	case WACOM_HID_WD_TOUCHRING:
+		/*
+		 * Userspace expects touchrings to increase in value with
+		 * clockwise gestures and have their zero point at the
+		 * tablet's left. HID events "should" be clockwise-
+		 * increasing and zero at top, though the MobileStudio
+		 * Pro and 2nd-gen Intuos Pro don't do this...
+		 */
+		if (hdev->vendor == 0x56a &&
+		    (hdev->product == 0x34d || hdev->product == 0x34e ||  /* MobileStudio Pro */
+		     hdev->product == 0x357 || hdev->product == 0x358)) { /* Intuos Pro 2 */
+			value = (field->logical_maximum - value);
+
+			if (hdev->product == 0x357 || hdev->product == 0x358)
+				value = wacom_offset_rotation(input, usage, value, 3, 16);
+			else if (hdev->product == 0x34d || hdev->product == 0x34e)
+				value = wacom_offset_rotation(input, usage, value, 1, 2);
+		}
+		else {
+			value = wacom_offset_rotation(input, usage, value, 1, 4);
+		}
+		do_report = true;
+		break;
 	case WACOM_HID_WD_TOUCHRINGSTATUS:
 		if (!value)
 			input_event(input, usage->type, usage->code, 0);
@@ -1945,10 +1996,14 @@
 					 value, i);
 		 /* fall through*/
 	default:
+		do_report = true;
+		break;
+	}
+
+	if (do_report) {
 		input_event(input, usage->type, usage->code, value);
 		if (value)
 			wacom_wac->hid_data.pad_input_event_flag = true;
-		break;
 	}
 }
 
@@ -2086,22 +2141,34 @@
 		wacom_wac->hid_data.tipswitch |= value;
 		return;
 	case HID_DG_TOOLSERIALNUMBER:
-		wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL);
-		wacom_wac->serial[0] |= (__u32)value;
+		if (value) {
+			wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL);
+			wacom_wac->serial[0] |= (__u32)value;
+		}
 		return;
+	case HID_DG_TWIST:
+		/*
+		 * Userspace expects pen twist to have its zero point when
+		 * the buttons/finger is on the tablet's left. HID values
+		 * are zero when buttons are toward the top.
+		 */
+		value = wacom_offset_rotation(input, usage, value, 1, 4);
+		break;
 	case WACOM_HID_WD_SENSE:
 		wacom_wac->hid_data.sense_state = value;
 		return;
 	case WACOM_HID_WD_SERIALHI:
-		wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF);
-		wacom_wac->serial[0] |= ((__u64)value) << 32;
-		/*
-		 * Non-USI EMR devices may contain additional tool type
-		 * information here. See WACOM_HID_WD_TOOLTYPE case for
-		 * more details.
-		 */
-		if (value >> 20 == 1) {
-			wacom_wac->id[0] |= value & 0xFFFFF;
+		if (value) {
+			wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF);
+			wacom_wac->serial[0] |= ((__u64)value) << 32;
+			/*
+			 * Non-USI EMR devices may contain additional tool type
+			 * information here. See WACOM_HID_WD_TOOLTYPE case for
+			 * more details.
+			 */
+			if (value >> 20 == 1) {
+				wacom_wac->id[0] |= value & 0xFFFFF;
+			}
 		}
 		return;
 	case WACOM_HID_WD_TOOLTYPE:
@@ -2205,7 +2272,7 @@
 		input_report_key(input, wacom_wac->tool[0], prox);
 		if (wacom_wac->serial[0]) {
 			input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]);
-			input_report_abs(input, ABS_MISC, id);
+			input_report_abs(input, ABS_MISC, prox ? id : 0);
 		}
 
 		wacom_wac->hid_data.tipswitch = false;
@@ -2216,6 +2283,7 @@
 	if (!prox) {
 		wacom_wac->tool[0] = 0;
 		wacom_wac->id[0] = 0;
+		wacom_wac->serial[0] = 0;
 	}
 }
 
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 060df71..bcbb031 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -936,14 +936,10 @@
 
 void vmbus_hvsock_device_unregister(struct vmbus_channel *channel)
 {
-	mutex_lock(&vmbus_connection.channel_mutex);
-
 	BUG_ON(!is_hvsock_channel(channel));
 
 	channel->rescind = true;
 	vmbus_device_unregister(channel->device_obj);
-
-	mutex_unlock(&vmbus_connection.channel_mutex);
 }
 EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister);
 
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index daa75bd..2364281 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -170,6 +170,10 @@
 		out_src = smsg_out;
 		break;
 
+	case WRITE_TO_FILE:
+		out_src = fcopy_transaction.fcopy_msg;
+		out_len = sizeof(struct hv_do_fcopy);
+		break;
 	default:
 		out_src = fcopy_transaction.fcopy_msg;
 		out_len = fcopy_transaction.recv_len;
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index bc9cebc..c2a2ce8 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -144,6 +144,11 @@
 		.driver_data = (kernel_ulong_t)0,
 	},
 	{
+		/* Lewisburg PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa1a6),
+		.driver_data = (kernel_ulong_t)0,
+	},
+	{
 		/* Gemini Lake */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
@@ -158,6 +163,11 @@
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Cedar Fork PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x18e1),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c
index 9414900..f129869 100644
--- a/drivers/hwtracing/stm/core.c
+++ b/drivers/hwtracing/stm/core.c
@@ -1119,7 +1119,7 @@
 
 	stm_source_link_drop(src);
 
-	device_destroy(&stm_source_class, src->dev.devt);
+	device_unregister(&src->dev);
 }
 EXPORT_SYMBOL_GPL(stm_source_unregister_device);
 
diff --git a/drivers/i2c/busses/i2c-img-scb.c b/drivers/i2c/busses/i2c-img-scb.c
index 84fb35f..eb1d91b 100644
--- a/drivers/i2c/busses/i2c-img-scb.c
+++ b/drivers/i2c/busses/i2c-img-scb.c
@@ -1459,6 +1459,6 @@
 };
 module_platform_driver(img_scb_i2c_driver);
 
-MODULE_AUTHOR("James Hogan <james.hogan@imgtec.com>");
+MODULE_AUTHOR("James Hogan <jhogan@kernel.org>");
 MODULE_DESCRIPTION("IMG host I2C driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 01b2adf..eaf39e5 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -1451,6 +1451,7 @@
 		if (hwif_init(hwif) == 0) {
 			printk(KERN_INFO "%s: failed to initialize IDE "
 					 "interface\n", hwif->name);
+			device_unregister(hwif->portdev);
 			device_unregister(&hwif->gendev);
 			ide_disable_port(hwif);
 			continue;
diff --git a/drivers/ide/ide-scan-pci.c b/drivers/ide/ide-scan-pci.c
index 86aa88a..acf8748 100644
--- a/drivers/ide/ide-scan-pci.c
+++ b/drivers/ide/ide-scan-pci.c
@@ -56,6 +56,7 @@
 {
 	struct list_head *l;
 	struct pci_driver *d;
+	int ret;
 
 	list_for_each(l, &ide_pci_drivers) {
 		d = list_entry(l, struct pci_driver, node);
@@ -63,10 +64,14 @@
 			const struct pci_device_id *id =
 				pci_match_id(d->id_table, dev);
 
-			if (id != NULL && d->probe(dev, id) >= 0) {
-				dev->driver = d;
-				pci_dev_get(dev);
-				return 1;
+			if (id != NULL) {
+				pci_assign_irq(dev);
+				ret = d->probe(dev, id);
+				if (ret >= 0) {
+					dev->driver = d;
+					pci_dev_get(dev);
+					return 1;
+				}
 			}
 		}
 	}
diff --git a/drivers/ide/setup-pci.c b/drivers/ide/setup-pci.c
index 112d2fe..fdc8e81 100644
--- a/drivers/ide/setup-pci.c
+++ b/drivers/ide/setup-pci.c
@@ -179,6 +179,7 @@
 /**
  *	ide_pci_enable	-	do PCI enables
  *	@dev: PCI device
+ *	@bars: PCI BARs mask
  *	@d: IDE port info
  *
  *	Enable the IDE PCI device. We attempt to enable the device in full
@@ -189,9 +190,10 @@
  *	Returns zero on success or an error code
  */
 
-static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d)
+static int ide_pci_enable(struct pci_dev *dev, int bars,
+			  const struct ide_port_info *d)
 {
-	int ret, bars;
+	int ret;
 
 	if (pci_enable_device(dev)) {
 		ret = pci_enable_device_io(dev);
@@ -216,18 +218,6 @@
 		goto out;
 	}
 
-	if (d->host_flags & IDE_HFLAG_SINGLE)
-		bars = (1 << 2) - 1;
-	else
-		bars = (1 << 4) - 1;
-
-	if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) {
-		if (d->host_flags & IDE_HFLAG_CS5520)
-			bars |= (1 << 2);
-		else
-			bars |= (1 << 4);
-	}
-
 	ret = pci_request_selected_regions(dev, bars, d->name);
 	if (ret < 0)
 		printk(KERN_ERR "%s %s: can't reserve resources\n",
@@ -403,6 +393,7 @@
 /**
  *	ide_setup_pci_controller	-	set up IDE PCI
  *	@dev: PCI device
+ *	@bars: PCI BARs mask
  *	@d: IDE port info
  *	@noisy: verbose flag
  *
@@ -411,7 +402,7 @@
  *	and enables it if need be
  */
 
-static int ide_setup_pci_controller(struct pci_dev *dev,
+static int ide_setup_pci_controller(struct pci_dev *dev, int bars,
 				    const struct ide_port_info *d, int noisy)
 {
 	int ret;
@@ -420,7 +411,7 @@
 	if (noisy)
 		ide_setup_pci_noise(dev, d);
 
-	ret = ide_pci_enable(dev, d);
+	ret = ide_pci_enable(dev, bars, d);
 	if (ret < 0)
 		goto out;
 
@@ -428,16 +419,20 @@
 	if (ret < 0) {
 		printk(KERN_ERR "%s %s: error accessing PCI regs\n",
 			d->name, pci_name(dev));
-		goto out;
+		goto out_free_bars;
 	}
 	if (!(pcicmd & PCI_COMMAND_IO)) {	/* is device disabled? */
 		ret = ide_pci_configure(dev, d);
 		if (ret < 0)
-			goto out;
+			goto out_free_bars;
 		printk(KERN_INFO "%s %s: device enabled (Linux)\n",
 			d->name, pci_name(dev));
 	}
 
+	goto out;
+
+out_free_bars:
+	pci_release_selected_regions(dev, bars);
 out:
 	return ret;
 }
@@ -540,13 +535,28 @@
 {
 	struct pci_dev *pdev[] = { dev1, dev2 };
 	struct ide_host *host;
-	int ret, i, n_ports = dev2 ? 4 : 2;
+	int ret, i, n_ports = dev2 ? 4 : 2, bars;
 	struct ide_hw hw[4], *hws[] = { NULL, NULL, NULL, NULL };
 
+	if (d->host_flags & IDE_HFLAG_SINGLE)
+		bars = (1 << 2) - 1;
+	else
+		bars = (1 << 4) - 1;
+
+	if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) {
+		if (d->host_flags & IDE_HFLAG_CS5520)
+			bars |= (1 << 2);
+		else
+			bars |= (1 << 4);
+	}
+
 	for (i = 0; i < n_ports / 2; i++) {
-		ret = ide_setup_pci_controller(pdev[i], d, !i);
-		if (ret < 0)
+		ret = ide_setup_pci_controller(pdev[i], bars, d, !i);
+		if (ret < 0) {
+			if (i == 1)
+				pci_release_selected_regions(pdev[0], bars);
 			goto out;
+		}
 
 		ide_pci_setup_ports(pdev[i], d, &hw[i*2], &hws[i*2]);
 	}
@@ -554,7 +564,7 @@
 	host = ide_host_alloc(d, hws, n_ports);
 	if (host == NULL) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_free_bars;
 	}
 
 	host->dev[0] = &dev1->dev;
@@ -576,7 +586,7 @@
 		 * do_ide_setup_pci_device() on the first device!
 		 */
 		if (ret < 0)
-			goto out;
+			goto out_free_bars;
 
 		/* fixup IRQ */
 		if (ide_pci_is_in_compatibility_mode(pdev[i])) {
@@ -589,6 +599,13 @@
 	ret = ide_host_register(host, d, hws);
 	if (ret)
 		ide_host_free(host);
+	else
+		goto out;
+
+out_free_bars:
+	i = n_ports / 2;
+	while (i--)
+		pci_release_selected_regions(pdev[i], bars);
 out:
 	return ret;
 }
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index e6706a0..47c3d7f 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -257,7 +257,7 @@
 	unsigned int vref_mv)
 {
 	struct ad7793_state *st = iio_priv(indio_dev);
-	int i, ret = -1;
+	int i, ret;
 	unsigned long long scale_uv;
 	u32 id;
 
@@ -266,7 +266,7 @@
 		return ret;
 
 	/* reset the serial interface */
-	ret = spi_write(st->sd.spi, (u8 *)&ret, sizeof(ret));
+	ret = ad_sd_reset(&st->sd, 32);
 	if (ret < 0)
 		goto out;
 	usleep_range(500, 2000); /* Wait for at least 500us */
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index d10bd0c..22c4c17 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -177,6 +177,34 @@
 }
 EXPORT_SYMBOL_GPL(ad_sd_read_reg);
 
+/**
+ * ad_sd_reset() - Reset the serial interface
+ *
+ * @sigma_delta: The sigma delta device
+ * @reset_length: Number of SCLKs with DIN = 1
+ *
+ * Returns 0 on success, an error code otherwise.
+ **/
+int ad_sd_reset(struct ad_sigma_delta *sigma_delta,
+	unsigned int reset_length)
+{
+	uint8_t *buf;
+	unsigned int size;
+	int ret;
+
+	size = DIV_ROUND_UP(reset_length, 8);
+	buf = kcalloc(size, sizeof(*buf), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memset(buf, 0xff, size);
+	ret = spi_write(sigma_delta->spi, buf, size);
+	kfree(buf);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ad_sd_reset);
+
 static int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta,
 	unsigned int mode, unsigned int channel)
 {
diff --git a/drivers/iio/adc/mcp320x.c b/drivers/iio/adc/mcp320x.c
index 634717a..071dd23 100644
--- a/drivers/iio/adc/mcp320x.c
+++ b/drivers/iio/adc/mcp320x.c
@@ -17,6 +17,8 @@
  * MCP3204
  * MCP3208
  * ------------
+ * 13 bit converter
+ * MCP3301
  *
  * Datasheet can be found here:
  * http://ww1.microchip.com/downloads/en/DeviceDoc/21293C.pdf  mcp3001
@@ -96,7 +98,7 @@
 }
 
 static int mcp320x_adc_conversion(struct mcp320x *adc, u8 channel,
-				  bool differential, int device_index)
+				  bool differential, int device_index, int *val)
 {
 	int ret;
 
@@ -117,19 +119,25 @@
 
 	switch (device_index) {
 	case mcp3001:
-		return (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3);
+		*val = (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3);
+		return 0;
 	case mcp3002:
 	case mcp3004:
 	case mcp3008:
-		return (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6);
+		*val = (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6);
+		return 0;
 	case mcp3201:
-		return (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1);
+		*val = (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1);
+		return 0;
 	case mcp3202:
 	case mcp3204:
 	case mcp3208:
-		return (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4);
+		*val = (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4);
+		return 0;
 	case mcp3301:
-		return sign_extend32((adc->rx_buf[0] & 0x1f) << 8 | adc->rx_buf[1], 12);
+		*val = sign_extend32((adc->rx_buf[0] & 0x1f) << 8
+				    | adc->rx_buf[1], 12);
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -150,12 +158,10 @@
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
 		ret = mcp320x_adc_conversion(adc, channel->address,
-			channel->differential, device_index);
-
+			channel->differential, device_index, val);
 		if (ret < 0)
 			goto out;
 
-		*val = ret;
 		ret = IIO_VAL_INT;
 		break;
 
@@ -312,6 +318,7 @@
 	indio_dev->name = spi_get_device_id(spi)->name;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->info = &mcp320x_info;
+	spi_set_drvdata(spi, indio_dev);
 
 	chip_info = &mcp320x_chip_infos[spi_get_device_id(spi)->driver_data];
 	indio_dev->channels = chip_info->channels;
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index e3c15f8..4df32cf 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -1666,7 +1666,7 @@
 
 	num_channels = of_property_count_u32_elems(node, "st,adc-channels");
 	if (num_channels < 0 ||
-	    num_channels >= adc_info->max_channels) {
+	    num_channels > adc_info->max_channels) {
 		dev_err(&indio_dev->dev, "Bad st,adc-channels?\n");
 		return num_channels < 0 ? num_channels : -EINVAL;
 	}
diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c
index d121002..e0dc204 100644
--- a/drivers/iio/adc/ti-ads1015.c
+++ b/drivers/iio/adc/ti-ads1015.c
@@ -52,7 +52,7 @@
 
 #define ADS1015_CFG_COMP_QUE_MASK	GENMASK(1, 0)
 #define ADS1015_CFG_COMP_LAT_MASK	BIT(2)
-#define ADS1015_CFG_COMP_POL_MASK	BIT(2)
+#define ADS1015_CFG_COMP_POL_MASK	BIT(3)
 #define ADS1015_CFG_COMP_MODE_MASK	BIT(4)
 #define ADS1015_CFG_DR_MASK	GENMASK(7, 5)
 #define ADS1015_CFG_MOD_MASK	BIT(8)
@@ -1017,10 +1017,12 @@
 
 		switch (irq_trig) {
 		case IRQF_TRIGGER_LOW:
-			cfg_comp |= ADS1015_CFG_COMP_POL_LOW;
+			cfg_comp |= ADS1015_CFG_COMP_POL_LOW <<
+					ADS1015_CFG_COMP_POL_SHIFT;
 			break;
 		case IRQF_TRIGGER_HIGH:
-			cfg_comp |= ADS1015_CFG_COMP_POL_HIGH;
+			cfg_comp |= ADS1015_CFG_COMP_POL_HIGH <<
+					ADS1015_CFG_COMP_POL_SHIFT;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c
index 1edd99f..e3cfb91 100644
--- a/drivers/iio/adc/twl4030-madc.c
+++ b/drivers/iio/adc/twl4030-madc.c
@@ -887,21 +887,27 @@
 
 	/* Enable 3v1 bias regulator for MADC[3:6] */
 	madc->usb3v1 = devm_regulator_get(madc->dev, "vusb3v1");
-	if (IS_ERR(madc->usb3v1))
-		return -ENODEV;
+	if (IS_ERR(madc->usb3v1)) {
+		ret = -ENODEV;
+		goto err_i2c;
+	}
 
 	ret = regulator_enable(madc->usb3v1);
-	if (ret)
+	if (ret) {
 		dev_err(madc->dev, "could not enable 3v1 bias regulator\n");
+		goto err_i2c;
+	}
 
 	ret = iio_device_register(iio_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "could not register iio device\n");
-		goto err_i2c;
+		goto err_usb3v1;
 	}
 
 	return 0;
 
+err_usb3v1:
+	regulator_disable(madc->usb3v1);
 err_i2c:
 	twl4030_madc_set_current_generator(madc, 0, 0);
 err_current_generator:
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index d99bb14..02e833b 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -463,8 +463,17 @@
 	u8 drdy_mask;
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
 
-	if (!sdata->sensor_settings->drdy_irq.addr)
+	if (!sdata->sensor_settings->drdy_irq.addr) {
+		/*
+		 * there are some devices (e.g. LIS3MDL) where drdy line is
+		 * routed to a given pin and it is not possible to select a
+		 * different one. Take into account irq status register
+		 * to understand if irq trigger can be properly supported
+		 */
+		if (sdata->sensor_settings->drdy_irq.addr_stat_drdy)
+			sdata->hw_irq_trigger = enable;
 		return 0;
+	}
 
 	/* Enable/Disable the interrupt generator 1. */
 	if (sdata->sensor_settings->drdy_irq.ig1.en_addr > 0) {
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 17ec4ce..a47428b 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -310,8 +310,10 @@
 	ret = indio_dev->info->debugfs_reg_access(indio_dev,
 						  indio_dev->cached_reg_addr,
 						  0, &val);
-	if (ret)
+	if (ret) {
 		dev_err(indio_dev->dev.parent, "%s: read failed\n", __func__);
+		return ret;
+	}
 
 	len = snprintf(buf, sizeof(buf), "0x%X\n", val);
 
diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c
index e68368b..08aafba 100644
--- a/drivers/iio/magnetometer/st_magn_core.c
+++ b/drivers/iio/magnetometer/st_magn_core.c
@@ -315,6 +315,10 @@
 				},
 			},
 		},
+		.drdy_irq = {
+			/* drdy line is routed drdy pin */
+			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
+		},
 		.multi_read_bit = true,
 		.bootime = 2,
 	},
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 0d2ea3e..8f26428 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -573,7 +573,7 @@
 	u8 osrs = BMP280_OSRS_TEMP_X(data->oversampling_temp + 1) |
 		  BMP280_OSRS_PRESS_X(data->oversampling_press + 1);
 
-	ret = regmap_update_bits(data->regmap, BMP280_REG_CTRL_MEAS,
+	ret = regmap_write_bits(data->regmap, BMP280_REG_CTRL_MEAS,
 				 BMP280_OSRS_TEMP_MASK |
 				 BMP280_OSRS_PRESS_MASK |
 				 BMP280_MODE_MASK,
diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c
index 9b90534..eb212f8c 100644
--- a/drivers/iio/trigger/stm32-timer-trigger.c
+++ b/drivers/iio/trigger/stm32-timer-trigger.c
@@ -174,6 +174,7 @@
 		clk_disable(priv->clk);
 
 	/* Stop timer */
+	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0);
 	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0);
 	regmap_write(priv->regmap, TIM_PSC, 0);
 	regmap_write(priv->regmap, TIM_ARR, 0);
@@ -715,8 +716,9 @@
 	if (ret)
 		return ret;
 
+	/* TIMx_ARR register shouldn't be buffered (ARPE=0) */
+	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0);
 	regmap_write(priv->regmap, TIM_ARR, preset);
-	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, TIM_CR1_ARPE);
 
 	return len;
 }
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 30825bb..8861c05 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -100,6 +100,8 @@
 	if (ret)
 		goto pid_query_error;
 
+	nlmsg_end(skb, nlh);
+
 	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
 		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
 
@@ -170,6 +172,8 @@
 				&pm_msg->loc_addr, IWPM_NLA_MANAGE_ADDR);
 	if (ret)
 		goto add_mapping_error;
+
+	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
 	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
@@ -246,6 +250,8 @@
 				&pm_msg->rem_addr, IWPM_NLA_QUERY_REMOTE_ADDR);
 	if (ret)
 		goto query_mapping_error;
+
+	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
 	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
@@ -308,6 +314,8 @@
 	if (ret)
 		goto remove_mapping_error;
 
+	nlmsg_end(skb, nlh);
+
 	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index c81c559..3c4faad 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -597,6 +597,9 @@
 				&mapping_num, IWPM_NLA_MAPINFO_SEND_NUM);
 	if (ret)
 		goto mapinfo_num_error;
+
+	nlmsg_end(skb, nlh);
+
 	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
@@ -678,6 +681,8 @@
 			if (ret)
 				goto send_mapping_info_unlock;
 
+			nlmsg_end(skb, nlh);
+
 			iwpm_print_sockaddr(&map_info->local_sockaddr,
 				"send_mapping_info: Local sockaddr:");
 			iwpm_print_sockaddr(&map_info->mapped_sockaddr,
diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index 70ad19c..88bdafb 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -432,8 +432,10 @@
 	atomic_set(&qp->qp_sec->error_list_count, 0);
 	init_completion(&qp->qp_sec->error_complete);
 	ret = security_ib_alloc_security(&qp->qp_sec->security);
-	if (ret)
+	if (ret) {
 		kfree(qp->qp_sec);
+		qp->qp_sec = NULL;
+	}
 
 	return ret;
 }
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 4ab30d8..52a2cf2 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3869,15 +3869,15 @@
 	resp.raw_packet_caps = attr.raw_packet_caps;
 	resp.response_length += sizeof(resp.raw_packet_caps);
 
-	if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps))
+	if (ucore->outlen < resp.response_length + sizeof(resp.tm_caps))
 		goto end;
 
-	resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size;
-	resp.xrq_caps.max_num_tags      = attr.xrq_caps.max_num_tags;
-	resp.xrq_caps.max_ops		= attr.xrq_caps.max_ops;
-	resp.xrq_caps.max_sge		= attr.xrq_caps.max_sge;
-	resp.xrq_caps.flags		= attr.xrq_caps.flags;
-	resp.response_length += sizeof(resp.xrq_caps);
+	resp.tm_caps.max_rndv_hdr_size	= attr.tm_caps.max_rndv_hdr_size;
+	resp.tm_caps.max_num_tags	= attr.tm_caps.max_num_tags;
+	resp.tm_caps.max_ops		= attr.tm_caps.max_ops;
+	resp.tm_caps.max_sge		= attr.tm_caps.max_sge;
+	resp.tm_caps.flags		= attr.tm_caps.flags;
+	resp.response_length += sizeof(resp.tm_caps);
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index ee9e27d..de57d6c 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1646,7 +1646,7 @@
 	 */
 	if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) {
 		if (attr.qp_state >= IB_QPS_INIT) {
-			if (qp->device->get_link_layer(qp->device, attr.port_num) !=
+			if (rdma_port_get_link_layer(qp->device, attr.port_num) !=
 			    IB_LINK_LAYER_INFINIBAND)
 				return true;
 			goto lid_check;
@@ -1655,7 +1655,7 @@
 
 	/* Can't get a quick answer, iterate over all ports */
 	for (port = 0; port < qp->device->phys_port_cnt; port++)
-		if (qp->device->get_link_layer(qp->device, port) !=
+		if (rdma_port_get_link_layer(qp->device, port) !=
 		    IB_LINK_LAYER_INFINIBAND)
 			num_eth_ports++;
 
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index b3ad37f..ecbac91 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -93,11 +93,13 @@
 	struct ib_device		ibdev;
 	struct list_head		list;
 	unsigned long			flags;
-#define BNXT_RE_FLAG_NETDEV_REGISTERED	0
-#define BNXT_RE_FLAG_IBDEV_REGISTERED	1
-#define BNXT_RE_FLAG_GOT_MSIX		2
-#define BNXT_RE_FLAG_RCFW_CHANNEL_EN	8
-#define BNXT_RE_FLAG_QOS_WORK_REG	16
+#define BNXT_RE_FLAG_NETDEV_REGISTERED		0
+#define BNXT_RE_FLAG_IBDEV_REGISTERED		1
+#define BNXT_RE_FLAG_GOT_MSIX			2
+#define BNXT_RE_FLAG_HAVE_L2_REF		3
+#define BNXT_RE_FLAG_RCFW_CHANNEL_EN		4
+#define BNXT_RE_FLAG_QOS_WORK_REG		5
+#define BNXT_RE_FLAG_TASK_IN_PROG		6
 	struct net_device		*netdev;
 	unsigned int			version, major, minor;
 	struct bnxt_en_dev		*en_dev;
@@ -108,6 +110,8 @@
 
 	struct delayed_work		worker;
 	u8				cur_prio_map;
+	u8				active_speed;
+	u8				active_width;
 
 	/* FP Notification Queue (CQ & SRQ) */
 	struct tasklet_struct		nq_task;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 01eee15..0d89621 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -259,14 +259,9 @@
 	port_attr->sm_sl = 0;
 	port_attr->subnet_timeout = 0;
 	port_attr->init_type_reply = 0;
-	/* call the underlying netdev's ethtool hooks to query speed settings
-	 * for which we acquire rtnl_lock _only_ if it's registered with
-	 * IB stack to avoid race in the NETDEV_UNREG path
-	 */
-	if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
-		if (ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed,
-				     &port_attr->active_width))
-			return -EINVAL;
+	port_attr->active_speed = rdev->active_speed;
+	port_attr->active_width = rdev->active_width;
+
 	return 0;
 }
 
@@ -319,6 +314,7 @@
 	struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
 	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+	struct bnxt_qplib_gid *gid_to_del;
 
 	/* Delete the entry from the hardware */
 	ctx = *context;
@@ -328,11 +324,25 @@
 	if (sgid_tbl && sgid_tbl->active) {
 		if (ctx->idx >= sgid_tbl->max)
 			return -EINVAL;
+		gid_to_del = &sgid_tbl->tbl[ctx->idx];
+		/* DEL_GID is called in WQ context(netdevice_event_work_handler)
+		 * or via the ib_unregister_device path. In the former case QP1
+		 * may not be destroyed yet, in which case just return as FW
+		 * needs that entry to be present and will fail it's deletion.
+		 * We could get invoked again after QP1 is destroyed OR get an
+		 * ADD_GID call with a different GID value for the same index
+		 * where we issue MODIFY_GID cmd to update the GID entry -- TBD
+		 */
+		if (ctx->idx == 0 &&
+		    rdma_link_local_addr((struct in6_addr *)gid_to_del) &&
+		    ctx->refcnt == 1 && rdev->qp1_sqp) {
+			dev_dbg(rdev_to_dev(rdev),
+				"Trying to delete GID0 while QP1 is alive\n");
+			return -EFAULT;
+		}
 		ctx->refcnt--;
 		if (!ctx->refcnt) {
-			rc = bnxt_qplib_del_sgid(sgid_tbl,
-						 &sgid_tbl->tbl[ctx->idx],
-						 true);
+			rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true);
 			if (rc) {
 				dev_err(rdev_to_dev(rdev),
 					"Failed to remove GID: %#x", rc);
@@ -816,6 +826,8 @@
 
 		kfree(rdev->sqp_ah);
 		kfree(rdev->qp1_sqp);
+		rdev->qp1_sqp = NULL;
+		rdev->sqp_ah = NULL;
 	}
 
 	if (!IS_ERR_OR_NULL(qp->rumem))
@@ -1436,11 +1448,14 @@
 		qp->qplib_qp.modify_flags |=
 				CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
 		qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu);
+		qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu);
 	} else if (qp_attr->qp_state == IB_QPS_RTR) {
 		qp->qplib_qp.modify_flags |=
 			CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
 		qp->qplib_qp.path_mtu =
 			__from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu));
+		qp->qplib_qp.mtu =
+			ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
 	}
 
 	if (qp_attr_mask & IB_QP_TIMEOUT) {
@@ -1551,43 +1566,46 @@
 {
 	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
 	struct bnxt_re_dev *rdev = qp->rdev;
-	struct bnxt_qplib_qp qplib_qp;
+	struct bnxt_qplib_qp *qplib_qp;
 	int rc;
 
-	memset(&qplib_qp, 0, sizeof(struct bnxt_qplib_qp));
-	qplib_qp.id = qp->qplib_qp.id;
-	qplib_qp.ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
+	qplib_qp = kzalloc(sizeof(*qplib_qp), GFP_KERNEL);
+	if (!qplib_qp)
+		return -ENOMEM;
 
-	rc = bnxt_qplib_query_qp(&rdev->qplib_res, &qplib_qp);
+	qplib_qp->id = qp->qplib_qp.id;
+	qplib_qp->ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
+
+	rc = bnxt_qplib_query_qp(&rdev->qplib_res, qplib_qp);
 	if (rc) {
 		dev_err(rdev_to_dev(rdev), "Failed to query HW QP");
-		return rc;
+		goto out;
 	}
-	qp_attr->qp_state = __to_ib_qp_state(qplib_qp.state);
-	qp_attr->en_sqd_async_notify = qplib_qp.en_sqd_async_notify ? 1 : 0;
-	qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp.access);
-	qp_attr->pkey_index = qplib_qp.pkey_index;
-	qp_attr->qkey = qplib_qp.qkey;
+	qp_attr->qp_state = __to_ib_qp_state(qplib_qp->state);
+	qp_attr->en_sqd_async_notify = qplib_qp->en_sqd_async_notify ? 1 : 0;
+	qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp->access);
+	qp_attr->pkey_index = qplib_qp->pkey_index;
+	qp_attr->qkey = qplib_qp->qkey;
 	qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
-	rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp.ah.flow_label,
-			qplib_qp.ah.host_sgid_index,
-			qplib_qp.ah.hop_limit,
-			qplib_qp.ah.traffic_class);
-	rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp.ah.dgid.data);
-	rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp.ah.sl);
-	ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp.ah.dmac);
-	qp_attr->path_mtu = __to_ib_mtu(qplib_qp.path_mtu);
-	qp_attr->timeout = qplib_qp.timeout;
-	qp_attr->retry_cnt = qplib_qp.retry_cnt;
-	qp_attr->rnr_retry = qplib_qp.rnr_retry;
-	qp_attr->min_rnr_timer = qplib_qp.min_rnr_timer;
-	qp_attr->rq_psn = qplib_qp.rq.psn;
-	qp_attr->max_rd_atomic = qplib_qp.max_rd_atomic;
-	qp_attr->sq_psn = qplib_qp.sq.psn;
-	qp_attr->max_dest_rd_atomic = qplib_qp.max_dest_rd_atomic;
-	qp_init_attr->sq_sig_type = qplib_qp.sig_type ? IB_SIGNAL_ALL_WR :
-							IB_SIGNAL_REQ_WR;
-	qp_attr->dest_qp_num = qplib_qp.dest_qpn;
+	rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp->ah.flow_label,
+			qplib_qp->ah.host_sgid_index,
+			qplib_qp->ah.hop_limit,
+			qplib_qp->ah.traffic_class);
+	rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp->ah.dgid.data);
+	rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp->ah.sl);
+	ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp->ah.dmac);
+	qp_attr->path_mtu = __to_ib_mtu(qplib_qp->path_mtu);
+	qp_attr->timeout = qplib_qp->timeout;
+	qp_attr->retry_cnt = qplib_qp->retry_cnt;
+	qp_attr->rnr_retry = qplib_qp->rnr_retry;
+	qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer;
+	qp_attr->rq_psn = qplib_qp->rq.psn;
+	qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic;
+	qp_attr->sq_psn = qplib_qp->sq.psn;
+	qp_attr->max_dest_rd_atomic = qplib_qp->max_dest_rd_atomic;
+	qp_init_attr->sq_sig_type = qplib_qp->sig_type ? IB_SIGNAL_ALL_WR :
+							 IB_SIGNAL_REQ_WR;
+	qp_attr->dest_qp_num = qplib_qp->dest_qpn;
 
 	qp_attr->cap.max_send_wr = qp->qplib_qp.sq.max_wqe;
 	qp_attr->cap.max_send_sge = qp->qplib_qp.sq.max_sge;
@@ -1596,7 +1614,9 @@
 	qp_attr->cap.max_inline_data = qp->qplib_qp.max_inline_data;
 	qp_init_attr->cap = qp_attr->cap;
 
-	return 0;
+out:
+	kfree(qplib_qp);
+	return rc;
 }
 
 /* Routine for sending QP1 packets for RoCE V1 an V2
@@ -1908,6 +1928,7 @@
 	switch (wr->opcode) {
 	case IB_WR_ATOMIC_CMP_AND_SWP:
 		wqe->type = BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP;
+		wqe->atomic.cmp_data = atomic_wr(wr)->compare_add;
 		wqe->atomic.swap_data = atomic_wr(wr)->swap;
 		break;
 	case IB_WR_ATOMIC_FETCH_AND_ADD:
@@ -3062,7 +3083,7 @@
 		return rc;
 	}
 
-	if (mr->npages && mr->pages) {
+	if (mr->pages) {
 		rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
 							&mr->qplib_frpl);
 		kfree(mr->pages);
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 82d1cbc..e7450ea 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1161,6 +1161,8 @@
 		}
 	}
 	set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags);
+	ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+			 &rdev->active_width);
 	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE);
 	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_GID_CHANGE);
 
@@ -1255,10 +1257,14 @@
 		else if (netif_carrier_ok(rdev->netdev))
 			bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
 					       IB_EVENT_PORT_ACTIVE);
+		ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+				 &rdev->active_width);
 		break;
 	default:
 		break;
 	}
+	smp_mb__before_atomic();
+	clear_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
 	kfree(re_work);
 }
 
@@ -1317,6 +1323,11 @@
 		break;
 
 	case NETDEV_UNREGISTER:
+		/* netdev notifier will call NETDEV_UNREGISTER again later since
+		 * we are still holding the reference to the netdev
+		 */
+		if (test_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags))
+			goto exit;
 		bnxt_re_ib_unreg(rdev, false);
 		bnxt_re_remove_one(rdev);
 		bnxt_re_dev_unreg(rdev);
@@ -1335,6 +1346,7 @@
 			re_work->vlan_dev = (real_dev == netdev ?
 					     NULL : netdev);
 			INIT_WORK(&re_work->work, bnxt_re_task);
+			set_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
 			queue_work(bnxt_re_wq, &re_work->work);
 		}
 	}
@@ -1375,6 +1387,22 @@
 
 static void __exit bnxt_re_mod_exit(void)
 {
+	struct bnxt_re_dev *rdev;
+	LIST_HEAD(to_be_deleted);
+
+	mutex_lock(&bnxt_re_dev_lock);
+	/* Free all adapter allocated resources */
+	if (!list_empty(&bnxt_re_dev_list))
+		list_splice_init(&bnxt_re_dev_list, &to_be_deleted);
+	mutex_unlock(&bnxt_re_dev_lock);
+
+	list_for_each_entry(rdev, &to_be_deleted, list) {
+		dev_info(rdev_to_dev(rdev), "Unregistering Device");
+		bnxt_re_dev_stop(rdev);
+		bnxt_re_ib_unreg(rdev, true);
+		bnxt_re_remove_one(rdev);
+		bnxt_re_dev_unreg(rdev);
+	}
 	unregister_netdevi