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-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
index 33e96f7..147d4e8 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
+++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
@@ -14,3 +14,11 @@
 		Show or set the gain boost of the amp, from 0-31 range.
 		18 = indoors (default)
 		14 = outdoors
+
+What		/sys/bus/iio/devices/iio:deviceX/noise_level_tripped
+Date:		May 2017
+KernelVersion:	4.13
+Contact:	Matt Ranostay <matt.ranostay@konsulko.com>
+Description:
+		When 1 the noise level is over the trip level and not reporting
+		valid data
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 676fdf5..5cbb6f0 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -211,7 +211,9 @@
 		device, after it has been suspended at run time, from a resume
 		request to the moment the device will be ready to process I/O,
 		in microseconds.  If it is equal to 0, however, this means that
-		the PM QoS resume latency may be arbitrary.
+		the PM QoS resume latency may be arbitrary and the special value
+		"n/a" means that user space cannot accept any resume latency at
+		all for the given device.
 
 		Not all drivers support this attribute.  If it isn't supported,
 		it is not present.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-swap b/Documentation/ABI/testing/sysfs-kernel-mm-swap
index 587db52..9467201 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-swap
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-swap
@@ -14,13 +14,3 @@
 		still used for tmpfs etc. other users.  If set to
 		false, the global swap readahead algorithm will be
 		used for all swappable pages.
-
-What:		/sys/kernel/mm/swap/vma_ra_max_order
-Date:		August 2017
-Contact:	Linux memory management mailing list <linux-mm@kvack.org>
-Description:	The max readahead size in order for VMA based swap readahead
-
-		VMA based swap readahead algorithm will readahead at
-		most 1 << max_order pages for each readahead.  The
-		real readahead size for each readahead will be scaled
-		according to the estimation algorithm.
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/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index 8282099..5da1018 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -352,44 +352,30 @@
 ----------------------
 
 .. kernel-doc:: include/linux/rcupdate.h
-   :external:
 
 .. kernel-doc:: include/linux/rcupdate_wait.h
-   :external:
 
 .. kernel-doc:: include/linux/rcutree.h
-   :external:
 
 .. kernel-doc:: kernel/rcu/tree.c
-   :external:
 
 .. kernel-doc:: kernel/rcu/tree_plugin.h
-   :external:
 
 .. kernel-doc:: kernel/rcu/tree_exp.h
-   :external:
 
 .. kernel-doc:: kernel/rcu/update.c
-   :external:
 
 .. kernel-doc:: include/linux/srcu.h
-   :external:
 
 .. kernel-doc:: kernel/rcu/srcutree.c
-   :external:
 
 .. kernel-doc:: include/linux/rculist_bl.h
-   :external:
 
 .. kernel-doc:: include/linux/rculist.h
-   :external:
 
 .. kernel-doc:: include/linux/rculist_nulls.h
-   :external:
 
 .. kernel-doc:: include/linux/rcu_sync.h
-   :external:
 
 .. kernel-doc:: kernel/rcu/sync.c
-   :external:
 
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/iio/proximity/as3935.txt b/Documentation/devicetree/bindings/iio/proximity/as3935.txt
index 38d7431..b6c1afa 100644
--- a/Documentation/devicetree/bindings/iio/proximity/as3935.txt
+++ b/Documentation/devicetree/bindings/iio/proximity/as3935.txt
@@ -16,6 +16,10 @@
 	- ams,tuning-capacitor-pf: Calibration tuning capacitor stepping
 	  value 0 - 120pF. This will require using the calibration data from
 	  the manufacturer.
+	- ams,nflwdth: Set the noise and watchdog threshold register on
+	  startup. This will need to set according to the noise from the
+	  MCU board, and possibly the local environment. Refer to the
+	  datasheet for the threshold settings.
 
 Example:
 
@@ -27,4 +31,5 @@
 	interrupt-parent = <&gpio1>;
 	interrupts = <16 1>;
 	ams,tuning-capacitor-pf = <80>;
+	ams,nflwdth = <0x44>;
 };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
index 4c29cda..5eb108e 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
@@ -99,7 +99,7 @@
 			compatible = "arm,gic-v3-its";
 			msi-controller;
 			#msi-cells = <1>;
-			reg = <0x0 0x2c200000 0 0x200000>;
+			reg = <0x0 0x2c200000 0 0x20000>;
 		};
 	};
 
@@ -124,14 +124,14 @@
 			compatible = "arm,gic-v3-its";
 			msi-controller;
 			#msi-cells = <1>;
-			reg = <0x0 0x2c200000 0 0x200000>;
+			reg = <0x0 0x2c200000 0 0x20000>;
 		};
 
 		gic-its@2c400000 {
 			compatible = "arm,gic-v3-its";
 			msi-controller;
 			#msi-cells = <1>;
-			reg = <0x0 0x2c400000 0 0x200000>;
+			reg = <0x0 0x2c400000 0 0x20000>;
 		};
 
 		ppi-partitions {
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/mmc/marvell,xenon-sdhci.txt b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
index b878a1e..ed1456f 100644
--- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
@@ -16,11 +16,13 @@
 
 - clocks:
   Array of clocks required for SDHC.
-  Require at least input clock for Xenon IP core.
+  Require at least input clock for Xenon IP core. For Armada AP806 and
+  CP110, the AXI clock is also mandatory.
 
 - clock-names:
   Array of names corresponding to clocks property.
   The input clock for Xenon IP core should be named as "core".
+  The input clock for the AXI bus must be named as "axi".
 
 - reg:
   * For "marvell,armada-3700-sdhci", two register areas.
@@ -106,8 +108,8 @@
 		compatible = "marvell,armada-ap806-sdhci";
 		reg = <0xaa0000 0x1000>;
 		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>
-		clocks = <&emmc_clk>;
-		clock-names = "core";
+		clocks = <&emmc_clk>,<&axi_clk>;
+		clock-names = "core", "axi";
 		bus-width = <4>;
 		marvell,xenon-phy-slow-mode;
 		marvell,xenon-tun-count = <11>;
@@ -126,8 +128,8 @@
 		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>
 		vqmmc-supply = <&sd_vqmmc_regulator>;
 		vmmc-supply = <&sd_vmmc_regulator>;
-		clocks = <&sdclk>;
-		clock-names = "core";
+		clocks = <&sdclk>, <&axi_clk>;
+		clock-names = "core", "axi";
 		bus-width = <4>;
 		marvell,xenon-tun-count = <9>;
 	};
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/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 0500193..d477024 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -36,6 +36,7 @@
   * Intel Gemini Lake (SOC)
   * Intel Cannon Lake-H (PCH)
   * Intel Cannon Lake-LP (PCH)
+  * Intel Cedar Fork (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 329e740..f6f8038 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -1108,14 +1108,6 @@
     ld
 	Link target. Often, LDFLAGS_$@ is used to set specific options to ld.
 
-    objcopy
-	Copy binary. Uses OBJCOPYFLAGS usually specified in
-	arch/$(ARCH)/Makefile.
-	OBJCOPYFLAGS_$@ may be used to set additional options.
-
-    gzip
-	Compress target. Use maximum compression to compress target.
-
 	Example:
 		#arch/x86/boot/Makefile
 		LDFLAGS_bootsect := -Ttext 0x0 -s --oformat binary
@@ -1139,6 +1131,19 @@
 	      resulting in the target file being recompiled for no
 	      obvious reason.
 
+    objcopy
+	Copy binary. Uses OBJCOPYFLAGS usually specified in
+	arch/$(ARCH)/Makefile.
+	OBJCOPYFLAGS_$@ may be used to set additional options.
+
+    gzip
+	Compress target. Use maximum compression to compress target.
+
+	Example:
+		#arch/x86/boot/compressed/Makefile
+		$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
+			$(call if_changed,gzip)
+
     dtc
 	Create flattened device tree blob object suitable for linking
 	into vmlinux. Device tree blobs linked into vmlinux are placed
@@ -1219,7 +1224,7 @@
 	that may be shared between individual architectures.
 	The recommended approach how to use a generic header file is
 	to list the file in the Kbuild file.
-	See "7.3 generic-y" for further info on syntax etc.
+	See "7.2 generic-y" for further info on syntax etc.
 
 --- 6.11 Post-link pass
 
@@ -1254,13 +1259,13 @@
 arch/<arch>/include/asm/ to list asm files coming from asm-generic.
 See subsequent chapter for the syntax of the Kbuild file.
 
-	--- 7.1 no-export-headers
+--- 7.1 no-export-headers
 
 	no-export-headers is essentially used by include/uapi/linux/Kbuild to
 	avoid exporting specific headers (e.g. kvm.h) on architectures that do
 	not support it. It should be avoided as much as possible.
 
-	--- 7.2 generic-y
+--- 7.2 generic-y
 
 	If an architecture uses a verbatim copy of a header from
 	include/asm-generic then this is listed in the file
@@ -1287,7 +1292,7 @@
 		Example: termios.h
 			#include <asm-generic/termios.h>
 
-	--- 7.3 generated-y
+--- 7.3 generated-y
 
 	If an architecture generates other header files alongside generic-y
 	wrappers, generated-y specifies them.
@@ -1299,7 +1304,7 @@
 			#arch/x86/include/asm/Kbuild
 			generated-y += syscalls_32.h
 
-	--- 7.5 mandatory-y
+--- 7.4 mandatory-y
 
 	mandatory-y is essentially used by include/uapi/asm-generic/Kbuild.asm
 	to define the minimum set of headers that must be exported in
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 57f52cd..9ba04c0 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -2387,7 +2387,7 @@
 	and packet type ID), so in a "gatewayed" configuration, all
 	outgoing traffic will generally use the same device.  Incoming
 	traffic may also end up on a single device, but that is
-	dependent upon the balancing policy of the peer's 8023.ad
+	dependent upon the balancing policy of the peer's 802.3ad
 	implementation.  In a "local" configuration, traffic will be
 	distributed across the devices in the bond.
 
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/process/index.rst b/Documentation/process/index.rst
index 82fc399..61e43cc 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -25,6 +25,7 @@
    submitting-patches
    coding-style
    email-clients
+   kernel-enforcement-statement
 
 Other guides to the community that are of interest to most developers are: 
 
diff --git a/Documentation/process/kernel-enforcement-statement.rst b/Documentation/process/kernel-enforcement-statement.rst
new file mode 100644
index 0000000..1e23d42
--- /dev/null
+++ b/Documentation/process/kernel-enforcement-statement.rst
@@ -0,0 +1,147 @@
+﻿Linux Kernel Enforcement Statement
+----------------------------------
+
+As developers of the Linux kernel, we have a keen interest in how our software
+is used and how the license for our software is enforced.  Compliance with the
+reciprocal sharing obligations of GPL-2.0 is critical to the long-term
+sustainability of our software and community.
+
+Although there is a right to enforce the separate copyright interests in the
+contributions made to our community, we share an interest in ensuring that
+individual enforcement actions are conducted in a manner that benefits our
+community and do not have an unintended negative impact on the health and
+growth of our software ecosystem.  In order to deter unhelpful enforcement
+actions, we agree that it is in the best interests of our development
+community to undertake the following commitment to users of the Linux kernel
+on behalf of ourselves and any successors to our copyright interests:
+
+    Notwithstanding the termination provisions of the GPL-2.0, we agree that
+    it is in the best interests of our development community to adopt the
+    following provisions of GPL-3.0 as additional permissions under our
+    license with respect to any non-defensive assertion of rights under the
+    license.
+
+	However, if you cease all violation of this License, then your license
+	from a particular copyright holder is reinstated (a) provisionally,
+	unless and until the copyright holder explicitly and finally
+	terminates your license, and (b) permanently, if the copyright holder
+	fails to notify you of the violation by some reasonable means prior to
+	60 days after the cessation.
+
+	Moreover, your license from a particular copyright holder is
+	reinstated permanently if the copyright holder notifies you of the
+	violation by some reasonable means, this is the first time you have
+	received notice of violation of this License (for any work) from that
+	copyright holder, and you cure the violation prior to 30 days after
+	your receipt of the notice.
+
+Our intent in providing these assurances is to encourage more use of the
+software.  We want companies and individuals to use, modify and distribute
+this software.  We want to work with users in an open and transparent way to
+eliminate any uncertainty about our expectations regarding compliance or
+enforcement that might limit adoption of our software.  We view legal action
+as a last resort, to be initiated only when other community efforts have
+failed to resolve the problem.
+
+Finally, once a non-compliance issue is resolved, we hope the user will feel
+welcome to join us in our efforts on this project.  Working together, we will
+be stronger.
+
+Except where noted below, we speak only for ourselves, and not for any company
+we might work for today, have in the past, or will in the future.
+
+  - Bjorn Andersson (Linaro)
+  - Andrea Arcangeli (Red Hat)
+  - Neil Armstrong
+  - Jens Axboe
+  - Pablo Neira Ayuso
+  - Khalid Aziz
+  - Ralf Baechle
+  - Felipe Balbi
+  - Arnd Bergmann
+  - Ard Biesheuvel
+  - Paolo Bonzini (Red Hat)
+  - Christian Borntraeger
+  - Mark Brown (Linaro)
+  - Paul Burton
+  - Javier Martinez Canillas
+  - Rob Clark
+  - Jonathan Corbet
+  - Vivien Didelot (Savoir-faire Linux)
+  - Hans de Goede (Red Hat)
+  - Mel Gorman (SUSE)
+  - Sven Eckelmann
+  - Alex Elder (Linaro)
+  - Fabio Estevam
+  - Larry Finger
+  - Bhumika Goyal
+  - Andy Gross
+  - Juergen Gross
+  - Shawn Guo
+  - Ulf Hansson
+  - Tejun Heo
+  - Rob Herring
+  - Masami Hiramatsu
+  - Michal Hocko
+  - Simon Horman
+  - Johan Hovold (Hovold Consulting AB)
+  - Christophe JAILLET
+  - Olof Johansson
+  - Lee Jones (Linaro)
+  - Heiner Kallweit
+  - Srinivas Kandagatla
+  - Jan Kara
+  - Shuah Khan (Samsung)
+  - David Kershner
+  - Jaegeuk Kim
+  - Namhyung Kim
+  - Colin Ian King
+  - Jeff Kirsher
+  - Greg Kroah-Hartman (Linux Foundation)
+  - Christian König
+  - Vinod Koul
+  - Krzysztof Kozlowski
+  - Viresh Kumar
+  - Aneesh Kumar K.V
+  - Julia Lawall
+  - Doug Ledford (Red Hat)
+  - Chuck Lever (Oracle)
+  - Daniel Lezcano
+  - Shaohua Li
+  - Xin Long (Red Hat)
+  - Tony Luck
+  - Mike Marshall
+  - Chris Mason
+  - Paul E. McKenney
+  - David S. Miller
+  - Ingo Molnar
+  - Kuninori Morimoto
+  - Borislav Petkov
+  - Jiri Pirko
+  - Josh Poimboeuf
+  - Sebastian Reichel (Collabora)
+  - Guenter Roeck
+  - Joerg Roedel
+  - Leon Romanovsky
+  - Steven Rostedt (VMware)
+  - Ivan Safonov
+  - Ivan Safonov
+  - Anna Schumaker
+  - Jes Sorensen
+  - K.Y. Srinivasan
+  - Heiko Stuebner
+  - Jiri Kosina (SUSE)
+  - Dmitry Torokhov
+  - Linus Torvalds
+  - Thierry Reding
+  - Rik van Riel
+  - Geert Uytterhoeven (Glider bvba)
+  - Daniel Vetter
+  - Linus Walleij
+  - Richard Weinberger
+  - Dan Williams
+  - Rafael J. Wysocki
+  - Arvind Yadav
+  - Masahiro Yamada
+  - Wei Yongjun
+  - Lv Zheng
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..af0cb69 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
@@ -5334,9 +5346,7 @@
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	include/linux/fcntl.h
-F:	include/linux/fs.h
 F:	include/uapi/linux/fcntl.h
-F:	include/uapi/linux/fs.h
 F:	fs/fcntl.c
 F:	fs/locks.c
 
@@ -5345,6 +5355,8 @@
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/*
+F:	include/linux/fs.h
+F:	include/uapi/linux/fs.h
 
 FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	Riku Voipio <riku.voipio@iki.fi>
@@ -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*
@@ -7559,7 +7571,7 @@
 F:	arch/mips/kvm/
 
 KERNEL VIRTUAL MACHINE FOR POWERPC (KVM/powerpc)
-M:	Alexander Graf <agraf@suse.com>
+M:	Paul Mackerras <paulus@ozlabs.org>
 L:	kvm-ppc@vger.kernel.org
 W:	http://www.linux-kvm.org/
 T:	git git://github.com/agraf/linux-2.6.git
@@ -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
@@ -9189,7 +9213,6 @@
 MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER
 M:	Bin Liu <b-liu@ti.com>
 L:	linux-usb@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
 S:	Maintained
 F:	drivers/usb/musb/
 
@@ -9337,7 +9360,7 @@
 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
@@ -10156,7 +10179,6 @@
 
 PARAVIRT_OPS INTERFACE
 M:	Juergen Gross <jgross@suse.com>
-M:	Chris Wright <chrisw@sous-sol.org>
 M:	Alok Kataria <akataria@vmware.com>
 M:	Rusty Russell <rusty@rustcorp.com.au>
 L:	virtualization@lists.linux-foundation.org
@@ -10536,6 +10558,8 @@
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 R:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
+R:	Jiri Olsa <jolsa@redhat.com>
+R:	Namhyung Kim <namhyung@kernel.org>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Supported
@@ -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..5f91a28 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc7
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -130,8 +130,8 @@
 ifneq ($(KBUILD_OUTPUT),)
 # check that the output directory actually exists
 saved-output := $(KBUILD_OUTPUT)
-$(shell [ -d $(KBUILD_OUTPUT) ] || mkdir -p $(KBUILD_OUTPUT))
-KBUILD_OUTPUT := $(realpath $(KBUILD_OUTPUT))
+KBUILD_OUTPUT := $(shell mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) \
+								&& /bin/pwd)
 $(if $(KBUILD_OUTPUT),, \
      $(error failed to create output directory "$(saved-output)"))
 
@@ -697,11 +697,11 @@
 
 ifeq ($(cc-name),clang)
 ifneq ($(CROSS_COMPILE),)
-CLANG_TARGET	:= -target $(notdir $(CROSS_COMPILE:%-=%))
+CLANG_TARGET	:= --target=$(notdir $(CROSS_COMPILE:%-=%))
 GCC_TOOLCHAIN	:= $(realpath $(dir $(shell which $(LD)))/..)
 endif
 ifneq ($(GCC_TOOLCHAIN),)
-CLANG_GCC_TC	:= -gcc-toolchain $(GCC_TOOLCHAIN)
+CLANG_GCC_TC	:= --gcc-toolchain=$(GCC_TOOLCHAIN)
 endif
 KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
 KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
@@ -933,7 +933,11 @@
   ifeq ($(has_libelf),1)
     objtool_target := tools/objtool FORCE
   else
-    $(warning "Cannot use CONFIG_STACK_VALIDATION, please install libelf-dev, libelf-devel or elfutils-libelf-devel")
+    ifdef CONFIG_ORC_UNWINDER
+      $(error "Cannot generate ORC metadata for CONFIG_ORC_UNWINDER=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel")
+    else
+      $(warning "Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel")
+    endif
     SKIP_STACK_VALIDATION := 1
     export SKIP_STACK_VALIDATION
   endif
@@ -1172,11 +1176,11 @@
 
 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:
@@ -1395,7 +1399,7 @@
 	@echo  '                    Build, install, and boot kernel before'
 	@echo  '                    running kselftest on it'
 	@echo  '  kselftest-clean - Remove all generated kselftest files'
-	@echo  '  kselftest-merge - Merge all the config dependencies of kselftest to existed'
+	@echo  '  kselftest-merge - Merge all the config dependencies of kselftest to existing'
 	@echo  '                    .config.'
 	@echo  ''
 	@echo 'Userspace tools targets:'
diff --git a/arch/Kconfig b/arch/Kconfig
index 1aafb4e..d789a89 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -937,9 +937,6 @@
 	  and non-text memory will be made non-executable. This provides
 	  protection against certain security exploits (e.g. writing to text)
 
-config ARCH_WANT_RELAX_ORDER
-	bool
-
 config ARCH_HAS_REFCOUNT
 	bool
 	help
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/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c
index 118dc6a..7ad074f 100644
--- a/arch/alpha/kernel/sys_alcor.c
+++ b/arch/alpha/kernel/sys_alcor.c
@@ -181,10 +181,10 @@
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 alcor_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[7][5] __initdata = {
+	static char irq_tab[7][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		/* note: IDSEL 17 is XLT only */
 		{16+13, 16+13, 16+13, 16+13, 16+13},	/* IdSel 17,  TULIP  */
diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c
index 4c50f8f4..c0fa1fe 100644
--- a/arch/alpha/kernel/sys_cabriolet.c
+++ b/arch/alpha/kernel/sys_cabriolet.c
@@ -173,10 +173,10 @@
  * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip.
  */
 
-static inline int __init
+static inline int
 eb66p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT  INTA  INTB  INTC   INTD */
 		{16+0, 16+0, 16+5,  16+9, 16+13},  /* IdSel 6,  slot 0, J25 */
 		{16+1, 16+1, 16+6, 16+10, 16+14},  /* IdSel 7,  slot 1, J26 */
@@ -203,10 +203,10 @@
  * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip.
  */
 
-static inline int __init
+static inline int
 cabriolet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT   INTA  INTB  INTC   INTD */
 		{ 16+2, 16+2, 16+7, 16+11, 16+15}, /* IdSel 5,  slot 2, J21 */
 		{ 16+0, 16+0, 16+5,  16+9, 16+13}, /* IdSel 6,  slot 0, J19 */
@@ -287,10 +287,10 @@
  * 
  */
 
-static inline int __init
+static inline int
 alphapc164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[7][5] __initdata = {
+	static char irq_tab[7][5] = {
 		/*INT   INTA  INTB   INTC   INTD */
 		{ 16+2, 16+2, 16+9,  16+13, 16+17}, /* IdSel  5, slot 2, J20 */
 		{ 16+0, 16+0, 16+7,  16+11, 16+15}, /* IdSel  6, slot 0, J29 */
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 6c35159..9e1e40e 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -356,7 +356,7 @@
  *  10	 64 bit PCI option slot 3 (not bus 0)
  */
 
-static int __init
+static int
 isa_irq_fixup(const struct pci_dev *dev, int irq)
 {
 	u8 irq8;
@@ -372,10 +372,10 @@
 	return irq8 & 0xf;
 }
 
-static int __init
+static int
 dp264_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[6][5] __initdata = {
+	static char irq_tab[6][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 5 ISA Bridge */
 		{ 16+ 3, 16+ 3, 16+ 2, 16+ 2, 16+ 2}, /* IdSel 6 SCSI builtin*/
@@ -394,10 +394,10 @@
 	return isa_irq_fixup(dev, irq);
 }
 
-static int __init
+static int
 monet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[13][5] __initdata = {
+	static char irq_tab[13][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{    45,    45,    45,    45,    45}, /* IdSel 3 21143 PCI1 */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 4 unused */
@@ -423,7 +423,7 @@
 	return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP);
 }
 
-static u8 __init
+static u8
 monet_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	struct pci_controller *hose = dev->sysdata;
@@ -456,10 +456,10 @@
 	return slot;
 }
 
-static int __init
+static int
 webbrick_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[13][5] __initdata = {
+	static char irq_tab[13][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 7 ISA Bridge */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 8 unused */
@@ -478,10 +478,10 @@
 	return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP);
 }
 
-static int __init
+static int
 clipper_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[7][5] __initdata = {
+	static char irq_tab[7][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 16+ 8, 16+ 8, 16+ 9, 16+10, 16+11}, /* IdSel 1 slot 1 */
 		{ 16+12, 16+12, 16+13, 16+14, 16+15}, /* IdSel 2 slot 2 */
diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c
index ad40a42..372661c 100644
--- a/arch/alpha/kernel/sys_eb64p.c
+++ b/arch/alpha/kernel/sys_eb64p.c
@@ -167,10 +167,10 @@
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 eb64p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT  INTA  INTB  INTC   INTD */
 		{16+7, 16+7, 16+7, 16+7,  16+7},  /* IdSel 5,  slot ?, ?? */
 		{16+0, 16+0, 16+2, 16+4,  16+9},  /* IdSel 6,  slot ?, ?? */
diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c
index 15f4208..2731738 100644
--- a/arch/alpha/kernel/sys_eiger.c
+++ b/arch/alpha/kernel/sys_eiger.c
@@ -141,7 +141,7 @@
 	}
 }
 
-static int __init
+static int
 eiger_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	u8 irq_orig;
@@ -158,7 +158,7 @@
 	return irq_orig - 0x80;
 }
 
-static u8 __init
+static u8
 eiger_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	struct pci_controller *hose = dev->sysdata;
diff --git a/arch/alpha/kernel/sys_miata.c b/arch/alpha/kernel/sys_miata.c
index d5b9776..731d693f 100644
--- a/arch/alpha/kernel/sys_miata.c
+++ b/arch/alpha/kernel/sys_miata.c
@@ -149,10 +149,10 @@
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 miata_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-        static char irq_tab[18][5] __initdata = {
+        static char irq_tab[18][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{16+ 8, 16+ 8, 16+ 8, 16+ 8, 16+ 8},  /* IdSel 14,  DC21142 */
 		{   -1,    -1,    -1,    -1,    -1},  /* IdSel 15,  EIDE    */
@@ -196,7 +196,7 @@
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 miata_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c
index 5e82dc1..350ec9c 100644
--- a/arch/alpha/kernel/sys_mikasa.c
+++ b/arch/alpha/kernel/sys_mikasa.c
@@ -145,10 +145,10 @@
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 mikasa_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[8][5] __initdata = {
+	static char irq_tab[8][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{16+12, 16+12, 16+12, 16+12, 16+12},	/* IdSel 17,  SCSI */
 		{   -1,    -1,    -1,    -1,    -1},	/* IdSel 18,  PCEB */
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 8ae04a1..d019e4c 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -62,7 +62,7 @@
 	common_init_isa_dma();
 }
 
-static int __init
+static int
 nautilus_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	/* Preserve the IRQ set up by the console.  */
diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c
index 063e594..2301678 100644
--- a/arch/alpha/kernel/sys_noritake.c
+++ b/arch/alpha/kernel/sys_noritake.c
@@ -193,10 +193,10 @@
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 noritake_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[15][5] __initdata = {
+	static char irq_tab[15][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		/* note: IDSELs 16, 17, and 25 are CORELLE only */
 		{ 16+1,  16+1,  16+1,  16+1,  16+1},  /* IdSel 16,  QLOGIC */
@@ -221,7 +221,7 @@
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 noritake_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c
index dfd510a..546822d 100644
--- a/arch/alpha/kernel/sys_rawhide.c
+++ b/arch/alpha/kernel/sys_rawhide.c
@@ -221,10 +221,10 @@
  * 
  */
 
-static int __init
+static int
 rawhide_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 16+16, 16+16, 16+16, 16+16, 16+16}, /* IdSel 1 SCSI PCI 1 */
 		{ 16+ 0, 16+ 0, 16+ 1, 16+ 2, 16+ 3}, /* IdSel 2 slot 2 */
diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c
index a3f4852..3b35e19 100644
--- a/arch/alpha/kernel/sys_ruffian.c
+++ b/arch/alpha/kernel/sys_ruffian.c
@@ -117,10 +117,10 @@
  *
  */
 
-static int __init
+static int
 ruffian_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-        static char irq_tab[11][5] __initdata = {
+        static char irq_tab[11][5] = {
 	      /*INT  INTA INTB INTC INTD */
 		{-1,  -1,  -1,  -1,  -1},  /* IdSel 13,  21052	     */
 		{-1,  -1,  -1,  -1,  -1},  /* IdSel 14,  SIO	     */
@@ -139,7 +139,7 @@
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 ruffian_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c
index 08ee737..e178007 100644
--- a/arch/alpha/kernel/sys_rx164.c
+++ b/arch/alpha/kernel/sys_rx164.c
@@ -142,7 +142,7 @@
  * 
  */
 
-static int __init
+static int
 rx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 #if 0
@@ -156,7 +156,7 @@
 	  { 16+1, 16+1, 16+6, 16+11, 16+16},      /* IdSel 10, slot 4 */
 	};
 #else
-	static char irq_tab[6][5] __initdata = {
+	static char irq_tab[6][5] = {
 	  /*INT   INTA  INTB  INTC   INTD */
 	  { 16+0, 16+0, 16+6, 16+11, 16+16},      /* IdSel 5,  slot 0 */
 	  { 16+1, 16+1, 16+7, 16+12, 16+17},      /* IdSel 6,  slot 1 */
diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c
index 8a0aa6d..86d259c 100644
--- a/arch/alpha/kernel/sys_sable.c
+++ b/arch/alpha/kernel/sys_sable.c
@@ -192,10 +192,10 @@
  * with the values in the irq swizzling tables above.
  */
 
-static int __init
+static int
 sable_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[9][5] __initdata = {
+	static char irq_tab[9][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 32+0,  32+0,  32+0,  32+0,  32+0},  /* IdSel 0,  TULIP  */
 		{ 32+1,  32+1,  32+1,  32+1,  32+1},  /* IdSel 1,  SCSI   */
@@ -374,10 +374,10 @@
  * with the values in the irq swizzling tables above.
  */
 
-static int __init
+static int
 lynx_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[19][5] __initdata = {
+	static char irq_tab[19][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{   -1,    -1,    -1,    -1,    -1},  /* IdSel 13,  PCEB   */
 		{   -1,    -1,    -1,    -1,    -1},  /* IdSel 14,  PPB    */
@@ -404,7 +404,7 @@
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 lynx_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index febd24e..9fd2895 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -144,7 +144,7 @@
 	outb((level_bits >> 8) & 0xff, 0x4d1);
 }
 
-static inline int __init
+static inline int
 noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	/*
@@ -165,7 +165,7 @@
 	 * that they use the default INTA line, if they are interrupt
 	 * driven at all).
 	 */
-	static char irq_tab[][5] __initdata = {
+	static char irq_tab[][5] = {
 		/*INT A   B   C   D */
 		{ 3,  3,  3,  3,  3}, /* idsel  6 (53c810) */ 
 		{-1, -1, -1, -1, -1}, /* idsel  7 (SIO: PCI/ISA bridge) */
@@ -183,10 +183,10 @@
 	return irq >= 0 ? tmp : -1;
 }
 
-static inline int __init
+static inline int
 p2k_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[][5] __initdata = {
+	static char irq_tab[][5] = {
 		/*INT A   B   C   D */
 		{ 0,  0, -1, -1, -1}, /* idsel  6 (53c810) */
 		{-1, -1, -1, -1, -1}, /* idsel  7 (SIO: PCI/ISA bridge) */
diff --git a/arch/alpha/kernel/sys_sx164.c b/arch/alpha/kernel/sys_sx164.c
index d063b36..23eee54 100644
--- a/arch/alpha/kernel/sys_sx164.c
+++ b/arch/alpha/kernel/sys_sx164.c
@@ -94,10 +94,10 @@
  *   9  32 bit PCI option slot 3
  */
 
-static int __init
+static int
 sx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 16+ 9, 16+ 9, 16+13, 16+17, 16+21}, /* IdSel 5 slot 2 J17 */
 		{ 16+11, 16+11, 16+15, 16+19, 16+23}, /* IdSel 6 slot 0 J19 */
diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c
index dd0f1ea..9101f2b 100644
--- a/arch/alpha/kernel/sys_takara.c
+++ b/arch/alpha/kernel/sys_takara.c
@@ -155,10 +155,10 @@
  * assign it whatever the hell IRQ we like and it doesn't matter.
  */
 
-static int __init
+static int
 takara_map_irq_srm(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[15][5] __initdata = {
+	static char irq_tab[15][5] = {
 		{ 16+3, 16+3, 16+3, 16+3, 16+3},   /* slot  6 == device 3 */
 		{ 16+2, 16+2, 16+2, 16+2, 16+2},   /* slot  7 == device 2 */
 		{ 16+1, 16+1, 16+1, 16+1, 16+1},   /* slot  8 == device 1 */
@@ -210,7 +210,7 @@
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 takara_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot = PCI_SLOT(dev->devfn);
diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c
index ee18748..c3f8b79 100644
--- a/arch/alpha/kernel/sys_wildfire.c
+++ b/arch/alpha/kernel/sys_wildfire.c
@@ -288,10 +288,10 @@
  *   7	 64 bit PCI 1 option slot 7
  */
 
-static int __init
+static int
 wildfire_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[8][5] __initdata = {
+	static char irq_tab[8][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ -1,    -1,    -1,    -1,    -1}, /* IdSel 0 ISA Bridge */
 		{ 36,    36,    36+1, 36+2, 36+3}, /* IdSel 1 SCSI builtin */
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..8f627c2 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 +134,18 @@
 
 		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 divide by 1
+			 * but it divides by 8) SDIO IP uses wrong clock and
+			 * works unstable (see STAR 9001204800)
+			 * We switched to the minimum possible value of the
+			 * divisor (div-by-2) in HSDK platform code.
+			 * So add temporary fix and change clock frequency
+			 * to 50000000 Hz until we fix dw sdio driver itself.
+			 */
+			clock-frequency = <50000000>;
 			#clock-cells = <0>;
 		};
 
@@ -141,6 +166,8 @@
 			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..7b8f8fa 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -72,7 +72,7 @@
 # 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/kernel/smp.c b/arch/arc/kernel/smp.c
index f462671..6df9d94 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -23,6 +23,8 @@
 #include <linux/cpumask.h>
 #include <linux/reboot.h>
 #include <linux/irqdomain.h>
+#include <linux/export.h>
+
 #include <asm/processor.h>
 #include <asm/setup.h>
 #include <asm/mach_desc.h>
@@ -30,6 +32,9 @@
 #ifndef CONFIG_ARC_HAS_LLSC
 arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+EXPORT_SYMBOL_GPL(smp_atomic_ops_lock);
+EXPORT_SYMBOL_GPL(smp_bitops_lock);
 #endif
 
 struct plat_smp_ops  __weak plat_smp_ops;
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..19ab3cf 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -6,4 +6,6 @@
 #
 
 menuconfig ARC_SOC_HSDK
-       bool "ARC HS Development Kit SOC"
+	bool "ARC HS Development Kit SOC"
+	select CLK_HSDK
+	select RESET_HSDK
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index a2e7fd1..fd0ae5e 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -38,6 +38,46 @@
 #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!");
+}
+
+#define SDIO_BASE		(ARC_PERIPHERAL_BASE + 0xA000)
+#define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
+#define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
+
 static void __init hsdk_init_early(void)
 {
 	/*
@@ -52,6 +92,18 @@
 
 	/* Really apply settings made above */
 	writel(1, (void __iomem *) CREG_PAE_UPDATE);
+
+	/*
+	 * Switch SDIO external ciu clock divider from default div-by-8 to
+	 * minimum possible div-by-2.
+	 */
+	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
+
+	/*
+	 * 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/Makefile b/arch/arm/Makefile
index 47d3a1a..817e5cf 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -131,7 +131,7 @@
 KBUILD_CFLAGS	+=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm
 KBUILD_AFLAGS	+=$(CFLAGS_ABI) $(AFLAGS_ISA) $(arch-y) $(tune-y) -include asm/unified.h -msoft-float
 
-CHECKFLAGS	+= -D__arm__
+CHECKFLAGS	+= -D__arm__ -m32
 
 #Default value
 head-y		:= arch/arm/kernel/head$(MMUEXT).o
diff --git a/arch/arm/boot/compressed/debug.S b/arch/arm/boot/compressed/debug.S
index 5392ee6..8f6e371 100644
--- a/arch/arm/boot/compressed/debug.S
+++ b/arch/arm/boot/compressed/debug.S
@@ -23,7 +23,11 @@
 	strb	r0, [r1]
 	mov	r0, #0x03		@ SYS_WRITEC
    ARM(	svc	#0x123456	)
+#ifdef CONFIG_CPU_V7M
+ THUMB(	bkpt	#0xab		)
+#else
  THUMB(	svc	#0xab		)
+#endif
 	mov	pc, lr
 	.align	2
 1:	.word	_GLOBAL_OFFSET_TABLE_ - .
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/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 7ff0811e..4960722 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -178,7 +178,7 @@
 			};
 
 			i2c0: i2c@11000 {
-				compatible = "marvell,mv64xxx-i2c";
+				compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c";
 				reg = <0x11000 0x20>;
 				#address-cells = <1>;
 				#size-cells = <0>;
@@ -189,7 +189,7 @@
 			};
 
 			i2c1: i2c@11100 {
-				compatible = "marvell,mv64xxx-i2c";
+				compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c";
 				reg = <0x11100 0x20>;
 				#address-cells = <1>;
 				#size-cells = <0>;
diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
index 63a5af8..cf0087b 100644
--- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
@@ -67,8 +67,8 @@
 				pinctrl-0 = <&pinctrl_macb0_default>;
 				phy-mode = "rmii";
 
-				ethernet-phy@1 {
-					reg = <0x1>;
+				ethernet-phy@0 {
+					reg = <0x0>;
 					interrupt-parent = <&pioA>;
 					interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>;
 					pinctrl-names = "default";
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/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index c7e9ccf..cbc2600 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -309,7 +309,7 @@
 				vddana-supply = <&vdd_3v3_lp_reg>;
 				vref-supply = <&vdd_3v3_lp_reg>;
 				pinctrl-names = "default";
-				pinctrl-0 = <&pinctrl_adc_default>;
+				pinctrl-0 = <&pinctrl_adc_default &pinctrl_adtrg_default>;
 				status = "okay";
 			};
 
@@ -340,6 +340,20 @@
 					bias-disable;
 				};
 
+				/*
+				 * The ADTRG pin can work on any edge type.
+				 * In here it's being pulled up, so need to
+				 * connect it to ground to get an edge e.g.
+				 * Trigger can be configured on falling, rise
+				 * or any edge, and the pull-up can be changed
+				 * to pull-down or left floating according to
+				 * needs.
+				 */
+				pinctrl_adtrg_default: adtrg_default {
+					pinmux = <PIN_PD31__ADTRG>;
+					bias-pull-up;
+				};
+
 				pinctrl_charger_chglev: charger_chglev {
 					pinmux = <PIN_PA12__GPIO>;
 					bias-disable;
diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
index 82651c3..b8565fc 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
@@ -18,12 +18,9 @@
 	compatible = "raspberrypi,model-zero-w", "brcm,bcm2835";
 	model = "Raspberry Pi Zero W";
 
-	/* Needed by firmware to properly init UARTs */
-	aliases {
-		uart0 = "/soc/serial@7e201000";
-		uart1 = "/soc/serial@7e215040";
-		serial0 = "/soc/serial@7e201000";
-		serial1 = "/soc/serial@7e215040";
+	chosen {
+		/* 8250 auxiliary UART instead of pl011 */
+		stdout-path = "serial1:115200n8";
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
index 20725ca..c71a0d7 100644
--- a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
+++ b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
@@ -8,6 +8,11 @@
 	compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
 	model = "Raspberry Pi 3 Model B";
 
+	chosen {
+		/* 8250 auxiliary UART instead of pl011 */
+		stdout-path = "serial1:115200n8";
+	};
+
 	memory {
 		reg = <0 0x40000000>;
 	};
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 431dcfc..013431e 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -20,8 +20,13 @@
 	#address-cells = <1>;
 	#size-cells = <1>;
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
 	chosen {
-		bootargs = "earlyprintk console=ttyAMA0";
+		stdout-path = "serial0:115200n8";
 	};
 
 	thermal-zones {
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/gemini.dtsi b/arch/arm/boot/dts/gemini.dtsi
index c68e8d4..f0d178c 100644
--- a/arch/arm/boot/dts/gemini.dtsi
+++ b/arch/arm/boot/dts/gemini.dtsi
@@ -145,11 +145,12 @@
 		};
 
 		watchdog@41000000 {
-			compatible = "cortina,gemini-watchdog";
+			compatible = "cortina,gemini-watchdog", "faraday,ftwdt010";
 			reg = <0x41000000 0x1000>;
 			interrupts = <3 IRQ_TYPE_LEVEL_HIGH>;
 			resets = <&syscon GEMINI_RESET_WDOG>;
 			clocks = <&syscon GEMINI_CLK_APB>;
+			clock-names = "PCLK";
 		};
 
 		uart0: serial@42000000 {
diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi
index f46814a..4d308d1 100644
--- a/arch/arm/boot/dts/imx7d.dtsi
+++ b/arch/arm/boot/dts/imx7d.dtsi
@@ -144,10 +144,10 @@
 		interrupt-names = "msi";
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0x7>;
-		interrupt-map = <0 0 0 1 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 2 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 3 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 4 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-map = <0 0 0 1 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&clks IMX7D_PCIE_CTRL_ROOT_CLK>,
 			 <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>,
 			 <&clks IMX7D_PCIE_PHY_ROOT_CLK>;
diff --git a/arch/arm/boot/dts/moxart.dtsi b/arch/arm/boot/dts/moxart.dtsi
index 1f4c795..da7b323 100644
--- a/arch/arm/boot/dts/moxart.dtsi
+++ b/arch/arm/boot/dts/moxart.dtsi
@@ -87,9 +87,10 @@
 		};
 
 		watchdog: watchdog@98500000 {
-			compatible = "moxa,moxart-watchdog";
+			compatible = "moxa,moxart-watchdog", "faraday,ftwdt010";
 			reg = <0x98500000 0x10>;
 			clocks = <&clk_apb>;
+			clock-names = "PCLK";
 		};
 
 		sdhci: sdhci@98e00000 {
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/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index 38d2216..b1a26b4 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -1430,6 +1430,7 @@
 				atmel,min-sample-rate-hz = <200000>;
 				atmel,max-sample-rate-hz = <20000000>;
 				atmel,startup-time-ms = <4>;
+				atmel,trigger-edge-type = <IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
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/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index b147cb0..eef072a 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -311,8 +311,8 @@
 					#size-cells = <0>;
 					reg = <0>;
 
-					tcon1_in_drc1: endpoint@0 {
-						reg = <0>;
+					tcon1_in_drc1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&drc1_out_tcon1>;
 					};
 				};
@@ -1012,8 +1012,8 @@
 					#size-cells = <0>;
 					reg = <1>;
 
-					be1_out_drc1: endpoint@0 {
-						reg = <0>;
+					be1_out_drc1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&drc1_in_be1>;
 					};
 				};
@@ -1042,8 +1042,8 @@
 					#size-cells = <0>;
 					reg = <0>;
 
-					drc1_in_be1: endpoint@0 {
-						reg = <0>;
+					drc1_in_be1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&be1_out_drc1>;
 					};
 				};
@@ -1053,8 +1053,8 @@
 					#size-cells = <0>;
 					reg = <1>;
 
-					drc1_out_tcon1: endpoint@0 {
-						reg = <0>;
+					drc1_out_tcon1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&tcon1_in_drc1>;
 					};
 				};
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/debug.S b/arch/arm/kernel/debug.S
index ea9646c..0a498cb 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -115,7 +115,11 @@
 		mov	r1, r0
 		mov	r0, #0x04		@ SYS_WRITE0
 	ARM(	svc	#0x123456	)
+#ifdef CONFIG_CPU_V7M
+	THUMB(	bkpt	#0xab		)
+#else
 	THUMB(	svc	#0xab		)
+#endif
 		ret	lr
 ENDPROC(printascii)
 
@@ -124,7 +128,11 @@
 		strb	r0, [r1]
 		mov	r0, #0x03		@ SYS_WRITEC
 	ARM(	svc	#0x123456	)
+#ifdef CONFIG_CPU_V7M
+	THUMB(	bkpt	#0xab		)
+#else
 	THUMB(	svc	#0xab		)
+#endif
 		ret	lr
 ENDPROC(printch)
 
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/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 71a34e8..57058ac 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -32,6 +32,7 @@
 #include <asm/mach/arch.h>
 
 #include "db8500-regs.h"
+#include "pm_domains.h"
 
 static int __init ux500_l2x0_unlock(void)
 {
@@ -157,6 +158,9 @@
 
 static void __init u8500_init_machine(void)
 {
+	/* Initialize ux500 power domains */
+	ux500_pm_domains_init();
+
 	/* automatically probe child nodes of dbx5x0 devices */
 	if (of_machine_is_compatible("st-ericsson,u8540"))
 		of_platform_populate(NULL, u8500_local_bus_nodes,
diff --git a/arch/arm/mach-ux500/pm.c b/arch/arm/mach-ux500/pm.c
index a970e7f..f6c33a0 100644
--- a/arch/arm/mach-ux500/pm.c
+++ b/arch/arm/mach-ux500/pm.c
@@ -19,7 +19,6 @@
 #include <linux/of_address.h>
 
 #include "db8500-regs.h"
-#include "pm_domains.h"
 
 /* ARM WFI Standby signal register */
 #define PRCM_ARM_WFI_STANDBY    (prcmu_base + 0x130)
@@ -203,7 +202,4 @@
 
 	/* Set up ux500 suspend callbacks. */
 	suspend_set_ops(UX500_SUSPEND_OPS);
-
-	/* Initialize ux500 power domains */
-	ux500_pm_domains_init();
 }
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 3b8e728..91537d9 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -344,6 +344,11 @@
 	 * reserved here.
 	 */
 #endif
+	/*
+	 * In any case, always ensure address 0 is never used as many things
+	 * get very confused if 0 is returned as a legitimate address.
+	 */
+	memblock_reserve(0, 1);
 }
 
 void __init adjust_lowmem_bounds(void)
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index e71eefa..0641ba5 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -1,7 +1,7 @@
 #include <linux/bootmem.h>
 #include <linux/gfp.h>
 #include <linux/export.h>
-#include <linux/rwlock.h>
+#include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
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/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
index caf8b6f..d06e34b 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
@@ -61,13 +61,6 @@
 	chosen {
 		stdout-path = "serial0:115200n8";
 	};
-
-	reg_vcc3v3: vcc3v3 {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
 };
 
 &ehci0 {
@@ -91,7 +84,7 @@
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;
 	cd-inverted;
 	disable-wp;
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/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index 8263a8a..f2aa2a8 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -336,7 +336,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xf6000000 0  0xf6000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			num-lanes = <1>;
 			clocks = <&cpm_clk 1 13>;
@@ -362,7 +362,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xf7000000 0  0xf7000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
@@ -389,7 +389,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xf8000000 0  0xf8000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index b71ee6c..4fe7032 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -335,7 +335,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xfa000000 0  0xfa000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			num-lanes = <1>;
 			clocks = <&cps_clk 1 13>;
@@ -361,7 +361,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xfb000000 0  0xfb000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
@@ -388,7 +388,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xfc000000 0  0xfc000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index 4786c67..d9d8850 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -62,6 +62,7 @@
 		brightness-levels = <256 128 64 16 8 4 0>;
 		default-brightness-level = <6>;
 
+		power-supply = <&reg_12v>;
 		enable-gpios = <&gpio6 7 GPIO_ACTIVE_HIGH>;
 	};
 
@@ -83,6 +84,15 @@
 		regulator-always-on;
 	};
 
+	reg_12v: regulator2 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-12V";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	rsnd_ak4613: sound {
 		compatible = "simple-audio-card";
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 6d615cb..41d6184 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -582,7 +582,7 @@
 	vop_mmu: iommu@ff373f00 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff373f00 0x0 0x100>;
-		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "vop_mmu";
 		#iommu-cells = <0>;
 		status = "disabled";
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index e0518b4..1070c82 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>;
 		};
 	};
 
@@ -808,7 +740,7 @@
 	iep_mmu: iommu@ff900800 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff900800 0x0 0x100>;
-		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "iep_mmu";
 		#iommu-cells = <0>;
 		status = "disabled";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
index 7fd4bfc..fef8227 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
@@ -371,10 +371,10 @@
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-max-microvolt = <3000000>;
 				regulator-state-mem {
 					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <3300000>;
+					regulator-suspend-microvolt = <3000000>;
 				};
 			};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 53ff3d1..910628d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -325,12 +325,12 @@
 			vcc_sd: LDO_REG4 {
 				regulator-name = "vcc_sd";
 				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-max-microvolt = <3000000>;
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <3300000>;
+					regulator-suspend-microvolt = <3000000>;
 				};
 			};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
index 6c30bb0..0f873c8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
@@ -315,10 +315,10 @@
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-max-microvolt = <3000000>;
 				regulator-state-mem {
 					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <3300000>;
+					regulator-suspend-microvolt = <3000000>;
 				};
 			};
 
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/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 903f3bf..7e25c5c 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -155,14 +155,16 @@
 		return __cmpxchg_small(ptr, old, new, size);
 
 	case 4:
-		return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new);
+		return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr,
+				     (u32)old, new);
 
 	case 8:
 		/* lld/scd are only available for MIPS64 */
 		if (!IS_ENABLED(CONFIG_64BIT))
 			return __cmpxchg_called_with_bad_pointer();
 
-		return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new);
+		return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr,
+				     (u64)old, new);
 
 	default:
 		return __cmpxchg_called_with_bad_pointer();
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/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c
index 100f23d..ac584c5 100644
--- a/arch/mips/loongson32/common/platform.c
+++ b/arch/mips/loongson32/common/platform.c
@@ -183,18 +183,20 @@
 }
 
 static struct plat_stmmacenet_data ls1x_eth0_pdata = {
-	.bus_id		= 0,
-	.phy_addr	= -1,
+	.bus_id			= 0,
+	.phy_addr		= -1,
 #if defined(CONFIG_LOONGSON1_LS1B)
-	.interface	= PHY_INTERFACE_MODE_MII,
+	.interface		= PHY_INTERFACE_MODE_MII,
 #elif defined(CONFIG_LOONGSON1_LS1C)
-	.interface	= PHY_INTERFACE_MODE_RMII,
+	.interface		= PHY_INTERFACE_MODE_RMII,
 #endif
-	.mdio_bus_data	= &ls1x_mdio_bus_data,
-	.dma_cfg	= &ls1x_eth_dma_cfg,
-	.has_gmac	= 1,
-	.tx_coe		= 1,
-	.init		= ls1x_eth_mux_init,
+	.mdio_bus_data		= &ls1x_mdio_bus_data,
+	.dma_cfg		= &ls1x_eth_dma_cfg,
+	.has_gmac		= 1,
+	.tx_coe			= 1,
+	.rx_queues_to_use	= 1,
+	.tx_queues_to_use	= 1,
+	.init			= ls1x_eth_mux_init,
 };
 
 static struct resource ls1x_eth0_resources[] = {
@@ -222,14 +224,16 @@
 
 #ifdef CONFIG_LOONGSON1_LS1B
 static struct plat_stmmacenet_data ls1x_eth1_pdata = {
-	.bus_id		= 1,
-	.phy_addr	= -1,
-	.interface	= PHY_INTERFACE_MODE_MII,
-	.mdio_bus_data	= &ls1x_mdio_bus_data,
-	.dma_cfg	= &ls1x_eth_dma_cfg,
-	.has_gmac	= 1,
-	.tx_coe		= 1,
-	.init		= ls1x_eth_mux_init,
+	.bus_id			= 1,
+	.phy_addr		= -1,
+	.interface		= PHY_INTERFACE_MODE_MII,
+	.mdio_bus_data		= &ls1x_mdio_bus_data,
+	.dma_cfg		= &ls1x_eth_dma_cfg,
+	.has_gmac		= 1,
+	.tx_coe			= 1,
+	.rx_queues_to_use	= 1,
+	.tx_queues_to_use	= 1,
+	.init			= ls1x_eth_mux_init,
 };
 
 static struct resource ls1x_eth1_resources[] = {
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 192542d..16d9ef5 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -2558,7 +2558,6 @@
 					break;
 				default:
 					/* Reserved R6 ops */
-					pr_err("Reserved MIPS R6 CMP.condn.S operation\n");
 					return SIGILL;
 				}
 			}
@@ -2719,7 +2718,6 @@
 					break;
 				default:
 					/* Reserved R6 ops */
-					pr_err("Reserved MIPS R6 CMP.condn.D operation\n");
 					return SIGILL;
 				}
 			}
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 7646891..01b7a87 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -667,7 +667,7 @@
 {
 	int src, dst, r, td, ts, mem_off, b_off;
 	bool need_swap, did_move, cmp_eq;
-	unsigned int target;
+	unsigned int target = 0;
 	u64 t64;
 	s64 t64s;
 	int bpf_op = BPF_OP(insn->code);
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 321db265..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/tools/generic-board-config.sh b/arch/mips/tools/generic-board-config.sh
index 5c4f936..654d652 100755
--- a/arch/mips/tools/generic-board-config.sh
+++ b/arch/mips/tools/generic-board-config.sh
@@ -30,8 +30,6 @@
 boards_origin="$5"
 shift 5
 
-cd "${srctree}"
-
 # Only print Skipping... lines if the user explicitly specified BOARDS=. In the
 # general case it only serves to obscure the useful output about what actually
 # was included.
@@ -48,7 +46,7 @@
 esac
 
 for board in $@; do
-	board_cfg="arch/mips/configs/generic/board-${board}.config"
+	board_cfg="${srctree}/arch/mips/configs/generic/board-${board}.config"
 	if [ ! -f "${board_cfg}" ]; then
 		echo "WARNING: Board config '${board_cfg}' not found"
 		continue
@@ -84,7 +82,7 @@
 	done || continue
 
 	# Merge this board config fragment into our final config file
-	./scripts/kconfig/merge_config.sh \
+	${srctree}/scripts/kconfig/merge_config.sh \
 		-m -O ${objtree} ${cfg} ${board_cfg} \
 		| grep -Ev '^(#|Using)'
 done
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/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index c6d6272..7baa226 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -35,12 +35,12 @@
 EXPORT_SYMBOL(__xchg8);
 EXPORT_SYMBOL(__xchg32);
 EXPORT_SYMBOL(__cmpxchg_u32);
+EXPORT_SYMBOL(__cmpxchg_u64);
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(__atomic_hash);
 #endif
 #ifdef CONFIG_64BIT
 EXPORT_SYMBOL(__xchg64);
-EXPORT_SYMBOL(__cmpxchg_u64);
 #endif
 
 #include <linux/uaccess.h>
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/syscall.S b/arch/parisc/kernel/syscall.S
index 23de307..41e60a9 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -742,7 +742,7 @@
 10:	ldd	0(%r25), %r25
 11:	ldd	0(%r24), %r24
 #else
-	/* Load new value into r22/r23 - high/low */
+	/* Load old value into r22/r23 - high/low */
 10:	ldw	0(%r25), %r22
 11:	ldw	4(%r25), %r23
 	/* Load new value into fr4 for atomic store later */
@@ -834,11 +834,11 @@
 	copy	%r0, %r28
 #else
 	/* Compare first word */
-19:	ldw,ma	0(%r26), %r29
+19:	ldw	0(%r26), %r29
 	sub,=	%r29, %r22, %r0
 	b,n	cas2_end
 	/* Compare second word */
-20:	ldw,ma	4(%r26), %r29
+20:	ldw	4(%r26), %r29
 	sub,=	%r29, %r23, %r0
 	b,n	cas2_end
 	/* Perform the store */
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 2d956aa..8c0105a 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -253,7 +253,10 @@
 		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
 
 		for_each_online_cpu(cpu) {
-			if (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)
+			if (cpu == 0)
+				continue;
+			if ((cpu0_loc != 0) &&
+			    (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
 				continue;
 
 			clocksource_cr16.name = "cr16_unstable";
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/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 48da0f5..b82586c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -734,7 +734,29 @@
 EXC_VIRT(program_check, 0x4700, 0x100, 0x700)
 TRAMP_KVM(PACA_EXGEN, 0x700)
 EXC_COMMON_BEGIN(program_check_common)
-	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
+	/*
+	 * It's possible to receive a TM Bad Thing type program check with
+	 * userspace register values (in particular r1), but with SRR1 reporting
+	 * that we came from the kernel. Normally that would confuse the bad
+	 * stack logic, and we would report a bad kernel stack pointer. Instead
+	 * we switch to the emergency stack if we're taking a TM Bad Thing from
+	 * the kernel.
+	 */
+	li	r10,MSR_PR		/* Build a mask of MSR_PR ..	*/
+	oris	r10,r10,0x200000@h	/* .. and SRR1_PROGTM		*/
+	and	r10,r10,r12		/* Mask SRR1 with that.		*/
+	srdi	r10,r10,8		/* Shift it so we can compare	*/
+	cmpldi	r10,(0x200000 >> 8)	/* .. with an immediate.	*/
+	bne 1f				/* If != go to normal path.	*/
+
+	/* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack	*/
+	andi.	r10,r12,MSR_PR;		/* Set CR0 correctly for label	*/
+					/* 3 in EXCEPTION_PROLOG_COMMON	*/
+	mr	r10,r1			/* Save r1			*/
+	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack		*/
+	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
+	b 3f				/* Jump into the macro !!	*/
+1:	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
 	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
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/signal_64.c b/arch/powerpc/kernel/signal_64.c
index c83c115..b2c0029 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -452,9 +452,20 @@
 	if (MSR_TM_RESV(msr))
 		return -EINVAL;
 
-	/* pull in MSR TM from user context */
+	/* pull in MSR TS bits from user context */
 	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
 
+	/*
+	 * Ensure that TM is enabled in regs->msr before we leave the signal
+	 * handler. It could be the case that (a) user disabled the TM bit
+	 * through the manipulation of the MSR bits in uc_mcontext or (b) the
+	 * TM bit was disabled because a sufficient number of context switches
+	 * happened whilst in the signal handler and load_tm overflowed,
+	 * disabling the TM bit. In either case we can end up with an illegal
+	 * TM state leading to a TM Bad Thing when we return to userspace.
+	 */
+	regs->msr |= MSR_TM;
+
 	/* pull in MSR LE from user context */
 	regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index c98e90b..b4e2b71 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -181,34 +181,25 @@
 	 *  - we have no stack frame and can not allocate one
 	 *  - LR points back to the original caller (in A)
 	 *  - CTR holds the new NIP in C
-	 *  - r0 & r12 are free
-	 *
-	 * r0 can't be used as the base register for a DS-form load or store, so
-	 * we temporarily shuffle r1 (stack pointer) into r0 and then put it back.
+	 *  - r0, r11 & r12 are free
 	 */
 livepatch_handler:
 	CURRENT_THREAD_INFO(r12, r1)
 
-	/* Save stack pointer into r0 */
-	mr	r0, r1
-
 	/* Allocate 3 x 8 bytes */
-	ld	r1, TI_livepatch_sp(r12)
-	addi	r1, r1, 24
-	std	r1, TI_livepatch_sp(r12)
+	ld	r11, TI_livepatch_sp(r12)
+	addi	r11, r11, 24
+	std	r11, TI_livepatch_sp(r12)
 
 	/* Save toc & real LR on livepatch stack */
-	std	r2,  -24(r1)
+	std	r2,  -24(r11)
 	mflr	r12
-	std	r12, -16(r1)
+	std	r12, -16(r11)
 
 	/* Store stack end marker */
 	lis     r12, STACK_END_MAGIC@h
 	ori     r12, r12, STACK_END_MAGIC@l
-	std	r12, -8(r1)
-
-	/* Restore real stack pointer */
-	mr	r1, r0
+	std	r12, -8(r11)
 
 	/* Put ctr in r12 for global entry and branch there */
 	mfctr	r12
@@ -216,36 +207,30 @@
 
 	/*
 	 * Now we are returning from the patched function to the original
-	 * caller A. We are free to use r0 and r12, and we can use r2 until we
+	 * caller A. We are free to use r11, r12 and we can use r2 until we
 	 * restore it.
 	 */
 
 	CURRENT_THREAD_INFO(r12, r1)
 
-	/* Save stack pointer into r0 */
-	mr	r0, r1
-
-	ld	r1, TI_livepatch_sp(r12)
+	ld	r11, TI_livepatch_sp(r12)
 
 	/* Check stack marker hasn't been trashed */
 	lis     r2,  STACK_END_MAGIC@h
 	ori     r2,  r2, STACK_END_MAGIC@l
-	ld	r12, -8(r1)
+	ld	r12, -8(r11)
 1:	tdne	r12, r2
 	EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
 
 	/* Restore LR & toc from livepatch stack */
-	ld	r12, -16(r1)
+	ld	r12, -16(r11)
 	mtlr	r12
-	ld	r2,  -24(r1)
+	ld	r2,  -24(r11)
 
 	/* Pop livepatch stack frame */
-	CURRENT_THREAD_INFO(r12, r0)
-	subi	r1, r1, 24
-	std	r1, TI_livepatch_sp(r12)
-
-	/* Restore real stack pointer */
-	mr	r1, r0
+	CURRENT_THREAD_INFO(r12, r1)
+	subi	r11, r11, 24
+	std	r11, TI_livepatch_sp(r12)
 
 	/* Return to original caller of live patched function */
 	blr
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_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 8f2da8b..4dffa61 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -478,28 +478,30 @@
 		return ret;
 
 	dir = iommu_tce_direction(tce);
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
-			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
-		return H_PARAMETER;
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) {
+		ret = H_PARAMETER;
+		goto unlock_exit;
+	}
 
 	entry = ioba >> stt->page_shift;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
-		if (dir == DMA_NONE) {
+		if (dir == DMA_NONE)
 			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
 					stit->tbl, entry);
-		} else {
-			idx = srcu_read_lock(&vcpu->kvm->srcu);
+		else
 			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
 					entry, ua, dir);
-			srcu_read_unlock(&vcpu->kvm->srcu, idx);
-		}
 
 		if (ret == H_SUCCESS)
 			continue;
 
 		if (ret == H_TOO_HARD)
-			return ret;
+			goto unlock_exit;
 
 		WARN_ON_ONCE(1);
 		kvmppc_clear_tce(stit->tbl, entry);
@@ -507,7 +509,10 @@
 
 	kvmppc_tce_put(stt, entry, tce);
 
-	return H_SUCCESS;
+unlock_exit:
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 17936f8..42639fb 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -989,13 +989,14 @@
 	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
-	stdcix	r11,r9,r10
 	eieio
+	stdcix	r11,r9,r10
 	lwz	r11, VCPU_XIVE_CAM_WORD(r4)
 	li	r9, TM_QW1_OS + TM_WORD2
 	stwcix	r11,r9,r10
 	li	r9, 1
 	stw	r9, VCPU_XIVE_PUSHED(r4)
+	eieio
 no_xive:
 #endif /* CONFIG_KVM_XICS */
 
@@ -1121,6 +1122,13 @@
 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)
 
@@ -1303,6 +1311,7 @@
 	bne	3f
 BEGIN_FTR_SECTION
 	PPC_MSGSYNC
+	lwsync
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
@@ -1393,8 +1402,8 @@
 	cmpldi	cr0, r10, 0
 	beq	1f
 	/* First load to pull the context, we ignore the value */
-	lwzx	r11, r7, r10
 	eieio
+	lwzx	r11, r7, r10
 	/* Second load to recover the context state (Words 0 and 1) */
 	ldx	r11, r6, r10
 	b	3f
@@ -1402,8 +1411,8 @@
 	cmpldi	cr0, r10, 0
 	beq	1f
 	/* First load to pull the context, we ignore the value */
-	lwzcix	r11, r7, r10
 	eieio
+	lwzcix	r11, r7, r10
 	/* Second load to recover the context state (Words 0 and 1) */
 	ldcix	r11, r6, r10
 3:	std	r11, VCPU_XIVE_SAVED_STATE(r9)
@@ -1413,6 +1422,7 @@
 	stw	r10, VCPU_XIVE_PUSHED(r9)
 	stb	r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
 	stb	r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
+	eieio
 1:
 #endif /* CONFIG_KVM_XICS */
 	/* Save more register state  */
@@ -1956,9 +1966,14 @@
 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
@@ -2776,6 +2791,10 @@
 	PPC_MSGCLR(6)
 	/* see if it's a host IPI */
 	li	r3, 1
+BEGIN_FTR_SECTION
+	PPC_MSGSYNC
+	lwsync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
 	bnelr
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/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3480faa..ee279c7 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -644,8 +644,7 @@
 		break;
 #endif
 	case KVM_CAP_PPC_HTM:
-		r = cpu_has_feature(CPU_FTR_TM_COMP) &&
-		    is_kvmppc_hv_enabled(kvm);
+		r = cpu_has_feature(CPU_FTR_TM_COMP) && hv_enabled;
 		break;
 	default:
 		r = 0;
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index fb9f58b..f208f56 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 */
@@ -1683,11 +1684,13 @@
  * Logical instructions
  */
 		case 26:	/* cntlzw */
-			op->val = __builtin_clz((unsigned int) regs->gpr[rd]);
+			val = (unsigned int) regs->gpr[rd];
+			op->val = ( val ? __builtin_clz(val) : 32 );
 			goto logical_done;
 #ifdef __powerpc64__
 		case 58:	/* cntlzd */
-			op->val = __builtin_clzl(regs->gpr[rd]);
+			val = regs->gpr[rd];
+			op->val = ( val ? __builtin_clzl(val) : 64 );
 			goto logical_done;
 #endif
 		case 28:	/* and */
@@ -2526,7 +2529,7 @@
 
  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 +2537,7 @@
 
  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/numa.c b/arch/powerpc/mm/numa.c
index b95c584..a51df9e 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1438,7 +1438,6 @@
 
 int arch_update_cpu_topology(void)
 {
-	lockdep_assert_cpus_held();
 	return numa_update_cpu_topology(true);
 }
 
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/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 9ccac86..8812624 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -399,6 +399,20 @@
 
 	/* Take the mutex lock for this node and then decrement the reference count */
 	mutex_lock(&ref->lock);
+	if (ref->refc == 0) {
+		/*
+		 * The scenario where this is true is, when perf session is
+		 * started, followed by offlining of all cpus in a given node.
+		 *
+		 * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline()
+		 * function set the ref->count to zero, if the cpu which is
+		 * about to offline is the last cpu in a given node and make
+		 * an OPAL call to disable the engine in that node.
+		 *
+		 */
+		mutex_unlock(&ref->lock);
+		return;
+	}
 	ref->refc--;
 	if (ref->refc == 0) {
 		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
@@ -523,8 +537,8 @@
 
 	/* We need only vbase for core counters */
 	mem_info->vbase = page_address(alloc_pages_node(phys_id,
-					  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
-					  get_order(size)));
+					  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+					  __GFP_NOWARN, get_order(size)));
 	if (!mem_info->vbase)
 		return -ENOMEM;
 
@@ -646,6 +660,20 @@
 		return;
 
 	mutex_lock(&ref->lock);
+	if (ref->refc == 0) {
+		/*
+		 * The scenario where this is true is, when perf session is
+		 * started, followed by offlining of all cpus in a given core.
+		 *
+		 * In the cpuhotplug offline path, ppc_core_imc_cpu_offline()
+		 * function set the ref->count to zero, if the cpu which is
+		 * about to offline is the last cpu in a given core and make
+		 * an OPAL call to disable the engine in that core.
+		 *
+		 */
+		mutex_unlock(&ref->lock);
+		return;
+	}
 	ref->refc--;
 	if (ref->refc == 0) {
 		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
@@ -763,8 +791,8 @@
 		 * free the memory in cpu offline path.
 		 */
 		local_mem = page_address(alloc_pages_node(phys_id,
-				  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
-				  get_order(size)));
+				  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+				  __GFP_NOWARN, get_order(size)));
 		if (!local_mem)
 			return -ENOMEM;
 
@@ -1148,7 +1176,8 @@
 	}
 
 	/* Only free the attr_groups which are dynamically allocated  */
-	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
+	if (pmu_ptr->attr_groups[IMC_EVENT_ATTR])
+		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
 	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
 	kfree(pmu_ptr);
 	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/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index afa46a7..04e042e 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -27,6 +27,7 @@
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_BLK_DEV_RAM=y
 # CONFIG_BLK_DEV_XPRAM is not set
 # CONFIG_DCSSBLK is not set
 # CONFIG_DASD is not set
@@ -59,6 +60,7 @@
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_PANIC_ON_OOPS=y
 # CONFIG_SCHED_DEBUG is not set
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/entry.S b/arch/s390/kernel/entry.S
index 21900e1..d185aa3 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -521,12 +521,15 @@
 	tmhh	%r8,0x0001		# test problem state bit
 	jnz	2f			# -> fault in user space
 #if IS_ENABLED(CONFIG_KVM)
-	# cleanup critical section for sie64a
+	# cleanup critical section for program checks in sie64a
 	lgr	%r14,%r9
 	slg	%r14,BASED(.Lsie_critical_start)
 	clg	%r14,BASED(.Lsie_critical_length)
 	jhe	0f
-	brasl	%r14,.Lcleanup_sie
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+	larl	%r9,sie_exit			# skip forward to sie_exit
 #endif
 0:	tmhh	%r8,0x4000		# PER bit set in old PSW ?
 	jnz	1f			# -> enabled, can't be a double fault
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/smp.c b/arch/s390/kernel/smp.c
index 1cee675..495ff69 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -293,7 +293,10 @@
 	lc->lpp = LPP_MAGIC;
 	lc->current_pid = tsk->pid;
 	lc->user_timer = tsk->thread.user_timer;
+	lc->guest_timer = tsk->thread.guest_timer;
 	lc->system_timer = tsk->thread.system_timer;
+	lc->hardirq_timer = tsk->thread.hardirq_timer;
+	lc->softirq_timer = tsk->thread.softirq_timer;
 	lc->steal_timer = 0;
 }
 
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/sparc/Kconfig b/arch/sparc/Kconfig
index 0be3828..4e83f95 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -44,7 +44,6 @@
 	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
 	select LOCKDEP_SMALL if LOCKDEP
-	select ARCH_WANT_RELAX_ORDER
 
 config SPARC32
 	def_bool !64BIT
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/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 8a13d46..50e0d2b 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -176,7 +176,7 @@
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
  * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
- * is just setting the LSB, which makes it an invalid stack address and is also
+ * is just clearing the MSB, which makes it an invalid stack address and is also
  * a signal to the unwinder that it's a pt_regs pointer in disguise.
  *
  * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the
@@ -185,7 +185,7 @@
 .macro ENCODE_FRAME_POINTER
 #ifdef CONFIG_FRAME_POINTER
 	mov %esp, %ebp
-	orl $0x1, %ebp
+	andl $0x7fffffff, %ebp
 #endif
 .endm
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 4916725..f6cdb7a 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -808,7 +808,7 @@
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
-	UNWIND_HINT_IRET_REGS offset=8
+	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
 	/* Sanity check */
 	.if \shift_ist != -1 && \paranoid == 0
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 16076eb..141e07b 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -546,9 +546,6 @@
 	if (event->attr.type != bts_pmu.type)
 		return -ENOENT;
 
-	if (x86_add_exclusive(x86_lbr_exclusive_bts))
-		return -EBUSY;
-
 	/*
 	 * BTS leaks kernel addresses even when CPL0 tracing is
 	 * disabled, so disallow intel_bts driver for unprivileged
@@ -562,6 +559,9 @@
 	    !capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
+	if (x86_add_exclusive(x86_lbr_exclusive_bts))
+		return -EBUSY;
+
 	ret = x86_reserve_hardware();
 	if (ret) {
 		x86_del_exclusive(x86_lbr_exclusive_bts);
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.c b/arch/x86/events/intel/uncore.c
index 1c5390f..d45e063 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -822,7 +822,7 @@
 		pmus[i].type	= type;
 		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
 		if (!pmus[i].boxes)
-			return -ENOMEM;
+			goto err;
 	}
 
 	type->pmus = pmus;
@@ -836,7 +836,7 @@
 		attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
 					sizeof(*attr_group), GFP_KERNEL);
 		if (!attr_group)
-			return -ENOMEM;
+			goto err;
 
 		attrs = (struct attribute **)(attr_group + 1);
 		attr_group->name = "events";
@@ -849,7 +849,15 @@
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
+
 	return 0;
+
+err:
+	for (i = 0; i < type->num_boxes; i++)
+		kfree(pmus[i].boxes);
+	kfree(pmus);
+
+	return -ENOMEM;
 }
 
 static int __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/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 1a8eb55..a5db63f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -85,6 +85,8 @@
 u32 *hv_vp_index;
 EXPORT_SYMBOL_GPL(hv_vp_index);
 
+u32 hv_max_vp_index;
+
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
@@ -93,6 +95,9 @@
 
 	hv_vp_index[smp_processor_id()] = msr_vp_index;
 
+	if (msr_vp_index > hv_max_vp_index)
+		hv_max_vp_index = msr_vp_index;
+
 	return 0;
 }
 
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 39e7f6e..9cc9e1c 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -36,9 +36,9 @@
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
-static struct hv_flush_pcpu __percpu *pcpu_flush;
+static struct hv_flush_pcpu __percpu **pcpu_flush;
 
-static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex;
+static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex;
 
 /*
  * Fills in gva_list starting from offset. Returns the number of items added.
@@ -76,6 +76,18 @@
 {
 	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
 
+	/* valid_bank_mask can represent up to 64 banks */
+	if (hv_max_vp_index / 64 >= 64)
+		return 0;
+
+	/*
+	 * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
+	 * structs are not cleared between calls, we risk flushing unneeded
+	 * vCPUs otherwise.
+	 */
+	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
+		flush->hv_vp_set.bank_contents[vcpu_bank] = 0;
+
 	/*
 	 * Some banks may end up being empty but this is acceptable.
 	 */
@@ -83,11 +95,6 @@
 		vcpu = hv_cpu_number_to_vp_number(cpu);
 		vcpu_bank = vcpu / 64;
 		vcpu_offset = vcpu % 64;
-
-		/* valid_bank_mask can represent up to 64 banks */
-		if (vcpu_bank >= 64)
-			return 0;
-
 		__set_bit(vcpu_offset, (unsigned long *)
 			  &flush->hv_vp_set.bank_contents[vcpu_bank]);
 		if (vcpu_bank >= nr_bank)
@@ -102,6 +109,7 @@
 				    const struct flush_tlb_info *info)
 {
 	int cpu, vcpu, gva_n, max_gvas;
+	struct hv_flush_pcpu **flush_pcpu;
 	struct hv_flush_pcpu *flush;
 	u64 status = U64_MAX;
 	unsigned long flags;
@@ -116,7 +124,17 @@
 
 	local_irq_save(flags);
 
-	flush = this_cpu_ptr(pcpu_flush);
+	flush_pcpu = this_cpu_ptr(pcpu_flush);
+
+	if (unlikely(!*flush_pcpu))
+		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+
+	flush = *flush_pcpu;
+
+	if (unlikely(!flush)) {
+		local_irq_restore(flags);
+		goto do_native;
+	}
 
 	if (info->mm) {
 		flush->address_space = virt_to_phys(info->mm->pgd);
@@ -173,6 +191,7 @@
 				       const struct flush_tlb_info *info)
 {
 	int nr_bank = 0, max_gvas, gva_n;
+	struct hv_flush_pcpu_ex **flush_pcpu;
 	struct hv_flush_pcpu_ex *flush;
 	u64 status = U64_MAX;
 	unsigned long flags;
@@ -187,7 +206,17 @@
 
 	local_irq_save(flags);
 
-	flush = this_cpu_ptr(pcpu_flush_ex);
+	flush_pcpu = this_cpu_ptr(pcpu_flush_ex);
+
+	if (unlikely(!*flush_pcpu))
+		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+
+	flush = *flush_pcpu;
+
+	if (unlikely(!flush)) {
+		local_irq_restore(flags);
+		goto do_native;
+	}
 
 	if (info->mm) {
 		flush->address_space = virt_to_phys(info->mm->pgd);
@@ -222,18 +251,18 @@
 		flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
 		status = hv_do_rep_hypercall(
 			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
-			0, nr_bank + 2, flush, NULL);
+			0, nr_bank, flush, NULL);
 	} else if (info->end &&
 		   ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
 		status = hv_do_rep_hypercall(
 			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
-			0, nr_bank + 2, flush, NULL);
+			0, nr_bank, flush, NULL);
 	} else {
 		gva_n = fill_gva_list(flush->gva_list, nr_bank,
 				      info->start, info->end);
 		status = hv_do_rep_hypercall(
 			HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX,
-			gva_n, nr_bank + 2, flush, NULL);
+			gva_n, nr_bank, flush, NULL);
 	}
 
 	local_irq_restore(flags);
@@ -266,7 +295,7 @@
 		return;
 
 	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-		pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
+		pcpu_flush = alloc_percpu(struct hv_flush_pcpu *);
 	else
-		pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
+		pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *);
 }
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-asm.h b/arch/x86/include/asm/alternative-asm.h
index e7636ba..6c98821 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -62,8 +62,10 @@
 #define new_len2		145f-144f
 
 /*
- * max without conditionals. Idea adapted from:
+ * gas compatible max based on the idea from:
  * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
  */
 #define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
 
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 1b02038..ccbe24e 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -103,12 +103,12 @@
 	alt_end_marker ":\n"
 
 /*
- * max without conditionals. Idea adapted from:
+ * gas compatible max based on the idea from:
  * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
  *
- * The additional "-" is needed because gas works with s32s.
+ * The additional "-" is needed because gas uses a "true" value of -1.
  */
-#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))"
+#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))"
 
 /*
  * Pad the second replacement alternative with additional NOPs if it is
@@ -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/mce.h b/arch/x86/include/asm/mce.h
index 1812649..8edac1d 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -187,7 +187,6 @@
 
 extern struct mce_vendor_flags mce_flags;
 
-extern struct mca_config mca_cfg;
 extern struct mca_msr_regs msr_ops;
 
 enum mce_notifier_prios {
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 7ae318c..3c856a1 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -126,13 +126,7 @@
 	DEBUG_LOCKS_WARN_ON(preemptible());
 }
 
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-	int cpu = smp_processor_id();
-
-	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_clear_cpu(cpu, mm_cpumask(mm));
-}
+void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
@@ -286,6 +280,32 @@
 	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 +316,8 @@
  */
 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..530f448 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)
@@ -291,6 +289,7 @@
  * to this information.
  */
 extern u32 *hv_vp_index;
+extern u32 hv_max_vp_index;
 
 /**
  * hv_cpu_number_to_vp_number() - Map CPU to VP.
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/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 4893abf..c4aed0d 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -82,6 +82,22 @@
 #define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
 #endif
 
+static inline bool tlb_defer_switch_to_init_mm(void)
+{
+	/*
+	 * If we have PCID, then switching to init_mm is reasonably
+	 * fast.  If we don't have PCID, then switching to init_mm is
+	 * quite slow, so we try to defer it in the hopes that we can
+	 * avoid it entirely.  The latter approach runs the risk of
+	 * receiving otherwise unnecessary IPIs.
+	 *
+	 * This choice is just a heuristic.  The tlb code can handle this
+	 * function returning true or false regardless of whether we have
+	 * PCID.
+	 */
+	return !static_cpu_has(X86_FEATURE_PCID);
+}
+
 /*
  * 6 because 6 should be plenty and struct tlb_state will fit in
  * two cache lines.
@@ -105,6 +121,23 @@
 	u16 next_asid;
 
 	/*
+	 * We can be in one of several states:
+	 *
+	 *  - Actively using an mm.  Our CPU's bit will be set in
+	 *    mm_cpumask(loaded_mm) and is_lazy == false;
+	 *
+	 *  - Not using a real mm.  loaded_mm == &init_mm.  Our CPU's bit
+	 *    will not be set in mm_cpumask(&init_mm) and is_lazy == false.
+	 *
+	 *  - Lazily using a real mm.  loaded_mm != &init_mm, our bit
+	 *    is set in mm_cpumask(loaded_mm), but is_lazy == true.
+	 *    We're heuristically guessing that the CR3 load we
+	 *    skipped more than makes up for the overhead added by
+	 *    lazy mode.
+	 */
+	bool is_lazy;
+
+	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
 	 * disabling interrupts when modifying either one.
 	 */
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/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 458da85..6db28f1 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -27,6 +27,8 @@
 	{}
 };
 
+#define PCI_DEVICE_ID_AMD_CNB17H_F4     0x1704
+
 const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
@@ -37,6 +39,7 @@
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{}
 };
 EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -48,6 +51,7 @@
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{}
 };
 
@@ -402,11 +406,48 @@
 }
 EXPORT_SYMBOL_GPL(amd_flush_garts);
 
+static void __fix_erratum_688(void *info)
+{
+#define MSR_AMD64_IC_CFG 0xC0011021
+
+	msr_set_bit(MSR_AMD64_IC_CFG, 3);
+	msr_set_bit(MSR_AMD64_IC_CFG, 14);
+}
+
+/* Apply erratum 688 fix so machines without a BIOS fix work. */
+static __init void fix_erratum_688(void)
+{
+	struct pci_dev *F4;
+	u32 val;
+
+	if (boot_cpu_data.x86 != 0x14)
+		return;
+
+	if (!amd_northbridges.num)
+		return;
+
+	F4 = node_to_amd_nb(0)->link;
+	if (!F4)
+		return;
+
+	if (pci_read_config_dword(F4, 0x164, &val))
+		return;
+
+	if (val & BIT(2))
+		return;
+
+	on_each_cpu(__fix_erratum_688, NULL, 0);
+
+	pr_info("x86/cpu/AMD: CPU erratum 688 worked around\n");
+}
+
 static __init int init_amd_nbs(void)
 {
 	amd_cache_northbridges();
 	amd_cache_gart();
 
+	fix_erratum_688();
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d705c76..ff89177 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -573,11 +573,21 @@
 	return ~0U;
 }
 
+static u32 skx_deadline_rev(void)
+{
+	switch (boot_cpu_data.x86_mask) {
+	case 0x03: return 0x01000136;
+	case 0x04: return 0x02000014;
+	}
+
+	return ~0U;
+}
+
 static const struct x86_cpu_id deadline_match[] = {
 	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X,	hsx_deadline_rev),
 	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X,	0x0b000020),
 	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D,	bdx_deadline_rev),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X,	0x02000014),
+	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X,	skx_deadline_rev),
 
 	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE,	0x22),
 	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT,	0x20),
@@ -600,7 +610,8 @@
 	const struct x86_cpu_id *m;
 	u32 rev;
 
-	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) ||
+	    boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return;
 
 	m = x86_match_cpu(deadline_match);
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/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 24f74932..9990a71 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -831,7 +831,6 @@
 	} else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		unsigned int apicid, nshared, first, last;
 
-		this_leaf = this_cpu_ci->info_list + index;
 		nshared = base->eax.split.num_threads_sharing + 1;
 		apicid = cpu_data(cpu).apicid;
 		first = apicid - (apicid % nshared);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 098530a..debb974 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -1,3 +1,6 @@
+#ifndef __X86_MCE_INTERNAL_H__
+#define __X86_MCE_INTERNAL_H__
+
 #include <linux/device.h>
 #include <asm/mce.h>
 
@@ -108,3 +111,7 @@
 static inline void mce_register_injector_chain(struct notifier_block *nb)	{ }
 static inline void mce_unregister_injector_chain(struct notifier_block *nb)	{ }
 #endif
+
+extern struct mca_config mca_cfg;
+
+#endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 40e28ed..486f640 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -28,6 +28,8 @@
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
+#include "mce-internal.h"
+
 #define NR_BLOCKS         5
 #define THRESHOLD_MAX     0xFFF
 #define INT_TYPE_APIC     0x00020000
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 86e8f0b..c4fa4a8 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -122,9 +122,6 @@
 	bool *res = &dis_ucode_ldr;
 #endif
 
-	if (!have_cpuid_p())
-		return *res;
-
 	/*
 	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
 	 * completely accurate as xen pv guests don't see that CPUID bit set but
@@ -166,24 +163,36 @@
 void __init load_ucode_bsp(void)
 {
 	unsigned int cpuid_1_eax;
+	bool intel = true;
 
-	if (check_loader_disabled_bsp())
+	if (!have_cpuid_p())
 		return;
 
 	cpuid_1_eax = native_cpuid_eax(1);
 
 	switch (x86_cpuid_vendor()) {
 	case X86_VENDOR_INTEL:
-		if (x86_family(cpuid_1_eax) >= 6)
-			load_ucode_intel_bsp();
+		if (x86_family(cpuid_1_eax) < 6)
+			return;
 		break;
+
 	case X86_VENDOR_AMD:
-		if (x86_family(cpuid_1_eax) >= 0x10)
-			load_ucode_amd_bsp(cpuid_1_eax);
+		if (x86_family(cpuid_1_eax) < 0x10)
+			return;
+		intel = false;
 		break;
+
 	default:
-		break;
+		return;
 	}
+
+	if (check_loader_disabled_bsp())
+		return;
+
+	if (intel)
+		load_ucode_intel_bsp();
+	else
+		load_ucode_amd_bsp(cpuid_1_eax);
 }
 
 static bool check_loader_disabled_ap(void)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 8f7a9bb..7dbcb7a 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -34,6 +34,7 @@
 #include <linux/mm.h>
 
 #include <asm/microcode_intel.h>
+#include <asm/intel-family.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
 #include <asm/setup.h>
@@ -918,6 +919,18 @@
 	return 0;
 }
 
+static bool is_blacklisted(unsigned int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) {
+		pr_err_once("late loading on model 79 is disabled.\n");
+		return true;
+	}
+
+	return false;
+}
+
 static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 					     bool refresh_fw)
 {
@@ -926,6 +939,9 @@
 	const struct firmware *firmware;
 	enum ucode_state ret;
 
+	if (is_blacklisted(cpu))
+		return UCODE_NFOUND;
+
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
 		c->x86, c->x86_model, c->x86_mask);
 
@@ -950,6 +966,9 @@
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
+	if (is_blacklisted(cpu))
+		return UCODE_NFOUND;
+
 	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
 }
 
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/head32.c b/arch/x86/kernel/head32.c
index cf2ce06..2902ca4 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -30,10 +30,11 @@
 
 asmlinkage __visible void __init i386_start_kernel(void)
 {
-	cr4_init_shadow();
-
+	/* Make sure IDT is set up before any exception happens */
 	idt_setup_early_handler();
 
+	cr4_init_shadow();
+
 	sanitize_boot_params(&boot_params);
 
 	x86_early_init_platform_quirks();
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/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index db2182d..3fc0f9a 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -3,6 +3,15 @@
 
 /* Kprobes and Optprobes common header */
 
+#include <asm/asm.h>
+
+#ifdef CONFIG_FRAME_POINTER
+# define SAVE_RBP_STRING "	push %" _ASM_BP "\n" \
+			 "	mov  %" _ASM_SP ", %" _ASM_BP "\n"
+#else
+# define SAVE_RBP_STRING "	push %" _ASM_BP "\n"
+#endif
+
 #ifdef CONFIG_X86_64
 #define SAVE_REGS_STRING			\
 	/* Skip cs, ip, orig_ax. */		\
@@ -17,7 +26,7 @@
 	"	pushq %r10\n"			\
 	"	pushq %r11\n"			\
 	"	pushq %rbx\n"			\
-	"	pushq %rbp\n"			\
+	SAVE_RBP_STRING				\
 	"	pushq %r12\n"			\
 	"	pushq %r13\n"			\
 	"	pushq %r14\n"			\
@@ -48,7 +57,7 @@
 	"	pushl %es\n"			\
 	"	pushl %ds\n"			\
 	"	pushl %eax\n"			\
-	"	pushl %ebp\n"			\
+	SAVE_RBP_STRING				\
 	"	pushl %edi\n"			\
 	"	pushl %esi\n"			\
 	"	pushl %edx\n"			\
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index f015371..0742491 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1080,8 +1080,6 @@
 	 * raw stack chunk with redzones:
 	 */
 	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
-	regs->flags &= ~X86_EFLAGS_IF;
-	trace_hardirqs_off();
 	regs->ip = (unsigned long)(jp->entry);
 
 	/*
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/reboot.c b/arch/x86/kernel/reboot.c
index 54180fa..add33f6 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -105,6 +105,10 @@
 	load_cr3(initial_page_table);
 #else
 	write_cr3(real_mode_header->trampoline_pgd);
+
+	/* Exiting long mode will fail if CR4.PCIDE is set. */
+	if (static_cpu_has(X86_FEATURE_PCID))
+		cr4_clear_bits(X86_CR4_PCIDE);
 #endif
 
 	/* Jump to the identity-mapped low memory code */
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/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index d145a0b..3dc26f9 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -44,7 +44,8 @@
 			state->stack_info.type, state->stack_info.next_sp,
 			state->stack_mask, state->graph_idx);
 
-	for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+	for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp;
+	     sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
 		if (get_stack_info(sp, state->task, &stack_info, &visit_mask))
 			break;
 
@@ -174,6 +175,7 @@
  * This determines if the frame pointer actually contains an encoded pointer to
  * pt_regs on the stack.  See ENCODE_FRAME_POINTER.
  */
+#ifdef CONFIG_X86_64
 static struct pt_regs *decode_frame_pointer(unsigned long *bp)
 {
 	unsigned long regs = (unsigned long)bp;
@@ -183,6 +185,23 @@
 
 	return (struct pt_regs *)(regs & ~0x1);
 }
+#else
+static struct pt_regs *decode_frame_pointer(unsigned long *bp)
+{
+	unsigned long regs = (unsigned long)bp;
+
+	if (regs & 0x80000000)
+		return NULL;
+
+	return (struct pt_regs *)(regs | 0x80000000);
+}
+#endif
+
+#ifdef CONFIG_X86_32
+#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long))
+#else
+#define KERNEL_REGS_SIZE (sizeof(struct pt_regs))
+#endif
 
 static bool update_stack_state(struct unwind_state *state,
 			       unsigned long *next_bp)
@@ -202,7 +221,7 @@
 	regs = decode_frame_pointer(next_bp);
 	if (regs) {
 		frame = (unsigned long *)regs;
-		len = regs_size(regs);
+		len = KERNEL_REGS_SIZE;
 		state->got_irq = true;
 	} else {
 		frame = next_bp;
@@ -226,6 +245,14 @@
 	    frame < prev_frame_end)
 		return false;
 
+	/*
+	 * On 32-bit with user mode regs, make sure the last two regs are safe
+	 * to access:
+	 */
+	if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) &&
+	    !on_stack(info, frame, len + 2*sizeof(long)))
+		return false;
+
 	/* Move state to the next frame: */
 	if (regs) {
 		state->regs = regs;
@@ -328,6 +355,13 @@
 	    state->regs->sp < (unsigned long)task_pt_regs(state->task))
 		goto the_end;
 
+	/*
+	 * There are some known frame pointer issues on 32-bit.  Disable
+	 * unwinder warnings on 32-bit until it gets objtool support.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		goto the_end;
+
 	if (state->regs) {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 570b70d..b95007e 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -86,8 +86,8 @@
 		idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE;
 
 		if (unlikely((idx >= lookup_num_blocks-1))) {
-			orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%lx\n",
-				 idx, lookup_num_blocks, ip);
+			orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n",
+				 idx, lookup_num_blocks, (void *)ip);
 			return NULL;
 		}
 
@@ -96,8 +96,8 @@
 
 		if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) ||
 			     (__start_orc_unwind + stop > __stop_orc_unwind))) {
-			orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%lx\n",
-				 idx, lookup_num_blocks, start, stop, ip);
+			orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n",
+				 idx, lookup_num_blocks, start, stop, (void *)ip);
 			return NULL;
 		}
 
@@ -373,7 +373,7 @@
 
 	case ORC_REG_R10:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R10 at ip %p\n",
+			orc_warn("missing regs for base reg R10 at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -382,7 +382,7 @@
 
 	case ORC_REG_R13:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R13 at ip %p\n",
+			orc_warn("missing regs for base reg R13 at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -391,7 +391,7 @@
 
 	case ORC_REG_DI:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DI at ip %p\n",
+			orc_warn("missing regs for base reg DI at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -400,7 +400,7 @@
 
 	case ORC_REG_DX:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DX at ip %p\n",
+			orc_warn("missing regs for base reg DX at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -408,7 +408,7 @@
 		break;
 
 	default:
-		orc_warn("unknown SP base reg %d for ip %p\n",
+		orc_warn("unknown SP base reg %d for ip %pB\n",
 			 orc->sp_reg, (void *)state->ip);
 		goto done;
 	}
@@ -436,7 +436,7 @@
 
 	case ORC_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
-			orc_warn("can't dereference registers at %p for ip %p\n",
+			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
 		}
@@ -448,7 +448,7 @@
 
 	case ORC_TYPE_REGS_IRET:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
-			orc_warn("can't dereference iret registers at %p for ip %p\n",
+			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
 		}
@@ -465,7 +465,8 @@
 		break;
 
 	default:
-		orc_warn("unknown .orc_unwind entry type %d\n", orc->type);
+		orc_warn("unknown .orc_unwind entry type %d for ip %pB\n",
+			 orc->type, (void *)orig_ip);
 		break;
 	}
 
@@ -487,7 +488,7 @@
 		break;
 
 	default:
-		orc_warn("unknown BP base reg %d for ip %p\n",
+		orc_warn("unknown BP base reg %d for ip %pB\n",
 			 orc->bp_reg, (void *)orig_ip);
 		goto done;
 	}
@@ -496,7 +497,7 @@
 	if (state->stack_info.type == prev_type &&
 	    on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) &&
 	    state->sp <= prev_sp) {
-		orc_warn("stack going in the wrong direction? ip=%p\n",
+		orc_warn("stack going in the wrong direction? ip=%pB\n",
 			 (void *)orig_ip);
 		goto done;
 	}
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..7a69cf0 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:
@@ -3974,19 +3974,19 @@
 				unsigned level, unsigned gpte)
 {
 	/*
-	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
-	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
-	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
-	 */
-	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
-
-	/*
 	 * The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
 	 * If it is clear, there are no large pages at this level, so clear
 	 * PT_PAGE_SIZE_MASK in gpte if that is the case.
 	 */
 	gpte &= level - mmu->last_nonleaf_level;
 
+	/*
+	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
+	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
+	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
+	 */
+	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
+
 	return gpte & PT_PAGE_SIZE_MASK;
 }
 
@@ -4555,6 +4555,7 @@
 
 	update_permission_bitmask(vcpu, context, true);
 	update_pkru_bitmask(vcpu, context, true);
+	update_last_nonleaf_level(vcpu, context);
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 86b68dc..f18d1f8 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -334,10 +334,11 @@
 		--walker->level;
 
 		index = PT_INDEX(addr, walker->level);
-
 		table_gfn = gpte_to_gfn(pte);
 		offset    = index * sizeof(pt_element_t);
 		pte_gpa   = gfn_to_gpa(table_gfn) + offset;
+
+		BUG_ON(walker->level < 1);
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 06c0c6d..95a0160 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 |
@@ -11283,7 +11297,7 @@
 
 	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
-	kvm_set_cr4(vcpu, vmcs12->host_cr4);
+	vmx_set_cr4(vcpu, vmcs12->host_cr4);
 
 	nested_ept_uninit_mmu_context(vcpu);
 
@@ -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/Makefile b/arch/x86/mm/Makefile
index 72bf8c0..e1f0958 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,12 @@
-# Kernel does not boot with instrumentation of tlb.c.
-KCOV_INSTRUMENT_tlb.o	:= n
+# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c
+KCOV_INSTRUMENT_tlb.o		:= n
+KCOV_INSTRUMENT_mem_encrypt.o	:= n
+
+KASAN_SANITIZE_mem_encrypt.o	:= n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_mem_encrypt.o	= -pg
+endif
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
 	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o
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..0f3d0ce 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -30,6 +30,7 @@
 
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
+
 static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 			    u16 *new_asid, bool *need_flush)
 {
@@ -80,7 +81,7 @@
 		return;
 
 	/* Warn if we're not lazy. */
-	WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm)));
+	WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy));
 
 	switch_mm(NULL, &init_mm, NULL);
 }
@@ -126,8 +127,7 @@
 	 * 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.
@@ -143,45 +143,24 @@
 		__flush_tlb_all();
 	}
 #endif
+	this_cpu_write(cpu_tlbstate.is_lazy, false);
 
 	if (real_prev == next) {
-		VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
-			  next->context.ctx_id);
-
-		if (cpumask_test_cpu(cpu, mm_cpumask(next))) {
-			/*
-			 * There's nothing to do: we weren't lazy, and we
-			 * aren't changing our mm.  We don't need to flush
-			 * anything, nor do we need to update CR3, CR4, or
-			 * LDTR.
-			 */
-			return;
-		}
-
-		/* Resume remote flushes and then read tlb_gen. */
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
-
-		if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) <
-		    next_tlb_gen) {
-			/*
-			 * Ideally, we'd have a flush_tlb() variant that
-			 * takes the known CR3 value as input.  This would
-			 * be faster on Xen PV and on hypothetical CPUs
-			 * on which INVPCID is fast.
-			 */
-			this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen,
-				       next_tlb_gen);
-			write_cr3(__sme_pa(next->pgd) | prev_asid);
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
-					TLB_FLUSH_ALL);
-		}
+		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+			   next->context.ctx_id);
 
 		/*
-		 * We just exited lazy mode, which means that CR4 and/or LDTR
-		 * may be stale.  (Changes to the required CR4 and LDTR states
-		 * are not reflected in tlb_gen.)
+		 * We don't currently support having a real mm loaded without
+		 * our cpu set in mm_cpumask().  We have all the bookkeeping
+		 * in place to figure out whether we would need to flush
+		 * if our cpu were cleared in mm_cpumask(), but we don't
+		 * currently use it.
 		 */
+		if (WARN_ON_ONCE(real_prev != &init_mm &&
+				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+
+		return;
 	} else {
 		u16 new_asid;
 		bool need_flush;
@@ -192,7 +171,7 @@
 			 * 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)))
@@ -200,10 +179,9 @@
 		}
 
 		/* Stop remote flushes for the previous mm */
-		if (cpumask_test_cpu(cpu, mm_cpumask(real_prev)))
-			cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
-
-		VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next)));
+		VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
+				real_prev != &init_mm);
+		cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
 
 		/*
 		 * Start remote flushes and then read tlb_gen.
@@ -216,12 +194,12 @@
 		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);
 		}
 
@@ -234,6 +212,40 @@
 }
 
 /*
+ * Please ignore the name of this function.  It should be called
+ * switch_to_kernel_thread().
+ *
+ * enter_lazy_tlb() is a hint from the scheduler that we are entering a
+ * kernel thread or other context without an mm.  Acceptable implementations
+ * include doing nothing whatsoever, switching to init_mm, or various clever
+ * lazy tricks to try to minimize TLB flushes.
+ *
+ * The scheduler reserves the right to call enter_lazy_tlb() several times
+ * in a row.  It will notify us that we're going back to a real mm by
+ * calling switch_mm_irqs_off().
+ */
+void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
+		return;
+
+	if (tlb_defer_switch_to_init_mm()) {
+		/*
+		 * There's a significant optimization that may be possible
+		 * here.  We have accurate enough TLB flush tracking that we
+		 * don't need to maintain coherence of TLB per se when we're
+		 * lazy.  We do, however, need to maintain coherence of
+		 * paging-structure caches.  We could, in principle, leave our
+		 * old mm loaded and only switch to init_mm when
+		 * tlb_remove_page() happens.
+		 */
+		this_cpu_write(cpu_tlbstate.is_lazy, true);
+	} else {
+		switch_mm(NULL, &init_mm, NULL);
+	}
+}
+
+/*
  * Call this when reinitializing a CPU.  It fixes the following potential
  * problems:
  *
@@ -265,7 +277,7 @@
 		!(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);
@@ -304,16 +316,20 @@
 	/* This code cannot presently handle being reentered. */
 	VM_WARN_ON(!irqs_disabled());
 
+	if (unlikely(loaded_mm == &init_mm))
+		return;
+
 	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
 		   loaded_mm->context.ctx_id);
 
-	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) {
+	if (this_cpu_read(cpu_tlbstate.is_lazy)) {
 		/*
-		 * We're in lazy mode -- don't flush.  We can get here on
-		 * remote flushes due to races and on local flushes if a
-		 * kernel thread coincidentally flushes the mm it's lazily
-		 * still using.
+		 * We're in lazy mode.  We need to at least flush our
+		 * paging-structure cache to avoid speculatively reading
+		 * garbage into our TLB.  Since switching to init_mm is barely
+		 * slower than a minimal flush, just switch to init_mm.
 		 */
+		switch_mm_irqs_off(NULL, &init_mm, NULL);
 		return;
 	}
 
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/enlighten.c b/arch/x86/xen/enlighten.c
index 0e7ef69..d669e9d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -93,11 +93,11 @@
 	int rc;
 
 	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "x86/xen/hvm_guest:prepare",
+				       "x86/xen/guest:prepare",
 				       cpu_up_prepare_cb, cpu_dead_cb);
 	if (rc >= 0) {
 		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "x86/xen/hvm_guest:online",
+					       "x86/xen/guest:online",
 					       xen_cpu_up_online, NULL);
 		if (rc < 0)
 			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
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/bio.c b/block/bio.c
index b38e962..101c2a9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1239,8 +1239,8 @@
 	 */
 	bmd->is_our_pages = map_data ? 0 : 1;
 	memcpy(bmd->iov, iter->iov, sizeof(struct iovec) * iter->nr_segs);
-	iov_iter_init(&bmd->iter, iter->type, bmd->iov,
-			iter->nr_segs, iter->count);
+	bmd->iter = *iter;
+	bmd->iter.iov = bmd->iov;
 
 	ret = -ENOMEM;
 	bio = bio_kmalloc(gfp_mask, nr_pages);
@@ -1331,6 +1331,7 @@
 	int ret, offset;
 	struct iov_iter i;
 	struct iovec iov;
+	struct bio_vec *bvec;
 
 	iov_for_each(iov, i, *iter) {
 		unsigned long uaddr = (unsigned long) iov.iov_base;
@@ -1375,7 +1376,12 @@
 		ret = get_user_pages_fast(uaddr, local_nr_pages,
 				(iter->type & WRITE) != WRITE,
 				&pages[cur_page]);
-		if (ret < local_nr_pages) {
+		if (unlikely(ret < local_nr_pages)) {
+			for (j = cur_page; j < page_limit; j++) {
+				if (!pages[j])
+					break;
+				put_page(pages[j]);
+			}
 			ret = -EFAULT;
 			goto out_unmap;
 		}
@@ -1383,6 +1389,7 @@
 		offset = offset_in_page(uaddr);
 		for (j = cur_page; j < page_limit; j++) {
 			unsigned int bytes = PAGE_SIZE - offset;
+			unsigned short prev_bi_vcnt = bio->bi_vcnt;
 
 			if (len <= 0)
 				break;
@@ -1397,6 +1404,13 @@
 					    bytes)
 				break;
 
+			/*
+			 * check if vector was merged with previous
+			 * drop page reference if needed
+			 */
+			if (bio->bi_vcnt == prev_bi_vcnt)
+				put_page(pages[j]);
+
 			len -= bytes;
 			offset = 0;
 		}
@@ -1423,10 +1437,8 @@
 	return bio;
 
  out_unmap:
-	for (j = 0; j < nr_pages; j++) {
-		if (!pages[j])
-			break;
-		put_page(pages[j]);
+	bio_for_each_segment_all(bvec, bio, j) {
+		put_page(bvec->bv_page);
 	}
  out:
 	kfree(pages);
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/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index e4b0ed3..39aecad 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -57,6 +57,8 @@
 	char *req, *p;
 	int len;
 
+	BUG_ON(!id_0 && !id_1);
+
 	if (id_0) {
 		lookup = id_0->data;
 		len = id_0->len;
@@ -105,7 +107,7 @@
 	if (id_0 && id_1) {
 		const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
 
-		if (!kids->id[0]) {
+		if (!kids->id[1]) {
 			pr_debug("First ID matches, but second is missing\n");
 			goto reject;
 		}
diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c
index af4cd86..d140d8bb 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.c
+++ b/crypto/asymmetric_keys/pkcs7_parser.c
@@ -88,6 +88,9 @@
 	bool want = false;
 
 	sinfo = msg->signed_infos;
+	if (!sinfo)
+		goto inconsistent;
+
 	if (sinfo->authattrs) {
 		want = true;
 		msg->have_authattrs = true;
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/crypto/shash.c b/crypto/shash.c
index 5e31c8d..325a14d 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -41,7 +41,7 @@
 	int err;
 
 	absize = keylen + (alignmask & ~(crypto_tfm_ctx_alignment() - 1));
-	buffer = kmalloc(absize, GFP_KERNEL);
+	buffer = kmalloc(absize, GFP_ATOMIC);
 	if (!buffer)
 		return -ENOMEM;
 
@@ -275,12 +275,14 @@
 
 int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc)
 {
-	struct scatterlist *sg = req->src;
-	unsigned int offset = sg->offset;
 	unsigned int nbytes = req->nbytes;
+	struct scatterlist *sg;
+	unsigned int offset;
 	int err;
 
-	if (nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset)) {
+	if (nbytes &&
+	    (sg = req->src, offset = sg->offset,
+	     nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset))) {
 		void *data;
 
 		data = kmap_atomic(sg_page(sg));
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 4faa0fd..d5692e3 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -426,14 +426,9 @@
 
 static int skcipher_walk_first(struct skcipher_walk *walk)
 {
-	walk->nbytes = 0;
-
 	if (WARN_ON_ONCE(in_irq()))
 		return -EDEADLK;
 
-	if (unlikely(!walk->total))
-		return 0;
-
 	walk->buffer = NULL;
 	if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
 		int err = skcipher_copy_iv(walk);
@@ -452,10 +447,15 @@
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 
+	walk->total = req->cryptlen;
+	walk->nbytes = 0;
+
+	if (unlikely(!walk->total))
+		return 0;
+
 	scatterwalk_start(&walk->in, req->src);
 	scatterwalk_start(&walk->out, req->dst);
 
-	walk->total = req->cryptlen;
 	walk->iv = req->iv;
 	walk->oiv = req->iv;
 
@@ -509,6 +509,11 @@
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	int err;
 
+	walk->nbytes = 0;
+
+	if (unlikely(!walk->total))
+		return 0;
+
 	walk->flags &= ~SKCIPHER_WALK_PHYS;
 
 	scatterwalk_start(&walk->in, req->src);
diff --git a/crypto/xts.c b/crypto/xts.c
index d86c11a..e31828e 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -554,8 +554,10 @@
 		ctx->name[len - 1] = 0;
 
 		if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
-			     "xts(%s)", ctx->name) >= CRYPTO_MAX_ALG_NAME)
-			return -ENAMETOOLONG;
+			     "xts(%s)", ctx->name) >= CRYPTO_MAX_ALG_NAME) {
+			err = -ENAMETOOLONG;
+			goto err_drop_spawn;
+		}
 	} else
 		goto err_drop_spawn;
 
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..e26ea20 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -571,10 +571,9 @@
  *     }
  * }
  *
- * Calling this function with index %2 return %-ENOENT and with index %3
- * returns the last entry. If the property does not contain any more values
- * %-ENODATA is returned. The NULL entry must be single integer and
- * preferably contain value %0.
+ * Calling this function with index %2 or index %3 return %-ENOENT. If the
+ * property does not contain any more values %-ENOENT is returned. The NULL
+ * entry must be single integer and preferably contain value %0.
  *
  * Return: %0 on success, negative error code on failure.
  */
@@ -590,11 +589,11 @@
 
 	data = acpi_device_data_of_node(fwnode);
 	if (!data)
-		return -EINVAL;
+		return -ENOENT;
 
 	ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj);
 	if (ret)
-		return ret;
+		return ret == -EINVAL ? -ENOENT : -EINVAL;
 
 	/*
 	 * The simplest case is when the value is a single reference.  Just
@@ -606,7 +605,7 @@
 
 		ret = acpi_bus_get_device(obj->reference.handle, &device);
 		if (ret)
-			return ret;
+			return ret == -ENODEV ? -EINVAL : ret;
 
 		args->adev = device;
 		args->nargs = 0;
@@ -622,8 +621,10 @@
 	 * The index argument is then used to determine which reference
 	 * the caller wants (along with the arguments).
 	 */
-	if (obj->type != ACPI_TYPE_PACKAGE || index >= obj->package.count)
-		return -EPROTO;
+	if (obj->type != ACPI_TYPE_PACKAGE)
+		return -EINVAL;
+	if (index >= obj->package.count)
+		return -ENOENT;
 
 	element = obj->package.elements;
 	end = element + obj->package.count;
@@ -635,7 +636,7 @@
 			ret = acpi_bus_get_device(element->reference.handle,
 						  &device);
 			if (ret)
-				return -ENODEV;
+				return -EINVAL;
 
 			nargs = 0;
 			element++;
@@ -649,11 +650,11 @@
 				else if (type == ACPI_TYPE_LOCAL_REFERENCE)
 					break;
 				else
-					return -EPROTO;
+					return -EINVAL;
 			}
 
 			if (nargs > MAX_ACPI_REFERENCE_ARGS)
-				return -EPROTO;
+				return -EINVAL;
 
 			if (idx == index) {
 				args->adev = device;
@@ -670,13 +671,13 @@
 				return -ENOENT;
 			element++;
 		} else {
-			return -EPROTO;
+			return -EINVAL;
 		}
 
 		idx++;
 	}
 
-	return -ENODATA;
+	return -ENOENT;
 }
 EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference);
 
@@ -908,11 +909,12 @@
 					    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 +924,8 @@
 			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 +943,8 @@
 		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 +1295,16 @@
 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..fddf76e 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;
@@ -2583,6 +2582,48 @@
 	return true;
 }
 
+/**
+ * binder_get_node_refs_for_txn() - Get required refs on node for txn
+ * @node:         struct binder_node for which to get refs
+ * @proc:         returns @node->proc if valid
+ * @error:        if no @proc then returns BR_DEAD_REPLY
+ *
+ * User-space normally keeps the node alive when creating a transaction
+ * since it has a reference to the target. The local strong ref keeps it
+ * alive if the sending process dies before the target process processes
+ * the transaction. If the source process is malicious or has a reference
+ * counting bug, relying on the local strong ref can fail.
+ *
+ * Since user-space can cause the local strong ref to go away, we also take
+ * a tmpref on the node to ensure it survives while we are constructing
+ * the transaction. We also need a tmpref on the proc while we are
+ * constructing the transaction, so we take that here as well.
+ *
+ * Return: The target_node with refs taken or NULL if no @node->proc is NULL.
+ * Also sets @proc if valid. If the @node->proc is NULL indicating that the
+ * target proc has died, @error is set to BR_DEAD_REPLY
+ */
+static struct binder_node *binder_get_node_refs_for_txn(
+		struct binder_node *node,
+		struct binder_proc **procp,
+		uint32_t *error)
+{
+	struct binder_node *target_node = NULL;
+
+	binder_node_inner_lock(node);
+	if (node->proc) {
+		target_node = node;
+		binder_inc_node_nilocked(node, 1, 0, NULL);
+		binder_inc_node_tmpref_ilocked(node);
+		node->proc->tmp_ref++;
+		*procp = node->proc;
+	} else
+		*error = BR_DEAD_REPLY;
+	binder_node_inner_unlock(node);
+
+	return target_node;
+}
+
 static void binder_transaction(struct binder_proc *proc,
 			       struct binder_thread *thread,
 			       struct binder_transaction_data *tr, int reply,
@@ -2686,43 +2727,35 @@
 			ref = binder_get_ref_olocked(proc, tr->target.handle,
 						     true);
 			if (ref) {
-				binder_inc_node(ref->node, 1, 0, NULL);
-				target_node = ref->node;
+				target_node = binder_get_node_refs_for_txn(
+						ref->node, &target_proc,
+						&return_error);
+			} else {
+				binder_user_error("%d:%d got transaction to invalid handle\n",
+						  proc->pid, thread->pid);
+				return_error = BR_FAILED_REPLY;
 			}
 			binder_proc_unlock(proc);
-			if (target_node == NULL) {
-				binder_user_error("%d:%d got transaction to invalid handle\n",
-					proc->pid, thread->pid);
-				return_error = BR_FAILED_REPLY;
-				return_error_param = -EINVAL;
-				return_error_line = __LINE__;
-				goto err_invalid_target_handle;
-			}
 		} else {
 			mutex_lock(&context->context_mgr_node_lock);
 			target_node = context->binder_context_mgr_node;
-			if (target_node == NULL) {
+			if (target_node)
+				target_node = binder_get_node_refs_for_txn(
+						target_node, &target_proc,
+						&return_error);
+			else
 				return_error = BR_DEAD_REPLY;
-				mutex_unlock(&context->context_mgr_node_lock);
-				return_error_line = __LINE__;
-				goto err_no_context_mgr_node;
-			}
-			binder_inc_node(target_node, 1, 0, NULL);
 			mutex_unlock(&context->context_mgr_node_lock);
 		}
-		e->to_node = target_node->debug_id;
-		binder_node_lock(target_node);
-		target_proc = target_node->proc;
-		if (target_proc == NULL) {
-			binder_node_unlock(target_node);
-			return_error = BR_DEAD_REPLY;
+		if (!target_node) {
+			/*
+			 * return_error is set above
+			 */
+			return_error_param = -EINVAL;
 			return_error_line = __LINE__;
 			goto err_dead_binder;
 		}
-		binder_inner_proc_lock(target_proc);
-		target_proc->tmp_ref++;
-		binder_inner_proc_unlock(target_proc);
-		binder_node_unlock(target_node);
+		e->to_node = target_node->debug_id;
 		if (security_binder_transaction(proc->tsk,
 						target_proc->tsk) < 0) {
 			return_error = BR_FAILED_REPLY;
@@ -3072,6 +3105,8 @@
 	if (target_thread)
 		binder_thread_dec_tmpref(target_thread);
 	binder_proc_dec_tmpref(target_proc);
+	if (target_node)
+		binder_dec_node_tmpref(target_node);
 	/*
 	 * write barrier to synchronize with initialization
 	 * of log entry
@@ -3083,6 +3118,7 @@
 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:
@@ -3090,6 +3126,8 @@
 err_copy_data_failed:
 	trace_binder_transaction_failed_buffer_release(t->buffer);
 	binder_transaction_buffer_release(target_proc, t->buffer, offp);
+	if (target_node)
+		binder_dec_node_tmpref(target_node);
 	target_node = NULL;
 	t->buffer->transaction = NULL;
 	binder_alloc_free_buf(&target_proc->alloc, t->buffer);
@@ -3104,13 +3142,14 @@
 err_empty_call_stack:
 err_dead_binder:
 err_invalid_target_handle:
-err_no_context_mgr_node:
 	if (target_thread)
 		binder_thread_dec_tmpref(target_thread);
 	if (target_proc)
 		binder_proc_dec_tmpref(target_proc);
-	if (target_node)
+	if (target_node) {
 		binder_dec_node(target_node, 1, 0);
+		binder_dec_node_tmpref(target_node);
+	}
 
 	binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
 		     "%d:%d transaction failed %d/%d, size %lld-%lld line %d\n",
@@ -3623,12 +3662,6 @@
 	}
 }
 
-static int binder_has_thread_work(struct binder_thread *thread)
-{
-	return !binder_worklist_empty(thread->proc, &thread->todo) ||
-		thread->looper_need_return;
-}
-
 static int binder_put_node_cmd(struct binder_proc *proc,
 			       struct binder_thread *thread,
 			       void __user **ptrp,
@@ -4258,12 +4291,9 @@
 
 	binder_inner_proc_unlock(thread->proc);
 
-	if (binder_has_work(thread, wait_for_proc_work))
-		return POLLIN;
-
 	poll_wait(filp, &thread->wait, wait);
 
-	if (binder_has_thread_work(thread))
+	if (binder_has_work(thread, wait_for_proc_work))
 		return POLLIN;
 
 	return 0;
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 8fe1658..c2819a3 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -215,17 +215,12 @@
 		}
 	}
 
-	if (!vma && need_mm)
-		mm = get_task_mm(alloc->tsk);
+	if (!vma && need_mm && mmget_not_zero(alloc->vma_vm_mm))
+		mm = alloc->vma_vm_mm;
 
 	if (mm) {
 		down_write(&mm->mmap_sem);
 		vma = alloc->vma;
-		if (vma && mm != alloc->vma_vm_mm) {
-			pr_err("%d: vma mm and task mm mismatch\n",
-				alloc->pid);
-			vma = NULL;
-		}
 	}
 
 	if (!vma && need_mm) {
@@ -565,7 +560,7 @@
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
 				   alloc->pid, buffer->data,
-				   prev->data, next->data);
+				   prev->data, next ? next->data : NULL);
 		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
 					 buffer_start_page(buffer) + PAGE_SIZE,
 					 NULL);
@@ -720,6 +715,7 @@
 	barrier();
 	alloc->vma = vma;
 	alloc->vma_vm_mm = vma->vm_mm;
+	mmgrab(alloc->vma_vm_mm);
 
 	return 0;
 
@@ -795,6 +791,8 @@
 		vfree(alloc->buffer);
 	}
 	mutex_unlock(&alloc->mutex);
+	if (alloc->vma_vm_mm)
+		mmdrop(alloc->vma_vm_mm);
 
 	binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE,
 		     "%s: %d buffers %d, pages %d\n",
@@ -889,7 +887,6 @@
 void binder_alloc_vma_close(struct binder_alloc *alloc)
 {
 	WRITE_ONCE(alloc->vma, NULL);
-	WRITE_ONCE(alloc->vma_vm_mm, NULL);
 }
 
 /**
@@ -913,6 +910,7 @@
 	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 +921,22 @@
 
 	index = page - alloc->pages;
 	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
-	if (alloc->vma) {
-		mm = get_task_mm(alloc->tsk);
-		if (!mm)
-			goto err_get_task_mm_failed;
+	vma = alloc->vma;
+	if (vma) {
+		if (!mmget_not_zero(alloc->vma_vm_mm))
+			goto err_mmget;
+		mm = alloc->vma_vm_mm;
 		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);
 
@@ -950,14 +954,13 @@
 
 	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);
-err_get_task_mm_failed:
+	mmput_async(mm);
+err_mmget:
 err_page_already_freed:
 	mutex_unlock(&alloc->mutex);
 err_get_alloc_mutex_failed:
@@ -996,7 +999,6 @@
  */
 void binder_alloc_init(struct binder_alloc *alloc)
 {
-	alloc->tsk = current->group_leader;
 	alloc->pid = current->group_leader->pid;
 	mutex_init(&alloc->mutex);
 	INIT_LIST_HEAD(&alloc->buffers);
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index a3a3602..2dd33b6 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -100,7 +100,6 @@
  */
 struct binder_alloc {
 	struct mutex mutex;
-	struct task_struct *tsk;
 	struct vm_area_struct *vma;
 	struct mm_struct *vma_vm_mm;
 	void *buffer;
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/cpu.c b/drivers/base/cpu.c
index 321cd7b..227bac5 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -377,7 +377,8 @@
 
 	per_cpu(cpu_sys_devices, num) = &cpu->dev;
 	register_cpu_under_node(num, cpu_to_node(num));
-	dev_pm_qos_expose_latency_limit(&cpu->dev, 0);
+	dev_pm_qos_expose_latency_limit(&cpu->dev,
+					PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
 
 	return 0;
 }
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/node.c b/drivers/base/node.c
index 3855902..aae2402 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -27,13 +27,21 @@
 
 static ssize_t node_read_cpumap(struct device *dev, bool list, char *buf)
 {
+	ssize_t n;
+	cpumask_var_t mask;
 	struct node *node_dev = to_node(dev);
-	const struct cpumask *mask = cpumask_of_node(node_dev->dev.id);
 
 	/* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */
 	BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1));
 
-	return cpumap_print_to_pagebuf(list, buf, mask);
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return 0;
+
+	cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask);
+	n = cpumap_print_to_pagebuf(list, buf, mask);
+	free_cpumask_var(mask);
+
+	return n;
 }
 
 static inline ssize_t node_read_cpumask(struct device *dev,
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/domain_governor.c b/drivers/base/power/domain_governor.c
index 281f949..51751cc 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -14,23 +14,20 @@
 static int dev_update_qos_constraint(struct device *dev, void *data)
 {
 	s64 *constraint_ns_p = data;
-	s32 constraint_ns = -1;
+	s64 constraint_ns = -1;
 
 	if (dev->power.subsys_data && dev->power.subsys_data->domain_data)
 		constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns;
 
-	if (constraint_ns < 0) {
+	if (constraint_ns < 0)
 		constraint_ns = dev_pm_qos_read_value(dev);
-		constraint_ns *= NSEC_PER_USEC;
-	}
-	if (constraint_ns == 0)
+
+	if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
 		return 0;
 
-	/*
-	 * constraint_ns cannot be negative here, because the device has been
-	 * suspended.
-	 */
-	if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0)
+	constraint_ns *= NSEC_PER_USEC;
+
+	if (constraint_ns < *constraint_ns_p || *constraint_ns_p < 0)
 		*constraint_ns_p = constraint_ns;
 
 	return 0;
@@ -63,10 +60,14 @@
 
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	if (constraint_ns < 0)
+	if (constraint_ns == 0)
 		return false;
 
-	constraint_ns *= NSEC_PER_USEC;
+	if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+		constraint_ns = -1;
+	else
+		constraint_ns *= NSEC_PER_USEC;
+
 	/*
 	 * We can walk the children without any additional locking, because
 	 * they all have been suspended at this point and their
@@ -76,14 +77,19 @@
 		device_for_each_child(dev, &constraint_ns,
 				      dev_update_qos_constraint);
 
-	if (constraint_ns > 0) {
-		constraint_ns -= td->suspend_latency_ns +
-				td->resume_latency_ns;
-		if (constraint_ns == 0)
-			return false;
+	if (constraint_ns < 0) {
+		/* The children have no constraints. */
+		td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+		td->cached_suspend_ok = true;
+	} else {
+		constraint_ns -= td->suspend_latency_ns + td->resume_latency_ns;
+		if (constraint_ns > 0) {
+			td->effective_constraint_ns = constraint_ns;
+			td->cached_suspend_ok = true;
+		} else {
+			td->effective_constraint_ns = 0;
+		}
 	}
-	td->effective_constraint_ns = constraint_ns;
-	td->cached_suspend_ok = constraint_ns >= 0;
 
 	/*
 	 * The children have been suspended already, so we don't need to take
@@ -145,13 +151,14 @@
 		td = &to_gpd_data(pdd)->td;
 		constraint_ns = td->effective_constraint_ns;
 		/* default_suspend_ok() need not be called before us. */
-		if (constraint_ns < 0) {
+		if (constraint_ns < 0)
 			constraint_ns = dev_pm_qos_read_value(pdd->dev);
-			constraint_ns *= NSEC_PER_USEC;
-		}
-		if (constraint_ns == 0)
+
+		if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
 			continue;
 
+		constraint_ns *= NSEC_PER_USEC;
+
 		/*
 		 * constraint_ns cannot be negative here, because the device has
 		 * been suspended.
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..7d29286 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -189,7 +189,7 @@
 	plist_head_init(&c->list);
 	c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
 	c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
 
@@ -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/base/power/runtime.c b/drivers/base/power/runtime.c
index 7bcf80f..13e0159 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -253,7 +253,7 @@
 	    || (dev->power.request_pending
 			&& dev->power.request == RPM_REQ_RESUME))
 		retval = -EAGAIN;
-	else if (__dev_pm_qos_read_value(dev) < 0)
+	else if (__dev_pm_qos_read_value(dev) == 0)
 		retval = -EPERM;
 	else if (dev->power.runtime_status == RPM_SUSPENDED)
 		retval = 1;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 156ab57..632077f 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -218,7 +218,14 @@
 					  struct device_attribute *attr,
 					  char *buf)
 {
-	return sprintf(buf, "%d\n", dev_pm_qos_requested_resume_latency(dev));
+	s32 value = dev_pm_qos_requested_resume_latency(dev);
+
+	if (value == 0)
+		return sprintf(buf, "n/a\n");
+	else if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+		value = 0;
+
+	return sprintf(buf, "%d\n", value);
 }
 
 static ssize_t pm_qos_resume_latency_store(struct device *dev,
@@ -228,11 +235,21 @@
 	s32 value;
 	int ret;
 
-	if (kstrtos32(buf, 0, &value))
-		return -EINVAL;
+	if (!kstrtos32(buf, 0, &value)) {
+		/*
+		 * Prevent users from writing negative or "no constraint" values
+		 * directly.
+		 */
+		if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+			return -EINVAL;
 
-	if (value < 0)
+		if (value == 0)
+			value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+	} else if (!strcmp(buf, "n/a") || !strcmp(buf, "n/a\n")) {
+		value = 0;
+	} else {
 		return -EINVAL;
+	}
 
 	ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req,
 					value);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index d0b65bb..7ed99c1 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -21,6 +21,7 @@
 #include <linux/phy.h>
 
 struct property_set {
+	struct device *dev;
 	struct fwnode_handle fwnode;
 	const struct property_entry *properties;
 };
@@ -682,6 +683,10 @@
  * Caller is responsible to call fwnode_handle_put() on the returned
  * args->fwnode pointer.
  *
+ * Returns: %0 on success
+ *	    %-ENOENT when the index is out of bounds, the index has an empty
+ *		     reference or the property was not found
+ *	    %-EINVAL on parse error
  */
 int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode,
 				       const char *prop, const char *nargs_prop,
@@ -891,6 +896,7 @@
 void device_remove_properties(struct device *dev)
 {
 	struct fwnode_handle *fwnode;
+	struct property_set *pset;
 
 	fwnode = dev_fwnode(dev);
 	if (!fwnode)
@@ -900,16 +906,16 @@
 	 * the pset. If there is no real firmware node (ACPI/DT) primary
 	 * will hold the pset.
 	 */
-	if (is_pset_node(fwnode)) {
+	pset = to_pset_node(fwnode);
+	if (pset) {
 		set_primary_fwnode(dev, NULL);
-		pset_free_set(to_pset_node(fwnode));
 	} else {
-		fwnode = fwnode->secondary;
-		if (!IS_ERR(fwnode) && is_pset_node(fwnode)) {
+		pset = to_pset_node(fwnode->secondary);
+		if (pset && dev == pset->dev)
 			set_secondary_fwnode(dev, NULL);
-			pset_free_set(to_pset_node(fwnode));
-		}
 	}
+	if (pset && dev == pset->dev)
+		pset_free_set(pset);
 }
 EXPORT_SYMBOL_GPL(device_remove_properties);
 
@@ -938,6 +944,7 @@
 
 	p->fwnode.ops = &pset_fwnode_ops;
 	set_secondary_fwnode(dev, &p->fwnode);
+	p->dev = dev;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(device_add_properties);
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..9adfb54 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -243,7 +243,6 @@
 	struct nbd_config *config = nbd->config;
 	config->blksize = blocksize;
 	config->bytesize = blocksize * nr_blocks;
-	nbd_size_update(nbd);
 }
 
 static void nbd_complete_rq(struct request *req)
@@ -387,6 +386,15 @@
 	return result;
 }
 
+/*
+ * Different settings for sk->sk_sndtimeo can result in different return values
+ * if there is a signal pending when we enter sendmsg, because reasons?
+ */
+static inline int was_interrupted(int result)
+{
+	return result == -ERESTARTSYS || result == -EINTR;
+}
+
 /* always call with the tx_lock held */
 static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 {
@@ -459,7 +467,7 @@
 	result = sock_xmit(nbd, index, 1, &from,
 			(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
 	if (result <= 0) {
-		if (result == -ERESTARTSYS) {
+		if (was_interrupted(result)) {
 			/* If we havne't sent anything we can just return BUSY,
 			 * however if we have sent something we need to make
 			 * sure we only allow this req to be sent until we are
@@ -503,7 +511,7 @@
 			}
 			result = sock_xmit(nbd, index, 1, &from, flags, &sent);
 			if (result <= 0) {
-				if (result == -ERESTARTSYS) {
+				if (was_interrupted(result)) {
 					/* We've already sent the header, we
 					 * have no choice but to set pending and
 					 * return BUSY.
@@ -820,9 +828,13 @@
 	 * 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,
@@ -1090,6 +1102,7 @@
 		args->index = i;
 		queue_work(recv_workqueue, &args->work);
 	}
+	nbd_size_update(nbd);
 	return error;
 }
 
@@ -1194,6 +1207,12 @@
 	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/skd_main.c b/drivers/block/skd_main.c
index 7cedb42..64d0fc1 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -2604,7 +2604,7 @@
 		return NULL;
 	*dma_handle = dma_map_single(dev, buf, s->size, dir);
 	if (dma_mapping_error(dev, *dma_handle)) {
-		kfree(buf);
+		kmem_cache_free(s, buf);
 		buf = NULL;
 	}
 	return buf;
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/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index c7f3969..70db4d5 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -720,7 +720,7 @@
 			if (mbus->hw_io_coherency)
 				w->mbus_attr |= ATTR_HW_COHERENCY;
 			w->base = base & DDR_BASE_CS_LOW_MASK;
-			w->size = (size | ~DDR_SIZE_MASK) + 1;
+			w->size = (u64)(size | ~DDR_SIZE_MASK) + 1;
 		}
 	}
 	mvebu_mbus_dram_info.num_cs = cs;
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/clk/clk-bulk.c b/drivers/clk/clk-bulk.c
index c834f5a..4c10456 100644
--- a/drivers/clk/clk-bulk.c
+++ b/drivers/clk/clk-bulk.c
@@ -105,6 +105,7 @@
 
 	return  ret;
 }
+EXPORT_SYMBOL_GPL(clk_bulk_prepare);
 
 #endif /* CONFIG_HAVE_CLK_PREPARE */
 
diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c
index 62d7854..5970a50 100644
--- a/drivers/clk/rockchip/clk-rk3128.c
+++ b/drivers/clk/rockchip/clk-rk3128.c
@@ -315,13 +315,13 @@
 			RK2928_CLKGATE_CON(10), 8, GFLAGS),
 
 	GATE(SCLK_PVTM_CORE, "clk_pvtm_core", "xin24m", 0,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(10), 0, GFLAGS),
 	GATE(SCLK_PVTM_GPU, "clk_pvtm_gpu", "xin24m", 0,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(10), 1, GFLAGS),
 	GATE(SCLK_PVTM_FUNC, "clk_pvtm_func", "xin24m", 0,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(10), 2, GFLAGS),
 	GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(2), 15, GFLAGS),
 
 	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0,
 			RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS,
@@ -541,7 +541,7 @@
 	GATE(0, "pclk_grf", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 4, GFLAGS),
 	GATE(0, "pclk_mipiphy", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 0, GFLAGS),
 
-	GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 2, GFLAGS),
+	GATE(0, "pclk_pmu", "pclk_pmu_pre", 0, RK2928_CLKGATE_CON(9), 2, GFLAGS),
 	GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 3, GFLAGS),
 
 	/* PD_MMC */
@@ -577,6 +577,8 @@
 	"aclk_peri",
 	"hclk_peri",
 	"pclk_peri",
+	"pclk_pmu",
+	"sclk_timer5",
 };
 
 static struct rockchip_clk_provider *__init rk3128_common_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index e40b775..d8d3cb6 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -294,6 +294,18 @@
 #define PLL_ENABLED	(1 << 31)
 #define PLL_LOCKED	(1 << 29)
 
+static void exynos4_clk_enable_pll(u32 reg)
+{
+	u32 pll_con = readl(reg_base + reg);
+	pll_con |= PLL_ENABLED;
+	writel(pll_con, reg_base + reg);
+
+	while (!(pll_con & PLL_LOCKED)) {
+		cpu_relax();
+		pll_con = readl(reg_base + reg);
+	}
+}
+
 static void exynos4_clk_wait_for_pll(u32 reg)
 {
 	u32 pll_con;
@@ -315,6 +327,9 @@
 	samsung_clk_save(reg_base, exynos4_save_pll,
 				ARRAY_SIZE(exynos4_clk_pll_regs));
 
+	exynos4_clk_enable_pll(EPLL_CON0);
+	exynos4_clk_enable_pll(VPLL_CON0);
+
 	if (exynos4_soc == EXYNOS4210) {
 		samsung_clk_save(reg_base, exynos4_save_soc,
 					ARRAY_SIZE(exynos4210_clk_save));
diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c
index a1df588..1de8cac 100644
--- a/drivers/clocksource/cs5535-clockevt.c
+++ b/drivers/clocksource/cs5535-clockevt.c
@@ -117,7 +117,8 @@
 	/* Turn off the clock (and clear the event) */
 	disable_timer(cs5535_event_clock);
 
-	if (clockevent_state_shutdown(&cs5535_clockevent))
+	if (clockevent_state_detached(&cs5535_clockevent) ||
+	    clockevent_state_shutdown(&cs5535_clockevent))
 		return IRQ_HANDLED;
 
 	/* Clear the counter */
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/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 48eaf28..aa39040 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -298,8 +298,8 @@
 		data->needs_update = 0;
 	}
 
-	/* resume_latency is 0 means no restriction */
-	if (resume_latency && resume_latency < latency_req)
+	if (resume_latency < latency_req &&
+	    resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
 		latency_req = resume_latency;
 
 	/* Special case when user has set very strict latency requirement */
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index d9fbbf0..0f9754e 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -349,8 +349,6 @@
 /* The crypto framework makes it hard to avoid this global. */
 static struct device *artpec6_crypto_dev;
 
-static struct dentry *dbgfs_root;
-
 #ifdef CONFIG_FAULT_INJECTION
 static DECLARE_FAULT_ATTR(artpec6_crypto_fail_status_read);
 static DECLARE_FAULT_ATTR(artpec6_crypto_fail_dma_array_full);
@@ -2984,6 +2982,8 @@
 	char *desc;
 };
 
+static struct dentry *dbgfs_root;
+
 static void artpec6_crypto_init_debugfs(void)
 {
 	dbgfs_root = debugfs_create_dir("artpec6_crypto", NULL);
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/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index b585ce5..4835dd4 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -553,9 +553,9 @@
 {
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req);
 	struct scatterlist sg[1], *tsg;
-	int err = 0, len = 0, reg, ncp;
+	int err = 0, len = 0, reg, ncp = 0;
 	unsigned int i;
-	const u32 *buffer = (const u32 *)rctx->buffer;
+	u32 *buffer = (void *)rctx->buffer;
 
 	rctx->sg = hdev->req->src;
 	rctx->total = hdev->req->nbytes;
@@ -620,10 +620,13 @@
 		reg |= HASH_CR_DMAA;
 		stm32_hash_write(hdev, HASH_CR, reg);
 
-		for (i = 0; i < DIV_ROUND_UP(ncp, sizeof(u32)); i++)
-			stm32_hash_write(hdev, HASH_DIN, buffer[i]);
-
-		stm32_hash_set_nblw(hdev, ncp);
+		if (ncp) {
+			memset(buffer + ncp, 0,
+			       DIV_ROUND_UP(ncp, sizeof(u32)) - ncp);
+			writesl(hdev->io_base + HASH_DIN, buffer,
+				DIV_ROUND_UP(ncp, sizeof(u32)));
+		}
+		stm32_hash_set_nblw(hdev, DIV_ROUND_UP(ncp, sizeof(u32)));
 		reg = stm32_hash_read(hdev, HASH_STR);
 		reg |= HASH_STR_DCAL;
 		stm32_hash_write(hdev, HASH_STR, reg);
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/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 66fb40d..0383063 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -383,7 +383,7 @@
 	return err;
 }
 
-static void sync_fill_fence_info(struct dma_fence *fence,
+static int sync_fill_fence_info(struct dma_fence *fence,
 				 struct sync_fence_info *info)
 {
 	strlcpy(info->obj_name, fence->ops->get_timeline_name(fence),
@@ -399,6 +399,8 @@
 		test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ?
 		ktime_to_ns(fence->timestamp) :
 		ktime_set(0, 0);
+
+	return info->status;
 }
 
 static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
@@ -424,8 +426,12 @@
 	 * sync_fence_info and return the actual number of fences on
 	 * info->num_fences.
 	 */
-	if (!info.num_fences)
+	if (!info.num_fences) {
+		info.status = dma_fence_is_signaled(sync_file->fence);
 		goto no_fences;
+	} else {
+		info.status = 1;
+	}
 
 	if (info.num_fences < num_fences)
 		return -EINVAL;
@@ -435,8 +441,10 @@
 	if (!fence_info)
 		return -ENOMEM;
 
-	for (i = 0; i < num_fences; i++)
-		sync_fill_fence_info(fences[i], &fence_info[i]);
+	for (i = 0; i < num_fences; i++) {
+		int status = sync_fill_fence_info(fences[i], &fence_info[i]);
+		info.status = info.status <= 0 ? info.status : status;
+	}
 
 	if (copy_to_user(u64_to_user_ptr(info.sync_fence_info), fence_info,
 			 size)) {
@@ -446,7 +454,6 @@
 
 no_fences:
 	sync_file_get_name(sync_file, info.name, sizeof(info.name));
-	info.status = dma_fence_is_signaled(sync_file->fence);
 	info.num_fences = num_fences;
 
 	if (copy_to_user((void __user *)arg, &info, sizeof(info)))
diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
index 32905d5..55f9c62 100644
--- a/drivers/dma/altera-msgdma.c
+++ b/drivers/dma/altera-msgdma.c
@@ -212,11 +212,12 @@
 static struct msgdma_sw_desc *msgdma_get_descriptor(struct msgdma_device *mdev)
 {
 	struct msgdma_sw_desc *desc;
+	unsigned long flags;
 
-	spin_lock_bh(&mdev->lock);
+	spin_lock_irqsave(&mdev->lock, flags);
 	desc = list_first_entry(&mdev->free_list, struct msgdma_sw_desc, node);
 	list_del(&desc->node);
-	spin_unlock_bh(&mdev->lock);
+	spin_unlock_irqrestore(&mdev->lock, flags);
 
 	INIT_LIST_HEAD(&desc->tx_list);
 
@@ -306,13 +307,14 @@
 	struct msgdma_device *mdev = to_mdev(tx->chan);
 	struct msgdma_sw_desc *new;
 	dma_cookie_t cookie;
+	unsigned long flags;
 
 	new = tx_to_desc(tx);
-	spin_lock_bh(&mdev->lock);
+	spin_lock_irqsave(&mdev->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
 	list_add_tail(&new->node, &mdev->pending_list);
-	spin_unlock_bh(&mdev->lock);
+	spin_unlock_irqrestore(&mdev->lock, flags);
 
 	return cookie;
 }
@@ -336,17 +338,18 @@
 	struct msgdma_extended_desc *desc;
 	size_t copy;
 	u32 desc_cnt;
+	unsigned long irqflags;
 
 	desc_cnt = DIV_ROUND_UP(len, MSGDMA_MAX_TRANS_LEN);
 
-	spin_lock_bh(&mdev->lock);
+	spin_lock_irqsave(&mdev->lock, irqflags);
 	if (desc_cnt > mdev->desc_free_cnt) {
-		spin_unlock_bh(&mdev->lock);
+		spin_unlock_irqrestore(&mdev->lock, irqflags);
 		dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev);
 		return NULL;
 	}
 	mdev->desc_free_cnt -= desc_cnt;
-	spin_unlock_bh(&mdev->lock);
+	spin_unlock_irqrestore(&mdev->lock, irqflags);
 
 	do {
 		/* Allocate and populate the descriptor */
@@ -397,18 +400,19 @@
 	u32 desc_cnt = 0, i;
 	struct scatterlist *sg;
 	u32 stride;
+	unsigned long irqflags;
 
 	for_each_sg(sgl, sg, sg_len, i)
 		desc_cnt += DIV_ROUND_UP(sg_dma_len(sg), MSGDMA_MAX_TRANS_LEN);
 
-	spin_lock_bh(&mdev->lock);
+	spin_lock_irqsave(&mdev->lock, irqflags);
 	if (desc_cnt > mdev->desc_free_cnt) {
-		spin_unlock_bh(&mdev->lock);
+		spin_unlock_irqrestore(&mdev->lock, irqflags);
 		dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev);
 		return NULL;
 	}
 	mdev->desc_free_cnt -= desc_cnt;
-	spin_unlock_bh(&mdev->lock);
+	spin_unlock_irqrestore(&mdev->lock, irqflags);
 
 	avail = sg_dma_len(sgl);
 
@@ -566,10 +570,11 @@
 static void msgdma_issue_pending(struct dma_chan *chan)
 {
 	struct msgdma_device *mdev = to_mdev(chan);
+	unsigned long flags;
 
-	spin_lock_bh(&mdev->lock);
+	spin_lock_irqsave(&mdev->lock, flags);
 	msgdma_start_transfer(mdev);
-	spin_unlock_bh(&mdev->lock);
+	spin_unlock_irqrestore(&mdev->lock, flags);
 }
 
 /**
@@ -634,10 +639,11 @@
 static void msgdma_free_chan_resources(struct dma_chan *dchan)
 {
 	struct msgdma_device *mdev = to_mdev(dchan);
+	unsigned long flags;
 
-	spin_lock_bh(&mdev->lock);
+	spin_lock_irqsave(&mdev->lock, flags);
 	msgdma_free_descriptors(mdev);
-	spin_unlock_bh(&mdev->lock);
+	spin_unlock_irqrestore(&mdev->lock, flags);
 	kfree(mdev->sw_desq);
 }
 
@@ -682,8 +688,9 @@
 	u32 count;
 	u32 __maybe_unused size;
 	u32 __maybe_unused status;
+	unsigned long flags;
 
-	spin_lock(&mdev->lock);
+	spin_lock_irqsave(&mdev->lock, flags);
 
 	/* Read number of responses that are available */
 	count = ioread32(mdev->csr + MSGDMA_CSR_RESP_FILL_LEVEL);
@@ -698,13 +705,13 @@
 		 * bits. So we need to just drop these values.
 		 */
 		size = ioread32(mdev->resp + MSGDMA_RESP_BYTES_TRANSFERRED);
-		status = ioread32(mdev->resp - MSGDMA_RESP_STATUS);
+		status = ioread32(mdev->resp + MSGDMA_RESP_STATUS);
 
 		msgdma_complete_descriptor(mdev);
 		msgdma_chan_desc_cleanup(mdev);
 	}
 
-	spin_unlock(&mdev->lock);
+	spin_unlock_irqrestore(&mdev->lock, flags);
 }
 
 /**
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 3879f80..a7ea20e 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -1143,11 +1143,24 @@
 	struct edma_desc *edesc;
 	struct device *dev = chan->device->dev;
 	struct edma_chan *echan = to_edma_chan(chan);
-	unsigned int width, pset_len;
+	unsigned int width, pset_len, array_size;
 
 	if (unlikely(!echan || !len))
 		return NULL;
 
+	/* Align the array size (acnt block) with the transfer properties */
+	switch (__ffs((src | dest | len))) {
+	case 0:
+		array_size = SZ_32K - 1;
+		break;
+	case 1:
+		array_size = SZ_32K - 2;
+		break;
+	default:
+		array_size = SZ_32K - 4;
+		break;
+	}
+
 	if (len < SZ_64K) {
 		/*
 		 * Transfer size less than 64K can be handled with one paRAM
@@ -1169,7 +1182,7 @@
 		 * When the full_length is multibple of 32767 one slot can be
 		 * used to complete the transfer.
 		 */
-		width = SZ_32K - 1;
+		width = array_size;
 		pset_len = rounddown(len, width);
 		/* One slot is enough for lengths multiple of (SZ_32K -1) */
 		if (unlikely(pset_len == len))
@@ -1217,7 +1230,7 @@
 		}
 		dest += pset_len;
 		src += pset_len;
-		pset_len = width = len % (SZ_32K - 1);
+		pset_len = width = len % array_size;
 
 		ret = edma_config_pset(chan, &edesc->pset[1], src, dest, 1,
 				       width, pset_len, DMA_MEM_TO_MEM);
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 2f65a8f..f1d04b7 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -262,13 +262,14 @@
 	mutex_lock(&xbar->mutex);
 	map->xbar_out = find_first_zero_bit(xbar->dma_inuse,
 					    xbar->dma_requests);
-	mutex_unlock(&xbar->mutex);
 	if (map->xbar_out == xbar->dma_requests) {
+		mutex_unlock(&xbar->mutex);
 		dev_err(&pdev->dev, "Run out of free DMA requests\n");
 		kfree(map);
 		return ERR_PTR(-ENOMEM);
 	}
 	set_bit(map->xbar_out, xbar->dma_inuse);
+	mutex_unlock(&xbar->mutex);
 
 	map->xbar_in = (u16)dma_spec->args[0];
 
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 1cb2d1c..a94601d 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -238,7 +238,8 @@
 
 	efi_random_get_seed(sys_table);
 
-	if (!nokaslr()) {
+	/* hibernation expects the runtime regions to stay in the same place */
+	if (!IS_ENABLED(CONFIG_HIBERNATION) && !nokaslr()) {
 		/*
 		 * Randomize the base of the UEFI runtime services region.
 		 * Preserve the 2 MB alignment of the region by taking a
diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c
index 08129b7..41c48a1 100644
--- a/drivers/firmware/efi/test/efi_test.c
+++ b/drivers/firmware/efi/test/efi_test.c
@@ -593,6 +593,9 @@
 	if (copy_from_user(&qcaps, qcaps_user, sizeof(qcaps)))
 		return -EFAULT;
 
+	if (qcaps.capsule_count == ULONG_MAX)
+		return -EINVAL;
+
 	capsules = kcalloc(qcaps.capsule_count + 1,
 			   sizeof(efi_capsule_header_t), GFP_KERNEL);
 	if (!capsules)
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/gpio/Kconfig b/drivers/gpio/Kconfig
index 3388d54..3f80f16 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -453,7 +453,8 @@
 config GPIO_THUNDERX
 	tristate "Cavium ThunderX/OCTEON-TX GPIO"
 	depends on ARCH_THUNDER || (64BIT && COMPILE_TEST)
-	depends on PCI_MSI && IRQ_DOMAIN_HIERARCHY
+	depends on PCI_MSI
+	select IRQ_DOMAIN_HIERARCHY
 	select IRQ_FASTEOI_HIERARCHY_HANDLERS
 	help
 	  Say yes here to support the on-chip GPIO lines on the ThunderX
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index dbf869f..3233b72 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -518,7 +518,13 @@
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 		irq_set_handler_locked(d, handle_level_irq);
 	else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
-		irq_set_handler_locked(d, handle_edge_irq);
+		/*
+		 * Edge IRQs are already cleared/acked in irq_handler and
+		 * not need to be masked, as result handle_edge_irq()
+		 * logic is excessed here and may cause lose of interrupts.
+		 * So just use handle_simple_irq.
+		 */
+		irq_set_handler_locked(d, handle_simple_irq);
 
 	return 0;
 
@@ -678,7 +684,7 @@
 static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank)
 {
 	void __iomem *isr_reg = NULL;
-	u32 isr;
+	u32 enabled, isr, level_mask;
 	unsigned int bit;
 	struct gpio_bank *bank = gpiobank;
 	unsigned long wa_lock_flags;
@@ -691,23 +697,21 @@
 	pm_runtime_get_sync(bank->chip.parent);
 
 	while (1) {
-		u32 isr_saved, level_mask = 0;
-		u32 enabled;
-
 		raw_spin_lock_irqsave(&bank->lock, lock_flags);
 
 		enabled = omap_get_gpio_irqbank_mask(bank);
-		isr_saved = isr = readl_relaxed(isr_reg) & enabled;
+		isr = readl_relaxed(isr_reg) & enabled;
 
 		if (bank->level_mask)
 			level_mask = bank->level_mask & enabled;
+		else
+			level_mask = 0;
 
 		/* clear edge sensitive interrupts before handler(s) are
 		called so that we don't miss any interrupt occurred while
 		executing them */
-		omap_disable_gpio_irqbank(bank, isr_saved & ~level_mask);
-		omap_clear_gpio_irqbank(bank, isr_saved & ~level_mask);
-		omap_enable_gpio_irqbank(bank, isr_saved & ~level_mask);
+		if (isr & ~level_mask)
+			omap_clear_gpio_irqbank(bank, isr & ~level_mask);
 
 		raw_spin_unlock_irqrestore(&bank->lock, lock_flags);
 
@@ -1010,7 +1014,7 @@
 
 /*---------------------------------------------------------------------*/
 
-static void __init omap_gpio_show_rev(struct gpio_bank *bank)
+static void omap_gpio_show_rev(struct gpio_bank *bank)
 {
 	static bool called;
 	u32 rev;
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 4d21135..eb4528c 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -203,7 +203,7 @@
 
 	if (pin <= 255) {
 		char ev_name[5];
-		sprintf(ev_name, "_%c%02X",
+		sprintf(ev_name, "_%c%02hhX",
 			agpio->triggering == ACPI_EDGE_SENSITIVE ? 'E' : 'L',
 			pin);
 		if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle)))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 7ef6c28..bc74613 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -834,7 +834,7 @@
 	placement.busy_placement = &placements;
 	placements.fpfn = 0;
 	placements.lpfn = adev->mc.gart_size >> PAGE_SHIFT;
-	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.flags = bo->mem.placement | TTM_PL_FLAG_TT;
 
 	r = ttm_bo_mem_space(bo, &placement, &tmp, true, false);
 	if (unlikely(r))
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/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 31db356..430a6b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -225,11 +225,7 @@
 	if (r)
 		return r;
 
-	/* Skip this for APU for now */
-	if (!(adev->flags & AMD_IS_APU))
-		r = amdgpu_uvd_suspend(adev);
-
-	return r;
+	return amdgpu_uvd_suspend(adev);
 }
 
 static int uvd_v6_0_resume(void *handle)
@@ -237,12 +233,10 @@
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	/* Skip this for APU for now */
-	if (!(adev->flags & AMD_IS_APU)) {
-		r = amdgpu_uvd_resume(adev);
-		if (r)
-			return r;
-	}
+	r = amdgpu_uvd_resume(adev);
+	if (r)
+		return r;
+
 	return uvd_v6_0_hw_init(adev);
 }
 
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/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index c274323..b526f49 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -830,7 +830,7 @@
 {
 	uint32_t reference_clock, tmp;
 	struct cgs_display_info info = {0};
-	struct cgs_mode_info mode_info;
+	struct cgs_mode_info mode_info = {0};
 
 	info.mode_info = &mode_info;
 
@@ -3948,10 +3948,9 @@
 	uint32_t ref_clock;
 	uint32_t refresh_rate = 0;
 	struct cgs_display_info info = {0};
-	struct cgs_mode_info mode_info;
+	struct cgs_mode_info mode_info = {0};
 
 	info.mode_info = &mode_info;
-
 	cgs_get_active_displays_info(hwmgr->device, &info);
 	num_active_displays = info.display_count;
 
@@ -3967,6 +3966,7 @@
 	frame_time_in_us = 1000000 / refresh_rate;
 
 	pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us;
+
 	data->frame_time_x2 = frame_time_in_us * 2 / 100;
 
 	display_gap2 = pre_vbi_time_in_us * (ref_clock / 100);
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 97c94f9..38cea6f 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -205,32 +205,17 @@
 			   struct amd_sched_entity *entity)
 {
 	struct amd_sched_rq *rq = entity->rq;
-	int r;
 
 	if (!amd_sched_entity_is_initialized(sched, entity))
 		return;
+
 	/**
 	 * The client will not queue more IBs during this fini, consume existing
-	 * queued IBs or discard them on SIGKILL
+	 * queued IBs
 	*/
-	if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL)
-		r = -ERESTARTSYS;
-	else
-		r = wait_event_killable(sched->job_scheduled,
-					amd_sched_entity_is_idle(entity));
+	wait_event(sched->job_scheduled, amd_sched_entity_is_idle(entity));
+
 	amd_sched_rq_remove_entity(rq, entity);
-	if (r) {
-		struct amd_sched_job *job;
-
-		/* Park the kernel for a moment to make sure it isn't processing
-		 * our enity.
-		 */
-		kthread_park(sched->thread);
-		kthread_unpark(sched->thread);
-		while (kfifo_out(&entity->job_queue, &job, sizeof(job)))
-			sched->ops->free_job(job);
-
-	}
 	kfifo_free(&entity->job_queue);
 }
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 4e53aae..0028591 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2960,6 +2960,7 @@
 		drm_modeset_backoff(&ctx);
 	}
 
+	drm_atomic_state_put(state);
 	drm_modeset_drop_locks(&ctx);
 	drm_modeset_acquire_fini(&ctx);
 
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..82b7242 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -168,23 +168,21 @@
 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;
 
 	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;
+	private = drm_dev->dev_private;
 
-		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 +190,15 @@
 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;
 
 	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);
+	private = drm_dev->dev_private;
+	drm_atomic_helper_resume(drm_dev, private->suspend_state);
+	exynos_drm_fbdev_resume(drm_dev);
+	drm_kms_helper_poll_enable(drm_dev);
 
 	return 0;
 }
@@ -439,6 +430,7 @@
 
 	kfree(drm->dev_private);
 	drm->dev_private = NULL;
+	dev_set_drvdata(dev, NULL);
 
 	drm_dev_unref(drm);
 }
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..645d1bb7f 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/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 21c36e2..d4726a3 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -2723,6 +2723,9 @@
 	uint32_t per_ctx_start[CACHELINE_DWORDS] = {0};
 	unsigned char *bb_start_sva;
 
+	if (!wa_ctx->per_ctx.valid)
+		return 0;
+
 	per_ctx_start[0] = 0x18800001;
 	per_ctx_start[1] = wa_ctx->per_ctx.guest_gma;
 
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index 91b4300..e5320b4 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -701,8 +701,7 @@
 			CACHELINE_BYTES;
 		workload->wa_ctx.per_ctx.guest_gma =
 			per_ctx & PER_CTX_ADDR_MASK;
-
-		WARN_ON(workload->wa_ctx.indirect_ctx.size && !(per_ctx & 0x1));
+		workload->wa_ctx.per_ctx.valid = per_ctx & 1;
 	}
 
 	if (emulate_schedule_in)
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 2294466..a5bed2e 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1429,18 +1429,7 @@
 	return 0;
 }
 
-static int ring_timestamp_mmio_read(struct intel_vgpu *vgpu,
-		unsigned int offset, void *p_data, unsigned int bytes)
-{
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-
-	mmio_hw_access_pre(dev_priv);
-	vgpu_vreg(vgpu, offset) = I915_READ(_MMIO(offset));
-	mmio_hw_access_post(dev_priv);
-	return intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
-}
-
-static int instdone_mmio_read(struct intel_vgpu *vgpu,
+static int mmio_read_from_hw(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
@@ -1589,6 +1578,8 @@
 	MMIO_F(prefix(BLT_RING_BASE), s, f, am, rm, d, r, w); \
 	MMIO_F(prefix(GEN6_BSD_RING_BASE), s, f, am, rm, d, r, w); \
 	MMIO_F(prefix(VEBOX_RING_BASE), s, f, am, rm, d, r, w); \
+	if (HAS_BSD2(dev_priv)) \
+		MMIO_F(prefix(GEN8_BSD2_RING_BASE), s, f, am, rm, d, r, w); \
 } while (0)
 
 #define MMIO_RING_D(prefix, d) \
@@ -1635,10 +1626,9 @@
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x6c)
-	MMIO_RING_DFH(RING_REG, D_ALL, 0, instdone_mmio_read, NULL);
-	MMIO_DH(RING_REG(GEN8_BSD2_RING_BASE), D_ALL, instdone_mmio_read, NULL);
+	MMIO_RING_DFH(RING_REG, D_ALL, 0, mmio_read_from_hw, NULL);
 #undef RING_REG
-	MMIO_DH(GEN7_SC_INSTDONE, D_BDW_PLUS, instdone_mmio_read, NULL);
+	MMIO_DH(GEN7_SC_INSTDONE, D_BDW_PLUS, mmio_read_from_hw, NULL);
 
 	MMIO_GM_RDR(0x2148, D_ALL, NULL, NULL);
 	MMIO_GM_RDR(CCID, D_ALL, NULL, NULL);
@@ -1648,7 +1638,7 @@
 	MMIO_RING_DFH(RING_TAIL, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_RING_DFH(RING_HEAD, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_RING_DFH(RING_CTL, D_ALL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, mmio_read_from_hw, NULL);
 	MMIO_RING_GM_RDR(RING_START, D_ALL, NULL, NULL);
 
 	/* RING MODE */
@@ -1662,9 +1652,9 @@
 	MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
 			NULL, NULL);
 	MMIO_RING_DFH(RING_TIMESTAMP, D_ALL, F_CMD_ACCESS,
-			ring_timestamp_mmio_read, NULL);
+			mmio_read_from_hw, NULL);
 	MMIO_RING_DFH(RING_TIMESTAMP_UDW, D_ALL, F_CMD_ACCESS,
-			ring_timestamp_mmio_read, NULL);
+			mmio_read_from_hw, NULL);
 
 	MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
@@ -2411,9 +2401,6 @@
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	int ret;
 
-	MMIO_DFH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, NULL,
-			intel_vgpu_reg_imr_handler);
-
 	MMIO_DH(GEN8_GT_IMR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_imr_handler);
 	MMIO_DH(GEN8_GT_IER(0), D_BDW_PLUS, NULL, intel_vgpu_reg_ier_handler);
 	MMIO_DH(GEN8_GT_IIR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_iir_handler);
@@ -2476,68 +2463,34 @@
 	MMIO_DH(GEN8_MASTER_IRQ, D_BDW_PLUS, NULL,
 		intel_vgpu_reg_master_irq_handler);
 
-	MMIO_DFH(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
-		F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x1c134, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-
-	MMIO_DFH(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
-		NULL, NULL);
-	MMIO_DFH(RING_HEAD(GEN8_BSD2_RING_BASE),  D_BDW_PLUS,
-		F_CMD_ACCESS, NULL, NULL);
-	MMIO_GM_RDR(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
-	MMIO_DFH(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
-		NULL, NULL);
-	MMIO_DFH(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
-		F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
-		F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL,
-		ring_mode_mmio_write);
-	MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
-		F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
-		F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(RING_TIMESTAMP(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
-			ring_timestamp_mmio_read, NULL);
-
-	MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS,
+		mmio_read_from_hw, NULL);
 
 #define RING_REG(base) (base + 0xd0)
 	MMIO_RING_F(RING_REG, 4, F_RO, 0,
 		~_MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET), D_BDW_PLUS, NULL,
 		ring_reset_ctl_write);
-	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO, 0,
-		~_MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET), D_BDW_PLUS, NULL,
-		ring_reset_ctl_write);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x230)
 	MMIO_RING_DFH(RING_REG, D_BDW_PLUS, 0, NULL, elsp_mmio_write);
-	MMIO_DH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, elsp_mmio_write);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x234)
 	MMIO_RING_F(RING_REG, 8, F_RO | F_CMD_ACCESS, 0, ~0, D_BDW_PLUS,
 		NULL, NULL);
-	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO | F_CMD_ACCESS, 0,
-		~0LL, D_BDW_PLUS, NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x244)
 	MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
-		NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x370)
 	MMIO_RING_F(RING_REG, 48, F_RO, 0, ~0, D_BDW_PLUS, NULL, NULL);
-	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 48, F_RO, 0, ~0, D_BDW_PLUS,
-			NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x3a0)
 	MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK, NULL, NULL);
 #undef RING_REG
 
 	MMIO_D(PIPEMISC(PIPE_A), D_BDW_PLUS);
@@ -2557,11 +2510,9 @@
 
 #define RING_REG(base) (base + 0x270)
 	MMIO_RING_F(RING_REG, 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL);
-	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL);
 #undef RING_REG
 
 	MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL);
-	MMIO_GM_RDR(RING_HWS_PGA(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
 
 	MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
@@ -2849,7 +2800,6 @@
 	MMIO_D(0x65f08, D_SKL | D_KBL);
 	MMIO_D(0x320f0, D_SKL | D_KBL);
 
-	MMIO_DFH(_REG_VCS2_EXCC, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(0x70034, D_SKL_PLUS);
 	MMIO_D(0x71034, D_SKL_PLUS);
 	MMIO_D(0x72034, D_SKL_PLUS);
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index fbd023a..7d01c77 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -54,9 +54,6 @@
 
 #define VGT_SPRSTRIDE(pipe)	_PIPE(pipe, _SPRA_STRIDE, _PLANE_STRIDE_2_B)
 
-#define _REG_VECS_EXCC		0x1A028
-#define _REG_VCS2_EXCC		0x1c028
-
 #define _REG_701C0(pipe, plane) (0x701c0 + pipe * 0x1000 + (plane - 1) * 0x100)
 #define _REG_701C4(pipe, plane) (0x701c4 + pipe * 0x1000 + (plane - 1) * 0x100)
 
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index 436377d..03532df 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -308,20 +308,8 @@
 
 static void tbs_sched_clean_vgpu(struct intel_vgpu *vgpu)
 {
-	struct intel_gvt_workload_scheduler *scheduler = &vgpu->gvt->scheduler;
-	int ring_id;
-
 	kfree(vgpu->sched_data);
 	vgpu->sched_data = NULL;
-
-	spin_lock_bh(&scheduler->mmio_context_lock);
-	for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) {
-		if (scheduler->engine_owner[ring_id] == vgpu) {
-			intel_gvt_switch_mmio(vgpu, NULL, ring_id);
-			scheduler->engine_owner[ring_id] = NULL;
-		}
-	}
-	spin_unlock_bh(&scheduler->mmio_context_lock);
 }
 
 static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
@@ -388,6 +376,7 @@
 {
 	struct intel_gvt_workload_scheduler *scheduler =
 		&vgpu->gvt->scheduler;
+	int ring_id;
 
 	gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id);
 
@@ -401,4 +390,13 @@
 		scheduler->need_reschedule = true;
 		scheduler->current_vgpu = NULL;
 	}
+
+	spin_lock_bh(&scheduler->mmio_context_lock);
+	for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) {
+		if (scheduler->engine_owner[ring_id] == vgpu) {
+			intel_gvt_switch_mmio(vgpu, NULL, ring_id);
+			scheduler->engine_owner[ring_id] = NULL;
+		}
+	}
+	spin_unlock_bh(&scheduler->mmio_context_lock);
 }
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 0d431a9..93a49eb 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -68,6 +68,7 @@
 struct shadow_per_ctx {
 	unsigned long guest_gma;
 	unsigned long shadow_gma;
+	unsigned valid;
 };
 
 struct intel_shadow_wa_ctx {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 19404c9..32e857d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2657,6 +2657,9 @@
 	if (READ_ONCE(obj->mm.pages))
 		return -ENODEV;
 
+	if (obj->mm.madv != I915_MADV_WILLNEED)
+		return -EFAULT;
+
 	/* Before the pages are instantiated the object is treated as being
 	 * in the CPU domain. The pages will be clflushed as required before
 	 * use, and we can freely write into the pages directly. If userspace
@@ -3013,10 +3016,15 @@
 
 static void nop_submit_request(struct drm_i915_gem_request *request)
 {
+	unsigned long flags;
+
 	GEM_BUG_ON(!i915_terminally_wedged(&request->i915->gpu_error));
 	dma_fence_set_error(&request->fence, -EIO);
-	i915_gem_request_submit(request);
+
+	spin_lock_irqsave(&request->engine->timeline->lock, flags);
+	__i915_gem_request_submit(request);
 	intel_engine_init_global_seqno(request->engine, request->global_seqno);
+	spin_unlock_irqrestore(&request->engine->timeline->lock, flags);
 }
 
 static void engine_set_wedged(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 4df039e..e161d38 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -33,21 +33,20 @@
 #include "intel_drv.h"
 #include "i915_trace.h"
 
-static bool ggtt_is_idle(struct drm_i915_private *dev_priv)
+static bool ggtt_is_idle(struct drm_i915_private *i915)
 {
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+       struct intel_engine_cs *engine;
+       enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv, id) {
-		struct intel_timeline *tl;
+       if (i915->gt.active_requests)
+	       return false;
 
-		tl = &ggtt->base.timeline.engine[engine->id];
-		if (i915_gem_active_isset(&tl->last_request))
-			return false;
-	}
+       for_each_engine(engine, i915, id) {
+	       if (engine->last_retired_context != i915->kernel_context)
+		       return false;
+       }
 
-	return true;
+       return true;
 }
 
 static int ggtt_flush(struct drm_i915_private *i915)
@@ -157,7 +156,8 @@
 				    min_size, alignment, cache_level,
 				    start, end, mode);
 
-	/* Retire before we search the active list. Although we have
+	/*
+	 * Retire before we search the active list. Although we have
 	 * reasonable accuracy in our retirement lists, we may have
 	 * a stray pin (preventing eviction) that can only be resolved by
 	 * retiring.
@@ -182,7 +182,8 @@
 		BUG_ON(ret);
 	}
 
-	/* Can we unpin some objects such as idle hw contents,
+	/*
+	 * Can we unpin some objects such as idle hw contents,
 	 * or pending flips? But since only the GGTT has global entries
 	 * such as scanouts, rinbuffers and contexts, we can skip the
 	 * purge when inspecting per-process local address spaces.
@@ -190,19 +191,33 @@
 	if (!i915_is_ggtt(vm) || flags & PIN_NONBLOCK)
 		return -ENOSPC;
 
-	if (ggtt_is_idle(dev_priv)) {
-		/* If we still have pending pageflip completions, drop
-		 * back to userspace to give our workqueues time to
-		 * acquire our locks and unpin the old scanouts.
-		 */
-		return intel_has_pending_fb_unpin(dev_priv) ? -EAGAIN : -ENOSPC;
+	/*
+	 * Not everything in the GGTT is tracked via VMA using
+	 * i915_vma_move_to_active(), otherwise we could evict as required
+	 * with minimal stalling. Instead we are forced to idle the GPU and
+	 * explicitly retire outstanding requests which will then remove
+	 * the pinning for active objects such as contexts and ring,
+	 * enabling us to evict them on the next iteration.
+	 *
+	 * To ensure that all user contexts are evictable, we perform
+	 * a switch to the perma-pinned kernel context. This all also gives
+	 * us a termination condition, when the last retired context is
+	 * the kernel's there is no more we can evict.
+	 */
+	if (!ggtt_is_idle(dev_priv)) {
+		ret = ggtt_flush(dev_priv);
+		if (ret)
+			return ret;
+
+		goto search_again;
 	}
 
-	ret = ggtt_flush(dev_priv);
-	if (ret)
-		return ret;
-
-	goto search_again;
+	/*
+	 * If we still have pending pageflip completions, drop
+	 * back to userspace to give our workqueues time to
+	 * acquire our locks and unpin the old scanouts.
+	 */
+	return intel_has_pending_fb_unpin(dev_priv) ? -EAGAIN : -ENOSPC;
 
 found:
 	/* drm_mm doesn't allow any other other operations while
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/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 94185d6..370b9d2 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2537,6 +2537,10 @@
 	.poll		= i915_perf_poll,
 	.read		= i915_perf_read,
 	.unlocked_ioctl	= i915_perf_ioctl,
+	/* Our ioctl have no arguments, so it's safe to use the same function
+	 * to handle 32bits compatibility.
+	 */
+	.compat_ioctl   = i915_perf_ioctl,
 };
 
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ed7cd9e..c9bcc6c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -6998,6 +6998,7 @@
  */
 #define  L3_GENERAL_PRIO_CREDITS(x)		(((x) >> 1) << 19)
 #define  L3_HIGH_PRIO_CREDITS(x)		(((x) >> 1) << 14)
+#define  L3_PRIO_CREDITS_MASK			((0x1f << 19) | (0x1f << 14))
 
 #define GEN7_L3CNTLREG1				_MMIO(0xB01C)
 #define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C
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..5d4cd3d 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;
@@ -1233,7 +1240,7 @@
 {
 	enum port port;
 
-	if (!HAS_DDI(dev_priv))
+	if (!HAS_DDI(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		return;
 
 	if (!dev_priv->vbt.child_dev_num)
diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c
index ff9ecd2..b8315bc 100644
--- a/drivers/gpu/drm/i915/intel_color.c
+++ b/drivers/gpu/drm/i915/intel_color.c
@@ -74,7 +74,7 @@
 #define I9XX_CSC_COEFF_1_0		\
 	((7 << 12) | I9XX_CSC_COEFF_FP(CTM_COEFF_1_0, 8))
 
-static bool crtc_state_is_legacy(struct drm_crtc_state *state)
+static bool crtc_state_is_legacy_gamma(struct drm_crtc_state *state)
 {
 	return !state->degamma_lut &&
 		!state->ctm &&
@@ -288,7 +288,7 @@
 	}
 
 	mode = (state->ctm ? CGM_PIPE_MODE_CSC : 0);
-	if (!crtc_state_is_legacy(state)) {
+	if (!crtc_state_is_legacy_gamma(state)) {
 		mode |= (state->degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) |
 			(state->gamma_lut ? CGM_PIPE_MODE_GAMMA : 0);
 	}
@@ -469,7 +469,7 @@
 	struct intel_crtc_state *intel_state = to_intel_crtc_state(state);
 	enum pipe pipe = to_intel_crtc(state->crtc)->pipe;
 
-	if (crtc_state_is_legacy(state)) {
+	if (crtc_state_is_legacy_gamma(state)) {
 		haswell_load_luts(state);
 		return;
 	}
@@ -529,7 +529,7 @@
 
 	glk_load_degamma_lut(state);
 
-	if (crtc_state_is_legacy(state)) {
+	if (crtc_state_is_legacy_gamma(state)) {
 		haswell_load_luts(state);
 		return;
 	}
@@ -551,7 +551,7 @@
 	uint32_t i, lut_size;
 	uint32_t word0, word1;
 
-	if (crtc_state_is_legacy(state)) {
+	if (crtc_state_is_legacy_gamma(state)) {
 		/* Turn off degamma/gamma on CGM block. */
 		I915_WRITE(CGM_PIPE_MODE(pipe),
 			   (state->ctm ? CGM_PIPE_MODE_CSC : 0));
@@ -632,12 +632,10 @@
 		return 0;
 
 	/*
-	 * We also allow no degamma lut and a gamma lut at the legacy
+	 * We also allow no degamma lut/ctm and a gamma lut at the legacy
 	 * size (256 entries).
 	 */
-	if (!crtc_state->degamma_lut &&
-	    crtc_state->gamma_lut &&
-	    crtc_state->gamma_lut->length == LEGACY_LUT_LENGTH)
+	if (crtc_state_is_legacy_gamma(crtc_state))
 		return 0;
 
 	return -EINVAL;
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..5e5fe03 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -664,8 +664,8 @@
 			    int *n_entries)
 {
 	if (IS_BROADWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(hsw_ddi_translations_fdi);
-		return hsw_ddi_translations_fdi;
+		*n_entries = ARRAY_SIZE(bdw_ddi_translations_fdi);
+		return bdw_ddi_translations_fdi;
 	} else if (IS_HASWELL(dev_priv)) {
 		*n_entries = ARRAY_SIZE(hsw_ddi_translations_fdi);
 		return hsw_ddi_translations_fdi;
@@ -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);
@@ -2101,8 +2102,7 @@
 		 * register writes.
 		 */
 		val = I915_READ(DPCLKA_CFGCR0);
-		val &= ~(DPCLKA_CFGCR0_DDI_CLK_OFF(port) |
-			 DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port));
+		val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port);
 		I915_WRITE(DPCLKA_CFGCR0, val);
 	} else if (IS_GEN9_BC(dev_priv)) {
 		/* DDI -> PLL mapping  */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f172755..5c7828c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10245,13 +10245,10 @@
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
+	enum transcoder cpu_transcoder;
 	struct drm_display_mode *mode;
 	struct intel_crtc_state *pipe_config;
-	int htot = I915_READ(HTOTAL(cpu_transcoder));
-	int hsync = I915_READ(HSYNC(cpu_transcoder));
-	int vtot = I915_READ(VTOTAL(cpu_transcoder));
-	int vsync = I915_READ(VSYNC(cpu_transcoder));
+	u32 htot, hsync, vtot, vsync;
 	enum pipe pipe = intel_crtc->pipe;
 
 	mode = kzalloc(sizeof(*mode), GFP_KERNEL);
@@ -10279,6 +10276,13 @@
 	i9xx_crtc_clock_get(intel_crtc, pipe_config);
 
 	mode->clock = pipe_config->port_clock / pipe_config->pixel_multiplier;
+
+	cpu_transcoder = pipe_config->cpu_transcoder;
+	htot = I915_READ(HTOTAL(cpu_transcoder));
+	hsync = I915_READ(HSYNC(cpu_transcoder));
+	vtot = I915_READ(VTOTAL(cpu_transcoder));
+	vsync = I915_READ(VSYNC(cpu_transcoder));
+
 	mode->hdisplay = (htot & 0xffff) + 1;
 	mode->htotal = ((htot & 0xffff0000) >> 16) + 1;
 	mode->hsync_start = (hsync & 0xffff) + 1;
@@ -12359,7 +12363,6 @@
 	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 +12379,6 @@
 
 		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 +14032,7 @@
 
 		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_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 6413494..2031986 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2307,8 +2307,8 @@
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
 
-	intel_dp->panel_power_off_time = ktime_get_boottime();
 	wait_panel_off(intel_dp);
+	intel_dp->panel_power_off_time = ktime_get_boottime();
 
 	/* We got a reference when we enabled the VDD. */
 	intel_display_power_put(dev_priv, intel_dp->aux_power_domain);
@@ -5273,7 +5273,7 @@
 	 * seems sufficient to avoid this problem.
 	 */
 	if (dev_priv->quirks & QUIRK_INCREASE_T12_DELAY) {
-		vbt.t11_t12 = max_t(u16, vbt.t11_t12, 900 * 10);
+		vbt.t11_t12 = max_t(u16, vbt.t11_t12, 1300 * 10);
 		DRM_DEBUG_KMS("Increasing T12 panel delay as per the quirk to %d\n",
 			      vbt.t11_t12);
 	}
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_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index a2a3d93..df808a9 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -1996,7 +1996,7 @@
 
 	/* 3. Configure DPLL_CFGCR0 */
 	/* Avoid touch CFGCR1 if HDMI mode is not enabled */
-	if (pll->state.hw_state.cfgcr0 & DPLL_CTRL1_HDMI_MODE(pll->id)) {
+	if (pll->state.hw_state.cfgcr0 & DPLL_CFGCR0_HDMI_MODE) {
 		val = pll->state.hw_state.cfgcr1;
 		I915_WRITE(CNL_DPLL_CFGCR1(pll->id), val);
 		/* 4. Reab back to ensure writes completed */
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_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 9ab5969..3c2d9cf 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1048,9 +1048,12 @@
 	}
 
 	/* WaProgramL3SqcReg1DefaultForPerf:bxt */
-	if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER))
-		I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) |
-					   L3_HIGH_PRIO_CREDITS(2));
+	if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) {
+		u32 val = I915_READ(GEN8_L3SQCREG1);
+		val &= ~L3_PRIO_CREDITS_MASK;
+		val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2);
+		I915_WRITE(GEN8_L3SQCREG1, val);
+	}
 
 	/* WaToEnableHwFixForPushConstHWBug:bxt */
 	if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER))
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_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ed66293..0a09f8f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -8245,14 +8245,17 @@
 				   int high_prio_credits)
 {
 	u32 misccpctl;
+	u32 val;
 
 	/* WaTempDisableDOPClkGating:bdw */
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 
-	I915_WRITE(GEN8_L3SQCREG1,
-		   L3_GENERAL_PRIO_CREDITS(general_prio_credits) |
-		   L3_HIGH_PRIO_CREDITS(high_prio_credits));
+	val = I915_READ(GEN8_L3SQCREG1);
+	val &= ~L3_PRIO_CREDITS_MASK;
+	val |= L3_GENERAL_PRIO_CREDITS(general_prio_credits);
+	val |= L3_HIGH_PRIO_CREDITS(high_prio_credits);
+	I915_WRITE(GEN8_L3SQCREG1, val);
 
 	/*
 	 * Wait at least 100 clocks before re-enabling clock gating.
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index b66d8e1..49577eb 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -368,7 +368,7 @@
 {
 	enum i915_power_well_id id = power_well->id;
 	bool wait_fuses = power_well->hsw.has_fuses;
-	enum skl_power_gate pg;
+	enum skl_power_gate uninitialized_var(pg);
 	u32 val;
 
 	if (wait_fuses) {
@@ -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/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index dbb31a0..deaf869 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -248,7 +248,7 @@
 	clk_disable_unprepare(ahb_clk);
 disable_gdsc:
 	regulator_disable(gdsc_reg);
-	pm_runtime_put_autosuspend(dev);
+	pm_runtime_put_sync(dev);
 put_clk:
 	clk_put(ahb_clk);
 put_gdsc:
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
index c2bdad8..824067d 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
@@ -83,6 +83,8 @@
 				  .caps = MDP_LM_CAP_WB },
 			     },
 		.nb_stages = 5,
+		.max_width = 2048,
+		.max_height = 0xFFFF,
 	},
 	.dspp = {
 		.count = 3,
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index 6fcb58a..4409776 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -804,8 +804,6 @@
 
 	spin_unlock_irqrestore(&mdp5_crtc->cursor.lock, flags);
 
-	pm_runtime_put_autosuspend(&pdev->dev);
-
 set_cursor:
 	ret = mdp5_ctl_set_cursor(ctl, pipeline, 0, cursor_enable);
 	if (ret) {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index f15821a0..ea5bb0e 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -610,17 +610,6 @@
 	struct dma_fence *fence;
 	int i, ret;
 
-	if (!exclusive) {
-		/* NOTE: _reserve_shared() must happen before _add_shared_fence(),
-		 * which makes this a slightly strange place to call it.  OTOH this
-		 * is a convenient can-fail point to hook it in.  (And similar to
-		 * how etnaviv and nouveau handle this.)
-		 */
-		ret = reservation_object_reserve_shared(msm_obj->resv);
-		if (ret)
-			return ret;
-	}
-
 	fobj = reservation_object_get_list(msm_obj->resv);
 	if (!fobj || (fobj->shared_count == 0)) {
 		fence = reservation_object_get_excl(msm_obj->resv);
@@ -1045,10 +1034,10 @@
 	}
 
 	vaddr = msm_gem_get_vaddr(obj);
-	if (!vaddr) {
+	if (IS_ERR(vaddr)) {
 		msm_gem_put_iova(obj, aspace);
 		drm_gem_object_unreference(obj);
-		return ERR_PTR(-ENOMEM);
+		return ERR_CAST(vaddr);
 	}
 
 	if (bo)
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 5d0a75d..93535ca 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -221,7 +221,7 @@
 	return ret;
 }
 
-static int submit_fence_sync(struct msm_gem_submit *submit)
+static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
 {
 	int i, ret = 0;
 
@@ -229,6 +229,20 @@
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
 		bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE;
 
+		if (!write) {
+			/* NOTE: _reserve_shared() must happen before
+			 * _add_shared_fence(), which makes this a slightly
+			 * strange place to call it.  OTOH this is a
+			 * convenient can-fail point to hook it in.
+			 */
+			ret = reservation_object_reserve_shared(msm_obj->resv);
+			if (ret)
+				return ret;
+		}
+
+		if (no_implicit)
+			continue;
+
 		ret = msm_gem_sync_object(&msm_obj->base, submit->gpu->fctx, write);
 		if (ret)
 			break;
@@ -451,11 +465,9 @@
 	if (ret)
 		goto out;
 
-	if (!(args->flags & MSM_SUBMIT_NO_IMPLICIT)) {
-		ret = submit_fence_sync(submit);
-		if (ret)
-			goto out;
-	}
+	ret = submit_fence_sync(submit, !!(args->flags & MSM_SUBMIT_NO_IMPLICIT));
+	if (ret)
+		goto out;
 
 	ret = submit_pin_objects(submit);
 	if (ret)
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index ffbff27..6a88703 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -718,7 +718,8 @@
 			msm_gem_put_iova(gpu->rb->bo, gpu->aspace);
 		msm_ringbuffer_destroy(gpu->rb);
 	}
-	if (gpu->aspace) {
+
+	if (!IS_ERR_OR_NULL(gpu->aspace)) {
 		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
 			NULL, 0);
 		msm_gem_address_space_put(gpu->aspace);
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index 0366b80..ec56794 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -111,10 +111,14 @@
 
 		wait_event(rd->fifo_event, circ_space(&rd->fifo) > 0);
 
+		/* Note that smp_load_acquire() is not strictly required
+		 * as CIRC_SPACE_TO_END() does not access the tail more
+		 * than once.
+		 */
 		n = min(sz, circ_space_to_end(&rd->fifo));
 		memcpy(fptr, ptr, n);
 
-		fifo->head = (fifo->head + n) & (BUF_SZ - 1);
+		smp_store_release(&fifo->head, (fifo->head + n) & (BUF_SZ - 1));
 		sz  -= n;
 		ptr += n;
 
@@ -145,13 +149,17 @@
 	if (ret)
 		goto out;
 
+	/* Note that smp_load_acquire() is not strictly required
+	 * as CIRC_CNT_TO_END() does not access the head more than
+	 * once.
+	 */
 	n = min_t(int, sz, circ_count_to_end(&rd->fifo));
 	if (copy_to_user(buf, fptr, n)) {
 		ret = -EFAULT;
 		goto out;
 	}
 
-	fifo->tail = (fifo->tail + n) & (BUF_SZ - 1);
+	smp_store_release(&fifo->tail, (fifo->tail + n) & (BUF_SZ - 1));
 	*ppos += n;
 
 	wake_up_all(&rd->fifo_event);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index f770784..2b12d82 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -223,7 +223,7 @@
 nouveau_fbcon_accel_save_disable(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	if (drm->fbcon) {
+	if (drm->fbcon && drm->fbcon->helper.fbdev) {
 		drm->fbcon->saved_flags = drm->fbcon->helper.fbdev->flags;
 		drm->fbcon->helper.fbdev->flags |= FBINFO_HWACCEL_DISABLED;
 	}
@@ -233,7 +233,7 @@
 nouveau_fbcon_accel_restore(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	if (drm->fbcon) {
+	if (drm->fbcon && drm->fbcon->helper.fbdev) {
 		drm->fbcon->helper.fbdev->flags = drm->fbcon->saved_flags;
 	}
 }
@@ -245,7 +245,8 @@
 	struct nouveau_fbdev *fbcon = drm->fbcon;
 	if (fbcon && drm->channel) {
 		console_lock();
-		fbcon->helper.fbdev->flags |= FBINFO_HWACCEL_DISABLED;
+		if (fbcon->helper.fbdev)
+			fbcon->helper.fbdev->flags |= FBINFO_HWACCEL_DISABLED;
 		console_unlock();
 		nouveau_channel_idle(drm->channel);
 		nvif_object_fini(&fbcon->twod);
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 2dbf62a..e4751f9 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -3265,11 +3265,14 @@
 void
 nv50_mstm_service(struct nv50_mstm *mstm)
 {
-	struct drm_dp_aux *aux = mstm->mgr.aux;
+	struct drm_dp_aux *aux = mstm ? mstm->mgr.aux : NULL;
 	bool handled = true;
 	int ret;
 	u8 esi[8] = {};
 
+	if (!aux)
+		return;
+
 	while (handled) {
 		ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT_ESI, esi, 8);
 		if (ret != 8) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c b/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c
index 8e2e24a..44e116f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c
@@ -39,5 +39,5 @@
 g84_bsp_new(struct nvkm_device *device, int index, struct nvkm_engine **pengine)
 {
 	return nvkm_xtensa_new_(&g84_bsp, device, index,
-				true, 0x103000, pengine);
+				device->chipset != 0x92, 0x103000, pengine);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
index d06ad2c..455da29 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
@@ -241,6 +241,8 @@
 			mmu->func->map_pgt(vpgd->obj, pde, vpgt->mem);
 		}
 
+		mmu->func->flush(vm);
+
 		nvkm_memory_del(&pgt);
 	}
 }
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/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 6a573d2..658fa2d 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -405,6 +405,14 @@
 		return -EINVAL;
 	}
 
+	/*
+	 * IPUv3EX / i.MX51 has a different register layout, and on IPUv3M /
+	 * i.MX53 channel arbitration locking doesn't seem to work properly.
+	 * Allow enabling the lock feature on IPUv3H / i.MX6 only.
+	 */
+	if (bursts && ipu->ipu_type != IPUV3H)
+		return -EINVAL;
+
 	for (i = 0; i < ARRAY_SIZE(idmac_lock_en_info); i++) {
 		if (channel->num == idmac_lock_en_info[i].chnum)
 			break;
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index c35f74c..c860a79 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -73,6 +73,14 @@
 #define  IPU_PRE_STORE_ENG_CTRL_WR_NUM_BYTES(v)		((v & 0x7) << 1)
 #define  IPU_PRE_STORE_ENG_CTRL_OUTPUT_ACTIVE_BPP(v)	((v & 0x3) << 4)
 
+#define IPU_PRE_STORE_ENG_STATUS			0x120
+#define  IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_X_MASK	0xffff
+#define  IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_X_SHIFT	0
+#define  IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_MASK	0x3fff
+#define  IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_SHIFT	16
+#define  IPU_PRE_STORE_ENG_STATUS_STORE_FIFO_FULL	(1 << 30)
+#define  IPU_PRE_STORE_ENG_STATUS_STORE_FIELD		(1 << 31)
+
 #define IPU_PRE_STORE_ENG_SIZE				0x130
 #define  IPU_PRE_STORE_ENG_SIZE_INPUT_WIDTH(v)		((v & 0xffff) << 0)
 #define  IPU_PRE_STORE_ENG_SIZE_INPUT_HEIGHT(v)		((v & 0xffff) << 16)
@@ -93,6 +101,7 @@
 	dma_addr_t		buffer_paddr;
 	void			*buffer_virt;
 	bool			in_use;
+	unsigned int		safe_window_end;
 };
 
 static DEFINE_MUTEX(ipu_pre_list_mutex);
@@ -160,6 +169,9 @@
 	u32 active_bpp = info->cpp[0] >> 1;
 	u32 val;
 
+	/* calculate safe window for ctrl register updates */
+	pre->safe_window_end = height - 2;
+
 	writel(bufaddr, pre->regs + IPU_PRE_CUR_BUF);
 	writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF);
 
@@ -199,7 +211,24 @@
 
 void ipu_pre_update(struct ipu_pre *pre, unsigned int bufaddr)
 {
+	unsigned long timeout = jiffies + msecs_to_jiffies(5);
+	unsigned short current_yblock;
+	u32 val;
+
 	writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF);
+
+	do {
+		if (time_after(jiffies, timeout)) {
+			dev_warn(pre->dev, "timeout waiting for PRE safe window\n");
+			return;
+		}
+
+		val = readl(pre->regs + IPU_PRE_STORE_ENG_STATUS);
+		current_yblock =
+			(val >> IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_SHIFT) &
+			IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_MASK;
+	} while (current_yblock == 0 || current_yblock >= pre->safe_window_end);
+
 	writel(IPU_PRE_CTRL_SDW_UPDATE, pre->regs + IPU_PRE_CTRL_SET);
 }
 
diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c
index ecc9ea4..0013ca9 100644
--- a/drivers/gpu/ipu-v3/ipu-prg.c
+++ b/drivers/gpu/ipu-v3/ipu-prg.c
@@ -14,6 +14,7 @@
 #include <drm/drm_fourcc.h>
 #include <linux/clk.h>
 #include <linux/err.h>
+#include <linux/iopoll.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
 #include <linux/module.h>
@@ -329,6 +330,12 @@
 	val = IPU_PRG_REG_UPDATE_REG_UPDATE;
 	writel(val, prg->regs + IPU_PRG_REG_UPDATE);
 
+	/* wait for both double buffers to be filled */
+	readl_poll_timeout(prg->regs + IPU_PRG_STATUS, val,
+			   (val & IPU_PRG_STATUS_BUFFER0_READY(prg_chan)) &&
+			   (val & IPU_PRG_STATUS_BUFFER1_READY(prg_chan)),
+			   5, 1000);
+
 	clk_disable_unprepare(prg->clk_ipg);
 
 	chan->enabled = true;
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 0a3117c..374301f 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -281,6 +281,7 @@
 	Support for ELECOM devices:
 	  - BM084 Bluetooth Mouse
 	  - DEFT Trackball (Wired and wireless)
+	  - HUGE Trackball (Wired and wireless)
 
 config HID_ELO
 	tristate "ELO USB 4000/4500 touchscreen"
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 9bc9116..330ca98 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2032,6 +2032,8 @@
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRED) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRELESS) },
 #endif
 #if IS_ENABLED(CONFIG_HID_ELO)
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) },
diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c
index e2c7465..54aeea5 100644
--- a/drivers/hid/hid-elecom.c
+++ b/drivers/hid/hid-elecom.c
@@ -3,6 +3,7 @@
  *  Copyright (c) 2010 Richard Nauber <Richard.Nauber@gmail.com>
  *  Copyright (c) 2016 Yuxuan Shui <yshuiv7@gmail.com>
  *  Copyright (c) 2017 Diego Elio Pettenò <flameeyes@flameeyes.eu>
+ *  Copyright (c) 2017 Alex Manoussakis <amanou@gnu.org>
  */
 
 /*
@@ -32,9 +33,11 @@
 		break;
 	case USB_DEVICE_ID_ELECOM_DEFT_WIRED:
 	case USB_DEVICE_ID_ELECOM_DEFT_WIRELESS:
-		/* The DEFT trackball has eight buttons, but its descriptor only
-		 * reports five, disabling the three Fn buttons on the top of
-		 * the mouse.
+	case USB_DEVICE_ID_ELECOM_HUGE_WIRED:
+	case USB_DEVICE_ID_ELECOM_HUGE_WIRELESS:
+		/* The DEFT/HUGE trackball has eight buttons, but its descriptor
+		 * only reports five, disabling the three Fn buttons on the top
+		 * of the mouse.
 		 *
 		 * Apply the following diff to the descriptor:
 		 *
@@ -62,7 +65,7 @@
 		 * End Collection,                     End Collection,
 		 */
 		if (*rsize == 213 && rdesc[13] == 5 && rdesc[21] == 5) {
-			hid_info(hdev, "Fixing up Elecom DEFT Fn buttons\n");
+			hid_info(hdev, "Fixing up Elecom DEFT/HUGE Fn buttons\n");
 			rdesc[13] = 8; /* Button/Variable Report Count */
 			rdesc[21] = 8; /* Button/Variable Usage Maximum */
 			rdesc[29] = 0; /* Button/Constant Report Count */
@@ -76,6 +79,8 @@
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRED) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRELESS) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, elecom_devices);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index b397a14..be2e005 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -368,6 +368,8 @@
 #define USB_DEVICE_ID_ELECOM_BM084	0x0061
 #define USB_DEVICE_ID_ELECOM_DEFT_WIRED	0x00fe
 #define USB_DEVICE_ID_ELECOM_DEFT_WIRELESS	0x00ff
+#define USB_DEVICE_ID_ELECOM_HUGE_WIRED	0x010c
+#define USB_DEVICE_ID_ELECOM_HUGE_WIRELESS	0x010d
 
 #define USB_VENDOR_ID_DREAM_CHEEKY	0x1d34
 #define USB_DEVICE_ID_DREAM_CHEEKY_WN	0x0004
@@ -533,6 +535,7 @@
 #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 +663,7 @@
 #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-core.c b/drivers/hid/usbhid/hid-core.c
index 089bad8..045b5da 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -975,6 +975,8 @@
 	unsigned int rsize = 0;
 	char *rdesc;
 	int ret, n;
+	int num_descriptors;
+	size_t offset = offsetof(struct hid_descriptor, desc);
 
 	quirks = usbhid_lookup_quirk(le16_to_cpu(dev->descriptor.idVendor),
 			le16_to_cpu(dev->descriptor.idProduct));
@@ -997,10 +999,18 @@
 		return -ENODEV;
 	}
 
+	if (hdesc->bLength < sizeof(struct hid_descriptor)) {
+		dbg_hid("hid descriptor is too short\n");
+		return -EINVAL;
+	}
+
 	hid->version = le16_to_cpu(hdesc->bcdHID);
 	hid->country = hdesc->bCountryCode;
 
-	for (n = 0; n < hdesc->bNumDescriptors; n++)
+	num_descriptors = min_t(int, hdesc->bNumDescriptors,
+	       (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor));
+
+	for (n = 0; n < num_descriptors; n++)
 		if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT)
 			rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength);
 
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.c b/drivers/hv/channel.c
index efd5db7..894b67a 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -640,6 +640,7 @@
 		 */
 		return;
 	}
+	mutex_lock(&vmbus_connection.channel_mutex);
 	/*
 	 * Close all the sub-channels first and then close the
 	 * primary channel.
@@ -648,16 +649,15 @@
 		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
 		vmbus_close_internal(cur_channel);
 		if (cur_channel->rescind) {
-			mutex_lock(&vmbus_connection.channel_mutex);
-			hv_process_channel_removal(cur_channel,
+			hv_process_channel_removal(
 					   cur_channel->offermsg.child_relid);
-			mutex_unlock(&vmbus_connection.channel_mutex);
 		}
 	}
 	/*
 	 * Now close the primary.
 	 */
 	vmbus_close_internal(channel);
+	mutex_unlock(&vmbus_connection.channel_mutex);
 }
 EXPORT_SYMBOL_GPL(vmbus_close);
 
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 060df71..379b0df 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -159,7 +159,7 @@
 
 
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
-
+	channel->rescind = true;
 	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
 				msglistentry) {
 
@@ -381,14 +381,21 @@
 		       true);
 }
 
-void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
+void hv_process_channel_removal(u32 relid)
 {
 	unsigned long flags;
-	struct vmbus_channel *primary_channel;
+	struct vmbus_channel *primary_channel, *channel;
 
-	BUG_ON(!channel->rescind);
 	BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
 
+	/*
+	 * Make sure channel is valid as we may have raced.
+	 */
+	channel = relid2channel(relid);
+	if (!channel)
+		return;
+
+	BUG_ON(!channel->rescind);
 	if (channel->target_cpu != get_cpu()) {
 		put_cpu();
 		smp_call_function_single(channel->target_cpu,
@@ -515,6 +522,7 @@
 	if (!fnew) {
 		if (channel->sc_creation_callback != NULL)
 			channel->sc_creation_callback(newchannel);
+		newchannel->probe_done = true;
 		return;
 	}
 
@@ -834,7 +842,6 @@
 {
 	struct vmbus_channel_rescind_offer *rescind;
 	struct vmbus_channel *channel;
-	unsigned long flags;
 	struct device *dev;
 
 	rescind = (struct vmbus_channel_rescind_offer *)hdr;
@@ -873,16 +880,6 @@
 		return;
 	}
 
-	spin_lock_irqsave(&channel->lock, flags);
-	channel->rescind = true;
-	spin_unlock_irqrestore(&channel->lock, flags);
-
-	/*
-	 * Now that we have posted the rescind state, perform
-	 * rescind related cleanup.
-	 */
-	vmbus_rescind_cleanup(channel);
-
 	/*
 	 * Now wait for offer handling to complete.
 	 */
@@ -901,6 +898,7 @@
 	if (channel->device_obj) {
 		if (channel->chn_rescind_callback) {
 			channel->chn_rescind_callback(channel);
+			vmbus_rescind_cleanup(channel);
 			return;
 		}
 		/*
@@ -909,6 +907,7 @@
 		 */
 		dev = get_device(&channel->device_obj->device);
 		if (dev) {
+			vmbus_rescind_cleanup(channel);
 			vmbus_device_unregister(channel->device_obj);
 			put_device(dev);
 		}
@@ -921,29 +920,28 @@
 		 * 1. Close all sub-channels first
 		 * 2. Then close the primary channel.
 		 */
+		mutex_lock(&vmbus_connection.channel_mutex);
+		vmbus_rescind_cleanup(channel);
 		if (channel->state == CHANNEL_OPEN_STATE) {
 			/*
 			 * The channel is currently not open;
 			 * it is safe for us to cleanup the channel.
 			 */
-			mutex_lock(&vmbus_connection.channel_mutex);
-			hv_process_channel_removal(channel,
-						channel->offermsg.child_relid);
-			mutex_unlock(&vmbus_connection.channel_mutex);
+			hv_process_channel_removal(rescind->child_relid);
 		}
+		mutex_unlock(&vmbus_connection.channel_mutex);
 	}
 }
 
 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);
+	/* We always get a rescind msg when a connection is closed. */
+	while (!READ_ONCE(channel->probe_done) || !READ_ONCE(channel->rescind))
+		msleep(1);
 
-	mutex_unlock(&vmbus_connection.channel_mutex);
+	vmbus_device_unregister(channel->device_obj);
 }
 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/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index a9d49f6..937801a 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -768,8 +768,7 @@
 	struct vmbus_channel *channel = hv_dev->channel;
 
 	mutex_lock(&vmbus_connection.channel_mutex);
-	hv_process_channel_removal(channel,
-				   channel->offermsg.child_relid);
+	hv_process_channel_removal(channel->offermsg.child_relid);
 	mutex_unlock(&vmbus_connection.channel_mutex);
 	kfree(hv_dev);
 
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index 97a62f5..a973eb6 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -477,6 +477,11 @@
 		/* disable touchscreen features */
 		da9052_reg_write(hwmon->da9052, DA9052_TSI_CONT_A_REG, 0x00);
 
+		/* Sample every 1ms */
+		da9052_reg_update(hwmon->da9052, DA9052_ADC_CONT_REG,
+					  DA9052_ADCCONT_ADCMODE,
+					  DA9052_ADCCONT_ADCMODE);
+
 		err = da9052_request_irq(hwmon->da9052, DA9052_IRQ_TSIREADY,
 					 "tsiready-irq", da9052_tsi_datardy_irq,
 					 hwmon);
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index 5eafbaa..dfc40c7 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -268,14 +268,11 @@
 		return err;
 	}
 
-	tmp102->ready_time = jiffies;
-	if (tmp102->config_orig & TMP102_CONF_SD) {
-		/*
-		 * Mark that we are not ready with data until the first
-		 * conversion is complete
-		 */
-		tmp102->ready_time += msecs_to_jiffies(CONVERSION_TIME_MS);
-	}
+	/*
+	 * Mark that we are not ready with data until the first
+	 * conversion is complete
+	 */
+	tmp102->ready_time = jiffies + msecs_to_jiffies(CONVERSION_TIME_MS);
 
 	hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name,
 							 tmp102,
diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c
index 9c0dbb8..e1be610 100644
--- a/drivers/hwmon/xgene-hwmon.c
+++ b/drivers/hwmon/xgene-hwmon.c
@@ -630,7 +630,7 @@
 			 sizeof(struct slimpro_resp_msg) * ASYNC_MSG_FIFO_SIZE,
 			 GFP_KERNEL);
 	if (rc)
-		goto out_mbox_free;
+		return -ENOMEM;
 
 	INIT_WORK(&ctx->workq, xgene_hwmon_evt_work);
 
@@ -646,7 +646,8 @@
 		if (IS_ERR(ctx->mbox_chan)) {
 			dev_err(&pdev->dev,
 				"SLIMpro mailbox channel request failed\n");
-			return -ENODEV;
+			rc = -ENODEV;
+			goto out_mbox_free;
 		}
 	} else {
 		struct acpi_pcct_hw_reduced *cppc_ss;
@@ -654,7 +655,8 @@
 		if (device_property_read_u32(&pdev->dev, "pcc-channel",
 					     &ctx->mbox_idx)) {
 			dev_err(&pdev->dev, "no pcc-channel property\n");
-			return -ENODEV;
+			rc = -ENODEV;
+			goto out_mbox_free;
 		}
 
 		cl->rx_callback = xgene_hwmon_pcc_rx_cb;
@@ -662,7 +664,8 @@
 		if (IS_ERR(ctx->mbox_chan)) {
 			dev_err(&pdev->dev,
 				"PPC channel request failed\n");
-			return -ENODEV;
+			rc = -ENODEV;
+			goto out_mbox_free;
 		}
 
 		/*
@@ -675,13 +678,13 @@
 		if (!cppc_ss) {
 			dev_err(&pdev->dev, "PPC subspace not found\n");
 			rc = -ENODEV;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		if (!ctx->mbox_chan->mbox->txdone_irq) {
 			dev_err(&pdev->dev, "PCC IRQ not supported\n");
 			rc = -ENODEV;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		/*
@@ -696,14 +699,14 @@
 		} else {
 			dev_err(&pdev->dev, "Failed to get PCC comm region\n");
 			rc = -ENODEV;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		if (!ctx->pcc_comm_addr) {
 			dev_err(&pdev->dev,
 				"Failed to ioremap PCC comm region\n");
 			rc = -ENOMEM;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		/*
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/Kconfig b/drivers/i2c/busses/Kconfig
index c06dce2..45a3f3ca 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -131,6 +131,7 @@
 	    Gemini Lake (SOC)
 	    Cannon Lake-H (PCH)
 	    Cannon Lake-LP (PCH)
+	    Cedar Fork (PCH)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index e114e4e..9e12a53 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -68,6 +68,7 @@
  * Gemini Lake (SOC)		0x31d4	32	hard	yes	yes	yes
  * Cannon Lake-H (PCH)		0xa323	32	hard	yes	yes	yes
  * Cannon Lake-LP (PCH)		0x9da3	32	hard	yes	yes	yes
+ * Cedar Fork (PCH)		0x18df	32	hard	yes	yes	yes
  *
  * Features supported by this driver:
  * Software PEC				no
@@ -204,6 +205,7 @@
 
 /* Older devices have their ID defined in <linux/pci_ids.h> */
 #define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS		0x0f12
+#define PCI_DEVICE_ID_INTEL_CDF_SMBUS			0x18df
 #define PCI_DEVICE_ID_INTEL_DNV_SMBUS			0x19df
 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS		0x1c22
 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS		0x1d22
@@ -1025,6 +1027,7 @@
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BRASWELL_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CDF_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) },
@@ -1513,6 +1516,7 @@
 	case PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS:
 	case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS:
 	case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS:
+	case PCI_DEVICE_ID_INTEL_CDF_SMBUS:
 	case PCI_DEVICE_ID_INTEL_DNV_SMBUS:
 	case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS:
 		priv->features |= FEATURE_I2C_BLOCK_READ;
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/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 54a47b4..f96830f 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1021,7 +1021,7 @@
 	}
 
 	dev_dbg(&pdev->dev, "using scl-gpio %d and sda-gpio %d for recovery\n",
-			rinfo->sda_gpio, rinfo->scl_gpio);
+			rinfo->scl_gpio, rinfo->sda_gpio);
 
 	rinfo->prepare_recovery = i2c_imx_prepare_recovery;
 	rinfo->unprepare_recovery = i2c_imx_unprepare_recovery;
@@ -1100,7 +1100,7 @@
 	}
 
 	/* Request IRQ */
-	ret = devm_request_irq(&pdev->dev, irq, i2c_imx_isr, 0,
+	ret = devm_request_irq(&pdev->dev, irq, i2c_imx_isr, IRQF_SHARED,
 				pdev->name, i2c_imx);
 	if (ret) {
 		dev_err(&pdev->dev, "can't claim irq %d\n", irq);
diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c
index 22ffcb7..b51adff 100644
--- a/drivers/i2c/busses/i2c-ismt.c
+++ b/drivers/i2c/busses/i2c-ismt.c
@@ -340,12 +340,15 @@
 			data->word = dma_buffer[0] | (dma_buffer[1] << 8);
 			break;
 		case I2C_SMBUS_BLOCK_DATA:
-		case I2C_SMBUS_I2C_BLOCK_DATA:
 			if (desc->rxbytes != dma_buffer[0] + 1)
 				return -EMSGSIZE;
 
 			memcpy(data->block, dma_buffer, desc->rxbytes);
 			break;
+		case I2C_SMBUS_I2C_BLOCK_DATA:
+			memcpy(&data->block[1], dma_buffer, desc->rxbytes);
+			data->block[0] = desc->rxbytes;
+			break;
 		}
 		return 0;
 	}
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 1ebb5e9..23c2ea2 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -360,6 +360,7 @@
 	unsigned long fclk_rate = 12000000;
 	unsigned long internal_clk = 0;
 	struct clk *fclk;
+	int error;
 
 	if (omap->rev >= OMAP_I2C_REV_ON_3430_3530) {
 		/*
@@ -378,6 +379,13 @@
 		 * do this bit unconditionally.
 		 */
 		fclk = clk_get(omap->dev, "fck");
+		if (IS_ERR(fclk)) {
+			error = PTR_ERR(fclk);
+			dev_err(omap->dev, "could not get fck: %i\n", error);
+
+			return error;
+		}
+
 		fclk_rate = clk_get_rate(fclk);
 		clk_put(fclk);
 
@@ -410,6 +418,12 @@
 		else
 			internal_clk = 4000;
 		fclk = clk_get(omap->dev, "fck");
+		if (IS_ERR(fclk)) {
+			error = PTR_ERR(fclk);
+			dev_err(omap->dev, "could not get fck: %i\n", error);
+
+			return error;
+		}
 		fclk_rate = clk_get_rate(fclk) / 1000;
 		clk_put(fclk);
 
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 0ecdb47..174579d 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -85,6 +85,9 @@
 /* SB800 constants */
 #define SB800_PIIX4_SMB_IDX		0xcd6
 
+#define KERNCZ_IMC_IDX			0x3e
+#define KERNCZ_IMC_DATA			0x3f
+
 /*
  * SB800 port is selected by bits 2:1 of the smb_en register (0x2c)
  * or the smb_sel register (0x2e), depending on bit 0 of register 0x2f.
@@ -94,6 +97,12 @@
 #define SB800_PIIX4_PORT_IDX_ALT	0x2e
 #define SB800_PIIX4_PORT_IDX_SEL	0x2f
 #define SB800_PIIX4_PORT_IDX_MASK	0x06
+#define SB800_PIIX4_PORT_IDX_SHIFT	1
+
+/* On kerncz, SmBus0Sel is at bit 20:19 of PMx00 DecodeEn */
+#define SB800_PIIX4_PORT_IDX_KERNCZ		0x02
+#define SB800_PIIX4_PORT_IDX_MASK_KERNCZ	0x18
+#define SB800_PIIX4_PORT_IDX_SHIFT_KERNCZ	3
 
 /* insmod parameters */
 
@@ -149,6 +158,8 @@
  */
 static DEFINE_MUTEX(piix4_mutex_sb800);
 static u8 piix4_port_sel_sb800;
+static u8 piix4_port_mask_sb800;
+static u8 piix4_port_shift_sb800;
 static const char *piix4_main_port_names_sb800[PIIX4_MAX_ADAPTERS] = {
 	" port 0", " port 2", " port 3", " port 4"
 };
@@ -159,6 +170,7 @@
 
 	/* SB800 */
 	bool sb800_main;
+	bool notify_imc;
 	u8 port;		/* Port number, shifted */
 };
 
@@ -347,7 +359,19 @@
 
 	/* Find which register is used for port selection */
 	if (PIIX4_dev->vendor == PCI_VENDOR_ID_AMD) {
-		piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_ALT;
+		switch (PIIX4_dev->device) {
+		case PCI_DEVICE_ID_AMD_KERNCZ_SMBUS:
+			piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_KERNCZ;
+			piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK_KERNCZ;
+			piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT_KERNCZ;
+			break;
+		case PCI_DEVICE_ID_AMD_HUDSON2_SMBUS:
+		default:
+			piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_ALT;
+			piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK;
+			piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT;
+			break;
+		}
 	} else {
 		mutex_lock(&piix4_mutex_sb800);
 		outb_p(SB800_PIIX4_PORT_IDX_SEL, SB800_PIIX4_SMB_IDX);
@@ -355,6 +379,8 @@
 		piix4_port_sel_sb800 = (port_sel & 0x01) ?
 				       SB800_PIIX4_PORT_IDX_ALT :
 				       SB800_PIIX4_PORT_IDX;
+		piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK;
+		piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT;
 		mutex_unlock(&piix4_mutex_sb800);
 	}
 
@@ -572,6 +598,67 @@
 	return 0;
 }
 
+static uint8_t piix4_imc_read(uint8_t idx)
+{
+	outb_p(idx, KERNCZ_IMC_IDX);
+	return inb_p(KERNCZ_IMC_DATA);
+}
+
+static void piix4_imc_write(uint8_t idx, uint8_t value)
+{
+	outb_p(idx, KERNCZ_IMC_IDX);
+	outb_p(value, KERNCZ_IMC_DATA);
+}
+
+static int piix4_imc_sleep(void)
+{
+	int timeout = MAX_TIMEOUT;
+
+	if (!request_muxed_region(KERNCZ_IMC_IDX, 2, "smbus_kerncz_imc"))
+		return -EBUSY;
+
+	/* clear response register */
+	piix4_imc_write(0x82, 0x00);
+	/* request ownership flag */
+	piix4_imc_write(0x83, 0xB4);
+	/* kick off IMC Mailbox command 96 */
+	piix4_imc_write(0x80, 0x96);
+
+	while (timeout--) {
+		if (piix4_imc_read(0x82) == 0xfa) {
+			release_region(KERNCZ_IMC_IDX, 2);
+			return 0;
+		}
+		usleep_range(1000, 2000);
+	}
+
+	release_region(KERNCZ_IMC_IDX, 2);
+	return -ETIMEDOUT;
+}
+
+static void piix4_imc_wakeup(void)
+{
+	int timeout = MAX_TIMEOUT;
+
+	if (!request_muxed_region(KERNCZ_IMC_IDX, 2, "smbus_kerncz_imc"))
+		return;
+
+	/* clear response register */
+	piix4_imc_write(0x82, 0x00);
+	/* release ownership flag */
+	piix4_imc_write(0x83, 0xB5);
+	/* kick off IMC Mailbox command 96 */
+	piix4_imc_write(0x80, 0x96);
+
+	while (timeout--) {
+		if (piix4_imc_read(0x82) == 0xfa)
+			break;
+		usleep_range(1000, 2000);
+	}
+
+	release_region(KERNCZ_IMC_IDX, 2);
+}
+
 /*
  * Handles access to multiple SMBus ports on the SB800.
  * The port is selected by bits 2:1 of the smb_en register (0x2c).
@@ -612,12 +699,47 @@
 		return -EBUSY;
 	}
 
+	/*
+	 * Notify the IMC (Integrated Micro Controller) if required.
+	 * Among other responsibilities, the IMC is in charge of monitoring
+	 * the System fans and temperature sensors, and act accordingly.
+	 * All this is done through SMBus and can/will collide
+	 * with our transactions if they are long (BLOCK_DATA).
+	 * Therefore we need to request the ownership flag during those
+	 * transactions.
+	 */
+	if ((size == I2C_SMBUS_BLOCK_DATA) && adapdata->notify_imc) {
+		int ret;
+
+		ret = piix4_imc_sleep();
+		switch (ret) {
+		case -EBUSY:
+			dev_warn(&adap->dev,
+				 "IMC base address index region 0x%x already in use.\n",
+				 KERNCZ_IMC_IDX);
+			break;
+		case -ETIMEDOUT:
+			dev_warn(&adap->dev,
+				 "Failed to communicate with the IMC.\n");
+			break;
+		default:
+			break;
+		}
+
+		/* If IMC communication fails do not retry */
+		if (ret) {
+			dev_warn(&adap->dev,
+				 "Continuing without IMC notification.\n");
+			adapdata->notify_imc = false;
+		}
+	}
+
 	outb_p(piix4_port_sel_sb800, SB800_PIIX4_SMB_IDX);
 	smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1);
 
 	port = adapdata->port;
-	if ((smba_en_lo & SB800_PIIX4_PORT_IDX_MASK) != port)
-		outb_p((smba_en_lo & ~SB800_PIIX4_PORT_IDX_MASK) | port,
+	if ((smba_en_lo & piix4_port_mask_sb800) != port)
+		outb_p((smba_en_lo & ~piix4_port_mask_sb800) | port,
 		       SB800_PIIX4_SMB_IDX + 1);
 
 	retval = piix4_access(adap, addr, flags, read_write,
@@ -628,6 +750,9 @@
 	/* Release the semaphore */
 	outb_p(smbslvcnt | 0x20, SMBSLVCNT);
 
+	if ((size == I2C_SMBUS_BLOCK_DATA) && adapdata->notify_imc)
+		piix4_imc_wakeup();
+
 	mutex_unlock(&piix4_mutex_sb800);
 
 	return retval;
@@ -679,7 +804,7 @@
 static struct i2c_adapter *piix4_aux_adapter;
 
 static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba,
-			     bool sb800_main, u8 port,
+			     bool sb800_main, u8 port, bool notify_imc,
 			     const char *name, struct i2c_adapter **padap)
 {
 	struct i2c_adapter *adap;
@@ -706,7 +831,8 @@
 
 	adapdata->smba = smba;
 	adapdata->sb800_main = sb800_main;
-	adapdata->port = port << 1;
+	adapdata->port = port << piix4_port_shift_sb800;
+	adapdata->notify_imc = notify_imc;
 
 	/* set up the sysfs linkage to our parent device */
 	adap->dev.parent = &dev->dev;
@@ -728,14 +854,15 @@
 	return 0;
 }
 
-static int piix4_add_adapters_sb800(struct pci_dev *dev, unsigned short smba)
+static int piix4_add_adapters_sb800(struct pci_dev *dev, unsigned short smba,
+				    bool notify_imc)
 {
 	struct i2c_piix4_adapdata *adapdata;
 	int port;
 	int retval;
 
 	for (port = 0; port < PIIX4_MAX_ADAPTERS; port++) {
-		retval = piix4_add_adapter(dev, smba, true, port,
+		retval = piix4_add_adapter(dev, smba, true, port, notify_imc,
 					   piix4_main_port_names_sb800[port],
 					   &piix4_main_adapters[port]);
 		if (retval < 0)
@@ -769,6 +896,7 @@
 	     dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS &&
 	     dev->revision >= 0x40) ||
 	    dev->vendor == PCI_VENDOR_ID_AMD) {
+		bool notify_imc = false;
 		is_sb800 = true;
 
 		if (!request_region(SB800_PIIX4_SMB_IDX, 2, "smba_idx")) {
@@ -778,6 +906,20 @@
 			return -EBUSY;
 		}
 
+		if (dev->vendor == PCI_VENDOR_ID_AMD &&
+		    dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS) {
+			u8 imc;
+
+			/*
+			 * Detect if IMC is active or not, this method is
+			 * described on coreboot's AMD IMC notes
+			 */
+			pci_bus_read_config_byte(dev->bus, PCI_DEVFN(0x14, 3),
+						 0x40, &imc);
+			if (imc & 0x80)
+				notify_imc = true;
+		}
+
 		/* base address location etc changed in SB800 */
 		retval = piix4_setup_sb800(dev, id, 0);
 		if (retval < 0) {
@@ -789,7 +931,7 @@
 		 * Try to register multiplexed main SMBus adapter,
 		 * give up if we can't
 		 */
-		retval = piix4_add_adapters_sb800(dev, retval);
+		retval = piix4_add_adapters_sb800(dev, retval, notify_imc);
 		if (retval < 0) {
 			release_region(SB800_PIIX4_SMB_IDX, 2);
 			return retval;
@@ -800,7 +942,7 @@
 			return retval;
 
 		/* Try to register main SMBus adapter, give up if we can't */
-		retval = piix4_add_adapter(dev, retval, false, 0, "",
+		retval = piix4_add_adapter(dev, retval, false, 0, false, "",
 					   &piix4_main_adapters[0]);
 		if (retval < 0)
 			return retval;
@@ -827,7 +969,7 @@
 	if (retval > 0) {
 		/* Try to add the aux adapter if it exists,
 		 * piix4_add_adapter will clean up if this fails */
-		piix4_add_adapter(dev, retval, false, 0,
+		piix4_add_adapter(dev, retval, false, 0, false,
 				  is_sb800 ? piix4_aux_port_name_sb800 : "",
 				  &piix4_aux_adapter);
 	}
diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c
index 22e08ae..25fcc3c 100644
--- a/drivers/i2c/busses/i2c-sprd.c
+++ b/drivers/i2c/busses/i2c-sprd.c
@@ -627,6 +627,7 @@
 
 static const struct of_device_id sprd_i2c_of_match[] = {
 	{ .compatible = "sprd,sc9860-i2c", },
+	{},
 };
 
 static struct platform_driver sprd_i2c_driver = {
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 47c67b0..d4a6e9c 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -215,7 +215,7 @@
 	unsigned int msg_num;
 	unsigned int msg_id;
 	struct stm32f7_i2c_msg f7_msg;
-	struct stm32f7_i2c_setup *setup;
+	struct stm32f7_i2c_setup setup;
 	struct stm32f7_i2c_timings timing;
 };
 
@@ -265,7 +265,7 @@
 	},
 };
 
-struct stm32f7_i2c_setup stm32f7_setup = {
+static const struct stm32f7_i2c_setup stm32f7_setup = {
 	.rise_time = STM32F7_I2C_RISE_TIME_DEFAULT,
 	.fall_time = STM32F7_I2C_FALL_TIME_DEFAULT,
 	.dnf = STM32F7_I2C_DNF_DEFAULT,
@@ -537,7 +537,7 @@
 	writel_relaxed(timing, i2c_dev->base + STM32F7_I2C_TIMINGR);
 
 	/* Enable I2C */
-	if (i2c_dev->setup->analog_filter)
+	if (i2c_dev->setup.analog_filter)
 		stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1,
 				     STM32F7_I2C_CR1_ANFOFF);
 	else
@@ -887,22 +887,19 @@
 	}
 
 	setup = of_device_get_match_data(&pdev->dev);
-	i2c_dev->setup->rise_time = setup->rise_time;
-	i2c_dev->setup->fall_time = setup->fall_time;
-	i2c_dev->setup->dnf = setup->dnf;
-	i2c_dev->setup->analog_filter = setup->analog_filter;
+	i2c_dev->setup = *setup;
 
 	ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-rising-time-ns",
 				       &rise_time);
 	if (!ret)
-		i2c_dev->setup->rise_time = rise_time;
+		i2c_dev->setup.rise_time = rise_time;
 
 	ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-falling-time-ns",
 				       &fall_time);
 	if (!ret)
-		i2c_dev->setup->fall_time = fall_time;
+		i2c_dev->setup.fall_time = fall_time;
 
-	ret = stm32f7_i2c_setup_timing(i2c_dev, i2c_dev->setup);
+	ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup);
 	if (ret)
 		goto clk_free;
 
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/Kconfig b/drivers/iio/adc/Kconfig
index 5762565..1d13bf0 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -243,6 +243,8 @@
 config DLN2_ADC
 	tristate "Diolan DLN-2 ADC driver support"
 	depends on MFD_DLN2
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
 	help
 	  Say yes here to build support for Diolan DLN-2 ADC.
 
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/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index bc5b38e..a70ef7f 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -225,6 +225,7 @@
 	char				*name;
 	unsigned int			trgmod_value;
 	unsigned int			edge_type;
+	bool				hw_trig;
 };
 
 struct at91_adc_state {
@@ -254,16 +255,25 @@
 		.name = "external_rising",
 		.trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_EXT_TRIG_RISE,
 		.edge_type = IRQ_TYPE_EDGE_RISING,
+		.hw_trig = true,
 	},
 	{
 		.name = "external_falling",
 		.trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_EXT_TRIG_FALL,
 		.edge_type = IRQ_TYPE_EDGE_FALLING,
+		.hw_trig = true,
 	},
 	{
 		.name = "external_any",
 		.trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_EXT_TRIG_ANY,
 		.edge_type = IRQ_TYPE_EDGE_BOTH,
+		.hw_trig = true,
+	},
+	{
+		.name = "software",
+		.trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_NO_TRIGGER,
+		.edge_type = IRQ_TYPE_NONE,
+		.hw_trig = false,
 	},
 };
 
@@ -597,7 +607,7 @@
 	struct at91_adc_state *st;
 	struct resource	*res;
 	int ret, i;
-	u32 edge_type;
+	u32 edge_type = IRQ_TYPE_NONE;
 
 	indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*st));
 	if (!indio_dev)
@@ -641,14 +651,14 @@
 	ret = of_property_read_u32(pdev->dev.of_node,
 				   "atmel,trigger-edge-type", &edge_type);
 	if (ret) {
-		dev_err(&pdev->dev,
-			"invalid or missing value for atmel,trigger-edge-type\n");
-		return ret;
+		dev_dbg(&pdev->dev,
+			"atmel,trigger-edge-type not specified, only software trigger available\n");
 	}
 
 	st->selected_trig = NULL;
 
-	for (i = 0; i < AT91_SAMA5D2_HW_TRIG_CNT; i++)
+	/* find the right trigger, or no trigger at all */
+	for (i = 0; i < AT91_SAMA5D2_HW_TRIG_CNT + 1; i++)
 		if (at91_adc_trigger_list[i].edge_type == edge_type) {
 			st->selected_trig = &at91_adc_trigger_list[i];
 			break;
@@ -717,24 +727,27 @@
 
 	platform_set_drvdata(pdev, indio_dev);
 
-	ret = at91_adc_buffer_init(indio_dev);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "couldn't initialize the buffer.\n");
-		goto per_clk_disable_unprepare;
-	}
+	if (st->selected_trig->hw_trig) {
+		ret = at91_adc_buffer_init(indio_dev);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "couldn't initialize the buffer.\n");
+			goto per_clk_disable_unprepare;
+		}
 
-	ret = at91_adc_trigger_init(indio_dev);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "couldn't setup the triggers.\n");
-		goto per_clk_disable_unprepare;
+		ret = at91_adc_trigger_init(indio_dev);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "couldn't setup the triggers.\n");
+			goto per_clk_disable_unprepare;
+		}
 	}
 
 	ret = iio_device_register(indio_dev);
 	if (ret < 0)
 		goto per_clk_disable_unprepare;
 
-	dev_info(&pdev->dev, "setting up trigger as %s\n",
-		 st->selected_trig->name);
+	if (st->selected_trig->hw_trig)
+		dev_info(&pdev->dev, "setting up trigger as %s\n",
+			 st->selected_trig->name);
 
 	dev_info(&pdev->dev, "version: %x\n",
 		 readl_relaxed(st->base + AT91_SAMA5D2_VERSION));
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/dummy/iio_simple_dummy_events.c b/drivers/iio/dummy/iio_simple_dummy_events.c
index ed63ffd..7ec2a0b 100644
--- a/drivers/iio/dummy/iio_simple_dummy_events.c
+++ b/drivers/iio/dummy/iio_simple_dummy_events.c
@@ -72,6 +72,7 @@
 				st->event_en = state;
 			else
 				return -EINVAL;
+			break;
 		default:
 			return -EINVAL;
 		}
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/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c
index ebfb1de..9143145 100644
--- a/drivers/iio/pressure/zpa2326.c
+++ b/drivers/iio/pressure/zpa2326.c
@@ -865,7 +865,6 @@
 static int zpa2326_wait_oneshot_completion(const struct iio_dev   *indio_dev,
 					   struct zpa2326_private *private)
 {
-	int          ret;
 	unsigned int val;
 	long     timeout;
 
@@ -887,14 +886,11 @@
 		/* Timed out. */
 		zpa2326_warn(indio_dev, "no one shot interrupt occurred (%ld)",
 			     timeout);
-		ret = -ETIME;
-	} else if (timeout < 0) {
-		zpa2326_warn(indio_dev,
-			     "wait for one shot interrupt cancelled");
-		ret = -ERESTARTSYS;
+		return -ETIME;
 	}
 
-	return ret;
+	zpa2326_warn(indio_dev, "wait for one shot interrupt cancelled");
+	return -ERESTARTSYS;
 }
 
 static int zpa2326_init_managed_irq(struct device          *parent,
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
index 0eeff29..4a48b7b 100644
--- a/drivers/iio/proximity/as3935.c
+++ b/drivers/iio/proximity/as3935.c
@@ -39,8 +39,12 @@
 #define AS3935_AFE_GAIN_MAX	0x1F
 #define AS3935_AFE_PWR_BIT	BIT(0)
 
+#define AS3935_NFLWDTH		0x01
+#define AS3935_NFLWDTH_MASK	0x7f
+
 #define AS3935_INT		0x03
 #define AS3935_INT_MASK		0x0f
+#define AS3935_DISTURB_INT	BIT(2)
 #define AS3935_EVENT_INT	BIT(3)
 #define AS3935_NOISE_INT	BIT(0)
 
@@ -48,6 +52,7 @@
 #define AS3935_DATA_MASK	0x3F
 
 #define AS3935_TUNE_CAP		0x08
+#define AS3935_DEFAULTS		0x3C
 #define AS3935_CALIBRATE	0x3D
 
 #define AS3935_READ_DATA	BIT(14)
@@ -62,7 +67,9 @@
 	struct mutex lock;
 	struct delayed_work work;
 
+	unsigned long noise_tripped;
 	u32 tune_cap;
+	u32 nflwdth_reg;
 	u8 buffer[16]; /* 8-bit data + 56-bit padding + 64-bit timestamp */
 	u8 buf[2] ____cacheline_aligned;
 };
@@ -145,12 +152,29 @@
 	return len;
 }
 
+static ssize_t as3935_noise_level_tripped_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct as3935_state *st = iio_priv(dev_to_iio_dev(dev));
+	int ret;
+
+	mutex_lock(&st->lock);
+	ret = sprintf(buf, "%d\n", !time_after(jiffies, st->noise_tripped + HZ));
+	mutex_unlock(&st->lock);
+
+	return ret;
+}
+
 static IIO_DEVICE_ATTR(sensor_sensitivity, S_IRUGO | S_IWUSR,
 	as3935_sensor_sensitivity_show, as3935_sensor_sensitivity_store, 0);
 
+static IIO_DEVICE_ATTR(noise_level_tripped, S_IRUGO,
+	as3935_noise_level_tripped_show, NULL, 0);
 
 static struct attribute *as3935_attributes[] = {
 	&iio_dev_attr_sensor_sensitivity.dev_attr.attr,
+	&iio_dev_attr_noise_level_tripped.dev_attr.attr,
 	NULL,
 };
 
@@ -246,7 +270,11 @@
 	case AS3935_EVENT_INT:
 		iio_trigger_poll_chained(st->trig);
 		break;
+	case AS3935_DISTURB_INT:
 	case AS3935_NOISE_INT:
+		mutex_lock(&st->lock);
+		st->noise_tripped = jiffies;
+		mutex_unlock(&st->lock);
 		dev_warn(&st->spi->dev, "noise level is too high\n");
 		break;
 	}
@@ -269,15 +297,14 @@
 
 static void calibrate_as3935(struct as3935_state *st)
 {
-	/* mask disturber interrupt bit */
-	as3935_write(st, AS3935_INT, BIT(5));
-
+	as3935_write(st, AS3935_DEFAULTS, 0x96);
 	as3935_write(st, AS3935_CALIBRATE, 0x96);
 	as3935_write(st, AS3935_TUNE_CAP,
 		BIT(5) | (st->tune_cap / TUNE_CAP_DIV));
 
 	mdelay(2);
 	as3935_write(st, AS3935_TUNE_CAP, (st->tune_cap / TUNE_CAP_DIV));
+	as3935_write(st, AS3935_NFLWDTH, st->nflwdth_reg);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -370,6 +397,15 @@
 		return -EINVAL;
 	}
 
+	ret = of_property_read_u32(np,
+			"ams,nflwdth", &st->nflwdth_reg);
+	if (!ret && st->nflwdth_reg > AS3935_NFLWDTH_MASK) {
+		dev_err(&spi->dev,
+			"invalid nflwdth setting of %d\n",
+			st->nflwdth_reg);
+		return -EINVAL;
+	}
+
 	indio_dev->dev.parent = &spi->dev;
 	indio_dev->name = spi_get_device_id(spi)->name;
 	indio_dev->channels = as3935_channels;
@@ -384,6 +420,7 @@
 		return -ENOMEM;
 
 	st->trig = trig;
+	st->noise_tripped = jiffies - HZ;
 	trig->dev.parent = indio_dev->dev.parent;
 	iio_trigger_set_drvdata(trig, indio_dev);
 	trig->ops = &iio_interrupt_trigger_ops;
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/netlink.c b/drivers/infiniband/core/netlink.c
index b12e587..1fb72c3 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -175,13 +175,24 @@
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
+	/*
+	 * LS responses overload the 0x100 (NLM_F_ROOT) flag.  Don't
+	 * mistakenly call the .dump() function.
+	 */
+	if (index == RDMA_NL_LS) {
+		if (cb_table[op].doit)
+			return cb_table[op].doit(skb, nlh, extack);
+		return -EINVAL;
+	}
 	/* FIXME: Convert IWCM to properly handle doit callbacks */
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM ||
 	    index == RDMA_NL_IWCM) {
 		struct netlink_dump_control c = {
 			.dump = cb_table[op].dump,
 		};
-		return netlink_dump_start(nls, skb, nlh, &c);
+		if (c.dump)
+			return netlink_dump_start(nls, skb, nlh, &c);
+		return -EINVAL;
 	}
 
 	if (cb_table[op].doit)
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_netdevice_notifier(&bnxt_re_netdev_notifier);
 	if (bnxt_re_wq)
 		destroy_workqueue(bnxt_re_wq);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 391bb70..2bdb156 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -107,6 +107,9 @@
 		return -EINVAL;
 	}
 
+	if (test_bit(FIRMWARE_TIMED_OUT, &rcfw->flags))
+		return -ETIMEDOUT;
+
 	/* Cmdq are in 16-byte units, each request can consume 1 or more
 	 * cmdqe
 	 */
@@ -226,6 +229,7 @@
 		/* timed out */
 		dev_err(&rcfw->pdev->dev, "QPLIB: cmdq[%#x]=%#x timedout (%d)msec",
 			cookie, opcode, RCFW_CMD_WAIT_TIME_MS);
+		set_bit(FIRMWARE_TIMED_OUT, &rcfw->flags);
 		return rc;
 	}
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 0ed312f..85b16da 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -162,8 +162,9 @@
 	unsigned long		*cmdq_bitmap;
 	u32			bmap_size;
 	unsigned long		flags;
-#define FIRMWARE_INITIALIZED_FLAG	1
+#define FIRMWARE_INITIALIZED_FLAG	BIT(0)
 #define FIRMWARE_FIRST_FLAG		BIT(31)
+#define FIRMWARE_TIMED_OUT		BIT(3)
 	wait_queue_head_t	waitq;
 	int			(*aeq_handler)(struct bnxt_qplib_rcfw *,
 					       struct creq_func_event *);
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index ceaa2fa..daf7a56 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2333,9 +2333,14 @@
 	unsigned int stid = GET_TID(rpl);
 	struct c4iw_listen_ep *ep = get_ep_from_stid(dev, stid);
 
+	if (!ep) {
+		pr_debug("%s stid %d lookup failure!\n", __func__, stid);
+		goto out;
+	}
 	pr_debug("%s ep %p\n", __func__, ep);
 	c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
 	c4iw_put_ep(&ep->com);
+out:
 	return 0;
 }
 
@@ -2594,9 +2599,9 @@
 	c4iw_put_ep(&child_ep->com);
 reject:
 	reject_cr(dev, hwtid, skb);
+out:
 	if (parent_ep)
 		c4iw_put_ep(&parent_ep->com);
-out:
 	return 0;
 }
 
@@ -3457,7 +3462,7 @@
 		cm_id->provider_data = ep;
 		goto out;
 	}
-
+	remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
 			ep->com.local_addr.ss_family);
 fail2:
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index b2ed4b9..0be4278 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1066,6 +1066,8 @@
 static int thermal_init(struct hfi1_devdata *dd);
 
 static void update_statusp(struct hfi1_pportdata *ppd, u32 state);
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs);
 static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 				  int msecs);
 static void log_state_transition(struct hfi1_pportdata *ppd, u32 state);
@@ -8238,6 +8240,7 @@
 	u64 regs[CCE_NUM_INT_CSRS];
 	u32 bit;
 	int i;
+	irqreturn_t handled = IRQ_NONE;
 
 	this_cpu_inc(*dd->int_counter);
 
@@ -8258,9 +8261,10 @@
 	for_each_set_bit(bit, (unsigned long *)&regs[0],
 			 CCE_NUM_INT_CSRS * 64) {
 		is_interrupt(dd, bit);
+		handled = IRQ_HANDLED;
 	}
 
-	return IRQ_HANDLED;
+	return handled;
 }
 
 static irqreturn_t sdma_interrupt(int irq, void *data)
@@ -9413,7 +9417,7 @@
 	write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask);
 }
 
-void reset_qsfp(struct hfi1_pportdata *ppd)
+int reset_qsfp(struct hfi1_pportdata *ppd)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	u64 mask, qsfp_mask;
@@ -9443,6 +9447,13 @@
 	 * for alarms and warnings
 	 */
 	set_qsfp_int_n(ppd, 1);
+
+	/*
+	 * After the reset, AOC transmitters are enabled by default. They need
+	 * to be turned off to complete the QSFP setup before they can be
+	 * enabled again.
+	 */
+	return set_qsfp_tx(ppd, 0);
 }
 
 static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,
@@ -10305,6 +10316,7 @@
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	u32 previous_state;
+	int offline_state_ret;
 	int ret;
 
 	update_lcb_cache(dd);
@@ -10326,28 +10338,11 @@
 		ppd->offline_disabled_reason =
 		HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT);
 
-	/*
-	 * Wait for offline transition. It can take a while for
-	 * the link to go down.
-	 */
-	ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000);
-	if (ret < 0)
-		return ret;
+	offline_state_ret = wait_phys_link_offline_substates(ppd, 10000);
+	if (offline_state_ret < 0)
+		return offline_state_ret;
 
-	/*
-	 * Now in charge of LCB - must be after the physical state is
-	 * offline.quiet and before host_link_state is changed.
-	 */
-	set_host_lcb_access(dd);
-	write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
-
-	/* make sure the logical state is also down */
-	ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
-	if (ret)
-		force_logical_link_state_down(ppd);
-
-	ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
-
+	/* Disabling AOC transmitters */
 	if (ppd->port_type == PORT_TYPE_QSFP &&
 	    ppd->qsfp_info.limiting_active &&
 	    qsfp_mod_present(ppd)) {
@@ -10365,6 +10360,30 @@
 	}
 
 	/*
+	 * Wait for the offline.Quiet transition if it hasn't happened yet. It
+	 * can take a while for the link to go down.
+	 */
+	if (offline_state_ret != PLS_OFFLINE_QUIET) {
+		ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * Now in charge of LCB - must be after the physical state is
+	 * offline.quiet and before host_link_state is changed.
+	 */
+	set_host_lcb_access(dd);
+	write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
+
+	/* make sure the logical state is also down */
+	ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
+	if (ret)
+		force_logical_link_state_down(ppd);
+
+	ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
+
+	/*
 	 * The LNI has a mandatory wait time after the physical state
 	 * moves to Offline.Quiet.  The wait time may be different
 	 * depending on how the link went down.  The 8051 firmware
@@ -10396,6 +10415,9 @@
 			& (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) {
 		/* went down while attempting link up */
 		check_lni_states(ppd);
+
+		/* The QSFP doesn't need to be reset on LNI failure */
+		ppd->qsfp_info.reset_needed = 0;
 	}
 
 	/* the active link width (downgrade) is 0 on link down */
@@ -12804,6 +12826,39 @@
 	return 0;
 }
 
+/*
+ * wait_phys_link_offline_quiet_substates - wait for any offline substate
+ * @ppd: port device
+ * @msecs: the number of milliseconds to wait
+ *
+ * Wait up to msecs milliseconds for any offline physical link
+ * state change to occur.
+ * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT.
+ */
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs)
+{
+	u32 read_state;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(msecs);
+	while (1) {
+		read_state = read_physical_state(ppd->dd);
+		if ((read_state & 0xF0) == PLS_OFFLINE)
+			break;
+		if (time_after(jiffies, timeout)) {
+			dd_dev_err(ppd->dd,
+				   "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n",
+				   read_state, msecs);
+			return -ETIMEDOUT;
+		}
+		usleep_range(1950, 2050); /* sleep 2ms-ish */
+	}
+
+	log_state_transition(ppd, read_state);
+	return read_state;
+}
+
 #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
 (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)
 
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index b8345a6..50b8645 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -204,6 +204,7 @@
 #define PLS_OFFLINE_READY_TO_QUIET_LT	   0x92
 #define PLS_OFFLINE_REPORT_FAILURE		   0x93
 #define PLS_OFFLINE_READY_TO_QUIET_BCC	   0x94
+#define PLS_OFFLINE_QUIET_DURATION	   0x95
 #define PLS_POLLING				   0x20
 #define PLS_POLLING_QUIET			   0x20
 #define PLS_POLLING_ACTIVE			   0x21
@@ -722,7 +723,7 @@
 void handle_link_bounce(struct work_struct *work);
 void handle_start_link(struct work_struct *work);
 void handle_sma_message(struct work_struct *work);
-void reset_qsfp(struct hfi1_pportdata *ppd);
+int reset_qsfp(struct hfi1_pportdata *ppd);
 void qsfp_event(struct work_struct *work);
 void start_freeze_handling(struct hfi1_pportdata *ppd, int flags);
 int send_idle_sma(struct hfi1_devdata *dd, u64 message);
diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c
index d46b171..1613af1 100644
--- a/drivers/infiniband/hw/hfi1/eprom.c
+++ b/drivers/infiniband/hw/hfi1/eprom.c
@@ -204,7 +204,10 @@
 	return ret;
 }
 
-/* magic character sequence that trails an image */
+/* magic character sequence that begins an image */
+#define IMAGE_START_MAGIC "APO="
+
+/* magic character sequence that might trail an image */
 #define IMAGE_TRAIL_MAGIC "egamiAPO"
 
 /* EPROM file types */
@@ -250,6 +253,7 @@
 {
 	void *buffer;
 	void *p;
+	u32 length;
 	int ret;
 
 	buffer = kmalloc(P1_SIZE, GFP_KERNEL);
@@ -262,15 +266,21 @@
 		return ret;
 	}
 
-	/* scan for image magic that may trail the actual data */
-	p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
-	if (!p) {
+	/* config partition is valid only if it starts with IMAGE_START_MAGIC */
+	if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) {
 		kfree(buffer);
 		return -ENOENT;
 	}
 
+	/* scan for image magic that may trail the actual data */
+	p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
+	if (p)
+		length = p - buffer;
+	else
+		length = P1_SIZE;
+
 	*data = buffer;
-	*size = p - buffer;
+	*size = length;
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 2bc8926..d9a1e98 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -930,15 +930,8 @@
 	switch (ret) {
 	case 0:
 		ret = setup_base_ctxt(fd, uctxt);
-		if (uctxt->subctxt_cnt) {
-			/*
-			 * Base context is done (successfully or not), notify
-			 * anybody using a sub-context that is waiting for
-			 * this completion.
-			 */
-			clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
-			wake_up(&uctxt->wait);
-		}
+		if (ret)
+			deallocate_ctxt(uctxt);
 		break;
 	case 1:
 		ret = complete_subctxt(fd);
@@ -1305,25 +1298,25 @@
 	/* Now allocate the RcvHdr queue and eager buffers. */
 	ret = hfi1_create_rcvhdrq(dd, uctxt);
 	if (ret)
-		return ret;
+		goto done;
 
 	ret = hfi1_setup_eagerbufs(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	/* If sub-contexts are enabled, do the appropriate setup */
 	if (uctxt->subctxt_cnt)
 		ret = setup_subctxt(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	ret = hfi1_alloc_ctxt_rcv_groups(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	ret = init_user_ctxt(fd, uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	user_init(uctxt);
 
@@ -1331,12 +1324,22 @@
 	fd->uctxt = uctxt;
 	hfi1_rcd_get(uctxt);
 
-	return 0;
+done:
+	if (uctxt->subctxt_cnt) {
+		/*
+		 * On error, set the failed bit so sub-contexts will clean up
+		 * correctly.
+		 */
+		if (ret)
+			set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
 
-setup_failed:
-	/* Set the failed bit so sub-context init can do the right thing */
-	set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
-	deallocate_ctxt(uctxt);
+		/*
+		 * Base context is done (successfully or not), notify anybody
+		 * using a sub-context that is waiting for this completion.
+		 */
+		clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
+		wake_up(&uctxt->wait);
+	}
 
 	return ret;
 }
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 82447b7..09e50fd 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -68,7 +68,7 @@
 /*
  * Code to adjust PCIe capabilities.
  */
-static int tune_pcie_caps(struct hfi1_devdata *);
+static void tune_pcie_caps(struct hfi1_devdata *);
 
 /*
  * Do all the common PCIe setup and initialization.
@@ -351,7 +351,7 @@
  */
 int request_msix(struct hfi1_devdata *dd, u32 msireq)
 {
-	int nvec, ret;
+	int nvec;
 
 	nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq,
 				     PCI_IRQ_MSIX | PCI_IRQ_LEGACY);
@@ -360,12 +360,7 @@
 		return nvec;
 	}
 
-	ret = tune_pcie_caps(dd);
-	if (ret) {
-		dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret);
-		pci_free_irq_vectors(dd->pcidev);
-		return ret;
-	}
+	tune_pcie_caps(dd);
 
 	/* check for legacy IRQ */
 	if (nvec == 1 && !dd->pcidev->msix_enabled)
@@ -502,7 +497,7 @@
 module_param_named(aspm, aspm_mode, uint, S_IRUGO);
 MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic");
 
-static int tune_pcie_caps(struct hfi1_devdata *dd)
+static void tune_pcie_caps(struct hfi1_devdata *dd)
 {
 	struct pci_dev *parent;
 	u16 rc_mpss, rc_mps, ep_mpss, ep_mps;
@@ -513,22 +508,14 @@
 	 * Turn on extended tags in DevCtl in case the BIOS has turned it off
 	 * to improve WFR SDMA bandwidth
 	 */
-	ret = pcie_capability_read_word(dd->pcidev,
-					PCI_EXP_DEVCTL, &ectl);
-	if (ret) {
-		dd_dev_err(dd, "Unable to read from PCI config\n");
-		return ret;
-	}
-
-	if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl);
+	if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
 		dd_dev_info(dd, "Enabling PCIe extended tags\n");
 		ectl |= PCI_EXP_DEVCTL_EXT_TAG;
 		ret = pcie_capability_write_word(dd->pcidev,
 						 PCI_EXP_DEVCTL, ectl);
-		if (ret) {
-			dd_dev_err(dd, "Unable to write to PCI config\n");
-			return ret;
-		}
+		if (ret)
+			dd_dev_info(dd, "Unable to write to PCI config\n");
 	}
 	/* Find out supported and configured values for parent (root) */
 	parent = dd->pcidev->bus->self;
@@ -536,15 +523,22 @@
 	 * The driver cannot perform the tuning if it does not have
 	 * access to the upstream component.
 	 */
-	if (!parent)
-		return -EINVAL;
+	if (!parent) {
+		dd_dev_info(dd, "Parent not found\n");
+		return;
+	}
 	if (!pci_is_root_bus(parent->bus)) {
 		dd_dev_info(dd, "Parent not root\n");
-		return -EINVAL;
+		return;
 	}
-
-	if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
-		return -EINVAL;
+	if (!pci_is_pcie(parent)) {
+		dd_dev_info(dd, "Parent is not PCI Express capable\n");
+		return;
+	}
+	if (!pci_is_pcie(dd->pcidev)) {
+		dd_dev_info(dd, "PCI device is not PCI Express capable\n");
+		return;
+	}
 	rc_mpss = parent->pcie_mpss;
 	rc_mps = ffs(pcie_get_mps(parent)) - 8;
 	/* Find out supported and configured values for endpoint (us) */
@@ -590,8 +584,6 @@
 		ep_mrrs = max_mrrs;
 		pcie_set_readrq(dd->pcidev, ep_mrrs);
 	}
-
-	return 0;
 }
 
 /* End of PCIe capability tuning */
diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index a8af96d..d486355 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -790,7 +790,9 @@
 	 * reuse of stale settings established in our previous pass through.
 	 */
 	if (ppd->qsfp_info.reset_needed) {
-		reset_qsfp(ppd);
+		ret = reset_qsfp(ppd);
+		if (ret)
+			return ret;
 		refresh_qsfp_cache(ppd, &ppd->qsfp_info);
 	} else {
 		ppd->qsfp_info.reset_needed = 1;
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index 9b15664..a65e4cbd 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -201,7 +201,6 @@
 	CEQ_CREATED,
 	ILQ_CREATED,
 	IEQ_CREATED,
-	INET_NOTIFIER,
 	IP_ADDR_REGISTERED,
 	RDMA_DEV_REGISTERED
 };
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 14f36ba..5230dd3 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -1504,23 +1504,40 @@
 }
 
 /**
- * listen_port_in_use - determine if port is in use
- * @port: Listen port number
+ * i40iw_port_in_use - determine if port is in use
+ * @port: port number
+ * @active_side: flag for listener side vs active side
  */
-static bool i40iw_listen_port_in_use(struct i40iw_cm_core *cm_core, u16 port)
+static bool i40iw_port_in_use(struct i40iw_cm_core *cm_core, u16 port, bool active_side)
 {
 	struct i40iw_cm_listener *listen_node;
+	struct i40iw_cm_node *cm_node;
 	unsigned long flags;
 	bool ret = false;
 
-	spin_lock_irqsave(&cm_core->listen_list_lock, flags);
-	list_for_each_entry(listen_node, &cm_core->listen_nodes, list) {
-		if (listen_node->loc_port == port) {
-			ret = true;
-			break;
+	if (active_side) {
+		/* search connected node list */
+		spin_lock_irqsave(&cm_core->ht_lock, flags);
+		list_for_each_entry(cm_node, &cm_core->connected_nodes, list) {
+			if (cm_node->loc_port == port) {
+				ret = true;
+				break;
+			}
 		}
+			if (!ret)
+				clear_bit(port, cm_core->active_side_ports);
+		spin_unlock_irqrestore(&cm_core->ht_lock, flags);
+	} else {
+		spin_lock_irqsave(&cm_core->listen_list_lock, flags);
+		list_for_each_entry(listen_node, &cm_core->listen_nodes, list) {
+			if (listen_node->loc_port == port) {
+				ret = true;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
 	}
-	spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
+
 	return ret;
 }
 
@@ -1868,7 +1885,7 @@
 		spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
 
 		if (listener->iwdev) {
-			if (apbvt_del && !i40iw_listen_port_in_use(cm_core, listener->loc_port))
+			if (apbvt_del && !i40iw_port_in_use(cm_core, listener->loc_port, false))
 				i40iw_manage_apbvt(listener->iwdev,
 						   listener->loc_port,
 						   I40IW_MANAGE_APBVT_DEL);
@@ -2247,21 +2264,21 @@
 	if (cm_node->listener) {
 		i40iw_dec_refcnt_listen(cm_core, cm_node->listener, 0, true);
 	} else {
-		if (!i40iw_listen_port_in_use(cm_core, cm_node->loc_port) &&
-		    cm_node->apbvt_set) {
+		if (!i40iw_port_in_use(cm_core, cm_node->loc_port, true) && cm_node->apbvt_set) {
 			i40iw_manage_apbvt(cm_node->iwdev,
 					   cm_node->loc_port,
 					   I40IW_MANAGE_APBVT_DEL);
-			i40iw_get_addr_info(cm_node, &nfo);
-			if (cm_node->qhash_set) {
-				i40iw_manage_qhash(cm_node->iwdev,
-						   &nfo,
-						   I40IW_QHASH_TYPE_TCP_ESTABLISHED,
-						   I40IW_QHASH_MANAGE_TYPE_DELETE,
-						   NULL,
-						   false);
-				cm_node->qhash_set = 0;
-			}
+			cm_node->apbvt_set = 0;
+		}
+		i40iw_get_addr_info(cm_node, &nfo);
+		if (cm_node->qhash_set) {
+			i40iw_manage_qhash(cm_node->iwdev,
+					   &nfo,
+					   I40IW_QHASH_TYPE_TCP_ESTABLISHED,
+					   I40IW_QHASH_MANAGE_TYPE_DELETE,
+					   NULL,
+					   false);
+			cm_node->qhash_set = 0;
 		}
 	}
 
@@ -3255,7 +3272,8 @@
 	tcp_info->snd_mss = cpu_to_le32(((u32)cm_node->tcp_cntxt.mss));
 	if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
 		tcp_info->insert_vlan_tag = true;
-		tcp_info->vlan_tag = cpu_to_le16(cm_node->vlan_id);
+		tcp_info->vlan_tag = cpu_to_le16(((u16)cm_node->user_pri << I40IW_VLAN_PRIO_SHIFT) |
+						  cm_node->vlan_id);
 	}
 	if (cm_node->ipv4) {
 		tcp_info->src_port = cpu_to_le16(cm_node->loc_port);
@@ -3737,10 +3755,8 @@
 	struct sockaddr_in *raddr;
 	struct sockaddr_in6 *laddr6;
 	struct sockaddr_in6 *raddr6;
-	bool qhash_set = false;
-	int apbvt_set = 0;
-	int err = 0;
-	enum i40iw_status_code status;
+	int ret = 0;
+	unsigned long flags;
 
 	ibqp = i40iw_get_qp(cm_id->device, conn_param->qpn);
 	if (!ibqp)
@@ -3789,32 +3805,6 @@
 	cm_info.user_pri = rt_tos2priority(cm_id->tos);
 	i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_DCB, "%s TOS:[%d] UP:[%d]\n",
 		    __func__, cm_id->tos, cm_info.user_pri);
-	if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) ||
-	    (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32,
-				     raddr6->sin6_addr.in6_u.u6_addr32,
-				     sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) {
-		status = i40iw_manage_qhash(iwdev,
-					    &cm_info,
-					    I40IW_QHASH_TYPE_TCP_ESTABLISHED,
-					    I40IW_QHASH_MANAGE_TYPE_ADD,
-					    NULL,
-					    true);
-		if (status)
-			return -EINVAL;
-		qhash_set = true;
-	}
-	status = i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD);
-	if (status) {
-		i40iw_manage_qhash(iwdev,
-				   &cm_info,
-				   I40IW_QHASH_TYPE_TCP_ESTABLISHED,
-				   I40IW_QHASH_MANAGE_TYPE_DELETE,
-				   NULL,
-				   false);
-		return -EINVAL;
-	}
-
-	apbvt_set = 1;
 	cm_id->add_ref(cm_id);
 	cm_node = i40iw_create_cm_node(&iwdev->cm_core, iwdev,
 				       conn_param->private_data_len,
@@ -3822,17 +3812,40 @@
 				       &cm_info);
 
 	if (IS_ERR(cm_node)) {
-		err = PTR_ERR(cm_node);
-		goto err_out;
+		ret = PTR_ERR(cm_node);
+		cm_id->rem_ref(cm_id);
+		return ret;
 	}
 
+	if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) ||
+	    (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32,
+				     raddr6->sin6_addr.in6_u.u6_addr32,
+				     sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) {
+		if (i40iw_manage_qhash(iwdev, &cm_info, I40IW_QHASH_TYPE_TCP_ESTABLISHED,
+				       I40IW_QHASH_MANAGE_TYPE_ADD, NULL, true)) {
+			ret = -EINVAL;
+			goto err;
+		}
+		cm_node->qhash_set = true;
+	}
+
+	spin_lock_irqsave(&iwdev->cm_core.ht_lock, flags);
+	if (!test_and_set_bit(cm_info.loc_port, iwdev->cm_core.active_side_ports)) {
+		spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags);
+		if (i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD)) {
+			ret =  -EINVAL;
+			goto err;
+		}
+	} else {
+		spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags);
+	}
+
+	cm_node->apbvt_set = true;
 	i40iw_record_ird_ord(cm_node, (u16)conn_param->ird, (u16)conn_param->ord);
 	if (cm_node->send_rdma0_op == SEND_RDMA_READ_ZERO &&
 	    !cm_node->ord_size)
 		cm_node->ord_size = 1;
 
-	cm_node->apbvt_set = apbvt_set;
-	cm_node->qhash_set = qhash_set;
 	iwqp->cm_node = cm_node;
 	cm_node->iwqp = iwqp;
 	iwqp->cm_id = cm_id;
@@ -3840,11 +3853,9 @@
 
 	if (cm_node->state != I40IW_CM_STATE_OFFLOADED) {
 		cm_node->state = I40IW_CM_STATE_SYN_SENT;
-		err = i40iw_send_syn(cm_node, 0);
-		if (err) {
-			i40iw_rem_ref_cm_node(cm_node);
-			goto err_out;
-		}
+		ret = i40iw_send_syn(cm_node, 0);
+		if (ret)
+			goto err;
 	}
 
 	i40iw_debug(cm_node->dev,
@@ -3853,9 +3864,10 @@
 		    cm_node->rem_port,
 		    cm_node,
 		    cm_node->cm_id);
+
 	return 0;
 
-err_out:
+err:
 	if (cm_info.ipv4)
 		i40iw_debug(&iwdev->sc_dev,
 			    I40IW_DEBUG_CM,
@@ -3867,22 +3879,10 @@
 			    "Api - connect() FAILED: dest addr=%pI6",
 			    cm_info.rem_addr);
 
-	if (qhash_set)
-		i40iw_manage_qhash(iwdev,
-				   &cm_info,
-				   I40IW_QHASH_TYPE_TCP_ESTABLISHED,
-				   I40IW_QHASH_MANAGE_TYPE_DELETE,
-				   NULL,
-				   false);
-
-	if (apbvt_set && !i40iw_listen_port_in_use(&iwdev->cm_core,
-						   cm_info.loc_port))
-		i40iw_manage_apbvt(iwdev,
-				   cm_info.loc_port,
-				   I40IW_MANAGE_APBVT_DEL);
+	i40iw_rem_ref_cm_node(cm_node);
 	cm_id->rem_ref(cm_id);
 	iwdev->cm_core.stats_connect_errs++;
-	return err;
+	return ret;
 }
 
 /**
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.h b/drivers/infiniband/hw/i40iw/i40iw_cm.h
index 2e52e38..45abef7 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.h
@@ -71,6 +71,9 @@
 #define	I40IW_HW_IRD_SETTING_32	32
 #define	I40IW_HW_IRD_SETTING_64	64
 
+#define MAX_PORTS		65536
+#define I40IW_VLAN_PRIO_SHIFT   13
+
 enum ietf_mpa_flags {
 	IETF_MPA_FLAGS_MARKERS = 0x80,	/* receive Markers */
 	IETF_MPA_FLAGS_CRC = 0x40,	/* receive Markers */
@@ -411,6 +414,8 @@
 	spinlock_t ht_lock; /* manage hash table */
 	spinlock_t listen_list_lock; /* listen list */
 
+	unsigned long active_side_ports[BITS_TO_LONGS(MAX_PORTS)];
+
 	u64	stats_nodes_created;
 	u64	stats_nodes_destroyed;
 	u64	stats_listen_created;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index d1f5345..42ca534 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -48,7 +48,7 @@
  * @wqe: cqp wqe for header
  * @header: header for the cqp wqe
  */
-static inline void i40iw_insert_wqe_hdr(u64 *wqe, u64 header)
+void i40iw_insert_wqe_hdr(u64 *wqe, u64 header)
 {
 	wmb();            /* make sure WQE is populated before polarity is set */
 	set_64bit_val(wqe, 24, header);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index cc742c3..27590ae 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -99,8 +99,6 @@
 	.notifier_call = i40iw_net_event
 };
 
-static atomic_t i40iw_notifiers_registered;
-
 /**
  * i40iw_find_i40e_handler - find a handler given a client info
  * @ldev: pointer to a client info
@@ -1376,11 +1374,20 @@
  */
 static void i40iw_register_notifiers(void)
 {
-	if (atomic_inc_return(&i40iw_notifiers_registered) == 1) {
-		register_inetaddr_notifier(&i40iw_inetaddr_notifier);
-		register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
-		register_netevent_notifier(&i40iw_net_notifier);
-	}
+	register_inetaddr_notifier(&i40iw_inetaddr_notifier);
+	register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
+	register_netevent_notifier(&i40iw_net_notifier);
+}
+
+/**
+ * i40iw_unregister_notifiers - unregister tcp ip notifiers
+ */
+
+static void i40iw_unregister_notifiers(void)
+{
+	unregister_netevent_notifier(&i40iw_net_notifier);
+	unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
+	unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);
 }
 
 /**
@@ -1400,6 +1407,11 @@
 	u32 i;
 	u32 size;
 
+	if (!ldev->msix_count) {
+		i40iw_pr_err("No MSI-X vectors\n");
+		return I40IW_ERR_CONFIG;
+	}
+
 	iwdev->msix_count = ldev->msix_count;
 
 	size = sizeof(struct i40iw_msix_vector) * iwdev->msix_count;
@@ -1462,12 +1474,6 @@
 		if (!iwdev->reset)
 			i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx);
 		/* fallthrough */
-	case INET_NOTIFIER:
-		if (!atomic_dec_return(&i40iw_notifiers_registered)) {
-			unregister_netevent_notifier(&i40iw_net_notifier);
-			unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
-			unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);
-		}
 		/* fallthrough */
 	case PBLE_CHUNK_MEM:
 		i40iw_destroy_pble_pool(dev, iwdev->pble_rsrc);
@@ -1550,7 +1556,7 @@
 
 	status = i40iw_save_msix_info(iwdev, ldev);
 	if (status)
-		goto exit;
+		return status;
 	iwdev->hw.dev_context = (void *)ldev->pcidev;
 	iwdev->hw.hw_addr = ldev->hw_addr;
 	status = i40iw_allocate_dma_mem(&iwdev->hw,
@@ -1667,8 +1673,6 @@
 			break;
 		iwdev->init_state = PBLE_CHUNK_MEM;
 		iwdev->virtchnl_wq = alloc_ordered_workqueue("iwvch", WQ_MEM_RECLAIM);
-		i40iw_register_notifiers();
-		iwdev->init_state = INET_NOTIFIER;
 		status = i40iw_add_mac_ip(iwdev);
 		if (status)
 			break;
@@ -2018,6 +2022,8 @@
 	i40iw_client.type = I40E_CLIENT_IWARP;
 	spin_lock_init(&i40iw_handler_lock);
 	ret = i40e_register_client(&i40iw_client);
+	i40iw_register_notifiers();
+
 	return ret;
 }
 
@@ -2029,6 +2035,7 @@
  */
 static void __exit i40iw_exit_module(void)
 {
+	i40iw_unregister_notifiers();
 	i40e_unregister_client(&i40iw_client);
 }
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_p.h b/drivers/infiniband/hw/i40iw/i40iw_p.h
index e217a12..5498ad0 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_p.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_p.h
@@ -59,6 +59,8 @@
 						 struct i40iw_fast_reg_stag_info *info,
 						 bool post_sq);
 
+void i40iw_insert_wqe_hdr(u64 *wqe, u64 header);
+
 /* HMC/FPM functions */
 enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev,
 					    u8 hmc_fn_id);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c
index c2cab20..59f7067 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_puda.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c
@@ -123,12 +123,11 @@
 		get_64bit_val(wqe, 24, &offset24);
 
 	offset24 = (offset24) ? 0 : LS_64(1, I40IWQPSQ_VALID);
-	set_64bit_val(wqe, 24, offset24);
 
 	set_64bit_val(wqe, 0, buf->mem.pa);
 	set_64bit_val(wqe, 8,
 		      LS_64(buf->mem.size, I40IWQPSQ_FRAG_LEN));
-	set_64bit_val(wqe, 24, offset24);
+	i40iw_insert_wqe_hdr(wqe, offset24);
 }
 
 /**
@@ -409,9 +408,7 @@
 	set_64bit_val(wqe, 8, LS_64(info->len, I40IWQPSQ_FRAG_LEN));
 	set_64bit_val(wqe, 16, header[0]);
 
-	/* Ensure all data is written before writing valid bit */
-	wmb();
-	set_64bit_val(wqe, 24, header[1]);
+	i40iw_insert_wqe_hdr(wqe, header[1]);
 
 	i40iw_debug_buf(qp->dev, I40IW_DEBUG_PUDA, "PUDA SEND WQE", wqe, 32);
 	i40iw_qp_post_wr(&qp->qp_uk);
@@ -539,7 +536,7 @@
 		 LS_64(2, I40IW_CQPSQ_QP_NEXTIWSTATE) |
 		 LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID);
 
-	set_64bit_val(wqe, 24, header);
+	i40iw_insert_wqe_hdr(wqe, header);
 
 	i40iw_debug_buf(cqp->dev, I40IW_DEBUG_PUDA, "PUDA CQE", wqe, 32);
 	i40iw_sc_cqp_post_sq(cqp);
@@ -655,7 +652,7 @@
 	    LS_64(1, I40IW_CQPSQ_CQ_ENCEQEMASK) |
 	    LS_64(1, I40IW_CQPSQ_CQ_CEQIDVALID) |
 	    LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID);
-	set_64bit_val(wqe, 24, header);
+	i40iw_insert_wqe_hdr(wqe, header);
 
 	i40iw_debug_buf(dev, I40IW_DEBUG_PUDA, "PUDA CQE",
 			wqe, I40IW_CQP_WQE_SIZE * 8);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index 62f1f45..e52dbbb 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -160,7 +160,7 @@
 		return NOTIFY_DONE;
 
 	iwdev = &hdl->device;
-	if (iwdev->init_state < INET_NOTIFIER)
+	if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
 		return NOTIFY_DONE;
 
 	netdev = iwdev->ldev->netdev;
@@ -217,7 +217,7 @@
 		return NOTIFY_DONE;
 
 	iwdev = &hdl->device;
-	if (iwdev->init_state < INET_NOTIFIER)
+	if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
 		return NOTIFY_DONE;
 
 	netdev = iwdev->ldev->netdev;
@@ -266,7 +266,7 @@
 		if (!iwhdl)
 			return NOTIFY_DONE;
 		iwdev = &iwhdl->device;
-		if (iwdev->init_state < INET_NOTIFIER)
+		if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
 			return NOTIFY_DONE;
 		p = (__be32 *)neigh->primary_key;
 		i40iw_copy_ip_ntohl(local_ipaddr, p);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 1aa4110..62be0a4 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -826,12 +826,14 @@
 	attr->cap.max_inline_data = I40IW_MAX_INLINE_DATA_SIZE;
 	attr->cap.max_send_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
 	attr->cap.max_recv_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
+	attr->port_num = 1;
 	init_attr->event_handler = iwqp->ibqp.event_handler;
 	init_attr->qp_context = iwqp->ibqp.qp_context;
 	init_attr->send_cq = iwqp->ibqp.send_cq;
 	init_attr->recv_cq = iwqp->ibqp.recv_cq;
 	init_attr->srq = iwqp->ibqp.srq;
 	init_attr->cap = attr->cap;
+	init_attr->port_num = 1;
 	return 0;
 }
 
@@ -1027,7 +1029,19 @@
 				iwqp->hw_tcp_state = I40IW_TCP_STATE_CLOSED;
 				iwqp->last_aeq = I40IW_AE_RESET_SENT;
 				spin_unlock_irqrestore(&iwqp->lock, flags);
+				i40iw_cm_disconn(iwqp);
 			}
+		} else {
+			spin_lock_irqsave(&iwqp->lock, flags);
+			if (iwqp->cm_id) {
+				if (atomic_inc_return(&iwqp->close_timer_started) == 1) {
+					iwqp->cm_id->add_ref(iwqp->cm_id);
+					i40iw_schedule_cm_timer(iwqp->cm_node,
+								(struct i40iw_puda_buf *)iwqp,
+								 I40IW_TIMER_TYPE_CLOSE, 1, 0);
+				}
+			}
+			spin_unlock_irqrestore(&iwqp->lock, flags);
 		}
 	}
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index ab3c562..552f7bd 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -778,13 +778,13 @@
 	}
 
 	if (MLX5_CAP_GEN(mdev, tag_matching)) {
-		props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
-		props->xrq_caps.max_num_tags =
+		props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
+		props->tm_caps.max_num_tags =
 			(1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1;
-		props->xrq_caps.flags = IB_TM_CAP_RC;
-		props->xrq_caps.max_ops =
+		props->tm_caps.flags = IB_TM_CAP_RC;
+		props->tm_caps.max_ops =
 			1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
-		props->xrq_caps.max_sge = MLX5_TM_MAX_SGE;
+		props->tm_caps.max_sge = MLX5_TM_MAX_SGE;
 	}
 
 	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
@@ -3837,11 +3837,13 @@
 	if (!dbg)
 		return -ENOMEM;
 
+	dev->delay_drop.dbg = dbg;
+
 	dbg->dir_debugfs =
 		debugfs_create_dir("delay_drop",
 				   dev->mdev->priv.dbg_root);
 	if (!dbg->dir_debugfs)
-		return -ENOMEM;
+		goto out_debugfs;
 
 	dbg->events_cnt_debugfs =
 		debugfs_create_atomic_t("num_timeout_events", 0400,
@@ -3865,8 +3867,6 @@
 	if (!dbg->timeout_debugfs)
 		goto out_debugfs;
 
-	dev->delay_drop.dbg = dbg;
-
 	return 0;
 
 out_debugfs:
@@ -4174,9 +4174,9 @@
 err_uar_page:
 	mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar);
 
-err_cnt:
-	mlx5_ib_cleanup_cong_debugfs(dev);
 err_cong:
+	mlx5_ib_cleanup_cong_debugfs(dev);
+err_cnt:
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
 		mlx5_ib_dealloc_counters(dev);
 
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 914f212..f3dbd75 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -50,13 +50,9 @@
 {
 	unsigned long tmp;
 	unsigned long m;
-	int i, k;
-	u64 base = 0;
-	int p = 0;
-	int skip;
-	int mask;
-	u64 len;
-	u64 pfn;
+	u64 base = ~0, p = 0;
+	u64 len, pfn;
+	int i = 0;
 	struct scatterlist *sg;
 	int entry;
 	unsigned long page_shift = umem->page_shift;
@@ -76,33 +72,24 @@
 	m = find_first_bit(&tmp, BITS_PER_LONG);
 	if (max_page_shift)
 		m = min_t(unsigned long, max_page_shift - page_shift, m);
-	skip = 1 << m;
-	mask = skip - 1;
-	i = 0;
+
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
 		len = sg_dma_len(sg) >> page_shift;
 		pfn = sg_dma_address(sg) >> page_shift;
-		for (k = 0; k < len; k++) {
-			if (!(i & mask)) {
-				tmp = (unsigned long)pfn;
-				m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG));
-				skip = 1 << m;
-				mask = skip - 1;
-				base = pfn;
-				p = 0;
-			} else {
-				if (base + p != pfn) {
-					tmp = (unsigned long)p;
-					m = find_first_bit(&tmp, BITS_PER_LONG);
-					skip = 1 << m;
-					mask = skip - 1;
-					base = pfn;
-					p = 0;
-				}
-			}
-			p++;
-			i++;
+		if (base + p != pfn) {
+			/* If either the offset or the new
+			 * base are unaligned update m
+			 */
+			tmp = (unsigned long)(pfn | p);
+			if (!IS_ALIGNED(tmp, 1 << m))
+				m = find_first_bit(&tmp, BITS_PER_LONG);
+
+			base = pfn;
+			p = 0;
 		}
+
+		p += len;
+		i += len;
 	}
 
 	if (i) {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 0e2789d..37bbc54 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -47,7 +47,8 @@
 
 #define MLX5_UMR_ALIGN 2048
 
-static int clean_mr(struct mlx5_ib_mr *mr);
+static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
+static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 static int mr_cache_max_order(struct mlx5_ib_dev *dev);
 static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 
@@ -1270,8 +1271,9 @@
 
 		err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift,
 					 update_xlt_flags);
+
 		if (err) {
-			mlx5_ib_dereg_mr(&mr->ibmr);
+			dereg_mr(dev, mr);
 			return ERR_PTR(err);
 		}
 	}
@@ -1356,7 +1358,7 @@
 		err = mr_umem_get(pd, addr, len, access_flags, &mr->umem,
 				  &npages, &page_shift, &ncont, &order);
 		if (err < 0) {
-			clean_mr(mr);
+			clean_mr(dev, mr);
 			return err;
 		}
 	}
@@ -1410,7 +1412,7 @@
 		if (err) {
 			mlx5_ib_warn(dev, "Failed to rereg UMR\n");
 			ib_umem_release(mr->umem);
-			clean_mr(mr);
+			clean_mr(dev, mr);
 			return err;
 		}
 	}
@@ -1469,9 +1471,8 @@
 	}
 }
 
-static int clean_mr(struct mlx5_ib_mr *mr)
+static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
-	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
 	int allocated_from_cache = mr->allocated_from_cache;
 	int err;
 
@@ -1507,10 +1508,8 @@
 	return 0;
 }
 
-int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
-	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
-	struct mlx5_ib_mr *mr = to_mmr(ibmr);
 	int npages = mr->npages;
 	struct ib_umem *umem = mr->umem;
 
@@ -1539,7 +1538,7 @@
 	}
 #endif
 
-	clean_mr(mr);
+	clean_mr(dev, mr);
 
 	if (umem) {
 		ib_umem_release(umem);
@@ -1549,6 +1548,14 @@
 	return 0;
 }
 
+int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+
+	return dereg_mr(dev, mr);
+}
+
 struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 			       enum ib_mr_type mr_type,
 			       u32 max_num_sg)
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index f0dc5f4..442b9bd 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -3232,7 +3232,7 @@
 					    mr->ibmr.iova);
 			set_wqe_32bit_value(wqe->wqe_words,
 					    NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX,
-					    mr->ibmr.length);
+					    lower_32_bits(mr->ibmr.length));
 			set_wqe_32bit_value(wqe->wqe_words,
 					    NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0);
 			set_wqe_32bit_value(wqe->wqe_words,
@@ -3274,7 +3274,7 @@
 					    mr->npages * 8);
 
 			nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, "
-				  "length: %d, rkey: %0x, pgl_paddr: %llx, "
+				  "length: %lld, rkey: %0x, pgl_paddr: %llx, "
 				  "page_list_len: %u, wqe_misc: %x\n",
 				  (unsigned long long) mr->ibmr.iova,
 				  mr->ibmr.length,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index dcb5942..65b166c 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -252,7 +252,10 @@
 		case OCRDMA_MBX_ADDI_STATUS_INSUFFICIENT_RESOURCES:
 			err_num = -EAGAIN;
 			break;
+		default:
+			err_num = -EFAULT;
 		}
+		break;
 	default:
 		err_num = -EFAULT;
 	}
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index b2bb42e..254083b 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -387,7 +387,7 @@
 		u8 wqe_size;
 
 		u8 smac[ETH_ALEN];
-		u16 vlan_id;
+		u16 vlan;
 		int rc;
 	} *rqe_wr_id;
 
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index 4689e80..ad89653 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -105,7 +105,7 @@
 
 	qp->rqe_wr_id[qp->rq.gsi_cons].rc = data->u.data_length_error ?
 		-EINVAL : 0;
-	qp->rqe_wr_id[qp->rq.gsi_cons].vlan_id = data->vlan;
+	qp->rqe_wr_id[qp->rq.gsi_cons].vlan = data->vlan;
 	/* note: length stands for data length i.e. GRH is excluded */
 	qp->rqe_wr_id[qp->rq.gsi_cons].sg_list[0].length =
 		data->length.data_length;
@@ -694,6 +694,7 @@
 	struct qedr_cq *cq = get_qedr_cq(ibcq);
 	struct qedr_qp *qp = dev->gsi_qp;
 	unsigned long flags;
+	u16 vlan_id;
 	int i = 0;
 
 	spin_lock_irqsave(&cq->cq_lock, flags);
@@ -712,9 +713,14 @@
 		wc[i].wc_flags |= IB_WC_GRH | IB_WC_IP_CSUM_OK;
 		ether_addr_copy(wc[i].smac, qp->rqe_wr_id[qp->rq.cons].smac);
 		wc[i].wc_flags |= IB_WC_WITH_SMAC;
-		if (qp->rqe_wr_id[qp->rq.cons].vlan_id) {
+
+		vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan &
+			  VLAN_VID_MASK;
+		if (vlan_id) {
 			wc[i].wc_flags |= IB_WC_WITH_VLAN;
-			wc[i].vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan_id;
+			wc[i].vlan_id = vlan_id;
+			wc[i].sl = (qp->rqe_wr_id[qp->rq.cons].vlan &
+				    VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 		}
 
 		qedr_inc_sw_cons(&qp->rq);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 663a0c3..984aa34 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -416,9 +416,34 @@
 	return (enum ib_wc_status)status;
 }
 
-static inline int pvrdma_wc_opcode_to_ib(int opcode)
+static inline int pvrdma_wc_opcode_to_ib(unsigned int opcode)
 {
-	return opcode;
+	switch (opcode) {
+	case PVRDMA_WC_SEND:
+		return IB_WC_SEND;
+	case PVRDMA_WC_RDMA_WRITE:
+		return IB_WC_RDMA_WRITE;
+	case PVRDMA_WC_RDMA_READ:
+		return IB_WC_RDMA_READ;
+	case PVRDMA_WC_COMP_SWAP:
+		return IB_WC_COMP_SWAP;
+	case PVRDMA_WC_FETCH_ADD:
+		return IB_WC_FETCH_ADD;
+	case PVRDMA_WC_LOCAL_INV:
+		return IB_WC_LOCAL_INV;
+	case PVRDMA_WC_FAST_REG_MR:
+		return IB_WC_REG_MR;
+	case PVRDMA_WC_MASKED_COMP_SWAP:
+		return IB_WC_MASKED_COMP_SWAP;
+	case PVRDMA_WC_MASKED_FETCH_ADD:
+		return IB_WC_MASKED_FETCH_ADD;
+	case PVRDMA_WC_RECV:
+		return IB_WC_RECV;
+	case PVRDMA_WC_RECV_RDMA_WITH_IMM:
+		return IB_WC_RECV_RDMA_WITH_IMM;
+	default:
+		return IB_WC_SEND;
+	}
 }
 
 static inline int pvrdma_wc_flags_to_ib(int flags)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 14b62f7..7774654 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -823,12 +823,18 @@
 	    wc->status != IB_WC_WR_FLUSH_ERR) {
 		struct ipoib_neigh *neigh;
 
-		if (wc->status != IB_WC_RNR_RETRY_EXC_ERR)
-			ipoib_warn(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
-				   wc->status, wr_id, wc->vendor_err);
+		/* IB_WC[_RNR]_RETRY_EXC_ERR error is part of the life cycle,
+		 * so don't make waves.
+		 */
+		if (wc->status == IB_WC_RNR_RETRY_EXC_ERR ||
+		    wc->status == IB_WC_RETRY_EXC_ERR)
+			ipoib_dbg(priv,
+				  "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n",
+				   __func__, wc->status, wr_id, wc->vendor_err);
 		else
-			ipoib_dbg(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
-				  wc->status, wr_id, wc->vendor_err);
+			ipoib_warn(priv,
+				    "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n",
+				   __func__, wc->status, wr_id, wc->vendor_err);
 
 		spin_lock_irqsave(&priv->lock, flags);
 		neigh = tx->neigh;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 2e07537..6cd6163 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -1000,19 +1000,6 @@
 		 */
 		priv->dev->broadcast[8] = priv->pkey >> 8;
 		priv->dev->broadcast[9] = priv->pkey & 0xff;
-
-		/*
-		 * Update the broadcast address in the priv->broadcast object,
-		 * in case it already exists, otherwise no one will do that.
-		 */
-		if (priv->broadcast) {
-			spin_lock_irq(&priv->lock);
-			memcpy(priv->broadcast->mcmember.mgid.raw,
-			       priv->dev->broadcast + 4,
-			sizeof(union ib_gid));
-			spin_unlock_irq(&priv->lock);
-		}
-
 		return 0;
 	}
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index bac95b5..dcc77014 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -2180,6 +2180,7 @@
 {
 	struct ipoib_dev_priv *priv;
 	struct ib_port_attr attr;
+	struct rdma_netdev *rn;
 	int result = -ENOMEM;
 
 	priv = ipoib_intf_alloc(hca, port, format);
@@ -2279,7 +2280,8 @@
 	ipoib_dev_cleanup(priv->dev);
 
 device_init_failed:
-	free_netdev(priv->dev);
+	rn = netdev_priv(priv->dev);
+	rn->free_rdma_netdev(priv->dev);
 	kfree(priv);
 
 alloc_mem_failed:
@@ -2328,7 +2330,7 @@
 		return;
 
 	list_for_each_entry_safe(priv, tmp, dev_list, list) {
-		struct rdma_netdev *rn = netdev_priv(priv->dev);
+		struct rdma_netdev *parent_rn = netdev_priv(priv->dev);
 
 		ib_unregister_event_handler(&priv->event_handler);
 		flush_workqueue(ipoib_workqueue);
@@ -2350,10 +2352,15 @@
 		unregister_netdev(priv->dev);
 		mutex_unlock(&priv->sysfs_mutex);
 
-		rn->free_rdma_netdev(priv->dev);
+		parent_rn->free_rdma_netdev(priv->dev);
 
-		list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list)
+		list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
+			struct rdma_netdev *child_rn;
+
+			child_rn = netdev_priv(cpriv->dev);
+			child_rn->free_rdma_netdev(cpriv->dev);
 			kfree(cpriv);
+		}
 
 		kfree(priv);
 	}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 9927cd6..55a9b71 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -141,14 +141,17 @@
 		return restart_syscall();
 	}
 
-	priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name);
-	if (!priv) {
+	if (!down_write_trylock(&ppriv->vlan_rwsem)) {
 		rtnl_unlock();
 		mutex_unlock(&ppriv->sysfs_mutex);
-		return -ENOMEM;
+		return restart_syscall();
 	}
 
-	down_write(&ppriv->vlan_rwsem);
+	priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name);
+	if (!priv) {
+		result = -ENOMEM;
+		goto out;
+	}
 
 	/*
 	 * First ensure this isn't a duplicate. We check the parent device and
@@ -175,8 +178,11 @@
 	rtnl_unlock();
 	mutex_unlock(&ppriv->sysfs_mutex);
 
-	if (result) {
-		free_netdev(priv->dev);
+	if (result && priv) {
+		struct rdma_netdev *rn;
+
+		rn = netdev_priv(priv->dev);
+		rn->free_rdma_netdev(priv->dev);
 		kfree(priv);
 	}
 
@@ -204,7 +210,12 @@
 		return restart_syscall();
 	}
 
-	down_write(&ppriv->vlan_rwsem);
+	if (!down_write_trylock(&ppriv->vlan_rwsem)) {
+		rtnl_unlock();
+		mutex_unlock(&ppriv->sysfs_mutex);
+		return restart_syscall();
+	}
+
 	list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
 		if (priv->pkey == pkey &&
 		    priv->child_type == IPOIB_LEGACY_CHILD) {
@@ -224,7 +235,10 @@
 	mutex_unlock(&ppriv->sysfs_mutex);
 
 	if (dev) {
-		free_netdev(dev);
+		struct rdma_netdev *rn;
+
+		rn = netdev_priv(dev);
+		rn->free_rdma_netdev(priv->dev);
 		kfree(priv);
 		return 0;
 	}
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 9c3e9ab..322209d 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -154,7 +154,7 @@
 {
 	int i;
 
-	iser_err("page vec npages %d data length %d\n",
+	iser_err("page vec npages %d data length %lld\n",
 		 page_vec->npages, page_vec->fake_mr.length);
 	for (i = 0; i < page_vec->npages; i++)
 		iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]);
diff --git a/drivers/input/ff-core.c b/drivers/input/ff-core.c
index 8f20424..66a46c8 100644
--- a/drivers/input/ff-core.c
+++ b/drivers/input/ff-core.c
@@ -237,9 +237,15 @@
 EXPORT_SYMBOL_GPL(input_ff_erase);
 
 /*
- * flush_effects - erase all effects owned by a file handle
+ * input_ff_flush - erase all effects owned by a file handle
+ * @dev: input device to erase effect from
+ * @file: purported owner of the effects
+ *
+ * This function erases all force-feedback effects associated with
+ * the given owner from specified device. Note that @file may be %NULL,
+ * in which case all effects will be erased.
  */
-static int flush_effects(struct input_dev *dev, struct file *file)
+int input_ff_flush(struct input_dev *dev, struct file *file)
 {
 	struct ff_device *ff = dev->ff;
 	int i;
@@ -255,6 +261,7 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(input_ff_flush);
 
 /**
  * input_ff_event() - generic handler for force-feedback events
@@ -343,7 +350,7 @@
 	mutex_init(&ff->mutex);
 
 	dev->ff = ff;
-	dev->flush = flush_effects;
+	dev->flush = input_ff_flush;
 	dev->event = input_ff_event;
 	__set_bit(EV_FF, dev->evbit);
 
diff --git a/drivers/input/input.c b/drivers/input/input.c
index d268fdc..762bfb9 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -933,58 +933,52 @@
 }
 EXPORT_SYMBOL(input_set_keycode);
 
+bool input_match_device_id(const struct input_dev *dev,
+			   const struct input_device_id *id)
+{
+	if (id->flags & INPUT_DEVICE_ID_MATCH_BUS)
+		if (id->bustype != dev->id.bustype)
+			return false;
+
+	if (id->flags & INPUT_DEVICE_ID_MATCH_VENDOR)
+		if (id->vendor != dev->id.vendor)
+			return false;
+
+	if (id->flags & INPUT_DEVICE_ID_MATCH_PRODUCT)
+		if (id->product != dev->id.product)
+			return false;
+
+	if (id->flags & INPUT_DEVICE_ID_MATCH_VERSION)
+		if (id->version != dev->id.version)
+			return false;
+
+	if (!bitmap_subset(id->evbit, dev->evbit, EV_MAX) ||
+	    !bitmap_subset(id->keybit, dev->keybit, KEY_MAX) ||
+	    !bitmap_subset(id->relbit, dev->relbit, REL_MAX) ||
+	    !bitmap_subset(id->absbit, dev->absbit, ABS_MAX) ||
+	    !bitmap_subset(id->mscbit, dev->mscbit, MSC_MAX) ||
+	    !bitmap_subset(id->ledbit, dev->ledbit, LED_MAX) ||
+	    !bitmap_subset(id->sndbit, dev->sndbit, SND_MAX) ||
+	    !bitmap_subset(id->ffbit, dev->ffbit, FF_MAX) ||
+	    !bitmap_subset(id->swbit, dev->swbit, SW_MAX) ||
+	    !bitmap_subset(id->propbit, dev->propbit, INPUT_PROP_MAX)) {
+		return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(input_match_device_id);
+
 static const struct input_device_id *input_match_device(struct input_handler *handler,
 							struct input_dev *dev)
 {
 	const struct input_device_id *id;
 
 	for (id = handler->id_table; id->flags || id->driver_info; id++) {
-
-		if (id->flags & INPUT_DEVICE_ID_MATCH_BUS)
-			if (id->bustype != dev->id.bustype)
-				continue;
-
-		if (id->flags & INPUT_DEVICE_ID_MATCH_VENDOR)
-			if (id->vendor != dev->id.vendor)
-				continue;
-
-		if (id->flags & INPUT_DEVICE_ID_MATCH_PRODUCT)
-			if (id->product != dev->id.product)
-				continue;
-
-		if (id->flags & INPUT_DEVICE_ID_MATCH_VERSION)
-			if (id->version != dev->id.version)
-				continue;
-
-		if (!bitmap_subset(id->evbit, dev->evbit, EV_MAX))
-			continue;
-
-		if (!bitmap_subset(id->keybit, dev->keybit, KEY_MAX))
-			continue;
-
-		if (!bitmap_subset(id->relbit, dev->relbit, REL_MAX))
-			continue;
-
-		if (!bitmap_subset(id->absbit, dev->absbit, ABS_MAX))
-			continue;
-
-		if (!bitmap_subset(id->mscbit, dev->mscbit, MSC_MAX))
-			continue;
-
-		if (!bitmap_subset(id->ledbit, dev->ledbit, LED_MAX))
-			continue;
-
-		if (!bitmap_subset(id->sndbit, dev->sndbit, SND_MAX))
-			continue;
-
-		if (!bitmap_subset(id->ffbit, dev->ffbit, FF_MAX))
-			continue;
-
-		if (!bitmap_subset(id->swbit, dev->swbit, SW_MAX))
-			continue;
-
-		if (!handler->match || handler->match(handler, dev))
+		if (input_match_device_id(dev, id) &&
+		    (!handler->match || handler->match(handler, dev))) {
 			return id;
+		}
 	}
 
 	return NULL;
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index 29d677c..7b29a89 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -747,6 +747,68 @@
 		input_close_device(handle);
 }
 
+/*
+ * These codes are copied from from hid-ids.h, unfortunately there is no common
+ * usb_ids/bt_ids.h header.
+ */
+#define USB_VENDOR_ID_SONY			0x054c
+#define USB_DEVICE_ID_SONY_PS3_CONTROLLER		0x0268
+#define USB_DEVICE_ID_SONY_PS4_CONTROLLER		0x05c4
+#define USB_DEVICE_ID_SONY_PS4_CONTROLLER_2		0x09cc
+#define USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE	0x0ba0
+
+#define USB_VENDOR_ID_THQ			0x20d6
+#define USB_DEVICE_ID_THQ_PS3_UDRAW			0xcb17
+
+#define ACCEL_DEV(vnd, prd)						\
+	{								\
+		.flags = INPUT_DEVICE_ID_MATCH_VENDOR |			\
+				INPUT_DEVICE_ID_MATCH_PRODUCT |		\
+				INPUT_DEVICE_ID_MATCH_PROPBIT,		\
+		.vendor = (vnd),					\
+		.product = (prd),					\
+		.propbit = { BIT_MASK(INPUT_PROP_ACCELEROMETER) },	\
+	}
+
+static const struct input_device_id joydev_blacklist[] = {
+	/* Avoid touchpads and touchscreens */
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
+				INPUT_DEVICE_ID_MATCH_KEYBIT,
+		.evbit = { BIT_MASK(EV_KEY) },
+		.keybit = { [BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH) },
+	},
+	/* Avoid tablets, digitisers and similar devices */
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
+				INPUT_DEVICE_ID_MATCH_KEYBIT,
+		.evbit = { BIT_MASK(EV_KEY) },
+		.keybit = { [BIT_WORD(BTN_DIGI)] = BIT_MASK(BTN_DIGI) },
+	},
+	/* Disable accelerometers on composite devices */
+	ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER),
+	ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER),
+	ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_2),
+	ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE),
+	ACCEL_DEV(USB_VENDOR_ID_THQ, USB_DEVICE_ID_THQ_PS3_UDRAW),
+	{ /* sentinel */ }
+};
+
+static bool joydev_dev_is_blacklisted(struct input_dev *dev)
+{
+	const struct input_device_id *id;
+
+	for (id = joydev_blacklist; id->flags; id++) {
+		if (input_match_device_id(dev, id)) {
+			dev_dbg(&dev->dev,
+				"joydev: blacklisting '%s'\n", dev->name);
+			return true;
+		}
+	}
+
+	return false;
+}
+
 static bool joydev_dev_is_absolute_mouse(struct input_dev *dev)
 {
 	DECLARE_BITMAP(jd_scratch, KEY_CNT);
@@ -807,12 +869,8 @@
 
 static bool joydev_match(struct input_handler *handler, struct input_dev *dev)
 {
-	/* Avoid touchpads and touchscreens */
-	if (test_bit(EV_KEY, dev->evbit) && test_bit(BTN_TOUCH, dev->keybit))
-		return false;
-
-	/* Avoid tablets, digitisers and similar devices */
-	if (test_bit(EV_KEY, dev->evbit) && test_bit(BTN_DIGI, dev->keybit))
+	/* Disable blacklisted devices */
+	if (joydev_dev_is_blacklisted(dev))
 		return false;
 
 	/* Avoid absolute mice */
diff --git a/drivers/input/keyboard/tca8418_keypad.c b/drivers/input/keyboard/tca8418_keypad.c
index e37e335..6da607d 100644
--- a/drivers/input/keyboard/tca8418_keypad.c
+++ b/drivers/input/keyboard/tca8418_keypad.c
@@ -234,14 +234,7 @@
 static int tca8418_configure(struct tca8418_keypad *keypad_data,
 			     u32 rows, u32 cols)
 {
-	int reg, error;
-
-	/* Write config register, if this fails assume device not present */
-	error = tca8418_write_byte(keypad_data, REG_CFG,
-				CFG_INT_CFG | CFG_OVR_FLOW_IEN | CFG_KE_IEN);
-	if (error < 0)
-		return -ENODEV;
-
+	int reg, error = 0;
 
 	/* Assemble a mask for row and column registers */
 	reg  =  ~(~0 << rows);
@@ -257,6 +250,12 @@
 	error |= tca8418_write_byte(keypad_data, REG_DEBOUNCE_DIS2, reg >> 8);
 	error |= tca8418_write_byte(keypad_data, REG_DEBOUNCE_DIS3, reg >> 16);
 
+	if (error)
+		return error;
+
+	error = tca8418_write_byte(keypad_data, REG_CFG,
+				CFG_INT_CFG | CFG_OVR_FLOW_IEN | CFG_KE_IEN);
+
 	return error;
 }
 
@@ -268,6 +267,7 @@
 	struct input_dev *input;
 	u32 rows = 0, cols = 0;
 	int error, row_shift, max_keys;
+	u8 reg;
 
 	/* Check i2c driver capabilities */
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE)) {
@@ -301,10 +301,10 @@
 	keypad_data->client = client;
 	keypad_data->row_shift = row_shift;
 
-	/* Initialize the chip or fail if chip isn't present */
-	error = tca8418_configure(keypad_data, rows, cols);
-	if (error < 0)
-		return error;
+	/* Read key lock register, if this fails assume device not present */
+	error = tca8418_read_byte(keypad_data, REG_KEY_LCK_EC, &reg);
+	if (error)
+		return -ENODEV;
 
 	/* Configure input device */
 	input = devm_input_allocate_device(dev);
@@ -340,6 +340,11 @@
 		return error;
 	}
 
+	/* Initialize the chip */
+	error = tca8418_configure(keypad_data, rows, cols);
+	if (error < 0)
+		return error;
+
 	error = input_register_device(input);
 	if (error) {
 		dev_err(dev, "Unable to register input device, error: %d\n",
diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c
index 6cee5ad..debeeae 100644
--- a/drivers/input/misc/axp20x-pek.c
+++ b/drivers/input/misc/axp20x-pek.c
@@ -403,6 +403,7 @@
 	},
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(platform, axp_pek_id_match);
 
 static struct platform_driver axp20x_pek_driver = {
 	.probe		= axp20x_pek_probe,
@@ -417,4 +418,3 @@
 MODULE_DESCRIPTION("axp20x Power Button");
 MODULE_AUTHOR("Carlo Caione <carlo@caione.org>");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:axp20x-pek");
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index 6bf82ea..ae47312 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1635,13 +1635,25 @@
 		return NULL;
 	}
 
-	while (buflen > 0) {
+	while (buflen >= sizeof(*union_desc)) {
 		union_desc = (struct usb_cdc_union_desc *)buf;
 
+		if (union_desc->bLength > buflen) {
+			dev_err(&intf->dev, "Too large descriptor\n");
+			return NULL;
+		}
+
 		if (union_desc->bDescriptorType == USB_DT_CS_INTERFACE &&
 		    union_desc->bDescriptorSubType == USB_CDC_UNION_TYPE) {
 			dev_dbg(&intf->dev, "Found union header\n");
-			return union_desc;
+
+			if (union_desc->bLength >= sizeof(*union_desc))
+				return union_desc;
+
+			dev_err(&intf->dev,
+				"Union descriptor to short (%d vs %zd\n)",
+				union_desc->bLength, sizeof(*union_desc));
+			return NULL;
 		}
 
 		buflen -= union_desc->bLength;
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 022be0e..443151d 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -98,14 +98,15 @@
 					uinput_request_alloc_id(udev, request));
 }
 
-static void uinput_request_done(struct uinput_device *udev,
-				struct uinput_request *request)
+static void uinput_request_release_slot(struct uinput_device *udev,
+					unsigned int id)
 {
 	/* Mark slot as available */
-	udev->requests[request->id] = NULL;
-	wake_up(&udev->requests_waitq);
+	spin_lock(&udev->requests_lock);
+	udev->requests[id] = NULL;
+	spin_unlock(&udev->requests_lock);
 
-	complete(&request->done);
+	wake_up(&udev->requests_waitq);
 }
 
 static int uinput_request_send(struct uinput_device *udev,
@@ -138,20 +139,22 @@
 static int uinput_request_submit(struct uinput_device *udev,
 				 struct uinput_request *request)
 {
-	int error;
+	int retval;
 
-	error = uinput_request_reserve_slot(udev, request);
-	if (error)
-		return error;
+	retval = uinput_request_reserve_slot(udev, request);
+	if (retval)
+		return retval;
 
-	error = uinput_request_send(udev, request);
-	if (error) {
-		uinput_request_done(udev, request);
-		return error;
-	}
+	retval = uinput_request_send(udev, request);
+	if (retval)
+		goto out;
 
 	wait_for_completion(&request->done);
-	return request->retval;
+	retval = request->retval;
+
+ out:
+	uinput_request_release_slot(udev, request->id);
+	return retval;
 }
 
 /*
@@ -169,7 +172,7 @@
 		request = udev->requests[i];
 		if (request) {
 			request->retval = -ENODEV;
-			uinput_request_done(udev, request);
+			complete(&request->done);
 		}
 	}
 
@@ -230,6 +233,18 @@
 	return uinput_request_submit(udev, &request);
 }
 
+static int uinput_dev_flush(struct input_dev *dev, struct file *file)
+{
+	/*
+	 * If we are called with file == NULL that means we are tearing
+	 * down the device, and therefore we can not handle FF erase
+	 * requests: either we are handling UI_DEV_DESTROY (and holding
+	 * the udev->mutex), or the file descriptor is closed and there is
+	 * nobody on the other side anymore.
+	 */
+	return file ? input_ff_flush(dev, file) : 0;
+}
+
 static void uinput_destroy_device(struct uinput_device *udev)
 {
 	const char *name, *phys;
@@ -297,6 +312,12 @@
 		dev->ff->playback = uinput_dev_playback;
 		dev->ff->set_gain = uinput_dev_set_gain;
 		dev->ff->set_autocenter = uinput_dev_set_autocenter;
+		/*
+		 * The standard input_ff_flush() implementation does
+		 * not quite work for uinput as we can't reasonably
+		 * handle FF requests during device teardown.
+		 */
+		dev->flush = uinput_dev_flush;
 	}
 
 	error = input_register_device(udev->dev);
@@ -939,7 +960,7 @@
 			}
 
 			req->retval = ff_up.retval;
-			uinput_request_done(udev, req);
+			complete(&req->done);
 			goto out;
 
 		case UI_END_FF_ERASE:
@@ -955,7 +976,7 @@
 			}
 
 			req->retval = ff_erase.retval;
-			uinput_request_done(udev, req);
+			complete(&req->done);
 			goto out;
 	}
 
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 0e761d0..6d6b092 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1258,6 +1258,7 @@
 	{ "ELAN0605", 0 },
 	{ "ELAN0609", 0 },
 	{ "ELAN060B", 0 },
+	{ "ELAN0611", 0 },
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c
index 15b1330..e19eb60 100644
--- a/drivers/input/mouse/elan_i2c_i2c.c
+++ b/drivers/input/mouse/elan_i2c_i2c.c
@@ -598,7 +598,7 @@
 	}
 
 	/* Wait for F/W to update one page ROM data. */
-	msleep(20);
+	msleep(35);
 
 	error = elan_i2c_read_cmd(client, ETP_I2C_IAP_CTRL_CMD, val);
 	if (error) {
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 5af0b7d..ee5466a 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -1709,8 +1709,7 @@
 		.sensor_pdata = {
 			.sensor_type = rmi_sensor_touchpad,
 			.axis_align.flip_y = true,
-			/* to prevent cursors jumps: */
-			.kernel_tracking = true,
+			.kernel_tracking = false,
 			.topbuttonpad = topbuttonpad,
 		},
 		.f30_data = {
diff --git a/drivers/input/rmi4/rmi_f30.c b/drivers/input/rmi4/rmi_f30.c
index 34dfee5..82e0f0d 100644
--- a/drivers/input/rmi4/rmi_f30.c
+++ b/drivers/input/rmi4/rmi_f30.c
@@ -232,9 +232,10 @@
 	unsigned int trackstick_button = BTN_LEFT;
 	bool button_mapped = false;
 	int i;
+	int button_count = min_t(u8, f30->gpioled_count, TRACKSTICK_RANGE_END);
 
 	f30->gpioled_key_map = devm_kcalloc(&fn->dev,
-					    f30->gpioled_count,
+					    button_count,
 					    sizeof(f30->gpioled_key_map[0]),
 					    GFP_KERNEL);
 	if (!f30->gpioled_key_map) {
@@ -242,7 +243,7 @@
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < f30->gpioled_count; i++) {
+	for (i = 0; i < button_count; i++) {
 		if (!rmi_f30_is_valid_button(i, f30->ctrl))
 			continue;
 
diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c
index b796e89..4b8b9d7 100644
--- a/drivers/input/tablet/gtco.c
+++ b/drivers/input/tablet/gtco.c
@@ -230,13 +230,17 @@
 
 	/* Walk  this report and pull out the info we need */
 	while (i < length) {
-		prefix = report[i];
-
-		/* Skip over prefix */
-		i++;
+		prefix = report[i++];
 
 		/* Determine data size and save the data in the proper variable */
-		size = PREF_SIZE(prefix);
+		size = (1U << PREF_SIZE(prefix)) >> 1;
+		if (i + size > length) {
+			dev_err(ddev,
+				"Not enough data (need %d, have %d)\n",
+				i + size, length);
+			break;
+		}
+
 		switch (size) {
 		case 1:
 			data = report[i];
@@ -244,8 +248,7 @@
 		case 2:
 			data16 = get_unaligned_le16(&report[i]);
 			break;
-		case 3:
-			size = 4;
+		case 4:
 			data32 = get_unaligned_le32(&report[i]);
 			break;
 		}
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index 32d2762..b3bbad7 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -72,6 +72,9 @@
 #define GOODIX_REG_CONFIG_DATA		0x8047
 #define GOODIX_REG_ID			0x8140
 
+#define GOODIX_BUFFER_STATUS_READY	BIT(7)
+#define GOODIX_BUFFER_STATUS_TIMEOUT	20
+
 #define RESOLUTION_LOC		1
 #define MAX_CONTACTS_LOC	5
 #define TRIGGER_LOC		6
@@ -195,35 +198,53 @@
 
 static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 {
+	unsigned long max_timeout;
 	int touch_num;
 	int error;
 
-	error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR, data,
-				GOODIX_CONTACT_SIZE + 1);
-	if (error) {
-		dev_err(&ts->client->dev, "I2C transfer error: %d\n", error);
-		return error;
-	}
-
-	if (!(data[0] & 0x80))
-		return -EAGAIN;
-
-	touch_num = data[0] & 0x0f;
-	if (touch_num > ts->max_touch_num)
-		return -EPROTO;
-
-	if (touch_num > 1) {
-		data += 1 + GOODIX_CONTACT_SIZE;
-		error = goodix_i2c_read(ts->client,
-					GOODIX_READ_COOR_ADDR +
-						1 + GOODIX_CONTACT_SIZE,
-					data,
-					GOODIX_CONTACT_SIZE * (touch_num - 1));
-		if (error)
+	/*
+	 * The 'buffer status' bit, which indicates that the data is valid, is
+	 * not set as soon as the interrupt is raised, but slightly after.
+	 * This takes around 10 ms to happen, so we poll for 20 ms.
+	 */
+	max_timeout = jiffies + msecs_to_jiffies(GOODIX_BUFFER_STATUS_TIMEOUT);
+	do {
+		error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR,
+					data, GOODIX_CONTACT_SIZE + 1);
+		if (error) {
+			dev_err(&ts->client->dev, "I2C transfer error: %d\n",
+					error);
 			return error;
-	}
+		}
 
-	return touch_num;
+		if (data[0] & GOODIX_BUFFER_STATUS_READY) {
+			touch_num = data[0] & 0x0f;
+			if (touch_num > ts->max_touch_num)
+				return -EPROTO;
+
+			if (touch_num > 1) {
+				data += 1 + GOODIX_CONTACT_SIZE;
+				error = goodix_i2c_read(ts->client,
+						GOODIX_READ_COOR_ADDR +
+							1 + GOODIX_CONTACT_SIZE,
+						data,
+						GOODIX_CONTACT_SIZE *
+							(touch_num - 1));
+				if (error)
+					return error;
+			}
+
+			return touch_num;
+		}
+
+		usleep_range(1000, 2000); /* Poll every 1 - 2 ms */
+	} while (time_before(jiffies, max_timeout));
+
+	/*
+	 * The Goodix panel will send spurious interrupts after a
+	 * 'finger up' event, which will always cause a timeout.
+	 */
+	return 0;
 }
 
 static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
diff --git a/drivers/input/touchscreen/stmfts.c b/drivers/input/touchscreen/stmfts.c
index 157fdb4..8c6c617 100644
--- a/drivers/input/touchscreen/stmfts.c
+++ b/drivers/input/touchscreen/stmfts.c
@@ -663,12 +663,10 @@
 	sdata->input->open = stmfts_input_open;
 	sdata->input->close = stmfts_input_close;
 
+	input_set_capability(sdata->input, EV_ABS, ABS_MT_POSITION_X);
+	input_set_capability(sdata->input, EV_ABS, ABS_MT_POSITION_Y);
 	touchscreen_parse_properties(sdata->input, true, &sdata->prop);
 
-	input_set_abs_params(sdata->input, ABS_MT_POSITION_X, 0,
-						sdata->prop.max_x, 0, 0);
-	input_set_abs_params(sdata->input, ABS_MT_POSITION_Y, 0,
-						sdata->prop.max_y, 0, 0);
 	input_set_abs_params(sdata->input, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0);
 	input_set_abs_params(sdata->input, ABS_MT_TOUCH_MINOR, 0, 255, 0, 0);
 	input_set_abs_params(sdata->input, ABS_MT_ORIENTATION, 0, 255, 0, 0);
diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
index 7953381..f1043ae 100644
--- a/drivers/input/touchscreen/ti_am335x_tsc.c
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -161,7 +161,7 @@
 		break;
 	case 5:
 		config |= ts_dev->bit_xp | STEPCONFIG_INP_AN4 |
-				ts_dev->bit_xn | ts_dev->bit_yp;
+				STEPCONFIG_XNP | STEPCONFIG_YPN;
 		break;
 	case 8:
 		config |= ts_dev->bit_yp | STEPCONFIG_INP(ts_dev->inp_xp);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 49bd2ab..f3a2134 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -278,7 +278,7 @@
 config IPMMU_VMSA
 	bool "Renesas VMSA-compatible IPMMU"
 	depends on ARM || IOMMU_DMA
-	depends on ARCH_RENESAS || COMPILE_TEST
+	depends on ARCH_RENESAS || (COMPILE_TEST && !GENERIC_ATOMIC64)
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
 	select ARM_DMA_USE_IOMMU
@@ -373,7 +373,8 @@
 config QCOM_IOMMU
 	# Note: iommu drivers cannot (yet?) be built as modules
 	bool "Qualcomm IOMMU Support"
-	depends on ARCH_QCOM || COMPILE_TEST
+	depends on ARCH_QCOM || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	depends on HAS_DMA
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
 	select ARM_DMA_USE_IOMMU
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 51f8215..8e8874d 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2773,14 +2773,16 @@
 
 int __init amd_iommu_init_dma_ops(void)
 {
-	swiotlb        = iommu_pass_through ? 1 : 0;
+	swiotlb        = (iommu_pass_through || sme_me_mask) ? 1 : 0;
 	iommu_detected = 1;
 
 	/*
 	 * In case we don't initialize SWIOTLB (actually the common case
-	 * when AMD IOMMU is enabled), make sure there are global
-	 * dma_ops set as a fall-back for devices not handled by this
-	 * driver (for example non-PCI devices).
+	 * when AMD IOMMU is enabled and SME is not active), make sure there
+	 * are global dma_ops set as a fall-back for devices not handled by
+	 * this driver (for example non-PCI devices). When SME is active,
+	 * make sure that swiotlb variable remains set so the global dma_ops
+	 * continue to be SWIOTLB.
 	 */
 	if (!swiotlb)
 		dma_ops = &nommu_dma_ops;
@@ -3046,6 +3048,7 @@
 	mutex_unlock(&domain->api_lock);
 
 	domain_flush_tlb_pde(domain);
+	domain_flush_complete(domain);
 
 	return unmap_size;
 }
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 382de42..6fe2d03 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -874,7 +874,7 @@
 		hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4);
 		entry = (((u64) hi) << 32) + lo;
 		if (last_entry && last_entry != entry) {
-			pr_err("IOMMU:%d should use the same dev table as others!/n",
+			pr_err("IOMMU:%d should use the same dev table as others!\n",
 				iommu->index);
 			return false;
 		}
@@ -882,7 +882,7 @@
 
 		old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12;
 		if (old_devtb_size != dev_table_size) {
-			pr_err("The device table size of IOMMU:%d is not expected!/n",
+			pr_err("The device table size of IOMMU:%d is not expected!\n",
 				iommu->index);
 			return false;
 		}
@@ -890,7 +890,7 @@
 
 	old_devtb_phys = entry & PAGE_MASK;
 	if (old_devtb_phys >= 0x100000000ULL) {
-		pr_err("The address of old device table is above 4G, not trustworthy!/n");
+		pr_err("The address of old device table is above 4G, not trustworthy!\n");
 		return false;
 	}
 	old_devtb = memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB);
@@ -901,7 +901,7 @@
 	old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag,
 				get_order(dev_table_size));
 	if (old_dev_tbl_cpy == NULL) {
-		pr_err("Failed to allocate memory for copying old device table!/n");
+		pr_err("Failed to allocate memory for copying old device table!\n");
 		return false;
 	}
 
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index ca5ebae..57c920c 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -497,7 +497,7 @@
 #define	dmar_parse_one_rhsa		dmar_res_noop
 #endif
 
-static void __init
+static void
 dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
 {
 	struct acpi_dmar_hardware_unit *drhd;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index f596fcc..25c2c75 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -709,7 +709,7 @@
 				pm_runtime_force_resume)
 };
 
-static const struct of_device_id sysmmu_of_match[] __initconst = {
+static const struct of_device_id sysmmu_of_match[] = {
 	{ .compatible	= "samsung,exynos-sysmmu", },
 	{ },
 };
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index d665d0d..6961fc3 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -245,7 +245,7 @@
 static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries,
 			       struct io_pgtable_cfg *cfg)
 {
-	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)
 		return;
 
 	dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep),
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index bd515be..16d33ac 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -371,7 +371,8 @@
 	int ret;
 
 	spin_lock_irqsave(&dom->pgtlock, flags);
-	ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
+	ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32),
+			    size, prot);
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
 	return ret;
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index e60e3db..50947eb 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -157,10 +157,7 @@
 
 	err = of_iommu_xlate(info->dev, &iommu_spec);
 	of_node_put(iommu_spec.np);
-	if (err)
-		return err;
-
-	return info->np == pdev->bus->dev.of_node;
+	return err;
 }
 
 const struct iommu_ops *of_iommu_configure(struct device *dev,
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index e8d8934..e883956 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -107,6 +107,10 @@
 
 #define ITS_ITT_ALIGN		SZ_256
 
+/* The maximum number of VPEID bits supported by VLPI commands */
+#define ITS_MAX_VPEID_BITS	(16)
+#define ITS_MAX_VPEID		(1 << (ITS_MAX_VPEID_BITS))
+
 /* Convert page order to size in bytes */
 #define PAGE_ORDER_TO_SIZE(o)	(PAGE_SIZE << (o))
 
@@ -308,7 +312,7 @@
 
 static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr)
 {
-	its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 50, 8);
+	its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 51, 8);
 }
 
 static void its_encode_valid(struct its_cmd_block *cmd, int valid)
@@ -318,7 +322,7 @@
 
 static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr)
 {
-	its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 50, 16);
+	its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 51, 16);
 }
 
 static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
@@ -358,7 +362,7 @@
 
 static void its_encode_vpt_addr(struct its_cmd_block *cmd, u64 vpt_pa)
 {
-	its_mask_encode(&cmd->raw_cmd[3], vpt_pa >> 16, 50, 16);
+	its_mask_encode(&cmd->raw_cmd[3], vpt_pa >> 16, 51, 16);
 }
 
 static void its_encode_vpt_size(struct its_cmd_block *cmd, u8 vpt_size)
@@ -1478,9 +1482,9 @@
 	u64 val = its_read_baser(its, baser);
 	u64 esz = GITS_BASER_ENTRY_SIZE(val);
 	u64 type = GITS_BASER_TYPE(val);
+	u64 baser_phys, tmp;
 	u32 alloc_pages;
 	void *base;
-	u64 tmp;
 
 retry_alloc_baser:
 	alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
@@ -1496,8 +1500,24 @@
 	if (!base)
 		return -ENOMEM;
 
+	baser_phys = virt_to_phys(base);
+
+	/* Check if the physical address of the memory is above 48bits */
+	if (IS_ENABLED(CONFIG_ARM64_64K_PAGES) && (baser_phys >> 48)) {
+
+		/* 52bit PA is supported only when PageSize=64K */
+		if (psz != SZ_64K) {
+			pr_err("ITS: no 52bit PA support when psz=%d\n", psz);
+			free_pages((unsigned long)base, order);
+			return -ENXIO;
+		}
+
+		/* Convert 52bit PA to 48bit field */
+		baser_phys = GITS_BASER_PHYS_52_to_48(baser_phys);
+	}
+
 retry_baser:
-	val = (virt_to_phys(base)				 |
+	val = (baser_phys					 |
 		(type << GITS_BASER_TYPE_SHIFT)			 |
 		((esz - 1) << GITS_BASER_ENTRY_SIZE_SHIFT)	 |
 		((alloc_pages - 1) << GITS_BASER_PAGES_SHIFT)	 |
@@ -1582,13 +1602,12 @@
 
 static bool its_parse_indirect_baser(struct its_node *its,
 				     struct its_baser *baser,
-				     u32 psz, u32 *order)
+				     u32 psz, u32 *order, u32 ids)
 {
 	u64 tmp = its_read_baser(its, baser);
 	u64 type = GITS_BASER_TYPE(tmp);
 	u64 esz = GITS_BASER_ENTRY_SIZE(tmp);
 	u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb;
-	u32 ids = its->device_ids;
 	u32 new_order = *order;
 	bool indirect = false;
 
@@ -1680,9 +1699,13 @@
 			continue;
 
 		case GITS_BASER_TYPE_DEVICE:
+			indirect = its_parse_indirect_baser(its, baser,
+							    psz, &order,
+							    its->device_ids);
 		case GITS_BASER_TYPE_VCPU:
 			indirect = its_parse_indirect_baser(its, baser,
-							    psz, &order);
+							    psz, &order,
+							    ITS_MAX_VPEID_BITS);
 			break;
 		}
 
@@ -2551,7 +2574,7 @@
 
 static int its_vpe_id_alloc(void)
 {
-	return ida_simple_get(&its_vpeid_ida, 0, 1 << 16, GFP_KERNEL);
+	return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL);
 }
 
 static void its_vpe_id_free(u16 id)
@@ -2851,7 +2874,7 @@
 		return -ENOMEM;
 	}
 
-	BUG_ON(entries != vpe_proxy.dev->nr_ites);
+	BUG_ON(entries > vpe_proxy.dev->nr_ites);
 
 	raw_spin_lock_init(&vpe_proxy.lock);
 	vpe_proxy.next_victim = 0;
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 519149e..b5df99c 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1042,7 +1042,7 @@
 {
 	const __be32 *cell;
 	u64 hwid;
-	int i;
+	int cpu;
 
 	cell = of_get_property(dn, "reg", NULL);
 	if (!cell)
@@ -1056,9 +1056,9 @@
 	if (hwid & ~MPIDR_HWID_BITMASK)
 		return -1;
 
-	for (i = 0; i < num_possible_cpus(); i++)
-		if (cpu_logical_map(i) == hwid)
-			return i;
+	for_each_possible_cpu(cpu)
+		if (cpu_logical_map(cpu) == hwid)
+			return cpu;
 
 	return -1;
 }
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 2370e6d..cd0bcc3 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -173,7 +173,9 @@
 {
 	struct its_cmd_info info = {
 		.cmd_type = MAP_VLPI,
-		.map      = map,
+		{
+			.map      = map,
+		},
 	};
 
 	/*
@@ -189,7 +191,9 @@
 {
 	struct its_cmd_info info = {
 		.cmd_type = GET_VLPI,
-		.map      = map,
+		{
+			.map      = map,
+		},
 	};
 
 	return irq_set_vcpu_affinity(irq, &info);
@@ -205,7 +209,9 @@
 {
 	struct its_cmd_info info = {
 		.cmd_type = inv ? PROP_UPDATE_AND_INV_VLPI : PROP_UPDATE_VLPI,
-		.config   = config,
+		{
+			.config   = config,
+		},
 	};
 
 	return irq_set_vcpu_affinity(irq, &info);
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 6e52a88..c90976d 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -169,20 +169,19 @@
 {
 	unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
 
-	write_gic_rmask(BIT(intr));
+	write_gic_rmask(intr);
 	gic_clear_pcpu_masks(intr);
 }
 
 static void gic_unmask_irq(struct irq_data *d)
 {
-	struct cpumask *affinity = irq_data_get_affinity_mask(d);
 	unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
 	unsigned int cpu;
 
-	write_gic_smask(BIT(intr));
+	write_gic_smask(intr);
 
 	gic_clear_pcpu_masks(intr);
-	cpu = cpumask_first_and(affinity, cpu_online_mask);
+	cpu = cpumask_first(irq_data_get_effective_affinity_mask(d));
 	set_bit(intr, per_cpu_ptr(pcpu_masks, cpu));
 }
 
@@ -420,13 +419,17 @@
 				     irq_hw_number_t hw, unsigned int cpu)
 {
 	int intr = GIC_HWIRQ_TO_SHARED(hw);
+	struct irq_data *data;
 	unsigned long flags;
 
+	data = irq_get_irq_data(virq);
+
 	spin_lock_irqsave(&gic_lock, flags);
 	write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
 	write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu)));
 	gic_clear_pcpu_masks(intr);
 	set_bit(intr, per_cpu_ptr(pcpu_masks, cpu));
+	irq_data_update_effective_affinity(data, cpumask_of(cpu));
 	spin_unlock_irqrestore(&gic_lock, flags);
 
 	return 0;
@@ -645,7 +648,7 @@
 
 	/* Find the first available CPU vector. */
 	i = 0;
-	reserved = (C_SW0 | C_SW1) >> __fls(C_SW0);
+	reserved = (C_SW0 | C_SW1) >> __ffs(C_SW0);
 	while (!of_property_read_u32_index(node, "mti,reserved-cpu-vectors",
 					   i++, &cpu_vec))
 		reserved |= BIT(cpu_vec);
@@ -684,11 +687,11 @@
 
 	gicconfig = read_gic_config();
 	gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS;
-	gic_shared_intrs >>= __fls(GIC_CONFIG_NUMINTERRUPTS);
+	gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS);
 	gic_shared_intrs = (gic_shared_intrs + 1) * 8;
 
 	gic_vpes = gicconfig & GIC_CONFIG_PVPS;
-	gic_vpes >>= __fls(GIC_CONFIG_PVPS);
+	gic_vpes >>= __ffs(GIC_CONFIG_PVPS);
 	gic_vpes = gic_vpes + 1;
 
 	if (cpu_has_veic) {
@@ -767,7 +770,7 @@
 	for (i = 0; i < gic_shared_intrs; i++) {
 		change_gic_pol(i, GIC_POL_ACTIVE_HIGH);
 		change_gic_trig(i, GIC_TRIG_LEVEL);
-		write_gic_rmask(BIT(i));
+		write_gic_rmask(i);
 	}
 
 	for (i = 0; i < gic_vpes; i++) {
diff --git a/drivers/irqchip/irq-tango.c b/drivers/irqchip/irq-tango.c
index bdbb5c0..0c08530 100644
--- a/drivers/irqchip/irq-tango.c
+++ b/drivers/irqchip/irq-tango.c
@@ -141,7 +141,7 @@
 	for (i = 0; i < 2; i++) {
 		ct[i].chip.irq_ack = irq_gc_ack_set_bit;
 		ct[i].chip.irq_mask = irq_gc_mask_disable_reg;
-		ct[i].chip.irq_mask_ack = irq_gc_mask_disable_reg_and_ack;
+		ct[i].chip.irq_mask_ack = irq_gc_mask_disable_and_ack_set;
 		ct[i].chip.irq_unmask = irq_gc_unmask_enable_reg;
 		ct[i].chip.irq_set_type = tangox_irq_set_type;
 		ct[i].chip.name = gc->domain->name;
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 6c44609..cd2b3c6 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -825,7 +825,6 @@
 	isdn_net_local *lp;
 	struct ippp_struct *is;
 	int proto;
-	unsigned char protobuf[4];
 
 	is = file->private_data;
 
@@ -839,24 +838,28 @@
 	if (!lp)
 		printk(KERN_DEBUG "isdn_ppp_write: lp == NULL\n");
 	else {
-		/*
-		 * Don't reset huptimer for
-		 * LCP packets. (Echo requests).
-		 */
-		if (copy_from_user(protobuf, buf, 4))
-			return -EFAULT;
-		proto = PPP_PROTOCOL(protobuf);
-		if (proto != PPP_LCP)
-			lp->huptimer = 0;
+		if (lp->isdn_device < 0 || lp->isdn_channel < 0) {
+			unsigned char protobuf[4];
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			if (copy_from_user(protobuf, buf, 4))
+				return -EFAULT;
 
-		if (lp->isdn_device < 0 || lp->isdn_channel < 0)
+			proto = PPP_PROTOCOL(protobuf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
+
 			return 0;
+		}
 
 		if ((dev->drv[lp->isdn_device]->flags & DRV_FLAG_RUNNING) &&
 		    lp->dialstate == 0 &&
 		    (lp->flags & ISDN_NET_CONNECTED)) {
 			unsigned short hl;
 			struct sk_buff *skb;
+			unsigned char *cpy_buf;
 			/*
 			 * we need to reserve enough space in front of
 			 * sk_buff. old call to dev_alloc_skb only reserved
@@ -869,11 +872,21 @@
 				return count;
 			}
 			skb_reserve(skb, hl);
-			if (copy_from_user(skb_put(skb, count), buf, count))
+			cpy_buf = skb_put(skb, count);
+			if (copy_from_user(cpy_buf, buf, count))
 			{
 				kfree_skb(skb);
 				return -EFAULT;
 			}
+
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			proto = PPP_PROTOCOL(cpy_buf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
+
 			if (is->debug & 0x40) {
 				printk(KERN_DEBUG "ppp xmit: len %d\n", (int) skb->len);
 				isdn_ppp_frame_log("xmit", skb->data, skb->len, 32, is->unit, lp->ppp_slot);
diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c
index bbbbe08..9a257f9 100644
--- a/drivers/leds/leds-as3645a.c
+++ b/drivers/leds/leds-as3645a.c
@@ -112,6 +112,10 @@
 #define AS_PEAK_mA_TO_REG(a) \
 	((min_t(u32, AS_PEAK_mA_MAX, a) - 1250) / 250)
 
+/* LED numbers for Devicetree */
+#define AS_LED_FLASH				0
+#define AS_LED_INDICATOR			1
+
 enum as_mode {
 	AS_MODE_EXT_TORCH = 0 << AS_CONTROL_MODE_SETTING_SHIFT,
 	AS_MODE_INDICATOR = 1 << AS_CONTROL_MODE_SETTING_SHIFT,
@@ -491,10 +495,29 @@
 			      struct device_node *node)
 {
 	struct as3645a_config *cfg = &flash->cfg;
+	struct device_node *child;
 	const char *name;
 	int rval;
 
-	flash->flash_node = of_get_child_by_name(node, "flash");
+	for_each_child_of_node(node, child) {
+		u32 id = 0;
+
+		of_property_read_u32(child, "reg", &id);
+
+		switch (id) {
+		case AS_LED_FLASH:
+			flash->flash_node = of_node_get(child);
+			break;
+		case AS_LED_INDICATOR:
+			flash->indicator_node = of_node_get(child);
+			break;
+		default:
+			dev_warn(&flash->client->dev,
+				 "unknown LED %u encountered, ignoring\n", id);
+			break;
+		}
+	}
+
 	if (!flash->flash_node) {
 		dev_err(&flash->client->dev, "can't find flash node\n");
 		return -ENODEV;
@@ -534,11 +557,10 @@
 	of_property_read_u32(flash->flash_node, "voltage-reference",
 			     &cfg->voltage_reference);
 
-	of_property_read_u32(flash->flash_node, "peak-current-limit",
+	of_property_read_u32(flash->flash_node, "ams,input-max-microamp",
 			     &cfg->peak);
 	cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak);
 
-	flash->indicator_node = of_get_child_by_name(node, "indicator");
 	if (!flash->indicator_node) {
 		dev_warn(&flash->client->dev,
 			 "can't find indicator node\n");
@@ -721,6 +743,7 @@
 	as3645a_set_control(flash, AS_MODE_EXT_TORCH, false);
 
 	v4l2_flash_release(flash->vf);
+	v4l2_flash_release(flash->vfind);
 
 	led_classdev_flash_unregister(&flash->fled);
 	led_classdev_unregister(&flash->iled_cdev);
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 7d5286b..1841d03 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -64,7 +64,7 @@
 void __closure_wake_up(struct closure_waitlist *wait_list)
 {
 	struct llist_node *list;
-	struct closure *cl;
+	struct closure *cl, *t;
 	struct llist_node *reverse = NULL;
 
 	list = llist_del_all(&wait_list->list);
@@ -73,7 +73,7 @@
 	reverse = llist_reverse_order(list);
 
 	/* Then do the wakeups */
-	llist_for_each_entry(cl, reverse, list) {
+	llist_for_each_entry_safe(cl, t, reverse, list) {
 		closure_set_waiting(cl, 0);
 		closure_sub(cl, CLOSURE_WAITING + 1);
 	}
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 24eddbd..2031447 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -149,5 +149,6 @@
 
 extern atomic_t dm_global_event_nr;
 extern wait_queue_head_t dm_global_eventq;
+void dm_issue_global_event(void);
 
 #endif
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index a55ffd4..96ab465 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -2466,6 +2466,7 @@
 		kfree(cipher_api);
 		return ret;
 	}
+	kfree(cipher_api);
 
 	return 0;
 bad_mem:
@@ -2584,6 +2585,10 @@
 				ti->error = "Invalid feature value for sector_size";
 				return -EINVAL;
 			}
+			if (ti->len & ((cc->sector_size >> SECTOR_SHIFT) - 1)) {
+				ti->error = "Device size is not multiple of sector_size feature";
+				return -EINVAL;
+			}
 			cc->sector_shift = __ffs(cc->sector_size) - SECTOR_SHIFT;
 		} else if (!strcasecmp(opt_string, "iv_large_sectors"))
 			set_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 8756a68..e52676f 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -477,9 +477,13 @@
  * Round up the ptr to an 8-byte boundary.
  */
 #define ALIGN_MASK 7
+static inline size_t align_val(size_t val)
+{
+	return (val + ALIGN_MASK) & ~ALIGN_MASK;
+}
 static inline void *align_ptr(void *ptr)
 {
-	return (void *) (((size_t) (ptr + ALIGN_MASK)) & ~ALIGN_MASK);
+	return (void *)align_val((size_t)ptr);
 }
 
 /*
@@ -505,7 +509,7 @@
 	struct hash_cell *hc;
 	size_t len, needed = 0;
 	struct gendisk *disk;
-	struct dm_name_list *nl, *old_nl = NULL;
+	struct dm_name_list *orig_nl, *nl, *old_nl = NULL;
 	uint32_t *event_nr;
 
 	down_write(&_hash_lock);
@@ -516,17 +520,15 @@
 	 */
 	for (i = 0; i < NUM_BUCKETS; i++) {
 		list_for_each_entry (hc, _name_buckets + i, name_list) {
-			needed += sizeof(struct dm_name_list);
-			needed += strlen(hc->name) + 1;
-			needed += ALIGN_MASK;
-			needed += (sizeof(uint32_t) + ALIGN_MASK) & ~ALIGN_MASK;
+			needed += align_val(offsetof(struct dm_name_list, name) + strlen(hc->name) + 1);
+			needed += align_val(sizeof(uint32_t));
 		}
 	}
 
 	/*
 	 * Grab our output buffer.
 	 */
-	nl = get_result_buffer(param, param_size, &len);
+	nl = orig_nl = get_result_buffer(param, param_size, &len);
 	if (len < needed) {
 		param->flags |= DM_BUFFER_FULL_FLAG;
 		goto out;
@@ -549,11 +551,16 @@
 			strcpy(nl->name, hc->name);
 
 			old_nl = nl;
-			event_nr = align_ptr(((void *) (nl + 1)) + strlen(hc->name) + 1);
+			event_nr = align_ptr(nl->name + strlen(hc->name) + 1);
 			*event_nr = dm_get_event_nr(hc->md);
 			nl = align_ptr(event_nr + 1);
 		}
 	}
+	/*
+	 * If mismatch happens, security may be compromised due to buffer
+	 * overflow, so it's better to crash.
+	 */
+	BUG_ON((char *)nl - (char *)orig_nl != needed);
 
  out:
 	up_write(&_hash_lock);
@@ -1621,7 +1628,8 @@
  * which has a variable size, is not used by the function processing
  * the ioctl.
  */
-#define IOCTL_FLAGS_NO_PARAMS	1
+#define IOCTL_FLAGS_NO_PARAMS		1
+#define IOCTL_FLAGS_ISSUE_GLOBAL_EVENT	2
 
 /*-----------------------------------------------------------------
  * Implementation of open/close/ioctl on the special char
@@ -1635,12 +1643,12 @@
 		ioctl_fn fn;
 	} _ioctls[] = {
 		{DM_VERSION_CMD, 0, NULL}, /* version is dealt with elsewhere */
-		{DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS, remove_all},
+		{DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, remove_all},
 		{DM_LIST_DEVICES_CMD, 0, list_devices},
 
-		{DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_create},
-		{DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_remove},
-		{DM_DEV_RENAME_CMD, 0, dev_rename},
+		{DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_create},
+		{DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_remove},
+		{DM_DEV_RENAME_CMD, IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_rename},
 		{DM_DEV_SUSPEND_CMD, IOCTL_FLAGS_NO_PARAMS, dev_suspend},
 		{DM_DEV_STATUS_CMD, IOCTL_FLAGS_NO_PARAMS, dev_status},
 		{DM_DEV_WAIT_CMD, 0, dev_wait},
@@ -1869,6 +1877,9 @@
 	    unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS))
 		DMERR("ioctl %d tried to output some data but has IOCTL_FLAGS_NO_PARAMS set", cmd);
 
+	if (!r && ioctl_flags & IOCTL_FLAGS_ISSUE_GLOBAL_EVENT)
+		dm_issue_global_event();
+
 	/*
 	 * Copy the results back to userland.
 	 */
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5bfe285..2245d06 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3238,7 +3238,7 @@
 	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
-	mddev->pers->make_request(mddev, bio);
+	md_handle_request(mddev, bio);
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -3297,11 +3297,10 @@
 static sector_t rs_get_progress(struct raid_set *rs,
 				sector_t resync_max_sectors, bool *array_in_sync)
 {
-	sector_t r, recovery_cp, curr_resync_completed;
+	sector_t r, curr_resync_completed;
 	struct mddev *mddev = &rs->md;
 
 	curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp;
-	recovery_cp = mddev->recovery_cp;
 	*array_in_sync = false;
 
 	if (rs_is_raid0(rs)) {
@@ -3330,9 +3329,11 @@
 		} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 			r = curr_resync_completed;
 		else
-			r = recovery_cp;
+			r = mddev->recovery_cp;
 
-		if (r == MaxSector) {
+		if ((r == MaxSector) ||
+		    (test_bit(MD_RECOVERY_DONE, &mddev->recovery) &&
+		     (mddev->curr_resync_completed == resync_max_sectors))) {
 			/*
 			 * Sync complete.
 			 */
@@ -3892,7 +3893,7 @@
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 12, 1},
+	.version = {1, 13, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6e54145..4be8532 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -52,6 +52,12 @@
 atomic_t dm_global_event_nr = ATOMIC_INIT(0);
 DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq);
 
+void dm_issue_global_event(void)
+{
+	atomic_inc(&dm_global_event_nr);
+	wake_up(&dm_global_eventq);
+}
+
 /*
  * One of these is allocated per bio.
  */
@@ -1865,9 +1871,8 @@
 	dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj);
 
 	atomic_inc(&md->event_nr);
-	atomic_inc(&dm_global_event_nr);
 	wake_up(&md->eventq);
-	wake_up(&dm_global_eventq);
+	dm_issue_global_event();
 }
 
 /*
@@ -2283,6 +2288,7 @@
 	}
 
 	map = __bind(md, table, &limits);
+	dm_issue_global_event();
 
 out:
 	mutex_unlock(&md->suspend_lock);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 08fcaeb..0ff1bbf 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -266,6 +266,37 @@
  * call has finished, the bio has been linked into some internal structure
  * and so is visible to ->quiesce(), so we don't need the refcount any more.
  */
+void md_handle_request(struct mddev *mddev, struct bio *bio)
+{
+check_suspended:
+	rcu_read_lock();
+	if (mddev->suspended) {
+		DEFINE_WAIT(__wait);
+		for (;;) {
+			prepare_to_wait(&mddev->sb_wait, &__wait,
+					TASK_UNINTERRUPTIBLE);
+			if (!mddev->suspended)
+				break;
+			rcu_read_unlock();
+			schedule();
+			rcu_read_lock();
+		}
+		finish_wait(&mddev->sb_wait, &__wait);
+	}
+	atomic_inc(&mddev->active_io);
+	rcu_read_unlock();
+
+	if (!mddev->pers->make_request(mddev, bio)) {
+		atomic_dec(&mddev->active_io);
+		wake_up(&mddev->sb_wait);
+		goto check_suspended;
+	}
+
+	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
+		wake_up(&mddev->sb_wait);
+}
+EXPORT_SYMBOL(md_handle_request);
+
 static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
@@ -285,23 +316,6 @@
 		bio_endio(bio);
 		return BLK_QC_T_NONE;
 	}
-check_suspended:
-	rcu_read_lock();
-	if (mddev->suspended) {
-		DEFINE_WAIT(__wait);
-		for (;;) {
-			prepare_to_wait(&mddev->sb_wait, &__wait,
-					TASK_UNINTERRUPTIBLE);
-			if (!mddev->suspended)
-				break;
-			rcu_read_unlock();
-			schedule();
-			rcu_read_lock();
-		}
-		finish_wait(&mddev->sb_wait, &__wait);
-	}
-	atomic_inc(&mddev->active_io);
-	rcu_read_unlock();
 
 	/*
 	 * save the sectors now since our bio can
@@ -310,20 +324,14 @@
 	sectors = bio_sectors(bio);
 	/* bio could be mergeable after passing to underlayer */
 	bio->bi_opf &= ~REQ_NOMERGE;
-	if (!mddev->pers->make_request(mddev, bio)) {
-		atomic_dec(&mddev->active_io);
-		wake_up(&mddev->sb_wait);
-		goto check_suspended;
-	}
+
+	md_handle_request(mddev, bio);
 
 	cpu = part_stat_lock();
 	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
 	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
 	part_stat_unlock();
 
-	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
-		wake_up(&mddev->sb_wait);
-
 	return BLK_QC_T_NONE;
 }
 
@@ -439,16 +447,22 @@
 	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
 	struct bio *bio = mddev->flush_bio;
 
+	/*
+	 * must reset flush_bio before calling into md_handle_request to avoid a
+	 * deadlock, because other bios passed md_handle_request suspend check
+	 * could wait for this and below md_handle_request could wait for those
+	 * bios because of suspend check
+	 */
+	mddev->flush_bio = NULL;
+	wake_up(&mddev->sb_wait);
+
 	if (bio->bi_iter.bi_size == 0)
 		/* an empty barrier - all done */
 		bio_endio(bio);
 	else {
 		bio->bi_opf &= ~REQ_PREFLUSH;
-		mddev->pers->make_request(mddev, bio);
+		md_handle_request(mddev, bio);
 	}
-
-	mddev->flush_bio = NULL;
-	wake_up(&mddev->sb_wait);
 }
 
 void md_flush_request(struct mddev *mddev, struct bio *bio)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 561d22b..d8287d3 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -692,6 +692,7 @@
 extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
+extern void md_handle_request(struct mddev *mddev, struct bio *bio);
 extern void mddev_suspend(struct mddev *mddev);
 extern void mddev_resume(struct mddev *mddev);
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 4188a48..928e24a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -811,6 +811,14 @@
 			spin_unlock(&head->batch_head->batch_lock);
 			goto unlock_out;
 		}
+		/*
+		 * We must assign batch_head of this stripe within the
+		 * batch_lock, otherwise clear_batch_ready of batch head
+		 * stripe could clear BATCH_READY bit of this stripe and
+		 * this stripe->batch_head doesn't get assigned, which
+		 * could confuse clear_batch_ready for this stripe
+		 */
+		sh->batch_head = head->batch_head;
 
 		/*
 		 * at this point, head's BATCH_READY could be cleared, but we
@@ -818,8 +826,6 @@
 		 */
 		list_add(&sh->batch_list, &head->batch_list);
 		spin_unlock(&head->batch_head->batch_lock);
-
-		sh->batch_head = head->batch_head;
 	} else {
 		head->batch_head = head;
 		sh->batch_head = head->batch_head;
@@ -4599,7 +4605,8 @@
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
 					    (1 << STRIPE_PREREAD_ACTIVE) |
-					    (1 << STRIPE_DEGRADED)),
+					    (1 << STRIPE_DEGRADED) |
+					    (1 << STRIPE_ON_UNPLUG_LIST)),
 			      head_sh->state & (1 << STRIPE_INSYNC));
 
 		sh->check_state = head_sh->check_state;
@@ -6568,14 +6575,17 @@
 raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
 {
 	struct r5conf *conf;
-	unsigned long new;
+	unsigned int new;
 	int err;
 	struct r5worker_group *new_groups, *old_groups;
 	int group_cnt, worker_cnt_per_group;
 
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
-	if (kstrtoul(page, 10, &new))
+	if (kstrtouint(page, 10, &new))
+		return -EINVAL;
+	/* 8192 should be big enough */
+	if (new > 8192)
 		return -EINVAL;
 
 	err = mddev_lock(mddev);
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index eed6c39..f8a808d 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -1797,12 +1797,19 @@
 	 */
 	switch (msg->msg[1]) {
 	case CEC_MSG_GET_CEC_VERSION:
-	case CEC_MSG_GIVE_DEVICE_VENDOR_ID:
 	case CEC_MSG_ABORT:
 	case CEC_MSG_GIVE_DEVICE_POWER_STATUS:
-	case CEC_MSG_GIVE_PHYSICAL_ADDR:
 	case CEC_MSG_GIVE_OSD_NAME:
+		/*
+		 * These messages reply with a directed message, so ignore if
+		 * the initiator is Unregistered.
+		 */
+		if (!adap->passthrough && from_unregistered)
+			return 0;
+		/* Fall through */
+	case CEC_MSG_GIVE_DEVICE_VENDOR_ID:
 	case CEC_MSG_GIVE_FEATURES:
+	case CEC_MSG_GIVE_PHYSICAL_ADDR:
 		/*
 		 * Skip processing these messages if the passthrough mode
 		 * is on.
@@ -1810,7 +1817,7 @@
 		if (adap->passthrough)
 			goto skip_processing;
 		/* Ignore if addressing is wrong */
-		if (is_broadcast || from_unregistered)
+		if (is_broadcast)
 			return 0;
 		break;
 
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index 2fcba16..9139d01 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -141,22 +141,39 @@
 static void dvb_frontend_invoke_release(struct dvb_frontend *fe,
 					void (*release)(struct dvb_frontend *fe));
 
-static void dvb_frontend_free(struct kref *ref)
+static void __dvb_frontend_free(struct dvb_frontend *fe)
 {
-	struct dvb_frontend *fe =
-		container_of(ref, struct dvb_frontend, refcount);
 	struct dvb_frontend_private *fepriv = fe->frontend_priv;
 
+	if (!fepriv)
+		return;
+
 	dvb_free_device(fepriv->dvbdev);
 
 	dvb_frontend_invoke_release(fe, fe->ops.release);
 
 	kfree(fepriv);
+	fe->frontend_priv = NULL;
+}
+
+static void dvb_frontend_free(struct kref *ref)
+{
+	struct dvb_frontend *fe =
+		container_of(ref, struct dvb_frontend, refcount);
+
+	__dvb_frontend_free(fe);
 }
 
 static void dvb_frontend_put(struct dvb_frontend *fe)
 {
-	kref_put(&fe->refcount, dvb_frontend_free);
+	/*
+	 * Check if the frontend was registered, as otherwise
+	 * kref was not initialized yet.
+	 */
+	if (fe->frontend_priv)
+		kref_put(&fe->refcount, dvb_frontend_free);
+	else
+		__dvb_frontend_free(fe);
 }
 
 static void dvb_frontend_get(struct dvb_frontend *fe)
diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c
index 224283f..4d086a7 100644
--- a/drivers/media/dvb-frontends/dib3000mc.c
+++ b/drivers/media/dvb-frontends/dib3000mc.c
@@ -55,29 +55,57 @@
 
 static u16 dib3000mc_read_word(struct dib3000mc_state *state, u16 reg)
 {
-	u8 wb[2] = { (reg >> 8) | 0x80, reg & 0xff };
-	u8 rb[2];
 	struct i2c_msg msg[2] = {
-		{ .addr = state->i2c_addr >> 1, .flags = 0,        .buf = wb, .len = 2 },
-		{ .addr = state->i2c_addr >> 1, .flags = I2C_M_RD, .buf = rb, .len = 2 },
+		{ .addr = state->i2c_addr >> 1, .flags = 0,        .len = 2 },
+		{ .addr = state->i2c_addr >> 1, .flags = I2C_M_RD, .len = 2 },
 	};
+	u16 word;
+	u8 *b;
+
+	b = kmalloc(4, GFP_KERNEL);
+	if (!b)
+		return 0;
+
+	b[0] = (reg >> 8) | 0x80;
+	b[1] = reg;
+	b[2] = 0;
+	b[3] = 0;
+
+	msg[0].buf = b;
+	msg[1].buf = b + 2;
 
 	if (i2c_transfer(state->i2c_adap, msg, 2) != 2)
 		dprintk("i2c read error on %d\n",reg);
 
-	return (rb[0] << 8) | rb[1];
+	word = (b[2] << 8) | b[3];
+	kfree(b);
+
+	return word;
 }
 
 static int dib3000mc_write_word(struct dib3000mc_state *state, u16 reg, u16 val)
 {
-	u8 b[4] = {
-		(reg >> 8) & 0xff, reg & 0xff,
-		(val >> 8) & 0xff, val & 0xff,
-	};
 	struct i2c_msg msg = {
-		.addr = state->i2c_addr >> 1, .flags = 0, .buf = b, .len = 4
+		.addr = state->i2c_addr >> 1, .flags = 0, .len = 4
 	};
-	return i2c_transfer(state->i2c_adap, &msg, 1) != 1 ? -EREMOTEIO : 0;
+	int rc;
+	u8 *b;
+
+	b = kmalloc(4, GFP_KERNEL);
+	if (!b)
+		return -ENOMEM;
+
+	b[0] = reg >> 8;
+	b[1] = reg;
+	b[2] = val >> 8;
+	b[3] = val;
+
+	msg.buf = b;
+
+	rc = i2c_transfer(state->i2c_adap, &msg, 1) != 1 ? -EREMOTEIO : 0;
+	kfree(b);
+
+	return rc;
 }
 
 static int dib3000mc_identify(struct dib3000mc_state *state)
diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c
index 7bec3e0..5553b89 100644
--- a/drivers/media/dvb-frontends/dvb-pll.c
+++ b/drivers/media/dvb-frontends/dvb-pll.c
@@ -753,13 +753,19 @@
 				    struct i2c_adapter *i2c,
 				    unsigned int pll_desc_id)
 {
-	u8 b1 [] = { 0 };
-	struct i2c_msg msg = { .addr = pll_addr, .flags = I2C_M_RD,
-			       .buf = b1, .len = 1 };
+	u8 *b1;
+	struct i2c_msg msg = { .addr = pll_addr, .flags = I2C_M_RD, .len = 1 };
 	struct dvb_pll_priv *priv = NULL;
 	int ret;
 	const struct dvb_pll_desc *desc;
 
+	b1 = kmalloc(1, GFP_KERNEL);
+	if (!b1)
+		return NULL;
+
+	b1[0] = 0;
+	msg.buf = b1;
+
 	if ((id[dvb_pll_devcount] > DVB_PLL_UNDEFINED) &&
 	    (id[dvb_pll_devcount] < ARRAY_SIZE(pll_list)))
 		pll_desc_id = id[dvb_pll_devcount];
@@ -773,15 +779,19 @@
 			fe->ops.i2c_gate_ctrl(fe, 1);
 
 		ret = i2c_transfer (i2c, &msg, 1);
-		if (ret != 1)
+		if (ret != 1) {
+			kfree(b1);
 			return NULL;
+		}
 		if (fe->ops.i2c_gate_ctrl)
 			     fe->ops.i2c_gate_ctrl(fe, 0);
 	}
 
 	priv = kzalloc(sizeof(struct dvb_pll_priv), GFP_KERNEL);
-	if (priv == NULL)
+	if (!priv) {
+		kfree(b1);
 		return NULL;
+	}
 
 	priv->pll_i2c_address = pll_addr;
 	priv->i2c = i2c;
@@ -811,6 +821,8 @@
 				"insmod option" : "autodetected");
 	}
 
+	kfree(b1);
+
 	return fe;
 }
 EXPORT_SYMBOL(dvb_pll_attach);
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 7e7cc49..3c4f7fa 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -112,7 +112,7 @@
 
 config VIDEO_QCOM_CAMSS
 	tristate "Qualcomm 8x16 V4L2 Camera Subsystem driver"
-	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && HAS_DMA
 	depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST
 	select VIDEOBUF2_DMA_SG
 	select V4L2_FWNODE
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c b/drivers/media/platform/qcom/camss-8x16/camss-vfe.c
index b21b3c2..b22d2df 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss-8x16/camss-vfe.c
@@ -2660,7 +2660,7 @@
  *
  * Return -EINVAL or zero on success
  */
-int vfe_set_selection(struct v4l2_subdev *sd,
+static int vfe_set_selection(struct v4l2_subdev *sd,
 			     struct v4l2_subdev_pad_config *cfg,
 			     struct v4l2_subdev_selection *sel)
 {
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 68933d2..9b2a401 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -682,6 +682,7 @@
 			hfi_session_abort(inst);
 
 		load_scale_clocks(core);
+		INIT_LIST_HEAD(&inst->registeredbufs);
 	}
 
 	venus_helper_buffers_done(inst, VB2_BUF_STATE_ERROR);
diff --git a/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c b/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c
index 1edf667..146ae6f 100644
--- a/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c
+++ b/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c
@@ -172,7 +172,8 @@
 {
 	u32 status = 0;
 
-	status = readb(cec->reg + S5P_CEC_STATUS_0);
+	status = readb(cec->reg + S5P_CEC_STATUS_0) & 0xf;
+	status |= (readb(cec->reg + S5P_CEC_TX_STAT1) & 0xf) << 4;
 	status |= readb(cec->reg + S5P_CEC_STATUS_1) << 8;
 	status |= readb(cec->reg + S5P_CEC_STATUS_2) << 16;
 	status |= readb(cec->reg + S5P_CEC_STATUS_3) << 24;
diff --git a/drivers/media/platform/s5p-cec/s5p_cec.c b/drivers/media/platform/s5p-cec/s5p_cec.c
index 58d200e..8837e26 100644
--- a/drivers/media/platform/s5p-cec/s5p_cec.c
+++ b/drivers/media/platform/s5p-cec/s5p_cec.c
@@ -92,7 +92,10 @@
 	dev_dbg(cec->dev, "irq received\n");
 
 	if (status & CEC_STATUS_TX_DONE) {
-		if (status & CEC_STATUS_TX_ERROR) {
+		if (status & CEC_STATUS_TX_NACK) {
+			dev_dbg(cec->dev, "CEC_STATUS_TX_NACK set\n");
+			cec->tx = STATE_NACK;
+		} else if (status & CEC_STATUS_TX_ERROR) {
 			dev_dbg(cec->dev, "CEC_STATUS_TX_ERROR set\n");
 			cec->tx = STATE_ERROR;
 		} else {
@@ -135,6 +138,12 @@
 		cec_transmit_done(cec->adap, CEC_TX_STATUS_OK, 0, 0, 0, 0);
 		cec->tx = STATE_IDLE;
 		break;
+	case STATE_NACK:
+		cec_transmit_done(cec->adap,
+			CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_NACK,
+			0, 1, 0, 0);
+		cec->tx = STATE_IDLE;
+		break;
 	case STATE_ERROR:
 		cec_transmit_done(cec->adap,
 			CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_ERROR,
diff --git a/drivers/media/platform/s5p-cec/s5p_cec.h b/drivers/media/platform/s5p-cec/s5p_cec.h
index 8bcd8dc..86ded522 100644
--- a/drivers/media/platform/s5p-cec/s5p_cec.h
+++ b/drivers/media/platform/s5p-cec/s5p_cec.h
@@ -35,6 +35,7 @@
 #define CEC_STATUS_TX_TRANSFERRING	(1 << 1)
 #define CEC_STATUS_TX_DONE		(1 << 2)
 #define CEC_STATUS_TX_ERROR		(1 << 3)
+#define CEC_STATUS_TX_NACK		(1 << 4)
 #define CEC_STATUS_TX_BYTES		(0xFF << 8)
 #define CEC_STATUS_RX_RUNNING		(1 << 16)
 #define CEC_STATUS_RX_RECEIVING		(1 << 17)
@@ -55,6 +56,7 @@
 	STATE_IDLE,
 	STATE_BUSY,
 	STATE_DONE,
+	STATE_NACK,
 	STATE_ERROR
 };
 
diff --git a/drivers/media/rc/ir-sharp-decoder.c b/drivers/media/rc/ir-sharp-decoder.c
index ed43a42..129b558 100644
--- a/drivers/media/rc/ir-sharp-decoder.c
+++ b/drivers/media/rc/ir-sharp-decoder.c
@@ -245,5 +245,5 @@
 module_exit(ir_sharp_decode_exit);
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("James Hogan <james.hogan@imgtec.com>");
+MODULE_AUTHOR("James Hogan <jhogan@kernel.org>");
 MODULE_DESCRIPTION("Sharp IR protocol decoder");
diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c
index 2e487f9..4983eeb 100644
--- a/drivers/media/tuners/mt2060.c
+++ b/drivers/media/tuners/mt2060.c
@@ -38,41 +38,74 @@
 static int mt2060_readreg(struct mt2060_priv *priv, u8 reg, u8 *val)
 {
 	struct i2c_msg msg[2] = {
-		{ .addr = priv->cfg->i2c_address, .flags = 0,        .buf = &reg, .len = 1 },
-		{ .addr = priv->cfg->i2c_address, .flags = I2C_M_RD, .buf = val,  .len = 1 },
+		{ .addr = priv->cfg->i2c_address, .flags = 0, .len = 1 },
+		{ .addr = priv->cfg->i2c_address, .flags = I2C_M_RD, .len = 1 },
 	};
+	int rc = 0;
+	u8 *b;
+
+	b = kmalloc(2, GFP_KERNEL);
+	if (!b)
+		return -ENOMEM;
+
+	b[0] = reg;
+	b[1] = 0;
+
+	msg[0].buf = b;
+	msg[1].buf = b + 1;
 
 	if (i2c_transfer(priv->i2c, msg, 2) != 2) {
 		printk(KERN_WARNING "mt2060 I2C read failed\n");
-		return -EREMOTEIO;
+		rc = -EREMOTEIO;
 	}
-	return 0;
+	*val = b[1];
+	kfree(b);
+
+	return rc;
 }
 
 // Writes a single register
 static int mt2060_writereg(struct mt2060_priv *priv, u8 reg, u8 val)
 {
-	u8 buf[2] = { reg, val };
 	struct i2c_msg msg = {
-		.addr = priv->cfg->i2c_address, .flags = 0, .buf = buf, .len = 2
+		.addr = priv->cfg->i2c_address, .flags = 0, .len = 2
 	};
+	u8 *buf;
+	int rc = 0;
+
+	buf = kmalloc(2, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf[0] = reg;
+	buf[1] = val;
+
+	msg.buf = buf;
 
 	if (i2c_transfer(priv->i2c, &msg, 1) != 1) {
 		printk(KERN_WARNING "mt2060 I2C write failed\n");
-		return -EREMOTEIO;
+		rc = -EREMOTEIO;
 	}
-	return 0;
+	kfree(buf);
+	return rc;
 }
 
 // Writes a set of consecutive registers
 static int mt2060_writeregs(struct mt2060_priv *priv,u8 *buf, u8 len)
 {
 	int rem, val_len;
-	u8 xfer_buf[16];
+	u8 *xfer_buf;
+	int rc = 0;
 	struct i2c_msg msg = {
-		.addr = priv->cfg->i2c_address, .flags = 0, .buf = xfer_buf
+		.addr = priv->cfg->i2c_address, .flags = 0
 	};
 
+	xfer_buf = kmalloc(16, GFP_KERNEL);
+	if (!xfer_buf)
+		return -ENOMEM;
+
+	msg.buf = xfer_buf;
+
 	for (rem = len - 1; rem > 0; rem -= priv->i2c_max_regs) {
 		val_len = min_t(int, rem, priv->i2c_max_regs);
 		msg.len = 1 + val_len;
@@ -81,11 +114,13 @@
 
 		if (i2c_transfer(priv->i2c, &msg, 1) != 1) {
 			printk(KERN_WARNING "mt2060 I2C write failed (len=%i)\n", val_len);
-			return -EREMOTEIO;
+			rc = -EREMOTEIO;
+			break;
 		}
 	}
 
-	return 0;
+	kfree(xfer_buf);
+	return rc;
 }
 
 // Initialisation sequences
diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c
index 5dba23c..dc9bc18 100644
--- a/drivers/misc/cxl/cxllib.c
+++ b/drivers/misc/cxl/cxllib.c
@@ -219,8 +219,17 @@
 
 	down_read(&mm->mmap_sem);
 
-	for (dar = addr; dar < addr + size; dar += page_size) {
-		if (!vma || dar < vma->vm_start || dar > vma->vm_end) {
+	vma = find_vma(mm, addr);
+	if (!vma) {
+		pr_err("Can't find vma for addr %016llx\n", addr);
+		rc = -EFAULT;
+		goto out;
+	}
+	/* get the size of the pages allocated */
+	page_size = vma_kernel_pagesize(vma);
+
+	for (dar = (addr & ~(page_size - 1)); dar < (addr + size); dar += page_size) {
+		if (dar < vma->vm_start || dar >= vma->vm_end) {
 			vma = find_vma(mm, addr);
 			if (!vma) {
 				pr_err("Can't find vma for addr %016llx\n", addr);
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index c8307e8..0ccccba 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -127,6 +127,8 @@
 #define MEI_DEV_ID_BXT_M      0x1A9A  /* Broxton M */
 #define MEI_DEV_ID_APL_I      0x5A9A  /* Apollo Lake I */
 
+#define MEI_DEV_ID_GLK        0x319A  /* Gemini Lake */
+
 #define MEI_DEV_ID_KBP        0xA2BA  /* Kaby Point */
 #define MEI_DEV_ID_KBP_2      0xA2BB  /* Kaby Point 2 */
 
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 4ff40d3..78b3172 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -93,6 +93,8 @@
 	{MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_GLK, MEI_ME_PCH8_CFG)},
+
 	{MEI_PCI_DEVICE(MEI_DEV_ID_KBP, MEI_ME_PCH8_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, MEI_ME_PCH8_CFG)},
 
@@ -226,12 +228,15 @@
 	pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
 
 	/*
-	* For not wake-able HW runtime pm framework
-	* can't be used on pci device level.
-	* Use domain runtime pm callbacks instead.
-	*/
-	if (!pci_dev_run_wake(pdev))
-		mei_me_set_pm_domain(dev);
+	 * ME maps runtime suspend/resume to D0i states,
+	 * hence we need to go around native PCI runtime service which
+	 * eventually brings the device into D3cold/hot state,
+	 * but the mei device cannot wake up from D3 unlike from D0i3.
+	 * To get around the PCI device native runtime pm,
+	 * ME uses runtime pm domain handlers which take precedence
+	 * over the driver's pm handlers.
+	 */
+	mei_me_set_pm_domain(dev);
 
 	if (mei_pg_is_enabled(dev))
 		pm_runtime_put_noidle(&pdev->dev);
@@ -271,8 +276,7 @@
 	dev_dbg(&pdev->dev, "shutdown\n");
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
-		mei_me_unset_pm_domain(dev);
+	mei_me_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
@@ -300,8 +304,7 @@
 	dev_dbg(&pdev->dev, "stop\n");
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
-		mei_me_unset_pm_domain(dev);
+	mei_me_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 
diff --git a/drivers/misc/mei/pci-txe.c b/drivers/misc/mei/pci-txe.c
index e38a5f1..0566f9b 100644
--- a/drivers/misc/mei/pci-txe.c
+++ b/drivers/misc/mei/pci-txe.c
@@ -144,12 +144,14 @@
 	pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
 
 	/*
-	* For not wake-able HW runtime pm framework
-	* can't be used on pci device level.
-	* Use domain runtime pm callbacks instead.
-	*/
-	if (!pci_dev_run_wake(pdev))
-		mei_txe_set_pm_domain(dev);
+	 * TXE maps runtime suspend/resume to own power gating states,
+	 * hence we need to go around native PCI runtime service which
+	 * eventually brings the device into D3cold/hot state.
+	 * But the TXE device cannot wake up from D3 unlike from own
+	 * power gating. To get around PCI device native runtime pm,
+	 * TXE uses runtime pm domain handlers which take precedence.
+	 */
+	mei_txe_set_pm_domain(dev);
 
 	pm_runtime_put_noidle(&pdev->dev);
 
@@ -186,8 +188,7 @@
 	dev_dbg(&pdev->dev, "shutdown\n");
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
-		mei_txe_unset_pm_domain(dev);
+	mei_txe_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
@@ -215,8 +216,7 @@
 
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
-		mei_txe_unset_pm_domain(dev);
+	mei_txe_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
@@ -318,15 +318,7 @@
 	else
 		ret = -EAGAIN;
 
-	/*
-	 * If everything is okay we're about to enter PCI low
-	 * power state (D3) therefor we need to disable the
-	 * interrupts towards host.
-	 * However if device is not wakeable we do not enter
-	 * D-low state and we need to keep the interrupt kicking
-	 */
-	if (!ret && pci_dev_run_wake(pdev))
-		mei_disable_interrupts(dev);
+	/* keep irq on we are staying in D0 */
 
 	dev_dbg(&pdev->dev, "rpm: txe: runtime suspend ret=%d\n", ret);
 
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 29fc1e6..2ad7b5c 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1634,8 +1634,6 @@
 	}
 
 	mqrq->areq.mrq = &brq->mrq;
-
-	mmc_queue_bounce_pre(mqrq);
 }
 
 static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
@@ -1829,7 +1827,6 @@
 		brq = &mq_rq->brq;
 		old_req = mmc_queue_req_to_req(mq_rq);
 		type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
-		mmc_queue_bounce_post(mq_rq);
 
 		switch (status) {
 		case MMC_BLK_SUCCESS:
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index a7eb623..36217ad 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1286,6 +1286,23 @@
 	return err;
 }
 
+static void mmc_select_driver_type(struct mmc_card *card)
+{
+	int card_drv_type, drive_strength, drv_type;
+
+	card_drv_type = card->ext_csd.raw_driver_strength |
+			mmc_driver_type_mask(0);
+
+	drive_strength = mmc_select_drive_strength(card,
+						   card->ext_csd.hs200_max_dtr,
+						   card_drv_type, &drv_type);
+
+	card->drive_strength = drive_strength;
+
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
+}
+
 static int mmc_select_hs400es(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
@@ -1341,6 +1358,8 @@
 		goto out_err;
 	}
 
+	mmc_select_driver_type(card);
+
 	/* Switch card to HS400 */
 	val = EXT_CSD_TIMING_HS400 |
 	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
@@ -1374,23 +1393,6 @@
 	return err;
 }
 
-static void mmc_select_driver_type(struct mmc_card *card)
-{
-	int card_drv_type, drive_strength, drv_type;
-
-	card_drv_type = card->ext_csd.raw_driver_strength |
-			mmc_driver_type_mask(0);
-
-	drive_strength = mmc_select_drive_strength(card,
-						   card->ext_csd.hs200_max_dtr,
-						   card_drv_type, &drv_type);
-
-	card->drive_strength = drive_strength;
-
-	if (drv_type)
-		mmc_set_driver_type(card->host, drv_type);
-}
-
 /*
  * For device supporting HS200 mode, the following sequence
  * should be done before executing the tuning process.
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index affa737..0a4e77a 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -23,8 +23,6 @@
 #include "core.h"
 #include "card.h"
 
-#define MMC_QUEUE_BOUNCESZ	65536
-
 /*
  * Prepare a MMC request. This just filters out odd stuff.
  */
@@ -150,26 +148,6 @@
 		queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q);
 }
 
-static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host)
-{
-	unsigned int bouncesz = MMC_QUEUE_BOUNCESZ;
-
-	if (host->max_segs != 1 || (host->caps & MMC_CAP_NO_BOUNCE_BUFF))
-		return 0;
-
-	if (bouncesz > host->max_req_size)
-		bouncesz = host->max_req_size;
-	if (bouncesz > host->max_seg_size)
-		bouncesz = host->max_seg_size;
-	if (bouncesz > host->max_blk_count * 512)
-		bouncesz = host->max_blk_count * 512;
-
-	if (bouncesz <= 512)
-		return 0;
-
-	return bouncesz;
-}
-
 /**
  * mmc_init_request() - initialize the MMC-specific per-request data
  * @q: the request queue
@@ -184,26 +162,9 @@
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 
-	if (card->bouncesz) {
-		mq_rq->bounce_buf = kmalloc(card->bouncesz, gfp);
-		if (!mq_rq->bounce_buf)
-			return -ENOMEM;
-		if (card->bouncesz > 512) {
-			mq_rq->sg = mmc_alloc_sg(1, gfp);
-			if (!mq_rq->sg)
-				return -ENOMEM;
-			mq_rq->bounce_sg = mmc_alloc_sg(card->bouncesz / 512,
-							gfp);
-			if (!mq_rq->bounce_sg)
-				return -ENOMEM;
-		}
-	} else {
-		mq_rq->bounce_buf = NULL;
-		mq_rq->bounce_sg = NULL;
-		mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp);
-		if (!mq_rq->sg)
-			return -ENOMEM;
-	}
+	mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp);
+	if (!mq_rq->sg)
+		return -ENOMEM;
 
 	return 0;
 }
@@ -212,13 +173,6 @@
 {
 	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
 
-	/* It is OK to kfree(NULL) so this will be smooth */
-	kfree(mq_rq->bounce_sg);
-	mq_rq->bounce_sg = NULL;
-
-	kfree(mq_rq->bounce_buf);
-	mq_rq->bounce_buf = NULL;
-
 	kfree(mq_rq->sg);
 	mq_rq->sg = NULL;
 }
@@ -265,18 +219,11 @@
 	if (mmc_can_erase(card))
 		mmc_queue_setup_discard(mq->queue, card);
 
-	card->bouncesz = mmc_queue_calc_bouncesz(host);
-	if (card->bouncesz) {
-		blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512);
-		blk_queue_max_segments(mq->queue, card->bouncesz / 512);
-		blk_queue_max_segment_size(mq->queue, card->bouncesz);
-	} else {
-		blk_queue_bounce_limit(mq->queue, limit);
-		blk_queue_max_hw_sectors(mq->queue,
-			min(host->max_blk_count, host->max_req_size / 512));
-		blk_queue_max_segments(mq->queue, host->max_segs);
-		blk_queue_max_segment_size(mq->queue, host->max_seg_size);
-	}
+	blk_queue_bounce_limit(mq->queue, limit);
+	blk_queue_max_hw_sectors(mq->queue,
+		min(host->max_blk_count, host->max_req_size / 512));
+	blk_queue_max_segments(mq->queue, host->max_segs);
+	blk_queue_max_segment_size(mq->queue, host->max_seg_size);
 
 	sema_init(&mq->thread_sem, 1);
 
@@ -365,56 +312,7 @@
  */
 unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
 {
-	unsigned int sg_len;
-	size_t buflen;
-	struct scatterlist *sg;
 	struct request *req = mmc_queue_req_to_req(mqrq);
-	int i;
 
-	if (!mqrq->bounce_buf)
-		return blk_rq_map_sg(mq->queue, req, mqrq->sg);
-
-	sg_len = blk_rq_map_sg(mq->queue, req, mqrq->bounce_sg);
-
-	mqrq->bounce_sg_len = sg_len;
-
-	buflen = 0;
-	for_each_sg(mqrq->bounce_sg, sg, sg_len, i)
-		buflen += sg->length;
-
-	sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen);
-
-	return 1;
-}
-
-/*
- * If writing, bounce the data to the buffer before the request
- * is sent to the host driver
- */
-void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq)
-{
-	if (!mqrq->bounce_buf)
-		return;
-
-	if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != WRITE)
-		return;
-
-	sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
-		mqrq->bounce_buf, mqrq->sg[0].length);
-}
-
-/*
- * If reading, bounce the data from the buffer after the request
- * has been handled by the host driver
- */
-void mmc_queue_bounce_post(struct mmc_queue_req *mqrq)
-{
-	if (!mqrq->bounce_buf)
-		return;
-
-	if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != READ)
-		return;
-
-	sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
-		mqrq->bounce_buf, mqrq->sg[0].length);
+	return blk_rq_map_sg(mq->queue, req, mqrq->sg);
 }
diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h
index 04fc893..f18d3f6 100644
--- a/drivers/mmc/core/queue.h
+++ b/drivers/mmc/core/queue.h
@@ -49,9 +49,6 @@
 struct mmc_queue_req {
 	struct mmc_blk_request	brq;
 	struct scatterlist	*sg;
-	char			*bounce_buf;
-	struct scatterlist	*bounce_sg;
-	unsigned int		bounce_sg_len;
 	struct mmc_async_req	areq;
 	enum mmc_drv_op		drv_op;
 	int			drv_op_result;
@@ -81,11 +78,8 @@
 extern void mmc_cleanup_queue(struct mmc_queue *);
 extern void mmc_queue_suspend(struct mmc_queue *);
 extern void mmc_queue_resume(struct mmc_queue *);
-
 extern unsigned int mmc_queue_map_sg(struct mmc_queue *,
 				     struct mmc_queue_req *);
-extern void mmc_queue_bounce_pre(struct mmc_queue_req *);
-extern void mmc_queue_bounce_post(struct mmc_queue_req *);
 
 extern int mmc_access_rpmb(struct mmc_queue *);
 
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 02179ed..8c15637 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -5,7 +5,7 @@
 comment "MMC/SD/SDIO Host Controller Drivers"
 
 config MMC_DEBUG
-	bool "MMC host drivers debugginG"
+	bool "MMC host drivers debugging"
 	depends on MMC != n
 	help
 	  This is an option for use by developers; most people should
diff --git a/drivers/mmc/host/cavium-thunderx.c b/drivers/mmc/host/cavium-thunderx.c
index b9cc959..eee08d8 100644
--- a/drivers/mmc/host/cavium-thunderx.c
+++ b/drivers/mmc/host/cavium-thunderx.c
@@ -7,6 +7,7 @@
  *
  * Copyright (C) 2016 Cavium Inc.
  */
+#include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/mmc/mmc.h>
@@ -149,8 +150,11 @@
 	for (i = 0; i < CAVIUM_MAX_MMC; i++) {
 		if (host->slot[i])
 			cvm_mmc_of_slot_remove(host->slot[i]);
-		if (host->slot_pdev[i])
+		if (host->slot_pdev[i]) {
+			get_device(&host->slot_pdev[i]->dev);
 			of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+			put_device(&host->slot_pdev[i]->dev);
+		}
 	}
 	clk_disable_unprepare(host->clk);
 	return ret;
diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c
index 27fb625..fbd29f0 100644
--- a/drivers/mmc/host/cavium.c
+++ b/drivers/mmc/host/cavium.c
@@ -1038,7 +1038,7 @@
 	 */
 	mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
 		     MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_POWER_OFF_CARD |
-		     MMC_CAP_3_3V_DDR | MMC_CAP_NO_BOUNCE_BUFF;
+		     MMC_CAP_3_3V_DDR;
 
 	if (host->use_sg)
 		mmc->max_segs = 16;
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index c885c2d..85745ef 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -531,8 +531,7 @@
 	div->shift = __ffs(CLK_DIV_MASK);
 	div->width = __builtin_popcountl(CLK_DIV_MASK);
 	div->hw.init = &init;
-	div->flags = (CLK_DIVIDER_ONE_BASED |
-		      CLK_DIVIDER_ROUND_CLOSEST);
+	div->flags = CLK_DIVIDER_ONE_BASED;
 
 	clk = devm_clk_register(host->dev, &div->hw);
 	if (WARN_ON(IS_ERR(clk)))
@@ -717,6 +716,22 @@
 static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct meson_host *host = mmc_priv(mmc);
+	int ret;
+
+	/*
+	 * If this is the initial tuning, try to get a sane Rx starting
+	 * phase before doing the actual tuning.
+	 */
+	if (!mmc->doing_retune) {
+		ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk);
+
+		if (ret)
+			return ret;
+	}
+
+	ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk);
+	if (ret)
+		return ret;
 
 	return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk);
 }
@@ -746,6 +761,11 @@
 	case MMC_POWER_UP:
 		if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);
+
+		/* Reset phases */
+		clk_set_phase(host->rx_clk, 0);
+		clk_set_phase(host->tx_clk, 270);
+
 		break;
 
 	case MMC_POWER_ON:
@@ -759,8 +779,6 @@
 				host->vqmmc_enabled = true;
 		}
 
-		/* Reset rx phase */
-		clk_set_phase(host->rx_clk, 0);
 		break;
 	}
 
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 59ab194..c763b40 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -702,11 +702,7 @@
 
 	pxamci_init_ocr(host);
 
-	/*
-	 * This architecture used to disable bounce buffers through its
-	 * defconfig, now it is done at runtime as a host property.
-	 */
-	mmc->caps = MMC_CAP_NO_BOUNCE_BUFF;
+	mmc->caps = 0;
 	host->cmdat = 0;
 	if (!cpu_is_pxa25x()) {
 		mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ;
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index bbaddf1..67d787f 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -392,6 +392,7 @@
 
 enum {
 	INTEL_DSM_FNS		=  0,
+	INTEL_DSM_V18_SWITCH	=  3,
 	INTEL_DSM_DRV_STRENGTH	=  9,
 	INTEL_DSM_D3_RETUNE	= 10,
 };
@@ -447,6 +448,8 @@
 	int err;
 	u32 val;
 
+	intel_host->d3_retune = true;
+
 	err = __intel_dsm(intel_host, dev, INTEL_DSM_FNS, &intel_host->dsm_fns);
 	if (err) {
 		pr_debug("%s: DSM not supported, error %d\n",
@@ -557,6 +560,19 @@
 	sdhci_writel(host, val, INTEL_HS400_ES_REG);
 }
 
+static void sdhci_intel_voltage_switch(struct sdhci_host *host)
+{
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	struct intel_host *intel_host = sdhci_pci_priv(slot);
+	struct device *dev = &slot->chip->pdev->dev;
+	u32 result = 0;
+	int err;
+
+	err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result);
+	pr_debug("%s: %s DSM error %d result %u\n",
+		 mmc_hostname(host->mmc), __func__, err, result);
+}
+
 static const struct sdhci_ops sdhci_intel_byt_ops = {
 	.set_clock		= sdhci_set_clock,
 	.set_power		= sdhci_intel_set_power,
@@ -565,6 +581,7 @@
 	.reset			= sdhci_reset,
 	.set_uhs_signaling	= sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
+	.voltage_switch		= sdhci_intel_voltage_switch,
 };
 
 static void byt_read_dsm(struct sdhci_pci_slot *slot)
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 2eec2e6..0842bbc 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -466,6 +466,7 @@
 {
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_host *host;
+	struct xenon_priv *priv;
 	int err;
 
 	host = sdhci_pltfm_init(pdev, &sdhci_xenon_pdata,
@@ -474,6 +475,7 @@
 		return PTR_ERR(host);
 
 	pltfm_host = sdhci_priv(host);
+	priv = sdhci_pltfm_priv(pltfm_host);
 
 	/*
 	 * Link Xenon specific mmc_host_ops function,
@@ -491,9 +493,20 @@
 	if (err)
 		goto free_pltfm;
 
+	priv->axi_clk = devm_clk_get(&pdev->dev, "axi");
+	if (IS_ERR(priv->axi_clk)) {
+		err = PTR_ERR(priv->axi_clk);
+		if (err == -EPROBE_DEFER)
+			goto err_clk;
+	} else {
+		err = clk_prepare_enable(priv->axi_clk);
+		if (err)
+			goto err_clk;
+	}
+
 	err = mmc_of_parse(host->mmc);
 	if (err)
-		goto err_clk;
+		goto err_clk_axi;
 
 	sdhci_get_of_property(pdev);
 
@@ -502,11 +515,11 @@
 	/* Xenon specific dt parse */
 	err = xenon_probe_dt(pdev);
 	if (err)
-		goto err_clk;
+		goto err_clk_axi;
 
 	err = xenon_sdhc_prepare(host);
 	if (err)
-		goto err_clk;
+		goto err_clk_axi;
 
 	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
@@ -527,6 +540,8 @@
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
 	xenon_sdhc_unprepare(host);
+err_clk_axi:
+	clk_disable_unprepare(priv->axi_clk);
 err_clk:
 	clk_disable_unprepare(pltfm_host->clk);
 free_pltfm:
@@ -538,6 +553,7 @@
 {
 	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 
 	pm_runtime_get_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
@@ -546,7 +562,7 @@
 	sdhci_remove_host(host, 0);
 
 	xenon_sdhc_unprepare(host);
-
+	clk_disable_unprepare(priv->axi_clk);
 	clk_disable_unprepare(pltfm_host->clk);
 
 	sdhci_pltfm_free(pdev);
diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h
index 2bc0510..9994995 100644
--- a/drivers/mmc/host/sdhci-xenon.h
+++ b/drivers/mmc/host/sdhci-xenon.h
@@ -83,6 +83,7 @@
 	unsigned char	bus_width;
 	unsigned char	timing;
 	unsigned int	clock;
+	struct clk      *axi_clk;
 
 	int		phy_type;
 	/*
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 12cf828..a7293e1 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -129,50 +129,6 @@
 
 #define CMDREQ_TIMEOUT	5000
 
-#ifdef CONFIG_MMC_DEBUG
-
-#define STATUS_TO_TEXT(a, status, i) \
-	do { \
-		if ((status) & TMIO_STAT_##a) { \
-			if ((i)++) \
-				printk(KERN_DEBUG " | "); \
-			printk(KERN_DEBUG #a); \
-		} \
-	} while (0)
-
-static void pr_debug_status(u32 status)
-{
-	int i = 0;
-
-	pr_debug("status: %08x = ", status);
-	STATUS_TO_TEXT(CARD_REMOVE, status, i);
-	STATUS_TO_TEXT(CARD_INSERT, status, i);
-	STATUS_TO_TEXT(SIGSTATE, status, i);
-	STATUS_TO_TEXT(WRPROTECT, status, i);
-	STATUS_TO_TEXT(CARD_REMOVE_A, status, i);
-	STATUS_TO_TEXT(CARD_INSERT_A, status, i);
-	STATUS_TO_TEXT(SIGSTATE_A, status, i);
-	STATUS_TO_TEXT(CMD_IDX_ERR, status, i);
-	STATUS_TO_TEXT(STOPBIT_ERR, status, i);
-	STATUS_TO_TEXT(ILL_FUNC, status, i);
-	STATUS_TO_TEXT(CMD_BUSY, status, i);
-	STATUS_TO_TEXT(CMDRESPEND, status, i);
-	STATUS_TO_TEXT(DATAEND, status, i);
-	STATUS_TO_TEXT(CRCFAIL, status, i);
-	STATUS_TO_TEXT(DATATIMEOUT, status, i);
-	STATUS_TO_TEXT(CMDTIMEOUT, status, i);
-	STATUS_TO_TEXT(RXOVERFLOW, status, i);
-	STATUS_TO_TEXT(TXUNDERRUN, status, i);
-	STATUS_TO_TEXT(RXRDY, status, i);
-	STATUS_TO_TEXT(TXRQ, status, i);
-	STATUS_TO_TEXT(ILL_ACCESS, status, i);
-	printk("\n");
-}
-
-#else
-#define pr_debug_status(s)  do { } while (0)
-#endif
-
 static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
@@ -762,9 +718,6 @@
 	status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS);
 	ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask;
 
-	pr_debug_status(status);
-	pr_debug_status(ireg);
-
 	/* Clear the status except the interrupt status */
 	sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ);
 
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 5736b0c..a308e70 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -581,6 +581,14 @@
 		slave->mtd.erasesize = parent->erasesize;
 	}
 
+	/*
+	 * Slave erasesize might differ from the master one if the master
+	 * exposes several regions with different erasesize. Adjust
+	 * wr_alignment accordingly.
+	 */
+	if (!(slave->mtd.flags & MTD_NO_ERASE))
+		wr_alignment = slave->mtd.erasesize;
+
 	tmp = slave->offset;
 	remainder = do_div(tmp, wr_alignment);
 	if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) {
diff --git a/drivers/mtd/nand/atmel/pmecc.c b/drivers/mtd/nand/atmel/pmecc.c
index 146af821..8268636 100644
--- a/drivers/mtd/nand/atmel/pmecc.c
+++ b/drivers/mtd/nand/atmel/pmecc.c
@@ -363,7 +363,7 @@
 	size += (req->ecc.strength + 1) * sizeof(u16);
 	/* Reserve space for mu, dmu and delta. */
 	size = ALIGN(size, sizeof(s32));
-	size += (req->ecc.strength + 1) * sizeof(s32);
+	size += (req->ecc.strength + 1) * sizeof(s32) * 3;
 
 	user = kzalloc(size, GFP_KERNEL);
 	if (!user)
diff --git a/drivers/mtd/nand/lpc32xx_mlc.c b/drivers/mtd/nand/lpc32xx_mlc.c
index c3bb358..5796468 100644
--- a/drivers/mtd/nand/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/lpc32xx_mlc.c
@@ -707,7 +707,7 @@
 	}
 	res = clk_prepare_enable(host->clk);
 	if (res)
-		goto err_exit1;
+		goto err_put_clk;
 
 	nand_chip->cmd_ctrl = lpc32xx_nand_cmd_ctrl;
 	nand_chip->dev_ready = lpc32xx_nand_device_ready;
@@ -814,6 +814,7 @@
 		dma_release_channel(host->dma_chan);
 err_exit2:
 	clk_disable_unprepare(host->clk);
+err_put_clk:
 	clk_put(host->clk);
 err_exit1:
 	lpc32xx_wp_enable(host);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index bcc8cef1..12edaae 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2668,7 +2668,7 @@
 static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 			     struct mtd_oob_ops *ops)
 {
-	int chipnr, realpage, page, blockmask, column;
+	int chipnr, realpage, page, column;
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	uint32_t writelen = ops->len;
 
@@ -2704,7 +2704,6 @@
 
 	realpage = (int)(to >> chip->page_shift);
 	page = realpage & chip->pagemask;
-	blockmask = (1 << (chip->phys_erase_shift - chip->page_shift)) - 1;
 
 	/* Invalidate the page cache, when we write to the cached page */
 	if (to <= ((loff_t)chip->pagebuf << chip->page_shift) &&
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index cf1d4a1..19c00072 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -1784,7 +1784,7 @@
  * @nor:	pointer to a 'struct spi_nor'
  * @addr:	offset in the SFDP area to start reading data from
  * @len:	number of bytes to read
- * @buf:	buffer where the SFDP data are copied into
+ * @buf:	buffer where the SFDP data are copied into (dma-safe memory)
  *
  * Whatever the actual numbers of bytes for address and dummy cycles are
  * for (Fast) Read commands, the Read SFDP (5Ah) instruction is always
@@ -1829,6 +1829,36 @@
 	return ret;
 }
 
+/**
+ * spi_nor_read_sfdp_dma_unsafe() - read Serial Flash Discoverable Parameters.
+ * @nor:	pointer to a 'struct spi_nor'
+ * @addr:	offset in the SFDP area to start reading data from
+ * @len:	number of bytes to read
+ * @buf:	buffer where the SFDP data are copied into
+ *
+ * Wrap spi_nor_read_sfdp() using a kmalloc'ed bounce buffer as @buf is now not
+ * guaranteed to be dma-safe.
+ *
+ * Return: -ENOMEM if kmalloc() fails, the return code of spi_nor_read_sfdp()
+ *          otherwise.
+ */
+static int spi_nor_read_sfdp_dma_unsafe(struct spi_nor *nor, u32 addr,
+					size_t len, void *buf)
+{
+	void *dma_safe_buf;
+	int ret;
+
+	dma_safe_buf = kmalloc(len, GFP_KERNEL);
+	if (!dma_safe_buf)
+		return -ENOMEM;
+
+	ret = spi_nor_read_sfdp(nor, addr, len, dma_safe_buf);
+	memcpy(buf, dma_safe_buf, len);
+	kfree(dma_safe_buf);
+
+	return ret;
+}
+
 struct sfdp_parameter_header {
 	u8		id_lsb;
 	u8		minor;
@@ -2101,7 +2131,7 @@
 		    bfpt_header->length * sizeof(u32));
 	addr = SFDP_PARAM_HEADER_PTP(bfpt_header);
 	memset(&bfpt, 0, sizeof(bfpt));
-	err = spi_nor_read_sfdp(nor,  addr, len, &bfpt);
+	err = spi_nor_read_sfdp_dma_unsafe(nor,  addr, len, &bfpt);
 	if (err < 0)
 		return err;
 
@@ -2127,6 +2157,15 @@
 	params->size = bfpt.dwords[BFPT_DWORD(2)];
 	if (params->size & BIT(31)) {
 		params->size &= ~BIT(31);
+
+		/*
+		 * Prevent overflows on params->size. Anyway, a NOR of 2^64
+		 * bits is unlikely to exist so this error probably means
+		 * the BFPT we are reading is corrupted/wrong.
+		 */
+		if (params->size > 63)
+			return -EINVAL;
+
 		params->size = 1ULL << params->size;
 	} else {
 		params->size++;
@@ -2243,7 +2282,7 @@
 	int i, err;
 
 	/* Get the SFDP header. */
-	err = spi_nor_read_sfdp(nor, 0, sizeof(header), &header);
+	err = spi_nor_read_sfdp_dma_unsafe(nor, 0, sizeof(header), &header);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 13f0f21..a13a489 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -182,22 +182,23 @@
 /* FLEXCAN hardware feature flags
  *
  * Below is some version info we got:
- *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT Memory err RTR re-
- *                                Filter? connected?  detection  ception in MB
- *   MX25  FlexCAN2  03.00.00.00     no        no         no        no
- *   MX28  FlexCAN2  03.00.04.00    yes       yes         no        no
- *   MX35  FlexCAN2  03.00.00.00     no        no         no        no
- *   MX53  FlexCAN2  03.00.00.00    yes        no         no        no
- *   MX6s  FlexCAN3  10.00.12.00    yes       yes         no       yes
- *   VF610 FlexCAN3  ?               no       yes        yes       yes?
+ *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT IRQ Err Memory err RTR re-
+ *                                Filter? connected?  Passive detection  ception in MB
+ *   MX25  FlexCAN2  03.00.00.00     no        no         ?       no        no
+ *   MX28  FlexCAN2  03.00.04.00    yes       yes        no       no        no
+ *   MX35  FlexCAN2  03.00.00.00     no        no         ?       no        no
+ *   MX53  FlexCAN2  03.00.00.00    yes        no        no       no        no
+ *   MX6s  FlexCAN3  10.00.12.00    yes       yes        no       no       yes
+ *   VF610 FlexCAN3  ?               no       yes         ?      yes       yes?
  *
  * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
  */
-#define FLEXCAN_QUIRK_BROKEN_ERR_STATE	BIT(1) /* [TR]WRN_INT not connected */
+#define FLEXCAN_QUIRK_BROKEN_WERR_STATE	BIT(1) /* [TR]WRN_INT not connected */
 #define FLEXCAN_QUIRK_DISABLE_RXFG	BIT(2) /* Disable RX FIFO Global mask */
 #define FLEXCAN_QUIRK_ENABLE_EACEN_RRS	BIT(3) /* Enable EACEN and RRS bit in ctrl2 */
 #define FLEXCAN_QUIRK_DISABLE_MECR	BIT(4) /* Disable Memory error detection */
 #define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP	BIT(5) /* Use timestamp based offloading */
+#define FLEXCAN_QUIRK_BROKEN_PERR_STATE	BIT(6) /* No interrupt for error passive */
 
 /* Structure of the message buffer */
 struct flexcan_mb {
@@ -281,14 +282,17 @@
 };
 
 static const struct flexcan_devtype_data fsl_p1010_devtype_data = {
-	.quirks = FLEXCAN_QUIRK_BROKEN_ERR_STATE,
+	.quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE,
 };
 
-static const struct flexcan_devtype_data fsl_imx28_devtype_data;
+static const struct flexcan_devtype_data fsl_imx28_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_BROKEN_PERR_STATE,
+};
 
 static const struct flexcan_devtype_data fsl_imx6q_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
-		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
+		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_BROKEN_PERR_STATE,
 };
 
 static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
@@ -335,6 +339,22 @@
 }
 #endif
 
+static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_ctrl = (priv->reg_ctrl_default | FLEXCAN_CTRL_ERR_MSK);
+
+	flexcan_write(reg_ctrl, &regs->ctrl);
+}
+
+static inline void flexcan_error_irq_disable(const struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_ctrl = (priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_MSK);
+
+	flexcan_write(reg_ctrl, &regs->ctrl);
+}
+
 static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv)
 {
 	if (!priv->reg_xceiver)
@@ -713,6 +733,7 @@
 	struct flexcan_regs __iomem *regs = priv->regs;
 	irqreturn_t handled = IRQ_NONE;
 	u32 reg_iflag1, reg_esr;
+	enum can_state last_state = priv->can.state;
 
 	reg_iflag1 = flexcan_read(&regs->iflag1);
 
@@ -765,8 +786,10 @@
 		flexcan_write(reg_esr & FLEXCAN_ESR_ALL_INT, &regs->esr);
 	}
 
-	/* state change interrupt */
-	if (reg_esr & FLEXCAN_ESR_ERR_STATE)
+	/* state change interrupt or broken error state quirk fix is enabled */
+	if ((reg_esr & FLEXCAN_ESR_ERR_STATE) ||
+	    (priv->devtype_data->quirks & (FLEXCAN_QUIRK_BROKEN_WERR_STATE |
+	                                   FLEXCAN_QUIRK_BROKEN_PERR_STATE)))
 		flexcan_irq_state(dev, reg_esr);
 
 	/* bus error IRQ - handle if bus error reporting is activated */
@@ -774,6 +797,44 @@
 	    (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING))
 		flexcan_irq_bus_err(dev, reg_esr);
 
+	/* availability of error interrupt among state transitions in case
+	 * bus error reporting is de-activated and
+	 * FLEXCAN_QUIRK_BROKEN_PERR_STATE is enabled:
+	 *  +--------------------------------------------------------------+
+	 *  | +----------------------------------------------+ [stopped /  |
+	 *  | |                                              |  sleeping] -+
+	 *  +-+-> active <-> warning <-> passive -> bus off -+
+	 *        ___________^^^^^^^^^^^^_______________________________
+	 *        disabled(1)  enabled             disabled
+	 *
+	 * (1): enabled if FLEXCAN_QUIRK_BROKEN_WERR_STATE is enabled
+	 */
+	if ((last_state != priv->can.state) &&
+	    (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_PERR_STATE) &&
+	    !(priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) {
+		switch (priv->can.state) {
+		case CAN_STATE_ERROR_ACTIVE:
+			if (priv->devtype_data->quirks &
+			    FLEXCAN_QUIRK_BROKEN_WERR_STATE)
+				flexcan_error_irq_enable(priv);
+			else
+				flexcan_error_irq_disable(priv);
+			break;
+
+		case CAN_STATE_ERROR_WARNING:
+			flexcan_error_irq_enable(priv);
+			break;
+
+		case CAN_STATE_ERROR_PASSIVE:
+		case CAN_STATE_BUS_OFF:
+			flexcan_error_irq_disable(priv);
+			break;
+
+		default:
+			break;
+		}
+	}
+
 	return handled;
 }
 
@@ -887,7 +948,7 @@
 	 * on most Flexcan cores, too. Otherwise we don't get
 	 * any error warning or passive interrupts.
 	 */
-	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_ERR_STATE ||
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_WERR_STATE ||
 	    priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
 		reg_ctrl |= FLEXCAN_CTRL_ERR_MSK;
 	else
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 68ef0a4..b0c8085 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -342,7 +342,7 @@
 
 	/* enter the selected mode */
 	mod_reg_val = readl(priv->base + SUN4I_REG_MSEL_ADDR);
-	if (priv->can.ctrlmode & CAN_CTRLMODE_PRESUME_ACK)
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
 		mod_reg_val |= SUN4I_MSEL_LOOPBACK_MODE;
 	else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
 		mod_reg_val |= SUN4I_MSEL_LISTEN_ONLY_MODE;
@@ -811,7 +811,6 @@
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING |
 				       CAN_CTRLMODE_LISTENONLY |
 				       CAN_CTRLMODE_LOOPBACK |
-				       CAN_CTRLMODE_PRESUME_ACK |
 				       CAN_CTRLMODE_3_SAMPLES;
 	priv->base = addr;
 	priv->clk = clk;
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index be928ce..9fdb0f0 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -333,7 +333,7 @@
 		}
 
 		cf->can_id = id & ESD_IDMASK;
-		cf->can_dlc = get_can_dlc(msg->msg.rx.dlc);
+		cf->can_dlc = get_can_dlc(msg->msg.rx.dlc & ~ESD_RTR);
 
 		if (id & ESD_EXTID)
 			cf->can_id |= CAN_EFF_FLAG;
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index afcc131..68ac3e8 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -375,6 +375,8 @@
 
 		gs_free_tx_context(txc);
 
+		atomic_dec(&dev->active_tx_urbs);
+
 		netif_wake_queue(netdev);
 	}
 
@@ -463,14 +465,6 @@
 			  urb->transfer_buffer_length,
 			  urb->transfer_buffer,
 			  urb->transfer_dma);
-
-	atomic_dec(&dev->active_tx_urbs);
-
-	if (!netif_device_present(netdev))
-		return;
-
-	if (netif_queue_stopped(netdev))
-		netif_wake_queue(netdev);
 }
 
 static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 18cc529..9b18d96 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -137,6 +137,7 @@
 #define CMD_RESET_ERROR_COUNTER		49
 #define CMD_TX_ACKNOWLEDGE		50
 #define CMD_CAN_ERROR_EVENT		51
+#define CMD_FLUSH_QUEUE_REPLY		68
 
 #define CMD_LEAF_USB_THROTTLE		77
 #define CMD_LEAF_LOG_MESSAGE		106
@@ -1301,6 +1302,11 @@
 			goto warn;
 		break;
 
+	case CMD_FLUSH_QUEUE_REPLY:
+		if (dev->family != KVASER_LEAF)
+			goto warn;
+		break;
+
 	default:
 warn:		dev_warn(dev->udev->dev.parent,
 			 "Unhandled message (%d)\n", msg->id);
@@ -1609,7 +1615,8 @@
 	if (err)
 		netdev_warn(netdev, "Cannot flush queue, error %d\n", err);
 
-	if (kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, priv->channel))
+	err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, priv->channel);
+	if (err)
 		netdev_warn(netdev, "Cannot reset card, error %d\n", err);
 
 	err = kvaser_usb_stop_chip(priv);
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index dce7fa5..f123ed5 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -214,8 +214,14 @@
 
 static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr)
 {
-	/* Use the same MAC Address as FD Pause frames for all ports */
-	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 9) | addr[1]);
+	u16 val = addr[0] << 8 | addr[1];
+
+	/* The multicast bit is always transmitted as a zero, so the switch uses
+	 * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA.
+	 */
+	val &= 0xfeff;
+
+	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val);
 	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]);
 	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]);
 
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index c6678aa..d74c733 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1100,6 +1100,10 @@
 	};
 	int i, err;
 
+	/* DSA and CPU ports have to be members of multiple vlans */
+	if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
+		return 0;
+
 	if (!vid_begin)
 		return -EOPNOTSUPP;
 
@@ -3947,7 +3951,9 @@
 	if (chip->irq > 0) {
 		if (chip->info->g2_irqs > 0)
 			mv88e6xxx_g2_irq_free(chip);
+		mutex_lock(&chip->reg_lock);
 		mv88e6xxx_g1_irq_free(chip);
+		mutex_unlock(&chip->reg_lock);
 	}
 }
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index b1212de..967020f 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -742,8 +742,8 @@
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 
-	channels->max_rx = ENA_MAX_NUM_IO_QUEUES;
-	channels->max_tx = ENA_MAX_NUM_IO_QUEUES;
+	channels->max_rx = adapter->num_queues;
+	channels->max_tx = adapter->num_queues;
 	channels->max_other = 0;
 	channels->max_combined = 0;
 	channels->rx_count = adapter->num_queues;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index f7dc22f..c6bd5e2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -966,7 +966,7 @@
 		u64_stats_update_begin(&rx_ring->syncp);
 		rx_ring->rx_stats.bad_csum++;
 		u64_stats_update_end(&rx_ring->syncp);
-		netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
+		netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev,
 			  "RX IPv4 header checksum error\n");
 		return;
 	}
@@ -979,7 +979,7 @@
 			u64_stats_update_begin(&rx_ring->syncp);
 			rx_ring->rx_stats.bad_csum++;
 			u64_stats_update_end(&rx_ring->syncp);
-			netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
+			netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev,
 				  "RX L4 checksum error\n");
 			skb->ip_summed = CHECKSUM_NONE;
 			return;
@@ -3064,7 +3064,8 @@
 	if (ena_dev->mem_bar)
 		devm_iounmap(&pdev->dev, ena_dev->mem_bar);
 
-	devm_iounmap(&pdev->dev, ena_dev->reg_bar);
+	if (ena_dev->reg_bar)
+		devm_iounmap(&pdev->dev, ena_dev->reg_bar);
 
 	release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK;
 	pci_release_selected_regions(pdev, release_bars);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index 2149864..57e7968 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -22,8 +22,12 @@
 
 #define AQ_CFG_FORCE_LEGACY_INT 0U
 
-#define AQ_CFG_IS_INTERRUPT_MODERATION_DEF   1U
-#define AQ_CFG_INTERRUPT_MODERATION_RATE_DEF 0xFFFFU
+#define AQ_CFG_INTERRUPT_MODERATION_OFF		0
+#define AQ_CFG_INTERRUPT_MODERATION_ON		1
+#define AQ_CFG_INTERRUPT_MODERATION_AUTO	0xFFFFU
+
+#define AQ_CFG_INTERRUPT_MODERATION_USEC_MAX (0x1FF * 2)
+
 #define AQ_CFG_IRQ_MASK                      0x1FFU
 
 #define AQ_CFG_VECS_MAX   8U
@@ -51,6 +55,10 @@
 
 #define AQ_CFG_SKB_FRAGS_MAX   32U
 
+/* Number of descriptors available in one ring to resume this ring queue
+ */
+#define AQ_CFG_RESTART_DESC_THRES   (AQ_CFG_SKB_FRAGS_MAX * 2)
+
 #define AQ_CFG_NAPI_WEIGHT     64U
 
 #define AQ_CFG_MULTICAST_ADDRESS_MAX     32U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index a761e91..d5e99b4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -56,10 +56,6 @@
 	return aq_nic_set_link_ksettings(aq_nic, cmd);
 }
 
-/* there "5U" is number of queue[#] stats lines (InPackets+...+InErrors) */
-static const unsigned int aq_ethtool_stat_queue_lines = 5U;
-static const unsigned int aq_ethtool_stat_queue_chars =
-	5U * ETH_GSTRING_LEN;
 static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = {
 	"InPackets",
 	"InUCast",
@@ -83,56 +79,26 @@
 	"InOctetsDma",
 	"OutOctetsDma",
 	"InDroppedDma",
-	"Queue[0] InPackets",
-	"Queue[0] OutPackets",
-	"Queue[0] InJumboPackets",
-	"Queue[0] InLroPackets",
-	"Queue[0] InErrors",
-	"Queue[1] InPackets",
-	"Queue[1] OutPackets",
-	"Queue[1] InJumboPackets",
-	"Queue[1] InLroPackets",
-	"Queue[1] InErrors",
-	"Queue[2] InPackets",
-	"Queue[2] OutPackets",
-	"Queue[2] InJumboPackets",
-	"Queue[2] InLroPackets",
-	"Queue[2] InErrors",
-	"Queue[3] InPackets",
-	"Queue[3] OutPackets",
-	"Queue[3] InJumboPackets",
-	"Queue[3] InLroPackets",
-	"Queue[3] InErrors",
-	"Queue[4] InPackets",
-	"Queue[4] OutPackets",
-	"Queue[4] InJumboPackets",
-	"Queue[4] InLroPackets",
-	"Queue[4] InErrors",
-	"Queue[5] InPackets",
-	"Queue[5] OutPackets",
-	"Queue[5] InJumboPackets",
-	"Queue[5] InLroPackets",
-	"Queue[5] InErrors",
-	"Queue[6] InPackets",
-	"Queue[6] OutPackets",
-	"Queue[6] InJumboPackets",
-	"Queue[6] InLroPackets",
-	"Queue[6] InErrors",
-	"Queue[7] InPackets",
-	"Queue[7] OutPackets",
-	"Queue[7] InJumboPackets",
-	"Queue[7] InLroPackets",
-	"Queue[7] InErrors",
+};
+
+static const char aq_ethtool_queue_stat_names[][ETH_GSTRING_LEN] = {
+	"Queue[%d] InPackets",
+	"Queue[%d] OutPackets",
+	"Queue[%d] Restarts",
+	"Queue[%d] InJumboPackets",
+	"Queue[%d] InLroPackets",
+	"Queue[%d] InErrors",
 };
 
 static void aq_ethtool_stats(struct net_device *ndev,
 			     struct ethtool_stats *stats, u64 *data)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
 
-/* ASSERT: Need add lines to aq_ethtool_stat_names if AQ_CFG_VECS_MAX > 8 */
-	BUILD_BUG_ON(AQ_CFG_VECS_MAX > 8);
-	memset(data, 0, ARRAY_SIZE(aq_ethtool_stat_names) * sizeof(u64));
+	memset(data, 0, (ARRAY_SIZE(aq_ethtool_stat_names) +
+				ARRAY_SIZE(aq_ethtool_queue_stat_names) *
+				cfg->vecs) * sizeof(u64));
 	aq_nic_get_stats(aq_nic, data);
 }
 
@@ -154,8 +120,8 @@
 
 	strlcpy(drvinfo->bus_info, pdev ? pci_name(pdev) : "",
 		sizeof(drvinfo->bus_info));
-	drvinfo->n_stats = ARRAY_SIZE(aq_ethtool_stat_names) -
-		(AQ_CFG_VECS_MAX - cfg->vecs) * aq_ethtool_stat_queue_lines;
+	drvinfo->n_stats = ARRAY_SIZE(aq_ethtool_stat_names) +
+		cfg->vecs * ARRAY_SIZE(aq_ethtool_queue_stat_names);
 	drvinfo->testinfo_len = 0;
 	drvinfo->regdump_len = regs_count;
 	drvinfo->eedump_len = 0;
@@ -164,14 +130,25 @@
 static void aq_ethtool_get_strings(struct net_device *ndev,
 				   u32 stringset, u8 *data)
 {
+	int i, si;
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
+	u8 *p = data;
 
-	if (stringset == ETH_SS_STATS)
-		memcpy(data, *aq_ethtool_stat_names,
-		       sizeof(aq_ethtool_stat_names) -
-		       (AQ_CFG_VECS_MAX - cfg->vecs) *
-		       aq_ethtool_stat_queue_chars);
+	if (stringset == ETH_SS_STATS) {
+		memcpy(p, *aq_ethtool_stat_names,
+		       sizeof(aq_ethtool_stat_names));
+		p = p + sizeof(aq_ethtool_stat_names);
+		for (i = 0; i < cfg->vecs; i++) {
+			for (si = 0;
+				si < ARRAY_SIZE(aq_ethtool_queue_stat_names);
+				si++) {
+				snprintf(p, ETH_GSTRING_LEN,
+					 aq_ethtool_queue_stat_names[si], i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+	}
 }
 
 static int aq_ethtool_get_sset_count(struct net_device *ndev, int stringset)
@@ -182,9 +159,8 @@
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		ret = ARRAY_SIZE(aq_ethtool_stat_names) -
-			(AQ_CFG_VECS_MAX - cfg->vecs) *
-			aq_ethtool_stat_queue_lines;
+		ret = ARRAY_SIZE(aq_ethtool_stat_names) +
+			cfg->vecs * ARRAY_SIZE(aq_ethtool_queue_stat_names);
 		break;
 	default:
 		ret = -EOPNOTSUPP;
@@ -245,6 +221,69 @@
 	return err;
 }
 
+int aq_ethtool_get_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *coal)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
+
+	if (cfg->itr == AQ_CFG_INTERRUPT_MODERATION_ON ||
+	    cfg->itr == AQ_CFG_INTERRUPT_MODERATION_AUTO) {
+		coal->rx_coalesce_usecs = cfg->rx_itr;
+		coal->tx_coalesce_usecs = cfg->tx_itr;
+		coal->rx_max_coalesced_frames = 0;
+		coal->tx_max_coalesced_frames = 0;
+	} else {
+		coal->rx_coalesce_usecs = 0;
+		coal->tx_coalesce_usecs = 0;
+		coal->rx_max_coalesced_frames = 1;
+		coal->tx_max_coalesced_frames = 1;
+	}
+	return 0;
+}
+
+int aq_ethtool_set_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *coal)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
+
+	/* This is not yet supported
+	 */
+	if (coal->use_adaptive_rx_coalesce || coal->use_adaptive_tx_coalesce)
+		return -EOPNOTSUPP;
+
+	/* Atlantic only supports timing based coalescing
+	 */
+	if (coal->rx_max_coalesced_frames > 1 ||
+	    coal->rx_coalesce_usecs_irq ||
+	    coal->rx_max_coalesced_frames_irq)
+		return -EOPNOTSUPP;
+
+	if (coal->tx_max_coalesced_frames > 1 ||
+	    coal->tx_coalesce_usecs_irq ||
+	    coal->tx_max_coalesced_frames_irq)
+		return -EOPNOTSUPP;
+
+	/* We do not support frame counting. Check this
+	 */
+	if (!(coal->rx_max_coalesced_frames == !coal->rx_coalesce_usecs))
+		return -EOPNOTSUPP;
+	if (!(coal->tx_max_coalesced_frames == !coal->tx_coalesce_usecs))
+		return -EOPNOTSUPP;
+
+	if (coal->rx_coalesce_usecs > AQ_CFG_INTERRUPT_MODERATION_USEC_MAX ||
+	    coal->tx_coalesce_usecs > AQ_CFG_INTERRUPT_MODERATION_USEC_MAX)
+		return -EINVAL;
+
+	cfg->itr = AQ_CFG_INTERRUPT_MODERATION_ON;
+
+	cfg->rx_itr = coal->rx_coalesce_usecs;
+	cfg->tx_itr = coal->tx_coalesce_usecs;
+
+	return aq_nic_update_interrupt_moderation_settings(aq_nic);
+}
+
 const struct ethtool_ops aq_ethtool_ops = {
 	.get_link            = aq_ethtool_get_link,
 	.get_regs_len        = aq_ethtool_get_regs_len,
@@ -259,4 +298,6 @@
 	.get_ethtool_stats   = aq_ethtool_stats,
 	.get_link_ksettings  = aq_ethtool_get_link_ksettings,
 	.set_link_ksettings  = aq_ethtool_set_link_ksettings,
+	.get_coalesce	     = aq_ethtool_get_coalesce,
+	.set_coalesce	     = aq_ethtool_set_coalesce,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index bf9b3f0..0207927 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -151,8 +151,7 @@
 				     [ETH_ALEN],
 				     u32 count);
 
-	int (*hw_interrupt_moderation_set)(struct aq_hw_s *self,
-					   bool itr_enabled);
+	int (*hw_interrupt_moderation_set)(struct aq_hw_s *self);
 
 	int (*hw_rss_set)(struct aq_hw_s *self,
 			  struct aq_rss_parameters *rss_params);
@@ -163,6 +162,8 @@
 	int (*hw_get_regs)(struct aq_hw_s *self,
 			   struct aq_hw_caps_s *aq_hw_caps, u32 *regs_buff);
 
+	int (*hw_update_stats)(struct aq_hw_s *self);
+
 	int (*hw_get_hw_stats)(struct aq_hw_s *self, u64 *data,
 			       unsigned int *p_count);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 6ac9e26..483e976 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -16,6 +16,7 @@
 #include "aq_pci_func.h"
 #include "aq_nic_internal.h"
 
+#include <linux/moduleparam.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/timer.h>
@@ -24,6 +25,18 @@
 #include <linux/tcp.h>
 #include <net/ip.h>
 
+static unsigned int aq_itr = AQ_CFG_INTERRUPT_MODERATION_AUTO;
+module_param_named(aq_itr, aq_itr, uint, 0644);
+MODULE_PARM_DESC(aq_itr, "Interrupt throttling mode");
+
+static unsigned int aq_itr_tx;
+module_param_named(aq_itr_tx, aq_itr_tx, uint, 0644);
+MODULE_PARM_DESC(aq_itr_tx, "TX interrupt throttle rate");
+
+static unsigned int aq_itr_rx;
+module_param_named(aq_itr_rx, aq_itr_rx, uint, 0644);
+MODULE_PARM_DESC(aq_itr_rx, "RX interrupt throttle rate");
+
 static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues)
 {
 	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
@@ -61,9 +74,9 @@
 
 	cfg->is_polling = AQ_CFG_IS_POLLING_DEF;
 
-	cfg->is_interrupt_moderation = AQ_CFG_IS_INTERRUPT_MODERATION_DEF;
-	cfg->itr = cfg->is_interrupt_moderation ?
-		AQ_CFG_INTERRUPT_MODERATION_RATE_DEF : 0U;
+	cfg->itr = aq_itr;
+	cfg->tx_itr = aq_itr_tx;
+	cfg->rx_itr = aq_itr_rx;
 
 	cfg->is_rss = AQ_CFG_IS_RSS_DEF;
 	cfg->num_rss_queues = AQ_CFG_NUM_RSS_QUEUES_DEF;
@@ -119,6 +132,37 @@
 	return 0;
 }
 
+static int aq_nic_update_link_status(struct aq_nic_s *self)
+{
+	int err = self->aq_hw_ops.hw_get_link_status(self->aq_hw);
+
+	if (err)
+		return err;
+
+	if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps) {
+		pr_info("%s: link change old %d new %d\n",
+			AQ_CFG_DRV_NAME, self->link_status.mbps,
+			self->aq_hw->aq_link_status.mbps);
+		aq_nic_update_interrupt_moderation_settings(self);
+	}
+
+	self->link_status = self->aq_hw->aq_link_status;
+	if (!netif_carrier_ok(self->ndev) && self->link_status.mbps) {
+		aq_utils_obj_set(&self->header.flags,
+				 AQ_NIC_FLAG_STARTED);
+		aq_utils_obj_clear(&self->header.flags,
+				   AQ_NIC_LINK_DOWN);
+		netif_carrier_on(self->ndev);
+		netif_tx_wake_all_queues(self->ndev);
+	}
+	if (netif_carrier_ok(self->ndev) && !self->link_status.mbps) {
+		netif_carrier_off(self->ndev);
+		netif_tx_disable(self->ndev);
+		aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN);
+	}
+	return 0;
+}
+
 static void aq_nic_service_timer_cb(unsigned long param)
 {
 	struct aq_nic_s *self = (struct aq_nic_s *)param;
@@ -131,25 +175,12 @@
 	if (aq_utils_obj_test(&self->header.flags, AQ_NIC_FLAGS_IS_NOT_READY))
 		goto err_exit;
 
-	err = self->aq_hw_ops.hw_get_link_status(self->aq_hw);
-	if (err < 0)
+	err = aq_nic_update_link_status(self);
+	if (err)
 		goto err_exit;
 
-	self->link_status = self->aq_hw->aq_link_status;
-
-	self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw,
-		    self->aq_nic_cfg.is_interrupt_moderation);
-
-	if (self->link_status.mbps) {
-		aq_utils_obj_set(&self->header.flags,
-				 AQ_NIC_FLAG_STARTED);
-		aq_utils_obj_clear(&self->header.flags,
-				   AQ_NIC_LINK_DOWN);
-		netif_carrier_on(self->ndev);
-	} else {
-		netif_carrier_off(self->ndev);
-		aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN);
-	}
+	if (self->aq_hw_ops.hw_update_stats)
+		self->aq_hw_ops.hw_update_stats(self->aq_hw);
 
 	memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s));
 	memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s));
@@ -214,7 +245,6 @@
 	SET_NETDEV_DEV(ndev, dev);
 
 	ndev->if_port = port;
-	ndev->min_mtu = ETH_MIN_MTU;
 	self->ndev = ndev;
 
 	self->aq_pci_func = aq_pci_func;
@@ -241,7 +271,6 @@
 int aq_nic_ndev_register(struct aq_nic_s *self)
 {
 	int err = 0;
-	unsigned int i = 0U;
 
 	if (!self->ndev) {
 		err = -EINVAL;
@@ -263,8 +292,7 @@
 
 	netif_carrier_off(self->ndev);
 
-	for (i = AQ_CFG_VECS_MAX; i--;)
-		aq_nic_ndev_queue_stop(self, i);
+	netif_tx_disable(self->ndev);
 
 	err = register_netdev(self->ndev);
 	if (err < 0)
@@ -283,6 +311,7 @@
 	self->ndev->features = aq_hw_caps->hw_features;
 	self->ndev->priv_flags = aq_hw_caps->hw_priv_flags;
 	self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN;
+	self->ndev->max_mtu = self->aq_hw_caps.mtu - ETH_FCS_LEN - ETH_HLEN;
 
 	return 0;
 }
@@ -318,12 +347,9 @@
 		err = -EINVAL;
 		goto err_exit;
 	}
-	if (netif_running(ndev)) {
-		unsigned int i;
-
-		for (i = AQ_CFG_VECS_MAX; i--;)
-			netif_stop_subqueue(ndev, i);
-	}
+	if (netif_running(ndev))
+		netif_tx_disable(ndev);
+	netif_carrier_off(self->ndev);
 
 	for (self->aq_vecs = 0; self->aq_vecs < self->aq_nic_cfg.vecs;
 		self->aq_vecs++) {
@@ -383,16 +409,6 @@
 	return err;
 }
 
-void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx)
-{
-	netif_start_subqueue(self->ndev, idx);
-}
-
-void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx)
-{
-	netif_stop_subqueue(self->ndev, idx);
-}
-
 int aq_nic_start(struct aq_nic_s *self)
 {
 	struct aq_vec_s *aq_vec = NULL;
@@ -421,9 +437,8 @@
 	if (err < 0)
 		goto err_exit;
 
-	err = self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw,
-			    self->aq_nic_cfg.is_interrupt_moderation);
-	if (err < 0)
+	err = aq_nic_update_interrupt_moderation_settings(self);
+	if (err)
 		goto err_exit;
 	setup_timer(&self->service_timer, &aq_nic_service_timer_cb,
 		    (unsigned long)self);
@@ -451,10 +466,6 @@
 			goto err_exit;
 	}
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
-		aq_nic_ndev_queue_start(self, i);
-
 	err = netif_set_real_num_tx_queues(self->ndev, self->aq_vecs);
 	if (err < 0)
 		goto err_exit;
@@ -463,6 +474,8 @@
 	if (err < 0)
 		goto err_exit;
 
+	netif_tx_start_all_queues(self->ndev);
+
 err_exit:
 	return err;
 }
@@ -475,6 +488,7 @@
 	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
 	unsigned int frag_count = 0U;
 	unsigned int dx = ring->sw_tail;
+	struct aq_ring_buff_s *first = NULL;
 	struct aq_ring_buff_s *dx_buff = &ring->buff_ring[dx];
 
 	if (unlikely(skb_is_gso(skb))) {
@@ -485,6 +499,7 @@
 		dx_buff->len_l4 = tcp_hdrlen(skb);
 		dx_buff->mss = skb_shinfo(skb)->gso_size;
 		dx_buff->is_txc = 1U;
+		dx_buff->eop_index = 0xffffU;
 
 		dx_buff->is_ipv6 =
 			(ip_hdr(skb)->version == 6) ? 1U : 0U;
@@ -504,6 +519,7 @@
 	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa)))
 		goto exit;
 
+	first = dx_buff;
 	dx_buff->len_pkt = skb->len;
 	dx_buff->is_sop = 1U;
 	dx_buff->is_mapped = 1U;
@@ -532,40 +548,46 @@
 
 	for (; nr_frags--; ++frag_count) {
 		unsigned int frag_len = 0U;
+		unsigned int buff_offset = 0U;
+		unsigned int buff_size = 0U;
 		dma_addr_t frag_pa;
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_count];
 
 		frag_len = skb_frag_size(frag);
-		frag_pa = skb_frag_dma_map(aq_nic_get_dev(self), frag, 0,
-					   frag_len, DMA_TO_DEVICE);
 
-		if (unlikely(dma_mapping_error(aq_nic_get_dev(self), frag_pa)))
-			goto mapping_error;
+		while (frag_len) {
+			if (frag_len > AQ_CFG_TX_FRAME_MAX)
+				buff_size = AQ_CFG_TX_FRAME_MAX;
+			else
+				buff_size = frag_len;
 
-		while (frag_len > AQ_CFG_TX_FRAME_MAX) {
+			frag_pa = skb_frag_dma_map(aq_nic_get_dev(self),
+						   frag,
+						   buff_offset,
+						   buff_size,
+						   DMA_TO_DEVICE);
+
+			if (unlikely(dma_mapping_error(aq_nic_get_dev(self),
+						       frag_pa)))
+				goto mapping_error;
+
 			dx = aq_ring_next_dx(ring, dx);
 			dx_buff = &ring->buff_ring[dx];
 
 			dx_buff->flags = 0U;
-			dx_buff->len = AQ_CFG_TX_FRAME_MAX;
+			dx_buff->len = buff_size;
 			dx_buff->pa = frag_pa;
 			dx_buff->is_mapped = 1U;
+			dx_buff->eop_index = 0xffffU;
 
-			frag_len -= AQ_CFG_TX_FRAME_MAX;
-			frag_pa += AQ_CFG_TX_FRAME_MAX;
+			frag_len -= buff_size;
+			buff_offset += buff_size;
+
 			++ret;
 		}
-
-		dx = aq_ring_next_dx(ring, dx);
-		dx_buff = &ring->buff_ring[dx];
-
-		dx_buff->flags = 0U;
-		dx_buff->len = frag_len;
-		dx_buff->pa = frag_pa;
-		dx_buff->is_mapped = 1U;
-		++ret;
 	}
 
+	first->eop_index = dx;
 	dx_buff->is_eop = 1U;
 	dx_buff->skb = skb;
 	goto exit;
@@ -602,7 +624,6 @@
 	unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs;
 	unsigned int tc = 0U;
 	int err = NETDEV_TX_OK;
-	bool is_nic_in_bad_state;
 
 	frags = skb_shinfo(skb)->nr_frags + 1;
 
@@ -613,13 +634,10 @@
 		goto err_exit;
 	}
 
-	is_nic_in_bad_state = aq_utils_obj_test(&self->header.flags,
-						AQ_NIC_FLAGS_IS_NOT_TX_READY) ||
-						(aq_ring_avail_dx(ring) <
-						AQ_CFG_SKB_FRAGS_MAX);
+	aq_ring_update_queue_state(ring);
 
-	if (is_nic_in_bad_state) {
-		aq_nic_ndev_queue_stop(self, ring->idx);
+	/* Above status update may stop the queue. Check this. */
+	if (__netif_subqueue_stopped(self->ndev, ring->idx)) {
 		err = NETDEV_TX_BUSY;
 		goto err_exit;
 	}
@@ -631,9 +649,6 @@
 						      ring,
 						      frags);
 		if (err >= 0) {
-			if (aq_ring_avail_dx(ring) < AQ_CFG_SKB_FRAGS_MAX + 1)
-				aq_nic_ndev_queue_stop(self, ring->idx);
-
 			++ring->stats.tx.packets;
 			ring->stats.tx.bytes += skb->len;
 		}
@@ -645,6 +660,11 @@
 	return err;
 }
 
+int aq_nic_update_interrupt_moderation_settings(struct aq_nic_s *self)
+{
+	return self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw);
+}
+
 int aq_nic_set_packet_filter(struct aq_nic_s *self, unsigned int flags)
 {
 	int err = 0;
@@ -693,16 +713,9 @@
 
 int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu)
 {
-	int err = 0;
-
-	if (new_mtu > self->aq_hw_caps.mtu) {
-		err = -EINVAL;
-		goto err_exit;
-	}
 	self->aq_nic_cfg.mtu = new_mtu;
 
-err_exit:
-	return err;
+	return 0;
 }
 
 int aq_nic_set_mac(struct aq_nic_s *self, struct net_device *ndev)
@@ -905,9 +918,8 @@
 	struct aq_vec_s *aq_vec = NULL;
 	unsigned int i = 0U;
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
-		aq_nic_ndev_queue_stop(self, i);
+	netif_tx_disable(self->ndev);
+	netif_carrier_off(self->ndev);
 
 	del_timer_sync(&self->service_timer);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 7fc2a5e..4309983 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -40,6 +40,8 @@
 	u32 vecs;		/* vecs==allocated irqs */
 	u32 irq_type;
 	u32 itr;
+	u16 rx_itr;
+	u16 tx_itr;
 	u32 num_rss_queues;
 	u32 mtu;
 	u32 ucp_0x364;
@@ -49,7 +51,6 @@
 	u16 is_mc_list_enabled;
 	u16 mc_list_count;
 	bool is_autoneg;
-	bool is_interrupt_moderation;
 	bool is_polling;
 	bool is_rss;
 	bool is_lro;
@@ -83,8 +84,6 @@
 int aq_nic_init(struct aq_nic_s *self);
 int aq_nic_cfg_start(struct aq_nic_s *self);
 int aq_nic_ndev_register(struct aq_nic_s *self);
-void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx);
-void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx);
 void aq_nic_ndev_free(struct aq_nic_s *self);
 int aq_nic_start(struct aq_nic_s *self);
 int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb);
@@ -106,5 +105,6 @@
 struct aq_nic_cfg_s *aq_nic_get_cfg(struct aq_nic_s *self);
 u32 aq_nic_get_fw_version(struct aq_nic_s *self);
 int aq_nic_change_pm_state(struct aq_nic_s *self, pm_message_t *pm_msg);
+int aq_nic_update_interrupt_moderation_settings(struct aq_nic_s *self);
 
 #endif /* AQ_NIC_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 4c6c882..cadaa64 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -85,6 +85,7 @@
 	int err = 0;
 	unsigned int bar = 0U;
 	unsigned int port = 0U;
+	unsigned int numvecs = 0U;
 
 	err = pci_enable_device(self->pdev);
 	if (err < 0)
@@ -142,10 +143,12 @@
 		}
 	}
 
-	/*enable interrupts */
+	numvecs = min((u8)AQ_CFG_VECS_DEF, self->aq_hw_caps.msix_irqs);
+	numvecs = min(numvecs, num_online_cpus());
+
+	/* enable interrupts */
 #if !AQ_CFG_FORCE_LEGACY_INT
-	err = pci_alloc_irq_vectors(self->pdev, self->aq_hw_caps.msix_irqs,
-			      self->aq_hw_caps.msix_irqs, PCI_IRQ_MSIX);
+	err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs, PCI_IRQ_MSIX);
 
 	if (err < 0) {
 		err = pci_alloc_irq_vectors(self->pdev, 1, 1,
@@ -153,7 +156,7 @@
 		if (err < 0)
 			goto err_exit;
 	}
-#endif
+#endif /* AQ_CFG_FORCE_LEGACY_INT */
 
 	/* net device init */
 	for (port = 0; port < self->ports; ++port) {
@@ -265,6 +268,9 @@
 		aq_nic_ndev_free(self->port[port]);
 	}
 
+	if (self->mmio)
+		iounmap(self->mmio);
+
 	kfree(self);
 
 err_exit:;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 4eee199..0654e0c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -104,6 +104,38 @@
 	return 0;
 }
 
+static inline bool aq_ring_dx_in_range(unsigned int h, unsigned int i,
+				       unsigned int t)
+{
+	return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t));
+}
+
+void aq_ring_update_queue_state(struct aq_ring_s *ring)
+{
+	if (aq_ring_avail_dx(ring) <= AQ_CFG_SKB_FRAGS_MAX)
+		aq_ring_queue_stop(ring);
+	else if (aq_ring_avail_dx(ring) > AQ_CFG_RESTART_DESC_THRES)
+		aq_ring_queue_wake(ring);
+}
+
+void aq_ring_queue_wake(struct aq_ring_s *ring)
+{
+	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
+
+	if (__netif_subqueue_stopped(ndev, ring->idx)) {
+		netif_wake_subqueue(ndev, ring->idx);
+		ring->stats.tx.queue_restarts++;
+	}
+}
+
+void aq_ring_queue_stop(struct aq_ring_s *ring)
+{
+	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
+
+	if (!__netif_subqueue_stopped(ndev, ring->idx))
+		netif_stop_subqueue(ndev, ring->idx);
+}
+
 void aq_ring_tx_clean(struct aq_ring_s *self)
 {
 	struct device *dev = aq_nic_get_dev(self->aq_nic);
@@ -113,23 +145,28 @@
 		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
 
 		if (likely(buff->is_mapped)) {
-			if (unlikely(buff->is_sop))
+			if (unlikely(buff->is_sop)) {
+				if (!buff->is_eop &&
+				    buff->eop_index != 0xffffU &&
+				    (!aq_ring_dx_in_range(self->sw_head,
+						buff->eop_index,
+						self->hw_head)))
+					break;
+
 				dma_unmap_single(dev, buff->pa, buff->len,
 						 DMA_TO_DEVICE);
-			else
+			} else {
 				dma_unmap_page(dev, buff->pa, buff->len,
 					       DMA_TO_DEVICE);
+			}
 		}
 
 		if (unlikely(buff->is_eop))
 			dev_kfree_skb_any(buff->skb);
-	}
-}
 
-static inline unsigned int aq_ring_dx_in_range(unsigned int h, unsigned int i,
-					       unsigned int t)
-{
-	return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t));
+		buff->pa = 0U;
+		buff->eop_index = 0xffffU;
+	}
 }
 
 #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 782176c..5844078 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -65,7 +65,7 @@
 	};
 	union {
 		struct {
-			u32 len:16;
+			u16 len;
 			u32 is_ip_cso:1;
 			u32 is_udp_cso:1;
 			u32 is_tcp_cso:1;
@@ -77,8 +77,10 @@
 			u32 is_cleaned:1;
 			u32 is_error:1;
 			u32 rsvd3:6;
+			u16 eop_index;
+			u16 rsvd4;
 		};
-		u32 flags;
+		u64 flags;
 	};
 };
 
@@ -94,6 +96,7 @@
 	u64 errors;
 	u64 packets;
 	u64 bytes;
+	u64 queue_restarts;
 };
 
 union aq_ring_stats_s {
@@ -147,6 +150,9 @@
 int aq_ring_init(struct aq_ring_s *self);
 void aq_ring_rx_deinit(struct aq_ring_s *self);
 void aq_ring_free(struct aq_ring_s *self);
+void aq_ring_update_queue_state(struct aq_ring_s *ring);
+void aq_ring_queue_wake(struct aq_ring_s *ring);
+void aq_ring_queue_stop(struct aq_ring_s *ring);
 void aq_ring_tx_clean(struct aq_ring_s *self);
 int aq_ring_rx_clean(struct aq_ring_s *self,
 		     struct napi_struct *napi,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index ebf5880..5fecc9a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -59,12 +59,7 @@
 			if (ring[AQ_VEC_TX_ID].sw_head !=
 			    ring[AQ_VEC_TX_ID].hw_head) {
 				aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]);
-
-				if (aq_ring_avail_dx(&ring[AQ_VEC_TX_ID]) >
-				    AQ_CFG_SKB_FRAGS_MAX) {
-					aq_nic_ndev_queue_start(self->aq_nic,
-						ring[AQ_VEC_TX_ID].idx);
-				}
+				aq_ring_update_queue_state(&ring[AQ_VEC_TX_ID]);
 				was_tx_cleaned = true;
 			}
 
@@ -364,6 +359,7 @@
 		stats_tx->packets += tx->packets;
 		stats_tx->bytes += tx->bytes;
 		stats_tx->errors += tx->errors;
+		stats_tx->queue_restarts += tx->queue_restarts;
 	}
 }
 
@@ -377,8 +373,11 @@
 	memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s));
 	aq_vec_add_stats(self, &stats_rx, &stats_tx);
 
+	/* This data should mimic aq_ethtool_queue_stat_names structure
+	 */
 	data[count] += stats_rx.packets;
 	data[++count] += stats_tx.packets;
+	data[++count] += stats_tx.queue_restarts;
 	data[++count] += stats_rx.jumbo_packets;
 	data[++count] += stats_rx.lro_packets;
 	data[++count] += stats_rx.errors;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index c5a02df..07b3c49 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -765,24 +765,23 @@
 	return err;
 }
 
-static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self,
-						 bool itr_enabled)
+static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 {
 	unsigned int i = 0U;
+	u32 itr_rx;
 
-	if (itr_enabled && self->aq_nic_cfg->itr) {
-		if (self->aq_nic_cfg->itr != 0xFFFFU) {
+	if (self->aq_nic_cfg->itr) {
+		if (self->aq_nic_cfg->itr != AQ_CFG_INTERRUPT_MODERATION_AUTO) {
 			u32 itr_ = (self->aq_nic_cfg->itr >> 1);
 
 			itr_ = min(AQ_CFG_IRQ_MASK, itr_);
 
-			PHAL_ATLANTIC_A0->itr_rx = 0x80000000U |
-					(itr_ << 0x10);
+			itr_rx = 0x80000000U | (itr_ << 0x10);
 		} else  {
 			u32 n = 0xFFFFU & aq_hw_read_reg(self, 0x00002A00U);
 
 			if (n < self->aq_link_status.mbps) {
-				PHAL_ATLANTIC_A0->itr_rx = 0U;
+				itr_rx = 0U;
 			} else {
 				static unsigned int hw_timers_tbl_[] = {
 					0x01CU, /* 10Gbit */
@@ -797,8 +796,7 @@
 					hw_atl_utils_mbps_2_speed_index(
 						self->aq_link_status.mbps);
 
-				PHAL_ATLANTIC_A0->itr_rx =
-					0x80000000U |
+				itr_rx = 0x80000000U |
 					(hw_timers_tbl_[speed_index] << 0x10U);
 			}
 
@@ -806,11 +804,11 @@
 			aq_hw_write_reg(self, 0x00002A00U, 0x8D000000U);
 		}
 	} else {
-		PHAL_ATLANTIC_A0->itr_rx = 0U;
+		itr_rx = 0U;
 	}
 
 	for (i = HW_ATL_A0_RINGS_MAX; i--;)
-		reg_irq_thr_set(self, PHAL_ATLANTIC_A0->itr_rx, i);
+		reg_irq_thr_set(self, itr_rx, i);
 
 	return aq_hw_err_from_flags(self);
 }
@@ -885,6 +883,7 @@
 	.hw_rss_set                  = hw_atl_a0_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_a0_hw_rss_hash_set,
 	.hw_get_regs                 = hw_atl_utils_hw_get_regs,
+	.hw_update_stats             = hw_atl_utils_update_stats,
 	.hw_get_hw_stats             = hw_atl_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl_utils_get_fw_version,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 21784cc..ec68c20 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -788,39 +788,45 @@
 	return err;
 }
 
-static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self,
-						 bool itr_enabled)
+static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 {
 	unsigned int i = 0U;
+	u32 itr_tx = 2U;
+	u32 itr_rx = 2U;
 
-	if (itr_enabled && self->aq_nic_cfg->itr) {
+	switch (self->aq_nic_cfg->itr) {
+	case  AQ_CFG_INTERRUPT_MODERATION_ON:
+	case  AQ_CFG_INTERRUPT_MODERATION_AUTO:
 		tdm_tx_desc_wr_wb_irq_en_set(self, 0U);
 		tdm_tdm_intr_moder_en_set(self, 1U);
 		rdm_rx_desc_wr_wb_irq_en_set(self, 0U);
 		rdm_rdm_intr_moder_en_set(self, 1U);
 
-		PHAL_ATLANTIC_B0->itr_tx = 2U;
-		PHAL_ATLANTIC_B0->itr_rx = 2U;
+		if (self->aq_nic_cfg->itr == AQ_CFG_INTERRUPT_MODERATION_ON) {
+			/* HW timers are in 2us units */
+			int tx_max_timer = self->aq_nic_cfg->tx_itr / 2;
+			int tx_min_timer = tx_max_timer / 2;
 
-		if (self->aq_nic_cfg->itr != 0xFFFFU) {
-			unsigned int max_timer = self->aq_nic_cfg->itr / 2U;
-			unsigned int min_timer = self->aq_nic_cfg->itr / 32U;
+			int rx_max_timer = self->aq_nic_cfg->rx_itr / 2;
+			int rx_min_timer = rx_max_timer / 2;
 
-			max_timer = min(0x1FFU, max_timer);
-			min_timer = min(0xFFU, min_timer);
+			tx_max_timer = min(HW_ATL_INTR_MODER_MAX, tx_max_timer);
+			tx_min_timer = min(HW_ATL_INTR_MODER_MIN, tx_min_timer);
+			rx_max_timer = min(HW_ATL_INTR_MODER_MAX, rx_max_timer);
+			rx_min_timer = min(HW_ATL_INTR_MODER_MIN, rx_min_timer);
 
-			PHAL_ATLANTIC_B0->itr_tx |= min_timer << 0x8U;
-			PHAL_ATLANTIC_B0->itr_tx |= max_timer << 0x10U;
-			PHAL_ATLANTIC_B0->itr_rx |= min_timer << 0x8U;
-			PHAL_ATLANTIC_B0->itr_rx |= max_timer << 0x10U;
+			itr_tx |= tx_min_timer << 0x8U;
+			itr_tx |= tx_max_timer << 0x10U;
+			itr_rx |= rx_min_timer << 0x8U;
+			itr_rx |= rx_max_timer << 0x10U;
 		} else {
 			static unsigned int hw_atl_b0_timers_table_tx_[][2] = {
-				{0xffU, 0xffU}, /* 10Gbit */
-				{0xffU, 0x1ffU}, /* 5Gbit */
-				{0xffU, 0x1ffU}, /* 5Gbit 5GS */
-				{0xffU, 0x1ffU}, /* 2.5Gbit */
-				{0xffU, 0x1ffU}, /* 1Gbit */
-				{0xffU, 0x1ffU}, /* 100Mbit */
+				{0xfU, 0xffU}, /* 10Gbit */
+				{0xfU, 0x1ffU}, /* 5Gbit */
+				{0xfU, 0x1ffU}, /* 5Gbit 5GS */
+				{0xfU, 0x1ffU}, /* 2.5Gbit */
+				{0xfU, 0x1ffU}, /* 1Gbit */
+				{0xfU, 0x1ffU}, /* 100Mbit */
 			};
 
 			static unsigned int hw_atl_b0_timers_table_rx_[][2] = {
@@ -836,34 +842,36 @@
 					hw_atl_utils_mbps_2_speed_index(
 						self->aq_link_status.mbps);
 
-			PHAL_ATLANTIC_B0->itr_tx |=
-				hw_atl_b0_timers_table_tx_[speed_index]
-				[0] << 0x8U; /* set min timer value */
-			PHAL_ATLANTIC_B0->itr_tx |=
-				hw_atl_b0_timers_table_tx_[speed_index]
-				[1] << 0x10U; /* set max timer value */
+			/* Update user visible ITR settings */
+			self->aq_nic_cfg->tx_itr = hw_atl_b0_timers_table_tx_
+							[speed_index][1] * 2;
+			self->aq_nic_cfg->rx_itr = hw_atl_b0_timers_table_rx_
+							[speed_index][1] * 2;
 
-			PHAL_ATLANTIC_B0->itr_rx |=
-				hw_atl_b0_timers_table_rx_[speed_index]
-				[0] << 0x8U; /* set min timer value */
-			PHAL_ATLANTIC_B0->itr_rx |=
-				hw_atl_b0_timers_table_rx_[speed_index]
-				[1] << 0x10U; /* set max timer value */
+			itr_tx |= hw_atl_b0_timers_table_tx_
+						[speed_index][0] << 0x8U;
+			itr_tx |= hw_atl_b0_timers_table_tx_
+						[speed_index][1] << 0x10U;
+
+			itr_rx |= hw_atl_b0_timers_table_rx_
+						[speed_index][0] << 0x8U;
+			itr_rx |= hw_atl_b0_timers_table_rx_
+						[speed_index][1] << 0x10U;
 		}
-	} else {
+		break;
+	case AQ_CFG_INTERRUPT_MODERATION_OFF:
 		tdm_tx_desc_wr_wb_irq_en_set(self, 1U);
 		tdm_tdm_intr_moder_en_set(self, 0U);
 		rdm_rx_desc_wr_wb_irq_en_set(self, 1U);
 		rdm_rdm_intr_moder_en_set(self, 0U);
-		PHAL_ATLANTIC_B0->itr_tx = 0U;
-		PHAL_ATLANTIC_B0->itr_rx = 0U;
+		itr_tx = 0U;
+		itr_rx = 0U;
+		break;
 	}
 
 	for (i = HW_ATL_B0_RINGS_MAX; i--;) {
-		reg_tx_intr_moder_ctrl_set(self,
-					   PHAL_ATLANTIC_B0->itr_tx, i);
-		reg_rx_intr_moder_ctrl_set(self,
-					   PHAL_ATLANTIC_B0->itr_rx, i);
+		reg_tx_intr_moder_ctrl_set(self, itr_tx, i);
+		reg_rx_intr_moder_ctrl_set(self, itr_rx, i);
 	}
 
 	return aq_hw_err_from_flags(self);
@@ -939,6 +947,7 @@
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
 	.hw_get_regs                 = hw_atl_utils_hw_get_regs,
+	.hw_update_stats             = hw_atl_utils_update_stats,
 	.hw_get_hw_stats             = hw_atl_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl_utils_get_fw_version,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index f3957e93..9aa2c6e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -16,7 +16,7 @@
 
 #include "../aq_common.h"
 
-#define HW_ATL_B0_MTU_JUMBO (16000U)
+#define HW_ATL_B0_MTU_JUMBO  16352U
 #define HW_ATL_B0_MTU        1514U
 
 #define HW_ATL_B0_TX_RINGS 4U
@@ -139,6 +139,9 @@
 
 #define HW_ATL_B0_FW_VER_EXPECTED 0x01050006U
 
+#define HW_ATL_INTR_MODER_MAX  0x1FF
+#define HW_ATL_INTR_MODER_MIN  0xFF
+
 /* Hardware tx descriptor */
 struct __packed hw_atl_txd_s {
 	u64 buf_addr;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 4f5ec9a..1fe016f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -255,6 +255,15 @@
 	return err;
 }
 
+int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self,
+			       struct hw_aq_atl_utils_mbox_header *pmbox)
+{
+	return hw_atl_utils_fw_downld_dwords(self,
+				      PHAL_ATLANTIC->mbox_addr,
+				      (u32 *)(void *)pmbox,
+				      sizeof(*pmbox) / sizeof(u32));
+}
+
 void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 				 struct hw_aq_atl_utils_mbox *pmbox)
 {
@@ -267,9 +276,6 @@
 	if (err < 0)
 		goto err_exit;
 
-	if (pmbox != &PHAL_ATLANTIC->mbox)
-		memcpy(pmbox, &PHAL_ATLANTIC->mbox, sizeof(*pmbox));
-
 	if (IS_CHIP_FEATURE(REVISION_A0)) {
 		unsigned int mtu = self->aq_nic_cfg ?
 					self->aq_nic_cfg->mtu : 1514U;
@@ -299,17 +305,17 @@
 {
 	int err = 0;
 	u32 transaction_id = 0;
+	struct hw_aq_atl_utils_mbox_header mbox;
 
 	if (state == MPI_RESET) {
-		hw_atl_utils_mpi_read_stats(self, &PHAL_ATLANTIC->mbox);
+		hw_atl_utils_mpi_read_mbox(self, &mbox);
 
-		transaction_id = PHAL_ATLANTIC->mbox.transaction_id;
+		transaction_id = mbox.transaction_id;
 
 		AQ_HW_WAIT_FOR(transaction_id !=
-				(hw_atl_utils_mpi_read_stats
-					(self, &PHAL_ATLANTIC->mbox),
-					PHAL_ATLANTIC->mbox.transaction_id),
-					1000U, 100U);
+				(hw_atl_utils_mpi_read_mbox(self, &mbox),
+				 mbox.transaction_id),
+			       1000U, 100U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -351,8 +357,7 @@
 			break;
 
 		default:
-			link_status->mbps = 0U;
-			break;
+			return -EBUSY;
 		}
 	}
 
@@ -493,16 +498,51 @@
 	return 0;
 }
 
+int hw_atl_utils_update_stats(struct aq_hw_s *self)
+{
+	struct hw_atl_s *hw_self = PHAL_ATLANTIC;
+	struct hw_aq_atl_utils_mbox mbox;
+
+	if (!self->aq_link_status.mbps)
+		return 0;
+
+	hw_atl_utils_mpi_read_stats(self, &mbox);
+
+#define AQ_SDELTA(_N_) (hw_self->curr_stats._N_ += \
+			mbox.stats._N_ - hw_self->last_stats._N_)
+
+	AQ_SDELTA(uprc);
+	AQ_SDELTA(mprc);
+	AQ_SDELTA(bprc);
+	AQ_SDELTA(erpt);
+
+	AQ_SDELTA(uptc);
+	AQ_SDELTA(mptc);
+	AQ_SDELTA(bptc);
+	AQ_SDELTA(erpr);
+
+	AQ_SDELTA(ubrc);
+	AQ_SDELTA(ubtc);
+	AQ_SDELTA(mbrc);
+	AQ_SDELTA(mbtc);
+	AQ_SDELTA(bbrc);
+	AQ_SDELTA(bbtc);
+	AQ_SDELTA(dpc);
+
+#undef AQ_SDELTA
+
+	memcpy(&hw_self->last_stats, &mbox.stats, sizeof(mbox.stats));
+
+	return 0;
+}
+
 int hw_atl_utils_get_hw_stats(struct aq_hw_s *self,
 			      u64 *data, unsigned int *p_count)
 {
-	struct hw_atl_stats_s *stats = NULL;
+	struct hw_atl_s *hw_self = PHAL_ATLANTIC;
+	struct hw_atl_stats_s *stats = &hw_self->curr_stats;
 	int i = 0;
 
-	hw_atl_utils_mpi_read_stats(self, &PHAL_ATLANTIC->mbox);
-
-	stats = &PHAL_ATLANTIC->mbox.stats;
-
 	data[i] = stats->uprc + stats->mprc + stats->bprc;
 	data[++i] = stats->uprc;
 	data[++i] = stats->mprc;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index e0360a6..c99cc69 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -115,19 +115,22 @@
 	};
 };
 
-struct __packed hw_aq_atl_utils_mbox {
+struct __packed hw_aq_atl_utils_mbox_header {
 	u32 version;
 	u32 transaction_id;
-	int error;
+	u32 error;
+};
+
+struct __packed hw_aq_atl_utils_mbox {
+	struct hw_aq_atl_utils_mbox_header header;
 	struct hw_atl_stats_s stats;
 };
 
 struct __packed hw_atl_s {
 	struct aq_hw_s base;
-	struct hw_aq_atl_utils_mbox mbox;
+	struct hw_atl_stats_s last_stats;
+	struct hw_atl_stats_s curr_stats;
 	u64 speed;
-	u32 itr_tx;
-	u32 itr_rx;
 	unsigned int chip_features;
 	u32 fw_ver_actual;
 	atomic_t dpc;
@@ -170,6 +173,9 @@
 
 void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p);
 
+int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self,
+			       struct hw_aq_atl_utils_mbox_header *pmbox);
+
 void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 				 struct hw_aq_atl_utils_mbox *pmbox);
 
@@ -199,6 +205,8 @@
 
 int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version);
 
+int hw_atl_utils_update_stats(struct aq_hw_s *self);
+
 int hw_atl_utils_get_hw_stats(struct aq_hw_s *self,
 			      u64 *data,
 			      unsigned int *p_count);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index c3c53f6..83eec9a 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -432,6 +432,27 @@
 	netif_dbg(priv, hw, priv->netdev, "updated MIB counters\n");
 }
 
+static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv,
+					u64 *tx_bytes, u64 *tx_packets)
+{
+	struct bcm_sysport_tx_ring *ring;
+	u64 bytes = 0, packets = 0;
+	unsigned int start;
+	unsigned int q;
+
+	for (q = 0; q < priv->netdev->num_tx_queues; q++) {
+		ring = &priv->tx_rings[q];
+		do {
+			start = u64_stats_fetch_begin_irq(&priv->syncp);
+			bytes = ring->bytes;
+			packets = ring->packets;
+		} while (u64_stats_fetch_retry_irq(&priv->syncp, start));
+
+		*tx_bytes += bytes;
+		*tx_packets += packets;
+	}
+}
+
 static void bcm_sysport_get_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
@@ -439,11 +460,16 @@
 	struct bcm_sysport_stats64 *stats64 = &priv->stats64;
 	struct u64_stats_sync *syncp = &priv->syncp;
 	struct bcm_sysport_tx_ring *ring;
+	u64 tx_bytes = 0, tx_packets = 0;
 	unsigned int start;
 	int i, j;
 
-	if (netif_running(dev))
+	if (netif_running(dev)) {
 		bcm_sysport_update_mib_counters(priv);
+		bcm_sysport_update_tx_stats(priv, &tx_bytes, &tx_packets);
+		stats64->tx_bytes = tx_bytes;
+		stats64->tx_packets = tx_packets;
+	}
 
 	for (i =  0, j = 0; i < BCM_SYSPORT_STATS_LEN; i++) {
 		const struct bcm_sysport_stats *s;
@@ -461,12 +487,13 @@
 			continue;
 		p += s->stat_offset;
 
-		if (s->stat_sizeof == sizeof(u64))
+		if (s->stat_sizeof == sizeof(u64) &&
+		    s->type == BCM_SYSPORT_STAT_NETDEV64) {
 			do {
 				start = u64_stats_fetch_begin_irq(syncp);
 				data[i] = *(u64 *)p;
 			} while (u64_stats_fetch_retry_irq(syncp, start));
-		else
+		} else
 			data[i] = *(u32 *)p;
 		j++;
 	}
@@ -1716,27 +1743,12 @@
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct bcm_sysport_stats64 *stats64 = &priv->stats64;
-	struct bcm_sysport_tx_ring *ring;
-	u64 tx_packets = 0, tx_bytes = 0;
 	unsigned int start;
-	unsigned int q;
 
 	netdev_stats_to_stats64(stats, &dev->stats);
 
-	for (q = 0; q < dev->num_tx_queues; q++) {
-		ring = &priv->tx_rings[q];
-		do {
-			start = u64_stats_fetch_begin_irq(&priv->syncp);
-			tx_bytes = ring->bytes;
-			tx_packets = ring->packets;
-		} while (u64_stats_fetch_retry_irq(&priv->syncp, start));
-
-		stats->tx_bytes += tx_bytes;
-		stats->tx_packets += tx_packets;
-	}
-
-	stats64->tx_bytes = stats->tx_bytes;
-	stats64->tx_packets = stats->tx_packets;
+	bcm_sysport_update_tx_stats(priv, &stats->tx_bytes,
+				    &stats->tx_packets);
 
 	do {
 		start = u64_stats_fetch_begin_irq(&priv->syncp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index aacec8b..dc5de27 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -214,6 +214,8 @@
 	ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
 };
 
+static struct workqueue_struct *bnxt_pf_wq;
+
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
 	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF);
@@ -1024,12 +1026,28 @@
 	return 0;
 }
 
+static void bnxt_queue_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		queue_work(bnxt_pf_wq, &bp->sp_task);
+	else
+		schedule_work(&bp->sp_task);
+}
+
+static void bnxt_cancel_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		flush_workqueue(bnxt_pf_wq);
+	else
+		cancel_work_sync(&bp->sp_task);
+}
+
 static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	if (!rxr->bnapi->in_reset) {
 		rxr->bnapi->in_reset = true;
 		set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 	rxr->rx_next_cons = 0xffff;
 }
@@ -1717,7 +1735,7 @@
 	default:
 		goto async_event_process_exit;
 	}
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 async_event_process_exit:
 	bnxt_ulp_async_events(bp, cmpl);
 	return 0;
@@ -1751,7 +1769,7 @@
 
 		set_bit(vf_id - bp->pf.first_vf_id, bp->pf.vf_event_bmap);
 		set_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 		break;
 
 	case CMPL_BASE_TYPE_HWRM_ASYNC_EVENT:
@@ -3448,6 +3466,12 @@
 	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, false);
 }
 
+int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 msg_len,
+			      int timeout)
+{
+	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, true);
+}
+
 int hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
 {
 	int rc;
@@ -6327,7 +6351,9 @@
 	}
 
 	if (link_re_init) {
+		mutex_lock(&bp->link_lock);
 		rc = bnxt_update_phy_setting(bp);
+		mutex_unlock(&bp->link_lock);
 		if (rc)
 			netdev_warn(bp->dev, "failed to update phy settings\n");
 	}
@@ -6647,7 +6673,7 @@
 		vnic->rx_mask = mask;
 
 		set_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 }
 
@@ -6920,7 +6946,7 @@
 
 	netdev_err(bp->dev,  "TX timeout detected, starting reset task!\n");
 	set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -6952,7 +6978,7 @@
 	if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS) &&
 	    bp->stats_coal_ticks) {
 		set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
@@ -7025,30 +7051,28 @@
 	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
 		bnxt_hwrm_port_qstats(bp);
 
-	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
-	 * must be the last functions to be called before exiting.
-	 */
 	if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
-		int rc = 0;
+		int rc;
 
+		mutex_lock(&bp->link_lock);
 		if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
 				       &bp->sp_event))
 			bnxt_hwrm_phy_qcaps(bp);
 
-		bnxt_rtnl_lock_sp(bp);
-		if (test_bit(BNXT_STATE_OPEN, &bp->state))
-			rc = bnxt_update_link(bp, true);
-		bnxt_rtnl_unlock_sp(bp);
+		rc = bnxt_update_link(bp, true);
+		mutex_unlock(&bp->link_lock);
 		if (rc)
 			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
 				   rc);
 	}
 	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
-		bnxt_rtnl_lock_sp(bp);
-		if (test_bit(BNXT_STATE_OPEN, &bp->state))
-			bnxt_get_port_module_status(bp);
-		bnxt_rtnl_unlock_sp(bp);
+		mutex_lock(&bp->link_lock);
+		bnxt_get_port_module_status(bp);
+		mutex_unlock(&bp->link_lock);
 	}
+	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
+	 * must be the last functions to be called before exiting.
+	 */
 	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
 		bnxt_reset(bp, false);
 
@@ -7433,7 +7457,7 @@
 	spin_unlock_bh(&bp->ntp_fltr_lock);
 
 	set_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event);
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 
 	return new_fltr->sw_id;
 
@@ -7516,7 +7540,7 @@
 		if (bp->vxlan_port_cnt == 1) {
 			bp->vxlan_port = ti->port;
 			set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event);
-			schedule_work(&bp->sp_task);
+			bnxt_queue_sp_work(bp);
 		}
 		break;
 	case UDP_TUNNEL_TYPE_GENEVE:
@@ -7533,7 +7557,7 @@
 		return;
 	}
 
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 static void bnxt_udp_tunnel_del(struct net_device *dev,
@@ -7572,7 +7596,7 @@
 		return;
 	}
 
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
@@ -7720,7 +7744,7 @@
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	bnxt_shutdown_tc(bp);
-	cancel_work_sync(&bp->sp_task);
+	bnxt_cancel_sp_work(bp);
 	bp->sp_event = 0;
 
 	bnxt_clear_int_mode(bp);
@@ -7748,6 +7772,7 @@
 			   rc);
 		return rc;
 	}
+	mutex_init(&bp->link_lock);
 
 	rc = bnxt_update_link(bp, false);
 	if (rc) {
@@ -7946,7 +7971,7 @@
 	enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN;
 	enum pci_bus_speed speed = PCI_SPEED_UNKNOWN;
 
-	if (pcie_get_minimum_link(bp->pdev, &speed, &width) ||
+	if (pcie_get_minimum_link(pci_physfn(bp->pdev), &speed, &width) ||
 	    speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN)
 		netdev_info(bp->dev, "Failed to determine PCIe Link Info\n");
 	else
@@ -8138,8 +8163,17 @@
 	else
 		device_set_wakeup_capable(&pdev->dev, false);
 
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp)) {
+		if (!bnxt_pf_wq) {
+			bnxt_pf_wq =
+				create_singlethread_workqueue("bnxt_pf_wq");
+			if (!bnxt_pf_wq) {
+				dev_err(&pdev->dev, "Unable to create workqueue.\n");
+				goto init_err_pci_clean;
+			}
+		}
 		bnxt_init_tc(bp);
+	}
 
 	rc = register_netdev(dev);
 	if (rc)
@@ -8375,4 +8409,17 @@
 #endif
 };
 
-module_pci_driver(bnxt_pci_driver);
+static int __init bnxt_init(void)
+{
+	return pci_register_driver(&bnxt_pci_driver);
+}
+
+static void __exit bnxt_exit(void)
+{
+	pci_unregister_driver(&bnxt_pci_driver);
+	if (bnxt_pf_wq)
+		destroy_workqueue(bnxt_pf_wq);
+}
+
+module_init(bnxt_init);
+module_exit(bnxt_exit);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 7b888d4..c911e69 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1290,6 +1290,10 @@
 	unsigned long		*ntp_fltr_bmap;
 	int			ntp_fltr_count;
 
+	/* To protect link related settings during link changes and
+	 * ethtool settings changes.
+	 */
+	struct mutex		link_lock;
 	struct bnxt_link_info	link_info;
 	struct ethtool_eee	eee;
 	u32			lpi_tmr_lo;
@@ -1358,6 +1362,7 @@
 int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 void bnxt_hwrm_cmd_hdr_init(struct bnxt *, void *, u16, u16, u16);
 int _hwrm_send_message(struct bnxt *, void *, u32, int);
+int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 len, int timeout);
 int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index aa1f3a2..fed37cd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -50,7 +50,9 @@
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
 	req.flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		u8 *pri2cos = &resp->pri0_cos_queue_id;
 		int i, j;
@@ -66,6 +68,7 @@
 			}
 		}
 	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -119,9 +122,13 @@
 	int rc, i;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_QCFG, -1, -1);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
 		return rc;
+	}
 
 	data = &resp->queue_id0 + offsetof(struct bnxt_cos2bw_cfg, queue_id);
 	for (i = 0; i < bp->max_tc; i++, data += sizeof(cos2bw) - 4) {
@@ -143,6 +150,7 @@
 			}
 		}
 	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return 0;
 }
 
@@ -240,12 +248,17 @@
 	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_QCFG, -1, -1);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
 		return rc;
+	}
 
 	pri_mask = le32_to_cpu(resp->flags);
 	pfc->pfc_en = pri_mask;
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 8eff05a..3cbe771 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1052,6 +1052,7 @@
 	u32 ethtool_speed;
 
 	ethtool_link_ksettings_zero_link_mode(lk_ksettings, supported);
+	mutex_lock(&bp->link_lock);
 	bnxt_fw_to_ethtool_support_spds(link_info, lk_ksettings);
 
 	ethtool_link_ksettings_zero_link_mode(lk_ksettings, advertising);
@@ -1099,6 +1100,7 @@
 			base->port = PORT_FIBRE;
 	}
 	base->phy_address = link_info->phy_addr;
+	mutex_unlock(&bp->link_lock);
 
 	return 0;
 }
@@ -1190,6 +1192,7 @@
 	if (!BNXT_SINGLE_PF(bp))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
 	if (base->autoneg == AUTONEG_ENABLE) {
 		BNXT_ETHTOOL_TO_FW_SPDS(fw_advertising, lk_ksettings,
 					advertising);
@@ -1234,6 +1237,7 @@
 		rc = bnxt_hwrm_set_link_setting(bp, set_pause, false);
 
 set_setting_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
@@ -1805,7 +1809,8 @@
 	req.dir_ordinal = cpu_to_le16(ordinal);
 	req.dir_ext = cpu_to_le16(ext);
 	req.opt_ordinal = NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ;
-	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc == 0) {
 		if (index)
 			*index = le16_to_cpu(output->dir_idx);
@@ -1814,6 +1819,7 @@
 		if (data_length)
 			*data_length = le32_to_cpu(output->dir_data_length);
 	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index d37925a..5ee1866 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -502,6 +502,7 @@
 	int rc = 0, vfs_supported;
 	int min_rx_rings, min_tx_rings, min_rss_ctxs;
 	int tx_ok = 0, rx_ok = 0, rss_ok = 0;
+	int avail_cp, avail_stat;
 
 	/* Check if we can enable requested num of vf's. At a mininum
 	 * we require 1 RX 1 TX rings for each VF. In this minimum conf
@@ -509,6 +510,10 @@
 	 */
 	vfs_supported = *num_vfs;
 
+	avail_cp = bp->pf.max_cp_rings - bp->cp_nr_rings;
+	avail_stat = bp->pf.max_stat_ctxs - bp->num_stat_ctxs;
+	avail_cp = min_t(int, avail_cp, avail_stat);
+
 	while (vfs_supported) {
 		min_rx_rings = vfs_supported;
 		min_tx_rings = vfs_supported;
@@ -523,10 +528,12 @@
 			    min_rx_rings)
 				rx_ok = 1;
 		}
-		if (bp->pf.max_vnics - bp->nr_vnics < min_rx_rings)
+		if (bp->pf.max_vnics - bp->nr_vnics < min_rx_rings ||
+		    avail_cp < min_rx_rings)
 			rx_ok = 0;
 
-		if (bp->pf.max_tx_rings - bp->tx_nr_rings >= min_tx_rings)
+		if (bp->pf.max_tx_rings - bp->tx_nr_rings >= min_tx_rings &&
+		    avail_cp >= min_tx_rings)
 			tx_ok = 1;
 
 		if (bp->pf.max_rsscos_ctxs - bp->rsscos_nr_ctxs >= min_rss_ctxs)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index ccd699f..7dd3d13 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -750,6 +750,10 @@
 {
 	int rc = 0;
 
+	if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
+	    cls_flower->common.chain_index)
+		return -EOPNOTSUPP;
+
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
 		rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index cec94bb..8bc126a 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -1278,7 +1278,7 @@
 
 	ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0);
 	if (ret)
-		return -ENOMEM;
+		goto error;
 
 	n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE;
 	for (i = 0, j = 0; i < cp->max_cid_space; i++) {
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index e7f5494..5b19826 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1847,7 +1847,7 @@
 	struct lio *lio = container_of(ptp, struct lio, ptp_info);
 	struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
 
-	ns = timespec_to_ns(ts);
+	ns = timespec64_to_ns(ts);
 
 	spin_lock_irqsave(&lio->ptp_lock, flags);
 	lio_pci_writeq(oct, ns, CN6XXX_MIO_PTP_CLOCK_HI);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 49b80da..805ab45 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -565,8 +565,10 @@
 		return true;
 	default:
 		bpf_warn_invalid_xdp_action(action);
+		/* fall through */
 	case XDP_ABORTED:
 		trace_xdp_exception(nic->netdev, prog, action);
+		/* fall through */
 	case XDP_DROP:
 		/* Check if it's a recycled page, if not
 		 * unmap the DMA mapping.
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 38c7b21..ede1876 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -374,8 +374,8 @@
 #define FEC_ENET_TS_AVAIL       ((uint)0x00010000)
 #define FEC_ENET_TS_TIMER       ((uint)0x00008000)
 
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII | FEC_ENET_TS_TIMER)
-#define FEC_NAPI_IMASK	(FEC_ENET_MII | FEC_ENET_TS_TIMER)
+#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
+#define FEC_NAPI_IMASK	FEC_ENET_MII
 #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
 
 /* ENET interrupt coalescing macro define */
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 56f56d6..3dc2d77 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1559,14 +1559,14 @@
 	if (int_events == 0)
 		return false;
 
-	if (int_events & FEC_ENET_RXF)
+	if (int_events & FEC_ENET_RXF_0)
 		fep->work_rx |= (1 << 2);
 	if (int_events & FEC_ENET_RXF_1)
 		fep->work_rx |= (1 << 0);
 	if (int_events & FEC_ENET_RXF_2)
 		fep->work_rx |= (1 << 1);
 
-	if (int_events & FEC_ENET_TXF)
+	if (int_events & FEC_ENET_TXF_0)
 		fep->work_tx |= (1 << 2);
 	if (int_events & FEC_ENET_TXF_1)
 		fep->work_tx |= (1 << 0);
@@ -1604,8 +1604,8 @@
 	}
 
 	if (fep->ptp_clock)
-		fec_ptp_check_pps_event(fep);
-
+		if (fec_ptp_check_pps_event(fep))
+			ret = IRQ_HANDLED;
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 59efbd6..5bcb223 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -37,20 +37,15 @@
 }
 
 static int hnae3_match_n_instantiate(struct hnae3_client *client,
-				     struct hnae3_ae_dev *ae_dev,
-				     bool is_reg, bool *matched)
+				     struct hnae3_ae_dev *ae_dev, bool is_reg)
 {
 	int ret;
 
-	*matched = false;
-
 	/* check if this client matches the type of ae_dev */
 	if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
 	      hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
 		return 0;
 	}
-	/* there is a match of client and dev */
-	*matched = true;
 
 	/* now, (un-)instantiate client by calling lower layer */
 	if (is_reg) {
@@ -69,7 +64,6 @@
 {
 	struct hnae3_client *client_tmp;
 	struct hnae3_ae_dev *ae_dev;
-	bool matched;
 	int ret = 0;
 
 	mutex_lock(&hnae3_common_lock);
@@ -86,7 +80,7 @@
 		/* if the client could not be initialized on current port, for
 		 * any error reasons, move on to next available port
 		 */
-		ret = hnae3_match_n_instantiate(client, ae_dev, true, &matched);
+		ret = hnae3_match_n_instantiate(client, ae_dev, true);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
 				"match and instantiation failed for port\n");
@@ -102,12 +96,11 @@
 void hnae3_unregister_client(struct hnae3_client *client)
 {
 	struct hnae3_ae_dev *ae_dev;
-	bool matched;
 
 	mutex_lock(&hnae3_common_lock);
 	/* un-initialize the client on every matched port */
 	list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
-		hnae3_match_n_instantiate(client, ae_dev, false, &matched);
+		hnae3_match_n_instantiate(client, ae_dev, false);
 	}
 
 	list_del(&client->node);
@@ -124,7 +117,6 @@
 	const struct pci_device_id *id;
 	struct hnae3_ae_dev *ae_dev;
 	struct hnae3_client *client;
-	bool matched;
 	int ret = 0;
 
 	mutex_lock(&hnae3_common_lock);
@@ -151,13 +143,10 @@
 		 * initialize the figure out client instance
 		 */
 		list_for_each_entry(client, &hnae3_client_list, node) {
-			ret = hnae3_match_n_instantiate(client, ae_dev, true,
-							&matched);
+			ret = hnae3_match_n_instantiate(client, ae_dev, true);
 			if (ret)
 				dev_err(&ae_dev->pdev->dev,
 					"match and instantiation failed\n");
-			if (matched)
-				break;
 		}
 	}
 
@@ -175,7 +164,6 @@
 	const struct pci_device_id *id;
 	struct hnae3_ae_dev *ae_dev;
 	struct hnae3_client *client;
-	bool matched;
 
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_dev */
@@ -187,12 +175,8 @@
 		/* check the client list for the match with this ae_dev type and
 		 * un-initialize the figure out client instance
 		 */
-		list_for_each_entry(client, &hnae3_client_list, node) {
-			hnae3_match_n_instantiate(client, ae_dev, false,
-						  &matched);
-			if (matched)
-				break;
-		}
+		list_for_each_entry(client, &hnae3_client_list, node)
+			hnae3_match_n_instantiate(client, ae_dev, false);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
 		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
@@ -212,7 +196,6 @@
 	const struct pci_device_id *id;
 	struct hnae3_ae_algo *ae_algo;
 	struct hnae3_client *client;
-	bool matched;
 	int ret = 0;
 
 	mutex_lock(&hnae3_common_lock);
@@ -246,13 +229,10 @@
 	 * initialize the figure out client instance
 	 */
 	list_for_each_entry(client, &hnae3_client_list, node) {
-		ret = hnae3_match_n_instantiate(client, ae_dev, true,
-						&matched);
+		ret = hnae3_match_n_instantiate(client, ae_dev, true);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
 				"match and instantiation failed\n");
-		if (matched)
-			break;
 	}
 
 out_err:
@@ -270,7 +250,6 @@
 	const struct pci_device_id *id;
 	struct hnae3_ae_algo *ae_algo;
 	struct hnae3_client *client;
-	bool matched;
 
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_algo */
@@ -279,12 +258,8 @@
 		if (!id)
 			continue;
 
-		list_for_each_entry(client, &hnae3_client_list, node) {
-			hnae3_match_n_instantiate(client, ae_dev, false,
-						  &matched);
-			if (matched)
-				break;
-		}
+		list_for_each_entry(client, &hnae3_client_list, node)
+			hnae3_match_n_instantiate(client, ae_dev, false);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
 		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index b2f28ae..1a01cad 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -49,7 +49,17 @@
 #define HNAE3_CLASS_NAME_SIZE 16
 
 #define HNAE3_DEV_INITED_B			0x0
-#define HNAE_DEV_SUPPORT_ROCE_B			0x1
+#define HNAE3_DEV_SUPPORT_ROCE_B		0x1
+#define HNAE3_DEV_SUPPORT_DCB_B			0x2
+
+#define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
+		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
+
+#define hnae3_dev_roce_supported(hdev) \
+	hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+
+#define hnae3_dev_dcb_supported(hdev) \
+	hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
 
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
@@ -366,12 +376,12 @@
 struct hnae3_tc_info {
 	u16	tqp_offset;	/* TQP offset from base TQP */
 	u16	tqp_count;	/* Total TQPs */
-	u8	up;		/* user priority */
 	u8	tc;		/* TC index */
 	bool	enable;		/* If this TC is enable or not */
 };
 
 #define HNAE3_MAX_TC		8
+#define HNAE3_MAX_USER_PRIO	8
 struct hnae3_knic_private_info {
 	struct net_device *netdev; /* Set by KNIC client when init instance */
 	u16 rss_size;		   /* Allocated RSS queues */
@@ -379,6 +389,7 @@
 	u16 num_desc;
 
 	u8 num_tc;		   /* Total number of enabled TCs */
+	u8 prio_tc[HNAE3_MAX_USER_PRIO];  /* TC indexed by prio */
 	struct hnae3_tc_info tc_info[HNAE3_MAX_TC]; /* Idx of array is HW TC */
 
 	u16 num_tqps;		  /* total number of TQPs in this handle */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 91ae013..758cf39 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -238,7 +238,7 @@
 	u8 rsv[18];
 };
 
-#define HCLGE_VECTOR_ELEMENTS_PER_CMD	11
+#define HCLGE_VECTOR_ELEMENTS_PER_CMD	10
 
 enum hclge_int_type {
 	HCLGE_INT_TX,
@@ -252,8 +252,12 @@
 #define HCLGE_INT_TYPE_S	0
 #define HCLGE_INT_TYPE_M	0x3
 #define HCLGE_TQP_ID_S		2
-#define HCLGE_TQP_ID_M		(0x3fff << HCLGE_TQP_ID_S)
+#define HCLGE_TQP_ID_M		(0x7ff << HCLGE_TQP_ID_S)
+#define HCLGE_INT_GL_IDX_S	13
+#define HCLGE_INT_GL_IDX_M	(0x3 << HCLGE_INT_GL_IDX_S)
 	__le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD];
+	u8 vfid;
+	u8 rsv;
 };
 
 #define HCLGE_TC_NUM		8
@@ -266,7 +270,8 @@
 
 struct hclge_rx_priv_buff {
 	__le16 buf_num[HCLGE_TC_NUM];
-	u8 rsv[8];
+	__le16 shared_buf;
+	u8 rsv[6];
 };
 
 struct hclge_query_version {
@@ -684,6 +689,7 @@
 #define HCLGE_DEFAULT_TX_BUF		0x4000	 /* 16k  bytes */
 #define HCLGE_TOTAL_PKT_BUF		0x108000 /* 1.03125M bytes */
 #define HCLGE_DEFAULT_DV		0xA000	 /* 40k byte */
+#define HCLGE_DEFAULT_NON_DCB_DV	0x7800	/* 30K byte */
 
 #define HCLGE_TYPE_CRQ			0
 #define HCLGE_TYPE_CSQ			1
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index bb45365..c1cdbfd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -46,17 +46,7 @@
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
-	/* Required last entry */
-	{0, }
-};
-
-static const struct pci_device_id roce_pci_tbl[] = {
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
-	/* Required last entry */
+	/* required last entry */
 	{0, }
 };
 
@@ -894,7 +884,7 @@
 	hdev->num_tqps = __le16_to_cpu(req->tqp_num);
 	hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
 
-	if (hnae_get_bit(hdev->ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B)) {
+	if (hnae3_dev_roce_supported(hdev)) {
 		hdev->num_roce_msix =
 		hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
 			       HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
@@ -1063,9 +1053,9 @@
 	hdev->base_tqp_pid = 0;
 	hdev->rss_size_max = 1;
 	hdev->rx_buf_len = cfg.rx_buf_len;
-	for (i = 0; i < ETH_ALEN; i++)
-		hdev->hw.mac.mac_addr[i] = cfg.mac_addr[i];
+	ether_addr_copy(hdev->hw.mac.mac_addr, cfg.mac_addr);
 	hdev->hw.mac.media_type = cfg.media_type;
+	hdev->hw.mac.phy_addr = cfg.phy_addr;
 	hdev->num_desc = cfg.tqp_desc_num;
 	hdev->tm_info.num_pg = 1;
 	hdev->tm_info.num_tc = cfg.tc_num;
@@ -1454,7 +1444,11 @@
 	tc_num = hclge_get_tc_num(hdev);
 	pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
 
-	shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+	if (hnae3_dev_dcb_supported(hdev))
+		shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+	else
+		shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_NON_DCB_DV;
+
 	shared_buf_tc = pfc_enable_num * hdev->mps +
 			(tc_num - pfc_enable_num) * hdev->mps / 2 +
 			hdev->mps;
@@ -1495,6 +1489,16 @@
 	struct hclge_priv_buf *priv;
 	int i;
 
+	/* When DCB is not supported, rx private
+	 * buffer is not allocated.
+	 */
+	if (!hnae3_dev_dcb_supported(hdev)) {
+		if (!hclge_is_rx_buf_ok(hdev, rx_all))
+			return -ENOMEM;
+
+		return 0;
+	}
+
 	/* step 1, try to alloc private buffer for all enabled tc */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		priv = &hdev->priv_buf[i];
@@ -1510,6 +1514,11 @@
 				priv->wl.high = 2 * hdev->mps;
 				priv->buf_size = priv->wl.high;
 			}
+		} else {
+			priv->enable = 0;
+			priv->wl.low = 0;
+			priv->wl.high = 0;
+			priv->buf_size = 0;
 		}
 	}
 
@@ -1522,8 +1531,15 @@
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		priv = &hdev->priv_buf[i];
 
-		if (hdev->hw_tc_map & BIT(i))
-			priv->enable = 1;
+		priv->enable = 0;
+		priv->wl.low = 0;
+		priv->wl.high = 0;
+		priv->buf_size = 0;
+
+		if (!(hdev->hw_tc_map & BIT(i)))
+			continue;
+
+		priv->enable = 1;
 
 		if (hdev->tm_info.hw_pfc_map & BIT(i)) {
 			priv->wl.low = 128;
@@ -1616,6 +1632,10 @@
 			cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B);
 	}
 
+	req->shared_buf =
+		cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
+			    (1 << HCLGE_TC0_PRI_BUF_EN_B));
+
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
@@ -1782,18 +1802,22 @@
 		return ret;
 	}
 
-	ret = hclge_rx_priv_wl_config(hdev);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"could not configure rx private waterline %d\n", ret);
-		return ret;
-	}
+	if (hnae3_dev_dcb_supported(hdev)) {
+		ret = hclge_rx_priv_wl_config(hdev);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"could not configure rx private waterline %d\n",
+				ret);
+			return ret;
+		}
 
-	ret = hclge_common_thrd_config(hdev);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"could not configure common threshold %d\n", ret);
-		return ret;
+		ret = hclge_common_thrd_config(hdev);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"could not configure common threshold %d\n",
+				ret);
+			return ret;
+		}
 	}
 
 	ret = hclge_common_wl_config(hdev);
@@ -2582,6 +2606,7 @@
 	u16 tc_valid[HCLGE_MAX_TC_NUM];
 	u16 tc_size[HCLGE_MAX_TC_NUM];
 	u32 *rss_indir = NULL;
+	u16 rss_size = 0, roundup_size;
 	const u8 *key;
 	int i, ret, j;
 
@@ -2596,7 +2621,13 @@
 	for (j = 0; j < hdev->num_vmdq_vport + 1; j++) {
 		for (i = 0; i < HCLGE_RSS_IND_TBL_SIZE; i++) {
 			vport[j].rss_indirection_tbl[i] =
-				i % hdev->rss_size_max;
+				i % vport[j].alloc_rss_size;
+
+			/* vport 0 is for PF */
+			if (j != 0)
+				continue;
+
+			rss_size = vport[j].alloc_rss_size;
 			rss_indir[i] = vport[j].rss_indirection_tbl[i];
 		}
 	}
@@ -2613,42 +2644,32 @@
 	if (ret)
 		goto err;
 
-	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		if (hdev->hw_tc_map & BIT(i))
-			tc_valid[i] = 1;
-		else
-			tc_valid[i] = 0;
-
-		switch (hdev->rss_size_max) {
-		case HCLGE_RSS_TC_SIZE_0:
-			tc_size[i] = 0;
-			break;
-		case HCLGE_RSS_TC_SIZE_1:
-			tc_size[i] = 1;
-			break;
-		case HCLGE_RSS_TC_SIZE_2:
-			tc_size[i] = 2;
-			break;
-		case HCLGE_RSS_TC_SIZE_3:
-			tc_size[i] = 3;
-			break;
-		case HCLGE_RSS_TC_SIZE_4:
-			tc_size[i] = 4;
-			break;
-		case HCLGE_RSS_TC_SIZE_5:
-			tc_size[i] = 5;
-			break;
-		case HCLGE_RSS_TC_SIZE_6:
-			tc_size[i] = 6;
-			break;
-		case HCLGE_RSS_TC_SIZE_7:
-			tc_size[i] = 7;
-			break;
-		default:
-			break;
-		}
-		tc_offset[i] = hdev->rss_size_max * i;
+	/* Each TC have the same queue size, and tc_size set to hardware is
+	 * the log2 of roundup power of two of rss_size, the acutal queue
+	 * size is limited by indirection table.
+	 */
+	if (rss_size > HCLGE_RSS_TC_SIZE_7 || rss_size == 0) {
+		dev_err(&hdev->pdev->dev,
+			"Configure rss tc size failed, invalid TC_SIZE = %d\n",
+			rss_size);
+		ret = -EINVAL;
+		goto err;
 	}
+
+	roundup_size = roundup_pow_of_two(rss_size);
+	roundup_size = ilog2(roundup_size);
+
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
+		tc_valid[i] = 0;
+
+		if (!(hdev->hw_tc_map & BIT(i)))
+			continue;
+
+		tc_valid[i] = 1;
+		tc_size[i] = roundup_size;
+		tc_offset[i] = rss_size * i;
+	}
+
 	ret = hclge_set_rss_tc_mode(hdev, tc_valid, tc_size, tc_offset);
 
 err:
@@ -2679,7 +2700,11 @@
 			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
 		hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
 			       HCLGE_TQP_ID_S,	node->tqp_index);
+		hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+			       HCLGE_INT_GL_IDX_S,
+			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
 		req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+		req->vfid = vport->vport_id;
 
 		if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
 			req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
@@ -2763,8 +2788,12 @@
 			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
 		hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
 			       HCLGE_TQP_ID_S,	node->tqp_index);
+		hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+			       HCLGE_INT_GL_IDX_S,
+			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
 
 		req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+		req->vfid = vport->vport_id;
 
 		if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
 			req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
@@ -2778,7 +2807,7 @@
 			}
 			i = 0;
 			hclge_cmd_setup_basic_desc(&desc,
-						   HCLGE_OPC_ADD_RING_TO_VECTOR,
+						   HCLGE_OPC_DEL_RING_TO_VECTOR,
 						   false);
 			req->int_vector_id = vector_id;
 		}
@@ -3665,6 +3694,7 @@
 {
 #define HCLGE_VLAN_TYPE_VF_TABLE   0
 #define HCLGE_VLAN_TYPE_PORT_TABLE 1
+	struct hnae3_handle *handle;
 	int ret;
 
 	ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_VF_TABLE,
@@ -3674,8 +3704,11 @@
 
 	ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_PORT_TABLE,
 					 true);
+	if (ret)
+		return ret;
 
-	return ret;
+	handle = &hdev->vport[0].nic;
+	return hclge_set_port_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
 }
 
 static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
@@ -3920,8 +3953,7 @@
 				goto err;
 
 			if (hdev->roce_client &&
-			    hnae_get_bit(hdev->ae_dev->flag,
-					 HNAE_DEV_SUPPORT_ROCE_B)) {
+			    hnae3_dev_roce_supported(hdev)) {
 				struct hnae3_client *rc = hdev->roce_client;
 
 				ret = hclge_init_roce_base_info(vport);
@@ -3944,8 +3976,7 @@
 
 			break;
 		case HNAE3_CLIENT_ROCE:
-			if (hnae_get_bit(hdev->ae_dev->flag,
-					 HNAE_DEV_SUPPORT_ROCE_B)) {
+			if (hnae3_dev_roce_supported(hdev)) {
 				hdev->roce_client = client;
 				vport->roce.client = client;
 			}
@@ -4057,7 +4088,6 @@
 static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
-	const struct pci_device_id *id;
 	struct hclge_dev *hdev;
 	int ret;
 
@@ -4072,10 +4102,6 @@
 	hdev->ae_dev = ae_dev;
 	ae_dev->priv = hdev;
 
-	id = pci_match_id(roce_pci_tbl, ae_dev->pdev);
-	if (id)
-		hnae_set_bit(ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B, 1);
-
 	ret = hclge_pci_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "PCI init failed\n");
@@ -4138,12 +4164,6 @@
 		return ret;
 	}
 
-	ret = hclge_rss_init_hw(hdev);
-	if (ret) {
-		dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
-		return  ret;
-	}
-
 	ret = hclge_init_vlan_config(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
@@ -4156,6 +4176,12 @@
 		return ret;
 	}
 
+	ret = hclge_rss_init_hw(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
+		return ret;
+	}
+
 	setup_timer(&hdev->service_timer, hclge_service_timer,
 		    (unsigned long)hdev);
 	INIT_WORK(&hdev->service_task, hclge_service_task);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index edb10ad..9fcfd93 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -176,7 +176,6 @@
 struct hclge_tc_info {
 	u8 tc_id;
 	u8 tc_sch_mode;		/* 0: sp; 1: dwrr */
-	u8 up;
 	u8 pgid;
 	u32 bw_limit;
 };
@@ -197,6 +196,7 @@
 	u8 num_tc;
 	u8 num_pg;      /* It must be 1 if vNET-Base schd */
 	u8 pg_dwrr[HCLGE_PG_NUM];
+	u8 prio_tc[HNAE3_MAX_USER_PRIO];
 	struct hclge_pg_info pg_info[HCLGE_PG_NUM];
 	struct hclge_tc_info tc_info[HNAE3_MAX_TC];
 	enum hclge_fc_mode fc_mode;
@@ -477,6 +477,7 @@
 	u8  rss_hash_key[HCLGE_RSS_KEY_SIZE]; /* User configured hash keys */
 	/* User configured lookup table entries */
 	u8  rss_indirection_tbl[HCLGE_RSS_IND_TBL_SIZE];
+	u16 alloc_rss_size;
 
 	u16 qs_offset;
 	u16 bw_limit;		/* VSI BW Limit (0 = disabled) */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 1c577d2..73a75d7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -128,9 +128,7 @@
 {
 	u8 tc;
 
-	for (tc = 0; tc < hdev->tm_info.num_tc; tc++)
-		if (hdev->tm_info.tc_info[tc].up == pri_id)
-			break;
+	tc = hdev->tm_info.prio_tc[pri_id];
 
 	if (tc >= hdev->tm_info.num_tc)
 		return -EINVAL;
@@ -158,7 +156,7 @@
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, false);
 
-	for (pri_id = 0; pri_id < hdev->tm_info.num_tc; pri_id++) {
+	for (pri_id = 0; pri_id < HNAE3_MAX_USER_PRIO; pri_id++) {
 		ret = hclge_fill_pri_array(hdev, pri, pri_id);
 		if (ret)
 			return ret;
@@ -280,11 +278,11 @@
 
 	shap_cfg_cmd->pg_id = pg_id;
 
-	hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b);
-	hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u);
-	hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s);
-	hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b);
-	hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s);
+	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b);
+	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u);
+	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s);
+	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b);
+	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
@@ -307,11 +305,11 @@
 
 	shap_cfg_cmd->pri_id = pri_id;
 
-	hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b);
-	hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u);
-	hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s);
-	hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b);
-	hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s);
+	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b);
+	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u);
+	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s);
+	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b);
+	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
@@ -397,6 +395,7 @@
 			kinfo->num_tqps / kinfo->num_tc);
 	vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id;
 	vport->dwrr = 100;  /* 100 percent as init */
+	vport->alloc_rss_size = kinfo->rss_size;
 
 	for (i = 0; i < kinfo->num_tc; i++) {
 		if (hdev->hw_tc_map & BIT(i)) {
@@ -404,16 +403,17 @@
 			kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size;
 			kinfo->tc_info[i].tqp_count = kinfo->rss_size;
 			kinfo->tc_info[i].tc = i;
-			kinfo->tc_info[i].up = hdev->tm_info.tc_info[i].up;
 		} else {
 			/* Set to default queue if TC is disable */
 			kinfo->tc_info[i].enable = false;
 			kinfo->tc_info[i].tqp_offset = 0;
 			kinfo->tc_info[i].tqp_count = 1;
 			kinfo->tc_info[i].tc = 0;
-			kinfo->tc_info[i].up = 0;
 		}
 	}
+
+	memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc,
+	       FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc));
 }
 
 static void hclge_tm_vport_info_update(struct hclge_dev *hdev)
@@ -435,12 +435,15 @@
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
 		hdev->tm_info.tc_info[i].tc_id = i;
 		hdev->tm_info.tc_info[i].tc_sch_mode = HCLGE_SCH_MODE_DWRR;
-		hdev->tm_info.tc_info[i].up = i;
 		hdev->tm_info.tc_info[i].pgid = 0;
 		hdev->tm_info.tc_info[i].bw_limit =
 			hdev->tm_info.pg_info[0].bw_limit;
 	}
 
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
+		hdev->tm_info.prio_tc[i] =
+			(i >= hdev->tm_info.num_tc) ? 0 : i;
+
 	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
 }
 
@@ -976,6 +979,10 @@
 	if (ret)
 		return ret;
 
+	/* Only DCB-supported dev supports qset back pressure setting */
+	if (!hnae3_dev_dcb_supported(hdev))
+		return 0;
+
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
 		ret = hclge_tm_qs_bp_cfg(hdev, i);
 		if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 7e67337..85158b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -94,10 +94,10 @@
 	u32 rsvd1;
 };
 
-#define hclge_tm_set_feild(dest, string, val) \
+#define hclge_tm_set_field(dest, string, val) \
 			hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
 				       (HCLGE_TM_SHAP_##string##_LSH), val)
-#define hclge_tm_get_feild(src, string) \
+#define hclge_tm_get_field(src, string) \
 			hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
 				       (HCLGE_TM_SHAP_##string##_LSH))
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 1c3e294..35369e1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -41,11 +41,16 @@
 static const struct pci_device_id hns3_pci_tbl[] = {
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_GE), 0},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	/* required last entry */
 	{0, }
 };
@@ -1348,6 +1353,7 @@
 	}
 
 	ae_dev->pdev = pdev;
+	ae_dev->flag = ent->driver_data;
 	ae_dev->dev_type = HNAE3_DEV_KNIC;
 	pci_set_drvdata(pdev, ae_dev);
 
@@ -2705,10 +2711,11 @@
 		eth_hw_addr_random(netdev);
 		dev_warn(priv->dev, "using random MAC address %pM\n",
 			 netdev->dev_addr);
-		/* Also copy this new MAC address into hdev */
-		if (h->ae_algo->ops->set_mac_addr)
-			h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr);
 	}
+
+	if (h->ae_algo->ops->set_mac_addr)
+		h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr);
+
 }
 
 static void hns3_nic_set_priv_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index 2c74baa..fff09dc 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -402,7 +402,7 @@
 	unsigned long flags;
 
 	MAL_DBG2(mal, "poll(%d)" NL, budget);
- again:
+
 	/* Process TX skbs */
 	list_for_each(l, &mal->poll_list) {
 		struct mal_commac *mc =
@@ -451,7 +451,6 @@
 			spin_lock_irqsave(&mal->lock, flags);
 			mal_disable_eob_irq(mal);
 			spin_unlock_irqrestore(&mal->lock, flags);
-			goto again;
 		}
 		mc->ops->poll_tx(mc->dev);
 	}
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index cb8182f..c66abd4 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1093,11 +1093,12 @@
  * places them in a descriptor array, scrq_arr
  */
 
-static void create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
-			     union sub_crq *scrq_arr)
+static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
+			    union sub_crq *scrq_arr)
 {
 	union sub_crq hdr_desc;
 	int tmp_len = len;
+	int num_descs = 0;
 	u8 *data, *cur;
 	int tmp;
 
@@ -1126,7 +1127,10 @@
 		tmp_len -= tmp;
 		*scrq_arr = hdr_desc;
 		scrq_arr++;
+		num_descs++;
 	}
+
+	return num_descs;
 }
 
 /**
@@ -1144,16 +1148,12 @@
 				int *num_entries, u8 hdr_field)
 {
 	int hdr_len[3] = {0, 0, 0};
-	int tot_len, len;
+	int tot_len;
 	u8 *hdr_data = txbuff->hdr_data;
 
 	tot_len = build_hdr_data(hdr_field, txbuff->skb, hdr_len,
 				 txbuff->hdr_data);
-	len = tot_len;
-	len -= 24;
-	if (len > 0)
-		num_entries += len % 29 ? len / 29 + 1 : len / 29;
-	create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len,
+	*num_entries += create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len,
 			 txbuff->indir_arr + 1);
 }
 
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index ec8aa45..3b3983a 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -1824,11 +1824,12 @@
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	int i;
-	char *p = NULL;
 	const struct e1000_stats *stat = e1000_gstrings_stats;
 
 	e1000_update_stats(adapter);
-	for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) {
+	for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++, stat++) {
+		char *p;
+
 		switch (stat->type) {
 		case NETDEV_STATS:
 			p = (char *)netdev + stat->stat_offset;
@@ -1839,15 +1840,13 @@
 		default:
 			WARN_ONCE(1, "Invalid E1000 stat type: %u index %d\n",
 				  stat->type, i);
-			break;
+			continue;
 		}
 
 		if (stat->sizeof_stat == sizeof(u64))
 			data[i] = *(u64 *)p;
 		else
 			data[i] = *(u32 *)p;
-
-		stat++;
 	}
 /* BUG_ON(i != E1000_STATS_LEN); */
 }
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 98375e1..1982f79 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -520,8 +520,6 @@
 	struct net_device *netdev = adapter->netdev;
 	u32 rctl, tctl;
 
-	netif_carrier_off(netdev);
-
 	/* disable receives in the hardware */
 	rctl = er32(RCTL);
 	ew32(RCTL, rctl & ~E1000_RCTL_EN);
@@ -537,6 +535,15 @@
 	E1000_WRITE_FLUSH();
 	msleep(10);
 
+	/* Set the carrier off after transmits have been disabled in the
+	 * hardware, to avoid race conditions with e1000_watchdog() (which
+	 * may be running concurrently to us, checking for the carrier
+	 * bit to decide whether it should enable transmits again). Such
+	 * a race condition would result into transmission being disabled
+	 * in the hardware until the next IFF_DOWN+IFF_UP cycle.
+	 */
+	netif_carrier_off(netdev);
+
 	napi_disable(&adapter->napi);
 
 	e1000_irq_disable(adapter);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 57505b1..d591b3e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -298,7 +298,7 @@
 }
 
 /**
- * __i40e_read_nvm_word - Reads nvm word, assumes called does the locking
+ * __i40e_read_nvm_word - Reads nvm word, assumes caller does the locking
  * @hw: pointer to the HW structure
  * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
  * @data: word read from the Shadow RAM
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1519dfb..120c68f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1038,6 +1038,32 @@
 }
 
 /**
+ * i40e_reuse_rx_page - page flip buffer and store it back on the ring
+ * @rx_ring: rx descriptor ring to store buffers on
+ * @old_buff: donor buffer to have page reused
+ *
+ * Synchronizes page for reuse by the adapter
+ **/
+static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
+			       struct i40e_rx_buffer *old_buff)
+{
+	struct i40e_rx_buffer *new_buff;
+	u16 nta = rx_ring->next_to_alloc;
+
+	new_buff = &rx_ring->rx_bi[nta];
+
+	/* update, and store next to alloc */
+	nta++;
+	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+	/* transfer page from old buffer to new buffer */
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
+}
+
+/**
  * i40e_rx_is_programming_status - check for programming status descriptor
  * @qw: qword representing status_error_len in CPU ordering
  *
@@ -1071,15 +1097,24 @@
 					  union i40e_rx_desc *rx_desc,
 					  u64 qw)
 {
-	u32 ntc = rx_ring->next_to_clean + 1;
+	struct i40e_rx_buffer *rx_buffer;
+	u32 ntc = rx_ring->next_to_clean;
 	u8 id;
 
 	/* fetch, update, and store next to clean */
+	rx_buffer = &rx_ring->rx_bi[ntc++];
 	ntc = (ntc < rx_ring->count) ? ntc : 0;
 	rx_ring->next_to_clean = ntc;
 
 	prefetch(I40E_RX_DESC(rx_ring, ntc));
 
+	/* place unused page back on the ring */
+	i40e_reuse_rx_page(rx_ring, rx_buffer);
+	rx_ring->rx_stats.page_reuse_count++;
+
+	/* clear contents of buffer_info */
+	rx_buffer->page = NULL;
+
 	id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
 		  I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
 
@@ -1639,32 +1674,6 @@
 }
 
 /**
- * i40e_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: rx descriptor ring to store buffers on
- * @old_buff: donor buffer to have page reused
- *
- * Synchronizes page for reuse by the adapter
- **/
-static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
-			       struct i40e_rx_buffer *old_buff)
-{
-	struct i40e_rx_buffer *new_buff;
-	u16 nta = rx_ring->next_to_alloc;
-
-	new_buff = &rx_ring->rx_bi[nta];
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* transfer page from old buffer to new buffer */
-	new_buff->dma		= old_buff->dma;
-	new_buff->page		= old_buff->page;
-	new_buff->page_offset	= old_buff->page_offset;
-	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
-}
-
-/**
  * i40e_page_is_reusable - check if any reuse is possible
  * @page: page struct to check
  *
@@ -2093,6 +2102,7 @@
 
 		if (unlikely(i40e_rx_is_programming_status(qword))) {
 			i40e_clean_programming_status(rx_ring, rx_desc, qword);
+			cleaned_count++;
 			continue;
 		}
 		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
@@ -2260,7 +2270,7 @@
 		goto enable_int;
 	}
 
-	if (ITR_IS_DYNAMIC(tx_itr_setting)) {
+	if (ITR_IS_DYNAMIC(rx_itr_setting)) {
 		rx = i40e_set_new_dynamic_itr(&q_vector->rx);
 		rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr);
 	}
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index fd4a46b..ea69af2 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5326,7 +5326,7 @@
 				       DMA_TO_DEVICE);
 		dma_unmap_len_set(tx_buffer, len, 0);
 
-		if (i--)
+		if (i-- == 0)
 			i += tx_ring->count;
 		tx_buffer = &tx_ring->tx_buffer_info[i];
 	}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index 523f9d0..8a32eb7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -175,31 +175,9 @@
  **/
 static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw)
 {
-#ifndef CONFIG_SPARC
-	u32 regval;
-	u32 i;
-#endif
 	s32 ret_val;
 
 	ret_val = ixgbe_start_hw_generic(hw);
-
-#ifndef CONFIG_SPARC
-	/* Disable relaxed ordering */
-	for (i = 0; ((i < hw->mac.max_tx_queues) &&
-	     (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) {
-		regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(i));
-		regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN;
-		IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(i), regval);
-	}
-
-	for (i = 0; ((i < hw->mac.max_rx_queues) &&
-	     (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) {
-		regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i));
-		regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN |
-			    IXGBE_DCA_RXCTRL_HEAD_WRO_EN);
-		IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval);
-	}
-#endif
 	if (ret_val)
 		return ret_val;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 2c19070..6e6ab6f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -366,25 +366,6 @@
 	}
 	IXGBE_WRITE_FLUSH(hw);
 
-#ifndef CONFIG_ARCH_WANT_RELAX_ORDER
-	/* Disable relaxed ordering */
-	for (i = 0; i < hw->mac.max_tx_queues; i++) {
-		u32 regval;
-
-		regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(i));
-		regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN;
-		IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(i), regval);
-	}
-
-	for (i = 0; i < hw->mac.max_rx_queues; i++) {
-		u32 regval;
-
-		regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i));
-		regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN |
-			    IXGBE_DCA_RXCTRL_HEAD_WRO_EN);
-		IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval);
-	}
-#endif
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 72c5657..c3e7a81 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1048,7 +1048,7 @@
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_ring *temp_ring;
-	int i, err = 0;
+	int i, j, err = 0;
 	u32 new_rx_count, new_tx_count;
 
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
@@ -1085,8 +1085,8 @@
 	}
 
 	/* allocate temporary buffer to store rings in */
-	i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues);
-	i = max_t(int, i, adapter->num_xdp_queues);
+	i = max_t(int, adapter->num_tx_queues + adapter->num_xdp_queues,
+		  adapter->num_rx_queues);
 	temp_ring = vmalloc(i * sizeof(struct ixgbe_ring));
 
 	if (!temp_ring) {
@@ -1118,8 +1118,8 @@
 			}
 		}
 
-		for (i = 0; i < adapter->num_xdp_queues; i++) {
-			memcpy(&temp_ring[i], adapter->xdp_ring[i],
+		for (j = 0; j < adapter->num_xdp_queues; j++, i++) {
+			memcpy(&temp_ring[i], adapter->xdp_ring[j],
 			       sizeof(struct ixgbe_ring));
 
 			temp_ring[i].count = new_tx_count;
@@ -1139,10 +1139,10 @@
 			memcpy(adapter->tx_ring[i], &temp_ring[i],
 			       sizeof(struct ixgbe_ring));
 		}
-		for (i = 0; i < adapter->num_xdp_queues; i++) {
-			ixgbe_free_tx_resources(adapter->xdp_ring[i]);
+		for (j = 0; j < adapter->num_xdp_queues; j++, i++) {
+			ixgbe_free_tx_resources(adapter->xdp_ring[j]);
 
-			memcpy(adapter->xdp_ring[i], &temp_ring[i],
+			memcpy(adapter->xdp_ring[j], &temp_ring[i],
 			       sizeof(struct ixgbe_ring));
 		}
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index d962368..6d5f31e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4881,7 +4881,7 @@
 				IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)))
 		return;
 
-	vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) && ~mask;
+	vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask;
 	IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl);
 
 	if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK)
@@ -8020,29 +8020,23 @@
 	return 0;
 dma_error:
 	dev_err(tx_ring->dev, "TX DMA map failed\n");
-	tx_buffer = &tx_ring->tx_buffer_info[i];
 
 	/* clear dma mappings for failed tx_buffer_info map */
-	while (tx_buffer != first) {
+	for (;;) {
+		tx_buffer = &tx_ring->tx_buffer_info[i];
 		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_page(tx_ring->dev,
 				       dma_unmap_addr(tx_buffer, dma),
 				       dma_unmap_len(tx_buffer, len),
 				       DMA_TO_DEVICE);
 		dma_unmap_len_set(tx_buffer, len, 0);
-
-		if (i--)
+		if (tx_buffer == first)
+			break;
+		if (i == 0)
 			i += tx_ring->count;
-		tx_buffer = &tx_ring->tx_buffer_info[i];
+		i--;
 	}
 
-	if (dma_unmap_len(tx_buffer, len))
-		dma_unmap_single(tx_ring->dev,
-				 dma_unmap_addr(tx_buffer, dma),
-				 dma_unmap_len(tx_buffer, len),
-				 DMA_TO_DEVICE);
-	dma_unmap_len_set(tx_buffer, len, 0);
-
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
 
@@ -8529,6 +8523,10 @@
 		return ixgbe_ptp_set_ts_config(adapter, req);
 	case SIOCGHWTSTAMP:
 		return ixgbe_ptp_get_ts_config(adapter, req);
+	case SIOCGMIIPHY:
+		if (!adapter->hw.phy.ops.read_reg)
+			return -EOPNOTSUPP;
+		/* fall through */
 	default:
 		return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd);
 	}
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index dd0ee26..a37af58 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -333,7 +333,7 @@
 #define     MVPP2_GMAC_INBAND_AN_MASK		BIT(0)
 #define     MVPP2_GMAC_FLOW_CTRL_MASK		GENMASK(2, 1)
 #define     MVPP2_GMAC_PCS_ENABLE_MASK		BIT(3)
-#define     MVPP2_GMAC_PORT_RGMII_MASK		BIT(4)
+#define     MVPP2_GMAC_INTERNAL_CLK_MASK	BIT(4)
 #define     MVPP2_GMAC_DISABLE_PADDING		BIT(5)
 #define     MVPP2_GMAC_PORT_RESET_MASK		BIT(6)
 #define MVPP2_GMAC_AUTONEG_CONFIG		0xc
@@ -676,6 +676,7 @@
 #define MVPP2_PRS_RI_L3_MCAST			BIT(15)
 #define MVPP2_PRS_RI_L3_BCAST			(BIT(15) | BIT(16))
 #define MVPP2_PRS_RI_IP_FRAG_MASK		0x20000
+#define MVPP2_PRS_RI_IP_FRAG_TRUE		BIT(17)
 #define MVPP2_PRS_RI_UDF3_MASK			0x300000
 #define MVPP2_PRS_RI_UDF3_RX_SPECIAL		BIT(21)
 #define MVPP2_PRS_RI_L4_PROTO_MASK		0x1c00000
@@ -792,6 +793,7 @@
 	struct clk *pp_clk;
 	struct clk *gop_clk;
 	struct clk *mg_clk;
+	struct clk *axi_clk;
 
 	/* List of pointers to port structures */
 	struct mvpp2_port **port_list;
@@ -1165,6 +1167,11 @@
 	u32 port_map;
 };
 
+#define IS_TSO_HEADER(txq_pcpu, addr) \
+	((addr) >= (txq_pcpu)->tso_headers_dma && \
+	 (addr) < (txq_pcpu)->tso_headers_dma + \
+	 (txq_pcpu)->size * TSO_HEADER_SIZE)
+
 /* Queue modes */
 #define MVPP2_QDIST_SINGLE_MODE	0
 #define MVPP2_QDIST_MULTI_MODE	1
@@ -1532,7 +1539,7 @@
 	int off = MVPP2_PRS_TCAM_DATA_BYTE(offs);
 	u16 tcam_data;
 
-	tcam_data = (8 << pe->tcam.byte[off + 1]) | pe->tcam.byte[off];
+	tcam_data = (pe->tcam.byte[off + 1] << 8) | pe->tcam.byte[off];
 	if (tcam_data != data)
 		return false;
 	return true;
@@ -2315,7 +2322,7 @@
 	    (proto != IPPROTO_IGMP))
 		return -EINVAL;
 
-	/* Fragmented packet */
+	/* Not fragmented packet */
 	tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID,
 					MVPP2_PE_LAST_FREE_TID);
 	if (tid < 0)
@@ -2334,8 +2341,12 @@
 				  MVPP2_PRS_SRAM_OP_SEL_UDF_ADD);
 	mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
 				 MVPP2_PRS_IPV4_DIP_AI_BIT);
-	mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_MASK,
-				 ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK);
+	mvpp2_prs_sram_ri_update(&pe, ri, ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK);
+
+	mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00,
+				     MVPP2_PRS_TCAM_PROTO_MASK_L);
+	mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00,
+				     MVPP2_PRS_TCAM_PROTO_MASK);
 
 	mvpp2_prs_tcam_data_byte_set(&pe, 5, proto, MVPP2_PRS_TCAM_PROTO_MASK);
 	mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
@@ -2346,7 +2357,7 @@
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4);
 	mvpp2_prs_hw_write(priv, &pe);
 
-	/* Not fragmented packet */
+	/* Fragmented packet */
 	tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID,
 					MVPP2_PE_LAST_FREE_TID);
 	if (tid < 0)
@@ -2358,8 +2369,11 @@
 	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, ri, ri_mask);
 
-	mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, MVPP2_PRS_TCAM_PROTO_MASK_L);
-	mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, MVPP2_PRS_TCAM_PROTO_MASK);
+	mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE,
+				 ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK);
+
+	mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, 0x0);
+	mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, 0x0);
 
 	/* Update shadow table and hw entry */
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4);
@@ -2600,8 +2614,8 @@
 	/* place holders only - no ports */
 	mvpp2_prs_mac_drop_all_set(priv, 0, false);
 	mvpp2_prs_mac_promisc_set(priv, 0, false);
-	mvpp2_prs_mac_multi_set(priv, MVPP2_PE_MAC_MC_ALL, 0, false);
-	mvpp2_prs_mac_multi_set(priv, MVPP2_PE_MAC_MC_IP6, 0, false);
+	mvpp2_prs_mac_multi_set(priv, 0, MVPP2_PE_MAC_MC_ALL, false);
+	mvpp2_prs_mac_multi_set(priv, 0, MVPP2_PE_MAC_MC_IP6, false);
 }
 
 /* Set default entries for various types of dsa packets */
@@ -3382,7 +3396,7 @@
 	struct mvpp2_prs_entry *pe;
 	int tid;
 
-	pe = kzalloc(sizeof(*pe), GFP_KERNEL);
+	pe = kzalloc(sizeof(*pe), GFP_ATOMIC);
 	if (!pe)
 		return NULL;
 	mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_MAC);
@@ -3444,7 +3458,7 @@
 		if (tid < 0)
 			return tid;
 
-		pe = kzalloc(sizeof(*pe), GFP_KERNEL);
+		pe = kzalloc(sizeof(*pe), GFP_ATOMIC);
 		if (!pe)
 			return -ENOMEM;
 		mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_MAC);
@@ -4591,7 +4605,6 @@
 	        val |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK;
 	} else if (phy_interface_mode_is_rgmii(port->phy_interface)) {
 		val &= ~MVPP2_GMAC_PCS_ENABLE_MASK;
-		val |= MVPP2_GMAC_PORT_RGMII_MASK;
 	}
 	writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
 
@@ -5313,8 +5326,9 @@
 		struct mvpp2_txq_pcpu_buf *tx_buf =
 			txq_pcpu->buffs + txq_pcpu->txq_get_index;
 
-		dma_unmap_single(port->dev->dev.parent, tx_buf->dma,
-				 tx_buf->size, DMA_TO_DEVICE);
+		if (!IS_TSO_HEADER(txq_pcpu, tx_buf->dma))
+			dma_unmap_single(port->dev->dev.parent, tx_buf->dma,
+					 tx_buf->size, DMA_TO_DEVICE);
 		if (tx_buf->skb)
 			dev_kfree_skb_any(tx_buf->skb);
 
@@ -5601,7 +5615,7 @@
 
 		txq_pcpu->tso_headers =
 			dma_alloc_coherent(port->dev->dev.parent,
-					   MVPP2_AGGR_TXQ_SIZE * TSO_HEADER_SIZE,
+					   txq_pcpu->size * TSO_HEADER_SIZE,
 					   &txq_pcpu->tso_headers_dma,
 					   GFP_KERNEL);
 		if (!txq_pcpu->tso_headers)
@@ -5615,7 +5629,7 @@
 		kfree(txq_pcpu->buffs);
 
 		dma_free_coherent(port->dev->dev.parent,
-				  MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
+				  txq_pcpu->size * TSO_HEADER_SIZE,
 				  txq_pcpu->tso_headers,
 				  txq_pcpu->tso_headers_dma);
 	}
@@ -5639,7 +5653,7 @@
 		kfree(txq_pcpu->buffs);
 
 		dma_free_coherent(port->dev->dev.parent,
-				  MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
+				  txq_pcpu->size * TSO_HEADER_SIZE,
 				  txq_pcpu->tso_headers,
 				  txq_pcpu->tso_headers_dma);
 	}
@@ -6204,12 +6218,15 @@
 tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq,
 		  struct mvpp2_tx_desc *desc)
 {
+	struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu);
+
 	dma_addr_t buf_dma_addr =
 		mvpp2_txdesc_dma_addr_get(port, desc);
 	size_t buf_sz =
 		mvpp2_txdesc_size_get(port, desc);
-	dma_unmap_single(port->dev->dev.parent, buf_dma_addr,
-			 buf_sz, DMA_TO_DEVICE);
+	if (!IS_TSO_HEADER(txq_pcpu, buf_dma_addr))
+		dma_unmap_single(port->dev->dev.parent, buf_dma_addr,
+				 buf_sz, DMA_TO_DEVICE);
 	mvpp2_txq_desc_put(txq);
 }
 
@@ -6482,7 +6499,7 @@
 	}
 
 	/* Finalize TX processing */
-	if (txq_pcpu->count >= txq->done_pkts_coal)
+	if (!port->has_tx_irqs && txq_pcpu->count >= txq->done_pkts_coal)
 		mvpp2_txq_done(port, txq, txq_pcpu);
 
 	/* Set the timer in case not all frags were processed */
@@ -7496,7 +7513,7 @@
 /* Ports initialization */
 static int mvpp2_port_probe(struct platform_device *pdev,
 			    struct device_node *port_node,
-			    struct mvpp2 *priv)
+			    struct mvpp2 *priv, int index)
 {
 	struct device_node *phy_node;
 	struct phy *comphy;
@@ -7670,7 +7687,7 @@
 	}
 	netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
 
-	priv->port_list[id] = port;
+	priv->port_list[index] = port;
 	return 0;
 
 err_free_port_pcpu:
@@ -7963,6 +7980,18 @@
 		err = clk_prepare_enable(priv->mg_clk);
 		if (err < 0)
 			goto err_gop_clk;
+
+		priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk");
+		if (IS_ERR(priv->axi_clk)) {
+			err = PTR_ERR(priv->axi_clk);
+			if (err == -EPROBE_DEFER)
+				goto err_gop_clk;
+			priv->axi_clk = NULL;
+		} else {
+			err = clk_prepare_enable(priv->axi_clk);
+			if (err < 0)
+				goto err_gop_clk;
+		}
 	}
 
 	/* Get system's tclk rate */
@@ -8005,16 +8034,19 @@
 	}
 
 	/* Initialize ports */
+	i = 0;
 	for_each_available_child_of_node(dn, port_node) {
-		err = mvpp2_port_probe(pdev, port_node, priv);
+		err = mvpp2_port_probe(pdev, port_node, priv, i);
 		if (err < 0)
 			goto err_mg_clk;
+		i++;
 	}
 
 	platform_set_drvdata(pdev, priv);
 	return 0;
 
 err_mg_clk:
+	clk_disable_unprepare(priv->axi_clk);
 	if (priv->hw_version == MVPP22)
 		clk_disable_unprepare(priv->mg_clk);
 err_gop_clk:
@@ -8052,6 +8084,7 @@
 				  aggr_txq->descs_dma);
 	}
 
+	clk_disable_unprepare(priv->axi_clk);
 	clk_disable_unprepare(priv->mg_clk);
 	clk_disable_unprepare(priv->pp_clk);
 	clk_disable_unprepare(priv->gop_clk);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index ff60cf7..fc28171 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -77,35 +77,41 @@
 	list_add_tail(&delayed_event->list, &priv->waiting_events_list);
 }
 
-static void fire_delayed_event_locked(struct mlx5_device_context *dev_ctx,
-				      struct mlx5_core_dev *dev,
-				      struct mlx5_priv *priv)
+static void delayed_event_release(struct mlx5_device_context *dev_ctx,
+				  struct mlx5_priv *priv)
 {
+	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
 	struct mlx5_delayed_event *de;
 	struct mlx5_delayed_event *n;
+	struct list_head temp;
 
-	/* stop delaying events */
+	INIT_LIST_HEAD(&temp);
+
+	spin_lock_irq(&priv->ctx_lock);
+
 	priv->is_accum_events = false;
-
-	/* fire all accumulated events before new event comes */
-	list_for_each_entry_safe(de, n, &priv->waiting_events_list, list) {
+	list_splice_init(&priv->waiting_events_list, &temp);
+	if (!dev_ctx->context)
+		goto out;
+	list_for_each_entry_safe(de, n, &priv->waiting_events_list, list)
 		dev_ctx->intf->event(dev, dev_ctx->context, de->event, de->param);
+
+out:
+	spin_unlock_irq(&priv->ctx_lock);
+
+	list_for_each_entry_safe(de, n, &temp, list) {
 		list_del(&de->list);
 		kfree(de);
 	}
 }
 
-static void cleanup_delayed_evets(struct mlx5_priv *priv)
+/* accumulating events that can come after mlx5_ib calls to
+ * ib_register_device, till adding that interface to the events list.
+ */
+static void delayed_event_start(struct mlx5_priv *priv)
 {
-	struct mlx5_delayed_event *de;
-	struct mlx5_delayed_event *n;
-
 	spin_lock_irq(&priv->ctx_lock);
-	priv->is_accum_events = false;
-	list_for_each_entry_safe(de, n, &priv->waiting_events_list, list) {
-		list_del(&de->list);
-		kfree(de);
-	}
+	priv->is_accum_events = true;
 	spin_unlock_irq(&priv->ctx_lock);
 }
 
@@ -122,11 +128,8 @@
 		return;
 
 	dev_ctx->intf = intf;
-	/* accumulating events that can come after mlx5_ib calls to
-	 * ib_register_device, till adding that interface to the events list.
-	 */
 
-	priv->is_accum_events = true;
+	delayed_event_start(priv);
 
 	dev_ctx->context = intf->add(dev);
 	set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
@@ -137,8 +140,6 @@
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
 
-		fire_delayed_event_locked(dev_ctx, dev, priv);
-
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 		if (dev_ctx->intf->pfault) {
 			if (priv->pfault) {
@@ -150,11 +151,12 @@
 		}
 #endif
 		spin_unlock_irq(&priv->ctx_lock);
-	} else {
-		kfree(dev_ctx);
-		 /* delete all accumulated events */
-		cleanup_delayed_evets(priv);
 	}
+
+	delayed_event_release(dev_ctx, priv);
+
+	if (!dev_ctx->context)
+		kfree(dev_ctx);
 }
 
 static struct mlx5_device_context *mlx5_get_device(struct mlx5_interface *intf,
@@ -205,17 +207,21 @@
 	if (!dev_ctx)
 		return;
 
+	delayed_event_start(priv);
 	if (intf->attach) {
 		if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
-			return;
+			goto out;
 		intf->attach(dev, dev_ctx->context);
 		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
 	} else {
 		if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
-			return;
+			goto out;
 		dev_ctx->context = intf->add(dev);
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
 	}
+
+out:
+	delayed_event_release(dev_ctx, priv);
 }
 
 void mlx5_attach_device(struct mlx5_core_dev *dev)
@@ -414,8 +420,14 @@
 	if (priv->is_accum_events)
 		add_delayed_event(priv, dev, event, param);
 
+	/* After mlx5_detach_device, the dev_ctx->intf is still set and dev_ctx is
+	 * still in priv->ctx_list. In this case, only notify the dev_ctx if its
+	 * ADDED or ATTACHED bit are set.
+	 */
 	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf->event)
+		if (dev_ctx->intf->event &&
+		    (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state) ||
+		     test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)))
 			dev_ctx->intf->event(dev, dev_ctx->context, event, param);
 
 	spin_unlock_irqrestore(&priv->ctx_lock, flags);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index 1e3a6c3..80eef41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -139,7 +139,7 @@
 	{MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO, "NEXT_PRIO"}
 
 TRACE_EVENT(mlx5_fs_set_fte,
-	    TP_PROTO(const struct fs_fte *fte, bool new_fte),
+	    TP_PROTO(const struct fs_fte *fte, int new_fte),
 	    TP_ARGS(fte, new_fte),
 	    TP_STRUCT__entry(
 		__field(const struct fs_fte *, fte)
@@ -149,7 +149,7 @@
 		__field(u32, action)
 		__field(u32, flow_tag)
 		__field(u8,  mask_enable)
-		__field(bool, new_fte)
+		__field(int, new_fte)
 		__array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4))
 		__array(u32, mask_inner, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4))
 		__array(u32, mask_misc, MLX5_ST_SZ_DW(fte_match_set_misc))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index c1d384f..51c4cc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -41,6 +41,11 @@
 #define MLX5E_CEE_STATE_UP    1
 #define MLX5E_CEE_STATE_DOWN  0
 
+enum {
+	MLX5E_VENDOR_TC_GROUP_NUM = 7,
+	MLX5E_LOWEST_PRIO_GROUP   = 0,
+};
+
 /* If dcbx mode is non-host set the dcbx mode to host.
  */
 static int mlx5e_dcbnl_set_dcbx_mode(struct mlx5e_priv *priv,
@@ -85,6 +90,9 @@
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 tc_group[IEEE_8021QAZ_MAX_TCS];
+	bool is_tc_group_6_exist = false;
+	bool is_zero_bw_ets_tc = false;
 	int err = 0;
 	int i;
 
@@ -96,37 +104,64 @@
 		err = mlx5_query_port_prio_tc(mdev, i, &ets->prio_tc[i]);
 		if (err)
 			return err;
-	}
 
-	for (i = 0; i < ets->ets_cap; i++) {
+		err = mlx5_query_port_tc_group(mdev, i, &tc_group[i]);
+		if (err)
+			return err;
+
 		err = mlx5_query_port_tc_bw_alloc(mdev, i, &ets->tc_tx_bw[i]);
 		if (err)
 			return err;
-		if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC)
-			priv->dcbx.tc_tsa[i] = IEEE_8021QAZ_TSA_ETS;
+
+		if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC &&
+		    tc_group[i] == (MLX5E_LOWEST_PRIO_GROUP + 1))
+			is_zero_bw_ets_tc = true;
+
+		if (tc_group[i] == (MLX5E_VENDOR_TC_GROUP_NUM - 1))
+			is_tc_group_6_exist = true;
 	}
 
+	/* Report 0% ets tc if exits*/
+	if (is_zero_bw_ets_tc) {
+		for (i = 0; i < ets->ets_cap; i++)
+			if (tc_group[i] == MLX5E_LOWEST_PRIO_GROUP)
+				ets->tc_tx_bw[i] = 0;
+	}
+
+	/* Update tc_tsa based on fw setting*/
+	for (i = 0; i < ets->ets_cap; i++) {
+		if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC)
+			priv->dcbx.tc_tsa[i] = IEEE_8021QAZ_TSA_ETS;
+		else if (tc_group[i] == MLX5E_VENDOR_TC_GROUP_NUM &&
+			 !is_tc_group_6_exist)
+			priv->dcbx.tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR;
+	}
 	memcpy(ets->tc_tsa, priv->dcbx.tc_tsa, sizeof(ets->tc_tsa));
 
 	return err;
 }
 
-enum {
-	MLX5E_VENDOR_TC_GROUP_NUM = 7,
-	MLX5E_ETS_TC_GROUP_NUM    = 0,
-};
-
 static void mlx5e_build_tc_group(struct ieee_ets *ets, u8 *tc_group, int max_tc)
 {
 	bool any_tc_mapped_to_ets = false;
+	bool ets_zero_bw = false;
 	int strict_group;
 	int i;
 
-	for (i = 0; i <= max_tc; i++)
-		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS)
+	for (i = 0; i <= max_tc; i++) {
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
 			any_tc_mapped_to_ets = true;
+			if (!ets->tc_tx_bw[i])
+				ets_zero_bw = true;
+		}
+	}
 
-	strict_group = any_tc_mapped_to_ets ? 1 : 0;
+	/* strict group has higher priority than ets group */
+	strict_group = MLX5E_LOWEST_PRIO_GROUP;
+	if (any_tc_mapped_to_ets)
+		strict_group++;
+	if (ets_zero_bw)
+		strict_group++;
 
 	for (i = 0; i <= max_tc; i++) {
 		switch (ets->tc_tsa[i]) {
@@ -137,7 +172,9 @@
 			tc_group[i] = strict_group++;
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
-			tc_group[i] = MLX5E_ETS_TC_GROUP_NUM;
+			tc_group[i] = MLX5E_LOWEST_PRIO_GROUP;
+			if (ets->tc_tx_bw[i] && ets_zero_bw)
+				tc_group[i] = MLX5E_LOWEST_PRIO_GROUP + 1;
 			break;
 		}
 	}
@@ -146,9 +183,23 @@
 static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw,
 				 u8 *tc_group, int max_tc)
 {
+	int bw_for_ets_zero_bw_tc = 0;
+	int last_ets_zero_bw_tc = -1;
+	int num_ets_zero_bw = 0;
 	int i;
 
 	for (i = 0; i <= max_tc; i++) {
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS &&
+		    !ets->tc_tx_bw[i]) {
+			num_ets_zero_bw++;
+			last_ets_zero_bw_tc = i;
+		}
+	}
+
+	if (num_ets_zero_bw)
+		bw_for_ets_zero_bw_tc = MLX5E_MAX_BW_ALLOC / num_ets_zero_bw;
+
+	for (i = 0; i <= max_tc; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_VENDOR:
 			tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC;
@@ -157,12 +208,26 @@
 			tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC;
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
-			tc_tx_bw[i] = ets->tc_tx_bw[i];
+			tc_tx_bw[i] = ets->tc_tx_bw[i] ?
+				      ets->tc_tx_bw[i] :
+				      bw_for_ets_zero_bw_tc;
 			break;
 		}
 	}
+
+	/* Make sure the total bw for ets zero bw group is 100% */
+	if (last_ets_zero_bw_tc != -1)
+		tc_tx_bw[last_ets_zero_bw_tc] +=
+			MLX5E_MAX_BW_ALLOC % num_ets_zero_bw;
 }
 
+/* If there are ETS BW 0,
+ *   Set ETS group # to 1 for all ETS non zero BW tcs. Their sum must be 100%.
+ *   Set group #0 to all the ETS BW 0 tcs and
+ *     equally splits the 100% BW between them
+ *   Report both group #0 and #1 as ETS type.
+ *     All the tcs in group #0 will be reported with 0% BW.
+ */
 int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -188,7 +253,6 @@
 		return err;
 
 	memcpy(priv->dcbx.tc_tsa, ets->tc_tsa, sizeof(ets->tc_tsa));
-
 	return err;
 }
 
@@ -209,17 +273,9 @@
 	}
 
 	/* Validate Bandwidth Sum */
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
-			if (!ets->tc_tx_bw[i]) {
-				netdev_err(netdev,
-					   "Failed to validate ETS: BW 0 is illegal\n");
-				return -EINVAL;
-			}
-
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS)
 			bw_sum += ets->tc_tx_bw[i];
-		}
-	}
 
 	if (bw_sum != 0 && bw_sum != 100) {
 		netdev_err(netdev,
@@ -533,8 +589,7 @@
 static void mlx5e_dcbnl_getpgbwgcfgtx(struct net_device *netdev,
 				      int pgid, u8 *bw_pct)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct ieee_ets ets;
 
 	if (pgid >= CEE_DCBX_MAX_PGS) {
 		netdev_err(netdev,
@@ -542,8 +597,8 @@
 		return;
 	}
 
-	if (mlx5_query_port_tc_bw_alloc(mdev, pgid, bw_pct))
-		*bw_pct = 0;
+	mlx5e_dcbnl_ieee_getets(netdev, &ets);
+	*bw_pct = ets.tc_tx_bw[pgid];
 }
 
 static void mlx5e_dcbnl_setpfccfg(struct net_device *netdev,
@@ -739,8 +794,6 @@
 		ets.prio_tc[i] = i;
 	}
 
-	memcpy(priv->dcbx.tc_tsa, ets.tc_tsa, sizeof(ets.tc_tsa));
-
 	/* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */
 	ets.prio_tc[0] = 1;
 	ets.prio_tc[1] = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index f11fd07..850cdc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -291,7 +291,7 @@
 	priv->fs.vlan.filter_disabled = false;
 	if (priv->netdev->flags & IFF_PROMISC)
 		return;
-	mlx5e_del_any_vid_rules(priv);
+	mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0);
 }
 
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv)
@@ -302,7 +302,7 @@
 	priv->fs.vlan.filter_disabled = true;
 	if (priv->netdev->flags & IFF_PROMISC)
 		return;
-	mlx5e_add_any_vid_rules(priv);
+	mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0);
 }
 
 int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index dfc2972..cc11bbb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -184,7 +184,6 @@
 	struct mlx5e_sw_stats temp, *s = &temp;
 	struct mlx5e_rq_stats *rq_stats;
 	struct mlx5e_sq_stats *sq_stats;
-	u64 tx_offload_none = 0;
 	int i, j;
 
 	memset(s, 0, sizeof(*s));
@@ -199,6 +198,7 @@
 		s->rx_lro_bytes	+= rq_stats->lro_bytes;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop += rq_stats->xdp_drop;
 		s->rx_xdp_tx += rq_stats->xdp_tx;
@@ -229,14 +229,11 @@
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_xmit_more		+= sq_stats->xmit_more;
 			s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
-			tx_offload_none		+= sq_stats->csum_none;
+			s->tx_csum_none		+= sq_stats->csum_none;
+			s->tx_csum_partial	+= sq_stats->csum_partial;
 		}
 	}
 
-	/* Update calculated offload counters */
-	s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;
-	s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete;
-
 	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
 				priv->stats.pport.phy_counters,
 				counter_set.phys_layer_cntrs.link_down_events);
@@ -3333,8 +3330,8 @@
 
 	err = feature_handler(netdev, enable);
 	if (err) {
-		netdev_err(netdev, "%s feature 0x%llx failed err %d\n",
-			   enable ? "Enable" : "Disable", feature, err);
+		netdev_err(netdev, "%s feature %pNF failed, err %d\n",
+			   enable ? "Enable" : "Disable", &feature, err);
 		return err;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f1dd638..15a1687 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -627,6 +627,7 @@
 
 	if (lro) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		rq->stats.csum_unnecessary++;
 		return;
 	}
 
@@ -644,7 +645,9 @@
 			skb->csum_level = 1;
 			skb->encapsulation = 1;
 			rq->stats.csum_unnecessary_inner++;
+			return;
 		}
+		rq->stats.csum_unnecessary++;
 		return;
 	}
 csum_none:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 6d199ff..f863721 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -68,6 +68,7 @@
 	u64 rx_xdp_drop;
 	u64 rx_xdp_tx;
 	u64 rx_xdp_tx_full;
+	u64 tx_csum_none;
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
 	u64 tx_queue_stopped;
@@ -108,6 +109,7 @@
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
@@ -339,6 +341,7 @@
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;
 	u64 lro_packets;
@@ -363,6 +366,7 @@
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
@@ -392,6 +396,7 @@
 	u64 tso_bytes;
 	u64 tso_inner_packets;
 	u64 tso_inner_bytes;
+	u64 csum_partial;
 	u64 csum_partial_inner;
 	u64 nop;
 	/* less likely accessed in data path */
@@ -408,6 +413,7 @@
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index da503e6..9ba1f720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -78,9 +78,11 @@
 };
 
 struct mlx5e_tc_flow_parse_attr {
+	struct ip_tunnel_info tun_info;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
 	void *mod_hdr_actions;
+	int mirred_ifindex;
 };
 
 enum {
@@ -322,6 +324,12 @@
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 			       struct mlx5e_tc_flow *flow);
 
+static int mlx5e_attach_encap(struct mlx5e_priv *priv,
+			      struct ip_tunnel_info *tun_info,
+			      struct net_device *mirred_dev,
+			      struct net_device **encap_dev,
+			      struct mlx5e_tc_flow *flow);
+
 static struct mlx5_flow_handle *
 mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		      struct mlx5e_tc_flow_parse_attr *parse_attr,
@@ -329,9 +337,27 @@
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	struct mlx5_flow_handle *rule;
+	struct net_device *out_dev, *encap_dev = NULL;
+	struct mlx5_flow_handle *rule = NULL;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *out_priv;
 	int err;
 
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) {
+		out_dev = __dev_get_by_index(dev_net(priv->netdev),
+					     attr->parse_attr->mirred_ifindex);
+		err = mlx5e_attach_encap(priv, &parse_attr->tun_info,
+					 out_dev, &encap_dev, flow);
+		if (err) {
+			rule = ERR_PTR(err);
+			if (err != -EAGAIN)
+				goto err_attach_encap;
+		}
+		out_priv = netdev_priv(encap_dev);
+		rpriv = out_priv->ppriv;
+		attr->out_rep = rpriv->rep;
+	}
+
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
 	if (err) {
 		rule = ERR_PTR(err);
@@ -347,10 +373,14 @@
 		}
 	}
 
-	rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr);
-	if (IS_ERR(rule))
-		goto err_add_rule;
-
+	/* we get here if (1) there's no error (rule being null) or when
+	 * (2) there's an encap action and we're on -EAGAIN (no valid neigh)
+	 */
+	if (rule != ERR_PTR(-EAGAIN)) {
+		rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr);
+		if (IS_ERR(rule))
+			goto err_add_rule;
+	}
 	return rule;
 
 err_add_rule:
@@ -361,6 +391,7 @@
 err_add_vlan:
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
 		mlx5e_detach_encap(priv, flow);
+err_attach_encap:
 	return rule;
 }
 
@@ -389,6 +420,8 @@
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 			      struct mlx5e_encap_entry *e)
 {
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *esw_attr;
 	struct mlx5e_tc_flow *flow;
 	int err;
 
@@ -404,10 +437,9 @@
 	mlx5e_rep_queue_neigh_stats_work(priv);
 
 	list_for_each_entry(flow, &e->flows, encap) {
-		flow->esw_attr->encap_id = e->encap_id;
-		flow->rule = mlx5e_tc_add_fdb_flow(priv,
-						   flow->esw_attr->parse_attr,
-						   flow);
+		esw_attr = flow->esw_attr;
+		esw_attr->encap_id = e->encap_id;
+		flow->rule = mlx5_eswitch_add_offloaded_rule(esw, &esw_attr->parse_attr->spec, esw_attr);
 		if (IS_ERR(flow->rule)) {
 			err = PTR_ERR(flow->rule);
 			mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n",
@@ -421,15 +453,13 @@
 void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 			      struct mlx5e_encap_entry *e)
 {
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_tc_flow *flow;
-	struct mlx5_fc *counter;
 
 	list_for_each_entry(flow, &e->flows, encap) {
 		if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 			flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED;
-			counter = mlx5_flow_rule_counter(flow->rule);
-			mlx5_del_flow_rules(flow->rule);
-			mlx5_fc_destroy(priv->mdev, counter);
+			mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->esw_attr);
 		}
 	}
 
@@ -1317,6 +1347,69 @@
 	return true;
 }
 
+static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
+					  struct tcf_exts *exts)
+{
+	const struct tc_action *a;
+	bool modify_ip_header;
+	LIST_HEAD(actions);
+	u8 htype, ip_proto;
+	void *headers_v;
+	u16 ethertype;
+	int nkeys, i;
+
+	headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
+
+	/* for non-IP we only re-write MACs, so we're okay */
+	if (ethertype != ETH_P_IP && ethertype != ETH_P_IPV6)
+		goto out_ok;
+
+	modify_ip_header = false;
+	tcf_exts_to_list(exts, &actions);
+	list_for_each_entry(a, &actions, list) {
+		if (!is_tcf_pedit(a))
+			continue;
+
+		nkeys = tcf_pedit_nkeys(a);
+		for (i = 0; i < nkeys; i++) {
+			htype = tcf_pedit_htype(a, i);
+			if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 ||
+			    htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) {
+				modify_ip_header = true;
+				break;
+			}
+		}
+	}
+
+	ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
+	if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+		pr_info("can't offload re-write of ip proto %d\n", ip_proto);
+		return false;
+	}
+
+out_ok:
+	return true;
+}
+
+static bool actions_match_supported(struct mlx5e_priv *priv,
+				    struct tcf_exts *exts,
+				    struct mlx5e_tc_flow_parse_attr *parse_attr,
+				    struct mlx5e_tc_flow *flow)
+{
+	u32 actions;
+
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+		actions = flow->esw_attr->action;
+	else
+		actions = flow->nic_attr->action;
+
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		return modify_header_match_supported(&parse_attr->spec, exts);
+
+	return true;
+}
+
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
@@ -1378,6 +1471,9 @@
 		return -EINVAL;
 	}
 
+	if (!actions_match_supported(priv, exts, parse_attr, flow))
+		return -EOPNOTSUPP;
+
 	return 0;
 }
 
@@ -1564,7 +1660,7 @@
 		break;
 	default:
 		err = -EOPNOTSUPP;
-		goto out;
+		goto free_encap;
 	}
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
@@ -1573,7 +1669,7 @@
 	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
 				      &fl4, &n, &ttl);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
@@ -1590,7 +1686,7 @@
 	 */
 	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	read_lock_bh(&n->lock);
 	nud_state = n->nud_state;
@@ -1630,8 +1726,9 @@
 
 destroy_neigh_entry:
 	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-out:
+free_encap:
 	kfree(encap_header);
+out:
 	if (n)
 		neigh_release(n);
 	return err;
@@ -1668,7 +1765,7 @@
 		break;
 	default:
 		err = -EOPNOTSUPP;
-		goto out;
+		goto free_encap;
 	}
 
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
@@ -1678,7 +1775,7 @@
 	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
 				      &fl6, &n, &ttl);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
@@ -1695,7 +1792,7 @@
 	 */
 	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	read_lock_bh(&n->lock);
 	nud_state = n->nud_state;
@@ -1736,8 +1833,9 @@
 
 destroy_neigh_entry:
 	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-out:
+free_encap:
 	kfree(encap_header);
+out:
 	if (n)
 		neigh_release(n);
 	return err;
@@ -1791,6 +1889,7 @@
 		}
 	}
 
+	/* must verify if encap is valid or not */
 	if (found)
 		goto attach_flow;
 
@@ -1817,6 +1916,8 @@
 	*encap_dev = e->out_dev;
 	if (e->flags & MLX5_ENCAP_ENTRY_VALID)
 		attr->encap_id = e->encap_id;
+	else
+		err = -EAGAIN;
 
 	return err;
 
@@ -1871,7 +1972,7 @@
 
 		if (is_tcf_mirred_egress_redirect(a)) {
 			int ifindex = tcf_mirred_ifindex(a);
-			struct net_device *out_dev, *encap_dev = NULL;
+			struct net_device *out_dev;
 			struct mlx5e_priv *out_priv;
 
 			out_dev = __dev_get_by_index(dev_net(priv->netdev), ifindex);
@@ -1884,17 +1985,13 @@
 				rpriv = out_priv->ppriv;
 				attr->out_rep = rpriv->rep;
 			} else if (encap) {
-				err = mlx5e_attach_encap(priv, info,
-							 out_dev, &encap_dev, flow);
-				if (err && err != -EAGAIN)
-					return err;
+				parse_attr->mirred_ifindex = ifindex;
+				parse_attr->tun_info = *info;
+				attr->parse_attr = parse_attr;
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
 					MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					MLX5_FLOW_CONTEXT_ACTION_COUNT;
-				out_priv = netdev_priv(encap_dev);
-				rpriv = out_priv->ppriv;
-				attr->out_rep = rpriv->rep;
-				attr->parse_attr = parse_attr;
+				/* attr->out_rep is resolved when we handle encap */
 			} else {
 				pr_err("devices %s %s not on same switch HW, can't offload forwarding\n",
 				       priv->netdev->name, out_dev->name);
@@ -1934,6 +2031,10 @@
 
 		return -EINVAL;
 	}
+
+	if (!actions_match_supported(priv, exts, parse_attr, flow))
+		return -EOPNOTSUPP;
+
 	return err;
 }
 
@@ -1972,7 +2073,7 @@
 	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
 		err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow);
 		if (err < 0)
-			goto err_handle_encap_flow;
+			goto err_free;
 		flow->rule = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow);
 	} else {
 		err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow);
@@ -1983,10 +2084,13 @@
 
 	if (IS_ERR(flow->rule)) {
 		err = PTR_ERR(flow->rule);
-		goto err_free;
+		if (err != -EAGAIN)
+			goto err_free;
 	}
 
-	flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
+	if (err != -EAGAIN)
+		flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
+
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
 				     tc->ht_params);
 	if (err)
@@ -2000,16 +2104,6 @@
 err_del_rule:
 	mlx5e_tc_del_flow(priv, flow);
 
-err_handle_encap_flow:
-	if (err == -EAGAIN) {
-		err = rhashtable_insert_fast(&tc->ht, &flow->node,
-					     tc->ht_params);
-		if (err)
-			mlx5e_tc_del_flow(priv, flow);
-		else
-			return 0;
-	}
-
 err_free:
 	kvfree(parse_attr);
 	kfree(flow);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index fee43e4..1d6925d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -193,6 +193,7 @@
 			sq->stats.csum_partial_inner++;
 		} else {
 			eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
+			sq->stats.csum_partial++;
 		}
 	} else
 		sq->stats.csum_none++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
index e37453d..c0fd221 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
@@ -71,11 +71,11 @@
 	return 0;
 }
 
-int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps)
+int mlx5_fpga_caps(struct mlx5_core_dev *dev)
 {
 	u32 in[MLX5_ST_SZ_DW(fpga_cap)] = {0};
 
-	return mlx5_core_access_reg(dev, in, sizeof(in), caps,
+	return mlx5_core_access_reg(dev, in, sizeof(in), dev->caps.fpga,
 				    MLX5_ST_SZ_BYTES(fpga_cap),
 				    MLX5_REG_FPGA_CAP, 0, 0);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
index 94bdfd4..d05233c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
@@ -65,7 +65,7 @@
 	u64 rx_total_drop;
 };
 
-int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps);
+int mlx5_fpga_caps(struct mlx5_core_dev *dev);
 int mlx5_fpga_query(struct mlx5_core_dev *dev, struct mlx5_fpga_query *query);
 int mlx5_fpga_ctrl_op(struct mlx5_core_dev *dev, u8 op);
 int mlx5_fpga_access_reg(struct mlx5_core_dev *dev, u8 size, u64 addr,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index 9034e99..dc89703 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -139,8 +139,7 @@
 	if (err)
 		goto out;
 
-	err = mlx5_fpga_caps(fdev->mdev,
-			     fdev->mdev->caps.hca_cur[MLX5_CAP_FPGA]);
+	err = mlx5_fpga_caps(fdev->mdev);
 	if (err)
 		goto out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index e0d0efd..36ecc2b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -293,6 +293,9 @@
 	}
 
 	if (fte->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		int max_list_size = BIT(MLX5_CAP_FLOWTABLE_TYPE(dev,
+					log_max_flow_counter,
+					ft->type));
 		int list_size = 0;
 
 		list_for_each_entry(dst, &fte->node.children, node.list) {
@@ -305,12 +308,17 @@
 			in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
 			list_size++;
 		}
+		if (list_size > max_list_size) {
+			err = -EINVAL;
+			goto err_out;
+		}
 
 		MLX5_SET(flow_context, in_flow_context, flow_counter_list_size,
 			 list_size);
 	}
 
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+err_out:
 	kvfree(in);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 5509a752..48dd789 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -52,6 +52,7 @@
 	FS_FT_FDB             = 0X4,
 	FS_FT_SNIFFER_RX	= 0X5,
 	FS_FT_SNIFFER_TX	= 0X6,
+	FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX,
 };
 
 enum fs_flow_table_op_mod {
@@ -260,4 +261,14 @@
 #define fs_for_each_dst(pos, fte)			\
 	fs_list_for_each_entry(pos, &(fte)->node.children)
 
+#define MLX5_CAP_FLOWTABLE_TYPE(mdev, cap, type) (		\
+	(type == FS_FT_NIC_RX) ? MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) :		\
+	(type == FS_FT_ESW_EGRESS_ACL) ? MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) :		\
+	(type == FS_FT_ESW_INGRESS_ACL) ? MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) :		\
+	(type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :		\
+	(type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) :		\
+	(type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) :		\
+	(BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\
+	)
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 8aea0a0..db86e15 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -356,10 +356,11 @@
 void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
+	unsigned long flags;
 
-	spin_lock(&health->wq_lock);
+	spin_lock_irqsave(&health->wq_lock, flags);
 	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
-	spin_unlock(&health->wq_lock);
+	spin_unlock_irqrestore(&health->wq_lock, flags);
 	cancel_delayed_work_sync(&dev->priv.health.recover_work);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 8529805..145e392 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -572,12 +572,13 @@
 {
 	struct mlx5e_priv          *priv    = mlx5i_epriv(netdev);
 	const struct mlx5e_profile *profile = priv->profile;
+	struct mlx5_core_dev       *mdev    = priv->mdev;
 
 	mlx5e_detach_netdev(priv);
 	profile->cleanup(priv);
 	destroy_workqueue(priv->wq);
 	free_netdev(netdev);
 
-	mlx5e_destroy_mdev_resources(priv->mdev);
+	mlx5e_destroy_mdev_resources(mdev);
 }
 EXPORT_SYMBOL(mlx5_rdma_netdev_free);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 1975d43..e07061f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -677,6 +677,27 @@
 }
 EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group);
 
+int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
+			     u8 tc, u8 *tc_group)
+{
+	u32 out[MLX5_ST_SZ_DW(qetc_reg)];
+	void *ets_tcn_conf;
+	int err;
+
+	err = mlx5_query_port_qetcr_reg(mdev, out, sizeof(out));
+	if (err)
+		return err;
+
+	ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, out,
+				    tc_configuration[tc]);
+
+	*tc_group = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf,
+			     group);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_tc_group);
+
 int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw)
 {
 	u32 in[MLX5_ST_SZ_DW(qetc_reg)] = {0};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 6c48e99..2a8b529 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -109,7 +109,7 @@
 				mlx5_core_warn(dev,
 					       "failed to restore VF %d settings, err %d\n",
 					       vf, err);
-			continue;
+				continue;
 			}
 		}
 		mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 9d5e7cf..f3315bc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -96,6 +96,7 @@
 	const struct mlxsw_bus *bus;
 	void *bus_priv;
 	const struct mlxsw_bus_info *bus_info;
+	struct workqueue_struct *emad_wq;
 	struct list_head rx_listener_list;
 	struct list_head event_listener_list;
 	struct {
@@ -465,7 +466,7 @@
 {
 	unsigned long timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS);
 
-	mlxsw_core_schedule_dw(&trans->timeout_dw, timeout);
+	queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout);
 }
 
 static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
@@ -587,12 +588,18 @@
 
 static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 {
+	struct workqueue_struct *emad_wq;
 	u64 tid;
 	int err;
 
 	if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
 		return 0;
 
+	emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0);
+	if (!emad_wq)
+		return -ENOMEM;
+	mlxsw_core->emad_wq = emad_wq;
+
 	/* Set the upper 32 bits of the transaction ID field to a random
 	 * number. This allows us to discard EMADs addressed to other
 	 * devices.
@@ -619,6 +626,7 @@
 err_emad_trap_set:
 	mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener,
 				   mlxsw_core);
+	destroy_workqueue(mlxsw_core->emad_wq);
 	return err;
 }
 
@@ -631,6 +639,7 @@
 	mlxsw_core->emad.use_emad = false;
 	mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener,
 				   mlxsw_core);
+	destroy_workqueue(mlxsw_core->emad_wq);
 }
 
 static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index cc27c5d..4afc848 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -6401,6 +6401,36 @@
 	mlxsw_reg_mgpc_opcode_set(payload, opcode);
 }
 
+/* TIGCR - Tunneling IPinIP General Configuration Register
+ * -------------------------------------------------------
+ * The TIGCR register is used for setting up the IPinIP Tunnel configuration.
+ */
+#define MLXSW_REG_TIGCR_ID 0xA801
+#define MLXSW_REG_TIGCR_LEN 0x10
+
+MLXSW_REG_DEFINE(tigcr, MLXSW_REG_TIGCR_ID, MLXSW_REG_TIGCR_LEN);
+
+/* reg_tigcr_ipip_ttlc
+ * For IPinIP Tunnel encapsulation: whether to copy the ttl from the packet
+ * header.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, tigcr, ttlc, 0x04, 8, 1);
+
+/* reg_tigcr_ipip_ttl_uc
+ * The TTL for IPinIP Tunnel encapsulation of unicast packets if
+ * reg_tigcr_ipip_ttlc is unset.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, tigcr, ttl_uc, 0x04, 0, 8);
+
+static inline void mlxsw_reg_tigcr_pack(char *payload, bool ttlc, u8 ttl_uc)
+{
+	MLXSW_REG_ZERO(tigcr, payload);
+	mlxsw_reg_tigcr_ttlc_set(payload, ttlc);
+	mlxsw_reg_tigcr_ttl_uc_set(payload, ttl_uc);
+}
+
 /* SBPR - Shared Buffer Pools Register
  * -----------------------------------
  * The SBPR configures and retrieves the shared buffer pools and configuration.
@@ -6881,6 +6911,7 @@
 	MLXSW_REG(mcc),
 	MLXSW_REG(mcda),
 	MLXSW_REG(mgpc),
+	MLXSW_REG(tigcr),
 	MLXSW_REG(sbpr),
 	MLXSW_REG(sbcm),
 	MLXSW_REG(sbpm),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 2cfb3f5..5189022a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2723,6 +2723,7 @@
 		mlxsw_sp_nexthop_rif_fini(nh);
 		break;
 	case MLXSW_SP_NEXTHOP_TYPE_IPIP:
+		mlxsw_sp_nexthop_rif_fini(nh);
 		mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh);
 		break;
 	}
@@ -2742,7 +2743,11 @@
 	    router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
 						     MLXSW_SP_L3_PROTO_IPV4)) {
 		nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
-		return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		if (err)
+			return err;
+		mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
+		return 0;
 	}
 
 	nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
@@ -3500,20 +3505,6 @@
 static void mlxsw_sp_fib_lpm_tree_unlink(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_fib *fib)
 {
-	struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } };
-	struct mlxsw_sp_lpm_tree *lpm_tree;
-
-	/* Aggregate prefix lengths across all virtual routers to make
-	 * sure we only have used prefix lengths in the LPM tree.
-	 */
-	mlxsw_sp_vrs_prefixes(mlxsw_sp, fib->proto, &req_prefix_usage);
-	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
-					 fib->proto);
-	if (IS_ERR(lpm_tree))
-		goto err_tree_get;
-	mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree);
-
-err_tree_get:
 	if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage))
 		return;
 	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib);
@@ -4009,7 +4000,11 @@
 	    router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
 						     MLXSW_SP_L3_PROTO_IPV6)) {
 		nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
-		return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		if (err)
+			return err;
+		mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
+		return 0;
 	}
 
 	nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
@@ -5068,6 +5063,7 @@
 	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
 	if (IS_ERR(vr))
 		return ERR_CAST(vr);
+	vr->rif_count++;
 
 	err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index);
 	if (err)
@@ -5099,7 +5095,6 @@
 
 	mlxsw_sp_rif_counters_alloc(rif);
 	mlxsw_sp->router->rifs[rif_index] = rif;
-	vr->rif_count++;
 
 	return rif;
 
@@ -5110,6 +5105,7 @@
 	kfree(rif);
 err_rif_alloc:
 err_rif_index_alloc:
+	vr->rif_count--;
 	mlxsw_sp_vr_put(vr);
 	return ERR_PTR(err);
 }
@@ -5124,7 +5120,6 @@
 	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
 	vr = &mlxsw_sp->router->vrs[rif->vr_id];
 
-	vr->rif_count--;
 	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
 	mlxsw_sp_rif_counters_free(rif);
 	ops->deconfigure(rif);
@@ -5132,6 +5127,7 @@
 		/* Loopback RIFs are not associated with a FID. */
 		mlxsw_sp_fid_put(fid);
 	kfree(rif);
+	vr->rif_count--;
 	mlxsw_sp_vr_put(vr);
 }
 
@@ -5900,11 +5896,20 @@
 	kfree(mlxsw_sp->router->rifs);
 }
 
+static int
+mlxsw_sp_ipip_config_tigcr(struct mlxsw_sp *mlxsw_sp)
+{
+	char tigcr_pl[MLXSW_REG_TIGCR_LEN];
+
+	mlxsw_reg_tigcr_pack(tigcr_pl, true, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tigcr), tigcr_pl);
+}
+
 static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp->router->ipip_ops_arr = mlxsw_sp_ipip_ops_arr;
 	INIT_LIST_HEAD(&mlxsw_sp->router->ipip_list);
-	return 0;
+	return mlxsw_sp_ipip_config_tigcr(mlxsw_sp);
 }
 
 static void mlxsw_sp_ipips_fini(struct mlxsw_sp *mlxsw_sp)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index db97506..8ea9320 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -110,6 +110,8 @@
 	 */
 	if (!switchdev_port_same_parent_id(in_dev, out_dev))
 		return -EOPNOTSUPP;
+	if (!nfp_netdev_is_nfp_repr(out_dev))
+		return -EOPNOTSUPP;
 
 	output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev));
 	if (!output->port)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 1c0187f..e118b5f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1180,10 +1180,14 @@
 {
 	void *frag;
 
-	if (!dp->xdp_prog)
+	if (!dp->xdp_prog) {
 		frag = netdev_alloc_frag(dp->fl_bufsz);
-	else
-		frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD));
+	} else {
+		struct page *page;
+
+		page = alloc_page(GFP_KERNEL | __GFP_COLD);
+		frag = page ? page_address(page) : NULL;
+	}
 	if (!frag) {
 		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
@@ -1203,10 +1207,14 @@
 {
 	void *frag;
 
-	if (!dp->xdp_prog)
+	if (!dp->xdp_prog) {
 		frag = napi_alloc_frag(dp->fl_bufsz);
-	else
-		frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD));
+	} else {
+		struct page *page;
+
+		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		frag = page ? page_address(page) : NULL;
+	}
 	if (!frag) {
 		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 07969f0..dc016df 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -464,7 +464,7 @@
 
 		do {
 			start = u64_stats_fetch_begin(&nn->r_vecs[i].rx_sync);
-			*data++ = nn->r_vecs[i].rx_pkts;
+			data[0] = nn->r_vecs[i].rx_pkts;
 			tmp[0] = nn->r_vecs[i].hw_csum_rx_ok;
 			tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok;
 			tmp[2] = nn->r_vecs[i].hw_csum_rx_error;
@@ -472,14 +472,16 @@
 
 		do {
 			start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync);
-			*data++ = nn->r_vecs[i].tx_pkts;
-			*data++ = nn->r_vecs[i].tx_busy;
+			data[1] = nn->r_vecs[i].tx_pkts;
+			data[2] = nn->r_vecs[i].tx_busy;
 			tmp[3] = nn->r_vecs[i].hw_csum_tx;
 			tmp[4] = nn->r_vecs[i].hw_csum_tx_inner;
 			tmp[5] = nn->r_vecs[i].tx_gather;
 			tmp[6] = nn->r_vecs[i].tx_lso;
 		} while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start));
 
+		data += 3;
+
 		for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++)
 			gathered_stats[j] += tmp[j];
 	}
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
index bbe2463..c8c6231 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
@@ -88,6 +88,8 @@
 static int emac_get_sset_count(struct net_device *netdev, int sset)
 {
 	switch (sset) {
+	case ETH_SS_PRIV_FLAGS:
+		return 1;
 	case ETH_SS_STATS:
 		return EMAC_STATS_LEN;
 	default:
@@ -100,6 +102,10 @@
 	unsigned int i;
 
 	switch (stringset) {
+	case ETH_SS_PRIV_FLAGS:
+		strcpy(data, "single-pause-mode");
+		break;
+
 	case ETH_SS_STATS:
 		for (i = 0; i < EMAC_STATS_LEN; i++) {
 			strlcpy(data, emac_ethtool_stat_strings[i],
@@ -230,6 +236,27 @@
 	return EMAC_MAX_REG_SIZE * sizeof(u32);
 }
 
+#define EMAC_PRIV_ENABLE_SINGLE_PAUSE	BIT(0)
+
+static int emac_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	adpt->single_pause_mode = !!(flags & EMAC_PRIV_ENABLE_SINGLE_PAUSE);
+
+	if (netif_running(netdev))
+		return emac_reinit_locked(adpt);
+
+	return 0;
+}
+
+static u32 emac_get_priv_flags(struct net_device *netdev)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	return adpt->single_pause_mode ? EMAC_PRIV_ENABLE_SINGLE_PAUSE : 0;
+}
+
 static const struct ethtool_ops emac_ethtool_ops = {
 	.get_link_ksettings = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
@@ -253,6 +280,9 @@
 
 	.get_regs_len    = emac_get_regs_len,
 	.get_regs        = emac_get_regs,
+
+	.set_priv_flags = emac_set_priv_flags,
+	.get_priv_flags = emac_get_priv_flags,
 };
 
 void emac_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index bcd4708..3ed9033 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -551,6 +551,28 @@
 	mac &= ~(HUGEN | VLAN_STRIP | TPAUSE | SIMR | HUGE | MULTI_ALL |
 		 DEBUG_MODE | SINGLE_PAUSE_MODE);
 
+	/* Enable single-pause-frame mode if requested.
+	 *
+	 * If enabled, the EMAC will send a single pause frame when the RX
+	 * queue is full.  This normally leads to packet loss because
+	 * the pause frame disables the remote MAC only for 33ms (the quanta),
+	 * and then the remote MAC continues sending packets even though
+	 * the RX queue is still full.
+	 *
+	 * If disabled, the EMAC sends a pause frame every 31ms until the RX
+	 * queue is no longer full.  Normally, this is the preferred
+	 * method of operation.  However, when the system is hung (e.g.
+	 * cores are halted), the EMAC interrupt handler is never called
+	 * and so the RX queue fills up quickly and stays full.  The resuling
+	 * non-stop "flood" of pause frames sometimes has the effect of
+	 * disabling nearby switches.  In some cases, other nearby switches
+	 * are also affected, shutting down the entire network.
+	 *
+	 * The user can enable or disable single-pause-frame mode
+	 * via ethtool.
+	 */
+	mac |= adpt->single_pause_mode ? SINGLE_PAUSE_MODE : 0;
+
 	writel_relaxed(csr1, adpt->csr + EMAC_EMAC_WRAPPER_CSR1);
 
 	writel_relaxed(mac, adpt->base + EMAC_MAC_CTRL);
@@ -876,7 +898,8 @@
 
 		curr_rxbuf->dma_addr =
 			dma_map_single(adpt->netdev->dev.parent, skb->data,
-				       curr_rxbuf->length, DMA_FROM_DEVICE);
+				       adpt->rxbuf_size, DMA_FROM_DEVICE);
+
 		ret = dma_mapping_error(adpt->netdev->dev.parent,
 					curr_rxbuf->dma_addr);
 		if (ret) {
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 60850bf..7595435 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -443,6 +443,9 @@
 
 	/* default to automatic flow control */
 	adpt->automatic = true;
+
+	/* Disable single-pause-frame mode by default */
+	adpt->single_pause_mode = false;
 }
 
 /* Get the clock */
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.h b/drivers/net/ethernet/qualcomm/emac/emac.h
index 8ee4ec6..d7c9f44 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.h
+++ b/drivers/net/ethernet/qualcomm/emac/emac.h
@@ -363,6 +363,9 @@
 	bool				tx_flow_control;
 	bool				rx_flow_control;
 
+	/* True == use single-pause-frame mode. */
+	bool				single_pause_mode;
+
 	/* Ring parameter */
 	u8				tpd_burst;
 	u8				rfd_burst;
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 98f2255..1e33aea 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -51,10 +51,7 @@
 
 static int rmnet_is_real_dev_registered(const struct net_device *real_dev)
 {
-	rx_handler_func_t *rx_handler;
-
-	rx_handler = rcu_dereference(real_dev->rx_handler);
-	return (rx_handler == rmnet_rx_handler);
+	return rcu_access_pointer(real_dev->rx_handler) == rmnet_rx_handler;
 }
 
 /* Needs rtnl lock */
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index ca22f28..d24b47b 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2135,11 +2135,12 @@
 	if (likely(RTL_R16(IntrStatus) & RxAckBits))
 		work_done += rtl8139_rx(dev, tp, budget);
 
-	if (work_done < budget && napi_complete_done(napi, work_done)) {
+	if (work_done < budget) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&tp->lock, flags);
-		RTL_W16_F(IntrMask, rtl8139_intr_mask);
+		if (napi_complete_done(napi, work_done))
+			RTL_W16_F(IntrMask, rtl8139_intr_mask);
 		spin_unlock_irqrestore(&tp->lock, flags);
 	}
 	spin_unlock(&tp->rx_lock);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index e03fcf9..a3c949e 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8491,8 +8491,6 @@
 		rtl8168_driver_start(tp);
 	}
 
-	device_set_wakeup_enable(&pdev->dev, tp->features & RTL_FEATURE_WOL);
-
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_put_noidle(&pdev->dev);
 
diff --git a/drivers/net/ethernet/rocker/rocker_tlv.h b/drivers/net/ethernet/rocker/rocker_tlv.h
index a63ef82..dfae3c9 100644
--- a/drivers/net/ethernet/rocker/rocker_tlv.h
+++ b/drivers/net/ethernet/rocker/rocker_tlv.h
@@ -139,40 +139,52 @@
 int rocker_tlv_put(struct rocker_desc_info *desc_info,
 		   int attrtype, int attrlen, const void *data);
 
-static inline int rocker_tlv_put_u8(struct rocker_desc_info *desc_info,
-				    int attrtype, u8 value)
+static inline int
+rocker_tlv_put_u8(struct rocker_desc_info *desc_info, int attrtype, u8 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &value);
+	u8 tmp = value; /* work around GCC PR81715 */
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &tmp);
 }
 
-static inline int rocker_tlv_put_u16(struct rocker_desc_info *desc_info,
-				     int attrtype, u16 value)
+static inline int
+rocker_tlv_put_u16(struct rocker_desc_info *desc_info, int attrtype, u16 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &value);
+	u16 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &tmp);
 }
 
-static inline int rocker_tlv_put_be16(struct rocker_desc_info *desc_info,
-				      int attrtype, __be16 value)
+static inline int
+rocker_tlv_put_be16(struct rocker_desc_info *desc_info, int attrtype, __be16 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &value);
+	__be16 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &tmp);
 }
 
-static inline int rocker_tlv_put_u32(struct rocker_desc_info *desc_info,
-				     int attrtype, u32 value)
+static inline int
+rocker_tlv_put_u32(struct rocker_desc_info *desc_info, int attrtype, u32 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &value);
+	u32 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &tmp);
 }
 
-static inline int rocker_tlv_put_be32(struct rocker_desc_info *desc_info,
-				      int attrtype, __be32 value)
+static inline int
+rocker_tlv_put_be32(struct rocker_desc_info *desc_info, int attrtype, __be32 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &value);
+	__be32 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &tmp);
 }
 
-static inline int rocker_tlv_put_u64(struct rocker_desc_info *desc_info,
-				     int attrtype, u64 value)
+static inline int
+rocker_tlv_put_u64(struct rocker_desc_info *desc_info, int attrtype, u64 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &value);
+	u64 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &tmp);
 }
 
 static inline struct rocker_tlv *
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index dd6a2f9..3256e5c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -74,7 +74,7 @@
 		plat_dat->axi->axi_wr_osr_lmt--;
 	}
 
-	if (of_property_read_u32(np, "read,read-requests",
+	if (of_property_read_u32(np, "snps,read-requests",
 				 &plat_dat->axi->axi_rd_osr_lmt)) {
 		/**
 		 * Since the register has a reset value of 1, if property
@@ -511,6 +511,7 @@
 	.remove = dwc_eth_dwmac_remove,
 	.driver = {
 		.name           = "dwc-eth-dwmac",
+		.pm             = &stmmac_pltfr_pm_ops,
 		.of_match_table = dwc_eth_dwmac_match,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 99823f5..13133b3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -83,6 +83,117 @@
 	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
 	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
 
+#define RK3128_GRF_MAC_CON0	0x0168
+#define RK3128_GRF_MAC_CON1	0x016c
+
+/* RK3128_GRF_MAC_CON0 */
+#define RK3128_GMAC_TXCLK_DLY_ENABLE   GRF_BIT(14)
+#define RK3128_GMAC_TXCLK_DLY_DISABLE  GRF_CLR_BIT(14)
+#define RK3128_GMAC_RXCLK_DLY_ENABLE   GRF_BIT(15)
+#define RK3128_GMAC_RXCLK_DLY_DISABLE  GRF_CLR_BIT(15)
+#define RK3128_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7)
+#define RK3128_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0)
+
+/* RK3128_GRF_MAC_CON1 */
+#define RK3128_GMAC_PHY_INTF_SEL_RGMII	\
+		(GRF_BIT(6) | GRF_CLR_BIT(7) | GRF_CLR_BIT(8))
+#define RK3128_GMAC_PHY_INTF_SEL_RMII	\
+		(GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | GRF_BIT(8))
+#define RK3128_GMAC_FLOW_CTRL          GRF_BIT(9)
+#define RK3128_GMAC_FLOW_CTRL_CLR      GRF_CLR_BIT(9)
+#define RK3128_GMAC_SPEED_10M          GRF_CLR_BIT(10)
+#define RK3128_GMAC_SPEED_100M         GRF_BIT(10)
+#define RK3128_GMAC_RMII_CLK_25M       GRF_BIT(11)
+#define RK3128_GMAC_RMII_CLK_2_5M      GRF_CLR_BIT(11)
+#define RK3128_GMAC_CLK_125M           (GRF_CLR_BIT(12) | GRF_CLR_BIT(13))
+#define RK3128_GMAC_CLK_25M            (GRF_BIT(12) | GRF_BIT(13))
+#define RK3128_GMAC_CLK_2_5M           (GRF_CLR_BIT(12) | GRF_BIT(13))
+#define RK3128_GMAC_RMII_MODE          GRF_BIT(14)
+#define RK3128_GMAC_RMII_MODE_CLR      GRF_CLR_BIT(14)
+
+static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+		     RK3128_GMAC_PHY_INTF_SEL_RGMII |
+		     RK3128_GMAC_RMII_MODE_CLR);
+	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON0,
+		     DELAY_ENABLE(RK3128, tx_delay, rx_delay) |
+		     RK3128_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3128_GMAC_CLK_TX_DL_CFG(tx_delay));
+}
+
+static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+		     RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE);
+}
+
+static void rk3128_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	if (speed == 10)
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_CLK_2_5M);
+	else if (speed == 100)
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_CLK_25M);
+	else if (speed == 1000)
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_CLK_125M);
+	else
+		dev_err(dev, "unknown speed value for RGMII! speed=%d", speed);
+}
+
+static void rk3128_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	if (speed == 10) {
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_RMII_CLK_2_5M |
+			     RK3128_GMAC_SPEED_10M);
+	} else if (speed == 100) {
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_RMII_CLK_25M |
+			     RK3128_GMAC_SPEED_100M);
+	} else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+	}
+}
+
+static const struct rk_gmac_ops rk3128_ops = {
+	.set_to_rgmii = rk3128_set_to_rgmii,
+	.set_to_rmii = rk3128_set_to_rmii,
+	.set_rgmii_speed = rk3128_set_rgmii_speed,
+	.set_rmii_speed = rk3128_set_rmii_speed,
+};
+
 #define RK3228_GRF_MAC_CON0	0x0900
 #define RK3228_GRF_MAC_CON1	0x0904
 
@@ -1313,6 +1424,7 @@
 static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume);
 
 static const struct of_device_id rk_gmac_dwmac_match[] = {
+	{ .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops },
 	{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
 	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
 	{ .compatible = "rockchip,rk3328-gmac", .data = &rk3328_ops },
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index c4407e8..2f7d7ec 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -296,6 +296,7 @@
 {
 	void __iomem *ioaddr = hw->pcsr;
 	unsigned int pmt = 0;
+	u32 config;
 
 	if (mode & WAKE_MAGIC) {
 		pr_debug("GMAC: WOL Magic frame\n");
@@ -306,6 +307,12 @@
 		pmt |= power_down | global_unicast | wake_up_frame_en;
 	}
 
+	if (pmt) {
+		/* The receiver must be enabled for WOL before powering down */
+		config = readl(ioaddr + GMAC_CONFIG);
+		config |= GMAC_CONFIG_RE;
+		writel(config, ioaddr + GMAC_CONFIG);
+	}
 	writel(pmt, ioaddr + GMAC_PMT);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index e0ef02f..4b286e2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -275,7 +275,7 @@
 					goto exit;
 				i++;
 
-			} while ((ret == 1) || (i < 10));
+			} while ((ret == 1) && (i < 10));
 
 			if (i == 10)
 				ret = -EBUSY;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 67af0bd..7516ca2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -34,7 +34,7 @@
 
 	err = readl_poll_timeout(ioaddr + DMA_BUS_MODE, value,
 				 !(value & DMA_BUS_MODE_SFT_RESET),
-				 100000, 10000);
+				 10000, 100000);
 	if (err)
 		return -EBUSY;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 1763e48..16bd509 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -473,19 +473,18 @@
 				   struct dma_desc *np, struct sk_buff *skb)
 {
 	struct skb_shared_hwtstamps *shhwtstamp = NULL;
+	struct dma_desc *desc = p;
 	u64 ns;
 
 	if (!priv->hwts_rx_en)
 		return;
+	/* For GMAC4, the valid timestamp is from CTX next desc. */
+	if (priv->plat->has_gmac4)
+		desc = np;
 
 	/* Check if timestamp is available */
-	if (priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) {
-		/* For GMAC4, the valid timestamp is from CTX next desc. */
-		if (priv->plat->has_gmac4)
-			ns = priv->hw->desc->get_timestamp(np, priv->adv_ts);
-		else
-			ns = priv->hw->desc->get_timestamp(p, priv->adv_ts);
-
+	if (priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts)) {
+		ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts);
 		netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns);
 		shhwtstamp = skb_hwtstamps(skb);
 		memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
@@ -1800,12 +1799,13 @@
 {
 	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	unsigned int bytes_compl = 0, pkts_compl = 0;
-	unsigned int entry = tx_q->dirty_tx;
+	unsigned int entry;
 
 	netif_tx_lock(priv->dev);
 
 	priv->xstats.tx_clean++;
 
+	entry = tx_q->dirty_tx;
 	while (entry != tx_q->cur_tx) {
 		struct sk_buff *skb = tx_q->tx_skbuff[entry];
 		struct dma_desc *p;
@@ -3333,6 +3333,7 @@
 				 * them in stmmac_rx_refill() function so that
 				 * device can reuse it.
 				 */
+				dev_kfree_skb_any(rx_q->rx_skbuff[entry]);
 				rx_q->rx_skbuff[entry] = NULL;
 				dma_unmap_single(priv->device,
 						 rx_q->rx_skbuff_dma[entry],
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index a366b37..6383695 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -150,6 +150,13 @@
 	plat->rx_queues_to_use = 1;
 	plat->tx_queues_to_use = 1;
 
+	/* First Queue must always be in DCB mode. As MTL_QUEUE_DCB = 1 we need
+	 * to always set this, otherwise Queue will be classified as AVB
+	 * (because MTL_QUEUE_AVB = 0).
+	 */
+	plat->rx_queues_cfg[0].mode_to_use = MTL_QUEUE_DCB;
+	plat->tx_queues_cfg[0].mode_to_use = MTL_QUEUE_DCB;
+
 	rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0);
 	if (!rx_node)
 		return;
@@ -315,6 +322,7 @@
 		{ .compatible = "allwinner,sun8i-h3-emac" },
 		{ .compatible = "allwinner,sun8i-v3s-emac" },
 		{ .compatible = "allwinner,sun50i-a64-emac" },
+		{},
 	};
 
 	/* If phy-handle property is passed from DT, use it as the PHY */
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index f640407..ed51018 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -113,13 +113,7 @@
 
 static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni)
 {
-#ifdef __BIG_ENDIAN
-	return (vni[0] == tun_id[2]) &&
-	       (vni[1] == tun_id[1]) &&
-	       (vni[2] == tun_id[0]);
-#else
 	return !memcmp(vni, &tun_id[5], 3);
-#endif
 }
 
 static sa_family_t geneve_get_sk_family(struct geneve_sock *gs)
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index d98cdfb..5176be7 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -150,6 +150,8 @@
 	u32  num_chn;
 	u32  send_sections;
 	u32  recv_sections;
+	u32  send_section_size;
+	u32  recv_section_size;
 };
 
 enum rndis_device_state {
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index a5511b7..8d5077f 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -76,9 +76,6 @@
 	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
 	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
 
-	net_device->recv_section_size = NETVSC_RECV_SECTION_SIZE;
-	net_device->send_section_size = NETVSC_SEND_SECTION_SIZE;
-
 	init_completion(&net_device->channel_init_wait);
 	init_waitqueue_head(&net_device->subchan_open);
 	INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
@@ -262,7 +259,7 @@
 	int ret = 0;
 
 	/* Get receive buffer area. */
-	buf_size = device_info->recv_sections * net_device->recv_section_size;
+	buf_size = device_info->recv_sections * device_info->recv_section_size;
 	buf_size = roundup(buf_size, PAGE_SIZE);
 
 	net_device->recv_buf = vzalloc(buf_size);
@@ -344,7 +341,7 @@
 		goto cleanup;
 
 	/* Now setup the send buffer. */
-	buf_size = device_info->send_sections * net_device->send_section_size;
+	buf_size = device_info->send_sections * device_info->send_section_size;
 	buf_size = round_up(buf_size, PAGE_SIZE);
 
 	net_device->send_buf = vzalloc(buf_size);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index d4902ee5f..a32ae02 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -848,7 +848,9 @@
 	device_info.num_chn = count;
 	device_info.ring_size = ring_size;
 	device_info.send_sections = nvdev->send_section_cnt;
+	device_info.send_section_size = nvdev->send_section_size;
 	device_info.recv_sections = nvdev->recv_section_cnt;
+	device_info.recv_section_size = nvdev->recv_section_size;
 
 	rndis_filter_device_remove(dev, nvdev);
 
@@ -963,7 +965,9 @@
 	device_info.ring_size = ring_size;
 	device_info.num_chn = nvdev->num_chn;
 	device_info.send_sections = nvdev->send_section_cnt;
+	device_info.send_section_size = nvdev->send_section_size;
 	device_info.recv_sections = nvdev->recv_section_cnt;
+	device_info.recv_section_size = nvdev->recv_section_size;
 
 	rndis_filter_device_remove(hdev, nvdev);
 
@@ -1485,7 +1489,9 @@
 	device_info.num_chn = nvdev->num_chn;
 	device_info.ring_size = ring_size;
 	device_info.send_sections = new_tx;
+	device_info.send_section_size = nvdev->send_section_size;
 	device_info.recv_sections = new_rx;
+	device_info.recv_section_size = nvdev->recv_section_size;
 
 	netif_device_detach(ndev);
 	was_opened = rndis_filter_opened(nvdev);
@@ -1934,7 +1940,9 @@
 	device_info.ring_size = ring_size;
 	device_info.num_chn = VRSS_CHANNEL_DEFAULT;
 	device_info.send_sections = NETVSC_DEFAULT_TX;
+	device_info.send_section_size = NETVSC_SEND_SECTION_SIZE;
 	device_info.recv_sections = NETVSC_DEFAULT_RX;
+	device_info.recv_section_size = NETVSC_RECV_SECTION_SIZE;
 
 	nvdev = rndis_filter_device_add(dev, &device_info);
 	if (IS_ERR(nvdev)) {
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 5dea206..0bcc07f 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -197,8 +197,8 @@
 {
 	int err;
 
-	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap");
-
+	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap",
+			      THIS_MODULE);
 	if (err)
 		goto out1;
 
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 98e4dea..5ab1b88 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -742,6 +742,7 @@
 	sg_init_table(sg, ret);
 	ret = skb_to_sgvec(skb, sg, 0, skb->len);
 	if (unlikely(ret < 0)) {
+		aead_request_free(req);
 		macsec_txsa_put(tx_sa);
 		kfree_skb(skb);
 		return ERR_PTR(ret);
@@ -954,6 +955,7 @@
 	sg_init_table(sg, ret);
 	ret = skb_to_sgvec(skb, sg, 0, skb->len);
 	if (unlikely(ret < 0)) {
+		aead_request_free(req);
 		kfree_skb(skb);
 		return ERR_PTR(ret);
 	}
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index c2d0ea2..cba5cb3 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -204,8 +204,8 @@
 {
 	int err;
 
-	err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap");
-
+	err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap",
+			      THIS_MODULE);
 	if (err)
 		goto out1;
 
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index a9d16a3..cd931cf 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -160,15 +160,6 @@
 
 endif
 
-menuconfig PHYLIB
-	tristate "PHY Device support and infrastructure"
-	depends on NETDEVICES
-	select MDIO_DEVICE
-	help
-	  Ethernet controllers are usually attached to PHY
-	  devices.  This option provides infrastructure for
-	  managing PHY devices.
-
 config PHYLINK
 	tristate
 	depends on NETDEVICES
@@ -179,6 +170,15 @@
 	  configuration links, PHYs, and Serdes links with MAC level
 	  autonegotiation modes.
 
+menuconfig PHYLIB
+	tristate "PHY Device support and infrastructure"
+	depends on NETDEVICES
+	select MDIO_DEVICE
+	help
+	  Ethernet controllers are usually attached to PHY
+	  devices.  This option provides infrastructure for
+	  managing PHY devices.
+
 if PHYLIB
 
 config SWPHY
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index e842d2c..2b1e67b 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -373,7 +373,8 @@
 		cmd->base.port = PORT_BNC;
 	else
 		cmd->base.port = PORT_MII;
-
+	cmd->base.transceiver = phy_is_internal(phydev) ?
+				XCVR_INTERNAL : XCVR_EXTERNAL;
 	cmd->base.phy_address = phydev->mdio.addr;
 	cmd->base.autoneg = phydev->autoneg;
 	cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8cf0c59..67f25ac 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -879,7 +879,7 @@
 {
 	const char *drv_name = phydev->drv ? phydev->drv->name : "unbound";
 	char *irq_str;
-	char irq_num[4];
+	char irq_num[8];
 
 	switch(phydev->irq) {
 	case PHY_POLL:
diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index d15dd39..2e5150b 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -44,7 +44,7 @@
 	priv->phy_drv->read_status(phydev);
 
 	val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
-	val &= XILINX_GMII2RGMII_SPEED_MASK;
+	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
 
 	if (phydev->speed == SPEED_1000)
 		val |= BMCR_SPEED1000;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index a404552..e365866 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -120,7 +120,7 @@
 	int		n_channels;	/* how many channels are attached 54 */
 	spinlock_t	rlock;		/* lock for receive side 58 */
 	spinlock_t	wlock;		/* lock for transmit side 5c */
-	int		*xmit_recursion __percpu; /* xmit recursion detect */
+	int __percpu	*xmit_recursion; /* xmit recursion detect */
 	int		mru;		/* max receive unit 60 */
 	unsigned int	flags;		/* control bits 64 */
 	unsigned int	xstate;		/* transmit state bits 68 */
@@ -1339,7 +1339,17 @@
 
 static int ppp_dev_init(struct net_device *dev)
 {
+	struct ppp *ppp;
+
 	netdev_lockdep_set_classes(dev);
+
+	ppp = netdev_priv(dev);
+	/* Let the netdevice take a reference on the ppp file. This ensures
+	 * that ppp_destroy_interface() won't run before the device gets
+	 * unregistered.
+	 */
+	atomic_inc(&ppp->file.refcnt);
+
 	return 0;
 }
 
@@ -1362,6 +1372,15 @@
 	wake_up_interruptible(&ppp->file.rwait);
 }
 
+static void ppp_dev_priv_destructor(struct net_device *dev)
+{
+	struct ppp *ppp;
+
+	ppp = netdev_priv(dev);
+	if (atomic_dec_and_test(&ppp->file.refcnt))
+		ppp_destroy_interface(ppp);
+}
+
 static const struct net_device_ops ppp_netdev_ops = {
 	.ndo_init	 = ppp_dev_init,
 	.ndo_uninit      = ppp_dev_uninit,
@@ -1387,6 +1406,7 @@
 	dev->tx_queue_len = 3;
 	dev->type = ARPHRD_PPP;
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+	dev->priv_destructor = ppp_dev_priv_destructor;
 	netif_keep_dst(dev);
 }
 
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 21b71ae..1b10fcc 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -517,6 +517,10 @@
 					     &tap_proto, 0);
 	if (!q)
 		goto err;
+	if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL)) {
+		sk_free(&q->sk);
+		goto err;
+	}
 
 	RCU_INIT_POINTER(q->sock.wq, &q->wq);
 	init_waitqueue_head(&q->wq.wait);
@@ -540,22 +544,18 @@
 	if ((tap->dev->features & NETIF_F_HIGHDMA) && (tap->dev->features & NETIF_F_SG))
 		sock_set_flag(&q->sk, SOCK_ZEROCOPY);
 
-	err = -ENOMEM;
-	if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL))
-		goto err_array;
-
 	err = tap_set_queue(tap, file, q);
-	if (err)
-		goto err_queue;
+	if (err) {
+		/* tap_sock_destruct() will take care of freeing skb_array */
+		goto err_put;
+	}
 
 	dev_put(tap->dev);
 
 	rtnl_unlock();
 	return err;
 
-err_queue:
-	skb_array_cleanup(&q->skb_array);
-err_array:
+err_put:
 	sock_put(&q->sk);
 err:
 	if (tap)
@@ -1249,8 +1249,8 @@
 	return 0;
 }
 
-int tap_create_cdev(struct cdev *tap_cdev,
-		    dev_t *tap_major, const char *device_name)
+int tap_create_cdev(struct cdev *tap_cdev, dev_t *tap_major,
+		    const char *device_name, struct module *module)
 {
 	int err;
 
@@ -1259,6 +1259,7 @@
 		goto out1;
 
 	cdev_init(tap_cdev, &tap_fops);
+	tap_cdev->owner = module;
 	err = cdev_add(tap_cdev, *tap_major, TAP_NUM_DEVS);
 	if (err)
 		goto out2;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 3c9985f..5550f56 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1286,6 +1286,7 @@
 	buflen += SKB_DATA_ALIGN(len + pad);
 	rcu_read_unlock();
 
+	alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES);
 	if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL)))
 		return ERR_PTR(-ENOMEM);
 
@@ -1496,11 +1497,13 @@
 	switch (tun->flags & TUN_TYPE_MASK) {
 	case IFF_TUN:
 		if (tun->flags & IFF_NO_PI) {
-			switch (skb->data[0] & 0xf0) {
-			case 0x40:
+			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
+
+			switch (ip_version) {
+			case 4:
 				pi.proto = htons(ETH_P_IP);
 				break;
-			case 0x60:
+			case 6:
 				pi.proto = htons(ETH_P_IPV6);
 				break;
 			default:
@@ -2025,6 +2028,9 @@
 
 		if (!dev)
 			return -ENOMEM;
+		err = dev_get_valid_name(net, dev, name);
+		if (err < 0)
+			goto err_free_dev;
 
 		dev_net_set(dev, net);
 		dev->rtnl_link_ops = &tun_link_ops;
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 8ab281b..3e7a3ac 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -54,11 +54,19 @@
 		desc->bInterfaceProtocol == 3);
 }
 
+static int is_novatel_rndis(struct usb_interface_descriptor *desc)
+{
+	return (desc->bInterfaceClass == USB_CLASS_MISC &&
+		desc->bInterfaceSubClass == 4 &&
+		desc->bInterfaceProtocol == 1);
+}
+
 #else
 
 #define is_rndis(desc)		0
 #define is_activesync(desc)	0
 #define is_wireless_rndis(desc)	0
+#define is_novatel_rndis(desc)	0
 
 #endif
 
@@ -150,7 +158,8 @@
 	 */
 	rndis = (is_rndis(&intf->cur_altsetting->desc) ||
 		 is_activesync(&intf->cur_altsetting->desc) ||
-		 is_wireless_rndis(&intf->cur_altsetting->desc));
+		 is_wireless_rndis(&intf->cur_altsetting->desc) ||
+		 is_novatel_rndis(&intf->cur_altsetting->desc));
 
 	memset(info, 0, sizeof(*info));
 	info->control = intf;
@@ -547,9 +556,12 @@
 #define REALTEK_VENDOR_ID	0x0bda
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
+#define LINKSYS_VENDOR_ID	0x13b1
 #define NVIDIA_VENDOR_ID	0x0955
 #define HP_VENDOR_ID		0x03f0
 #define MICROSOFT_VENDOR_ID	0x045e
+#define UBLOX_VENDOR_ID		0x1546
+#define TPLINK_VENDOR_ID	0x2357
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -737,6 +749,15 @@
 	.driver_info = 0,
 },
 
+#if IS_ENABLED(CONFIG_USB_RTL8152)
+/* Linksys USB3GIGV1 Ethernet Adapter */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LINKSYS_VENDOR_ID, 0x0041, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+#endif
+
 /* ThinkPad USB-C Dock (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM,
@@ -793,6 +814,13 @@
 	.driver_info = 0,
 },
 
+	/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
@@ -844,12 +872,30 @@
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = (kernel_ulong_t)&wwan_info,
 }, {
+	/* Huawei ME906 and ME909 */
+	USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x15c1, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&wwan_info,
+}, {
 	/* ZTE modules */
 	USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, USB_CLASS_COMM,
 				      USB_CDC_SUBCLASS_ETHERNET,
 				      USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&zte_cdc_info,
 }, {
+	/* U-blox TOBY-L2 */
+	USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1143, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&wwan_info,
+}, {
+	/* U-blox SARA-U2 */
+	USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1104, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&wwan_info,
+}, {
 	USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET,
 			USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long) &cdc_info,
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index b99a7fb..0161f77 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1265,30 +1265,45 @@
 				      struct ethtool_eeprom *ee, u8 *data)
 {
 	struct lan78xx_net *dev = netdev_priv(netdev);
+	int ret;
+
+	ret = usb_autopm_get_interface(dev->intf);
+	if (ret)
+		return ret;
 
 	ee->magic = LAN78XX_EEPROM_MAGIC;
 
-	return lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data);
+	ret = lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data);
+
+	usb_autopm_put_interface(dev->intf);
+
+	return ret;
 }
 
 static int lan78xx_ethtool_set_eeprom(struct net_device *netdev,
 				      struct ethtool_eeprom *ee, u8 *data)
 {
 	struct lan78xx_net *dev = netdev_priv(netdev);
+	int ret;
 
-	/* Allow entire eeprom update only */
-	if ((ee->magic == LAN78XX_EEPROM_MAGIC) &&
-	    (ee->offset == 0) &&
-	    (ee->len == 512) &&
-	    (data[0] == EEPROM_INDICATOR))
-		return lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data);
+	ret = usb_autopm_get_interface(dev->intf);
+	if (ret)
+		return ret;
+
+	/* Invalid EEPROM_INDICATOR at offset zero will result in a failure
+	 * to load data from EEPROM
+	 */
+	if (ee->magic == LAN78XX_EEPROM_MAGIC)
+		ret = lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data);
 	else if ((ee->magic == LAN78XX_OTP_MAGIC) &&
 		 (ee->offset == 0) &&
 		 (ee->len == 512) &&
 		 (data[0] == OTP_INDICATOR_1))
-		return lan78xx_write_raw_otp(dev, ee->offset, ee->len, data);
+		ret = lan78xx_write_raw_otp(dev, ee->offset, ee->len, data);
 
-	return -EINVAL;
+	usb_autopm_put_interface(dev->intf);
+
+	return ret;
 }
 
 static void lan78xx_get_strings(struct net_device *netdev, u32 stringset,
@@ -2434,7 +2449,6 @@
 	/* LAN7801 only has RGMII mode */
 	if (dev->chipid == ID_REV_CHIP_ID_7801_)
 		buf &= ~MAC_CR_GMII_EN_;
-	buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_;
 	ret = lan78xx_write_reg(dev, MAC_CR, buf);
 
 	ret = lan78xx_read_reg(dev, MAC_TX, &buf);
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index ceb78e2..d51d9ab 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -613,7 +613,9 @@
 #define VENDOR_ID_MICROSOFT		0x045e
 #define VENDOR_ID_SAMSUNG		0x04e8
 #define VENDOR_ID_LENOVO		0x17ef
+#define VENDOR_ID_LINKSYS		0x13b1
 #define VENDOR_ID_NVIDIA		0x0955
+#define VENDOR_ID_TPLINK		0x2357
 
 #define MCU_TYPE_PLA			0x0100
 #define MCU_TYPE_USB			0x0000
@@ -5316,7 +5318,9 @@
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x720c)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7214)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_TPLINK,  0x0601)},
 	{}
 };
 
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index a151f26..b807c91 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -632,6 +632,10 @@
 	/* RNDIS for tethering */
 	USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3),
 	.driver_info = (unsigned long) &rndis_info,
+}, {
+	/* Novatel Verizon USB730L */
+	USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1),
+	.driver_info = (unsigned long) &rndis_info,
 },
 	{ },		// END
 };
diff --git a/drivers/net/wimax/i2400m/fw.c b/drivers/net/wimax/i2400m/fw.c
index c9c711d..a89b568 100644
--- a/drivers/net/wimax/i2400m/fw.c
+++ b/drivers/net/wimax/i2400m/fw.c
@@ -652,7 +652,7 @@
 	struct device *dev = i2400m_dev(i2400m);
 	struct {
 		struct i2400m_bootrom_header cmd;
-		u8 cmd_payload[chunk_len];
+		u8 cmd_payload[];
 	} __packed *buf;
 	struct i2400m_bootrom_header ack;
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index ee8ed9da..4491ca5 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -486,7 +486,7 @@
 
 	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;
 
-	dev->min_mtu = 0;
+	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = ETH_MAX_MTU - VLAN_ETH_HLEN;
 
 	/*
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 523387e..8b8689c 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1316,7 +1316,7 @@
 	netdev->features |= netdev->hw_features;
 
 	netdev->ethtool_ops = &xennet_ethtool_ops;
-	netdev->min_mtu = 0;
+	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = XEN_NETIF_MAX_TX_SIZE;
 	SET_NETDEV_DEV(netdev, &dev->dev);
 
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 1427a38..3e4d1e7 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1417,6 +1417,15 @@
 		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
 		struct nd_namespace_index *nsindex;
 
+		/*
+		 * If any of the DIMMs do not support labels the only
+		 * possible BTT format is v1.
+		 */
+		if (!ndd) {
+			loop_bitmask = 0;
+			break;
+		}
+
 		nsindex = to_namespace_index(ndd, ndd->ns_current);
 		if (nsindex == NULL)
 			loop_bitmask |= 1;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index acc816b..5a14cc7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -134,8 +134,6 @@
 		return false;
 	if (nvme_req(req)->status & NVME_SC_DNR)
 		return false;
-	if (jiffies - req->start_time >= req->timeout)
-		return false;
 	if (nvme_req(req)->retries >= nvme_max_retries)
 		return false;
 	return true;
@@ -2138,7 +2136,7 @@
 	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
 
 	if (a == &dev_attr_uuid.attr) {
-		if (uuid_is_null(&ns->uuid) ||
+		if (uuid_is_null(&ns->uuid) &&
 		    !memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
 			return 0;
 	}
@@ -2590,7 +2588,7 @@
 		container_of(work, struct nvme_ctrl, async_event_work);
 
 	spin_lock_irq(&ctrl->lock);
-	while (ctrl->event_limit > 0) {
+	while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) {
 		int aer_idx = --ctrl->event_limit;
 
 		spin_unlock_irq(&ctrl->lock);
@@ -2677,7 +2675,8 @@
 		/*FALLTHRU*/
 	case NVME_SC_ABORT_REQ:
 		++ctrl->event_limit;
-		queue_work(nvme_wq, &ctrl->async_event_work);
+		if (ctrl->state == NVME_CTRL_LIVE)
+			queue_work(nvme_wq, &ctrl->async_event_work);
 		break;
 	default:
 		break;
@@ -2692,7 +2691,7 @@
 		nvme_queue_scan(ctrl);
 		break;
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		schedule_work(&ctrl->fw_act_work);
+		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 4730775..555c976 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -565,6 +565,7 @@
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
 	opts->nr_io_queues = num_online_cpus();
 	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
+	opts->kato = NVME_DEFAULT_KATO;
 
 	options = o = kstrdup(buf, GFP_KERNEL);
 	if (!options)
@@ -655,21 +656,22 @@
 				goto out;
 			}
 
-			if (opts->discovery_nqn) {
-				pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n");
-				ret = -EINVAL;
-				goto out;
-			}
-
 			if (token < 0) {
 				pr_err("Invalid keep_alive_tmo %d\n", token);
 				ret = -EINVAL;
 				goto out;
-			} else if (token == 0) {
+			} else if (token == 0 && !opts->discovery_nqn) {
 				/* Allowed for debug */
 				pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
 			}
 			opts->kato = token;
+
+			if (opts->discovery_nqn && opts->kato) {
+				pr_err("Discovery controllers cannot accept KATO != 0\n");
+				ret = -EINVAL;
+				goto out;
+			}
+
 			break;
 		case NVMF_OPT_CTRL_LOSS_TMO:
 			if (match_int(args, &token)) {
@@ -762,8 +764,6 @@
 	uuid_copy(&opts->host->id, &hostid);
 
 out:
-	if (!opts->discovery_nqn && !opts->kato)
-		opts->kato = NVME_DEFAULT_KATO;
 	kfree(options);
 	return ret;
 }
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index d2e882c..be49d0f 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1376,7 +1376,7 @@
 	if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
 		status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
 	else if (freq->status)
-		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 
 	/*
 	 * For the linux implementation, if we have an unsuccesful
@@ -1404,7 +1404,7 @@
 		 */
 		if (freq->transferred_length !=
 			be32_to_cpu(op->cmd_iu.data_len)) {
-			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+			status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 			goto done;
 		}
 		result.u64 = 0;
@@ -1421,7 +1421,7 @@
 					freq->transferred_length ||
 			     op->rsp_iu.status_code ||
 			     sqe->common.command_id != cqe->command_id)) {
-			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+			status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 			goto done;
 		}
 		result = cqe->result;
@@ -1429,7 +1429,7 @@
 		break;
 
 	default:
-		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 		goto done;
 	}
 
@@ -1989,16 +1989,17 @@
 	 * as well as those by FC-NVME spec.
 	 */
 	WARN_ON_ONCE(sqe->common.metadata);
-	WARN_ON_ONCE(sqe->common.dptr.prp1);
-	WARN_ON_ONCE(sqe->common.dptr.prp2);
 	sqe->common.flags |= NVME_CMD_SGL_METABUF;
 
 	/*
-	 * format SQE DPTR field per FC-NVME rules
-	 *    type=data block descr; subtype=offset;
-	 *    offset is currently 0.
+	 * format SQE DPTR field per FC-NVME rules:
+	 *    type=0x5     Transport SGL Data Block Descriptor
+	 *    subtype=0xA  Transport-specific value
+	 *    address=0
+	 *    length=length of the data series
 	 */
-	sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET;
+	sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) |
+					NVME_SGL_FMT_TRANSPORT_A;
 	sqe->rw.dptr.sgl.length = cpu_to_le32(data_len);
 	sqe->rw.dptr.sgl.addr = 0;
 
@@ -2544,10 +2545,10 @@
 	nvme_fc_abort_aen_ops(ctrl);
 
 	/* wait for all io that had to be aborted */
-	spin_lock_irqsave(&ctrl->lock, flags);
+	spin_lock_irq(&ctrl->lock);
 	wait_event_lock_irq(ctrl->ioabort_wait, ctrl->iocnt == 0, ctrl->lock);
 	ctrl->flags &= ~FCCTRL_TERMIO;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
+	spin_unlock_irq(&ctrl->lock);
 
 	nvme_fc_term_aen_ops(ctrl);
 
@@ -2733,7 +2734,7 @@
 {
 	struct nvme_fc_ctrl *ctrl;
 	unsigned long flags;
-	int ret, idx;
+	int ret, idx, retry;
 
 	if (!(rport->remoteport.port_role &
 	    (FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) {
@@ -2759,6 +2760,7 @@
 	ctrl->rport = rport;
 	ctrl->dev = lport->dev;
 	ctrl->cnum = idx;
+	init_waitqueue_head(&ctrl->ioabort_wait);
 
 	get_device(ctrl->dev);
 	kref_init(&ctrl->ref);
@@ -2824,9 +2826,37 @@
 	list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
 	spin_unlock_irqrestore(&rport->lock, flags);
 
-	ret = nvme_fc_create_association(ctrl);
+	/*
+	 * It's possible that transactions used to create the association
+	 * may fail. Examples: CreateAssociation LS or CreateIOConnection
+	 * LS gets dropped/corrupted/fails; or a frame gets dropped or a
+	 * command times out for one of the actions to init the controller
+	 * (Connect, Get/Set_Property, Set_Features, etc). Many of these
+	 * transport errors (frame drop, LS failure) inherently must kill
+	 * the association. The transport is coded so that any command used
+	 * to create the association (prior to a LIVE state transition
+	 * while NEW or RECONNECTING) will fail if it completes in error or
+	 * times out.
+	 *
+	 * As such: as the connect request was mostly likely due to a
+	 * udev event that discovered the remote port, meaning there is
+	 * not an admin or script there to restart if the connect
+	 * request fails, retry the initial connection creation up to
+	 * three times before giving up and declaring failure.
+	 */
+	for (retry = 0; retry < 3; retry++) {
+		ret = nvme_fc_create_association(ctrl);
+		if (!ret)
+			break;
+	}
+
 	if (ret) {
+		/* couldn't schedule retry - fail out */
+		dev_err(ctrl->ctrl.device,
+			"NVME-FC{%d}: Connect retry failed\n", ctrl->cnum);
+
 		ctrl->ctrl.opts = NULL;
+
 		/* initiate nvme ctrl ref counting teardown */
 		nvme_uninit_ctrl(&ctrl->ctrl);
 		nvme_put_ctrl(&ctrl->ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4a21213..3f5a04c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -24,6 +24,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/once.h>
 #include <linux/pci.h>
 #include <linux/poison.h>
 #include <linux/t10-pi.h>
@@ -93,7 +94,7 @@
 	struct mutex shutdown_lock;
 	bool subsystem;
 	void __iomem *cmb;
-	dma_addr_t cmb_dma_addr;
+	pci_bus_addr_t cmb_bus_addr;
 	u64 cmb_size;
 	u32 cmbsz;
 	u32 cmbloc;
@@ -540,6 +541,20 @@
 }
 #endif
 
+static void nvme_print_sgl(struct scatterlist *sgl, int nents)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		dma_addr_t phys = sg_phys(sg);
+		pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
+			"dma_address:%pad dma_length:%d\n",
+			i, &phys, sg->offset, sg->length, &sg_dma_address(sg),
+			sg_dma_len(sg));
+	}
+}
+
 static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -622,19 +637,10 @@
 	return BLK_STS_OK;
 
  bad_sgl:
-	if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n",
-				blk_rq_payload_bytes(req), iod->nents)) {
-		for_each_sg(iod->sg, sg, iod->nents, i) {
-			dma_addr_t phys = sg_phys(sg);
-			pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
-			       "dma_address:%pad dma_length:%d\n", i, &phys,
-					sg->offset, sg->length,
-					&sg_dma_address(sg),
-					sg_dma_len(sg));
-		}
-	}
+	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
+			"Invalid SGL for payload:%d nents:%d\n",
+			blk_rq_payload_bytes(req), iod->nents);
 	return BLK_STS_IOERR;
-
 }
 
 static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
@@ -1220,7 +1226,7 @@
 	if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) {
 		unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth),
 						      dev->ctrl.page_size);
-		nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset;
+		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
 		nvmeq->sq_cmds_io = dev->cmb + offset;
 	} else {
 		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
@@ -1313,11 +1319,11 @@
 	if (result < 0)
 		goto release_cq;
 
+	nvme_init_queue(nvmeq, qid);
 	result = queue_request_irq(nvmeq);
 	if (result < 0)
 		goto release_sq;
 
-	nvme_init_queue(nvmeq, qid);
 	return result;
 
  release_sq:
@@ -1464,6 +1470,7 @@
 		return result;
 
 	nvmeq->cq_vector = 0;
+	nvme_init_queue(nvmeq, 0);
 	result = queue_request_irq(nvmeq);
 	if (result) {
 		nvmeq->cq_vector = -1;
@@ -1520,7 +1527,7 @@
 	resource_size_t bar_size;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	void __iomem *cmb;
-	dma_addr_t dma_addr;
+	int bar;
 
 	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
 	if (!(NVME_CMB_SZ(dev->cmbsz)))
@@ -1533,7 +1540,8 @@
 	szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
 	size = szu * NVME_CMB_SZ(dev->cmbsz);
 	offset = szu * NVME_CMB_OFST(dev->cmbloc);
-	bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc));
+	bar = NVME_CMB_BIR(dev->cmbloc);
+	bar_size = pci_resource_len(pdev, bar);
 
 	if (offset > bar_size)
 		return NULL;
@@ -1546,12 +1554,11 @@
 	if (size > bar_size - offset)
 		size = bar_size - offset;
 
-	dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset;
-	cmb = ioremap_wc(dma_addr, size);
+	cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size);
 	if (!cmb)
 		return NULL;
 
-	dev->cmb_dma_addr = dma_addr;
+	dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset;
 	dev->cmb_size = size;
 	return cmb;
 }
@@ -2156,7 +2163,6 @@
 	if (result)
 		goto out;
 
-	nvme_init_queue(dev->queues[0], 0);
 	result = nvme_alloc_admin_tags(dev);
 	if (result)
 		goto out;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 5898300..87bac27 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -571,6 +571,12 @@
 	if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags))
 		return;
 
+	if (nvme_rdma_queue_idx(queue) == 0) {
+		nvme_rdma_free_qe(queue->device->dev,
+			&queue->ctrl->async_event_sqe,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+	}
+
 	nvme_rdma_destroy_queue_ib(queue);
 	rdma_destroy_id(queue->cm_id);
 }
@@ -739,8 +745,6 @@
 static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe,
-			sizeof(struct nvme_command), DMA_TO_DEVICE);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
@@ -765,8 +769,10 @@
 
 	if (new) {
 		ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
-		if (IS_ERR(ctrl->ctrl.admin_tagset))
+		if (IS_ERR(ctrl->ctrl.admin_tagset)) {
+			error = PTR_ERR(ctrl->ctrl.admin_tagset);
 			goto out_free_queue;
+		}
 
 		ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
 		if (IS_ERR(ctrl->ctrl.admin_q)) {
@@ -846,8 +852,10 @@
 
 	if (new) {
 		ctrl->ctrl.tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, false);
-		if (IS_ERR(ctrl->ctrl.tagset))
+		if (IS_ERR(ctrl->ctrl.tagset)) {
+			ret = PTR_ERR(ctrl->ctrl.tagset);
 			goto out_free_io_queues;
+		}
 
 		ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
 		if (IS_ERR(ctrl->ctrl.connect_q)) {
@@ -942,7 +950,12 @@
 	}
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
+	if (!changed) {
+		/* state change failure is ok if we're in DELETING state */
+		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+		return;
+	}
+
 	ctrl->ctrl.nr_reconnects = 0;
 
 	nvme_start_ctrl(&ctrl->ctrl);
@@ -962,7 +975,7 @@
 	struct nvme_rdma_ctrl *ctrl = container_of(work,
 			struct nvme_rdma_ctrl, err_work);
 
-	nvme_stop_ctrl(&ctrl->ctrl);
+	nvme_stop_keep_alive(&ctrl->ctrl);
 
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_stop_queues(&ctrl->ctrl);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 7c23eaf..645ba7e 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -387,13 +387,22 @@
 
 static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 {
+	u32 old_sqhd, new_sqhd;
+	u16 sqhd;
+
 	if (status)
 		nvmet_set_status(req, status);
 
-	/* XXX: need to fill in something useful for sq_head */
-	req->rsp->sq_head = 0;
-	if (likely(req->sq)) /* may happen during early failure */
-		req->rsp->sq_id = cpu_to_le16(req->sq->qid);
+	if (req->sq->size) {
+		do {
+			old_sqhd = req->sq->sqhd;
+			new_sqhd = (old_sqhd + 1) % req->sq->size;
+		} while (cmpxchg(&req->sq->sqhd, old_sqhd, new_sqhd) !=
+					old_sqhd);
+	}
+	sqhd = req->sq->sqhd & 0x0000FFFF;
+	req->rsp->sq_head = cpu_to_le16(sqhd);
+	req->rsp->sq_id = cpu_to_le16(req->sq->qid);
 	req->rsp->command_id = req->cmd->common.command_id;
 
 	if (req->ns)
@@ -420,6 +429,7 @@
 void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
 		u16 qid, u16 size)
 {
+	sq->sqhd = 0;
 	sq->qid = qid;
 	sq->size = size;
 
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 859a667..db3bf6b 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -109,9 +109,14 @@
 		pr_warn("queue already connected!\n");
 		return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
 	}
+	if (!sqsize) {
+		pr_warn("queue size zero!\n");
+		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+	}
 
-	nvmet_cq_setup(ctrl, req->cq, qid, sqsize);
-	nvmet_sq_setup(ctrl, req->sq, qid, sqsize);
+	/* note: convert queue size from 0's-based value to 1's-based value */
+	nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1);
+	nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1);
 	return 0;
 }
 
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 421e43b..58e010b 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -148,7 +148,7 @@
 	u32				a_id;
 	struct nvmet_fc_tgtport		*tgtport;
 	struct list_head		a_list;
-	struct nvmet_fc_tgt_queue	*queues[NVMET_NR_QUEUES];
+	struct nvmet_fc_tgt_queue	*queues[NVMET_NR_QUEUES + 1];
 	struct kref			ref;
 };
 
@@ -608,7 +608,7 @@
 	unsigned long flags;
 	int ret;
 
-	if (qid >= NVMET_NR_QUEUES)
+	if (qid > NVMET_NR_QUEUES)
 		return NULL;
 
 	queue = kzalloc((sizeof(*queue) +
@@ -783,6 +783,9 @@
 	u16 qid = nvmet_fc_getqueueid(connection_id);
 	unsigned long flags;
 
+	if (qid > NVMET_NR_QUEUES)
+		return NULL;
+
 	spin_lock_irqsave(&tgtport->lock, flags);
 	list_for_each_entry(assoc, &tgtport->assoc_list, a_list) {
 		if (association_id == assoc->association_id) {
@@ -888,7 +891,7 @@
 	int i;
 
 	spin_lock_irqsave(&tgtport->lock, flags);
-	for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) {
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
 		queue = assoc->queues[i];
 		if (queue) {
 			if (!nvmet_fc_tgt_q_get(queue))
@@ -1910,8 +1913,7 @@
 			spin_lock_irqsave(&fod->flock, flags);
 			fod->writedataactive = false;
 			spin_unlock_irqrestore(&fod->flock, flags);
-			nvmet_req_complete(&fod->req,
-					NVME_SC_FC_TRANSPORT_ERROR);
+			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 		} else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
 			fcpreq->fcp_error = ret;
 			fcpreq->transferred_length = 0;
@@ -1929,8 +1931,7 @@
 	/* if in the middle of an io and we need to tear down */
 	if (abort) {
 		if (fcpreq->op == NVMET_FCOP_WRITEDATA) {
-			nvmet_req_complete(&fod->req,
-					NVME_SC_FC_TRANSPORT_ERROR);
+			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return true;
 		}
 
@@ -1968,8 +1969,7 @@
 			fod->abort = true;
 			spin_unlock(&fod->flock);
 
-			nvmet_req_complete(&fod->req,
-					NVME_SC_FC_TRANSPORT_ERROR);
+			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return;
 		}
 
@@ -2533,13 +2533,17 @@
 {
 	struct nvmet_fc_tgtport *tgtport = port->priv;
 	unsigned long flags;
+	bool matched = false;
 
 	spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
 	if (tgtport->port == port) {
-		nvmet_fc_tgtport_put(tgtport);
+		matched = true;
 		tgtport->port = NULL;
 	}
 	spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
+
+	if (matched)
+		nvmet_fc_tgtport_put(tgtport);
 }
 
 static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = {
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 1cb9847..7b75d9d 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -224,8 +224,6 @@
 	struct fcloop_lport *lport;
 	struct list_head nport_list;
 	struct kref ref;
-	struct completion rport_unreg_done;
-	struct completion tport_unreg_done;
 	u64 node_name;
 	u64 port_name;
 	u32 port_role;
@@ -576,7 +574,7 @@
 	tfcp_req->aborted = true;
 	spin_unlock(&tfcp_req->reqlock);
 
-	tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
+	tfcp_req->status = NVME_SC_INTERNAL;
 
 	/*
 	 * nothing more to do. If io wasn't active, the transport should
@@ -631,6 +629,32 @@
 }
 
 static void
+fcloop_nport_free(struct kref *ref)
+{
+	struct fcloop_nport *nport =
+		container_of(ref, struct fcloop_nport, ref);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fcloop_lock, flags);
+	list_del(&nport->nport_list);
+	spin_unlock_irqrestore(&fcloop_lock, flags);
+
+	kfree(nport);
+}
+
+static void
+fcloop_nport_put(struct fcloop_nport *nport)
+{
+	kref_put(&nport->ref, fcloop_nport_free);
+}
+
+static int
+fcloop_nport_get(struct fcloop_nport *nport)
+{
+	return kref_get_unless_zero(&nport->ref);
+}
+
+static void
 fcloop_localport_delete(struct nvme_fc_local_port *localport)
 {
 	struct fcloop_lport *lport = localport->private;
@@ -644,8 +668,7 @@
 {
 	struct fcloop_rport *rport = remoteport->private;
 
-	/* release any threads waiting for the unreg to complete */
-	complete(&rport->nport->rport_unreg_done);
+	fcloop_nport_put(rport->nport);
 }
 
 static void
@@ -653,8 +676,7 @@
 {
 	struct fcloop_tport *tport = targetport->private;
 
-	/* release any threads waiting for the unreg to complete */
-	complete(&tport->nport->tport_unreg_done);
+	fcloop_nport_put(tport->nport);
 }
 
 #define	FCLOOP_HW_QUEUES		4
@@ -722,6 +744,7 @@
 		goto out_free_opts;
 	}
 
+	memset(&pinfo, 0, sizeof(pinfo));
 	pinfo.node_name = opts->wwnn;
 	pinfo.port_name = opts->wwpn;
 	pinfo.port_role = opts->roles;
@@ -804,32 +827,6 @@
 	return ret ? ret : count;
 }
 
-static void
-fcloop_nport_free(struct kref *ref)
-{
-	struct fcloop_nport *nport =
-		container_of(ref, struct fcloop_nport, ref);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fcloop_lock, flags);
-	list_del(&nport->nport_list);
-	spin_unlock_irqrestore(&fcloop_lock, flags);
-
-	kfree(nport);
-}
-
-static void
-fcloop_nport_put(struct fcloop_nport *nport)
-{
-	kref_put(&nport->ref, fcloop_nport_free);
-}
-
-static int
-fcloop_nport_get(struct fcloop_nport *nport)
-{
-	return kref_get_unless_zero(&nport->ref);
-}
-
 static struct fcloop_nport *
 fcloop_alloc_nport(const char *buf, size_t count, bool remoteport)
 {
@@ -938,6 +935,7 @@
 	if (!nport)
 		return -EIO;
 
+	memset(&pinfo, 0, sizeof(pinfo));
 	pinfo.node_name = nport->node_name;
 	pinfo.port_name = nport->port_name;
 	pinfo.port_role = nport->port_role;
@@ -979,24 +977,12 @@
 }
 
 static int
-__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
+__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
 {
-	int ret;
-
 	if (!rport)
 		return -EALREADY;
 
-	init_completion(&nport->rport_unreg_done);
-
-	ret = nvme_fc_unregister_remoteport(rport->remoteport);
-	if (ret)
-		return ret;
-
-	wait_for_completion(&nport->rport_unreg_done);
-
-	fcloop_nport_put(nport);
-
-	return ret;
+	return nvme_fc_unregister_remoteport(rport->remoteport);
 }
 
 static ssize_t
@@ -1029,7 +1015,7 @@
 	if (!nport)
 		return -ENOENT;
 
-	ret = __wait_remoteport_unreg(nport, rport);
+	ret = __remoteport_unreg(nport, rport);
 
 	return ret ? ret : count;
 }
@@ -1086,24 +1072,12 @@
 }
 
 static int
-__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
+__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
 {
-	int ret;
-
 	if (!tport)
 		return -EALREADY;
 
-	init_completion(&nport->tport_unreg_done);
-
-	ret = nvmet_fc_unregister_targetport(tport->targetport);
-	if (ret)
-		return ret;
-
-	wait_for_completion(&nport->tport_unreg_done);
-
-	fcloop_nport_put(nport);
-
-	return ret;
+	return nvmet_fc_unregister_targetport(tport->targetport);
 }
 
 static ssize_t
@@ -1136,7 +1110,7 @@
 	if (!nport)
 		return -ENOENT;
 
-	ret = __wait_targetport_unreg(nport, tport);
+	ret = __targetport_unreg(nport, tport);
 
 	return ret ? ret : count;
 }
@@ -1223,11 +1197,11 @@
 
 		spin_unlock_irqrestore(&fcloop_lock, flags);
 
-		ret = __wait_targetport_unreg(nport, tport);
+		ret = __targetport_unreg(nport, tport);
 		if (ret)
 			pr_warn("%s: Failed deleting target port\n", __func__);
 
-		ret = __wait_remoteport_unreg(nport, rport);
+		ret = __remoteport_unreg(nport, rport);
 		if (ret)
 			pr_warn("%s: Failed deleting remote port\n", __func__);
 
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 7d261ab..87e429b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -74,6 +74,7 @@
 	struct percpu_ref	ref;
 	u16			qid;
 	u16			size;
+	u32			sqhd;
 	struct completion	free_done;
 	struct completion	confirm_done;
 };
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index de54c7f..d12e5de 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -135,7 +135,7 @@
 
 	/* Stop the user from writing */
 	if (pos >= nvmem->size)
-		return 0;
+		return -EFBIG;
 
 	if (count < nvmem->word_size)
 		return -EINVAL;
@@ -789,6 +789,7 @@
 		return ERR_PTR(-EINVAL);
 
 	nvmem = __nvmem_device_get(nvmem_np, NULL, NULL);
+	of_node_put(nvmem_np);
 	if (IS_ERR(nvmem))
 		return ERR_CAST(nvmem);
 
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 260d33c..6389753 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1781,8 +1781,12 @@
 {
 	if (!dn || dn != of_stdout || console_set_on_cmdline)
 		return false;
-	return !add_preferred_console(name, index,
-				      kstrdup(of_stdout_options, GFP_KERNEL));
+
+	/*
+	 * XXX: cast `options' to char pointer to suppress complication
+	 * warnings: printk, UART and console drivers expect char pointer.
+	 */
+	return !add_preferred_console(name, index, (char *)of_stdout_options);
 }
 EXPORT_SYMBOL_GPL(of_console_check);
 
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index d94dd8b..9825858 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -44,7 +44,7 @@
 	return -EINVAL;
 }
 
-static void of_mdiobus_register_phy(struct mii_bus *mdio,
+static int of_mdiobus_register_phy(struct mii_bus *mdio,
 				    struct device_node *child, u32 addr)
 {
 	struct phy_device *phy;
@@ -60,9 +60,13 @@
 	else
 		phy = get_phy_device(mdio, addr, is_c45);
 	if (IS_ERR(phy))
-		return;
+		return PTR_ERR(phy);
 
-	rc = irq_of_parse_and_map(child, 0);
+	rc = of_irq_get(child, 0);
+	if (rc == -EPROBE_DEFER) {
+		phy_device_free(phy);
+		return rc;
+	}
 	if (rc > 0) {
 		phy->irq = rc;
 		mdio->irq[addr] = rc;
@@ -84,22 +88,23 @@
 	if (rc) {
 		phy_device_free(phy);
 		of_node_put(child);
-		return;
+		return rc;
 	}
 
 	dev_dbg(&mdio->dev, "registered phy %s at address %i\n",
 		child->name, addr);
+	return 0;
 }
 
-static void of_mdiobus_register_device(struct mii_bus *mdio,
-				       struct device_node *child, u32 addr)
+static int of_mdiobus_register_device(struct mii_bus *mdio,
+				      struct device_node *child, u32 addr)
 {
 	struct mdio_device *mdiodev;
 	int rc;
 
 	mdiodev = mdio_device_create(mdio, addr);
 	if (IS_ERR(mdiodev))
-		return;
+		return PTR_ERR(mdiodev);
 
 	/* Associate the OF node with the device structure so it
 	 * can be looked up later.
@@ -112,11 +117,12 @@
 	if (rc) {
 		mdio_device_free(mdiodev);
 		of_node_put(child);
-		return;
+		return rc;
 	}
 
 	dev_dbg(&mdio->dev, "registered mdio device %s at address %i\n",
 		child->name, addr);
+	return 0;
 }
 
 /* The following is a list of PHY compatible strings which appear in
@@ -219,9 +225,11 @@
 		}
 
 		if (of_mdiobus_child_is_phy(child))
-			of_mdiobus_register_phy(mdio, child, addr);
+			rc = of_mdiobus_register_phy(mdio, child, addr);
 		else
-			of_mdiobus_register_device(mdio, child, addr);
+			rc = of_mdiobus_register_device(mdio, child, addr);
+		if (rc)
+			goto unregister;
 	}
 
 	if (!scanphys)
@@ -242,12 +250,19 @@
 			dev_info(&mdio->dev, "scan phy %s at address %i\n",
 				 child->name, addr);
 
-			if (of_mdiobus_child_is_phy(child))
-				of_mdiobus_register_phy(mdio, child, addr);
+			if (of_mdiobus_child_is_phy(child)) {
+				rc = of_mdiobus_register_phy(mdio, child, addr);
+				if (rc)
+					goto unregister;
+			}
 		}
 	}
 
 	return 0;
+
+unregister:
+	mdiobus_unregister(mdio);
+	return rc;
 }
 EXPORT_SYMBOL(of_mdiobus_register);
 
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index d507c35..32771c2 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -25,7 +25,7 @@
 #include <linux/sort.h>
 #include <linux/slab.h>
 
-#define MAX_RESERVED_REGIONS	16
+#define MAX_RESERVED_REGIONS	32
 static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
 static int reserved_mem_count;
 
diff --git a/drivers/of/property.c b/drivers/of/property.c
index fbb7211..264c355 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -954,7 +954,7 @@
 	struct device_node *np;
 
 	/* Get the parent of the port */
-	np = of_get_next_parent(to_of_node(fwnode));
+	np = of_get_parent(to_of_node(fwnode));
 	if (!np)
 		return NULL;
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 4ddc6e8..f9308c2 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -251,9 +251,8 @@
 	return ret;
 }
 
-static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test)
+static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq)
 {
-	u8 irq;
 	u8 msi_count;
 	struct pci_epf *epf = epf_test->epf;
 	struct pci_epc *epc = epf->epc;
@@ -262,7 +261,6 @@
 
 	reg->status |= STATUS_IRQ_RAISED;
 	msi_count = pci_epc_get_msi(epc);
-	irq = (reg->command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
 	if (irq > msi_count || msi_count <= 0)
 		pci_epc_raise_irq(epc, PCI_EPC_IRQ_LEGACY, 0);
 	else
@@ -289,6 +287,8 @@
 	reg->command = 0;
 	reg->status = 0;
 
+	irq = (command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
+
 	if (command & COMMAND_RAISE_LEGACY_IRQ) {
 		reg->status = STATUS_IRQ_RAISED;
 		pci_epc_raise_irq(epc, PCI_EPC_IRQ_LEGACY, 0);
@@ -301,7 +301,7 @@
 			reg->status |= STATUS_WRITE_FAIL;
 		else
 			reg->status |= STATUS_WRITE_SUCCESS;
-		pci_epf_test_raise_irq(epf_test);
+		pci_epf_test_raise_irq(epf_test, irq);
 		goto reset_handler;
 	}
 
@@ -311,7 +311,7 @@
 			reg->status |= STATUS_READ_SUCCESS;
 		else
 			reg->status |= STATUS_READ_FAIL;
-		pci_epf_test_raise_irq(epf_test);
+		pci_epf_test_raise_irq(epf_test, irq);
 		goto reset_handler;
 	}
 
@@ -321,13 +321,12 @@
 			reg->status |= STATUS_COPY_SUCCESS;
 		else
 			reg->status |= STATUS_COPY_FAIL;
-		pci_epf_test_raise_irq(epf_test);
+		pci_epf_test_raise_irq(epf_test, irq);
 		goto reset_handler;
 	}
 
 	if (command & COMMAND_RAISE_MSI_IRQ) {
 		msi_count = pci_epc_get_msi(epc);
-		irq = (command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
 		if (irq > msi_count || msi_count <= 0)
 			goto reset_handler;
 		reg->status = STATUS_IRQ_RAISED;
diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c
index 89f4e3d..26ed0c0 100644
--- a/drivers/pci/host/pci-aardvark.c
+++ b/drivers/pci/host/pci-aardvark.c
@@ -935,6 +935,8 @@
 	bridge->sysdata = pcie;
 	bridge->busnr = 0;
 	bridge->ops = &advk_pcie_ops;
+	bridge->map_irq = of_irq_parse_and_map_pci;
+	bridge->swizzle_irq = pci_common_swizzle;
 
 	ret = pci_scan_root_bus_bridge(bridge);
 	if (ret < 0) {
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 9c40da5..1987fec 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -233,6 +233,7 @@
 	struct msi_controller chip;
 	DECLARE_BITMAP(used, INT_PCI_MSI_NR);
 	struct irq_domain *domain;
+	unsigned long pages;
 	struct mutex lock;
 	u64 phys;
 	int irq;
@@ -1529,22 +1530,9 @@
 		goto err;
 	}
 
-	/*
-	 * The PCI host bridge on Tegra contains some logic that intercepts
-	 * MSI writes, which means that the MSI target address doesn't have
-	 * to point to actual physical memory. Rather than allocating one 4
-	 * KiB page of system memory that's never used, we can simply pick
-	 * an arbitrary address within an area reserved for system memory
-	 * in the FPCI address map.
-	 *
-	 * However, in order to avoid confusion, we pick an address that
-	 * doesn't map to physical memory. The FPCI address map reserves a
-	 * 1012 GiB region for system memory and memory-mapped I/O. Since
-	 * none of the Tegra SoCs that contain this PCI host bridge can
-	 * address more than 16 GiB of system memory, the last 4 KiB of
-	 * these 1012 GiB is a good candidate.
-	 */
-	msi->phys = 0xfcfffff000;
+	/* setup AFI/FPCI range */
+	msi->pages = __get_free_pages(GFP_KERNEL, 0);
+	msi->phys = virt_to_phys((void *)msi->pages);
 
 	afi_writel(pcie, msi->phys >> soc->msi_base_shift, AFI_MSI_FPCI_BAR_ST);
 	afi_writel(pcie, msi->phys, AFI_MSI_AXI_BAR_ST);
@@ -1596,6 +1584,8 @@
 	afi_writel(pcie, 0, AFI_MSI_EN_VEC6);
 	afi_writel(pcie, 0, AFI_MSI_EN_VEC7);
 
+	free_pages(msi->pages, 0);
+
 	if (msi->irq > 0)
 		free_irq(msi->irq, pcie);
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 1eecfa3..8e075ea 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -686,7 +686,7 @@
 				     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	char *driver_override, *old = pdev->driver_override, *cp;
+	char *driver_override, *old, *cp;
 
 	/* We need to keep extra room for a newline */
 	if (count >= (PAGE_SIZE - 1))
@@ -700,12 +700,15 @@
 	if (cp)
 		*cp = '\0';
 
+	device_lock(dev);
+	old = pdev->driver_override;
 	if (strlen(driver_override)) {
 		pdev->driver_override = driver_override;
 	} else {
 		kfree(driver_override);
 		pdev->driver_override = NULL;
 	}
+	device_unlock(dev);
 
 	kfree(old);
 
@@ -716,8 +719,12 @@
 				    struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	ssize_t len;
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+	device_lock(dev);
+	len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);
 
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 0a9b787..3303dd8 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -235,6 +235,7 @@
 		ret = armpmu_register(pmu);
 		if (ret) {
 			pr_warn("Failed to register PMU for CPU%d\n", cpu);
+			kfree(pmu->name);
 			return ret;
 		}
 	}
diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
index 73ebad6..89c887e 100644
--- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
+++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
@@ -111,6 +111,8 @@
 #define     MVEBU_COMPHY_CONF6_40B		BIT(18)
 #define MVEBU_COMPHY_SELECTOR			0x1140
 #define     MVEBU_COMPHY_SELECTOR_PHY(n)	((n) * 0x4)
+#define MVEBU_COMPHY_PIPE_SELECTOR		0x1144
+#define     MVEBU_COMPHY_PIPE_SELECTOR_PIPE(n)	((n) * 0x4)
 
 #define MVEBU_COMPHY_LANES	6
 #define MVEBU_COMPHY_PORTS	3
@@ -468,13 +470,17 @@
 {
 	struct mvebu_comphy_lane *lane = phy_get_drvdata(phy);
 	struct mvebu_comphy_priv *priv = lane->priv;
-	int ret;
-	u32 mux, val;
+	int ret, mux;
+	u32 val;
 
 	mux = mvebu_comphy_get_mux(lane->id, lane->port, lane->mode);
 	if (mux < 0)
 		return -ENOTSUPP;
 
+	regmap_read(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, &val);
+	val &= ~(0xf << MVEBU_COMPHY_PIPE_SELECTOR_PIPE(lane->id));
+	regmap_write(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, val);
+
 	regmap_read(priv->regmap, MVEBU_COMPHY_SELECTOR, &val);
 	val &= ~(0xf << MVEBU_COMPHY_SELECTOR_PHY(lane->id));
 	val |= mux << MVEBU_COMPHY_SELECTOR_PHY(lane->id);
@@ -526,6 +532,10 @@
 	val &= ~(0xf << MVEBU_COMPHY_SELECTOR_PHY(lane->id));
 	regmap_write(priv->regmap, MVEBU_COMPHY_SELECTOR, val);
 
+	regmap_read(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, &val);
+	val &= ~(0xf << MVEBU_COMPHY_PIPE_SELECTOR_PIPE(lane->id));
+	regmap_write(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, val);
+
 	return 0;
 }
 
@@ -576,8 +586,8 @@
 		return PTR_ERR(priv->regmap);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	priv->base = devm_ioremap_resource(&pdev->dev, res);
-	if (!priv->base)
-		return -ENOMEM;
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
 
 	for_each_available_child_of_node(pdev->dev.of_node, child) {
 		struct mvebu_comphy_lane *lane;
diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c
index e3baad7..721a2a1 100644
--- a/drivers/phy/mediatek/phy-mtk-tphy.c
+++ b/drivers/phy/mediatek/phy-mtk-tphy.c
@@ -27,6 +27,7 @@
 /* banks shared by multiple phys */
 #define SSUSB_SIFSLV_V1_SPLLC		0x000	/* shared by u3 phys */
 #define SSUSB_SIFSLV_V1_U2FREQ		0x100	/* shared by u2 phys */
+#define SSUSB_SIFSLV_V1_CHIP		0x300	/* shared by u3 phys */
 /* u2 phy bank */
 #define SSUSB_SIFSLV_V1_U2PHY_COM	0x000
 /* u3/pcie/sata phy banks */
@@ -762,7 +763,7 @@
 	case PHY_TYPE_USB3:
 	case PHY_TYPE_PCIE:
 		u3_banks->spllc = tphy->sif_base + SSUSB_SIFSLV_V1_SPLLC;
-		u3_banks->chip = NULL;
+		u3_banks->chip = tphy->sif_base + SSUSB_SIFSLV_V1_CHIP;
 		u3_banks->phyd = instance->port_base + SSUSB_SIFSLV_V1_U3PHYD;
 		u3_banks->phya = instance->port_base + SSUSB_SIFSLV_V1_U3PHYA;
 		break;
diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c
index 4d2c57f..a958c9b 100644
--- a/drivers/phy/rockchip/phy-rockchip-typec.c
+++ b/drivers/phy/rockchip/phy-rockchip-typec.c
@@ -443,14 +443,34 @@
 	return regmap_write(tcphy->grf_regs, reg->offset, val | mask);
 }
 
+static void tcphy_dp_aux_set_flip(struct rockchip_typec_phy *tcphy)
+{
+	u16 tx_ana_ctrl_reg_1;
+
+	/*
+	 * Select the polarity of the xcvr:
+	 * 1, Reverses the polarity (If TYPEC, Pulls ups aux_p and pull
+	 * down aux_m)
+	 * 0, Normal polarity (if TYPEC, pulls up aux_m and pulls down
+	 * aux_p)
+	 */
+	tx_ana_ctrl_reg_1 = readl(tcphy->base + TX_ANA_CTRL_REG_1);
+	if (!tcphy->flip)
+		tx_ana_ctrl_reg_1 |= BIT(12);
+	else
+		tx_ana_ctrl_reg_1 &= ~BIT(12);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
+}
+
 static void tcphy_dp_aux_calibration(struct rockchip_typec_phy *tcphy)
 {
+	u16 tx_ana_ctrl_reg_1;
 	u16 rdata, rdata2, val;
 
 	/* disable txda_cal_latch_en for rewrite the calibration values */
-	rdata = readl(tcphy->base + TX_ANA_CTRL_REG_1);
-	val = rdata & 0xdfff;
-	writel(val, tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 = readl(tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 &= ~BIT(13);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
 
 	/*
 	 * read a resistor calibration code from CMN_TXPUCAL_CTRL[6:0] and
@@ -472,9 +492,8 @@
 	 * Activate this signal for 1 clock cycle to sample new calibration
 	 * values.
 	 */
-	rdata = readl(tcphy->base + TX_ANA_CTRL_REG_1);
-	val = rdata | 0x2000;
-	writel(val, tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 |= BIT(13);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
 	usleep_range(150, 200);
 
 	/* set TX Voltage Level and TX Deemphasis to 0 */
@@ -482,8 +501,10 @@
 	/* re-enable decap */
 	writel(0x100, tcphy->base + TX_ANA_CTRL_REG_2);
 	writel(0x300, tcphy->base + TX_ANA_CTRL_REG_2);
-	writel(0x2008, tcphy->base + TX_ANA_CTRL_REG_1);
-	writel(0x2018, tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 |= BIT(3);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 |= BIT(4);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
 
 	writel(0, tcphy->base + TX_ANA_CTRL_REG_5);
 
@@ -494,8 +515,10 @@
 	writel(0x1001, tcphy->base + TX_ANA_CTRL_REG_4);
 
 	/* re-enables Bandgap reference for LDO */
-	writel(0x2098, tcphy->base + TX_ANA_CTRL_REG_1);
-	writel(0x2198, tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 |= BIT(7);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 |= BIT(8);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
 
 	/*
 	 * re-enables the transmitter pre-driver, driver data selection MUX,
@@ -505,27 +528,26 @@
 	writel(0x303, tcphy->base + TX_ANA_CTRL_REG_2);
 
 	/*
-	 * BIT 12: Controls auxda_polarity, which selects the polarity of the
-	 * xcvr:
-	 * 1, Reverses the polarity (If TYPEC, Pulls ups aux_p and pull
-	 * down aux_m)
-	 * 0, Normal polarity (if TYPE_C, pulls up aux_m and pulls down
-	 * aux_p)
+	 * Do some magic undocumented stuff, some of which appears to
+	 * undo the "re-enables Bandgap reference for LDO" above.
 	 */
-	val = 0xa078;
-	if (!tcphy->flip)
-		val |= BIT(12);
-	writel(val, tcphy->base + TX_ANA_CTRL_REG_1);
+	tx_ana_ctrl_reg_1 |=  BIT(15);
+	tx_ana_ctrl_reg_1 &= ~BIT(8);
+	tx_ana_ctrl_reg_1 &= ~BIT(7);
+	tx_ana_ctrl_reg_1 |=  BIT(6);
+	tx_ana_ctrl_reg_1 |=  BIT(5);
+	writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1);
 
 	writel(0, tcphy->base + TX_ANA_CTRL_REG_3);
 	writel(0, tcphy->base + TX_ANA_CTRL_REG_4);
 	writel(0, tcphy->base + TX_ANA_CTRL_REG_5);
 
 	/*
-	 * Controls low_power_swing_en, set the voltage swing of the driver
-	 * to 400mv. The values	below are peak to peak (differential) values.
+	 * Controls low_power_swing_en, don't set the voltage swing of the
+	 * driver to 400mv. The values below are peak to peak (differential)
+	 * values.
 	 */
-	writel(4, tcphy->base + TXDA_COEFF_CALC_CTRL);
+	writel(0, tcphy->base + TXDA_COEFF_CALC_CTRL);
 	writel(0, tcphy->base + TXDA_CYA_AUXDA_CYA);
 
 	/* Controls tx_high_z_tm_en */
@@ -555,6 +577,7 @@
 	reset_control_deassert(tcphy->tcphy_rst);
 
 	property_enable(tcphy, &cfg->typec_conn_dir, tcphy->flip);
+	tcphy_dp_aux_set_flip(tcphy);
 
 	tcphy_cfg_24m(tcphy);
 
@@ -685,8 +708,11 @@
 	if (tcphy->mode == new_mode)
 		goto unlock_ret;
 
-	if (tcphy->mode == MODE_DISCONNECT)
-		tcphy_phy_init(tcphy, new_mode);
+	if (tcphy->mode == MODE_DISCONNECT) {
+		ret = tcphy_phy_init(tcphy, new_mode);
+		if (ret)
+			goto unlock_ret;
+	}
 
 	/* wait TCPHY for pipe ready */
 	for (timeout = 0; timeout < 100; timeout++) {
@@ -760,10 +786,12 @@
 	 */
 	if (new_mode == MODE_DFP_DP && tcphy->mode != MODE_DISCONNECT) {
 		tcphy_phy_deinit(tcphy);
-		tcphy_phy_init(tcphy, new_mode);
+		ret = tcphy_phy_init(tcphy, new_mode);
 	} else if (tcphy->mode == MODE_DISCONNECT) {
-		tcphy_phy_init(tcphy, new_mode);
+		ret = tcphy_phy_init(tcphy, new_mode);
 	}
+	if (ret)
+		goto unlock_ret;
 
 	ret = readx_poll_timeout(readl, tcphy->base + DP_MODE_CTL,
 				 val, val & DP_MODE_A2, 1000,
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 3cbcb25..4307bf0 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -454,6 +454,8 @@
 		char *name;
 
 		name = kasprintf(GFP_KERNEL, "%s-%u", type, index);
+		if (!name)
+			return ERR_PTR(-ENOMEM);
 		np = of_find_node_by_name(np, name);
 		kfree(name);
 	}
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 1778cf4..82cd8b0 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -100,6 +100,7 @@
 	tristate "AMD GPIO pin control"
 	depends on GPIOLIB
 	select GPIOLIB_IRQCHIP
+	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
 	help
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
index 0944310..ff78244 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
@@ -373,16 +373,12 @@
 	unsigned long events;
 	unsigned offset;
 	unsigned gpio;
-	unsigned int type;
 
 	events = bcm2835_gpio_rd(pc, GPEDS0 + bank * 4);
 	events &= mask;
 	events &= pc->enabled_irq_map[bank];
 	for_each_set_bit(offset, &events, 32) {
 		gpio = (32 * bank) + offset;
-		/* FIXME: no clue why the code looks up the type here */
-		type = pc->irq_type[gpio];
-
 		generic_handle_irq(irq_linear_revmap(pc->gpio_chip.irqdomain,
 						     gpio));
 	}
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 04e929f..fadbca9 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1577,6 +1577,7 @@
 	struct gpio_chip *chip = &pctrl->chip;
 	bool need_valid_mask = !dmi_check_system(chv_no_valid_mask);
 	int ret, i, offset;
+	int irq_base;
 
 	*chip = chv_gpio_chip;
 
@@ -1622,7 +1623,18 @@
 	/* Clear all interrupts */
 	chv_writel(0xffff, pctrl->regs + CHV_INTSTAT);
 
-	ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
+	if (!need_valid_mask) {
+		irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0,
+						chip->ngpio, NUMA_NO_NODE);
+		if (irq_base < 0) {
+			dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n");
+			return irq_base;
+		}
+	} else {
+		irq_base = 0;
+	}
+
+	ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, irq_base,
 				   handle_bad_irq, IRQ_TYPE_NONE);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to add IRQ chip\n");
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 3f6b34f..433af32 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -534,8 +534,16 @@
 				continue;
 			irq = irq_find_mapping(gc->irqdomain, irqnr + i);
 			generic_handle_irq(irq);
-			/* Clear interrupt */
+
+			/* Clear interrupt.
+			 * We must read the pin register again, in case the
+			 * value was changed while executing
+			 * generic_handle_irq() above.
+			 */
+			raw_spin_lock_irqsave(&gpio_dev->lock, flags);
+			regval = readl(regs + i);
 			writel(regval, regs + i);
+			raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 			ret = IRQ_HANDLED;
 		}
 	}
diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index 3e40d42..9c950bbf 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -407,10 +407,10 @@
 	ret = mcp_read(mcp, MCP_GPIO, &status);
 	if (ret < 0)
 		status = 0;
-	else
+	else {
+		mcp->cached_gpio = status;
 		status = !!(status & (1 << offset));
-
-	mcp->cached_gpio = status;
+	}
 
 	mutex_unlock(&mcp->lock);
 	return status;
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index 85de30f..56a8195 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -254,10 +254,12 @@
 {
 	struct acpi_device *device = bl_get_data(b);
 
-	if (b->props.power == FB_BLANK_POWERDOWN)
-		call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3);
-	else
-		call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0);
+	if (fext) {
+		if (b->props.power == FB_BLANK_POWERDOWN)
+			call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3);
+		else
+			call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0);
+	}
 
 	return set_lcd_level(device, b->props.brightness);
 }
diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c
index bb792a5..e03fa314 100644
--- a/drivers/platform/x86/intel_pmc_ipc.c
+++ b/drivers/platform/x86/intel_pmc_ipc.c
@@ -33,6 +33,7 @@
 #include <linux/suspend.h>
 #include <linux/acpi.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/spinlock.h>
 
 #include <asm/intel_pmc_ipc.h>
 
@@ -131,6 +132,7 @@
 	/* gcr */
 	void __iomem *gcr_mem_base;
 	bool has_gcr_regs;
+	spinlock_t gcr_lock;
 
 	/* punit */
 	struct platform_device *punit_dev;
@@ -225,17 +227,17 @@
 {
 	int ret;
 
-	mutex_lock(&ipclock);
+	spin_lock(&ipcdev.gcr_lock);
 
 	ret = is_gcr_valid(offset);
 	if (ret < 0) {
-		mutex_unlock(&ipclock);
+		spin_unlock(&ipcdev.gcr_lock);
 		return ret;
 	}
 
 	*data = readl(ipcdev.gcr_mem_base + offset);
 
-	mutex_unlock(&ipclock);
+	spin_unlock(&ipcdev.gcr_lock);
 
 	return 0;
 }
@@ -255,17 +257,17 @@
 {
 	int ret;
 
-	mutex_lock(&ipclock);
+	spin_lock(&ipcdev.gcr_lock);
 
 	ret = is_gcr_valid(offset);
 	if (ret < 0) {
-		mutex_unlock(&ipclock);
+		spin_unlock(&ipcdev.gcr_lock);
 		return ret;
 	}
 
 	writel(data, ipcdev.gcr_mem_base + offset);
 
-	mutex_unlock(&ipclock);
+	spin_unlock(&ipcdev.gcr_lock);
 
 	return 0;
 }
@@ -287,7 +289,7 @@
 	u32 new_val;
 	int ret = 0;
 
-	mutex_lock(&ipclock);
+	spin_lock(&ipcdev.gcr_lock);
 
 	ret = is_gcr_valid(offset);
 	if (ret < 0)
@@ -309,7 +311,7 @@
 	}
 
 gcr_ipc_unlock:
-	mutex_unlock(&ipclock);
+	spin_unlock(&ipcdev.gcr_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(intel_pmc_gcr_update);
@@ -480,52 +482,41 @@
 
 static int ipc_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	resource_size_t pci_resource;
+	struct intel_pmc_ipc_dev *pmc = &ipcdev;
 	int ret;
-	int len;
 
-	ipcdev.dev = &pci_dev_get(pdev)->dev;
-	ipcdev.irq_mode = IPC_TRIGGER_MODE_IRQ;
-
-	ret = pci_enable_device(pdev);
-	if (ret)
-		return ret;
-
-	ret = pci_request_regions(pdev, "intel_pmc_ipc");
-	if (ret)
-		return ret;
-
-	pci_resource = pci_resource_start(pdev, 0);
-	len = pci_resource_len(pdev, 0);
-	if (!pci_resource || !len) {
-		dev_err(&pdev->dev, "Failed to get resource\n");
-		return -ENOMEM;
-	}
-
-	init_completion(&ipcdev.cmd_complete);
-
-	if (request_irq(pdev->irq, ioc, 0, "intel_pmc_ipc", &ipcdev)) {
-		dev_err(&pdev->dev, "Failed to request irq\n");
+	/* Only one PMC is supported */
+	if (pmc->dev)
 		return -EBUSY;
+
+	pmc->irq_mode = IPC_TRIGGER_MODE_IRQ;
+
+	spin_lock_init(&ipcdev.gcr_lock);
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	ret = pcim_iomap_regions(pdev, 1 << 0, pci_name(pdev));
+	if (ret)
+		return ret;
+
+	init_completion(&pmc->cmd_complete);
+
+	pmc->ipc_base = pcim_iomap_table(pdev)[0];
+
+	ret = devm_request_irq(&pdev->dev, pdev->irq, ioc, 0, "intel_pmc_ipc",
+				pmc);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to request irq\n");
+		return ret;
 	}
 
-	ipcdev.ipc_base = ioremap_nocache(pci_resource, len);
-	if (!ipcdev.ipc_base) {
-		dev_err(&pdev->dev, "Failed to ioremap ipc base\n");
-		free_irq(pdev->irq, &ipcdev);
-		ret = -ENOMEM;
-	}
+	pmc->dev = &pdev->dev;
 
-	return ret;
-}
+	pci_set_drvdata(pdev, pmc);
 
-static void ipc_pci_remove(struct pci_dev *pdev)
-{
-	free_irq(pdev->irq, &ipcdev);
-	pci_release_regions(pdev);
-	pci_dev_put(pdev);
-	iounmap(ipcdev.ipc_base);
-	ipcdev.dev = NULL;
+	return 0;
 }
 
 static const struct pci_device_id ipc_pci_ids[] = {
@@ -540,7 +531,6 @@
 	.name = "intel_pmc_ipc",
 	.id_table = ipc_pci_ids,
 	.probe = ipc_pci_probe,
-	.remove = ipc_pci_remove,
 };
 
 static ssize_t intel_pmc_ipc_simple_cmd_store(struct device *dev,
@@ -850,17 +840,12 @@
 		return -ENXIO;
 	}
 	size = PLAT_RESOURCE_IPC_SIZE + PLAT_RESOURCE_GCR_SIZE;
+	res->end = res->start + size - 1;
 
-	if (!request_mem_region(res->start, size, pdev->name)) {
-		dev_err(&pdev->dev, "Failed to request ipc resource\n");
-		return -EBUSY;
-	}
-	addr = ioremap_nocache(res->start, size);
-	if (!addr) {
-		dev_err(&pdev->dev, "I/O memory remapping failed\n");
-		release_mem_region(res->start, size);
-		return -ENOMEM;
-	}
+	addr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
 	ipcdev.ipc_base = addr;
 
 	ipcdev.gcr_mem_base = addr + PLAT_RESOURCE_GCR_OFFSET;
@@ -917,12 +902,12 @@
 
 static int ipc_plat_probe(struct platform_device *pdev)
 {
-	struct resource *res;
 	int ret;
 
 	ipcdev.dev = &pdev->dev;
 	ipcdev.irq_mode = IPC_TRIGGER_MODE_IRQ;
 	init_completion(&ipcdev.cmd_complete);
+	spin_lock_init(&ipcdev.gcr_lock);
 
 	ipcdev.irq = platform_get_irq(pdev, 0);
 	if (ipcdev.irq < 0) {
@@ -939,11 +924,11 @@
 	ret = ipc_create_pmc_devices();
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to create pmc devices\n");
-		goto err_device;
+		return ret;
 	}
 
-	if (request_irq(ipcdev.irq, ioc, IRQF_NO_SUSPEND,
-			"intel_pmc_ipc", &ipcdev)) {
+	if (devm_request_irq(&pdev->dev, ipcdev.irq, ioc, IRQF_NO_SUSPEND,
+			     "intel_pmc_ipc", &ipcdev)) {
 		dev_err(&pdev->dev, "Failed to request irq\n");
 		ret = -EBUSY;
 		goto err_irq;
@@ -960,40 +945,22 @@
 
 	return 0;
 err_sys:
-	free_irq(ipcdev.irq, &ipcdev);
+	devm_free_irq(&pdev->dev, ipcdev.irq, &ipcdev);
 err_irq:
 	platform_device_unregister(ipcdev.tco_dev);
 	platform_device_unregister(ipcdev.punit_dev);
 	platform_device_unregister(ipcdev.telemetry_dev);
-err_device:
-	iounmap(ipcdev.ipc_base);
-	res = platform_get_resource(pdev, IORESOURCE_MEM,
-				    PLAT_RESOURCE_IPC_INDEX);
-	if (res) {
-		release_mem_region(res->start,
-				   PLAT_RESOURCE_IPC_SIZE +
-				   PLAT_RESOURCE_GCR_SIZE);
-	}
+
 	return ret;
 }
 
 static int ipc_plat_remove(struct platform_device *pdev)
 {
-	struct resource *res;
-
 	sysfs_remove_group(&pdev->dev.kobj, &intel_ipc_group);
-	free_irq(ipcdev.irq, &ipcdev);
+	devm_free_irq(&pdev->dev, ipcdev.irq, &ipcdev);
 	platform_device_unregister(ipcdev.tco_dev);
 	platform_device_unregister(ipcdev.punit_dev);
 	platform_device_unregister(ipcdev.telemetry_dev);
-	iounmap(ipcdev.ipc_base);
-	res = platform_get_resource(pdev, IORESOURCE_MEM,
-				    PLAT_RESOURCE_IPC_INDEX);
-	if (res) {
-		release_mem_region(res->start,
-				   PLAT_RESOURCE_IPC_SIZE +
-				   PLAT_RESOURCE_GCR_SIZE);
-	}
 	ipcdev.dev = NULL;
 	return 0;
 }
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index 315a4be..9a68914 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -51,6 +51,8 @@
 MODULE_PARM_DESC(mbox_sel,
 		 "RIO Messaging MBOX Selection Mask (default: 0x0f = all)");
 
+static DEFINE_SPINLOCK(tsi721_maint_lock);
+
 static void tsi721_omsg_handler(struct tsi721_device *priv, int ch);
 static void tsi721_imsg_handler(struct tsi721_device *priv, int ch);
 
@@ -124,12 +126,15 @@
 	void __iomem *regs = priv->regs + TSI721_DMAC_BASE(priv->mdma.ch_id);
 	struct tsi721_dma_desc *bd_ptr;
 	u32 rd_count, swr_ptr, ch_stat;
+	unsigned long flags;
 	int i, err = 0;
 	u32 op = do_wr ? MAINT_WR : MAINT_RD;
 
 	if (offset > (RIO_MAINT_SPACE_SZ - len) || (len != sizeof(u32)))
 		return -EINVAL;
 
+	spin_lock_irqsave(&tsi721_maint_lock, flags);
+
 	bd_ptr = priv->mdma.bd_base;
 
 	rd_count = ioread32(regs + TSI721_DMAC_DRDCNT);
@@ -197,7 +202,9 @@
 	 */
 	swr_ptr = ioread32(regs + TSI721_DMAC_DSWP);
 	iowrite32(swr_ptr, regs + TSI721_DMAC_DSRP);
+
 err_out:
+	spin_unlock_irqrestore(&tsi721_maint_lock, flags);
 
 	return err;
 }
diff --git a/drivers/rapidio/rio-access.c b/drivers/rapidio/rio-access.c
index a3824ba..3ee9af8 100644
--- a/drivers/rapidio/rio-access.c
+++ b/drivers/rapidio/rio-access.c
@@ -14,16 +14,8 @@
 #include <linux/module.h>
 
 /*
- * These interrupt-safe spinlocks protect all accesses to RIO
- * configuration space and doorbell access.
- */
-static DEFINE_SPINLOCK(rio_config_lock);
-static DEFINE_SPINLOCK(rio_doorbell_lock);
-
-/*
  *  Wrappers for all RIO configuration access functions.  They just check
- *  alignment, do locking and call the low-level functions pointed to
- *  by rio_mport->ops.
+ *  alignment and call the low-level functions pointed to by rio_mport->ops.
  */
 
 #define RIO_8_BAD 0
@@ -44,13 +36,10 @@
 	(struct rio_mport *mport, u32 offset, type *value)		\
 {									\
 	int res;							\
-	unsigned long flags;						\
 	u32 data = 0;							\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
-	spin_lock_irqsave(&rio_config_lock, flags);			\
 	res = mport->ops->lcread(mport, mport->id, offset, len, &data);	\
 	*value = (type)data;						\
-	spin_unlock_irqrestore(&rio_config_lock, flags);		\
 	return res;							\
 }
 
@@ -67,13 +56,8 @@
 int __rio_local_write_config_##size \
 	(struct rio_mport *mport, u32 offset, type value)		\
 {									\
-	int res;							\
-	unsigned long flags;						\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
-	spin_lock_irqsave(&rio_config_lock, flags);			\
-	res = mport->ops->lcwrite(mport, mport->id, offset, len, value);\
-	spin_unlock_irqrestore(&rio_config_lock, flags);		\
-	return res;							\
+	return mport->ops->lcwrite(mport, mport->id, offset, len, value);\
 }
 
 RIO_LOP_READ(8, u8, 1)
@@ -104,13 +88,10 @@
 	(struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type *value)	\
 {									\
 	int res;							\
-	unsigned long flags;						\
 	u32 data = 0;							\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
-	spin_lock_irqsave(&rio_config_lock, flags);			\
 	res = mport->ops->cread(mport, mport->id, destid, hopcount, offset, len, &data); \
 	*value = (type)data;						\
-	spin_unlock_irqrestore(&rio_config_lock, flags);		\
 	return res;							\
 }
 
@@ -127,13 +108,9 @@
 int rio_mport_write_config_##size \
 	(struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type value)	\
 {									\
-	int res;							\
-	unsigned long flags;						\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
-	spin_lock_irqsave(&rio_config_lock, flags);			\
-	res = mport->ops->cwrite(mport, mport->id, destid, hopcount, offset, len, value); \
-	spin_unlock_irqrestore(&rio_config_lock, flags);		\
-	return res;							\
+	return mport->ops->cwrite(mport, mport->id, destid, hopcount,	\
+			offset, len, value);				\
 }
 
 RIO_OP_READ(8, u8, 1)
@@ -162,14 +139,7 @@
  */
 int rio_mport_send_doorbell(struct rio_mport *mport, u16 destid, u16 data)
 {
-	int res;
-	unsigned long flags;
-
-	spin_lock_irqsave(&rio_doorbell_lock, flags);
-	res = mport->ops->dsend(mport, mport->id, destid, data);
-	spin_unlock_irqrestore(&rio_doorbell_lock, flags);
-
-	return res;
+	return mport->ops->dsend(mport, mport->id, destid, data);
 }
 
 EXPORT_SYMBOL_GPL(rio_mport_send_doorbell);
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index d0e5d6e..e2c1988 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -523,7 +523,7 @@
 	if (*str == '=')
 		str++;
 
-	if (!strncmp(str, "cec_disable", 7))
+	if (!strcmp(str, "cec_disable"))
 		ce_arr.disabled = 1;
 	else
 		return 0;
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index f18b36d..376a99b 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -590,7 +590,7 @@
 		case AXP803_DCDC3:
 			return !!(reg & BIT(6));
 		case AXP803_DCDC6:
-			return !!(reg & BIT(7));
+			return !!(reg & BIT(5));
 		}
 		break;
 
diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c
index ef2be56..790a4a7 100644
--- a/drivers/regulator/rn5t618-regulator.c
+++ b/drivers/regulator/rn5t618-regulator.c
@@ -29,7 +29,7 @@
 };
 
 #define REG(rid, ereg, emask, vreg, vmask, min, max, step)		\
-	[RN5T618_##rid] = {						\
+	{								\
 		.name		= #rid,					\
 		.of_match	= of_match_ptr(#rid),			\
 		.regulators_node = of_match_ptr("regulators"),		\
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index df63e44..bf04479 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -109,6 +109,7 @@
 	depends on OF && ARCH_QCOM
 	depends on QCOM_SMEM
 	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
+	depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n
 	select MFD_SYSCON
 	select QCOM_RPROC_COMMON
 	select QCOM_SCM
@@ -120,6 +121,7 @@
 	tristate "Qualcomm WCNSS Peripheral Image Loader"
 	depends on OF && ARCH_QCOM
 	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
+	depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n
 	depends on QCOM_SMEM
 	select QCOM_MDT_LOADER
 	select QCOM_RPROC_COMMON
diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index 612d914..633268e 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -264,15 +264,14 @@
 		if (!(att->flags & ATT_OWN))
 			continue;
 
-		if (b > IMX7D_RPROC_MEM_MAX)
+		if (b >= IMX7D_RPROC_MEM_MAX)
 			break;
 
 		priv->mem[b].cpu_addr = devm_ioremap(&pdev->dev,
 						     att->sa, att->size);
-		if (IS_ERR(priv->mem[b].cpu_addr)) {
+		if (!priv->mem[b].cpu_addr) {
 			dev_err(dev, "devm_ioremap_resource failed\n");
-			err = PTR_ERR(priv->mem[b].cpu_addr);
-			return err;
+			return -ENOMEM;
 		}
 		priv->mem[b].sys_addr = att->sa;
 		priv->mem[b].size = att->size;
@@ -296,7 +295,7 @@
 			return err;
 		}
 
-		if (b > IMX7D_RPROC_MEM_MAX)
+		if (b >= IMX7D_RPROC_MEM_MAX)
 			break;
 
 		priv->mem[b].cpu_addr = devm_ioremap_resource(&pdev->dev, &res);
diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig
index e0c3932..e2baecb 100644
--- a/drivers/reset/Kconfig
+++ b/drivers/reset/Kconfig
@@ -34,11 +34,12 @@
 	help
 	  This enables the reset controller driver for Marvell Berlin SoCs.
 
-config RESET_HSDK_V1
-	bool "HSDK v1 Reset Driver"
-	default n
+config RESET_HSDK
+	bool "Synopsys HSDK Reset Driver"
+	depends on HAS_IOMEM
+	depends on ARC_SOC_HSDK || COMPILE_TEST
 	help
-	  This enables the reset controller driver for HSDK v1.
+	  This enables the reset controller driver for HSDK board.
 
 config RESET_IMX7
 	bool "i.MX7 Reset Driver" if COMPILE_TEST
diff --git a/drivers/reset/Makefile b/drivers/reset/Makefile
index d368367..af1c15c 100644
--- a/drivers/reset/Makefile
+++ b/drivers/reset/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_RESET_A10SR) += reset-a10sr.o
 obj-$(CONFIG_RESET_ATH79) += reset-ath79.o
 obj-$(CONFIG_RESET_BERLIN) += reset-berlin.o
-obj-$(CONFIG_RESET_HSDK_V1) += reset-hsdk-v1.o
+obj-$(CONFIG_RESET_HSDK) += reset-hsdk.o
 obj-$(CONFIG_RESET_IMX7) += reset-imx7.o
 obj-$(CONFIG_RESET_LANTIQ) += reset-lantiq.o
 obj-$(CONFIG_RESET_LPC18XX) += reset-lpc18xx.o
diff --git a/drivers/reset/reset-hsdk-v1.c b/drivers/reset/reset-hsdk.c
similarity index 72%
rename from drivers/reset/reset-hsdk-v1.c
rename to drivers/reset/reset-hsdk.c
index bca13e4..8bce391 100644
--- a/drivers/reset/reset-hsdk-v1.c
+++ b/drivers/reset/reset-hsdk.c
@@ -1,7 +1,7 @@
 /*
  * Copyright (C) 2017 Synopsys.
  *
- * Synopsys HSDKv1 SDP reset driver.
+ * Synopsys HSDK Development platform reset driver.
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -18,9 +18,9 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#define to_hsdkv1_rst(p)	container_of((p), struct hsdkv1_rst, rcdev)
+#define to_hsdk_rst(p)	container_of((p), struct hsdk_rst, rcdev)
 
-struct hsdkv1_rst {
+struct hsdk_rst {
 	void __iomem			*regs_ctl;
 	void __iomem			*regs_rst;
 	spinlock_t			lock;
@@ -49,12 +49,12 @@
 #define CGU_IP_SW_RESET_RESET		BIT(0)
 #define SW_RESET_TIMEOUT		10000
 
-static void hsdkv1_reset_config(struct hsdkv1_rst *rst, unsigned long id)
+static void hsdk_reset_config(struct hsdk_rst *rst, unsigned long id)
 {
 	writel(rst_map[id], rst->regs_ctl + CGU_SYS_RST_CTRL);
 }
 
-static int hsdkv1_reset_do(struct hsdkv1_rst *rst)
+static int hsdk_reset_do(struct hsdk_rst *rst)
 {
 	u32 reg;
 
@@ -69,28 +69,28 @@
 		!(reg & CGU_IP_SW_RESET_RESET), 5, SW_RESET_TIMEOUT);
 }
 
-static int hsdkv1_reset_reset(struct reset_controller_dev *rcdev,
+static int hsdk_reset_reset(struct reset_controller_dev *rcdev,
 			      unsigned long id)
 {
-	struct hsdkv1_rst *rst = to_hsdkv1_rst(rcdev);
+	struct hsdk_rst *rst = to_hsdk_rst(rcdev);
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&rst->lock, flags);
-	hsdkv1_reset_config(rst, id);
-	ret = hsdkv1_reset_do(rst);
+	hsdk_reset_config(rst, id);
+	ret = hsdk_reset_do(rst);
 	spin_unlock_irqrestore(&rst->lock, flags);
 
 	return ret;
 }
 
-static const struct reset_control_ops hsdkv1_reset_ops = {
-	.reset	= hsdkv1_reset_reset,
+static const struct reset_control_ops hsdk_reset_ops = {
+	.reset	= hsdk_reset_reset,
 };
 
-static int hsdkv1_reset_probe(struct platform_device *pdev)
+static int hsdk_reset_probe(struct platform_device *pdev)
 {
-	struct hsdkv1_rst *rst;
+	struct hsdk_rst *rst;
 	struct resource *mem;
 
 	rst = devm_kzalloc(&pdev->dev, sizeof(*rst), GFP_KERNEL);
@@ -110,7 +110,7 @@
 	spin_lock_init(&rst->lock);
 
 	rst->rcdev.owner = THIS_MODULE;
-	rst->rcdev.ops = &hsdkv1_reset_ops;
+	rst->rcdev.ops = &hsdk_reset_ops;
 	rst->rcdev.of_node = pdev->dev.of_node;
 	rst->rcdev.nr_resets = HSDK_MAX_RESETS;
 	rst->rcdev.of_reset_n_cells = 1;
@@ -118,20 +118,20 @@
 	return reset_controller_register(&rst->rcdev);
 }
 
-static const struct of_device_id hsdkv1_reset_dt_match[] = {
-	{ .compatible = "snps,hsdk-v1.0-reset" },
+static const struct of_device_id hsdk_reset_dt_match[] = {
+	{ .compatible = "snps,hsdk-reset" },
 	{ },
 };
 
-static struct platform_driver hsdkv1_reset_driver = {
-	.probe	= hsdkv1_reset_probe,
+static struct platform_driver hsdk_reset_driver = {
+	.probe	= hsdk_reset_probe,
 	.driver	= {
-		.name = "hsdk-v1.0-reset",
-		.of_match_table = hsdkv1_reset_dt_match,
+		.name = "hsdk-reset",
+		.of_match_table = hsdk_reset_dt_match,
 	},
 };
-builtin_platform_driver(hsdkv1_reset_driver);
+builtin_platform_driver(hsdk_reset_driver);
 
 MODULE_AUTHOR("Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>");
-MODULE_DESCRIPTION("Synopsys HSDKv1 SDP reset driver");
+MODULE_DESCRIPTION("Synopsys HSDK SDP reset driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c
index c60904f..3907bbc 100644
--- a/drivers/reset/reset-socfpga.c
+++ b/drivers/reset/reset-socfpga.c
@@ -40,8 +40,9 @@
 	struct socfpga_reset_data *data = container_of(rcdev,
 						     struct socfpga_reset_data,
 						     rcdev);
-	int bank = id / BITS_PER_LONG;
-	int offset = id % BITS_PER_LONG;
+	int reg_width = sizeof(u32);
+	int bank = id / (reg_width * BITS_PER_BYTE);
+	int offset = id % (reg_width * BITS_PER_BYTE);
 	unsigned long flags;
 	u32 reg;
 
@@ -61,8 +62,9 @@
 						     struct socfpga_reset_data,
 						     rcdev);
 
-	int bank = id / BITS_PER_LONG;
-	int offset = id % BITS_PER_LONG;
+	int reg_width = sizeof(u32);
+	int bank = id / (reg_width * BITS_PER_BYTE);
+	int offset = id % (reg_width * BITS_PER_BYTE);
 	unsigned long flags;
 	u32 reg;
 
@@ -81,8 +83,9 @@
 {
 	struct socfpga_reset_data *data = container_of(rcdev,
 						struct socfpga_reset_data, rcdev);
-	int bank = id / BITS_PER_LONG;
-	int offset = id % BITS_PER_LONG;
+	int reg_width = sizeof(u32);
+	int bank = id / (reg_width * BITS_PER_BYTE);
+	int offset = id % (reg_width * BITS_PER_BYTE);
 	u32 reg;
 
 	reg = readl(data->membase + (bank * BANK_INCREMENT));
@@ -132,7 +135,7 @@
 	spin_lock_init(&data->lock);
 
 	data->rcdev.owner = THIS_MODULE;
-	data->rcdev.nr_resets = NR_BANKS * BITS_PER_LONG;
+	data->rcdev.nr_resets = NR_BANKS * (sizeof(u32) * BITS_PER_BYTE);
 	data->rcdev.ops = &socfpga_reset_ops;
 	data->rcdev.of_node = pdev->dev.of_node;
 
diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c
index 5a5e927..5dcc9bf 100644
--- a/drivers/rpmsg/qcom_glink_native.c
+++ b/drivers/rpmsg/qcom_glink_native.c
@@ -635,19 +635,18 @@
 	unsigned long flags;
 
 	intent = kzalloc(sizeof(*intent), GFP_KERNEL);
-
 	if (!intent)
 		return NULL;
 
 	intent->data = kzalloc(size, GFP_KERNEL);
 	if (!intent->data)
-		return NULL;
+		goto free_intent;
 
 	spin_lock_irqsave(&channel->intent_lock, flags);
 	ret = idr_alloc_cyclic(&channel->liids, intent, 1, -1, GFP_ATOMIC);
 	if (ret < 0) {
 		spin_unlock_irqrestore(&channel->intent_lock, flags);
-		return NULL;
+		goto free_data;
 	}
 	spin_unlock_irqrestore(&channel->intent_lock, flags);
 
@@ -656,6 +655,12 @@
 	intent->reuse = reuseable;
 
 	return intent;
+
+free_data:
+	kfree(intent->data);
+free_intent:
+	kfree(intent);
+	return NULL;
 }
 
 static void qcom_glink_handle_rx_done(struct qcom_glink *glink,
@@ -1197,7 +1202,7 @@
 
 	ret = qcom_glink_tx(glink, &cmd, sizeof(cmd), NULL, 0, true);
 	if (ret)
-		return ret;
+		goto unlock;
 
 	ret = wait_for_completion_timeout(&channel->intent_req_comp, 10 * HZ);
 	if (!ret) {
@@ -1207,6 +1212,7 @@
 		ret = channel->intent_req_result ? 0 : -ECANCELED;
 	}
 
+unlock:
 	mutex_unlock(&channel->intent_req_lock);
 	return ret;
 }
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index ea19b4f..29f35e2 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -1644,7 +1644,9 @@
 	dasd_schedule_device_bh(device);
 	if (device->block) {
 		dasd_schedule_block_bh(device->block);
-		blk_mq_run_hw_queues(device->block->request_queue, true);
+		if (device->block->request_queue)
+			blk_mq_run_hw_queues(device->block->request_queue,
+					     true);
 	}
 }
 EXPORT_SYMBOL_GPL(dasd_generic_handle_state_change);
@@ -3759,7 +3761,9 @@
 	dasd_schedule_device_bh(device);
 	if (device->block) {
 		dasd_schedule_block_bh(device->block);
-		blk_mq_run_hw_queues(device->block->request_queue, true);
+		if (device->block->request_queue)
+			blk_mq_run_hw_queues(device->block->request_queue,
+					     true);
 		}
 
 	if (!device->stopped)
@@ -4025,7 +4029,9 @@
 
 	if (device->block) {
 		dasd_schedule_block_bh(device->block);
-		blk_mq_run_hw_queues(device->block->request_queue, true);
+		if (device->block->request_queue)
+			blk_mq_run_hw_queues(device->block->request_queue,
+					     true);
 	}
 
 	clear_bit(DASD_FLAG_SUSPENDED, &device->flags);
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index 2e7fd96..eb51893 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -249,7 +249,7 @@
 static void scm_request_finish(struct scm_request *scmrq)
 {
 	struct scm_blk_dev *bdev = scmrq->bdev;
-	int *error;
+	blk_status_t *error;
 	int i;
 
 	for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) {
@@ -415,7 +415,7 @@
 
 static void scm_blk_request_done(struct request *req)
 {
-	int *error = blk_mq_rq_to_pdu(req);
+	blk_status_t *error = blk_mq_rq_to_pdu(req);
 
 	blk_mq_end_request(req, *error);
 }
@@ -450,7 +450,7 @@
 	atomic_set(&bdev->queued_reqs, 0);
 
 	bdev->tag_set.ops = &scm_mq_ops;
-	bdev->tag_set.cmd_size = sizeof(int);
+	bdev->tag_set.cmd_size = sizeof(blk_status_t);
 	bdev->tag_set.nr_hw_queues = nr_requests;
 	bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
 	bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 489b583..e5c32f4 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1225,10 +1225,16 @@
 static int recovery_check(struct device *dev, void *data)
 {
 	struct ccw_device *cdev = to_ccwdev(dev);
+	struct subchannel *sch;
 	int *redo = data;
 
 	spin_lock_irq(cdev->ccwlock);
 	switch (cdev->private->state) {
+	case DEV_STATE_ONLINE:
+		sch = to_subchannel(cdev->dev.parent);
+		if ((sch->schib.pmcw.pam & sch->opm) == sch->vpm)
+			break;
+		/* fall through */
 	case DEV_STATE_DISCONNECTED:
 		CIO_MSG_EVENT(3, "recovery: trigger 0.%x.%04x\n",
 			      cdev->private->dev_id.ssid,
@@ -1260,7 +1266,7 @@
 		}
 		spin_unlock_irq(&recovery_lock);
 	} else
-		CIO_MSG_EVENT(4, "recovery: end\n");
+		CIO_MSG_EVENT(3, "recovery: end\n");
 }
 
 static DECLARE_WORK(recovery_work, recovery_work_func);
@@ -1274,11 +1280,11 @@
 	schedule_work(&recovery_work);
 }
 
-static void ccw_device_schedule_recovery(void)
+void ccw_device_schedule_recovery(void)
 {
 	unsigned long flags;
 
-	CIO_MSG_EVENT(4, "recovery: schedule\n");
+	CIO_MSG_EVENT(3, "recovery: schedule\n");
 	spin_lock_irqsave(&recovery_lock, flags);
 	if (!timer_pending(&recovery_timer) || (recovery_phase != 0)) {
 		recovery_phase = 0;
diff --git a/drivers/s390/cio/device.h b/drivers/s390/cio/device.h
index ec497af..69cb70f 100644
--- a/drivers/s390/cio/device.h
+++ b/drivers/s390/cio/device.h
@@ -134,6 +134,7 @@
 void ccw_device_set_notoper(struct ccw_device *cdev);
 
 void ccw_device_set_timeout(struct ccw_device *, int);
+void ccw_device_schedule_recovery(void);
 
 /* Channel measurement facility related */
 void retry_set_schib(struct ccw_device *cdev);
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 12016e3..f98ea67 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -476,6 +476,17 @@
 	}
 }
 
+static void ccw_device_handle_broken_paths(struct ccw_device *cdev)
+{
+	struct subchannel *sch = to_subchannel(cdev->dev.parent);
+	u8 broken_paths = (sch->schib.pmcw.pam & sch->opm) ^ sch->vpm;
+
+	if (broken_paths && (cdev->private->path_broken_mask != broken_paths))
+		ccw_device_schedule_recovery();
+
+	cdev->private->path_broken_mask = broken_paths;
+}
+
 void ccw_device_verify_done(struct ccw_device *cdev, int err)
 {
 	struct subchannel *sch;
@@ -508,6 +519,7 @@
 			memset(&cdev->private->irb, 0, sizeof(struct irb));
 		}
 		ccw_device_report_path_events(cdev);
+		ccw_device_handle_broken_paths(cdev);
 		break;
 	case -ETIME:
 	case -EUSERS:
diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h
index 220f491..9a1b56b 100644
--- a/drivers/s390/cio/io_sch.h
+++ b/drivers/s390/cio/io_sch.h
@@ -131,6 +131,8 @@
 				   not operable */
 	u8 path_gone_mask;	/* mask of paths, that became unavailable */
 	u8 path_new_mask;	/* mask of paths, that became available */
+	u8 path_broken_mask;	/* mask of paths, which were found to be
+				   unusable */
 	struct {
 		unsigned int fast:1;	/* post with "channel end" */
 		unsigned int repall:1;	/* report every interrupt status */
diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c
index 82ac331..8475215 100644
--- a/drivers/s390/scsi/zfcp_aux.c
+++ b/drivers/s390/scsi/zfcp_aux.c
@@ -357,6 +357,8 @@
 
 	adapter->next_port_scan = jiffies;
 
+	adapter->erp_action.adapter = adapter;
+
 	if (zfcp_qdio_setup(adapter))
 		goto failed;
 
@@ -513,6 +515,9 @@
 	port->dev.groups = zfcp_port_attr_groups;
 	port->dev.release = zfcp_port_release;
 
+	port->erp_action.adapter = adapter;
+	port->erp_action.port = port;
+
 	if (dev_set_name(&port->dev, "0x%016llx", (unsigned long long)wwpn)) {
 		kfree(port);
 		goto err_out;
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index 37408f5..ec2532e 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -193,9 +193,8 @@
 		atomic_or(ZFCP_STATUS_COMMON_ERP_INUSE,
 				&zfcp_sdev->status);
 		erp_action = &zfcp_sdev->erp_action;
-		memset(erp_action, 0, sizeof(struct zfcp_erp_action));
-		erp_action->port = port;
-		erp_action->sdev = sdev;
+		WARN_ON_ONCE(erp_action->port != port);
+		WARN_ON_ONCE(erp_action->sdev != sdev);
 		if (!(atomic_read(&zfcp_sdev->status) &
 		      ZFCP_STATUS_COMMON_RUNNING))
 			act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY;
@@ -208,8 +207,8 @@
 		zfcp_erp_action_dismiss_port(port);
 		atomic_or(ZFCP_STATUS_COMMON_ERP_INUSE, &port->status);
 		erp_action = &port->erp_action;
-		memset(erp_action, 0, sizeof(struct zfcp_erp_action));
-		erp_action->port = port;
+		WARN_ON_ONCE(erp_action->port != port);
+		WARN_ON_ONCE(erp_action->sdev != NULL);
 		if (!(atomic_read(&port->status) & ZFCP_STATUS_COMMON_RUNNING))
 			act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY;
 		break;
@@ -219,7 +218,8 @@
 		zfcp_erp_action_dismiss_adapter(adapter);
 		atomic_or(ZFCP_STATUS_COMMON_ERP_INUSE, &adapter->status);
 		erp_action = &adapter->erp_action;
-		memset(erp_action, 0, sizeof(struct zfcp_erp_action));
+		WARN_ON_ONCE(erp_action->port != NULL);
+		WARN_ON_ONCE(erp_action->sdev != NULL);
 		if (!(atomic_read(&adapter->status) &
 		      ZFCP_STATUS_COMMON_RUNNING))
 			act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY;
@@ -229,7 +229,11 @@
 		return NULL;
 	}
 
-	erp_action->adapter = adapter;
+	WARN_ON_ONCE(erp_action->adapter != adapter);
+	memset(&erp_action->list, 0, sizeof(erp_action->list));
+	memset(&erp_action->timer, 0, sizeof(erp_action->timer));
+	erp_action->step = ZFCP_ERP_STEP_UNINITIALIZED;
+	erp_action->fsf_req_id = 0;
 	erp_action->action = need;
 	erp_action->status = act_status;
 
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index ec3ddd1..6cf8732 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -115,10 +115,15 @@
 	struct zfcp_unit *unit;
 	int npiv = adapter->connection_features & FSF_FEATURE_NPIV_MODE;
 
+	zfcp_sdev->erp_action.adapter = adapter;
+	zfcp_sdev->erp_action.sdev = sdev;
+
 	port = zfcp_get_port_by_wwpn(adapter, rport->port_name);
 	if (!port)
 		return -ENXIO;
 
+	zfcp_sdev->erp_action.port = port;
+
 	unit = zfcp_unit_find(port, zfcp_scsi_dev_lun(sdev));
 	if (unit)
 		put_device(&unit->dev);
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index a64285a..af3e4d3 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -699,13 +699,13 @@
 	int status;
 
 	dresp = (struct aac_mount *) fib_data(fibptr);
-	if (!(fibptr->dev->supplement_adapter_info.supported_options2 &
-	    AAC_OPTION_VARIABLE_BLOCK_SIZE))
+	if (!aac_supports_2T(fibptr->dev)) {
 		dresp->mnt[0].capacityhigh = 0;
-	if ((le32_to_cpu(dresp->status) != ST_OK) ||
-	    (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) {
-		_aac_probe_container2(context, fibptr);
-		return;
+		if ((le32_to_cpu(dresp->status) == ST_OK) &&
+			(le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) {
+			_aac_probe_container2(context, fibptr);
+			return;
+		}
 	}
 	scsicmd = (struct scsi_cmnd *) context;
 
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 92fabf2..403a639 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -2701,6 +2701,11 @@
 	return 0;
 }
 
+static inline int aac_supports_2T(struct aac_dev *dev)
+{
+	return (dev->adapter_info.options & AAC_OPT_NEW_COMM_64);
+}
+
 char * get_container_type(unsigned type);
 extern int numacb;
 extern char aac_driver_version[];
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 97d269f..1bc623a 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -302,9 +302,11 @@
 		return -ENOMEM;
 	aac_fib_init(fibctx);
 
-	mutex_lock(&dev->ioctl_mutex);
-	dev->adapter_shutdown = 1;
-	mutex_unlock(&dev->ioctl_mutex);
+	if (!dev->adapter_shutdown) {
+		mutex_lock(&dev->ioctl_mutex);
+		dev->adapter_shutdown = 1;
+		mutex_unlock(&dev->ioctl_mutex);
+	}
 
 	cmd = (struct aac_close *) fib_data(fibctx);
 	cmd->command = cpu_to_le32(VM_CloseAll);
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 87cc4a9..c9252b1 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -906,12 +906,14 @@
 
 	bus = aac_logical_to_phys(scmd_channel(cmd));
 	cid = scmd_id(cmd);
-	info = &aac->hba_map[bus][cid];
-	if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS ||
-	    info->devtype != AAC_DEVTYPE_NATIVE_RAW)
+
+	if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS)
 		return FAILED;
 
-	if (info->reset_state > 0)
+	info = &aac->hba_map[bus][cid];
+
+	if (info->devtype != AAC_DEVTYPE_NATIVE_RAW &&
+	    info->reset_state > 0)
 		return FAILED;
 
 	pr_err("%s: Host adapter reset request. SCSI hang ?\n",
@@ -962,12 +964,14 @@
 
 	bus = aac_logical_to_phys(scmd_channel(cmd));
 	cid = scmd_id(cmd);
-	info = &aac->hba_map[bus][cid];
-	if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS ||
-	    info->devtype != AAC_DEVTYPE_NATIVE_RAW)
+
+	if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS)
 		return FAILED;
 
-	if (info->reset_state > 0)
+	info = &aac->hba_map[bus][cid];
+
+	if (info->devtype != AAC_DEVTYPE_NATIVE_RAW &&
+	    info->reset_state > 0)
 		return FAILED;
 
 	pr_err("%s: Host adapter reset request. SCSI hang ?\n",
@@ -1547,8 +1551,9 @@
 {
 	int i;
 
+	mutex_lock(&aac->ioctl_mutex);
 	aac->adapter_shutdown = 1;
-	aac_send_shutdown(aac);
+	mutex_unlock(&aac->ioctl_mutex);
 
 	if (aac->aif_thread) {
 		int i;
@@ -1561,7 +1566,11 @@
 		}
 		kthread_stop(aac->thread);
 	}
+
+	aac_send_shutdown(aac);
+
 	aac_adapter_disable_int(aac);
+
 	if (aac_is_src(aac)) {
 		if (aac->max_msix > 1) {
 			for (i = 0; i < aac->max_msix; i++) {
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 48c2b2b..0c9361c 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -740,6 +740,8 @@
 	aac_set_intx_mode(dev);
 
 	src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK);
+
+	msleep(5000);
 }
 
 static void aac_send_hardware_soft_reset(struct aac_dev *dev)
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index 690816f..421fe86 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -2725,9 +2725,9 @@
  * Params   : SCpnt  - command causing reset
  * Returns  : one of SCSI_RESET_ macros
  */
-int acornscsi_host_reset(struct Scsi_Host *shpnt)
+int acornscsi_host_reset(struct scsi_cmnd *SCpnt)
 {
-	AS_Host *host = (AS_Host *)shpnt->hostdata;
+	AS_Host *host = (AS_Host *)SCpnt->device->host->hostdata;
 	struct scsi_cmnd *SCptr;
     
     host->stats.resets += 1;
@@ -2741,7 +2741,7 @@
 
 	printk(KERN_WARNING "acornscsi_reset: ");
 	print_sbic_status(asr, ssr, host->scsi.phase);
-	for (devidx = 0; devidx < 9; devidx ++) {
+	for (devidx = 0; devidx < 9; devidx++)
 	    acornscsi_dumplog(host, devidx);
     }
 #endif
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 9abe810..4ed3d26 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -4091,7 +4091,7 @@
 	memset(id_ctlr, 0, sizeof(*id_ctlr));
 	rc = hpsa_bmic_id_controller(h, id_ctlr, sizeof(*id_ctlr));
 	if (!rc)
-		if (id_ctlr->configured_logical_drive_count < 256)
+		if (id_ctlr->configured_logical_drive_count < 255)
 			*nlocals = id_ctlr->configured_logical_drive_count;
 		else
 			*nlocals = le16_to_cpu(
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 785fb42..2799a6b 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -3767,7 +3767,7 @@
 	 */
 	if ((vscsi->flags & (CLIENT_FAILED | RESPONSE_Q_DOWN))) {
 		pr_err("write_pending failed since: %d\n", vscsi->flags);
-		return 0;
+		return -EIO;
 	}
 
 	rc = srp_transfer_data(cmd, &vio_iu(iue)->srp.cmd, ibmvscsis_rdma,
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 5203258..31d31aa 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -383,11 +383,11 @@
 				fc_rport_enter_flogi(rdata);
 				mutex_unlock(&rdata->rp_mutex);
 			} else {
+				mutex_unlock(&rdata->rp_mutex);
 				FC_RPORT_DBG(rdata, "work delete\n");
 				mutex_lock(&lport->disc.disc_mutex);
 				list_del_rcu(&rdata->peers);
 				mutex_unlock(&lport->disc.disc_mutex);
-				mutex_unlock(&rdata->rp_mutex);
 				kref_put(&rdata->kref, fc_rport_destroy);
 			}
 		} else {
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index bd4605a..f8dc160 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1728,7 +1728,7 @@
 
 	if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) {
 		reason = FAILURE_SESSION_IN_RECOVERY;
-		sc->result = DID_REQUEUE;
+		sc->result = DID_REQUEUE << 16;
 		goto fault;
 	}
 
@@ -2851,9 +2851,6 @@
 /**
  * iscsi_session_teardown - destroy session, host, and cls_session
  * @cls_session: iscsi session
- *
- * The driver must have called iscsi_remove_session before
- * calling this.
  */
 void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 {
@@ -2863,6 +2860,8 @@
 
 	iscsi_pool_free(&session->cmdpool);
 
+	iscsi_remove_session(cls_session);
+
 	kfree(session->password);
 	kfree(session->password_in);
 	kfree(session->username);
@@ -2877,7 +2876,8 @@
 	kfree(session->portal_type);
 	kfree(session->discovery_parent_type);
 
-	iscsi_destroy_session(cls_session);
+	iscsi_free_session(cls_session);
+
 	iscsi_host_dec_session_cnt(shost);
 	module_put(owner);
 }
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 7e7ae78..100bc4c 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -6131,6 +6131,7 @@
 				"Extents and RPI headers enabled.\n");
 		}
 		mempool_free(mboxq, phba->mbox_mem_pool);
+		rc = -EIO;
 		goto out_free_bsmbx;
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 79ba3ce..23bdb1c 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -884,7 +884,7 @@
 					 wcqe->total_data_placed);
 			nCmd->transferred_length = 0;
 			nCmd->rcv_rsplen = 0;
-			nCmd->status = NVME_SC_FC_TRANSPORT_ERROR;
+			nCmd->status = NVME_SC_INTERNAL;
 		}
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 1f59e7a..6b33a1f 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -180,7 +180,7 @@
 		goto rel;
 
 	if (unlikely(res == QLA_FUNCTION_FAILED))
-		fd->status = NVME_SC_FC_TRANSPORT_ERROR;
+		fd->status = NVME_SC_INTERNAL;
 	else
 		fd->status = 0;
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 5b2437a..3bd956d 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3061,6 +3061,8 @@
 	    host->max_cmd_len, host->max_channel, host->max_lun,
 	    host->transportt, sht->vendor_id);
 
+	INIT_WORK(&base_vha->iocb_work, qla2x00_iocb_work_fn);
+
 	/* Set up the irqs */
 	ret = qla2x00_request_irqs(ha, rsp);
 	if (ret)
@@ -3223,7 +3225,6 @@
 	 */
 	qla2xxx_wake_dpc(base_vha);
 
-	INIT_WORK(&base_vha->iocb_work, qla2x00_iocb_work_fn);
 	INIT_WORK(&ha->board_disable, qla2x00_disable_board_on_pci_error);
 
 	if (IS_QLA8031(ha) || IS_MCTP_CAPABLE(ha)) {
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 3894205..dab876c 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -580,7 +580,8 @@
 		if (sshdr.asc == 0x20 || /* Invalid command operation code */
 		    sshdr.asc == 0x21 || /* Logical block address out of range */
 		    sshdr.asc == 0x24 || /* Invalid field in cdb */
-		    sshdr.asc == 0x26) { /* Parameter value invalid */
+		    sshdr.asc == 0x26 || /* Parameter value invalid */
+		    sshdr.asc == 0x27) { /* Write protected */
 			set_host_byte(scmd, DID_TARGET_FAILURE);
 		}
 		return SUCCESS;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 9cf6a80..ad3ea24 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1379,8 +1379,6 @@
 
 	ret = scsi_setup_cmnd(sdev, req);
 out:
-	if (ret != BLKPREP_OK)
-		cmd->flags &= ~SCMD_INITIALIZED;
 	return scsi_prep_return(q, req, ret);
 }
 
@@ -1900,7 +1898,6 @@
 	struct scsi_device *sdev = req->q->queuedata;
 	struct Scsi_Host *shost = sdev->host;
 	struct scatterlist *sg;
-	int ret;
 
 	scsi_init_command(sdev, cmd);
 
@@ -1934,10 +1931,7 @@
 
 	blk_mq_start_request(req);
 
-	ret = scsi_setup_cmnd(sdev, req);
-	if (ret != BLK_STS_OK)
-		cmd->flags &= ~SCMD_INITIALIZED;
-	return ret;
+	return scsi_setup_cmnd(sdev, req);
 }
 
 static void scsi_mq_done(struct scsi_cmnd *cmd)
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index e7818af..15590a0 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -956,6 +956,9 @@
 	if (*bflags & BLIST_NO_DIF)
 		sdev->no_dif = 1;
 
+	if (*bflags & BLIST_UNMAP_LIMIT_WS)
+		sdev->unmap_limit_for_ws = 1;
+
 	sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT;
 
 	if (*bflags & BLIST_TRY_VPD_PAGES)
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index bf53356..f796bd6 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1376,13 +1376,19 @@
 	spin_lock_irqsave(shost->host_lock, flags);
  restart:
 	list_for_each_entry(sdev, &shost->__devices, siblings) {
+		/*
+		 * We cannot call scsi_device_get() here, as
+		 * we might've been called from rmmod() causing
+		 * scsi_device_get() to fail the module_is_live()
+		 * check.
+		 */
 		if (sdev->channel != starget->channel ||
 		    sdev->id != starget->id ||
-		    scsi_device_get(sdev))
+		    !get_device(&sdev->sdev_gendev))
 			continue;
 		spin_unlock_irqrestore(shost->host_lock, flags);
 		scsi_remove_device(sdev);
-		scsi_device_put(sdev);
+		put_device(&sdev->sdev_gendev);
 		spin_lock_irqsave(shost->host_lock, flags);
 		goto restart;
 	}
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 3c6bc00..8c46a6d 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2739,7 +2739,8 @@
 
 	list_for_each_entry(rport, &fc_host->rports, peers) {
 
-		if ((rport->port_state == FC_PORTSTATE_BLOCKED) &&
+		if ((rport->port_state == FC_PORTSTATE_BLOCKED ||
+		     rport->port_state == FC_PORTSTATE_NOTPRESENT) &&
 			(rport->channel == channel)) {
 
 			switch (fc_host->tgtid_bind_type) {
@@ -2876,7 +2877,6 @@
 			memcpy(&rport->port_name, &ids->port_name,
 				sizeof(rport->port_name));
 			rport->port_id = ids->port_id;
-			rport->roles = ids->roles;
 			rport->port_state = FC_PORTSTATE_ONLINE;
 			rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT;
 
@@ -2885,15 +2885,7 @@
 						fci->f->dd_fcrport_size);
 			spin_unlock_irqrestore(shost->host_lock, flags);
 
-			if (ids->roles & FC_PORT_ROLE_FCP_TARGET) {
-				scsi_target_unblock(&rport->dev, SDEV_RUNNING);
-
-				/* initiate a scan of the target */
-				spin_lock_irqsave(shost->host_lock, flags);
-				rport->flags |= FC_RPORT_SCAN_PENDING;
-				scsi_queue_work(shost, &rport->scan_work);
-				spin_unlock_irqrestore(shost->host_lock, flags);
-			}
+			fc_remote_port_rolechg(rport, ids->roles);
 			return rport;
 		}
 	}
@@ -3328,6 +3320,9 @@
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device));
 
+	if (WARN_ON_ONCE(!rport))
+		return FAST_IO_FAIL;
+
 	return fc_block_rport(rport);
 }
 EXPORT_SYMBOL(fc_block_scsi_eh);
@@ -3571,7 +3566,7 @@
 static enum blk_eh_timer_return
 fc_bsg_job_timeout(struct request *req)
 {
-	struct bsg_job *job = (void *) req->special;
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
 	struct Scsi_Host *shost = fc_bsg_to_shost(job);
 	struct fc_rport *rport = fc_bsg_to_rport(job);
 	struct fc_internal *i = to_fc_internal(shost->transportt);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 8934f19..7404d26 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2211,22 +2211,6 @@
 EXPORT_SYMBOL_GPL(iscsi_free_session);
 
 /**
- * iscsi_destroy_session - destroy iscsi session
- * @session: iscsi_session
- *
- * Can be called by a LLD or iscsi_transport. There must not be
- * any running connections.
- */
-int iscsi_destroy_session(struct iscsi_cls_session *session)
-{
-	iscsi_remove_session(session);
-	ISCSI_DBG_TRANS_SESSION(session, "Completing session destruction\n");
-	iscsi_free_session(session);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(iscsi_destroy_session);
-
-/**
  * iscsi_create_conn - create iscsi class connection
  * @session: iscsi cls session
  * @dd_size: private driver data size
@@ -3689,7 +3673,7 @@
 		uint32_t group;
 
 		nlh = nlmsg_hdr(skb);
-		if (nlh->nlmsg_len < sizeof(*nlh) ||
+		if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) ||
 		    skb->len < nlh->nlmsg_len) {
 			break;
 		}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 11c1738..d175c5c 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -715,13 +715,21 @@
 		break;
 
 	case SD_LBP_WS16:
-		max_blocks = min_not_zero(sdkp->max_ws_blocks,
-					  (u32)SD_MAX_WS16_BLOCKS);
+		if (sdkp->device->unmap_limit_for_ws)
+			max_blocks = sdkp->max_unmap_blocks;
+		else
+			max_blocks = sdkp->max_ws_blocks;
+
+		max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS);
 		break;
 
 	case SD_LBP_WS10:
-		max_blocks = min_not_zero(sdkp->max_ws_blocks,
-					  (u32)SD_MAX_WS10_BLOCKS);
+		if (sdkp->device->unmap_limit_for_ws)
+			max_blocks = sdkp->max_unmap_blocks;
+		else
+			max_blocks = sdkp->max_ws_blocks;
+
+		max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS);
 		break;
 
 	case SD_LBP_ZERO:
@@ -2915,8 +2923,6 @@
 				sd_config_discard(sdkp, SD_LBP_WS16);
 			else if (sdkp->lbpws10)
 				sd_config_discard(sdkp, SD_LBP_WS10);
-			else if (sdkp->lbpu && sdkp->max_unmap_blocks)
-				sd_config_discard(sdkp, SD_LBP_UNMAP);
 			else
 				sd_config_discard(sdkp, SD_LBP_DISABLE);
 		}
@@ -3101,8 +3107,6 @@
 		sd_read_security(sdkp, buffer);
 	}
 
-	sdkp->first_scan = 0;
-
 	/*
 	 * We now have all cache related info, determine how we deal
 	 * with flush requests.
@@ -3117,7 +3121,7 @@
 	q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
 
 	/*
-	 * Use the device's preferred I/O size for reads and writes
+	 * Determine the device's preferred I/O size for reads and writes
 	 * unless the reported value is unreasonably small, large, or
 	 * garbage.
 	 */
@@ -3131,8 +3135,19 @@
 		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
 				      (sector_t)BLK_DEF_MAX_SECTORS);
 
-	/* Combine with controller limits */
-	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
+	/* Do not exceed controller limit */
+	rw_max = min(rw_max, queue_max_hw_sectors(q));
+
+	/*
+	 * Only update max_sectors if previously unset or if the current value
+	 * exceeds the capabilities of the hardware.
+	 */
+	if (sdkp->first_scan ||
+	    q->limits.max_sectors > q->limits.max_dev_sectors ||
+	    q->limits.max_sectors > q->limits.max_hw_sectors)
+		q->limits.max_sectors = rw_max;
+
+	sdkp->first_scan = 0;
 
 	set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity));
 	sd_config_write_same(sdkp);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index cf0e71d..aa28874 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -828,6 +828,39 @@
 	return max_sectors << 9;
 }
 
+static void
+sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo)
+{
+	Sg_request *srp;
+	int val;
+	unsigned int ms;
+
+	val = 0;
+	list_for_each_entry(srp, &sfp->rq_list, entry) {
+		if (val >= SG_MAX_QUEUE)
+			break;
+		rinfo[val].req_state = srp->done + 1;
+		rinfo[val].problem =
+			srp->header.masked_status &
+			srp->header.host_status &
+			srp->header.driver_status;
+		if (srp->done)
+			rinfo[val].duration =
+				srp->header.duration;
+		else {
+			ms = jiffies_to_msecs(jiffies);
+			rinfo[val].duration =
+				(ms > srp->header.duration) ?
+				(ms - srp->header.duration) : 0;
+		}
+		rinfo[val].orphan = srp->orphan;
+		rinfo[val].sg_io_owned = srp->sg_io_owned;
+		rinfo[val].pack_id = srp->header.pack_id;
+		rinfo[val].usr_ptr = srp->header.usr_ptr;
+		val++;
+	}
+}
+
 static long
 sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 {
@@ -1012,38 +1045,13 @@
 			return -EFAULT;
 		else {
 			sg_req_info_t *rinfo;
-			unsigned int ms;
 
-			rinfo = kmalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
-								GFP_KERNEL);
+			rinfo = kzalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
+					GFP_KERNEL);
 			if (!rinfo)
 				return -ENOMEM;
 			read_lock_irqsave(&sfp->rq_list_lock, iflags);
-			val = 0;
-			list_for_each_entry(srp, &sfp->rq_list, entry) {
-				if (val >= SG_MAX_QUEUE)
-					break;
-				memset(&rinfo[val], 0, SZ_SG_REQ_INFO);
-				rinfo[val].req_state = srp->done + 1;
-				rinfo[val].problem =
-					srp->header.masked_status &
-					srp->header.host_status &
-					srp->header.driver_status;
-				if (srp->done)
-					rinfo[val].duration =
-						srp->header.duration;
-				else {
-					ms = jiffies_to_msecs(jiffies);
-					rinfo[val].duration =
-						(ms > srp->header.duration) ?
-						(ms - srp->header.duration) : 0;
-				}
-				rinfo[val].orphan = srp->orphan;
-				rinfo[val].sg_io_owned = srp->sg_io_owned;
-				rinfo[val].pack_id = srp->header.pack_id;
-				rinfo[val].usr_ptr = srp->header.usr_ptr;
-				val++;
-			}
+			sg_fill_request_table(sfp, rinfo);
 			read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
 			result = __copy_to_user(p, rinfo,
 						SZ_SG_REQ_INFO * SG_MAX_QUEUE);
diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c
index 6c7d7a4..568e1c6 100644
--- a/drivers/spi/spi-armada-3700.c
+++ b/drivers/spi/spi-armada-3700.c
@@ -99,11 +99,6 @@
 /* A3700_SPI_IF_TIME_REG */
 #define A3700_SPI_CLK_CAPT_EDGE		BIT(7)
 
-/* Flags and macros for struct a3700_spi */
-#define A3700_INSTR_CNT			1
-#define A3700_ADDR_CNT			3
-#define A3700_DUMMY_CNT			1
-
 struct a3700_spi {
 	struct spi_master *master;
 	void __iomem *base;
@@ -117,9 +112,6 @@
 	u8 byte_len;
 	u32 wait_mask;
 	struct completion done;
-	u32 addr_cnt;
-	u32 instr_cnt;
-	size_t hdr_cnt;
 };
 
 static u32 spireg_read(struct a3700_spi *a3700_spi, u32 offset)
@@ -161,7 +153,7 @@
 }
 
 static int a3700_spi_pin_mode_set(struct a3700_spi *a3700_spi,
-				  unsigned int pin_mode)
+				  unsigned int pin_mode, bool receiving)
 {
 	u32 val;
 
@@ -177,6 +169,9 @@
 		break;
 	case SPI_NBITS_QUAD:
 		val |= A3700_SPI_DATA_PIN1;
+		/* RX during address reception uses 4-pin */
+		if (receiving)
+			val |= A3700_SPI_ADDR_PIN;
 		break;
 	default:
 		dev_err(&a3700_spi->master->dev, "wrong pin mode %u", pin_mode);
@@ -392,7 +387,8 @@
 
 	spireg_write(a3700_spi, A3700_SPI_INT_MASK_REG, 0);
 
-	return true;
+	/* Timeout was reached */
+	return false;
 }
 
 static bool a3700_spi_transfer_wait(struct spi_device *spi,
@@ -446,59 +442,43 @@
 
 static void a3700_spi_header_set(struct a3700_spi *a3700_spi)
 {
-	u32 instr_cnt = 0, addr_cnt = 0, dummy_cnt = 0;
+	unsigned int addr_cnt;
 	u32 val = 0;
 
 	/* Clear the header registers */
 	spireg_write(a3700_spi, A3700_SPI_IF_INST_REG, 0);
 	spireg_write(a3700_spi, A3700_SPI_IF_ADDR_REG, 0);
 	spireg_write(a3700_spi, A3700_SPI_IF_RMODE_REG, 0);
+	spireg_write(a3700_spi, A3700_SPI_IF_HDR_CNT_REG, 0);
 
 	/* Set header counters */
 	if (a3700_spi->tx_buf) {
-		if (a3700_spi->buf_len <= a3700_spi->instr_cnt) {
-			instr_cnt = a3700_spi->buf_len;
-		} else if (a3700_spi->buf_len <= (a3700_spi->instr_cnt +
-						  a3700_spi->addr_cnt)) {
-			instr_cnt = a3700_spi->instr_cnt;
-			addr_cnt = a3700_spi->buf_len - instr_cnt;
-		} else if (a3700_spi->buf_len <= a3700_spi->hdr_cnt) {
-			instr_cnt = a3700_spi->instr_cnt;
-			addr_cnt = a3700_spi->addr_cnt;
-			/* Need to handle the normal write case with 1 byte
-			 * data
-			 */
-			if (!a3700_spi->tx_buf[instr_cnt + addr_cnt])
-				dummy_cnt = a3700_spi->buf_len - instr_cnt -
-					    addr_cnt;
+		/*
+		 * when tx data is not 4 bytes aligned, there will be unexpected
+		 * bytes out of SPI output register, since it always shifts out
+		 * as whole 4 bytes. This might cause incorrect transaction with
+		 * some devices. To avoid that, use SPI header count feature to
+		 * transfer up to 3 bytes of data first, and then make the rest
+		 * of data 4-byte aligned.
+		 */
+		addr_cnt = a3700_spi->buf_len % 4;
+		if (addr_cnt) {
+			val = (addr_cnt & A3700_SPI_ADDR_CNT_MASK)
+				<< A3700_SPI_ADDR_CNT_BIT;
+			spireg_write(a3700_spi, A3700_SPI_IF_HDR_CNT_REG, val);
+
+			/* Update the buffer length to be transferred */
+			a3700_spi->buf_len -= addr_cnt;
+
+			/* transfer 1~3 bytes through address count */
+			val = 0;
+			while (addr_cnt--) {
+				val = (val << 8) | a3700_spi->tx_buf[0];
+				a3700_spi->tx_buf++;
+			}
+			spireg_write(a3700_spi, A3700_SPI_IF_ADDR_REG, val);
 		}
-		val |= ((instr_cnt & A3700_SPI_INSTR_CNT_MASK)
-			<< A3700_SPI_INSTR_CNT_BIT);
-		val |= ((addr_cnt & A3700_SPI_ADDR_CNT_MASK)
-			<< A3700_SPI_ADDR_CNT_BIT);
-		val |= ((dummy_cnt & A3700_SPI_DUMMY_CNT_MASK)
-			<< A3700_SPI_DUMMY_CNT_BIT);
 	}
-	spireg_write(a3700_spi, A3700_SPI_IF_HDR_CNT_REG, val);
-
-	/* Update the buffer length to be transferred */
-	a3700_spi->buf_len -= (instr_cnt + addr_cnt + dummy_cnt);
-
-	/* Set Instruction */
-	val = 0;
-	while (instr_cnt--) {
-		val = (val << 8) | a3700_spi->tx_buf[0];
-		a3700_spi->tx_buf++;
-	}
-	spireg_write(a3700_spi, A3700_SPI_IF_INST_REG, val);
-
-	/* Set Address */
-	val = 0;
-	while (addr_cnt--) {
-		val = (val << 8) | a3700_spi->tx_buf[0];
-		a3700_spi->tx_buf++;
-	}
-	spireg_write(a3700_spi, A3700_SPI_IF_ADDR_REG, val);
 }
 
 static int a3700_is_wfifo_full(struct a3700_spi *a3700_spi)
@@ -512,35 +492,12 @@
 static int a3700_spi_fifo_write(struct a3700_spi *a3700_spi)
 {
 	u32 val;
-	int i = 0;
 
 	while (!a3700_is_wfifo_full(a3700_spi) && a3700_spi->buf_len) {
-		val = 0;
-		if (a3700_spi->buf_len >= 4) {
-			val = cpu_to_le32(*(u32 *)a3700_spi->tx_buf);
-			spireg_write(a3700_spi, A3700_SPI_DATA_OUT_REG, val);
-
-			a3700_spi->buf_len -= 4;
-			a3700_spi->tx_buf += 4;
-		} else {
-			/*
-			 * If the remained buffer length is less than 4-bytes,
-			 * we should pad the write buffer with all ones. So that
-			 * it avoids overwrite the unexpected bytes following
-			 * the last one.
-			 */
-			val = GENMASK(31, 0);
-			while (a3700_spi->buf_len) {
-				val &= ~(0xff << (8 * i));
-				val |= *a3700_spi->tx_buf++ << (8 * i);
-				i++;
-				a3700_spi->buf_len--;
-
-				spireg_write(a3700_spi, A3700_SPI_DATA_OUT_REG,
-					     val);
-			}
-			break;
-		}
+		val = cpu_to_le32(*(u32 *)a3700_spi->tx_buf);
+		spireg_write(a3700_spi, A3700_SPI_DATA_OUT_REG, val);
+		a3700_spi->buf_len -= 4;
+		a3700_spi->tx_buf += 4;
 	}
 
 	return 0;
@@ -645,15 +602,18 @@
 	a3700_spi->rx_buf  = xfer->rx_buf;
 	a3700_spi->buf_len = xfer->len;
 
-	/* SPI transfer headers */
-	a3700_spi_header_set(a3700_spi);
-
 	if (xfer->tx_buf)
 		nbits = xfer->tx_nbits;
 	else if (xfer->rx_buf)
 		nbits = xfer->rx_nbits;
 
-	a3700_spi_pin_mode_set(a3700_spi, nbits);
+	a3700_spi_pin_mode_set(a3700_spi, nbits, xfer->rx_buf ? true : false);
+
+	/* Flush the FIFOs */
+	a3700_spi_fifo_flush(a3700_spi);
+
+	/* Transfer first bytes of data when buffer is not 4-byte aligned */
+	a3700_spi_header_set(a3700_spi);
 
 	if (xfer->rx_buf) {
 		/* Set read data length */
@@ -733,16 +693,11 @@
 				dev_err(&spi->dev, "wait wfifo empty timed out\n");
 				return -ETIMEDOUT;
 			}
-		} else {
-			/*
-			 * If the instruction in SPI_INSTR does not require data
-			 * to be written to the SPI device, wait until SPI_RDY
-			 * is 1 for the SPI interface to be in idle.
-			 */
-			if (!a3700_spi_transfer_wait(spi, A3700_SPI_XFER_RDY)) {
-				dev_err(&spi->dev, "wait xfer ready timed out\n");
-				return -ETIMEDOUT;
-			}
+		}
+
+		if (!a3700_spi_transfer_wait(spi, A3700_SPI_XFER_RDY)) {
+			dev_err(&spi->dev, "wait xfer ready timed out\n");
+			return -ETIMEDOUT;
 		}
 
 		val = spireg_read(a3700_spi, A3700_SPI_IF_CFG_REG);
@@ -834,10 +789,6 @@
 	memset(spi, 0, sizeof(struct a3700_spi));
 
 	spi->master = master;
-	spi->instr_cnt = A3700_INSTR_CNT;
-	spi->addr_cnt = A3700_ADDR_CNT;
-	spi->hdr_cnt = A3700_INSTR_CNT + A3700_ADDR_CNT +
-		       A3700_DUMMY_CNT;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	spi->base = devm_ioremap_resource(dev, res);
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 6ef6c44..a172ab2 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -1250,7 +1250,7 @@
 			goto qspi_probe_err;
 		}
 	} else {
-		goto qspi_probe_err;
+		goto qspi_resource_err;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi");
@@ -1272,7 +1272,7 @@
 		qspi->base[CHIP_SELECT]  = devm_ioremap_resource(dev, res);
 		if (IS_ERR(qspi->base[CHIP_SELECT])) {
 			ret = PTR_ERR(qspi->base[CHIP_SELECT]);
-			goto qspi_probe_err;
+			goto qspi_resource_err;
 		}
 	}
 
@@ -1280,7 +1280,7 @@
 				GFP_KERNEL);
 	if (!qspi->dev_ids) {
 		ret = -ENOMEM;
-		goto qspi_probe_err;
+		goto qspi_resource_err;
 	}
 
 	for (val = 0; val < num_irqs; val++) {
@@ -1369,8 +1369,9 @@
 	bcm_qspi_hw_uninit(qspi);
 	clk_disable_unprepare(qspi->clk);
 qspi_probe_err:
-	spi_master_put(master);
 	kfree(qspi->dev_ids);
+qspi_resource_err:
+	spi_master_put(master);
 	return ret;
 }
 /* probe function to be called by SoC specific platform driver probe */
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 680cdf5..ba9743f 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -263,8 +263,8 @@
 	 * no need to check it there.
 	 * However, we need to ensure the following calculations.
 	 */
-	if ((div < SPI_MBR_DIV_MIN) &&
-	    (div > SPI_MBR_DIV_MAX))
+	if (div < SPI_MBR_DIV_MIN ||
+	    div > SPI_MBR_DIV_MAX)
 		return -EINVAL;
 
 	/* Determine the first power of 2 greater than or equal to div */
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 6e65524..e8b5a5e 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -45,7 +45,6 @@
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/spi.h>
-#define SPI_DYN_FIRST_BUS_NUM 0
 
 static DEFINE_IDR(spi_master_idr);
 
@@ -2086,7 +2085,7 @@
 	struct device		*dev = ctlr->dev.parent;
 	struct boardinfo	*bi;
 	int			status = -ENODEV;
-	int			id;
+	int			id, first_dynamic;
 
 	if (!dev)
 		return -ENODEV;
@@ -2116,9 +2115,15 @@
 		}
 	}
 	if (ctlr->bus_num < 0) {
+		first_dynamic = of_alias_get_highest_id("spi");
+		if (first_dynamic < 0)
+			first_dynamic = 0;
+		else
+			first_dynamic++;
+
 		mutex_lock(&board_lock);
-		id = idr_alloc(&spi_master_idr, ctlr, SPI_DYN_FIRST_BUS_NUM, 0,
-			       GFP_KERNEL);
+		id = idr_alloc(&spi_master_idr, ctlr, first_dynamic,
+			       0, GFP_KERNEL);
 		mutex_unlock(&board_lock);
 		if (WARN(id < 0, "couldn't get idr"))
 			return id;
diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c
index d11c6de..6150d27 100644
--- a/drivers/staging/iio/adc/ad7192.c
+++ b/drivers/staging/iio/adc/ad7192.c
@@ -223,11 +223,9 @@
 	struct iio_dev *indio_dev = spi_get_drvdata(st->sd.spi);
 	unsigned long long scale_uv;
 	int i, ret, id;
-	u8 ones[6];
 
 	/* reset the serial interface */
-	memset(&ones, 0xFF, 6);
-	ret = spi_write(st->sd.spi, &ones, 6);
+	ret = ad_sd_reset(&st->sd, 48);
 	if (ret < 0)
 		goto out;
 	usleep_range(500, 1000); /* Wait for at least 500us */
diff --git a/drivers/staging/iio/meter/ade7759.c b/drivers/staging/iio/meter/ade7759.c
index 1691760..02573c5 100644
--- a/drivers/staging/iio/meter/ade7759.c
+++ b/drivers/staging/iio/meter/ade7759.c
@@ -172,7 +172,7 @@
 				reg_address);
 		goto error_ret;
 	}
-	*val = ((u64)st->rx[1] << 32) | (st->rx[2] << 24) |
+	*val = ((u64)st->rx[1] << 32) | ((u64)st->rx[2] << 24) |
 		(st->rx[3] << 16) | (st->rx[4] << 8) | st->rx[5];
 
 error_ret:
diff --git a/drivers/staging/media/imx/imx-media-dev.c b/drivers/staging/media/imx/imx-media-dev.c
index d96f451..b55e5eb 100644
--- a/drivers/staging/media/imx/imx-media-dev.c
+++ b/drivers/staging/media/imx/imx-media-dev.c
@@ -400,10 +400,10 @@
 					struct media_link, list);
 		ret = imx_media_add_vdev_to_pad(imxmd, vdev, link->source);
 		if (ret)
-			break;
+			return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 /* async subdev complete notifier */
diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c
index 13eaf16..87595c5 100644
--- a/drivers/staging/mt29f_spinand/mt29f_spinand.c
+++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c
@@ -496,8 +496,12 @@
 	if (!wbuf)
 		return -ENOMEM;
 
-	enable_read_hw_ecc = 0;
-	spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf);
+	enable_read_hw_ecc = 1;
+	retval = spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf);
+	if (retval < 0) {
+		dev_err(&spi_nand->dev, "ecc error on read page!!!\n");
+		return retval;
+	}
 
 	for (i = offset, j = 0; i < len; i++, j++)
 		wbuf[i] &= buf[j];
diff --git a/drivers/staging/pi433/rf69.c b/drivers/staging/pi433/rf69.c
index c4b1b21..290b419 100644
--- a/drivers/staging/pi433/rf69.c
+++ b/drivers/staging/pi433/rf69.c
@@ -570,12 +570,6 @@
 		dev_dbg(&spi->dev, "set: DIO mapping");
 	#endif
 
-	// check DIO number
-	if (DIONumber > 5) {
-		dev_dbg(&spi->dev, "set: illegal input param");
-		return -EINVAL;
-	}
-
 	switch (DIONumber) {
 	case 0: mask=MASK_DIO0; shift=SHIFT_DIO0; regaddr=REG_DIOMAPPING1; break;
 	case 1: mask=MASK_DIO1; shift=SHIFT_DIO1; regaddr=REG_DIOMAPPING1; break;
@@ -583,6 +577,9 @@
 	case 3: mask=MASK_DIO3; shift=SHIFT_DIO3; regaddr=REG_DIOMAPPING1; break;
 	case 4: mask=MASK_DIO4; shift=SHIFT_DIO4; regaddr=REG_DIOMAPPING2; break;
 	case 5: mask=MASK_DIO5; shift=SHIFT_DIO5; regaddr=REG_DIOMAPPING2; break;
+	default:
+		dev_dbg(&spi->dev, "set: illegal input param");
+		return -EINVAL;
 	}
 
 	// read reg
diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c
index 6b77820..cb8a95a 100644
--- a/drivers/staging/rtl8723bs/core/rtw_mlme.c
+++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c
@@ -119,9 +119,8 @@
 
 void _rtw_free_mlme_priv(struct mlme_priv *pmlmepriv)
 {
-	rtw_free_mlme_priv_ie_data(pmlmepriv);
-
 	if (pmlmepriv) {
+		rtw_free_mlme_priv_ie_data(pmlmepriv);
 		if (pmlmepriv->free_bss_buf) {
 			vfree(pmlmepriv->free_bss_buf);
 		}
diff --git a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c
index 9227745..ce1dd6f 100644
--- a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c
+++ b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c
@@ -311,6 +311,8 @@
 
 		if (num < 2)
 			return count;
+		if (id >= TOTAL_CAM_ENTRY)
+			return -EINVAL;
 
 		if (strcmp("c", cmd) == 0) {
 			_clear_cam_entry(adapter, id);
diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c
index 5f84526..edbf6af 100644
--- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c
+++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c
@@ -2901,11 +2901,11 @@
 	if (halmac_adapter->fw_version.h2c_version < 4)
 		return HALMAC_RET_FW_NO_SUPPORT;
 
+	driver_adapter = halmac_adapter->driver_adapter;
+
 	HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG,
 			"[TRACE]%s ==========>\n", __func__);
 
-	driver_adapter = halmac_adapter->driver_adapter;
-
 	HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG,
 			"[TRACE]%s <==========\n", __func__);
 
diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c
index f33024e..544f638 100644
--- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c
+++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c
@@ -1618,10 +1618,11 @@
 	void *driver_adapter = NULL;
 	enum halmac_ret_status status = HALMAC_RET_SUCCESS;
 
+	driver_adapter = halmac_adapter->driver_adapter;
+
 	HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG,
 			"%s!!\n", __func__);
 
-	driver_adapter = halmac_adapter->driver_adapter;
 	h2c_header = h2c_buff;
 	h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX;
 
@@ -1713,10 +1714,11 @@
 	void *driver_adapter = NULL;
 	enum halmac_ret_status status = HALMAC_RET_SUCCESS;
 
+	driver_adapter = halmac_adapter->driver_adapter;
+
 	HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG,
 			"halmac_send_h2c_set_pwr_mode_88xx!!\n");
 
-	driver_adapter = halmac_adapter->driver_adapter;
 	h2c_header = H2c_buff;
 	h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX;
 
@@ -2143,10 +2145,11 @@
 	enum halmac_cmd_process_status *process_status =
 		&halmac_adapter->halmac_state.scan_state_set.process_status;
 
+	driver_adapter = halmac_adapter->driver_adapter;
+
 	HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG,
 			"halmac_ctrl_ch_switch!!\n");
 
-	driver_adapter = halmac_adapter->driver_adapter;
 	halmac_api = (struct halmac_api *)halmac_adapter->halmac_api;
 
 	if (halmac_transition_scan_state_88xx(
@@ -2276,15 +2279,13 @@
 {
 	u8 h2c_buff[HALMAC_H2C_CMD_SIZE_88XX] = {0};
 	u16 h2c_seq_mum = 0;
-	void *driver_adapter = NULL;
+	void *driver_adapter = halmac_adapter->driver_adapter;
 	struct halmac_h2c_header_info h2c_header_info;
 	enum halmac_ret_status status = HALMAC_RET_SUCCESS;
 
 	HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG,
 			"%s!!\n", __func__);
 
-	driver_adapter = halmac_adapter->driver_adapter;
-
 	UPDATE_BEACON_PARSING_INFO_SET_FUNC_EN(h2c_buff, bcn_ie_info->func_en);
 	UPDATE_BEACON_PARSING_INFO_SET_SIZE_TH(h2c_buff, bcn_ie_info->size_th);
 	UPDATE_BEACON_PARSING_INFO_SET_TIMEOUT(h2c_buff, bcn_ie_info->timeout);
diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c
index 67956e2..56f7be6 100644
--- a/drivers/staging/speakup/main.c
+++ b/drivers/staging/speakup/main.c
@@ -1376,6 +1376,8 @@
 
 static int read_all_key;
 
+static int in_keyboard_notifier;
+
 static void start_read_all_timer(struct vc_data *vc, int command);
 
 enum {
@@ -1408,7 +1410,10 @@
 	cursor_track = read_all_mode;
 	spk_reset_index_count(0);
 	if (get_sentence_buf(vc, 0) == -1) {
-		kbd_fakekey2(vc, RA_DOWN_ARROW);
+		del_timer(&cursor_timer);
+		if (!in_keyboard_notifier)
+			speakup_fake_down_arrow();
+		start_read_all_timer(vc, RA_DOWN_ARROW);
 	} else {
 		say_sentence_num(0, 0);
 		synth_insert_next_index(0);
@@ -2212,8 +2217,10 @@
 	int ret = NOTIFY_OK;
 	static int keycode;	/* to hold the current keycode */
 
+	in_keyboard_notifier = 1;
+
 	if (vc->vc_mode == KD_GRAPHICS)
-		return ret;
+		goto out;
 
 	/*
 	 * First, determine whether we are handling a fake keypress on
@@ -2225,7 +2232,7 @@
 	 */
 
 	if (speakup_fake_key_pressed())
-		return ret;
+		goto out;
 
 	switch (code) {
 	case KBD_KEYCODE:
@@ -2266,6 +2273,8 @@
 			break;
 		}
 	}
+out:
+	in_keyboard_notifier = 0;
 	return ret;
 }
 
diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c
index 74cce4f..27ecf6f 100644
--- a/drivers/staging/unisys/visorbus/visorchipset.c
+++ b/drivers/staging/unisys/visorbus/visorchipset.c
@@ -1826,7 +1826,7 @@
 	return 0;
 }
 
-static int init_unisys(void)
+static int __init init_unisys(void)
 {
 	int result;
 
@@ -1841,7 +1841,7 @@
 	return 0;
 };
 
-static void exit_unisys(void)
+static void __exit exit_unisys(void)
 {
 	acpi_bus_unregister_driver(&unisys_acpi_driver);
 }
diff --git a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
index 5f3d8f2..4be864d 100644
--- a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
+++ b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
@@ -390,8 +390,7 @@
 			__func__, instance);
 		instance->alsa_stream = alsa_stream;
 		alsa_stream->instance = instance;
-		ret = 0; // xxx todo -1;
-		goto err_free_mem;
+		return 0;
 	}
 
 	/* Initialize and create a VCHI connection */
@@ -401,16 +400,15 @@
 			LOG_ERR("%s: failed to initialise VCHI instance (ret=%d)\n",
 				__func__, ret);
 
-			ret = -EIO;
-			goto err_free_mem;
+			return -EIO;
 		}
 		ret = vchi_connect(NULL, 0, vchi_instance);
 		if (ret) {
 			LOG_ERR("%s: failed to connect VCHI instance (ret=%d)\n",
 				__func__, ret);
 
-			ret = -EIO;
-			goto err_free_mem;
+			kfree(vchi_instance);
+			return -EIO;
 		}
 		initted = 1;
 	}
@@ -421,19 +419,16 @@
 	if (IS_ERR(instance)) {
 		LOG_ERR("%s: failed to initialize audio service\n", __func__);
 
-		ret = PTR_ERR(instance);
-		goto err_free_mem;
+		/* vchi_instance is retained for use the next time. */
+		return PTR_ERR(instance);
 	}
 
 	instance->alsa_stream = alsa_stream;
 	alsa_stream->instance = instance;
 
 	LOG_DBG(" success !\n");
-	ret = 0;
-err_free_mem:
-	kfree(vchi_instance);
 
-	return ret;
+	return 0;
 }
 
 int bcm2835_audio_open(struct bcm2835_alsa_stream *alsa_stream)
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
index 0159ca4..be08849 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
@@ -612,18 +612,20 @@
 			if (head_bytes > actual)
 				head_bytes = actual;
 
-			memcpy((char *)page_address(pages[0]) +
+			memcpy((char *)kmap(pages[0]) +
 				pagelist->offset,
 				fragments,
 				head_bytes);
+			kunmap(pages[0]);
 		}
 		if ((actual >= 0) && (head_bytes < actual) &&
 			(tail_bytes != 0)) {
-			memcpy((char *)page_address(pages[num_pages - 1]) +
+			memcpy((char *)kmap(pages[num_pages - 1]) +
 				((pagelist->offset + actual) &
 				(PAGE_SIZE - 1) & ~(g_cache_line_size - 1)),
 				fragments + g_cache_line_size,
 				tail_bytes);
+			kunmap(pages[num_pages - 1]);
 		}
 
 		down(&g_free_fragments_mutex);
diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c
index 1c0c955..7dd3804 100644
--- a/drivers/tty/mxser.c
+++ b/drivers/tty/mxser.c
@@ -246,11 +246,11 @@
 	unsigned char err_shadow;
 
 	struct async_icount icount; /* kernel counters for 4 input interrupts */
-	int timeout;
+	unsigned int timeout;
 
 	int read_status_mask;
 	int ignore_status_mask;
-	int xmit_fifo_size;
+	unsigned int xmit_fifo_size;
 	int xmit_head;
 	int xmit_tail;
 	int xmit_cnt;
@@ -572,8 +572,9 @@
 static int mxser_set_baud(struct tty_struct *tty, long newspd)
 {
 	struct mxser_port *info = tty->driver_data;
-	int quot = 0, baud;
+	unsigned int quot = 0, baud;
 	unsigned char cval;
+	u64 timeout;
 
 	if (!info->ioaddr)
 		return -1;
@@ -594,8 +595,13 @@
 		quot = 0;
 	}
 
-	info->timeout = ((info->xmit_fifo_size * HZ * 10 * quot) / info->baud_base);
-	info->timeout += HZ / 50;	/* Add .02 seconds of slop */
+	/*
+	 * worst case (128 * 1000 * 10 * 18432) needs 35 bits, so divide in the
+	 * u64 domain
+	 */
+	timeout = (u64)info->xmit_fifo_size * HZ * 10 * quot;
+	do_div(timeout, info->baud_base);
+	info->timeout = timeout + HZ / 50; /* Add .02 seconds of slop */
 
 	if (quot) {
 		info->MCR |= UART_MCR_DTR;
diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index 583c9a0..8c48c37 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -507,9 +507,14 @@
 {
 	unsigned int ctl, baud, quot, ier;
 	unsigned long flags;
+	int tries;
 
 	spin_lock_irqsave(&port->lock, flags);
 
+	/* Drain the hot tub fully before we power it off for the winter. */
+	for (tries = 3; !bcm_uart_tx_empty(port) && tries; tries--)
+		mdelay(10);
+
 	/* disable uart while changing speed */
 	bcm_uart_disable(port);
 	bcm_uart_flush(port);
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 849c1f9..f025218 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -1276,7 +1276,6 @@
 static int lpuart_startup(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
-	int ret;
 	unsigned long flags;
 	unsigned char temp;
 
@@ -1291,11 +1290,6 @@
 	sport->rxfifo_size = 0x1 << (((temp >> UARTPFIFO_RXSIZE_OFF) &
 		UARTPFIFO_FIFOSIZE_MASK) + 1);
 
-	ret = devm_request_irq(port->dev, port->irq, lpuart_int, 0,
-				DRIVER_NAME, sport);
-	if (ret)
-		return ret;
-
 	spin_lock_irqsave(&sport->port.lock, flags);
 
 	lpuart_setup_watermark(sport);
@@ -1333,7 +1327,6 @@
 static int lpuart32_startup(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
-	int ret;
 	unsigned long flags;
 	unsigned long temp;
 
@@ -1346,11 +1339,6 @@
 	sport->rxfifo_size = 0x1 << (((temp >> UARTFIFO_RXSIZE_OFF) &
 		UARTFIFO_FIFOSIZE_MASK) - 1);
 
-	ret = devm_request_irq(port->dev, port->irq, lpuart32_int, 0,
-				DRIVER_NAME, sport);
-	if (ret)
-		return ret;
-
 	spin_lock_irqsave(&sport->port.lock, flags);
 
 	lpuart32_setup_watermark(sport);
@@ -1380,8 +1368,6 @@
 
 	spin_unlock_irqrestore(&port->lock, flags);
 
-	devm_free_irq(port->dev, port->irq, sport);
-
 	if (sport->lpuart_dma_rx_use) {
 		del_timer_sync(&sport->lpuart_timer);
 		lpuart_dma_rx_free(&sport->port);
@@ -1400,7 +1386,6 @@
 
 static void lpuart32_shutdown(struct uart_port *port)
 {
-	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
 	unsigned long temp;
 	unsigned long flags;
 
@@ -1413,8 +1398,6 @@
 	lpuart32_write(port, temp, UARTCTRL);
 
 	spin_unlock_irqrestore(&port->lock, flags);
-
-	devm_free_irq(port->dev, port->irq, sport);
 }
 
 static void
@@ -2212,16 +2195,22 @@
 
 	platform_set_drvdata(pdev, &sport->port);
 
-	if (lpuart_is_32(sport))
+	if (lpuart_is_32(sport)) {
 		lpuart_reg.cons = LPUART32_CONSOLE;
-	else
+		ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart32_int, 0,
+					DRIVER_NAME, sport);
+	} else {
 		lpuart_reg.cons = LPUART_CONSOLE;
+		ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart_int, 0,
+					DRIVER_NAME, sport);
+	}
+
+	if (ret)
+		goto failed_irq_request;
 
 	ret = uart_add_one_port(&lpuart_reg, &sport->port);
-	if (ret) {
-		clk_disable_unprepare(sport->clk);
-		return ret;
-	}
+	if (ret)
+		goto failed_attach_port;
 
 	sport->dma_tx_chan = dma_request_slave_channel(sport->port.dev, "tx");
 	if (!sport->dma_tx_chan)
@@ -2240,6 +2229,11 @@
 	}
 
 	return 0;
+
+failed_attach_port:
+failed_irq_request:
+	clk_disable_unprepare(sport->clk);
+	return ret;
 }
 
 static int lpuart_remove(struct platform_device *pdev)
diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c
index cdd2f94..b9c7a90 100644
--- a/drivers/tty/serial/sccnxp.c
+++ b/drivers/tty/serial/sccnxp.c
@@ -889,7 +889,16 @@
 			goto err_out;
 		uartclk = 0;
 	} else {
-		clk_prepare_enable(clk);
+		ret = clk_prepare_enable(clk);
+		if (ret)
+			goto err_out;
+
+		ret = devm_add_action_or_reset(&pdev->dev,
+				(void(*)(void *))clk_disable_unprepare,
+				clk);
+		if (ret)
+			goto err_out;
+
 		uartclk = clk_get_rate(clk);
 	}
 
@@ -988,7 +997,7 @@
 	uart_unregister_driver(&s->uart);
 err_out:
 	if (!IS_ERR(s->regulator))
-		return regulator_disable(s->regulator);
+		regulator_disable(s->regulator);
 
 	return ret;
 }
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 2fe216b..84a8ac2 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -694,10 +694,8 @@
 	tty_set_termios_ldisc(tty, disc);
 	retval = tty_ldisc_open(tty, tty->ldisc);
 	if (retval) {
-		if (!WARN_ON(disc == N_TTY)) {
-			tty_ldisc_put(tty->ldisc);
-			tty->ldisc = NULL;
-		}
+		tty_ldisc_put(tty->ldisc);
+		tty->ldisc = NULL;
 	}
 	return retval;
 }
@@ -752,8 +750,9 @@
 
 	if (tty->ldisc) {
 		if (reinit) {
-			if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0)
-				tty_ldisc_reinit(tty, N_TTY);
+			if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0 &&
+			    tty_ldisc_reinit(tty, N_TTY) < 0)
+				WARN_ON(tty_ldisc_reinit(tty, N_NULL) < 0);
 		} else
 			tty_ldisc_kill(tty);
 	}
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 5e056064..18c923a 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1832,6 +1832,9 @@
 	{ USB_DEVICE(0xfff0, 0x0100), /* DATECS FP-2000 */
 	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
 	},
+	{ USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */
+	.driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */
+	},
 
 	{ USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */
 	.driver_info = CLEAR_HALT_CONDITIONS,
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 5aacea1..3e865db 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -190,8 +190,10 @@
 	/*
 	 * only set a new error if there is no previous error.
 	 * Errors are only cleared during read/open
+	 * Avoid propagating -EPIPE (stall) to userspace since it is
+	 * better handled as an empty read
 	 */
-	if (desc->rerr  == 0)
+	if (desc->rerr == 0 && status != -EPIPE)
 		desc->rerr = status;
 
 	if (length + desc->length > desc->wMaxCommand) {
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 4be52c6..883549e 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -643,15 +643,23 @@
 
 		} else if (header->bDescriptorType ==
 				USB_DT_INTERFACE_ASSOCIATION) {
+			struct usb_interface_assoc_descriptor *d;
+
+			d = (struct usb_interface_assoc_descriptor *)header;
+			if (d->bLength < USB_DT_INTERFACE_ASSOCIATION_SIZE) {
+				dev_warn(ddev,
+					 "config %d has an invalid interface association descriptor of length %d, skipping\n",
+					 cfgno, d->bLength);
+				continue;
+			}
+
 			if (iad_num == USB_MAXIADS) {
 				dev_warn(ddev, "found more Interface "
 					       "Association Descriptors "
 					       "than allocated for in "
 					       "configuration %d\n", cfgno);
 			} else {
-				config->intf_assoc[iad_num] =
-					(struct usb_interface_assoc_descriptor
-					*)header;
+				config->intf_assoc[iad_num] = d;
 				iad_num++;
 			}
 
@@ -852,7 +860,7 @@
 		}
 
 		if (dev->quirks & USB_QUIRK_DELAY_INIT)
-			msleep(100);
+			msleep(200);
 
 		result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno,
 		    bigbuffer, length);
@@ -952,10 +960,12 @@
 	for (i = 0; i < num; i++) {
 		buffer += length;
 		cap = (struct usb_dev_cap_header *)buffer;
-		length = cap->bLength;
 
-		if (total_len < length)
+		if (total_len < sizeof(*cap) || total_len < cap->bLength) {
+			dev->bos->desc->bNumDeviceCaps = i;
 			break;
+		}
+		length = cap->bLength;
 		total_len -= length;
 
 		if (cap->bDescriptorType != USB_DT_DEVICE_CAPABILITY) {
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 318bb3b..e9326f3 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -140,6 +140,9 @@
 MODULE_PARM_DESC(usbfs_memory_mb,
 		"maximum MB allowed for usbfs buffers (0 = no limit)");
 
+/* Hard limit, necessary to avoid arithmetic overflow */
+#define USBFS_XFER_MAX         (UINT_MAX / 2 - 1000000)
+
 static atomic64_t usbfs_memory_usage;	/* Total memory currently allocated */
 
 /* Check whether it's okay to allocate more memory for a transfer */
@@ -1460,6 +1463,8 @@
 				USBDEVFS_URB_ZERO_PACKET |
 				USBDEVFS_URB_NO_INTERRUPT))
 		return -EINVAL;
+	if ((unsigned int)uurb->buffer_length >= USBFS_XFER_MAX)
+		return -EINVAL;
 	if (uurb->buffer_length > 0 && !uurb->buffer)
 		return -EINVAL;
 	if (!(uurb->type == USBDEVFS_URB_TYPE_CONTROL &&
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 41eaf0b..e9ce6bb 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2710,13 +2710,16 @@
 	if (!(portstatus & USB_PORT_STAT_CONNECTION))
 		return -ENOTCONN;
 
-	/* bomb out completely if the connection bounced.  A USB 3.0
-	 * connection may bounce if multiple warm resets were issued,
+	/* Retry if connect change is set but status is still connected.
+	 * A USB 3.0 connection may bounce if multiple warm resets were issued,
 	 * but the device may have successfully re-connected. Ignore it.
 	 */
 	if (!hub_is_superspeed(hub->hdev) &&
-			(portchange & USB_PORT_STAT_C_CONNECTION))
-		return -ENOTCONN;
+	    (portchange & USB_PORT_STAT_C_CONNECTION)) {
+		usb_clear_port_feature(hub->hdev, port1,
+				       USB_PORT_FEAT_C_CONNECTION);
+		return -EAGAIN;
+	}
 
 	if (!(portstatus & USB_PORT_STAT_ENABLE))
 		return -EBUSY;
@@ -4838,7 +4841,7 @@
 			goto loop;
 
 		if (udev->quirks & USB_QUIRK_DELAY_INIT)
-			msleep(1000);
+			msleep(2000);
 
 		/* consecutive bus-powered hubs aren't reliable; they can
 		 * violate the voltage drop budget.  if the new child has
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 4c38ea4..371a07d8 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -2069,6 +2069,10 @@
 			elength = 1;
 			goto next_desc;
 		}
+		if ((buflen < elength) || (elength < 3)) {
+			dev_err(&intf->dev, "invalid descriptor buffer length\n");
+			break;
+		}
 		if (buffer[1] != USB_DT_CS_INTERFACE) {
 			dev_err(&intf->dev, "skipping garbage\n");
 			goto next_desc;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 82806e3..a6aaf2f 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -221,6 +221,10 @@
 	/* Corsair Strafe RGB */
 	{ USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* MIDI keyboard WORLDE MINI */
+	{ USB_DEVICE(0x1c75, 0x0204), .driver_info =
+			USB_QUIRK_CONFIG_INTF_STRINGS },
+
 	/* Acer C120 LED Projector */
 	{ USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM },
 
diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c
index 4cef7d4..a26d1fd 100644
--- a/drivers/usb/dwc3/dwc3-of-simple.c
+++ b/drivers/usb/dwc3/dwc3-of-simple.c
@@ -177,6 +177,7 @@
 	{ .compatible = "rockchip,rk3399-dwc3" },
 	{ .compatible = "xlnx,zynqmp-dwc3" },
 	{ .compatible = "cavium,octeon-7130-usb-uctl" },
+	{ .compatible = "sprd,sc9860-dwc3" },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, of_dwc3_simple_match);
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 827e376..75e6cb0 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -990,6 +990,8 @@
 					 DWC3_TRBCTL_CONTROL_DATA,
 					 true);
 
+		req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1];
+
 		/* Now prepare one extra TRB to align transfer size */
 		dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr,
 					 maxpacket - rem,
@@ -1015,6 +1017,8 @@
 					 DWC3_TRBCTL_CONTROL_DATA,
 					 true);
 
+		req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1];
+
 		/* Now prepare one extra TRB to align transfer size */
 		dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr,
 					 0, DWC3_TRBCTL_CONTROL_DATA,
@@ -1029,6 +1033,9 @@
 		dwc3_ep0_prepare_one_trb(dep, req->request.dma,
 				req->request.length, DWC3_TRBCTL_CONTROL_DATA,
 				false);
+
+		req->trb = &dwc->ep0_trb[dep->trb_enqueue];
+
 		ret = dwc3_ep0_start_trans(dep);
 	}
 
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index dd74c99..5d061b3 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2026,6 +2026,8 @@
 static void __composite_unbind(struct usb_gadget *gadget, bool unbind_driver)
 {
 	struct usb_composite_dev	*cdev = get_gadget_data(gadget);
+	struct usb_gadget_strings	*gstr = cdev->driver->strings[0];
+	struct usb_string		*dev_str = gstr->strings;
 
 	/* composite_disconnect() must already have been called
 	 * by the underlying peripheral controller driver!
@@ -2045,6 +2047,9 @@
 
 	composite_dev_cleanup(cdev);
 
+	if (dev_str[USB_GADGET_MANUFACTURER_IDX].s == cdev->def_manufacturer)
+		dev_str[USB_GADGET_MANUFACTURER_IDX].s = "";
+
 	kfree(cdev->def_manufacturer);
 	kfree(cdev);
 	set_gadget_data(gadget, NULL);
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index a22a892..aeb9f3c 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -1143,11 +1143,12 @@
 	NULL
 };
 
-int usb_os_desc_prepare_interf_dir(struct config_group *parent,
-				   int n_interf,
-				   struct usb_os_desc **desc,
-				   char **names,
-				   struct module *owner)
+struct config_group *usb_os_desc_prepare_interf_dir(
+		struct config_group *parent,
+		int n_interf,
+		struct usb_os_desc **desc,
+		char **names,
+		struct module *owner)
 {
 	struct config_group *os_desc_group;
 	struct config_item_type *os_desc_type, *interface_type;
@@ -1159,7 +1160,7 @@
 
 	char *vlabuf = kzalloc(vla_group_size(data_chunk), GFP_KERNEL);
 	if (!vlabuf)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	os_desc_group = vla_ptr(vlabuf, data_chunk, os_desc_group);
 	os_desc_type = vla_ptr(vlabuf, data_chunk, os_desc_type);
@@ -1184,7 +1185,7 @@
 		configfs_add_default_group(&d->group, os_desc_group);
 	}
 
-	return 0;
+	return os_desc_group;
 }
 EXPORT_SYMBOL(usb_os_desc_prepare_interf_dir);
 
diff --git a/drivers/usb/gadget/configfs.h b/drivers/usb/gadget/configfs.h
index 36c468c..540d5e9 100644
--- a/drivers/usb/gadget/configfs.h
+++ b/drivers/usb/gadget/configfs.h
@@ -5,11 +5,12 @@
 
 void unregister_gadget_item(struct config_item *item);
 
-int usb_os_desc_prepare_interf_dir(struct config_group *parent,
-				   int n_interf,
-				   struct usb_os_desc **desc,
-				   char **names,
-				   struct module *owner);
+struct config_group *usb_os_desc_prepare_interf_dir(
+		struct config_group *parent,
+		int n_interf,
+		struct usb_os_desc **desc,
+		char **names,
+		struct module *owner);
 
 static inline struct usb_os_desc *to_usb_os_desc(struct config_item *item)
 {
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 9990944..8b34258 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -46,7 +46,8 @@
 static void ffs_data_get(struct ffs_data *ffs);
 static void ffs_data_put(struct ffs_data *ffs);
 /* Creates new ffs_data object. */
-static struct ffs_data *__must_check ffs_data_new(void) __attribute__((malloc));
+static struct ffs_data *__must_check ffs_data_new(const char *dev_name)
+	__attribute__((malloc));
 
 /* Opened counter handling. */
 static void ffs_data_opened(struct ffs_data *ffs);
@@ -780,11 +781,12 @@
 					 struct usb_request *req)
 {
 	struct ffs_io_data *io_data = req->context;
+	struct ffs_data *ffs = io_data->ffs;
 
 	ENTER();
 
 	INIT_WORK(&io_data->work, ffs_user_copy_worker);
-	schedule_work(&io_data->work);
+	queue_work(ffs->io_completion_wq, &io_data->work);
 }
 
 static void __ffs_epfile_read_buffer_free(struct ffs_epfile *epfile)
@@ -1500,7 +1502,7 @@
 	if (unlikely(ret < 0))
 		return ERR_PTR(ret);
 
-	ffs = ffs_data_new();
+	ffs = ffs_data_new(dev_name);
 	if (unlikely(!ffs))
 		return ERR_PTR(-ENOMEM);
 	ffs->file_perms = data.perms;
@@ -1610,6 +1612,7 @@
 		BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
 		       waitqueue_active(&ffs->ep0req_completion.wait) ||
 		       waitqueue_active(&ffs->wait));
+		destroy_workqueue(ffs->io_completion_wq);
 		kfree(ffs->dev_name);
 		kfree(ffs);
 	}
@@ -1642,7 +1645,7 @@
 	ffs_data_put(ffs);
 }
 
-static struct ffs_data *ffs_data_new(void)
+static struct ffs_data *ffs_data_new(const char *dev_name)
 {
 	struct ffs_data *ffs = kzalloc(sizeof *ffs, GFP_KERNEL);
 	if (unlikely(!ffs))
@@ -1650,6 +1653,12 @@
 
 	ENTER();
 
+	ffs->io_completion_wq = alloc_ordered_workqueue("%s", 0, dev_name);
+	if (!ffs->io_completion_wq) {
+		kfree(ffs);
+		return NULL;
+	}
+
 	refcount_set(&ffs->ref, 1);
 	atomic_set(&ffs->opened, 0);
 	ffs->state = FFS_READ_DESCRIPTORS;
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index d6bd024..5153e29 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -307,8 +307,6 @@
 	struct completion	thread_notifier;
 	struct task_struct	*thread_task;
 
-	/* Callback functions. */
-	const struct fsg_operations	*ops;
 	/* Gadget's private data. */
 	void			*private_data;
 
@@ -2438,6 +2436,7 @@
 static int fsg_main_thread(void *common_)
 {
 	struct fsg_common	*common = common_;
+	int			i;
 
 	/*
 	 * Allow the thread to be killed by a signal, but set the signal mask
@@ -2476,21 +2475,16 @@
 	common->thread_task = NULL;
 	spin_unlock_irq(&common->lock);
 
-	if (!common->ops || !common->ops->thread_exits
-	 || common->ops->thread_exits(common) < 0) {
-		int i;
+	/* Eject media from all LUNs */
 
-		down_write(&common->filesem);
-		for (i = 0; i < ARRAY_SIZE(common->luns); i++) {
-			struct fsg_lun *curlun = common->luns[i];
-			if (!curlun || !fsg_lun_is_open(curlun))
-				continue;
+	down_write(&common->filesem);
+	for (i = 0; i < ARRAY_SIZE(common->luns); i++) {
+		struct fsg_lun *curlun = common->luns[i];
 
+		if (curlun && fsg_lun_is_open(curlun))
 			fsg_lun_close(curlun);
-			curlun->unit_attention_data = SS_MEDIUM_NOT_PRESENT;
-		}
-		up_write(&common->filesem);
 	}
+	up_write(&common->filesem);
 
 	/* Let fsg_unbind() know the thread has exited */
 	complete_and_exit(&common->thread_notifier, 0);
@@ -2681,13 +2675,6 @@
 }
 EXPORT_SYMBOL_GPL(fsg_common_remove_luns);
 
-void fsg_common_set_ops(struct fsg_common *common,
-			const struct fsg_operations *ops)
-{
-	common->ops = ops;
-}
-EXPORT_SYMBOL_GPL(fsg_common_set_ops);
-
 void fsg_common_free_buffers(struct fsg_common *common)
 {
 	_fsg_common_free_buffers(common->buffhds, common->fsg_num_buffers);
diff --git a/drivers/usb/gadget/function/f_mass_storage.h b/drivers/usb/gadget/function/f_mass_storage.h
index d390231..dc05ca0 100644
--- a/drivers/usb/gadget/function/f_mass_storage.h
+++ b/drivers/usb/gadget/function/f_mass_storage.h
@@ -60,17 +60,6 @@
 struct fsg_common;
 
 /* FSF callback functions */
-struct fsg_operations {
-	/*
-	 * Callback function to call when thread exits.  If no
-	 * callback is set or it returns value lower then zero MSF
-	 * will force eject all LUNs it operates on (including those
-	 * marked as non-removable or with prevent_medium_removal flag
-	 * set).
-	 */
-	int (*thread_exits)(struct fsg_common *common);
-};
-
 struct fsg_lun_opts {
 	struct config_group group;
 	struct fsg_lun *lun;
@@ -142,9 +131,6 @@
 
 void fsg_common_remove_luns(struct fsg_common *common);
 
-void fsg_common_set_ops(struct fsg_common *common,
-			const struct fsg_operations *ops);
-
 int fsg_common_create_lun(struct fsg_common *common, struct fsg_lun_config *cfg,
 			  unsigned int id, const char *name,
 			  const char **name_pfx);
diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c
index 8df244f..ea0da35a 100644
--- a/drivers/usb/gadget/function/f_printer.c
+++ b/drivers/usb/gadget/function/f_printer.c
@@ -555,6 +555,7 @@
 	size_t			size;	/* Amount of data in a TX request. */
 	size_t			bytes_copied = 0;
 	struct usb_request	*req;
+	int			value;
 
 	DBG(dev, "printer_write trying to send %d bytes\n", (int)len);
 
@@ -634,7 +635,11 @@
 			return -EAGAIN;
 		}
 
-		if (usb_ep_queue(dev->in_ep, req, GFP_ATOMIC)) {
+		/* here, we unlock, and only unlock, to avoid deadlock. */
+		spin_unlock(&dev->lock);
+		value = usb_ep_queue(dev->in_ep, req, GFP_ATOMIC);
+		spin_lock(&dev->lock);
+		if (value) {
 			list_add(&req->list, &dev->tx_reqs);
 			spin_unlock_irqrestore(&dev->lock, flags);
 			mutex_unlock(&dev->lock_printer_io);
diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c
index e1d5853..c7c5b3c 100644
--- a/drivers/usb/gadget/function/f_rndis.c
+++ b/drivers/usb/gadget/function/f_rndis.c
@@ -908,6 +908,7 @@
 			free_netdev(opts->net);
 	}
 
+	kfree(opts->rndis_interf_group);	/* single VLA chunk */
 	kfree(opts);
 }
 
@@ -916,6 +917,7 @@
 	struct f_rndis_opts *opts;
 	struct usb_os_desc *descs[1];
 	char *names[1];
+	struct config_group *rndis_interf_group;
 
 	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
 	if (!opts)
@@ -940,8 +942,14 @@
 	names[0] = "rndis";
 	config_group_init_type_name(&opts->func_inst.group, "",
 				    &rndis_func_type);
-	usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs,
-				       names, THIS_MODULE);
+	rndis_interf_group =
+		usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs,
+					       names, THIS_MODULE);
+	if (IS_ERR(rndis_interf_group)) {
+		rndis_free_inst(&opts->func_inst);
+		return ERR_CAST(rndis_interf_group);
+	}
+	opts->rndis_interf_group = rndis_interf_group;
 
 	return &opts->func_inst;
 }
diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h
index 540f1c4..79f70eb 100644
--- a/drivers/usb/gadget/function/u_fs.h
+++ b/drivers/usb/gadget/function/u_fs.h
@@ -279,6 +279,7 @@
 	}				file_perms;
 
 	struct eventfd_ctx *ffs_eventfd;
+	struct workqueue_struct *io_completion_wq;
 	bool no_disconnect;
 	struct work_struct reset_work;
 
diff --git a/drivers/usb/gadget/function/u_rndis.h b/drivers/usb/gadget/function/u_rndis.h
index a35ee3c..efdb7ac 100644
--- a/drivers/usb/gadget/function/u_rndis.h
+++ b/drivers/usb/gadget/function/u_rndis.h
@@ -26,6 +26,7 @@
 	bool				bound;
 	bool				borrowed_net;
 
+	struct config_group		*rndis_interf_group;
 	struct usb_os_desc		rndis_os_desc;
 	char				rndis_ext_compat_id[16];
 
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 684900f..5c28bee 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -28,7 +28,7 @@
 #include <linux/aio.h>
 #include <linux/uio.h>
 #include <linux/refcount.h>
-
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/moduleparam.h>
 
@@ -116,6 +116,7 @@
 struct dev_data {
 	spinlock_t			lock;
 	refcount_t			count;
+	int				udc_usage;
 	enum ep0_state			state;		/* P: lock */
 	struct usb_gadgetfs_event	event [N_EVENT];
 	unsigned			ev_next;
@@ -513,9 +514,9 @@
 		INIT_WORK(&priv->work, ep_user_copy_worker);
 		schedule_work(&priv->work);
 	}
-	spin_unlock(&epdata->dev->lock);
 
 	usb_ep_free_request(ep, req);
+	spin_unlock(&epdata->dev->lock);
 	put_ep(epdata);
 }
 
@@ -939,9 +940,11 @@
 			struct usb_request	*req = dev->req;
 
 			if ((retval = setup_req (ep, req, 0)) == 0) {
+				++dev->udc_usage;
 				spin_unlock_irq (&dev->lock);
 				retval = usb_ep_queue (ep, req, GFP_KERNEL);
 				spin_lock_irq (&dev->lock);
+				--dev->udc_usage;
 			}
 			dev->state = STATE_DEV_CONNECTED;
 
@@ -983,11 +986,14 @@
 				retval = -EIO;
 			else {
 				len = min (len, (size_t)dev->req->actual);
-// FIXME don't call this with the spinlock held ...
+				++dev->udc_usage;
+				spin_unlock_irq(&dev->lock);
 				if (copy_to_user (buf, dev->req->buf, len))
 					retval = -EFAULT;
 				else
 					retval = len;
+				spin_lock_irq(&dev->lock);
+				--dev->udc_usage;
 				clean_req (dev->gadget->ep0, dev->req);
 				/* NOTE userspace can't yet choose to stall */
 			}
@@ -1131,6 +1137,7 @@
 			retval = setup_req (dev->gadget->ep0, dev->req, len);
 			if (retval == 0) {
 				dev->state = STATE_DEV_CONNECTED;
+				++dev->udc_usage;
 				spin_unlock_irq (&dev->lock);
 				if (copy_from_user (dev->req->buf, buf, len))
 					retval = -EFAULT;
@@ -1142,6 +1149,7 @@
 						GFP_KERNEL);
 				}
 				spin_lock_irq(&dev->lock);
+				--dev->udc_usage;
 				if (retval < 0) {
 					clean_req (dev->gadget->ep0, dev->req);
 				} else
@@ -1243,9 +1251,21 @@
 	struct usb_gadget	*gadget = dev->gadget;
 	long ret = -ENOTTY;
 
-	if (gadget->ops->ioctl)
+	spin_lock_irq(&dev->lock);
+	if (dev->state == STATE_DEV_OPENED ||
+			dev->state == STATE_DEV_UNBOUND) {
+		/* Not bound to a UDC */
+	} else if (gadget->ops->ioctl) {
+		++dev->udc_usage;
+		spin_unlock_irq(&dev->lock);
+
 		ret = gadget->ops->ioctl (gadget, code, value);
 
+		spin_lock_irq(&dev->lock);
+		--dev->udc_usage;
+	}
+	spin_unlock_irq(&dev->lock);
+
 	return ret;
 }
 
@@ -1463,10 +1483,12 @@
 				if (value < 0)
 					break;
 
+				++dev->udc_usage;
 				spin_unlock (&dev->lock);
 				value = usb_ep_queue (gadget->ep0, dev->req,
 							GFP_KERNEL);
 				spin_lock (&dev->lock);
+				--dev->udc_usage;
 				if (value < 0) {
 					clean_req (gadget->ep0, dev->req);
 					break;
@@ -1490,8 +1512,12 @@
 		req->length = value;
 		req->zero = value < w_length;
 
+		++dev->udc_usage;
 		spin_unlock (&dev->lock);
 		value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL);
+		spin_lock(&dev->lock);
+		--dev->udc_usage;
+		spin_unlock(&dev->lock);
 		if (value < 0) {
 			DBG (dev, "ep_queue --> %d\n", value);
 			req->status = 0;
@@ -1518,21 +1544,24 @@
 		/* break link to FS */
 		ep = list_first_entry (&dev->epfiles, struct ep_data, epfiles);
 		list_del_init (&ep->epfiles);
+		spin_unlock_irq (&dev->lock);
+
 		dentry = ep->dentry;
 		ep->dentry = NULL;
 		parent = d_inode(dentry->d_parent);
 
 		/* break link to controller */
+		mutex_lock(&ep->lock);
 		if (ep->state == STATE_EP_ENABLED)
 			(void) usb_ep_disable (ep->ep);
 		ep->state = STATE_EP_UNBOUND;
 		usb_ep_free_request (ep->ep, ep->req);
 		ep->ep = NULL;
+		mutex_unlock(&ep->lock);
+
 		wake_up (&ep->wait);
 		put_ep (ep);
 
-		spin_unlock_irq (&dev->lock);
-
 		/* break link to dcache */
 		inode_lock(parent);
 		d_delete (dentry);
@@ -1603,6 +1632,11 @@
 
 	spin_lock_irq (&dev->lock);
 	dev->state = STATE_DEV_UNBOUND;
+	while (dev->udc_usage > 0) {
+		spin_unlock_irq(&dev->lock);
+		usleep_range(1000, 2000);
+		spin_lock_irq(&dev->lock);
+	}
 	spin_unlock_irq (&dev->lock);
 
 	destroy_ep_files (dev);
diff --git a/drivers/usb/gadget/legacy/mass_storage.c b/drivers/usb/gadget/legacy/mass_storage.c
index e99ab57..fcba597 100644
--- a/drivers/usb/gadget/legacy/mass_storage.c
+++ b/drivers/usb/gadget/legacy/mass_storage.c
@@ -107,15 +107,6 @@
 
 FSG_MODULE_PARAMETERS(/* no prefix */, mod_data);
 
-static unsigned long msg_registered;
-static void msg_cleanup(void);
-
-static int msg_thread_exits(struct fsg_common *common)
-{
-	msg_cleanup();
-	return 0;
-}
-
 static int msg_do_config(struct usb_configuration *c)
 {
 	struct fsg_opts *opts;
@@ -154,9 +145,6 @@
 
 static int msg_bind(struct usb_composite_dev *cdev)
 {
-	static const struct fsg_operations ops = {
-		.thread_exits = msg_thread_exits,
-	};
 	struct fsg_opts *opts;
 	struct fsg_config config;
 	int status;
@@ -173,8 +161,6 @@
 	if (status)
 		goto fail;
 
-	fsg_common_set_ops(opts->common, &ops);
-
 	status = fsg_common_set_cdev(opts->common, cdev, config.can_stall);
 	if (status)
 		goto fail_set_cdev;
@@ -256,18 +242,12 @@
 
 static int __init msg_init(void)
 {
-	int ret;
-
-	ret = usb_composite_probe(&msg_driver);
-	set_bit(0, &msg_registered);
-
-	return ret;
+	return usb_composite_probe(&msg_driver);
 }
 module_init(msg_init);
 
-static void msg_cleanup(void)
+static void __exit msg_cleanup(void)
 {
-	if (test_and_clear_bit(0, &msg_registered))
-		usb_composite_unregister(&msg_driver);
+	usb_composite_unregister(&msg_driver);
 }
 module_exit(msg_cleanup);
diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig
index 7cd5c96..1e95670 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -273,6 +273,7 @@
 config USB_SNP_UDC_PLAT
 	tristate "Synopsys USB 2.0 Device controller"
 	depends on USB_GADGET && OF && HAS_DMA
+	depends on EXTCON || EXTCON=n
 	select USB_GADGET_DUALSPEED
 	select USB_SNP_CORE
 	default ARCH_BCM_IPROC
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 98d7140..a884c02 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -29,6 +29,8 @@
 #include <linux/of_gpio.h>
 
 #include "atmel_usba_udc.h"
+#define USBA_VBUS_IRQFLAGS (IRQF_ONESHOT \
+			   | IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING)
 
 #ifdef CONFIG_USB_GADGET_DEBUG_FS
 #include <linux/debugfs.h>
@@ -2361,7 +2363,7 @@
 					IRQ_NOAUTOEN);
 			ret = devm_request_threaded_irq(&pdev->dev,
 					gpio_to_irq(udc->vbus_pin), NULL,
-					usba_vbus_irq_thread, IRQF_ONESHOT,
+					usba_vbus_irq_thread, USBA_VBUS_IRQFLAGS,
 					"atmel_usba_udc", udc);
 			if (ret) {
 				udc->vbus_pin = -ENODEV;
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 75c51ca..d41d07a 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1320,8 +1320,7 @@
 	udc->dev.driver = &driver->driver;
 	udc->gadget->dev.driver = &driver->driver;
 
-	if (driver->max_speed < udc->gadget->max_speed)
-		usb_gadget_udc_set_speed(udc, driver->max_speed);
+	usb_gadget_udc_set_speed(udc, driver->max_speed);
 
 	ret = driver->bind(udc->gadget, driver);
 	if (ret)
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index a030d79..f04e91e 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -237,6 +237,8 @@
 
 	struct usb_device		*udev;
 	struct list_head		urbp_list;
+	struct urbp			*next_frame_urbp;
+
 	u32				stream_en_ep;
 	u8				num_stream[30 / 2];
 
@@ -253,11 +255,13 @@
 	 */
 	struct dummy_ep			ep[DUMMY_ENDPOINTS];
 	int				address;
+	int				callback_usage;
 	struct usb_gadget		gadget;
 	struct usb_gadget_driver	*driver;
 	struct dummy_request		fifo_req;
 	u8				fifo_buf[FIFO_SIZE];
 	u16				devstatus;
+	unsigned			ints_enabled:1;
 	unsigned			udc_suspended:1;
 	unsigned			pullup:1;
 
@@ -375,11 +379,10 @@
 			     USB_PORT_STAT_CONNECTION) == 0)
 				dum_hcd->port_status |=
 					(USB_PORT_STAT_C_CONNECTION << 16);
-			if ((dum_hcd->port_status &
-			     USB_PORT_STAT_ENABLE) == 1 &&
-				(dum_hcd->port_status &
-				 USB_SS_PORT_LS_U0) == 1 &&
-				dum_hcd->rh_state != DUMMY_RH_SUSPENDED)
+			if ((dum_hcd->port_status & USB_PORT_STAT_ENABLE) &&
+			    (dum_hcd->port_status &
+			     USB_PORT_STAT_LINK_STATE) == USB_SS_PORT_LS_U0 &&
+			    dum_hcd->rh_state != DUMMY_RH_SUSPENDED)
 				dum_hcd->active = 1;
 		}
 	} else {
@@ -416,6 +419,7 @@
 static void set_link_state(struct dummy_hcd *dum_hcd)
 {
 	struct dummy *dum = dum_hcd->dum;
+	unsigned int power_bit;
 
 	dum_hcd->active = 0;
 	if (dum->pullup)
@@ -426,32 +430,43 @@
 			return;
 
 	set_link_state_by_speed(dum_hcd);
+	power_bit = (dummy_hcd_to_hcd(dum_hcd)->speed == HCD_USB3 ?
+			USB_SS_PORT_STAT_POWER : USB_PORT_STAT_POWER);
 
 	if ((dum_hcd->port_status & USB_PORT_STAT_ENABLE) == 0 ||
 	     dum_hcd->active)
 		dum_hcd->resuming = 0;
 
 	/* Currently !connected or in reset */
-	if ((dum_hcd->port_status & USB_PORT_STAT_CONNECTION) == 0 ||
+	if ((dum_hcd->port_status & power_bit) == 0 ||
 			(dum_hcd->port_status & USB_PORT_STAT_RESET) != 0) {
-		unsigned disconnect = USB_PORT_STAT_CONNECTION &
+		unsigned int disconnect = power_bit &
 				dum_hcd->old_status & (~dum_hcd->port_status);
-		unsigned reset = USB_PORT_STAT_RESET &
+		unsigned int reset = USB_PORT_STAT_RESET &
 				(~dum_hcd->old_status) & dum_hcd->port_status;
 
 		/* Report reset and disconnect events to the driver */
-		if (dum->driver && (disconnect || reset)) {
+		if (dum->ints_enabled && (disconnect || reset)) {
 			stop_activity(dum);
+			++dum->callback_usage;
+			spin_unlock(&dum->lock);
 			if (reset)
 				usb_gadget_udc_reset(&dum->gadget, dum->driver);
 			else
 				dum->driver->disconnect(&dum->gadget);
+			spin_lock(&dum->lock);
+			--dum->callback_usage;
 		}
-	} else if (dum_hcd->active != dum_hcd->old_active) {
+	} else if (dum_hcd->active != dum_hcd->old_active &&
+			dum->ints_enabled) {
+		++dum->callback_usage;
+		spin_unlock(&dum->lock);
 		if (dum_hcd->old_active && dum->driver->suspend)
 			dum->driver->suspend(&dum->gadget);
 		else if (!dum_hcd->old_active &&  dum->driver->resume)
 			dum->driver->resume(&dum->gadget);
+		spin_lock(&dum->lock);
+		--dum->callback_usage;
 	}
 
 	dum_hcd->old_status = dum_hcd->port_status;
@@ -972,8 +987,11 @@
 	 * can't enumerate without help from the driver we're binding.
 	 */
 
+	spin_lock_irq(&dum->lock);
 	dum->devstatus = 0;
 	dum->driver = driver;
+	dum->ints_enabled = 1;
+	spin_unlock_irq(&dum->lock);
 
 	return 0;
 }
@@ -984,6 +1002,16 @@
 	struct dummy		*dum = dum_hcd->dum;
 
 	spin_lock_irq(&dum->lock);
+	dum->ints_enabled = 0;
+	stop_activity(dum);
+
+	/* emulate synchronize_irq(): wait for callbacks to finish */
+	while (dum->callback_usage > 0) {
+		spin_unlock_irq(&dum->lock);
+		usleep_range(1000, 2000);
+		spin_lock_irq(&dum->lock);
+	}
+
 	dum->driver = NULL;
 	spin_unlock_irq(&dum->lock);
 
@@ -1037,7 +1065,12 @@
 	memzero_explicit(&dum->gadget, sizeof(struct usb_gadget));
 	dum->gadget.name = gadget_name;
 	dum->gadget.ops = &dummy_ops;
-	dum->gadget.max_speed = USB_SPEED_SUPER;
+	if (mod_data.is_super_speed)
+		dum->gadget.max_speed = USB_SPEED_SUPER;
+	else if (mod_data.is_high_speed)
+		dum->gadget.max_speed = USB_SPEED_HIGH;
+	else
+		dum->gadget.max_speed = USB_SPEED_FULL;
 
 	dum->gadget.dev.parent = &pdev->dev;
 	init_dummy_udc_hw(dum);
@@ -1246,6 +1279,8 @@
 
 	list_add_tail(&urbp->urbp_list, &dum_hcd->urbp_list);
 	urb->hcpriv = urbp;
+	if (!dum_hcd->next_frame_urbp)
+		dum_hcd->next_frame_urbp = urbp;
 	if (usb_pipetype(urb->pipe) == PIPE_CONTROL)
 		urb->error_count = 1;		/* mark as a new urb */
 
@@ -1521,6 +1556,8 @@
 	if (!is_active((dum->gadget.speed == USB_SPEED_SUPER ?
 			dum->ss_hcd : dum->hs_hcd)))
 		return NULL;
+	if (!dum->ints_enabled)
+		return NULL;
 	if ((address & ~USB_DIR_IN) == 0)
 		return &dum->ep[0];
 	for (i = 1; i < DUMMY_ENDPOINTS; i++) {
@@ -1762,6 +1799,7 @@
 		spin_unlock_irqrestore(&dum->lock, flags);
 		return;
 	}
+	dum_hcd->next_frame_urbp = NULL;
 
 	for (i = 0; i < DUMMY_ENDPOINTS; i++) {
 		if (!ep_info[i].name)
@@ -1778,6 +1816,10 @@
 		int			type;
 		int			status = -EINPROGRESS;
 
+		/* stop when we reach URBs queued after the timer interrupt */
+		if (urbp == dum_hcd->next_frame_urbp)
+			break;
+
 		urb = urbp->urb;
 		if (urb->unlinked)
 			goto return_urb;
@@ -1857,10 +1899,12 @@
 			 * until setup() returns; no reentrancy issues etc.
 			 */
 			if (value > 0) {
+				++dum->callback_usage;
 				spin_unlock(&dum->lock);
 				value = dum->driver->setup(&dum->gadget,
 						&setup);
 				spin_lock(&dum->lock);
+				--dum->callback_usage;
 
 				if (value >= 0) {
 					/* no delays (max 64KB data stage) */
@@ -2561,8 +2605,6 @@
 	.product_desc =		"Dummy host controller",
 	.hcd_priv_size =	sizeof(struct dummy_hcd),
 
-	.flags =		HCD_USB3 | HCD_SHARED,
-
 	.reset =		dummy_setup,
 	.start =		dummy_start,
 	.stop =			dummy_stop,
@@ -2591,8 +2633,12 @@
 	dev_info(&pdev->dev, "%s, driver " DRIVER_VERSION "\n", driver_desc);
 	dum = *((void **)dev_get_platdata(&pdev->dev));
 
-	if (!mod_data.is_super_speed)
+	if (mod_data.is_super_speed)
+		dummy_hcd.flags = HCD_USB3 | HCD_SHARED;
+	else if (mod_data.is_high_speed)
 		dummy_hcd.flags = HCD_USB2;
+	else
+		dummy_hcd.flags = HCD_USB11;
 	hs_hcd = usb_create_hcd(&dummy_hcd, &pdev->dev, dev_name(&pdev->dev));
 	if (!hs_hcd)
 		return -ENOMEM;
diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c
index df37c1e..63a2061 100644
--- a/drivers/usb/gadget/udc/renesas_usb3.c
+++ b/drivers/usb/gadget/udc/renesas_usb3.c
@@ -1038,7 +1038,7 @@
 			usb3_ep->ep.maxpacket);
 	u8 *buf = usb3_req->req.buf + usb3_req->req.actual;
 	u32 tmp = 0;
-	bool is_last;
+	bool is_last = !len ? true : false;
 
 	if (usb3_wait_pipe_status(usb3_ep, PX_STA_BUFSTS) < 0)
 		return -EBUSY;
@@ -1059,7 +1059,8 @@
 		usb3_write(usb3, tmp, fifo_reg);
 	}
 
-	is_last = usb3_is_transfer_complete(usb3_ep, usb3_req);
+	if (!is_last)
+		is_last = usb3_is_transfer_complete(usb3_ep, usb3_req);
 	/* Send the data */
 	usb3_set_px_con_send(usb3_ep, len, is_last);
 
@@ -1150,7 +1151,8 @@
 		usb3_set_p0_con_for_ctrl_read_data(usb3);
 	} else {
 		usb3_clear_bit(usb3, P0_MOD_DIR, USB3_P0_MOD);
-		usb3_set_p0_con_for_ctrl_write_data(usb3);
+		if (usb3_req->req.length)
+			usb3_set_p0_con_for_ctrl_write_data(usb3);
 	}
 
 	usb3_p0_xfer(usb3_ep, usb3_req);
@@ -2053,7 +2055,16 @@
 static u32 usb3_calc_rammap_val(struct renesas_usb3_ep *usb3_ep,
 				const struct usb_endpoint_descriptor *desc)
 {
-	return usb3_ep->rammap_val | PN_RAMMAP_MPKT(usb_endpoint_maxp(desc));
+	int i;
+	const u32 max_packet_array[] = {8, 16, 32, 64, 512};
+	u32 mpkt = PN_RAMMAP_MPKT(1024);
+
+	for (i = 0; i < ARRAY_SIZE(max_packet_array); i++) {
+		if (usb_endpoint_maxp(desc) <= max_packet_array[i])
+			mpkt = PN_RAMMAP_MPKT(max_packet_array[i]);
+	}
+
+	return usb3_ep->rammap_val | mpkt;
 }
 
 static int usb3_enable_pipe_n(struct renesas_usb3_ep *usb3_ep,
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 658d9d1..6dda362 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -447,7 +447,7 @@
 		if ((value & ASMT_CONTROL_WRITE_BIT) == 0)
 			return 0;
 
-		usleep_range(40, 60);
+		udelay(50);
 	}
 
 	dev_warn(&pdev->dev, "%s: check_write_ready timeout", __func__);
@@ -1022,7 +1022,7 @@
  *
  * Takes care of the handoff between the Pre-OS (i.e. BIOS) and the OS.
  * It signals to the BIOS that the OS wants control of the host controller,
- * and then waits 5 seconds for the BIOS to hand over control.
+ * and then waits 1 second for the BIOS to hand over control.
  * If we timeout, assume the BIOS is broken and take control anyway.
  */
 static void quirk_usb_handoff_xhci(struct pci_dev *pdev)
@@ -1069,9 +1069,9 @@
 	if (val & XHCI_HC_BIOS_OWNED) {
 		writel(val | XHCI_HC_OS_OWNED, base + ext_cap_offset);
 
-		/* Wait for 5 seconds with 10 microsecond polling interval */
+		/* Wait for 1 second with 10 microsecond polling interval */
 		timeout = handshake(base + ext_cap_offset, XHCI_HC_BIOS_OWNED,
-				0, 5000, 10);
+				0, 1000000, 10);
 
 		/* Assume a buggy BIOS and take HC ownership anyway */
 		if (timeout) {
@@ -1100,7 +1100,7 @@
 	 * operational or runtime registers.  Wait 5 seconds and no more.
 	 */
 	timeout = handshake(op_reg_base + XHCI_STS_OFFSET, XHCI_STS_CNR, 0,
-			5000, 10);
+			5000000, 10);
 	/* Assume a buggy HC and start HC initialization anyway */
 	if (timeout) {
 		val = readl(op_reg_base + XHCI_STS_OFFSET);
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index ad89a6d..a2336de 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -112,7 +112,7 @@
 
 	/* If PSI table exists, add the custom speed attributes from it */
 	if (usb3_1 && xhci->usb3_rhub.psi_count) {
-		u32 ssp_cap_base, bm_attrib, psi;
+		u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp;
 		int offset;
 
 		ssp_cap_base = USB_DT_BOS_SIZE + USB_DT_USB_SS_CAP_SIZE;
@@ -139,6 +139,15 @@
 		for (i = 0; i < xhci->usb3_rhub.psi_count; i++) {
 			psi = xhci->usb3_rhub.psi[i];
 			psi &= ~USB_SSP_SUBLINK_SPEED_RSVD;
+			psi_exp = XHCI_EXT_PORT_PSIE(psi);
+			psi_mant = XHCI_EXT_PORT_PSIM(psi);
+
+			/* Shift to Gbps and set SSP Link BIT(14) if 10Gpbs */
+			for (; psi_exp < 3; psi_exp++)
+				psi_mant /= 1000;
+			if (psi_mant >= 10)
+				psi |= BIT(14);
+
 			if ((psi & PLT_MASK) == PLT_SYM) {
 			/* Symmetric, create SSA RX and TX from one PSI entry */
 				put_unaligned_le32(psi, &buf[offset]);
@@ -411,14 +420,25 @@
 						     GFP_NOWAIT);
 			if (!command) {
 				spin_unlock_irqrestore(&xhci->lock, flags);
-				xhci_free_command(xhci, cmd);
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto cmd_cleanup;
 			}
-			xhci_queue_stop_endpoint(xhci, command, slot_id, i,
-						 suspend);
+
+			ret = xhci_queue_stop_endpoint(xhci, command, slot_id,
+						       i, suspend);
+			if (ret) {
+				spin_unlock_irqrestore(&xhci->lock, flags);
+				xhci_free_command(xhci, command);
+				goto cmd_cleanup;
+			}
 		}
 	}
-	xhci_queue_stop_endpoint(xhci, cmd, slot_id, 0, suspend);
+	ret = xhci_queue_stop_endpoint(xhci, cmd, slot_id, 0, suspend);
+	if (ret) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		goto cmd_cleanup;
+	}
+
 	xhci_ring_cmd_db(xhci);
 	spin_unlock_irqrestore(&xhci->lock, flags);
 
@@ -430,6 +450,8 @@
 		xhci_warn(xhci, "Timeout while waiting for stop endpoint command\n");
 		ret = -ETIME;
 	}
+
+cmd_cleanup:
 	xhci_free_command(xhci, cmd);
 	return ret;
 }
@@ -1506,9 +1528,6 @@
 				t2 |= PORT_WKOC_E | PORT_WKCONN_E;
 				t2 &= ~PORT_WKDISC_E;
 			}
-			if ((xhci->quirks & XHCI_U2_DISABLE_WAKE) &&
-			    (hcd->speed < HCD_USB3))
-				t2 &= ~PORT_WAKE_BITS;
 		} else
 			t2 &= ~PORT_WAKE_BITS;
 
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 8071c8f..76f3929 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -54,11 +54,6 @@
 #define PCI_DEVICE_ID_INTEL_APL_XHCI			0x5aa8
 #define PCI_DEVICE_ID_INTEL_DNV_XHCI			0x19d0
 
-#define PCI_DEVICE_ID_AMD_PROMONTORYA_4			0x43b9
-#define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba
-#define PCI_DEVICE_ID_AMD_PROMONTORYA_2			0x43bb
-#define PCI_DEVICE_ID_AMD_PROMONTORYA_1			0x43bc
-
 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI		0x1142
 
 static const char hcd_name[] = "xhci_hcd";
@@ -142,13 +137,6 @@
 	if (pdev->vendor == PCI_VENDOR_ID_AMD)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 
-	if ((pdev->vendor == PCI_VENDOR_ID_AMD) &&
-		((pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4) ||
-		(pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_3) ||
-		(pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2) ||
-		(pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_1)))
-		xhci->quirks |= XHCI_U2_DISABLE_WAKE;
-
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
 		xhci->quirks |= XHCI_INTEL_HOST;
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 163bafd..1cb6eae 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -178,14 +178,18 @@
 	 * 2. xhci_plat is child of a device from firmware (dwc3-plat)
 	 * 3. xhci_plat is grandchild of a pci device (dwc3-pci)
 	 */
-	sysdev = &pdev->dev;
-	if (sysdev->parent && !sysdev->of_node && sysdev->parent->of_node)
-		sysdev = sysdev->parent;
+	for (sysdev = &pdev->dev; sysdev; sysdev = sysdev->parent) {
+		if (is_of_node(sysdev->fwnode) ||
+			is_acpi_device_node(sysdev->fwnode))
+			break;
 #ifdef CONFIG_PCI
-	else if (sysdev->parent && sysdev->parent->parent &&
-		 sysdev->parent->parent->bus == &pci_bus_type)
-		sysdev = sysdev->parent->parent;
+		else if (sysdev->bus == &pci_bus_type)
+			break;
 #endif
+	}
+
+	if (!sysdev)
+		sysdev = &pdev->dev;
 
 	/* Try to set 64-bit DMA first */
 	if (WARN_ON(!sysdev->dma_mask))
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index a944365..82c746e 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1309,6 +1309,7 @@
 void xhci_cleanup_command_queue(struct xhci_hcd *xhci)
 {
 	struct xhci_command *cur_cmd, *tmp_cmd;
+	xhci->current_cmd = NULL;
 	list_for_each_entry_safe(cur_cmd, tmp_cmd, &xhci->cmd_list, cmd_list)
 		xhci_complete_del_and_free_cmd(cur_cmd, COMP_COMMAND_ABORTED);
 }
@@ -2579,15 +2580,21 @@
 				(struct xhci_generic_trb *) ep_trb);
 
 		/*
-		 * No-op TRB should not trigger interrupts.
-		 * If ep_trb is a no-op TRB, it means the
-		 * corresponding TD has been cancelled. Just ignore
-		 * the TD.
+		 * No-op TRB could trigger interrupts in a case where
+		 * a URB was killed and a STALL_ERROR happens right
+		 * after the endpoint ring stopped. Reset the halted
+		 * endpoint. Otherwise, the endpoint remains stalled
+		 * indefinitely.
 		 */
 		if (trb_is_noop(ep_trb)) {
-			xhci_dbg(xhci,
-				 "ep_trb is a no-op TRB. Skip it for slot %u ep %u\n",
-				 slot_id, ep_index);
+			if (trb_comp_code == COMP_STALL_ERROR ||
+			    xhci_requires_manual_halt_cleanup(xhci, ep_ctx,
+							      trb_comp_code))
+				xhci_cleanup_halted_endpoint(xhci, slot_id,
+							     ep_index,
+							     ep_ring->stream_id,
+							     td, ep_trb,
+							     EP_HARD_RESET);
 			goto cleanup;
 		}
 
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index b2ff1ff..51535ba 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1703,7 +1703,8 @@
 	if (xhci->quirks & XHCI_MTK_HOST) {
 		ret = xhci_mtk_add_ep_quirk(hcd, udev, ep);
 		if (ret < 0) {
-			xhci_free_endpoint_ring(xhci, virt_dev, ep_index);
+			xhci_ring_free(xhci, virt_dev->eps[ep_index].new_ring);
+			virt_dev->eps[ep_index].new_ring = NULL;
 			return ret;
 		}
 	}
@@ -4804,7 +4805,8 @@
 		 */
 		hcd->has_tt = 1;
 	} else {
-		if (xhci->sbrn == 0x31) {
+		/* Some 3.1 hosts return sbrn 0x30, can't rely on sbrn alone */
+		if (xhci->sbrn == 0x31 || xhci->usb3_rhub.min_rev >= 1) {
 			xhci_info(xhci, "Host supports USB 3.1 Enhanced SuperSpeed\n");
 			hcd->speed = HCD_USB31;
 			hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 2abaa4d..2b48aa4 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -735,6 +735,8 @@
 #define EP_MAXPSTREAMS(p)	(((p) << 10) & EP_MAXPSTREAMS_MASK)
 /* Endpoint is set up with a Linear Stream Array (vs. Secondary Stream Array) */
 #define	EP_HAS_LSA		(1 << 15)
+/* hosts with LEC=1 use bits 31:24 as ESIT high bits. */
+#define CTX_TO_MAX_ESIT_PAYLOAD_HI(p)	(((p) >> 24) & 0xff)
 
 /* ep_info2 bitmasks */
 /*
@@ -1681,7 +1683,7 @@
 
 static inline unsigned int hcd_index(struct usb_hcd *hcd)
 {
-	if (hcd->speed == HCD_USB3)
+	if (hcd->speed >= HCD_USB3)
 		return 0;
 	else
 		return 1;
@@ -1826,7 +1828,7 @@
 /* For controller with a broken Port Disable implementation */
 #define XHCI_BROKEN_PORT_PED	(1 << 25)
 #define XHCI_LIMIT_ENDPOINT_INTERVAL_7	(1 << 26)
-#define XHCI_U2_DISABLE_WAKE	(1 << 27)
+/* Reserved. It was XHCI_U2_DISABLE_WAKE */
 #define XHCI_ASMEDIA_MODIFY_FLOWCONTROL	(1 << 28)
 
 	unsigned int		num_active_eps;
@@ -2540,8 +2542,8 @@
 	u8 lsa;
 	u8 hid;
 
-	esit = EP_MAX_ESIT_PAYLOAD_HI(info) << 16 |
-		EP_MAX_ESIT_PAYLOAD_LO(tx_info);
+	esit = CTX_TO_MAX_ESIT_PAYLOAD_HI(info) << 16 |
+		CTX_TO_MAX_ESIT_PAYLOAD(tx_info);
 
 	ep_state = info & EP_STATE_MASK;
 	max_pstr = info & EP_MAXPSTREAMS_MASK;
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index eee82ca..b3fc602 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -202,12 +202,13 @@
 			return tmp;
 	}
 
-	if (in) {
+	if (in)
 		dev->in_pipe = usb_rcvbulkpipe(udev,
 			in->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK);
+	if (out)
 		dev->out_pipe = usb_sndbulkpipe(udev,
 			out->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK);
-	}
+
 	if (iso_in) {
 		dev->iso_in = &iso_in->desc;
 		dev->in_iso_pipe = usb_rcvisocpipe(udev,
@@ -1964,6 +1965,9 @@
 	int			status = 0;
 	struct urb		*urbs[param->sglen];
 
+	if (!param->sglen || param->iterations > UINT_MAX / param->sglen)
+		return -EINVAL;
+
 	memset(&context, 0, sizeof(context));
 	context.count = param->iterations * param->sglen;
 	context.dev = dev;
@@ -2087,6 +2091,8 @@
 
 	if (param->iterations <= 0)
 		return -EINVAL;
+	if (param->sglen > MAX_SGLEN)
+		return -EINVAL;
 	/*
 	 * Just a bunch of test cases that every HCD is expected to handle.
 	 *
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 0296920..ff5a1a8 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -906,7 +906,7 @@
 	 */
 	if (int_usb & MUSB_INTR_RESET) {
 		handled = IRQ_HANDLED;
-		if (devctl & MUSB_DEVCTL_HM) {
+		if (is_host_active(musb)) {
 			/*
 			 * When BABBLE happens what we can depends on which
 			 * platform MUSB is running, because some platforms
@@ -916,9 +916,7 @@
 			 * drop the session.
 			 */
 			dev_err(musb->controller, "Babble\n");
-
-			if (is_host_active(musb))
-				musb_recover_from_babble(musb);
+			musb_recover_from_babble(musb);
 		} else {
 			musb_dbg(musb, "BUS RESET as %s",
 				usb_otg_state_string(musb->xceiv->otg->state));
@@ -1861,22 +1859,22 @@
 		MUSB_DEVCTL_HR;
 	switch (devctl & ~s) {
 	case MUSB_QUIRK_B_INVALID_VBUS_91:
-		if (musb->quirk_retries--) {
+		if (musb->quirk_retries && !musb->flush_irq_work) {
 			musb_dbg(musb,
 				 "Poll devctl on invalid vbus, assume no session");
 			schedule_delayed_work(&musb->irq_work,
 					      msecs_to_jiffies(1000));
-
+			musb->quirk_retries--;
 			return;
 		}
 		/* fall through */
 	case MUSB_QUIRK_A_DISCONNECT_19:
-		if (musb->quirk_retries--) {
+		if (musb->quirk_retries && !musb->flush_irq_work) {
 			musb_dbg(musb,
 				 "Poll devctl on possible host mode disconnect");
 			schedule_delayed_work(&musb->irq_work,
 					      msecs_to_jiffies(1000));
-
+			musb->quirk_retries--;
 			return;
 		}
 		if (!musb->session)
@@ -2681,8 +2679,15 @@
 
 	musb_platform_disable(musb);
 	musb_disable_interrupts(musb);
+
+	musb->flush_irq_work = true;
+	while (flush_delayed_work(&musb->irq_work))
+		;
+	musb->flush_irq_work = false;
+
 	if (!(musb->io.quirks & MUSB_PRESERVE_SESSION))
 		musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
+
 	WARN_ON(!list_empty(&musb->pending_list));
 
 	spin_lock_irqsave(&musb->lock, flags);
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index c748f4a..20f4614 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -428,6 +428,8 @@
 	unsigned		test_mode:1;
 	unsigned		softconnect:1;
 
+	unsigned		flush_irq_work:1;
+
 	u8			address;
 	u8			test_mode_nr;
 	u16			ackpend;		/* ep0 */
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index ba25528..1ec0a49 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -26,15 +26,28 @@
 
 #define MUSB_DMA_NUM_CHANNELS 15
 
+#define DA8XX_USB_MODE		0x10
+#define DA8XX_USB_AUTOREQ	0x14
+#define DA8XX_USB_TEARDOWN	0x1c
+
+#define DA8XX_DMA_NUM_CHANNELS 4
+
 struct cppi41_dma_controller {
 	struct dma_controller controller;
-	struct cppi41_dma_channel rx_channel[MUSB_DMA_NUM_CHANNELS];
-	struct cppi41_dma_channel tx_channel[MUSB_DMA_NUM_CHANNELS];
+	struct cppi41_dma_channel *rx_channel;
+	struct cppi41_dma_channel *tx_channel;
 	struct hrtimer early_tx;
 	struct list_head early_tx_list;
 	u32 rx_mode;
 	u32 tx_mode;
 	u32 auto_req;
+
+	u32 tdown_reg;
+	u32 autoreq_reg;
+
+	void (*set_dma_mode)(struct cppi41_dma_channel *cppi41_channel,
+			     unsigned int mode);
+	u8 num_channels;
 };
 
 static void save_rx_toggle(struct cppi41_dma_channel *cppi41_channel)
@@ -349,6 +362,32 @@
 	}
 }
 
+static void da8xx_set_dma_mode(struct cppi41_dma_channel *cppi41_channel,
+		unsigned int mode)
+{
+	struct cppi41_dma_controller *controller = cppi41_channel->controller;
+	struct musb *musb = controller->controller.musb;
+	unsigned int shift;
+	u32 port;
+	u32 new_mode;
+	u32 old_mode;
+
+	old_mode = controller->tx_mode;
+	port = cppi41_channel->port_num;
+
+	shift = (port - 1) * 4;
+	if (!cppi41_channel->is_tx)
+		shift += 16;
+	new_mode = old_mode & ~(3 << shift);
+	new_mode |= mode << shift;
+
+	if (new_mode == old_mode)
+		return;
+	controller->tx_mode = new_mode;
+	musb_writel(musb->ctrl_base, DA8XX_USB_MODE, new_mode);
+}
+
+
 static void cppi41_set_autoreq_mode(struct cppi41_dma_channel *cppi41_channel,
 		unsigned mode)
 {
@@ -364,8 +403,8 @@
 	if (new_mode == old_mode)
 		return;
 	controller->auto_req = new_mode;
-	musb_writel(controller->controller.musb->ctrl_base, USB_CTRL_AUTOREQ,
-		    new_mode);
+	musb_writel(controller->controller.musb->ctrl_base,
+		    controller->autoreq_reg, new_mode);
 }
 
 static bool cppi41_configure_channel(struct dma_channel *channel,
@@ -373,6 +412,7 @@
 				dma_addr_t dma_addr, u32 len)
 {
 	struct cppi41_dma_channel *cppi41_channel = channel->private_data;
+	struct cppi41_dma_controller *controller = cppi41_channel->controller;
 	struct dma_chan *dc = cppi41_channel->dc;
 	struct dma_async_tx_descriptor *dma_desc;
 	enum dma_transfer_direction direction;
@@ -398,7 +438,7 @@
 			musb_writel(musb->ctrl_base,
 				RNDIS_REG(cppi41_channel->port_num), len);
 			/* gen rndis */
-			cppi41_set_dma_mode(cppi41_channel,
+			controller->set_dma_mode(cppi41_channel,
 					EP_MODE_DMA_GEN_RNDIS);
 
 			/* auto req */
@@ -407,14 +447,15 @@
 		} else {
 			musb_writel(musb->ctrl_base,
 					RNDIS_REG(cppi41_channel->port_num), 0);
-			cppi41_set_dma_mode(cppi41_channel,
+			controller->set_dma_mode(cppi41_channel,
 					EP_MODE_DMA_TRANSPARENT);
 			cppi41_set_autoreq_mode(cppi41_channel,
 					EP_MODE_AUTOREQ_NONE);
 		}
 	} else {
 		/* fallback mode */
-		cppi41_set_dma_mode(cppi41_channel, EP_MODE_DMA_TRANSPARENT);
+		controller->set_dma_mode(cppi41_channel,
+				EP_MODE_DMA_TRANSPARENT);
 		cppi41_set_autoreq_mode(cppi41_channel, EP_MODE_AUTOREQ_NONE);
 		len = min_t(u32, packet_sz, len);
 	}
@@ -445,7 +486,7 @@
 	struct cppi41_dma_channel *cppi41_channel = NULL;
 	u8 ch_num = hw_ep->epnum - 1;
 
-	if (ch_num >= MUSB_DMA_NUM_CHANNELS)
+	if (ch_num >= controller->num_channels)
 		return NULL;
 
 	if (is_tx)
@@ -581,12 +622,13 @@
 
 	do {
 		if (is_tx)
-			musb_writel(musb->ctrl_base, USB_TDOWN, tdbit);
+			musb_writel(musb->ctrl_base, controller->tdown_reg,
+				    tdbit);
 		ret = dmaengine_terminate_all(cppi41_channel->dc);
 	} while (ret == -EAGAIN);
 
 	if (is_tx) {
-		musb_writel(musb->ctrl_base, USB_TDOWN, tdbit);
+		musb_writel(musb->ctrl_base, controller->tdown_reg, tdbit);
 
 		csr = musb_readw(epio, MUSB_TXCSR);
 		if (csr & MUSB_TXCSR_TXPKTRDY) {
@@ -604,7 +646,7 @@
 	struct dma_chan *dc;
 	int i;
 
-	for (i = 0; i < MUSB_DMA_NUM_CHANNELS; i++) {
+	for (i = 0; i < ctrl->num_channels; i++) {
 		dc = ctrl->tx_channel[i].dc;
 		if (dc)
 			dma_release_channel(dc);
@@ -656,7 +698,7 @@
 			goto err;
 
 		ret = -EINVAL;
-		if (port > MUSB_DMA_NUM_CHANNELS || !port)
+		if (port > controller->num_channels || !port)
 			goto err;
 		if (is_tx)
 			cppi41_channel = &controller->tx_channel[port - 1];
@@ -697,6 +739,8 @@
 
 	hrtimer_cancel(&controller->early_tx);
 	cppi41_dma_controller_stop(controller);
+	kfree(controller->rx_channel);
+	kfree(controller->tx_channel);
 	kfree(controller);
 }
 EXPORT_SYMBOL_GPL(cppi41_dma_controller_destroy);
@@ -705,6 +749,7 @@
 cppi41_dma_controller_create(struct musb *musb, void __iomem *base)
 {
 	struct cppi41_dma_controller *controller;
+	int channel_size;
 	int ret = 0;
 
 	if (!musb->controller->parent->of_node) {
@@ -727,12 +772,37 @@
 	controller->controller.is_compatible = cppi41_is_compatible;
 	controller->controller.musb = musb;
 
+	if (musb->io.quirks & MUSB_DA8XX) {
+		controller->tdown_reg = DA8XX_USB_TEARDOWN;
+		controller->autoreq_reg = DA8XX_USB_AUTOREQ;
+		controller->set_dma_mode = da8xx_set_dma_mode;
+		controller->num_channels = DA8XX_DMA_NUM_CHANNELS;
+	} else {
+		controller->tdown_reg = USB_TDOWN;
+		controller->autoreq_reg = USB_CTRL_AUTOREQ;
+		controller->set_dma_mode = cppi41_set_dma_mode;
+		controller->num_channels = MUSB_DMA_NUM_CHANNELS;
+	}
+
+	channel_size = controller->num_channels *
+			sizeof(struct cppi41_dma_channel);
+	controller->rx_channel = kzalloc(channel_size, GFP_KERNEL);
+	if (!controller->rx_channel)
+		goto rx_channel_alloc_fail;
+	controller->tx_channel = kzalloc(channel_size, GFP_KERNEL);
+	if (!controller->tx_channel)
+		goto tx_channel_alloc_fail;
+
 	ret = cppi41_dma_controller_start(controller);
 	if (ret)
 		goto plat_get_fail;
 	return &controller->controller;
 
 plat_get_fail:
+	kfree(controller->tx_channel);
+tx_channel_alloc_fail:
+	kfree(controller->rx_channel);
+rx_channel_alloc_fail:
 	kfree(controller);
 kzalloc_fail:
 	if (ret == -EPROBE_DEFER)
diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c
index c9a09b5..dc353e2 100644
--- a/drivers/usb/musb/sunxi.c
+++ b/drivers/usb/musb/sunxi.c
@@ -297,6 +297,8 @@
 	if (test_bit(SUNXI_MUSB_FL_HAS_SRAM, &glue->flags))
 		sunxi_sram_release(musb->controller->parent);
 
+	devm_usb_put_phy(glue->dev, glue->xceiv);
+
 	return 0;
 }
 
diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c
index 5fe4a57..ccc2bf5 100644
--- a/drivers/usb/phy/phy-tegra-usb.c
+++ b/drivers/usb/phy/phy-tegra-usb.c
@@ -329,6 +329,14 @@
 	unsigned long val;
 	void __iomem *base = phy->regs;
 
+	/*
+	 * The USB driver may have already initiated the phy clock
+	 * disable so wait to see if the clock turns off and if not
+	 * then proceed with gating the clock.
+	 */
+	if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID, 0) == 0)
+		return;
+
 	if (phy->is_legacy_phy) {
 		val = readl(base + USB_SUSP_CTRL);
 		val |= USB_SUSP_SET;
@@ -351,6 +359,15 @@
 	unsigned long val;
 	void __iomem *base = phy->regs;
 
+	/*
+	 * The USB driver may have already initiated the phy clock
+	 * enable so wait to see if the clock turns on and if not
+	 * then proceed with ungating the clock.
+	 */
+	if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID,
+			       USB_PHY_CLK_VALID) == 0)
+		return;
+
 	if (phy->is_legacy_phy) {
 		val = readl(base + USB_SUSP_CTRL);
 		val |= USB_SUSP_CLR;
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index d1af831..50285b0 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -282,11 +282,26 @@
 			      struct usbhs_fifo *fifo)
 {
 	struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe);
+	int ret = 0;
 
-	if (!usbhs_pipe_is_dcp(pipe))
-		usbhsf_fifo_barrier(priv, fifo);
+	if (!usbhs_pipe_is_dcp(pipe)) {
+		/*
+		 * This driver checks the pipe condition first to avoid -EBUSY
+		 * from usbhsf_fifo_barrier() with about 10 msec delay in
+		 * the interrupt handler if the pipe is RX direction and empty.
+		 */
+		if (usbhs_pipe_is_dir_in(pipe))
+			ret = usbhs_pipe_is_accessible(pipe);
+		if (!ret)
+			ret = usbhsf_fifo_barrier(priv, fifo);
+	}
 
-	usbhs_write(priv, fifo->ctr, BCLR);
+	/*
+	 * if non-DCP pipe, this driver should set BCLR when
+	 * usbhsf_fifo_barrier() returns 0.
+	 */
+	if (!ret)
+		usbhs_write(priv, fifo->ctr, BCLR);
 }
 
 static int usbhsf_fifo_rcv_len(struct usbhs_priv *priv,
@@ -842,9 +857,9 @@
 		fifo->name, usbhs_pipe_number(pipe), pkt->length, pkt->zero);
 
 	usbhs_pipe_running(pipe, 1);
-	usbhsf_dma_start(pipe, fifo);
 	usbhs_pipe_set_trans_count_if_bulk(pipe, pkt->trans);
 	dma_async_issue_pending(chan);
+	usbhsf_dma_start(pipe, fifo);
 	usbhs_pipe_enable(pipe);
 
 xfer_work_end:
diff --git a/drivers/usb/serial/console.c b/drivers/usb/serial/console.c
index fdf8980..43a862a 100644
--- a/drivers/usb/serial/console.c
+++ b/drivers/usb/serial/console.c
@@ -186,6 +186,7 @@
 	tty_kref_put(tty);
  reset_open_count:
 	port->port.count = 0;
+	info->port = NULL;
 	usb_autopm_put_interface(serial->interface);
  error_get_interface:
 	usb_serial_put(serial);
@@ -265,7 +266,7 @@
 
 void usb_serial_console_disconnect(struct usb_serial *serial)
 {
-	if (serial->port[0] == usbcons_info.port) {
+	if (serial->port[0] && serial->port[0] == usbcons_info.port) {
 		usb_serial_console_exit();
 		usb_serial_put(serial);
 	}
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 2d945c9..412f812 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -177,6 +177,7 @@
 	{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
 	{ USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */
+	{ USB_DEVICE(0x18EF, 0xE032) }, /* ELV TFD500 Data Logger */
 	{ USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */
 	{ USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */
 	{ USB_DEVICE(0x1901, 0x0194) },	/* GE Healthcare Remote Alarm Box */
@@ -352,6 +353,7 @@
 #define CP210X_PARTNUM_CP2104	0x04
 #define CP210X_PARTNUM_CP2105	0x05
 #define CP210X_PARTNUM_CP2108	0x08
+#define CP210X_PARTNUM_UNKNOWN	0xFF
 
 /* CP210X_GET_COMM_STATUS returns these 0x13 bytes */
 struct cp210x_comm_status {
@@ -1491,8 +1493,11 @@
 	result = cp210x_read_vendor_block(serial, REQTYPE_DEVICE_TO_HOST,
 					  CP210X_GET_PARTNUM, &priv->partnum,
 					  sizeof(priv->partnum));
-	if (result < 0)
-		goto err_free_priv;
+	if (result < 0) {
+		dev_warn(&serial->interface->dev,
+			 "querying part number failed\n");
+		priv->partnum = CP210X_PARTNUM_UNKNOWN;
+	}
 
 	usb_set_serial_data(serial, priv);
 
@@ -1505,10 +1510,6 @@
 	}
 
 	return 0;
-err_free_priv:
-	kfree(priv);
-
-	return result;
 }
 
 static void cp210x_disconnect(struct usb_serial *serial)
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 1cec037..49d1b2d 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1015,6 +1015,8 @@
 	{ USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) },
 	{ USB_DEVICE(TI_VID, TI_CC3200_LAUNCHPAD_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) },
+	{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 4fcf1ce..f9d15bd 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -610,6 +610,13 @@
 #define ADI_GNICEPLUS_PID	0xF001
 
 /*
+ * Cypress WICED USB UART
+ */
+#define CYPRESS_VID			0x04B4
+#define CYPRESS_WICED_BT_USB_PID	0x009B
+#define CYPRESS_WICED_WL_USB_PID	0xF900
+
+/*
  * Microchip Technology, Inc.
  *
  * MICROCHIP_VID (0x04D8) and MICROCHIP_USB_BOARD_PID (0x000A) are
diff --git a/drivers/usb/serial/metro-usb.c b/drivers/usb/serial/metro-usb.c
index cc84da8..14511d6 100644
--- a/drivers/usb/serial/metro-usb.c
+++ b/drivers/usb/serial/metro-usb.c
@@ -45,6 +45,7 @@
 static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(FOCUS_VENDOR_ID, FOCUS_PRODUCT_ID_BI) },
 	{ USB_DEVICE(FOCUS_VENDOR_ID, FOCUS_PRODUCT_ID_UNI) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x0c2e, 0x0730, 0xff) },	/* MS7820 */
 	{ }, /* Terminating entry. */
 };
 MODULE_DEVICE_TABLE(usb, id_table);
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 54bfef1..ba672cf 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -522,6 +522,7 @@
 
 /* TP-LINK Incorporated products */
 #define TPLINK_VENDOR_ID			0x2357
+#define TPLINK_PRODUCT_LTE			0x000D
 #define TPLINK_PRODUCT_MA180			0x0201
 
 /* Changhong products */
@@ -2011,6 +2012,7 @@
 	{ USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) },
 	{ USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600A) },
 	{ USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600E) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, TPLINK_PRODUCT_LTE, 0xff, 0x00, 0x00) },	/* TP-Link LTE Module */
 	{ USB_DEVICE(TPLINK_VENDOR_ID, TPLINK_PRODUCT_MA180),
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(TPLINK_VENDOR_ID, 0x9000),					/* TP-Link MA260 */
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index ebc0bee..eb99289 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -174,6 +174,10 @@
 	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{DEVICE_SWI(0x413c, 0x81b5)},	/* Dell Wireless 5811e QDL */
 	{DEVICE_SWI(0x413c, 0x81b6)},	/* Dell Wireless 5811e QDL */
+	{DEVICE_SWI(0x413c, 0x81cf)},   /* Dell Wireless 5819 */
+	{DEVICE_SWI(0x413c, 0x81d0)},   /* Dell Wireless 5819 */
+	{DEVICE_SWI(0x413c, 0x81d1)},   /* Dell Wireless 5818 */
+	{DEVICE_SWI(0x413c, 0x81d2)},   /* Dell Wireless 5818 */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 1a59f33..a3ccb89 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -834,13 +834,25 @@
 			if (result == USB_STOR_TRANSPORT_GOOD) {
 				srb->result = SAM_STAT_GOOD;
 				srb->sense_buffer[0] = 0x0;
+			}
+
+			/*
+			 * ATA-passthru commands use sense data to report
+			 * the command completion status, and often devices
+			 * return Check Condition status when nothing is
+			 * wrong.
+			 */
+			else if (srb->cmnd[0] == ATA_16 ||
+					srb->cmnd[0] == ATA_12) {
+				/* leave the data alone */
+			}
 
 			/*
 			 * If there was a problem, report an unspecified
 			 * hardware error to prevent the higher layers from
 			 * entering an infinite retry loop.
 			 */
-			} else {
+			else {
 				srb->result = DID_ERROR << 16;
 				if ((sshdr.response_code & 0x72) == 0x72)
 					srb->sense_buffer[1] = HARDWARE_ERROR;
diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h
index f58caa9..a155cd0 100644
--- a/drivers/usb/storage/uas-detect.h
+++ b/drivers/usb/storage/uas-detect.h
@@ -9,7 +9,8 @@
 		intf->desc.bInterfaceProtocol == USB_PR_UAS);
 }
 
-static int uas_find_uas_alt_setting(struct usb_interface *intf)
+static struct usb_host_interface *uas_find_uas_alt_setting(
+		struct usb_interface *intf)
 {
 	int i;
 
@@ -17,10 +18,10 @@
 		struct usb_host_interface *alt = &intf->altsetting[i];
 
 		if (uas_is_interface(alt))
-			return alt->desc.bAlternateSetting;
+			return alt;
 	}
 
-	return -ENODEV;
+	return NULL;
 }
 
 static int uas_find_endpoints(struct usb_host_interface *alt,
@@ -58,14 +59,14 @@
 	struct usb_device *udev = interface_to_usbdev(intf);
 	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
 	unsigned long flags = id->driver_info;
-	int r, alt;
-
+	struct usb_host_interface *alt;
+	int r;
 
 	alt = uas_find_uas_alt_setting(intf);
-	if (alt < 0)
+	if (!alt)
 		return 0;
 
-	r = uas_find_endpoints(&intf->altsetting[alt], eps);
+	r = uas_find_endpoints(alt, eps);
 	if (r < 0)
 		return 0;
 
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index cfb1e3b..63cf981 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -873,14 +873,14 @@
 static int uas_switch_interface(struct usb_device *udev,
 				struct usb_interface *intf)
 {
-	int alt;
+	struct usb_host_interface *alt;
 
 	alt = uas_find_uas_alt_setting(intf);
-	if (alt < 0)
-		return alt;
+	if (!alt)
+		return -ENODEV;
 
-	return usb_set_interface(udev,
-			intf->altsetting[0].desc.bInterfaceNumber, alt);
+	return usb_set_interface(udev, alt->desc.bInterfaceNumber,
+			alt->desc.bAlternateSetting);
 }
 
 static int uas_configure_endpoints(struct uas_dev_info *devinfo)
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 5a70c33..eb06d88 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1459,6 +1459,13 @@
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_SANE_SENSE ),
 
+/* Reported by Kris Lindgren <kris.lindgren@gmail.com> */
+UNUSUAL_DEV( 0x0bc2, 0x3332, 0x0000, 0x9999,
+		"Seagate",
+		"External",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_WP_DETECT ),
+
 UNUSUAL_DEV(  0x0d49, 0x7310, 0x0000, 0x9999,
 		"Maxtor",
 		"USB to SATA",
diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c
index 35a1e77..9a53912 100644
--- a/drivers/uwb/hwa-rc.c
+++ b/drivers/uwb/hwa-rc.c
@@ -825,6 +825,8 @@
 
 	if (iface->cur_altsetting->desc.bNumEndpoints < 1)
 		return -ENODEV;
+	if (!usb_endpoint_xfer_int(&iface->cur_altsetting->endpoint[0].desc))
+		return -ENODEV;
 
 	result = -ENOMEM;
 	uwb_rc = uwb_rc_alloc();
diff --git a/drivers/uwb/uwbd.c b/drivers/uwb/uwbd.c
index 01c20a2..39dd4ef 100644
--- a/drivers/uwb/uwbd.c
+++ b/drivers/uwb/uwbd.c
@@ -302,18 +302,22 @@
 /** Start the UWB daemon */
 void uwbd_start(struct uwb_rc *rc)
 {
-	rc->uwbd.task = kthread_run(uwbd, rc, "uwbd");
-	if (rc->uwbd.task == NULL)
+	struct task_struct *task = kthread_run(uwbd, rc, "uwbd");
+	if (IS_ERR(task)) {
+		rc->uwbd.task = NULL;
 		printk(KERN_ERR "UWB: Cannot start management daemon; "
 		       "UWB won't work\n");
-	else
+	} else {
+		rc->uwbd.task = task;
 		rc->uwbd.pid = rc->uwbd.task->pid;
+	}
 }
 
 /* Stop the UWB daemon and free any unprocessed events */
 void uwbd_stop(struct uwb_rc *rc)
 {
-	kthread_stop(rc->uwbd.task);
+	if (rc->uwbd.task)
+		kthread_stop(rc->uwbd.task);
 	uwbd_flush(rc);
 }
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 8236059..57efbd3 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -1024,6 +1024,7 @@
 	mutex_unlock(&priv->lock);
 
 	if (use_ptemod) {
+		map->pages_vm_start = vma->vm_start;
 		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
 					  vma->vm_end - vma->vm_start,
 					  find_grant_ptes, map);
@@ -1061,7 +1062,6 @@
 					    set_grant_ptes_as_special, NULL);
 		}
 #endif
-		map->pages_vm_start = vma->vm_start;
 	}
 
 	return 0;
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index e89136a..b437fcc 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -57,7 +57,7 @@
 static void watch_target(struct xenbus_watch *watch,
 			 const char *path, const char *token)
 {
-	unsigned long long new_target;
+	unsigned long long new_target, static_max;
 	int err;
 	static bool watch_fired;
 	static long target_diff;
@@ -72,13 +72,20 @@
 	 * pages. PAGE_SHIFT converts bytes to pages, hence PAGE_SHIFT - 10.
 	 */
 	new_target >>= PAGE_SHIFT - 10;
-	if (watch_fired) {
-		balloon_set_new_target(new_target - target_diff);
-		return;
+
+	if (!watch_fired) {
+		watch_fired = true;
+		err = xenbus_scanf(XBT_NIL, "memory", "static-max", "%llu",
+				   &static_max);
+		if (err != 1)
+			static_max = new_target;
+		else
+			static_max >>= PAGE_SHIFT - 10;
+		target_diff = xen_pv_domain() ? 0
+				: static_max - balloon_stats.target_pages;
 	}
 
-	watch_fired = true;
-	target_diff = new_target - balloon_stats.target_pages;
+	balloon_set_new_target(new_target - target_diff);
 }
 static struct xenbus_watch target_watch = {
 	.node = "memory/target",
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
index 5fbfd9c..5b3d57f 100644
--- a/drivers/xen/xen-pciback/conf_space_header.c
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -169,6 +169,9 @@
 static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data)
 {
 	struct pci_bar_info *bar = data;
+	unsigned int pos = (offset - PCI_BASE_ADDRESS_0) / 4;
+	const struct resource *res = dev->resource;
+	u32 mask;
 
 	if (unlikely(!bar)) {
 		pr_warn(DRV_NAME ": driver data not found for %s\n",
@@ -179,7 +182,13 @@
 	/* A write to obtain the length must happen as a 32-bit write.
 	 * This does not (yet) support writing individual bytes
 	 */
-	if (value == ~0)
+	if (res[pos].flags & IORESOURCE_IO)
+		mask = ~PCI_BASE_ADDRESS_IO_MASK;
+	else if (pos && (res[pos - 1].flags & IORESOURCE_MEM_64))
+		mask = 0;
+	else
+		mask = ~PCI_BASE_ADDRESS_MEM_MASK;
+	if ((value | mask) == ~0U)
 		bar->which = 1;
 	else {
 		u32 tmpval;
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 82a8866..a1c1700 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -519,64 +519,6 @@
 	return err;
 }
 
-static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
-				     grant_ref_t *gnt_refs,
-				     unsigned int nr_grefs,
-				     void **vaddr)
-{
-	struct xenbus_map_node *node;
-	struct vm_struct *area;
-	pte_t *ptes[XENBUS_MAX_RING_GRANTS];
-	phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS];
-	int err = GNTST_okay;
-	int i;
-	bool leaked;
-
-	*vaddr = NULL;
-
-	if (nr_grefs > XENBUS_MAX_RING_GRANTS)
-		return -EINVAL;
-
-	node = kzalloc(sizeof(*node), GFP_KERNEL);
-	if (!node)
-		return -ENOMEM;
-
-	area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, ptes);
-	if (!area) {
-		kfree(node);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nr_grefs; i++)
-		phys_addrs[i] = arbitrary_virt_to_machine(ptes[i]).maddr;
-
-	err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles,
-				phys_addrs,
-				GNTMAP_host_map | GNTMAP_contains_pte,
-				&leaked);
-	if (err)
-		goto failed;
-
-	node->nr_handles = nr_grefs;
-	node->pv.area = area;
-
-	spin_lock(&xenbus_valloc_lock);
-	list_add(&node->next, &xenbus_valloc_pages);
-	spin_unlock(&xenbus_valloc_lock);
-
-	*vaddr = area->addr;
-	return 0;
-
-failed:
-	if (!leaked)
-		free_vm_area(area);
-	else
-		pr_alert("leaking VM area %p size %u page(s)", area, nr_grefs);
-
-	kfree(node);
-	return err;
-}
-
 struct map_ring_valloc_hvm
 {
 	unsigned int idx;
@@ -725,6 +667,65 @@
 }
 EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree);
 
+#ifdef CONFIG_XEN_PV
+static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
+				     grant_ref_t *gnt_refs,
+				     unsigned int nr_grefs,
+				     void **vaddr)
+{
+	struct xenbus_map_node *node;
+	struct vm_struct *area;
+	pte_t *ptes[XENBUS_MAX_RING_GRANTS];
+	phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS];
+	int err = GNTST_okay;
+	int i;
+	bool leaked;
+
+	*vaddr = NULL;
+
+	if (nr_grefs > XENBUS_MAX_RING_GRANTS)
+		return -EINVAL;
+
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, ptes);
+	if (!area) {
+		kfree(node);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nr_grefs; i++)
+		phys_addrs[i] = arbitrary_virt_to_machine(ptes[i]).maddr;
+
+	err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles,
+				phys_addrs,
+				GNTMAP_host_map | GNTMAP_contains_pte,
+				&leaked);
+	if (err)
+		goto failed;
+
+	node->nr_handles = nr_grefs;
+	node->pv.area = area;
+
+	spin_lock(&xenbus_valloc_lock);
+	list_add(&node->next, &xenbus_valloc_pages);
+	spin_unlock(&xenbus_valloc_lock);
+
+	*vaddr = area->addr;
+	return 0;
+
+failed:
+	if (!leaked)
+		free_vm_area(area);
+	else
+		pr_alert("leaking VM area %p size %u page(s)", area, nr_grefs);
+
+	kfree(node);
+	return err;
+}
+
 static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr)
 {
 	struct xenbus_map_node *node;
@@ -788,6 +789,12 @@
 	return err;
 }
 
+static const struct xenbus_ring_ops ring_ops_pv = {
+	.map = xenbus_map_ring_valloc_pv,
+	.unmap = xenbus_unmap_ring_vfree_pv,
+};
+#endif
+
 struct unmap_ring_vfree_hvm
 {
 	unsigned int idx;
@@ -916,11 +923,6 @@
 }
 EXPORT_SYMBOL_GPL(xenbus_read_driver_state);
 
-static const struct xenbus_ring_ops ring_ops_pv = {
-	.map = xenbus_map_ring_valloc_pv,
-	.unmap = xenbus_unmap_ring_vfree_pv,
-};
-
 static const struct xenbus_ring_ops ring_ops_hvm = {
 	.map = xenbus_map_ring_valloc_hvm,
 	.unmap = xenbus_unmap_ring_vfree_hvm,
@@ -928,8 +930,10 @@
 
 void __init xenbus_ring_ops_init(void)
 {
+#ifdef CONFIG_XEN_PV
 	if (!xen_feature(XENFEAT_auto_translated_physmap))
 		ring_ops = &ring_ops_pv;
 	else
+#endif
 		ring_ops = &ring_ops_hvm;
 }
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index adaf6f6..e1cbdfd 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -310,9 +310,13 @@
 
 	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
 
-	if (unlikely(copied < len && !PageUptodate(page))) {
-		copied = 0;
-		goto out;
+	if (!PageUptodate(page)) {
+		if (unlikely(copied < len)) {
+			copied = 0;
+			goto out;
+		} else if (len == PAGE_SIZE) {
+			SetPageUptodate(page);
+		}
 	}
 	/*
 	 * No need to use i_size_read() here, the i_size
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index ce7181e..a7c5a98 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -54,7 +54,7 @@
 	int size;			/* size of magic/mask */
 	char *magic;			/* magic or filename extension */
 	char *mask;			/* mask, NULL for exact match */
-	char *interpreter;		/* filename of interpreter */
+	const char *interpreter;	/* filename of interpreter */
 	char *name;
 	struct dentry *dentry;
 	struct file *interp_file;
@@ -131,27 +131,26 @@
 {
 	Node *fmt;
 	struct file *interp_file = NULL;
-	char iname[BINPRM_BUF_SIZE];
-	const char *iname_addr = iname;
 	int retval;
 	int fd_binary = -1;
 
 	retval = -ENOEXEC;
 	if (!enabled)
-		goto ret;
+		return retval;
 
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
 	if (fmt)
-		strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
+		dget(fmt->dentry);
 	read_unlock(&entries_lock);
 	if (!fmt)
-		goto ret;
+		return retval;
 
 	/* Need to be able to load the file after exec */
+	retval = -ENOENT;
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
-		return -ENOENT;
+		goto ret;
 
 	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
 		retval = remove_arg_zero(bprm);
@@ -195,22 +194,22 @@
 	bprm->argc++;
 
 	/* add the interp as argv[0] */
-	retval = copy_strings_kernel(1, &iname_addr, bprm);
+	retval = copy_strings_kernel(1, &fmt->interpreter, bprm);
 	if (retval < 0)
 		goto error;
 	bprm->argc++;
 
 	/* Update interp in case binfmt_script needs it. */
-	retval = bprm_change_interp(iname, bprm);
+	retval = bprm_change_interp(fmt->interpreter, bprm);
 	if (retval < 0)
 		goto error;
 
-	if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) {
+	if (fmt->flags & MISC_FMT_OPEN_FILE) {
 		interp_file = filp_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
-		interp_file = open_exec(iname);
+		interp_file = open_exec(fmt->interpreter);
 	}
 	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
@@ -238,6 +237,7 @@
 		goto error;
 
 ret:
+	dput(fmt->dentry);
 	return retval;
 error:
 	if (fd_binary > 0)
@@ -594,8 +594,13 @@
 
 static void bm_evict_inode(struct inode *inode)
 {
+	Node *e = inode->i_private;
+
+	if (e && e->flags & MISC_FMT_OPEN_FILE)
+		filp_close(e->interp_file, NULL);
+
 	clear_inode(inode);
-	kfree(inode->i_private);
+	kfree(e);
 }
 
 static void kill_node(Node *e)
@@ -603,24 +608,14 @@
 	struct dentry *dentry;
 
 	write_lock(&entries_lock);
-	dentry = e->dentry;
-	if (dentry) {
-		list_del_init(&e->list);
-		e->dentry = NULL;
-	}
+	list_del_init(&e->list);
 	write_unlock(&entries_lock);
 
-	if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) {
-		filp_close(e->interp_file, NULL);
-		e->interp_file = NULL;
-	}
-
-	if (dentry) {
-		drop_nlink(d_inode(dentry));
-		d_drop(dentry);
-		dput(dentry);
-		simple_release_fs(&bm_mnt, &entry_count);
-	}
+	dentry = e->dentry;
+	drop_nlink(d_inode(dentry));
+	d_drop(dentry);
+	dput(dentry);
+	simple_release_fs(&bm_mnt, &entry_count);
 }
 
 /* /<entry> */
@@ -665,7 +660,8 @@
 		root = file_inode(file)->i_sb->s_root;
 		inode_lock(d_inode(root));
 
-		kill_node(e);
+		if (!list_empty(&e->list))
+			kill_node(e);
 
 		inode_unlock(d_inode(root));
 		break;
@@ -794,7 +790,7 @@
 		inode_lock(d_inode(root));
 
 		while (!list_empty(&entries))
-			kill_node(list_entry(entries.next, Node, list));
+			kill_node(list_first_entry(&entries, Node, list));
 
 		inode_unlock(d_inode(root));
 		break;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index afdf4e3..7cde3f4 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -19,7 +19,6 @@
 	const char *i_arg, *i_name;
 	char *cp;
 	struct file *file;
-	char interp[BINPRM_BUF_SIZE];
 	int retval;
 
 	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
@@ -55,7 +54,7 @@
 			break;
 	}
 	for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++);
-	if (*cp == '\0') 
+	if (*cp == '\0')
 		return -ENOEXEC; /* No interpreter name found */
 	i_name = cp;
 	i_arg = NULL;
@@ -65,7 +64,6 @@
 		*cp++ = '\0';
 	if (*cp)
 		i_arg = cp;
-	strcpy (interp, i_name);
 	/*
 	 * OK, we've parsed out the interpreter name and
 	 * (optional) argument.
@@ -80,24 +78,27 @@
 	if (retval)
 		return retval;
 	retval = copy_strings_kernel(1, &bprm->interp, bprm);
-	if (retval < 0) return retval; 
+	if (retval < 0)
+		return retval;
 	bprm->argc++;
 	if (i_arg) {
 		retval = copy_strings_kernel(1, &i_arg, bprm);
-		if (retval < 0) return retval; 
+		if (retval < 0)
+			return retval;
 		bprm->argc++;
 	}
 	retval = copy_strings_kernel(1, &i_name, bprm);
-	if (retval) return retval; 
+	if (retval)
+		return retval;
 	bprm->argc++;
-	retval = bprm_change_interp(interp, bprm);
+	retval = bprm_change_interp(i_name, bprm);
 	if (retval < 0)
 		return retval;
 
 	/*
 	 * OK, now restart the process with the interpreter's dentry.
 	 */
-	file = open_exec(interp);
+	file = open_exec(i_name);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 93d088f..789f55e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -716,10 +716,12 @@
 
 	set_page_writeback(page);
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
-	if (result)
+	if (result) {
 		end_page_writeback(page);
-	else
+	} else {
+		clean_page_buffers(page);
 		unlock_page(page);
+	}
 	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b51d23f..280384b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -107,7 +107,8 @@
 	struct inode *inode;
 	struct page *page;
 	unsigned long index;
-	int ret;
+	unsigned int mirror = btrfs_io_bio(bio)->mirror_num;
+	int ret = 0;
 
 	if (bio->bi_status)
 		cb->errors = 1;
@@ -118,6 +119,21 @@
 	if (!refcount_dec_and_test(&cb->pending_bios))
 		goto out;
 
+	/*
+	 * Record the correct mirror_num in cb->orig_bio so that
+	 * read-repair can work properly.
+	 */
+	ASSERT(btrfs_io_bio(cb->orig_bio));
+	btrfs_io_bio(cb->orig_bio)->mirror_num = mirror;
+	cb->mirror_num = mirror;
+
+	/*
+	 * Some IO in this cb have failed, just skip checksum as there
+	 * is no way it could be correct.
+	 */
+	if (cb->errors == 1)
+		goto csum_failed;
+
 	inode = cb->inode;
 	ret = check_compressed_csum(BTRFS_I(inode), cb,
 				    (u64)bio->bi_iter.bi_sector << 9);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5a8933d..8fc6903 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -709,7 +709,6 @@
 #define BTRFS_FS_OPEN				5
 #define BTRFS_FS_QUOTA_ENABLED			6
 #define BTRFS_FS_QUOTA_ENABLING			7
-#define BTRFS_FS_QUOTA_DISABLING		8
 #define BTRFS_FS_UPDATE_UUID_TREE_GEN		9
 #define BTRFS_FS_CREATING_FREE_SPACE_TREE	10
 #define BTRFS_FS_BTREE_ERR			11
@@ -723,7 +722,7 @@
  * Indicate that a whole-filesystem exclusive operation is running
  * (device replace, resize, device add/delete, balance)
  */
-#define BTRFS_FS_EXCL_OP			14
+#define BTRFS_FS_EXCL_OP			16
 
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 487bbe4..dfdab84 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3643,7 +3643,14 @@
 	u64 flags;
 
 	do_barriers = !btrfs_test_opt(fs_info, NOBARRIER);
-	backup_super_roots(fs_info);
+
+	/*
+	 * max_mirrors == 0 indicates we're from commit_transaction,
+	 * not from fsync where the tree roots in fs_info have not
+	 * been consistent on disk.
+	 */
+	if (max_mirrors == 0)
+		backup_super_roots(fs_info);
 
 	sb = fs_info->super_for_commit;
 	dev_item = &sb->dev_item;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3e5bb0c..970190c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2801,7 +2801,7 @@
 		}
 	}
 
-	bio = btrfs_bio_alloc(bdev, sector << 9);
+	bio = btrfs_bio_alloc(bdev, (u64)sector << 9);
 	bio_add_page(bio, page, page_size, offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
@@ -3471,8 +3471,7 @@
 	unsigned int write_flags = 0;
 	unsigned long nr_written = 0;
 
-	if (wbc->sync_mode == WB_SYNC_ALL)
-		write_flags = REQ_SYNC;
+	write_flags = wbc_to_write_flags(wbc);
 
 	trace___extent_writepage(page, inode, wbc);
 
@@ -3718,7 +3717,7 @@
 	unsigned long i, num_pages;
 	unsigned long bio_flags = 0;
 	unsigned long start, end;
-	unsigned int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META;
+	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
@@ -4063,9 +4062,6 @@
 	if (epd->bio) {
 		int ret;
 
-		bio_set_op_attrs(epd->bio, REQ_OP_WRITE,
-				 epd->sync_io ? REQ_SYNC : 0);
-
 		ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
 		BUG_ON(ret < 0); /* -ENOMEM */
 		epd->bio = NULL;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 128f3e5..d94e3f6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -135,6 +135,18 @@
 						 const u64 offset,
 						 const u64 bytes)
 {
+	unsigned long index = offset >> PAGE_SHIFT;
+	unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
+	struct page *page;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		index++;
+		if (!page)
+			continue;
+		ClearPagePrivate2(page);
+		put_page(page);
+	}
 	return __endio_write_update_ordered(inode, offset + PAGE_SIZE,
 					    bytes - PAGE_SIZE, false);
 }
@@ -8357,11 +8369,8 @@
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
 	blk_status_t err = bio->bi_status;
 
-	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) {
+	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
 		err = btrfs_subio_endio_read(inode, io_bio, err);
-		if (!err)
-			bio->bi_status = 0;
-	}
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
 		      dip->logical_offset + dip->bytes - 1);
@@ -8369,7 +8378,7 @@
 
 	kfree(dip);
 
-	dio_bio->bi_status = bio->bi_status;
+	dio_bio->bi_status = err;
 	dio_end_io(dio_bio);
 
 	if (io_bio->end_io)
@@ -8387,6 +8396,7 @@
 	btrfs_work_func_t func;
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
+	u64 last_offset;
 	int ret;
 
 	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
@@ -8398,6 +8408,7 @@
 	}
 
 again:
+	last_offset = ordered_offset;
 	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
 						   &ordered_offset,
 						   ordered_bytes,
@@ -8409,6 +8420,12 @@
 	btrfs_queue_work(wq, &ordered->work);
 out_test:
 	/*
+	 * If btrfs_dec_test_ordered_pending does not find any ordered extent
+	 * in the range, we can exit.
+	 */
+	if (ordered_offset == last_offset)
+		return;
+	/*
 	 * our bio might span multiple ordered extents.  If we haven't
 	 * completed the accounting for the whole dio, go back and try again
 	 */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d6715c2..6c7a49f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2773,9 +2773,9 @@
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	fi_args->nodesize = fs_info->super_copy->nodesize;
-	fi_args->sectorsize = fs_info->super_copy->sectorsize;
-	fi_args->clone_alignment = fs_info->super_copy->sectorsize;
+	fi_args->nodesize = fs_info->nodesize;
+	fi_args->sectorsize = fs_info->sectorsize;
+	fi_args->clone_alignment = fs_info->sectorsize;
 
 	if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
 		ret = -EFAULT;
@@ -3032,7 +3032,7 @@
 out:
 	if (ret)
 		btrfs_cmp_data_free(cmp);
-	return 0;
+	return ret;
 }
 
 static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp)
@@ -4061,6 +4061,10 @@
 		ret = PTR_ERR(new_root);
 		goto out;
 	}
+	if (!is_fstree(new_root->objectid)) {
+		ret = -ENOENT;
+		goto out;
+	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5c8b61c..e172d48 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -807,7 +807,6 @@
 	}
 	ret = 0;
 out:
-	set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -953,7 +952,6 @@
 	if (!fs_info->quota_root)
 		goto out;
 	clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
-	set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags);
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
@@ -1307,6 +1305,8 @@
 		}
 	}
 	ret = del_qgroup_item(trans, quota_root, qgroupid);
+	if (ret && ret != -ENOENT)
+		goto out;
 
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
@@ -2086,8 +2086,6 @@
 
 	if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags))
 		set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
-	if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags))
-		clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 
 	spin_lock(&fs_info->qgroup_lock);
 	while (!list_empty(&fs_info->dirty_qgroups)) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 3a49a3c..9841fae 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2400,11 +2400,11 @@
 	while (!list_empty(list)) {
 		reloc_root = list_entry(list->next, struct btrfs_root,
 					root_list);
+		__del_reloc_root(reloc_root);
 		free_extent_buffer(reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
 		reloc_root->node = NULL;
 		reloc_root->commit_root = NULL;
-		__del_reloc_root(reloc_root);
 	}
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 32b043e..8fd195c 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -2630,7 +2630,7 @@
 	} else {
 		btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o",
 				(int)(mode & S_IFMT));
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 35a128a..161694b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1135,7 +1135,7 @@
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
 	sb->s_flags |= MS_POSIXACL;
 #endif
-	sb->s_flags |= MS_I_VERSION;
+	sb->s_flags |= SB_I_VERSION;
 	sb->s_iflags |= SB_I_CGROUPWB;
 
 	err = super_setup_bdi(sb);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ad7f4ba..c800d06 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4181,6 +4181,7 @@
 	struct extent_map *em, *n;
 	struct list_head extents;
 	struct extent_map_tree *tree = &inode->extent_tree;
+	u64 logged_start, logged_end;
 	u64 test_gen;
 	int ret = 0;
 	int num = 0;
@@ -4190,10 +4191,11 @@
 	down_write(&inode->dio_sem);
 	write_lock(&tree->lock);
 	test_gen = root->fs_info->last_trans_committed;
+	logged_start = start;
+	logged_end = end;
 
 	list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
 		list_del_init(&em->list);
-
 		/*
 		 * Just an arbitrary number, this can be really CPU intensive
 		 * once we start getting a lot of extents, and really once we
@@ -4208,6 +4210,12 @@
 
 		if (em->generation <= test_gen)
 			continue;
+
+		if (em->start < logged_start)
+			logged_start = em->start;
+		if ((em->start + em->len - 1) > logged_end)
+			logged_end = em->start + em->len - 1;
+
 		/* Need a ref to keep it from getting evicted from cache */
 		refcount_inc(&em->refs);
 		set_bit(EXTENT_FLAG_LOGGING, &em->flags);
@@ -4216,7 +4224,7 @@
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
-	btrfs_get_logged_extents(inode, logged_list, start, end);
+	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
 	/*
 	 * Some ordered extents started by fsync might have completed
 	 * before we could collect them into the list logged_list, which
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0e8f16c..b397375 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6166,7 +6166,7 @@
 	map_length = length;
 
 	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = __btrfs_map_block(fs_info, bio_op(bio), logical,
+	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical,
 				&map_length, &bbio, mirror_num, 1);
 	if (ret) {
 		btrfs_bio_counter_dec(fs_info);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 157fe59..1978a8c 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1991,6 +1991,7 @@
 retry:
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
+		spin_unlock(&ci->i_ceph_lock);
 		dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode);
 		goto out;
 	}
@@ -2008,8 +2009,10 @@
 			mutex_lock(&session->s_mutex);
 			goto retry;
 		}
-		if (cap->session->s_state < CEPH_MDS_SESSION_OPEN)
+		if (cap->session->s_state < CEPH_MDS_SESSION_OPEN) {
+			spin_unlock(&ci->i_ceph_lock);
 			goto out;
+		}
 
 		flushing = __mark_caps_flushing(inode, session, true,
 						&flush_tid, &oldest_flush_tid);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9dd6b83..f23c820 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -7,7 +7,6 @@
 #include <linux/sched.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-#include <linux/utsname.h>
 #include <linux/ratelimit.h>
 
 #include "super.h"
@@ -735,12 +734,13 @@
 			inode = req->r_inode;
 			ihold(inode);
 		} else {
-			/* req->r_dentry is non-null for LSSNAP request.
-			 * fall-thru */
-			WARN_ON_ONCE(!req->r_dentry);
+			/* req->r_dentry is non-null for LSSNAP request */
+			rcu_read_lock();
+			inode = get_nonsnap_parent(req->r_dentry);
+			rcu_read_unlock();
+			dout("__choose_mds using snapdir's parent %p\n", inode);
 		}
-	}
-	if (!inode && req->r_dentry) {
+	} else if (req->r_dentry) {
 		/* ignore race with rename; old or new d_parent is okay */
 		struct dentry *parent;
 		struct inode *dir;
@@ -884,8 +884,8 @@
 	void *p;
 
 	const char* metadata[][2] = {
-		{"hostname", utsname()->nodename},
-		{"kernel_version", utsname()->release},
+		{"hostname", mdsc->nodename},
+		{"kernel_version", init_utsname()->release},
 		{"entity_id", opt->name ? : ""},
 		{"root", fsopt->server_path ? : "/"},
 		{NULL, NULL}
@@ -3539,6 +3539,8 @@
 	init_rwsem(&mdsc->pool_perm_rwsem);
 	mdsc->pool_perm_tree = RB_ROOT;
 
+	strncpy(mdsc->nodename, utsname()->nodename,
+		sizeof(mdsc->nodename) - 1);
 	return 0;
 }
 
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index db57ae9..636d6b2 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -8,6 +8,7 @@
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
 #include <linux/refcount.h>
+#include <linux/utsname.h>
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/messenger.h>
@@ -368,6 +369,8 @@
 
 	struct rw_semaphore     pool_perm_rwsem;
 	struct rb_root		pool_perm_tree;
+
+	char nodename[__NEW_UTS_LEN + 1];
 };
 
 extern const char *ceph_mds_op_name(int op);
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 1ffc8b4..7fc0b85 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -374,12 +374,10 @@
 	     realm->ino, realm, snapc, snapc->seq,
 	     (unsigned int) snapc->num_snaps);
 
-	if (realm->cached_context) {
-		ceph_put_snap_context(realm->cached_context);
-		/* queue realm for cap_snap creation */
-		list_add_tail(&realm->dirty_item, dirty_realms);
-	}
+	ceph_put_snap_context(realm->cached_context);
 	realm->cached_context = snapc;
+	/* queue realm for cap_snap creation */
+	list_add_tail(&realm->dirty_item, dirty_realms);
 	return 0;
 
 fail:
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index f724361..d5b2e12 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -5,9 +5,14 @@
 	select CRYPTO
 	select CRYPTO_MD4
 	select CRYPTO_MD5
+	select CRYPTO_SHA256
+	select CRYPTO_CMAC
 	select CRYPTO_HMAC
 	select CRYPTO_ARC4
+	select CRYPTO_AEAD2
+	select CRYPTO_CCM
 	select CRYPTO_ECB
+	select CRYPTO_AES
 	select CRYPTO_DES
 	help
 	  This is the client VFS module for the SMB3 family of NAS protocols,
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 9727e1d..cbb9534 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -160,8 +160,13 @@
 			if ((ses->serverDomain == NULL) ||
 				(ses->serverOS == NULL) ||
 				(ses->serverNOS == NULL)) {
-				seq_printf(m, "\n%d) entry for %s not fully "
-					   "displayed\n\t", i, ses->serverName);
+				seq_printf(m, "\n%d) Name: %s Uses: %d Capability: 0x%x\tSession Status: %d\t",
+					i, ses->serverName, ses->ses_count,
+					ses->capabilities, ses->status);
+				if (ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST)
+					seq_printf(m, "Guest\t");
+				else if (ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
+					seq_printf(m, "Anonymous\t");
 			} else {
 				seq_printf(m,
 				    "\n%d) Name: %s  Domain: %s Uses: %d OS:"
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 180b335..8c8b75d 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -461,6 +461,8 @@
 		seq_puts(s, ",nocase");
 	if (tcon->retry)
 		seq_puts(s, ",hard");
+	else
+		seq_puts(s, ",soft");
 	if (tcon->use_persistent)
 		seq_puts(s, ",persistenthandles");
 	else if (tcon->use_resilient)
@@ -1447,7 +1449,7 @@
 	exit_cifs_idmap();
 #endif
 #ifdef CONFIG_CIFS_UPCALL
-	unregister_key_type(&cifs_spnego_key_type);
+	exit_cifs_spnego();
 #endif
 	cifs_destroy_request_bufs();
 	cifs_destroy_mids();
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 30bf89b..5a10e56 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -149,5 +149,5 @@
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "2.09"
+#define CIFS_VERSION   "2.10"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 808486c..e185b28 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -188,6 +188,8 @@
 #ifdef CONFIG_CIFS_SMB311
 	Smb_311,
 #endif /* SMB311 */
+	Smb_3any,
+	Smb_default,
 	Smb_version_err
 };
 
@@ -659,7 +661,9 @@
 #endif
 	unsigned int	max_read;
 	unsigned int	max_write;
-	__u8		preauth_hash[512];
+#ifdef CONFIG_CIFS_SMB311
+	__u8	preauth_sha_hash[64]; /* save initital negprot hash */
+#endif /* 3.1.1 */
 	struct delayed_work reconnect; /* reconnect workqueue job */
 	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
 	unsigned long echo_interval;
@@ -847,7 +851,9 @@
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
-	__u8 preauth_hash[512];
+#ifdef CONFIG_CIFS_SMB311
+	__u8 preauth_sha_hash[64];
+#endif /* 3.1.1 */
 };
 
 static inline bool
@@ -1701,6 +1707,10 @@
 #define SMB21_VERSION_STRING	"2.1"
 extern struct smb_version_operations smb21_operations;
 extern struct smb_version_values smb21_values;
+#define SMBDEFAULT_VERSION_STRING "default"
+extern struct smb_version_values smbdefault_values;
+#define SMB3ANY_VERSION_STRING "3"
+extern struct smb_version_values smb3any_values;
 #define SMB30_VERSION_STRING	"3.0"
 extern struct smb_version_operations smb30_operations;
 extern struct smb_version_values smb30_values;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5aa2d27..0bfc228 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -301,6 +301,8 @@
 	{ Smb_311, SMB311_VERSION_STRING },
 	{ Smb_311, ALT_SMB311_VERSION_STRING },
 #endif /* SMB311 */
+	{ Smb_3any, SMB3ANY_VERSION_STRING },
+	{ Smb_default, SMBDEFAULT_VERSION_STRING },
 	{ Smb_version_err, NULL }
 };
 
@@ -1148,6 +1150,14 @@
 		vol->vals = &smb311_values;
 		break;
 #endif /* SMB311 */
+	case Smb_3any:
+		vol->ops = &smb30_operations; /* currently identical with 3.0 */
+		vol->vals = &smb3any_values;
+		break;
+	case Smb_default:
+		vol->ops = &smb30_operations; /* currently identical with 3.0 */
+		vol->vals = &smbdefault_values;
+		break;
 	default:
 		cifs_dbg(VFS, "Unknown vers= option specified: %s\n", value);
 		return 1;
@@ -1274,9 +1284,9 @@
 
 	vol->actimeo = CIFS_DEF_ACTIMEO;
 
-	/* FIXME: add autonegotiation for SMB3 or later rather than just SMB3 */
-	vol->ops = &smb30_operations; /* both secure and accepted widely */
-	vol->vals = &smb30_values;
+	/* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */
+	vol->ops = &smb30_operations;
+	vol->vals = &smbdefault_values;
 
 	vol->echo_interval = SMB_ECHO_INTERVAL_DEFAULT;
 
@@ -1988,11 +1998,10 @@
 
 	if (got_version == false)
 		pr_warn("No dialect specified on mount. Default has changed to "
-			"a more secure dialect, SMB3 (vers=3.0), from CIFS "
+			"a more secure dialect, SMB2.1 or later (e.g. SMB3), from CIFS "
 			"(SMB1). To use the less secure SMB1 dialect to access "
-			"old servers which do not support SMB3 specify vers=1.0"
-			" on mount. For somewhat newer servers such as Windows "
-			"7 try vers=2.1.\n");
+			"old servers which do not support SMB3 (or SMB2.1) specify vers=1.0"
+			" on mount.\n");
 
 	kfree(mountdata_copy);
 	return 0;
@@ -2133,6 +2142,7 @@
 	if (vol->nosharesock)
 		return 0;
 
+	/* BB update this for smb3any and default case */
 	if ((server->vals != vol->vals) || (server->ops != vol->ops))
 		return 0;
 
@@ -4144,6 +4154,14 @@
 	cifs_dbg(FYI, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d\n",
 		 server->sec_mode, server->capabilities, server->timeAdj);
 
+	if (ses->auth_key.response) {
+		cifs_dbg(VFS, "Free previous auth_key.response = %p\n",
+			 ses->auth_key.response);
+		kfree(ses->auth_key.response);
+		ses->auth_key.response = NULL;
+		ses->auth_key.len = 0;
+	}
+
 	if (server->ops->sess_setup)
 		rc = server->ops->sess_setup(xid, ses, nls_info);
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0786f19..92fdf9c 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -224,6 +224,13 @@
 	if (backup_cred(cifs_sb))
 		create_options |= CREATE_OPEN_BACKUP_INTENT;
 
+	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
+	if (f_flags & O_SYNC)
+		create_options |= CREATE_WRITE_THROUGH;
+
+	if (f_flags & O_DIRECT)
+		create_options |= CREATE_NO_BUFFER;
+
 	oparms.tcon = tcon;
 	oparms.cifs_sb = cifs_sb;
 	oparms.desired_access = desired_access;
@@ -1102,8 +1109,10 @@
 	struct cifs_tcon *tcon;
 	unsigned int num, max_num, max_buf;
 	LOCKING_ANDX_RANGE *buf, *cur;
-	int types[] = {LOCKING_ANDX_LARGE_FILES,
-		       LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
+	static const int types[] = {
+		LOCKING_ANDX_LARGE_FILES,
+		LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES
+	};
 	int i;
 
 	xid = get_xid();
@@ -1434,8 +1443,10 @@
 		  unsigned int xid)
 {
 	int rc = 0, stored_rc;
-	int types[] = {LOCKING_ANDX_LARGE_FILES,
-		       LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
+	static const int types[] = {
+		LOCKING_ANDX_LARGE_FILES,
+		LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES
+	};
 	unsigned int i;
 	unsigned int max_num, num, max_buf;
 	LOCKING_ANDX_RANGE *buf, *cur;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a869363..7c732cb4 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -234,6 +234,8 @@
 	fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
 	fattr->cf_mtime = cifs_NTtimeToUnix(info->LastModificationTime);
 	fattr->cf_ctime = cifs_NTtimeToUnix(info->LastStatusChange);
+	/* old POSIX extensions don't get create time */
+
 	fattr->cf_mode = le64_to_cpu(info->Permissions);
 
 	/*
@@ -2024,6 +2026,19 @@
 	stat->blksize = CIFS_MAX_MSGSIZE;
 	stat->ino = CIFS_I(inode)->uniqueid;
 
+	/* old CIFS Unix Extensions doesn't return create time */
+	if (CIFS_I(inode)->createtime) {
+		stat->result_mask |= STATX_BTIME;
+		stat->btime =
+		      cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime));
+	}
+
+	stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED);
+	if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_COMPRESSED)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_ENCRYPTED)
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+
 	/*
 	 * If on a multiuser mount without unix extensions or cifsacl being
 	 * enabled, and the admin hasn't overridden them, set the ownership
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 7ca9808..62c88df 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -214,7 +214,7 @@
 	{STATUS_DATATYPE_MISALIGNMENT, -EIO, "STATUS_DATATYPE_MISALIGNMENT"},
 	{STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"},
 	{STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"},
-	{STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"},
+	{STATUS_BUFFER_OVERFLOW, -E2BIG, "STATUS_BUFFER_OVERFLOW"},
 	{STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"},
 	{STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"},
 	{STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"},
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index fb2934b..bdb963d 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -426,6 +426,7 @@
 	return rc;
 }
 
+#ifdef CONFIG_CIFS_XATTR
 static ssize_t
 move_smb2_ea_to_cifs(char *dst, size_t dst_size,
 		     struct smb2_file_full_ea_info *src, size_t src_size,
@@ -521,6 +522,7 @@
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
 	struct smb2_file_full_ea_info *smb2_data;
+	int ea_buf_size = SMB2_MIN_EA_BUF;
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
 	if (!utf16_path)
@@ -540,14 +542,32 @@
 		return rc;
 	}
 
-	smb2_data = kzalloc(SMB2_MAX_EA_BUF, GFP_KERNEL);
-	if (smb2_data == NULL) {
-		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
-		return -ENOMEM;
+	while (1) {
+		smb2_data = kzalloc(ea_buf_size, GFP_KERNEL);
+		if (smb2_data == NULL) {
+			SMB2_close(xid, tcon, fid.persistent_fid,
+				   fid.volatile_fid);
+			return -ENOMEM;
+		}
+
+		rc = SMB2_query_eas(xid, tcon, fid.persistent_fid,
+				    fid.volatile_fid,
+				    ea_buf_size, smb2_data);
+
+		if (rc != -E2BIG)
+			break;
+
+		kfree(smb2_data);
+		ea_buf_size <<= 1;
+
+		if (ea_buf_size > SMB2_MAX_EA_BUF) {
+			cifs_dbg(VFS, "EA size is too large\n");
+			SMB2_close(xid, tcon, fid.persistent_fid,
+				   fid.volatile_fid);
+			return -ENOMEM;
+		}
 	}
 
-	rc = SMB2_query_eas(xid, tcon, fid.persistent_fid, fid.volatile_fid,
-			    smb2_data);
 	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 
 	if (!rc)
@@ -613,6 +633,7 @@
 
 	return rc;
 }
+#endif
 
 static bool
 smb2_can_echo(struct TCP_Server_Info *server)
@@ -3110,6 +3131,46 @@
 	.create_lease_size = sizeof(struct create_lease),
 };
 
+struct smb_version_values smb3any_values = {
+	.version_string = SMB3ANY_VERSION_STRING,
+	.protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */
+	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION,
+	.large_lock_type = 0,
+	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
+	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
+	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
+	.header_size = sizeof(struct smb2_hdr),
+	.max_header_size = MAX_SMB2_HDR_SIZE,
+	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
+	.lock_cmd = SMB2_LOCK,
+	.cap_unix = 0,
+	.cap_nt_find = SMB2_NT_FIND,
+	.cap_large_files = SMB2_LARGE_FILES,
+	.signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
+	.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+	.create_lease_size = sizeof(struct create_lease_v2),
+};
+
+struct smb_version_values smbdefault_values = {
+	.version_string = SMBDEFAULT_VERSION_STRING,
+	.protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */
+	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION,
+	.large_lock_type = 0,
+	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
+	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
+	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
+	.header_size = sizeof(struct smb2_hdr),
+	.max_header_size = MAX_SMB2_HDR_SIZE,
+	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
+	.lock_cmd = SMB2_LOCK,
+	.cap_unix = 0,
+	.cap_nt_find = SMB2_NT_FIND,
+	.cap_large_files = SMB2_LARGE_FILES,
+	.signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
+	.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+	.create_lease_size = sizeof(struct create_lease_v2),
+};
+
 struct smb_version_values smb30_values = {
 	.version_string = SMB30_VERSION_STRING,
 	.protocol_id = SMB30_PROT_ID,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 5531e7e..5331631 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -439,7 +439,7 @@
 	build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt);
 	req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
 	req->NegotiateContextCount = cpu_to_le16(2);
-	inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + 2
+	inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context)
 			+ sizeof(struct smb2_encryption_neg_context)); /* calculate hash */
 }
 #else
@@ -491,10 +491,25 @@
 
 	req->hdr.sync_hdr.SessionId = 0;
 
-	req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id);
-
-	req->DialectCount = cpu_to_le16(1); /* One vers= at a time for now */
-	inc_rfc1001_len(req, 2);
+	if (strcmp(ses->server->vals->version_string,
+		   SMB3ANY_VERSION_STRING) == 0) {
+		req->Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
+		req->Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
+		req->DialectCount = cpu_to_le16(2);
+		inc_rfc1001_len(req, 4);
+	} else if (strcmp(ses->server->vals->version_string,
+		   SMBDEFAULT_VERSION_STRING) == 0) {
+		req->Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
+		req->Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
+		req->Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
+		req->DialectCount = cpu_to_le16(3);
+		inc_rfc1001_len(req, 6);
+	} else {
+		/* otherwise send specific dialect */
+		req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id);
+		req->DialectCount = cpu_to_le16(1);
+		inc_rfc1001_len(req, 2);
+	}
 
 	/* only one of SMB2 signing flags may be set in SMB2 request */
 	if (ses->sign)
@@ -528,16 +543,43 @@
 	 */
 	if (rc == -EOPNOTSUPP) {
 		cifs_dbg(VFS, "Dialect not supported by server. Consider "
-			"specifying vers=1.0 or vers=2.1 on mount for accessing"
+			"specifying vers=1.0 or vers=2.0 on mount for accessing"
 			" older servers\n");
 		goto neg_exit;
 	} else if (rc != 0)
 		goto neg_exit;
 
+	if (strcmp(ses->server->vals->version_string,
+		   SMB3ANY_VERSION_STRING) == 0) {
+		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
+			cifs_dbg(VFS,
+				"SMB2 dialect returned but not requested\n");
+			return -EIO;
+		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
+			cifs_dbg(VFS,
+				"SMB2.1 dialect returned but not requested\n");
+			return -EIO;
+		}
+	} else if (strcmp(ses->server->vals->version_string,
+		   SMBDEFAULT_VERSION_STRING) == 0) {
+		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
+			cifs_dbg(VFS,
+				"SMB2 dialect returned but not requested\n");
+			return -EIO;
+		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
+			/* ops set to 3.0 by default for default so update */
+			ses->server->ops = &smb21_operations;
+		}
+	} else if (le16_to_cpu(rsp->DialectRevision) !=
+				ses->server->vals->protocol_id) {
+		/* if requested single dialect ensure returned dialect matched */
+		cifs_dbg(VFS, "Illegal 0x%x dialect returned: not requested\n",
+			le16_to_cpu(rsp->DialectRevision));
+		return -EIO;
+	}
+
 	cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode);
 
-	/* BB we may eventually want to match the negotiated vs. requested
-	   dialect, even though we are only requesting one at a time */
 	if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID))
 		cifs_dbg(FYI, "negotiated smb2.0 dialect\n");
 	else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID))
@@ -558,6 +600,8 @@
 	}
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
+	/* BB: add check that dialect was valid given dialect(s) we asked for */
+
 	/* SMB2 only has an extended negflavor */
 	server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
 	/* set it to the maximum buffer size value we can send with 1 credit */
@@ -604,22 +648,30 @@
 {
 	int rc = 0;
 	struct validate_negotiate_info_req vneg_inbuf;
-	struct validate_negotiate_info_rsp *pneg_rsp;
+	struct validate_negotiate_info_rsp *pneg_rsp = NULL;
 	u32 rsplen;
+	u32 inbuflen; /* max of 4 dialects */
 
 	cifs_dbg(FYI, "validate negotiate\n");
 
 	/*
 	 * validation ioctl must be signed, so no point sending this if we
-	 * can not sign it.  We could eventually change this to selectively
+	 * can not sign it (ie are not known user).  Even if signing is not
+	 * required (enabled but not negotiated), in those cases we selectively
 	 * sign just this, the first and only signed request on a connection.
-	 * This is good enough for now since a user who wants better security
-	 * would also enable signing on the mount. Having validation of
-	 * negotiate info for signed connections helps reduce attack vectors
+	 * Having validation of negotiate info  helps reduce attack vectors.
 	 */
-	if (tcon->ses->server->sign == false)
+	if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST)
 		return 0; /* validation requires signing */
 
+	if (tcon->ses->user_name == NULL) {
+		cifs_dbg(FYI, "Can't validate negotiate: null user mount\n");
+		return 0; /* validation requires signing */
+	}
+
+	if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
+		cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n");
+
 	vneg_inbuf.Capabilities =
 			cpu_to_le32(tcon->ses->server->vals->req_capabilities);
 	memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
@@ -634,9 +686,30 @@
 	else
 		vneg_inbuf.SecurityMode = 0;
 
-	vneg_inbuf.DialectCount = cpu_to_le16(1);
-	vneg_inbuf.Dialects[0] =
-		cpu_to_le16(tcon->ses->server->vals->protocol_id);
+
+	if (strcmp(tcon->ses->server->vals->version_string,
+		SMB3ANY_VERSION_STRING) == 0) {
+		vneg_inbuf.Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
+		vneg_inbuf.Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
+		vneg_inbuf.DialectCount = cpu_to_le16(2);
+		/* structure is big enough for 3 dialects, sending only 2 */
+		inbuflen = sizeof(struct validate_negotiate_info_req) - 2;
+	} else if (strcmp(tcon->ses->server->vals->version_string,
+		SMBDEFAULT_VERSION_STRING) == 0) {
+		vneg_inbuf.Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
+		vneg_inbuf.Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
+		vneg_inbuf.Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
+		vneg_inbuf.DialectCount = cpu_to_le16(3);
+		/* structure is big enough for 3 dialects */
+		inbuflen = sizeof(struct validate_negotiate_info_req);
+	} else {
+		/* otherwise specific dialect was requested */
+		vneg_inbuf.Dialects[0] =
+			cpu_to_le16(tcon->ses->server->vals->protocol_id);
+		vneg_inbuf.DialectCount = cpu_to_le16(1);
+		/* structure is big enough for 3 dialects, sending only 1 */
+		inbuflen = sizeof(struct validate_negotiate_info_req) - 4;
+	}
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
@@ -654,8 +727,9 @@
 			 rsplen);
 
 		/* relax check since Mac returns max bufsize allowed on ioctl */
-		if (rsplen > CIFSMaxBufSize)
-			return -EIO;
+		if ((rsplen > CIFSMaxBufSize)
+		     || (rsplen < sizeof(struct validate_negotiate_info_rsp)))
+			goto err_rsp_free;
 	}
 
 	/* check validate negotiate info response matches what we got earlier */
@@ -674,10 +748,13 @@
 
 	/* validate negotiate successful */
 	cifs_dbg(FYI, "validate negotiate info successful\n");
+	kfree(pneg_rsp);
 	return 0;
 
 vneg_out:
 	cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n");
+err_rsp_free:
+	kfree(pneg_rsp);
 	return -EIO;
 }
 
@@ -1110,6 +1187,8 @@
 	while (sess_data->func)
 		sess_data->func(sess_data);
 
+	if ((ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) && (ses->sign))
+		cifs_dbg(VFS, "signing requested but authenticated as guest\n");
 	rc = sess_data->result;
 out:
 	kfree(sess_data);
@@ -1180,7 +1259,7 @@
 	struct smb2_tree_connect_req *req;
 	struct smb2_tree_connect_rsp *rsp = NULL;
 	struct kvec iov[2];
-	struct kvec rsp_iov;
+	struct kvec rsp_iov = { NULL, 0 };
 	int rc = 0;
 	int resp_buftype;
 	int unc_path_len;
@@ -1297,7 +1376,7 @@
 	return rc;
 
 tcon_error_exit:
-	if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
+	if (rsp && rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
 	}
 	goto tcon_exit;
@@ -1634,7 +1713,7 @@
 	struct cifs_tcon *tcon = oparms->tcon;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[4];
-	struct kvec rsp_iov;
+	struct kvec rsp_iov = {NULL, 0};
 	int resp_buftype;
 	int uni_path_len;
 	__le16 *copy_path = NULL;
@@ -1763,7 +1842,7 @@
 
 	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
-		if (err_buf)
+		if (err_buf && rsp)
 			*err_buf = kmemdup(rsp, get_rfc1002_length(rsp) + 4,
 					   GFP_KERNEL);
 		goto creat_exit;
@@ -1900,6 +1979,9 @@
 	} else
 		iov[0].iov_len = get_rfc1002_length(req) + 4;
 
+	/* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */
+	if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO)
+		req->hdr.sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
 
 	rc = SendReceive2(xid, ses, iov, n_iov, &resp_buftype, flags, &rsp_iov);
 	cifs_small_buf_release(req);
@@ -2116,9 +2198,13 @@
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
 	req->AdditionalInformation = cpu_to_le32(additional_info);
-	/* 4 for rfc1002 length field and 1 for Buffer */
-	req->InputBufferOffset =
-		cpu_to_le16(sizeof(struct smb2_query_info_req) - 1 - 4);
+
+	/*
+	 * We do not use the input buffer (do not send extra byte)
+	 */
+	req->InputBufferOffset = 0;
+	inc_rfc1001_len(req, -1);
+
 	req->OutputBufferLength = cpu_to_le32(output_len);
 
 	iov[0].iov_base = (char *)req;
@@ -2158,12 +2244,12 @@
 }
 
 int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
-	u64 persistent_fid, u64 volatile_fid,
-	struct smb2_file_full_ea_info *data)
+		   u64 persistent_fid, u64 volatile_fid,
+		   int ea_buf_size, struct smb2_file_full_ea_info *data)
 {
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
 			  FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, 0,
-			  SMB2_MAX_EA_BUF,
+			  ea_buf_size,
 			  sizeof(struct smb2_file_full_ea_info),
 			  (void **)&data,
 			  NULL);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 393ed5f..c2ec934 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -716,7 +716,7 @@
 	__u8   Guid[SMB2_CLIENT_GUID_SIZE];
 	__le16 SecurityMode;
 	__le16 DialectCount;
-	__le16 Dialects[1]; /* dialect (someday maybe list) client asked for */
+	__le16 Dialects[3]; /* BB expand this if autonegotiate > 3 dialects */
 } __packed;
 
 struct validate_negotiate_info_rsp {
@@ -832,7 +832,7 @@
 /* Channel field for read and write: exactly one of following flags can be set*/
 #define SMB2_CHANNEL_NONE		0x00000000
 #define SMB2_CHANNEL_RDMA_V1		0x00000001 /* SMB3 or later */
-#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000001 /* SMB3.02 or later */
+#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000002 /* SMB3.02 or later */
 
 /* SMB2 read request without RFC1001 length at the beginning */
 struct smb2_read_plain_req {
@@ -1178,7 +1178,8 @@
 	char   FileName[0];     /* Name to be assigned to new link */
 } __packed; /* level 11 Set */
 
-#define SMB2_MAX_EA_BUF 2048
+#define SMB2_MIN_EA_BUF  2048
+#define SMB2_MAX_EA_BUF 65536
 
 struct smb2_file_full_ea_info { /* encoding of response for level 15 */
 	__le32 next_entry_offset;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 0032170..e9ab522 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -134,6 +134,7 @@
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
 			  u64 persistent_file_id, u64 volatile_file_id,
+			  int ea_buf_size,
 			  struct smb2_file_full_ea_info *data);
 extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 67367cf..9949394 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -390,6 +390,7 @@
 	return generate_smb3signingkey(ses, &triplet);
 }
 
+#ifdef CONFIG_CIFS_SMB311
 int
 generate_smb311signingkey(struct cifs_ses *ses)
 
@@ -398,25 +399,26 @@
 	struct derivation *d;
 
 	d = &triplet.signing;
-	d->label.iov_base = "SMB2AESCMAC";
-	d->label.iov_len = 12;
-	d->context.iov_base = "SmbSign";
-	d->context.iov_len = 8;
+	d->label.iov_base = "SMBSigningKey";
+	d->label.iov_len = 14;
+	d->context.iov_base = ses->preauth_sha_hash;
+	d->context.iov_len = 64;
 
 	d = &triplet.encryption;
-	d->label.iov_base = "SMB2AESCCM";
-	d->label.iov_len = 11;
-	d->context.iov_base = "ServerIn ";
-	d->context.iov_len = 10;
+	d->label.iov_base = "SMBC2SCipherKey";
+	d->label.iov_len = 16;
+	d->context.iov_base = ses->preauth_sha_hash;
+	d->context.iov_len = 64;
 
 	d = &triplet.decryption;
-	d->label.iov_base = "SMB2AESCCM";
-	d->label.iov_len = 11;
-	d->context.iov_base = "ServerOut";
-	d->context.iov_len = 10;
+	d->label.iov_base = "SMBS2CCipherKey";
+	d->label.iov_len = 16;
+	d->context.iov_base = ses->preauth_sha_hash;
+	d->context.iov_len = 64;
 
 	return generate_smb3signingkey(ses, &triplet);
 }
+#endif /* 311 */
 
 int
 smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 018c588..8e704d1 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -109,6 +109,11 @@
 		goto out;
 	}
 	ukp = user_key_payload_locked(keyring_key);
+	if (!ukp) {
+		/* key was revoked before we acquired its semaphore */
+		res = -EKEYREVOKED;
+		goto out;
+	}
 	if (ukp->datalen != sizeof(struct fscrypt_key)) {
 		res = -EINVAL;
 		goto out;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 5fa2211..b53e66d 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -45,6 +45,12 @@
 #define DIO_PAGES	64
 
 /*
+ * Flags for dio_complete()
+ */
+#define DIO_COMPLETE_ASYNC		0x01	/* This is async IO */
+#define DIO_COMPLETE_INVALIDATE		0x02	/* Can invalidate pages */
+
+/*
  * This code generally works in units of "dio_blocks".  A dio_block is
  * somewhere between the hard sector size and the filesystem block size.  it
  * is determined on a per-invocation basis.   When talking to the filesystem
@@ -225,10 +231,11 @@
  * filesystems can use it to hold additional state between get_block calls and
  * dio_complete.
  */
-static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
+static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
 {
 	loff_t offset = dio->iocb->ki_pos;
 	ssize_t transferred = 0;
+	int err;
 
 	/*
 	 * AIO submission can race with bio completion to get here while
@@ -259,18 +266,37 @@
 		ret = transferred;
 
 	if (dio->end_io) {
-		int err;
-
 		// XXX: ki_pos??
 		err = dio->end_io(dio->iocb, offset, ret, dio->private);
 		if (err)
 			ret = err;
 	}
 
+	/*
+	 * Try again to invalidate clean pages which might have been cached by
+	 * non-direct readahead, or faulted in by get_user_pages() if the source
+	 * of the write was an mmap'ed region of the file we're writing.  Either
+	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
+	 * this invalidation fails, tough, the write still worked...
+	 *
+	 * And this page cache invalidation has to be after dio->end_io(), as
+	 * some filesystems convert unwritten extents to real allocations in
+	 * end_io() when necessary, otherwise a racing buffer read would cache
+	 * zeros from unwritten extents.
+	 */
+	if (flags & DIO_COMPLETE_INVALIDATE &&
+	    ret > 0 && dio->op == REQ_OP_WRITE &&
+	    dio->inode->i_mapping->nrpages) {
+		err = invalidate_inode_pages2_range(dio->inode->i_mapping,
+					offset >> PAGE_SHIFT,
+					(offset + ret - 1) >> PAGE_SHIFT);
+		WARN_ON_ONCE(err);
+	}
+
 	if (!(dio->flags & DIO_SKIP_DIO_COUNT))
 		inode_dio_end(dio->inode);
 
-	if (is_async) {
+	if (flags & DIO_COMPLETE_ASYNC) {
 		/*
 		 * generic_write_sync expects ki_pos to have been updated
 		 * already, but the submission path only does this for
@@ -291,7 +317,7 @@
 {
 	struct dio *dio = container_of(work, struct dio, complete_work);
 
-	dio_complete(dio, 0, true);
+	dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE);
 }
 
 static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio);
@@ -304,6 +330,7 @@
 	struct dio *dio = bio->bi_private;
 	unsigned long remaining;
 	unsigned long flags;
+	bool defer_completion = false;
 
 	/* cleanup the bio */
 	dio_bio_complete(dio, bio);
@@ -315,12 +342,24 @@
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
 	if (remaining == 0) {
-		if (dio->result && dio->defer_completion) {
+		/*
+		 * Defer completion when defer_completion is set or
+		 * when the inode has pages mapped and this is AIO write.
+		 * We need to invalidate those pages because there is a
+		 * chance they contain stale data in the case buffered IO
+		 * went in between AIO submission and completion into the
+		 * same region.
+		 */
+		if (dio->result)
+			defer_completion = dio->defer_completion ||
+					   (dio->op == REQ_OP_WRITE &&
+					    dio->inode->i_mapping->nrpages);
+		if (defer_completion) {
 			INIT_WORK(&dio->complete_work, dio_aio_complete_work);
 			queue_work(dio->inode->i_sb->s_dio_done_wq,
 				   &dio->complete_work);
 		} else {
-			dio_complete(dio, 0, true);
+			dio_complete(dio, 0, DIO_COMPLETE_ASYNC);
 		}
 	}
 }
@@ -838,7 +877,8 @@
 	 */
 	if (sdio->boundary) {
 		ret = dio_send_cur_page(dio, sdio, map_bh);
-		dio_bio_submit(dio, sdio);
+		if (sdio->bio)
+			dio_bio_submit(dio, sdio);
 		put_page(sdio->cur_page);
 		sdio->cur_page = NULL;
 	}
@@ -1210,10 +1250,19 @@
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
 	 * so that we can call ->fsync.
 	 */
-	if (dio->is_async && iov_iter_rw(iter) == WRITE &&
-	    ((iocb->ki_filp->f_flags & O_DSYNC) ||
-	     IS_SYNC(iocb->ki_filp->f_mapping->host))) {
-		retval = dio_set_defer_completion(dio);
+	if (dio->is_async && iov_iter_rw(iter) == WRITE) {
+		retval = 0;
+		if ((iocb->ki_filp->f_flags & O_DSYNC) ||
+		    IS_SYNC(iocb->ki_filp->f_mapping->host))
+			retval = dio_set_defer_completion(dio);
+		else if (!dio->inode->i_sb->s_dio_done_wq) {
+			/*
+			 * In case of AIO write racing with buffered read we
+			 * need to defer completion. We can't decide this now,
+			 * however the workqueue needs to be initialized here.
+			 */
+			retval = sb_init_dio_done_wq(dio->inode->i_sb);
+		}
 		if (retval) {
 			/*
 			 * We grab i_mutex only for reads so we don't have
@@ -1322,7 +1371,7 @@
 		dio_await_completion(dio);
 
 	if (drop_refcount(dio) == 0) {
-		retval = dio_complete(dio, retval, false);
+		retval = dio_complete(dio, retval, DIO_COMPLETE_INVALIDATE);
 	} else
 		BUG_ON(retval != -EIOCBQUEUED);
 
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 9c351bf..3fbc0ff 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -84,11 +84,16 @@
 static inline struct ecryptfs_auth_tok *
 ecryptfs_get_encrypted_key_payload_data(struct key *key)
 {
-	if (key->type == &key_type_encrypted)
-		return (struct ecryptfs_auth_tok *)
-			(&((struct encrypted_key_payload *)key->payload.data[0])->payload_data);
-	else
+	struct encrypted_key_payload *payload;
+
+	if (key->type != &key_type_encrypted)
 		return NULL;
+
+	payload = key->payload.data[0];
+	if (!payload)
+		return ERR_PTR(-EKEYREVOKED);
+
+	return (struct ecryptfs_auth_tok *)payload->payload_data;
 }
 
 static inline struct key *ecryptfs_get_encrypted_key(char *sig)
@@ -114,12 +119,17 @@
 ecryptfs_get_key_payload_data(struct key *key)
 {
 	struct ecryptfs_auth_tok *auth_tok;
+	struct user_key_payload *ukp;
 
 	auth_tok = ecryptfs_get_encrypted_key_payload_data(key);
-	if (!auth_tok)
-		return (struct ecryptfs_auth_tok *)user_key_payload_locked(key)->data;
-	else
+	if (auth_tok)
 		return auth_tok;
+
+	ukp = user_key_payload_locked(key);
+	if (!ukp)
+		return ERR_PTR(-EKEYREVOKED);
+
+	return (struct ecryptfs_auth_tok *)ukp->data;
 }
 
 #define ECRYPTFS_MAX_KEYSET_SIZE 1024
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 3cf1546..fa218cd 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -459,7 +459,8 @@
  * @auth_tok_key: key containing the authentication token
  * @auth_tok: authentication token
  *
- * Returns zero on valid auth tok; -EINVAL otherwise
+ * Returns zero on valid auth tok; -EINVAL if the payload is invalid; or
+ * -EKEYREVOKED if the key was revoked before we acquired its semaphore.
  */
 static int
 ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key,
@@ -468,6 +469,12 @@
 	int rc = 0;
 
 	(*auth_tok) = ecryptfs_get_key_payload_data(auth_tok_key);
+	if (IS_ERR(*auth_tok)) {
+		rc = PTR_ERR(*auth_tok);
+		*auth_tok = NULL;
+		goto out;
+	}
+
 	if (ecryptfs_verify_version((*auth_tok)->version)) {
 		printk(KERN_ERR "Data structure version mismatch. Userspace "
 		       "tools must match eCryptfs kernel module with major "
diff --git a/fs/exec.c b/fs/exec.c
index ac34d97..3e14ba2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1410,7 +1410,7 @@
 	kfree(bprm);
 }
 
-int bprm_change_interp(char *interp, struct linux_binprm *bprm)
+int bprm_change_interp(const char *interp, struct linux_binprm *bprm)
 {
 	/* If a binfmt changed the interp, free it first. */
 	if (bprm->interp != bprm->filename)
@@ -1802,6 +1802,7 @@
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
+	membarrier_execve(current);
 	acct_update_integrals(current);
 	task_numa_free(current);
 	free_bprm(bprm);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b104096..b0915b7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1677,7 +1677,7 @@
 		sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
 		return 1;
 	case Opt_i_version:
-		sb->s_flags |= MS_I_VERSION;
+		sb->s_flags |= SB_I_VERSION;
 		return 1;
 	case Opt_lazytime:
 		sb->s_flags |= MS_LAZYTIME;
@@ -2060,7 +2060,7 @@
 		SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
 	if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
 		SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
-	if (sb->s_flags & MS_I_VERSION)
+	if (sb->s_flags & SB_I_VERSION)
 		SEQ_OPTS_PUTS("i_version");
 	if (nodefs || sbi->s_stripe)
 		SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9a7c903..4b4a72f 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2525,7 +2525,7 @@
 bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
 void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
 void stop_discard_thread(struct f2fs_sb_info *sbi);
-void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
+void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount);
 void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void release_discard_addrs(struct f2fs_sb_info *sbi);
 int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 621b9b3..c695ff4 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1210,11 +1210,11 @@
 }
 
 /* This comes from f2fs_put_super and f2fs_trim_fs */
-void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
+void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount)
 {
 	__issue_discard_cmd(sbi, false);
 	__drop_discard_cmd(sbi);
-	__wait_discard_cmd(sbi, false);
+	__wait_discard_cmd(sbi, !umount);
 }
 
 static void mark_discard_range_all(struct f2fs_sb_info *sbi)
@@ -2244,7 +2244,7 @@
 	}
 	/* It's time to issue all the filed discards */
 	mark_discard_range_all(sbi);
-	f2fs_wait_discard_bios(sbi);
+	f2fs_wait_discard_bios(sbi, false);
 out:
 	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
 	return err;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 89f61eb..933c3d5 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -801,7 +801,7 @@
 	}
 
 	/* be sure to wait for any on-going discard commands */
-	f2fs_wait_discard_bios(sbi);
+	f2fs_wait_discard_bios(sbi, true);
 
 	if (f2fs_discard_en(sbi) && !sbi->discard_blks) {
 		struct cp_control cpc = {
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 0491da3..448a111 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -749,7 +749,7 @@
 			 * specific si_codes.  In that case use SI_SIGIO instead
 			 * to remove the ambiguity.
 			 */
-			if (sig_specific_sicodes(signum))
+			if ((signum != SIGPOLL) && sig_specific_sicodes(signum))
 				si.si_code = SI_SIGIO;
 
 			/* Make sure we are called with one of the POLL_*
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index b5ab06f..0438d4c 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -331,6 +331,13 @@
 	rcu_read_lock();
 
 	confkey = user_key_payload_rcu(key);
+	if (!confkey) {
+		/* key was revoked */
+		rcu_read_unlock();
+		key_put(key);
+		goto no_config;
+	}
+
 	buf = confkey->data;
 
 	for (len = confkey->datalen - 1; len >= 0; len--) {
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 622081b..2496738 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1308,7 +1308,8 @@
 			*/
 			over = !dir_emit(ctx, dirent->name, dirent->namelen,
 				       dirent->ino, dirent->type);
-			ctx->pos = dirent->off;
+			if (!over)
+				ctx->pos = dirent->off;
 		}
 
 		buf += reclen;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 65c8837..94a745a 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1059,7 +1059,7 @@
 	if (sb->s_flags & MS_MANDLOCK)
 		goto err;
 
-	sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION);
+	sb->s_flags &= ~(MS_NOSEC | SB_I_VERSION);
 
 	if (!parse_fuse_opt(data, &d, is_bdev))
 		goto err;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 98e845b..11066d8 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1945,13 +1945,9 @@
 {
 	struct gfs2_glock_iter *gi = seq->private;
 	loff_t n = *pos;
-	int ret;
 
-	if (gi->last_pos <= *pos)
-		n = (*pos - gi->last_pos);
-
-	ret = rhashtable_walk_start(&gi->hti);
-	if (ret)
+	rhashtable_walk_enter(&gl_hash_table, &gi->hti);
+	if (rhashtable_walk_start(&gi->hti) != 0)
 		return NULL;
 
 	do {
@@ -1959,6 +1955,7 @@
 	} while (gi->gl && n--);
 
 	gi->last_pos = *pos;
+
 	return gi->gl;
 }
 
@@ -1970,6 +1967,7 @@
 	(*pos)++;
 	gi->last_pos = *pos;
 	gfs2_glock_iter_next(gi);
+
 	return gi->gl;
 }
 
@@ -1980,6 +1978,7 @@
 
 	gi->gl = NULL;
 	rhashtable_walk_stop(&gi->hti);
+	rhashtable_walk_exit(&gi->hti);
 }
 
 static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
@@ -2042,12 +2041,10 @@
 		struct gfs2_glock_iter *gi = seq->private;
 
 		gi->sdp = inode->i_private;
-		gi->last_pos = 0;
 		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
 		if (seq->buf)
 			seq->size = GFS2_SEQ_GOODSIZE;
 		gi->gl = NULL;
-		rhashtable_walk_enter(&gl_hash_table, &gi->hti);
 	}
 	return ret;
 }
@@ -2063,7 +2060,6 @@
 	struct gfs2_glock_iter *gi = seq->private;
 
 	gi->gl = NULL;
-	rhashtable_walk_exit(&gi->hti);
 	return seq_release_private(inode, file);
 }
 
diff --git a/fs/iomap.c b/fs/iomap.c
index 269b24a..d4801f8 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -713,6 +713,8 @@
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	struct kiocb *iocb = dio->iocb;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
 	if (dio->end_io) {
@@ -726,12 +728,33 @@
 	if (likely(!ret)) {
 		ret = dio->size;
 		/* check for short read */
-		if (iocb->ki_pos + ret > dio->i_size &&
+		if (offset + ret > dio->i_size &&
 		    !(dio->flags & IOMAP_DIO_WRITE))
-			ret = dio->i_size - iocb->ki_pos;
+			ret = dio->i_size - offset;
 		iocb->ki_pos += ret;
 	}
 
+	/*
+	 * Try again to invalidate clean pages which might have been cached by
+	 * non-direct readahead, or faulted in by get_user_pages() if the source
+	 * of the write was an mmap'ed region of the file we're writing.  Either
+	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
+	 * this invalidation fails, tough, the write still worked...
+	 *
+	 * And this page cache invalidation has to be after dio->end_io(), as
+	 * some filesystems convert unwritten extents to real allocations in
+	 * end_io() when necessary, otherwise a racing buffer read would cache
+	 * zeros from unwritten extents.
+	 */
+	if (!dio->error &&
+	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+		int err;
+		err = invalidate_inode_pages2_range(inode->i_mapping,
+				offset >> PAGE_SHIFT,
+				(offset + dio->size - 1) >> PAGE_SHIFT);
+		WARN_ON_ONCE(err);
+	}
+
 	inode_dio_end(file_inode(iocb->ki_filp));
 	kfree(dio);
 
@@ -993,6 +1016,13 @@
 	WARN_ON_ONCE(ret);
 	ret = 0;
 
+	if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
+	    !inode->i_sb->s_dio_done_wq) {
+		ret = sb_init_dio_done_wq(inode->i_sb);
+		if (ret < 0)
+			goto out_free_dio;
+	}
+
 	inode_dio_begin(inode);
 
 	blk_start_plug(&plug);
@@ -1015,13 +1045,6 @@
 	if (ret < 0)
 		iomap_dio_set_error(dio, ret);
 
-	if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
-			!inode->i_sb->s_dio_done_wq) {
-		ret = sb_init_dio_done_wq(inode->i_sb);
-		if (ret < 0)
-			iomap_dio_set_error(dio, ret);
-	}
-
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!is_sync_kiocb(iocb))
 			return -EIOCBQUEUED;
@@ -1042,19 +1065,6 @@
 
 	ret = iomap_dio_complete(dio);
 
-	/*
-	 * Try again to invalidate clean pages which might have been cached by
-	 * non-direct readahead, or faulted in by get_user_pages() if the source
-	 * of the write was an mmap'ed region of the file we're writing.  Either
-	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
-	 * this invalidation fails, tough, the write still worked...
-	 */
-	if (iov_iter_rw(iter) == WRITE) {
-		int err = invalidate_inode_pages2_range(mapping,
-				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(err);
-	}
-
 	return ret;
 
 out_free_dio:
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index db692f5..447a24d 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -514,9 +514,11 @@
 	if (sbi->s_fmode != ISOFS_INVALID_MODE)
 		seq_printf(m, ",fmode=%o", sbi->s_fmode);
 
+#ifdef CONFIG_JOLIET
 	if (sbi->s_nls_iocharset &&
 	    strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0)
 		seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset);
+#endif
 	return 0;
 }
 
diff --git a/fs/mpage.c b/fs/mpage.c
index 37bb77c..c991fae 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -468,6 +468,16 @@
 		try_to_free_buffers(page);
 }
 
+/*
+ * For situations where we want to clean all buffers attached to a page.
+ * We don't need to calculate how many buffers are attached to the page,
+ * we just need to specify a number larger than the maximum number of buffers.
+ */
+void clean_page_buffers(struct page *page)
+{
+	clean_buffers(page, ~0U);
+}
+
 static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 		      void *data)
 {
@@ -605,10 +615,8 @@
 	if (bio == NULL) {
 		if (first_unmapped == blocks_per_page) {
 			if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9),
-								page, wbc)) {
-				clean_buffers(page, first_unmapped);
+								page, wbc))
 				goto out;
-			}
 		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
 				BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
diff --git a/fs/namespace.c b/fs/namespace.c
index 54059b1..d18deb4 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -468,7 +468,9 @@
 
 	/* File refers to upper, writable layer? */
 	upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER);
-	if (upperdentry && file_inode(file) == d_inode(upperdentry))
+	if (upperdentry &&
+	    (file_inode(file) == d_inode(upperdentry) ||
+	     file_inode(file) == d_inode(dentry)))
 		return 0;
 
 	/* Lower layer: can't write to real file, sorry... */
@@ -2823,7 +2825,8 @@
 			    SB_MANDLOCK |
 			    SB_DIRSYNC |
 			    SB_SILENT |
-			    SB_POSIXACL);
+			    SB_POSIXACL |
+			    SB_I_VERSION);
 
 	if (flags & MS_REMOUNT)
 		retval = do_remount(&path, flags, sb_flags, mnt_flags,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index efebe6c..22880ef 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -218,7 +218,6 @@
 static void pnfs_init_server(struct nfs_server *server)
 {
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
-	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 }
 
 #else
@@ -888,6 +887,7 @@
 	ida_init(&server->openowner_id);
 	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
+	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 
 	return server;
 }
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 44c638b..508126e 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -745,7 +745,8 @@
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
 
 	dprintk("--> %s\n", __func__);
-	nfs4_fl_put_deviceid(fl->dsaddr);
+	if (fl->dsaddr != NULL)
+		nfs4_fl_put_deviceid(fl->dsaddr);
 	/* This assumes a single RW lseg */
 	if (lseg->pls_range.iomode == IOMODE_RW) {
 		struct nfs4_filelayout *flo;
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index dd5d27d..30426c1 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -274,7 +274,7 @@
 	ssize_t ret;
 
 	ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc);
-	if (ret <= 0)
+	if (ret < 0)
 		return ERR_PTR(ret);
 
 	rkey = request_key(&key_type_id_resolver, desc, "");
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6c61e2b..f90090e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8399,8 +8399,7 @@
 		lo = NFS_I(inode)->layout;
 		/* If the open stateid was bad, then recover it. */
 		if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) ||
-		    nfs4_stateid_match_other(&lgp->args.stateid,
-					&lgp->args.ctx->state->stateid)) {
+		    !nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
 			spin_unlock(&inode->i_lock);
 			exception->state = lgp->args.ctx->state;
 			exception->stateid = &lgp->args.stateid;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 37c8af0..14ed979 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1842,8 +1842,8 @@
 	 * Assumes OPEN is the biggest non-idempotent compound.
 	 * 2 is the verifier.
 	 */
-	max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE +
-			      RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT;
+	max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + 2)
+				* XDR_UNIT + RPC_MAX_AUTH_SIZE;
 
 	encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr);
 	p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 3c69db7..8487486 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -927,6 +927,13 @@
 		exp_put(u->secinfo.si_exp);
 }
 
+static void
+nfsd4_secinfo_no_name_release(union nfsd4_op_u *u)
+{
+	if (u->secinfo_no_name.sin_exp)
+		exp_put(u->secinfo_no_name.sin_exp);
+}
+
 static __be32
 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	      union nfsd4_op_u *u)
@@ -2375,7 +2382,7 @@
 	},
 	[OP_SECINFO_NO_NAME] = {
 		.op_func = nfsd4_secinfo_no_name,
-		.op_release = nfsd4_secinfo_release,
+		.op_release = nfsd4_secinfo_no_name_release,
 		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_SECINFO_NO_NAME",
 		.op_rsize_bop = nfsd4_secinfo_rsize,
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aad97b3..c441f93 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -561,10 +561,8 @@
 		c->tmpfile = true;
 		err = ovl_copy_up_locked(c);
 	} else {
-		err = -EIO;
-		if (lock_rename(c->workdir, c->destdir) != NULL) {
-			pr_err("overlayfs: failed to lock workdir+upperdir\n");
-		} else {
+		err = ovl_lock_rename_workdir(c->workdir, c->destdir);
+		if (!err) {
 			err = ovl_copy_up_locked(c);
 			unlock_rename(c->workdir, c->destdir);
 		}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 3309b19..cc961a3 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -216,26 +216,6 @@
 	return err;
 }
 
-static int ovl_lock_rename_workdir(struct dentry *workdir,
-				   struct dentry *upperdir)
-{
-	/* Workdir should not be the same as upperdir */
-	if (workdir == upperdir)
-		goto err;
-
-	/* Workdir should not be subdir of upperdir and vice versa */
-	if (lock_rename(workdir, upperdir) != NULL)
-		goto err_unlock;
-
-	return 0;
-
-err_unlock:
-	unlock_rename(workdir, upperdir);
-err:
-	pr_err("overlayfs: failed to lock workdir+upperdir\n");
-	return -EIO;
-}
-
 static struct dentry *ovl_clear_empty(struct dentry *dentry,
 				      struct list_head *list)
 {
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index a619add..321511e 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -598,18 +598,30 @@
 	return true;
 }
 
-struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry)
+struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
+			    struct dentry *index)
 {
 	struct dentry *lowerdentry = ovl_dentry_lower(dentry);
 	struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL;
 	struct inode *inode;
+	/* Already indexed or could be indexed on copy up? */
+	bool indexed = (index || (ovl_indexdir(dentry->d_sb) && !upperdentry));
+
+	if (WARN_ON(upperdentry && indexed && !lowerdentry))
+		return ERR_PTR(-EIO);
 
 	if (!realinode)
 		realinode = d_inode(lowerdentry);
 
-	if (!S_ISDIR(realinode->i_mode) &&
-	    (upperdentry || (lowerdentry && ovl_indexdir(dentry->d_sb)))) {
-		struct inode *key = d_inode(lowerdentry ?: upperdentry);
+	/*
+	 * Copy up origin (lower) may exist for non-indexed upper, but we must
+	 * not use lower as hash key in that case.
+	 * Hash inodes that are or could be indexed by origin inode and
+	 * non-indexed upper inodes that could be hard linked by upper inode.
+	 */
+	if (!S_ISDIR(realinode->i_mode) && (upperdentry || indexed)) {
+		struct inode *key = d_inode(indexed ? lowerdentry :
+						      upperdentry);
 		unsigned int nlink;
 
 		inode = iget5_locked(dentry->d_sb, (unsigned long) key,
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index c3addd1..a12dc10 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -405,14 +405,13 @@
 	 * be treated as stale (i.e. after unlink of the overlay inode).
 	 * We don't know the verification rules for directory and whiteout
 	 * index entries, because they have not been implemented yet, so return
-	 * EROFS if those entries are found to avoid corrupting an index that
-	 * was created by a newer kernel.
+	 * EINVAL if those entries are found to abort the mount to avoid
+	 * corrupting an index that was created by a newer kernel.
 	 */
-	err = -EROFS;
+	err = -EINVAL;
 	if (d_is_dir(index) || ovl_is_whiteout(index))
 		goto fail;
 
-	err = -EINVAL;
 	if (index->d_name.len < sizeof(struct ovl_fh)*2)
 		goto fail;
 
@@ -506,6 +505,11 @@
 
 	index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len);
 	if (IS_ERR(index)) {
+		err = PTR_ERR(index);
+		if (err == -ENOENT) {
+			index = NULL;
+			goto out;
+		}
 		pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n"
 				    "overlayfs: mount with '-o index=off' to disable inodes index.\n",
 				    d_inode(origin)->i_ino, name.len, name.name,
@@ -515,18 +519,9 @@
 
 	inode = d_inode(index);
 	if (d_is_negative(index)) {
-		if (upper && d_inode(origin)->i_nlink > 1) {
-			pr_warn_ratelimited("overlayfs: hard link with origin but no index (ino=%lu).\n",
-					    d_inode(origin)->i_ino);
-			goto fail;
-		}
-
-		dput(index);
-		index = NULL;
+		goto out_dput;
 	} else if (upper && d_inode(upper) != inode) {
-		pr_warn_ratelimited("overlayfs: wrong index found (index=%pd2, ino=%lu, upper ino=%lu).\n",
-				    index, inode->i_ino, d_inode(upper)->i_ino);
-		goto fail;
+		goto out_dput;
 	} else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) ||
 		   ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) {
 		/*
@@ -546,6 +541,11 @@
 	kfree(name.name);
 	return index;
 
+out_dput:
+	dput(index);
+	index = NULL;
+	goto out;
+
 fail:
 	dput(index);
 	index = ERR_PTR(-EIO);
@@ -634,6 +634,7 @@
 		}
 
 		if (d.redirect) {
+			err = -ENOMEM;
 			upperredirect = kstrdup(d.redirect, GFP_KERNEL);
 			if (!upperredirect)
 				goto out_put_upper;
@@ -708,7 +709,7 @@
 		upperdentry = dget(index);
 
 	if (upperdentry || ctr) {
-		inode = ovl_get_inode(dentry, upperdentry);
+		inode = ovl_get_inode(dentry, upperdentry, index);
 		err = PTR_ERR(inode);
 		if (IS_ERR(inode))
 			goto out_free_oe;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index d4e8c1a..d9a0edd 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -235,6 +235,7 @@
 void ovl_inuse_unlock(struct dentry *dentry);
 int ovl_nlink_start(struct dentry *dentry, bool *locked);
 void ovl_nlink_end(struct dentry *dentry, bool locked);
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir);
 
 static inline bool ovl_is_impuredir(struct dentry *dentry)
 {
@@ -285,7 +286,8 @@
 bool ovl_is_private_xattr(const char *name);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev);
-struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry);
+struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
+			    struct dentry *index);
 static inline void ovl_copyattr(struct inode *from, struct inode *to)
 {
 	to->i_uid = from->i_uid;
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 878a750..25d9b5a 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -37,6 +37,9 @@
 	bool noxattr;
 	/* sb common to all layers */
 	struct super_block *same_sb;
+	/* Did we take the inuse lock? */
+	bool upperdir_locked;
+	bool workdir_locked;
 };
 
 /* private information held for every overlayfs dentry */
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 62e9b22..698b74d 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -988,6 +988,7 @@
 			 struct path *lowerstack, unsigned int numlower)
 {
 	int err;
+	struct dentry *index = NULL;
 	struct inode *dir = dentry->d_inode;
 	struct path path = { .mnt = mnt, .dentry = dentry };
 	LIST_HEAD(list);
@@ -1007,8 +1008,6 @@
 
 	inode_lock_nested(dir, I_MUTEX_PARENT);
 	list_for_each_entry(p, &list, l_node) {
-		struct dentry *index;
-
 		if (p->name[0] == '.') {
 			if (p->len == 1)
 				continue;
@@ -1018,18 +1017,20 @@
 		index = lookup_one_len(p->name, dentry, p->len);
 		if (IS_ERR(index)) {
 			err = PTR_ERR(index);
+			index = NULL;
 			break;
 		}
 		err = ovl_verify_index(index, lowerstack, numlower);
-		if (err) {
-			if (err == -EROFS)
-				break;
+		/* Cleanup stale and orphan index entries */
+		if (err && (err == -ESTALE || err == -ENOENT))
 			err = ovl_cleanup(dir, index);
-			if (err)
-				break;
-		}
+		if (err)
+			break;
+
 		dput(index);
+		index = NULL;
 	}
+	dput(index);
 	inode_unlock(dir);
 out:
 	ovl_cache_free(&list);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index fd5ea4f..f5738e9 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -174,6 +174,9 @@
 {
 	struct ovl_inode *oi = kmem_cache_alloc(ovl_inode_cachep, GFP_KERNEL);
 
+	if (!oi)
+		return NULL;
+
 	oi->cache = NULL;
 	oi->redirect = NULL;
 	oi->version = 0;
@@ -211,9 +214,10 @@
 
 	dput(ufs->indexdir);
 	dput(ufs->workdir);
-	ovl_inuse_unlock(ufs->workbasedir);
+	if (ufs->workdir_locked)
+		ovl_inuse_unlock(ufs->workbasedir);
 	dput(ufs->workbasedir);
-	if (ufs->upper_mnt)
+	if (ufs->upper_mnt && ufs->upperdir_locked)
 		ovl_inuse_unlock(ufs->upper_mnt->mnt_root);
 	mntput(ufs->upper_mnt);
 	for (i = 0; i < ufs->numlower; i++)
@@ -881,9 +885,13 @@
 			goto out_put_upperpath;
 
 		err = -EBUSY;
-		if (!ovl_inuse_trylock(upperpath.dentry)) {
-			pr_err("overlayfs: upperdir is in-use by another mount\n");
+		if (ovl_inuse_trylock(upperpath.dentry)) {
+			ufs->upperdir_locked = true;
+		} else if (ufs->config.index) {
+			pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n");
 			goto out_put_upperpath;
+		} else {
+			pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
 		}
 
 		err = ovl_mount_dir(ufs->config.workdir, &workpath);
@@ -901,9 +909,13 @@
 		}
 
 		err = -EBUSY;
-		if (!ovl_inuse_trylock(workpath.dentry)) {
-			pr_err("overlayfs: workdir is in-use by another mount\n");
+		if (ovl_inuse_trylock(workpath.dentry)) {
+			ufs->workdir_locked = true;
+		} else if (ufs->config.index) {
+			pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n");
 			goto out_put_workpath;
+		} else {
+			pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
 		}
 
 		ufs->workbasedir = workpath.dentry;
@@ -1156,11 +1168,13 @@
 out_free_lowertmp:
 	kfree(lowertmp);
 out_unlock_workdentry:
-	ovl_inuse_unlock(workpath.dentry);
+	if (ufs->workdir_locked)
+		ovl_inuse_unlock(workpath.dentry);
 out_put_workpath:
 	path_put(&workpath);
 out_unlock_upperdentry:
-	ovl_inuse_unlock(upperpath.dentry);
+	if (ufs->upperdir_locked)
+		ovl_inuse_unlock(upperpath.dentry);
 out_put_upperpath:
 	path_put(&upperpath);
 out_free_config:
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 1177945..b9b239f 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -430,7 +430,7 @@
 	}
 }
 
-/* Called must hold OVL_I(inode)->oi_lock */
+/* Caller must hold OVL_I(inode)->lock */
 static void ovl_cleanup_index(struct dentry *dentry)
 {
 	struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode;
@@ -469,6 +469,9 @@
 	err = PTR_ERR(index);
 	if (!IS_ERR(index))
 		err = ovl_cleanup(dir, index);
+	else
+		index = NULL;
+
 	inode_unlock(dir);
 	if (err)
 		goto fail;
@@ -557,3 +560,22 @@
 		mutex_unlock(&OVL_I(d_inode(dentry))->lock);
 	}
 }
+
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir)
+{
+	/* Workdir should not be the same as upperdir */
+	if (workdir == upperdir)
+		goto err;
+
+	/* Workdir should not be subdir of upperdir and vice versa */
+	if (lock_rename(workdir, upperdir) != NULL)
+		goto err_unlock;
+
+	return 0;
+
+err_unlock:
+	unlock_rename(workdir, upperdir);
+err:
+	pr_err("overlayfs: failed to lock workdir+upperdir\n");
+	return -EIO;
+}
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 88c3555..77a8eac 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -62,6 +62,7 @@
 #include <linux/mman.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/numa_balancing.h>
+#include <linux/sched/task_stack.h>
 #include <linux/sched/task.h>
 #include <linux/sched/cputime.h>
 #include <linux/proc_fs.h>
@@ -118,30 +119,25 @@
  * simple bit tests.
  */
 static const char * const task_state_array[] = {
-	"R (running)",		/*   0 */
-	"S (sleeping)",		/*   1 */
-	"D (disk sleep)",	/*   2 */
-	"T (stopped)",		/*   4 */
-	"t (tracing stop)",	/*   8 */
-	"X (dead)",		/*  16 */
-	"Z (zombie)",		/*  32 */
+
+	/* states in TASK_REPORT: */
+	"R (running)",		/* 0x00 */
+	"S (sleeping)",		/* 0x01 */
+	"D (disk sleep)",	/* 0x02 */
+	"T (stopped)",		/* 0x04 */
+	"t (tracing stop)",	/* 0x08 */
+	"X (dead)",		/* 0x10 */
+	"Z (zombie)",		/* 0x20 */
+	"P (parked)",		/* 0x40 */
+
+	/* states beyond TASK_REPORT: */
+	"I (idle)",		/* 0x80 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
 {
-	unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT;
-
-	/*
-	 * Parked tasks do not run; they sit in __kthread_parkme().
-	 * Without this check, we would report them as running, which is
-	 * clearly wrong, so we report them as sleeping instead.
-	 */
-	if (tsk->state == TASK_PARKED)
-		state = TASK_INTERRUPTIBLE;
-
-	BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1);
-
-	return task_state_array[fls(state)];
+	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array));
+	return task_state_array[__get_task_state(tsk)];
 }
 
 static inline int get_task_umask(struct task_struct *tsk)
@@ -421,7 +417,15 @@
 		 * esp and eip are intentionally zeroed out.  There is no
 		 * non-racy way to read them without freezing the task.
 		 * Programs that need reliable values can use ptrace(2).
+		 *
+		 * The only exception is if the task is core dumping because
+		 * a program is not able to use ptrace(2) in that case. It is
+		 * safe because the task has stopped executing permanently.
 		 */
+		if (permitted && (task->flags & PF_DUMPCORE)) {
+			eip = KSTK_EIP(task);
+			esp = KSTK_ESP(task);
+		}
 	}
 
 	get_task_comm(tcomm, task);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 8381db9..52ad151 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1297,21 +1297,18 @@
 	spin_lock(&dquot->dq_dqb_lock);
 	if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) ||
 	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
-		goto add;
+		goto finish;
 
 	tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace
 		+ space + rsv_space;
 
-	if (flags & DQUOT_SPACE_NOFAIL)
-		goto add;
-
 	if (dquot->dq_dqb.dqb_bhardlimit &&
 	    tspace > dquot->dq_dqb.dqb_bhardlimit &&
             !ignore_hardlimit(dquot)) {
 		if (flags & DQUOT_SPACE_WARN)
 			prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN);
 		ret = -EDQUOT;
-		goto out;
+		goto finish;
 	}
 
 	if (dquot->dq_dqb.dqb_bsoftlimit &&
@@ -1322,7 +1319,7 @@
 		if (flags & DQUOT_SPACE_WARN)
 			prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN);
 		ret = -EDQUOT;
-		goto out;
+		goto finish;
 	}
 
 	if (dquot->dq_dqb.dqb_bsoftlimit &&
@@ -1338,13 +1335,21 @@
 			 * be always printed
 			 */
 			ret = -EDQUOT;
-			goto out;
+			goto finish;
 		}
 	}
-add:
-	dquot->dq_dqb.dqb_rsvspace += rsv_space;
-	dquot->dq_dqb.dqb_curspace += space;
-out:
+finish:
+	/*
+	 * We have to be careful and go through warning generation & grace time
+	 * setting even if DQUOT_SPACE_NOFAIL is set. That's why we check it
+	 * only here...
+	 */
+	if (flags & DQUOT_SPACE_NOFAIL)
+		ret = 0;
+	if (!ret) {
+		dquot->dq_dqb.dqb_rsvspace += rsv_space;
+		dquot->dq_dqb.dqb_curspace += space;
+	}
 	spin_unlock(&dquot->dq_dqb_lock);
 	return ret;
 }
@@ -1980,7 +1985,9 @@
 		ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0,
 				      &warn_to[cnt]);
 		if (ret) {
+			spin_lock(&transfer_to[cnt]->dq_dqb_lock);
 			dquot_decr_inodes(transfer_to[cnt], inode_usage);
+			spin_unlock(&transfer_to[cnt]->dq_dqb_lock);
 			goto over_quota;
 		}
 	}
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index c0187cd..a73e5b3 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -328,12 +328,16 @@
 	if (!dquot->dq_off) {
 		alloc = true;
 		down_write(&dqopt->dqio_sem);
+	} else {
+		down_read(&dqopt->dqio_sem);
 	}
 	ret = qtree_write_dquot(
 			sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv,
 			dquot);
 	if (alloc)
 		up_write(&dqopt->dqio_sem);
+	else
+		up_read(&dqopt->dqio_sem);
 	return ret;
 }
 
diff --git a/fs/read_write.c b/fs/read_write.c
index a2b9a47..f0d4b16 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -112,7 +112,7 @@
 		 * In the generic case the entire file is data, so as long as
 		 * offset isn't at the end of the file then the offset is data.
 		 */
-		if (offset >= eof)
+		if ((unsigned long long)offset >= eof)
 			return -ENXIO;
 		break;
 	case SEEK_HOLE:
@@ -120,7 +120,7 @@
 		 * There is a virtual hole at the end of the file, so as long as
 		 * offset isn't i_size or larger, return i_size.
 		 */
-		if (offset >= eof)
+		if ((unsigned long long)offset >= eof)
 			return -ENXIO;
 		offset = eof;
 		break;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ef4b48d..1c713fd 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -588,6 +588,12 @@
 			break;
 		if (ACCESS_ONCE(ctx->released) ||
 		    fatal_signal_pending(current)) {
+			/*
+			 * &ewq->wq may be queued in fork_event, but
+			 * __remove_wait_queue ignores the head
+			 * parameter. It would be a problem if it
+			 * didn't.
+			 */
 			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
 			if (ewq->msg.event == UFFD_EVENT_FORK) {
 				struct userfaultfd_ctx *new;
@@ -1061,6 +1067,12 @@
 					(unsigned long)
 					uwq->msg.arg.reserved.reserved1;
 				list_move(&uwq->wq.entry, &fork_event);
+				/*
+				 * fork_nctx can be freed as soon as
+				 * we drop the lock, unless we take a
+				 * reference on it.
+				 */
+				userfaultfd_ctx_get(fork_nctx);
 				spin_unlock(&ctx->event_wqh.lock);
 				ret = 0;
 				break;
@@ -1091,19 +1103,53 @@
 
 	if (!ret && msg->event == UFFD_EVENT_FORK) {
 		ret = resolve_userfault_fork(ctx, fork_nctx, msg);
+		spin_lock(&ctx->event_wqh.lock);
+		if (!list_empty(&fork_event)) {
+			/*
+			 * The fork thread didn't abort, so we can
+			 * drop the temporary refcount.
+			 */
+			userfaultfd_ctx_put(fork_nctx);
 
-		if (!ret) {
-			spin_lock(&ctx->event_wqh.lock);
-			if (!list_empty(&fork_event)) {
-				uwq = list_first_entry(&fork_event,
-						       typeof(*uwq),
-						       wq.entry);
-				list_del(&uwq->wq.entry);
-				__add_wait_queue(&ctx->event_wqh, &uwq->wq);
+			uwq = list_first_entry(&fork_event,
+					       typeof(*uwq),
+					       wq.entry);
+			/*
+			 * If fork_event list wasn't empty and in turn
+			 * the event wasn't already released by fork
+			 * (the event is allocated on fork kernel
+			 * stack), put the event back to its place in
+			 * the event_wq. fork_event head will be freed
+			 * as soon as we return so the event cannot
+			 * stay queued there no matter the current
+			 * "ret" value.
+			 */
+			list_del(&uwq->wq.entry);
+			__add_wait_queue(&ctx->event_wqh, &uwq->wq);
+
+			/*
+			 * Leave the event in the waitqueue and report
+			 * error to userland if we failed to resolve
+			 * the userfault fork.
+			 */
+			if (likely(!ret))
 				userfaultfd_event_complete(ctx, uwq);
-			}
-			spin_unlock(&ctx->event_wqh.lock);
+		} else {
+			/*
+			 * Here the fork thread aborted and the
+			 * refcount from the fork thread on fork_nctx
+			 * has already been released. We still hold
+			 * the reference we took before releasing the
+			 * lock above. If resolve_userfault_fork
+			 * failed we've to drop it because the
+			 * fork_nctx has to be freed in such case. If
+			 * it succeeded we'll hold it because the new
+			 * uffd references it.
+			 */
+			if (ret)
+				userfaultfd_ctx_put(fork_nctx);
 		}
+		spin_unlock(&ctx->event_wqh.lock);
 	}
 
 	return ret;
diff --git a/fs/xattr.c b/fs/xattr.c
index 4424f7f..61cd28b 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -250,7 +250,7 @@
 	}
 	memcpy(value, buffer, len);
 out:
-	security_release_secctx(buffer, len);
+	kfree(buffer);
 out_noalloc:
 	return len;
 }
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index b008ff3..df3e600 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -156,7 +156,8 @@
 	trace_xfs_ag_resv_free(pag, type, 0);
 
 	resv = xfs_perag_resv(pag, type);
-	pag->pag_mount->m_ag_max_usable += resv->ar_asked;
+	if (pag->pag_agno == 0)
+		pag->pag_mount->m_ag_max_usable += resv->ar_asked;
 	/*
 	 * AGFL blocks are always considered "free", so whatever
 	 * was reserved at mount time must be given back at umount.
@@ -216,7 +217,14 @@
 		return error;
 	}
 
-	mp->m_ag_max_usable -= ask;
+	/*
+	 * Reduce the maximum per-AG allocation length by however much we're
+	 * trying to reserve for an AG.  Since this is a filesystem-wide
+	 * counter, we only make the adjustment for AG 0.  This assumes that
+	 * there aren't any AGs hungrier for per-AG reservation than AG 0.
+	 */
+	if (pag->pag_agno == 0)
+		mp->m_ag_max_usable -= ask;
 
 	resv = xfs_perag_resv(pag, type);
 	resv->ar_asked = ask;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 744dcae..f965ce8 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1584,6 +1584,10 @@
 
 				bp = xfs_btree_get_bufs(args->mp, args->tp,
 					args->agno, fbno, 0);
+				if (!bp) {
+					error = -EFSCORRUPTED;
+					goto error0;
+				}
 				xfs_trans_binval(args->tp, bp);
 			}
 			args->len = 1;
@@ -2141,6 +2145,10 @@
 		if (error)
 			goto out_agbp_relse;
 		bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0);
+		if (!bp) {
+			error = -EFSCORRUPTED;
+			goto out_agbp_relse;
+		}
 		xfs_trans_binval(tp, bp);
 	}
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 459f4b4f0..8926379 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -49,7 +49,6 @@
 #include "xfs_rmap.h"
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
-#include "xfs_rmap_btree.h"
 #include "xfs_icache.h"
 
 
@@ -192,12 +191,8 @@
 	int		maxrecs;	/* maximum record count at this level */
 	xfs_mount_t	*mp;		/* mount structure */
 	xfs_filblks_t	rval;		/* return value */
-	xfs_filblks_t   orig_len;
 
 	mp = ip->i_mount;
-
-	/* Calculate the worst-case size of the bmbt. */
-	orig_len = len;
 	maxrecs = mp->m_bmap_dmxr[0];
 	for (level = 0, rval = 0;
 	     level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
@@ -205,20 +200,12 @@
 		len += maxrecs - 1;
 		do_div(len, maxrecs);
 		rval += len;
-		if (len == 1) {
-			rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
+		if (len == 1)
+			return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
 				level - 1;
-			break;
-		}
 		if (level == 0)
 			maxrecs = mp->m_bmap_dmxr[1];
 	}
-
-	/* Calculate the worst-case size of the rmapbt. */
-	if (xfs_sb_version_hasrmapbt(&mp->m_sb))
-		rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) +
-				mp->m_rmap_maxlevels;
-
 	return rval;
 }
 
@@ -1490,14 +1477,14 @@
 	int			is_empty;
 	int			error;
 
-	bma->aeof = 0;
+	bma->aeof = false;
 	error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
 				     &is_empty);
 	if (error)
 		return error;
 
 	if (is_empty) {
-		bma->aeof = 1;
+		bma->aeof = true;
 		return 0;
 	}
 
@@ -3865,6 +3852,17 @@
 	}
 }
 
+/* trim extent to within eof */
+void
+xfs_trim_extent_eof(
+	struct xfs_bmbt_irec	*irec,
+	struct xfs_inode	*ip)
+
+{
+	xfs_trim_extent(irec, 0, XFS_B_TO_FSB(ip->i_mount,
+					      i_size_read(VFS_I(ip))));
+}
+
 /*
  * Trim the returned map to the required bounds
  */
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 851982a..502e0d8 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -208,6 +208,7 @@
 
 void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 		xfs_filblks_t len);
+void	xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 988bb3f..dfd6439 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1962,7 +1962,7 @@
 	if (!(mp->m_flags & XFS_MOUNT_IKEEP) &&
 	    rec.ir_free == XFS_INOBT_ALL_FREE &&
 	    mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) {
-		xic->deleted = 1;
+		xic->deleted = true;
 		xic->first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino);
 		xic->alloc = xfs_inobt_irec_to_allocmask(&rec);
 
@@ -1989,7 +1989,7 @@
 
 		xfs_difree_inode_chunk(mp, agno, &rec, dfops);
 	} else {
-		xic->deleted = 0;
+		xic->deleted = false;
 
 		error = xfs_inobt_update(cur, &rec);
 		if (error) {
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 8372e9b..71de185 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -270,6 +270,7 @@
 	uint32_t		ilf_fields;	/* flags for fields logged */
 	uint16_t		ilf_asize;	/* size of attr d/ext/root */
 	uint16_t		ilf_dsize;	/* size of data/ext/root */
+	uint32_t		ilf_pad;	/* pad for 64 bit boundary */
 	uint64_t		ilf_ino;	/* inode number */
 	union {
 		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
@@ -280,7 +281,12 @@
 	int32_t			ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_t;
 
-typedef struct xfs_inode_log_format_32 {
+/*
+ * Old 32 bit systems will log in this format without the 64 bit
+ * alignment padding. Recovery will detect this and convert it to the
+ * correct format.
+ */
+struct xfs_inode_log_format_32 {
 	uint16_t		ilf_type;	/* inode log item type */
 	uint16_t		ilf_size;	/* size of this item */
 	uint32_t		ilf_fields;	/* flags for fields logged */
@@ -294,24 +300,7 @@
 	int64_t			ilf_blkno;	/* blkno of inode buffer */
 	int32_t			ilf_len;	/* len of inode buffer */
 	int32_t			ilf_boffset;	/* off of inode in buffer */
-} __attribute__((packed)) xfs_inode_log_format_32_t;
-
-typedef struct xfs_inode_log_format_64 {
-	uint16_t		ilf_type;	/* inode log item type */
-	uint16_t		ilf_size;	/* size of this item */
-	uint32_t		ilf_fields;	/* flags for fields logged */
-	uint16_t		ilf_asize;	/* size of attr d/ext/root */
-	uint16_t		ilf_dsize;	/* size of data/ext/root */
-	uint32_t		ilf_pad;	/* pad for 64 bit boundary */
-	uint64_t		ilf_ino;	/* inode number */
-	union {
-		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
-		uuid_t		ilfu_uuid;	/* mount point value */
-	} ilf_u;
-	int64_t			ilf_blkno;	/* blkno of inode buffer */
-	int32_t			ilf_len;	/* len of inode buffer */
-	int32_t			ilf_boffset;	/* off of inode in buffer */
-} xfs_inode_log_format_64_t;
+} __attribute__((packed));
 
 
 /*
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 7034e17..3354140 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -247,6 +247,8 @@
 int
 xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
+	umode_t mode;
+	bool set_mode = false;
 	int error = 0;
 
 	if (!acl)
@@ -257,16 +259,24 @@
 		return error;
 
 	if (type == ACL_TYPE_ACCESS) {
-		umode_t mode;
-
 		error = posix_acl_update_mode(inode, &mode, &acl);
 		if (error)
 			return error;
-		error = xfs_set_mode(inode, mode);
-		if (error)
-			return error;
+		set_mode = true;
 	}
 
  set_acl:
-	return __xfs_set_acl(inode, acl, type);
+	error =  __xfs_set_acl(inode, acl, type);
+	if (error)
+		return error;
+
+	/*
+	 * We set the mode after successfully updating the ACL xattr because the
+	 * xattr update can fail at ENOSPC and we don't want to change the mode
+	 * if the ACL update hasn't been applied.
+	 */
+	if (set_mode)
+		error = xfs_set_mode(inode, mode);
+
+	return error;
 }
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 2917260..a3eeaba 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -343,7 +343,8 @@
 		error = xfs_reflink_end_cow(ip, offset, size);
 		break;
 	case XFS_IO_UNWRITTEN:
-		error = xfs_iomap_write_unwritten(ip, offset, size);
+		/* writeback should never update isize */
+		error = xfs_iomap_write_unwritten(ip, offset, size, false);
 		break;
 	default:
 		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
@@ -445,6 +446,19 @@
 {
 	offset >>= inode->i_blkbits;
 
+	/*
+	 * We have to make sure the cached mapping is within EOF to protect
+	 * against eofblocks trimming on file release leaving us with a stale
+	 * mapping. Otherwise, a page for a subsequent file extending buffered
+	 * write could get picked up by this writeback cycle and written to the
+	 * wrong blocks.
+	 *
+	 * Note that what we really want here is a generic mapping invalidation
+	 * mechanism to protect us from arbitrary extent modifying contexts, not
+	 * just eofblocks.
+	 */
+	xfs_trim_extent_eof(imap, XFS_I(inode));
+
 	return offset >= imap->br_startoff &&
 		offset < imap->br_startoff + imap->br_blockcount;
 }
@@ -734,6 +748,14 @@
 {
 	trace_xfs_invalidatepage(page->mapping->host, page, offset,
 				 length);
+
+	/*
+	 * If we are invalidating the entire page, clear the dirty state from it
+	 * so that we can check for attempts to release dirty cached pages in
+	 * xfs_vm_releasepage().
+	 */
+	if (offset == 0 && length >= PAGE_SIZE)
+		cancel_dirty_page(page);
 	block_invalidatepage(page, offset, length);
 }
 
@@ -1189,25 +1211,27 @@
 	 * mm accommodates an old ext3 case where clean pages might not have had
 	 * the dirty bit cleared. Thus, it can send actual dirty pages to
 	 * ->releasepage() via shrink_active_list(). Conversely,
-	 * block_invalidatepage() can send pages that are still marked dirty
-	 * but otherwise have invalidated buffers.
+	 * block_invalidatepage() can send pages that are still marked dirty but
+	 * otherwise have invalidated buffers.
 	 *
 	 * We want to release the latter to avoid unnecessary buildup of the
-	 * LRU, skip the former and warn if we've left any lingering
-	 * delalloc/unwritten buffers on clean pages. Skip pages with delalloc
-	 * or unwritten buffers and warn if the page is not dirty. Otherwise
-	 * try to release the buffers.
+	 * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages
+	 * that are entirely invalidated and need to be released.  Hence the
+	 * only time we should get dirty pages here is through
+	 * shrink_active_list() and so we can simply skip those now.
+	 *
+	 * warn if we've left any lingering delalloc/unwritten buffers on clean
+	 * or invalidated pages we are about to release.
 	 */
+	if (PageDirty(page))
+		return 0;
+
 	xfs_count_page_state(page, &delalloc, &unwritten);
 
-	if (delalloc) {
-		WARN_ON_ONCE(!PageDirty(page));
+	if (WARN_ON_ONCE(delalloc))
 		return 0;
-	}
-	if (unwritten) {
-		WARN_ON_ONCE(!PageDirty(page));
+	if (WARN_ON_ONCE(unwritten))
 		return 0;
-	}
 
 	return try_to_free_buffers(page);
 }
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index ebd66b1..e3a950e 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -302,6 +302,8 @@
 						 &bp, XFS_ATTR_FORK);
 			if (error)
 				return error;
+			node = bp->b_addr;
+			btree = dp->d_ops->node_tree_p(node);
 			child_fsb = be32_to_cpu(btree[i + 1].before);
 			xfs_trans_brelse(*trans, bp);
 		}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index cd9a540..6503cfa 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -84,6 +84,7 @@
 		GFP_NOFS, 0);
 }
 
+#ifdef CONFIG_XFS_RT
 int
 xfs_bmap_rtalloc(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
@@ -190,6 +191,7 @@
 	}
 	return 0;
 }
+#endif /* CONFIG_XFS_RT */
 
 /*
  * Check if the endoff is outside the last extent. If so the caller will grow
@@ -1459,7 +1461,19 @@
 		return error;
 
 	/*
-	 * The extent shiting code works on extent granularity. So, if
+	 * Clean out anything hanging around in the cow fork now that
+	 * we've flushed all the dirty data out to disk to avoid having
+	 * CoW extents at the wrong offsets.
+	 */
+	if (xfs_is_reflink_inode(ip)) {
+		error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
+				true);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * The extent shifting code works on extent granularity. So, if
 	 * stop_fsb is not the starting block of extent, we need to split
 	 * the extent at stop_fsb.
 	 */
@@ -2110,11 +2124,31 @@
 		ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
+	}
+
+	/* Swap the cow forks. */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		xfs_extnum_t	extnum;
+
+		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+
+		extnum = ip->i_cnextents;
+		ip->i_cnextents = tip->i_cnextents;
+		tip->i_cnextents = extnum;
+
 		cowfp = ip->i_cowfp;
 		ip->i_cowfp = tip->i_cowfp;
 		tip->i_cowfp = cowfp;
-		xfs_inode_set_cowblocks_tag(ip);
-		xfs_inode_set_cowblocks_tag(tip);
+
+		if (ip->i_cowfp && ip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(ip);
+		else
+			xfs_inode_clear_cowblocks_tag(ip);
+		if (tip->i_cowfp && tip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(tip);
+		else
+			xfs_inode_clear_cowblocks_tag(tip);
 	}
 
 	xfs_trans_log_inode(tp, ip,  src_log_flags);
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 0eaa81d..7d330b3 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -28,7 +28,20 @@
 struct xfs_trans;
 struct xfs_bmalloca;
 
+#ifdef CONFIG_XFS_RT
 int	xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
+#else /* !CONFIG_XFS_RT */
+/*
+ * Attempts to allocate RT extents when RT is disable indicates corruption and
+ * should trigger a shutdown.
+ */
+static inline int
+xfs_bmap_rtalloc(struct xfs_bmalloca *ap)
+{
+	return -EFSCORRUPTED;
+}
+#endif /* CONFIG_XFS_RT */
+
 int	xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
 		     int whichfork, int *eof);
 int	xfs_bmap_punch_delalloc_range(struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index da14658..2f97c12 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1258,8 +1258,6 @@
 	int		size;
 	int		offset;
 
-	total_nr_pages = bp->b_page_count;
-
 	/* skip the pages in the buffer before the start offset */
 	page_index = 0;
 	offset = *buf_offset;
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index bd786a9..eaf86f5 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -347,7 +347,7 @@
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 
-	xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx",
+	xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx",
 		  bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
 		  __return_address, bp->b_ops->name, bp->b_bn);
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index ebdd0bd..6526ef0 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -58,7 +58,7 @@
 	xfs_off_t		count,
 	bool			*did_zero)
 {
-	return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops);
+	return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops);
 }
 
 int
@@ -237,11 +237,13 @@
 	if (!count)
 		return 0; /* skip atime */
 
-	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	}
+
 	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
@@ -259,9 +261,10 @@
 
 	trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos);
 
-	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	}
 	ret = generic_file_read_iter(iocb, to);
@@ -377,8 +380,6 @@
 	 */
 	spin_lock(&ip->i_flags_lock);
 	if (iocb->ki_pos > i_size_read(inode)) {
-		bool	zero = false;
-
 		spin_unlock(&ip->i_flags_lock);
 		if (!drained_dio) {
 			if (*iolock == XFS_IOLOCK_SHARED) {
@@ -399,7 +400,7 @@
 			drained_dio = true;
 			goto restart;
 		}
-		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
+		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL);
 		if (error)
 			return error;
 	} else
@@ -436,7 +437,6 @@
 	struct inode		*inode = file_inode(iocb->ki_filp);
 	struct xfs_inode	*ip = XFS_I(inode);
 	loff_t			offset = iocb->ki_pos;
-	bool			update_size = false;
 	int			error = 0;
 
 	trace_xfs_end_io_direct_write(ip, offset, size);
@@ -447,6 +447,21 @@
 	if (size <= 0)
 		return size;
 
+	if (flags & IOMAP_DIO_COW) {
+		error = xfs_reflink_end_cow(ip, offset, size);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Unwritten conversion updates the in-core isize after extent
+	 * conversion but before updating the on-disk size. Updating isize any
+	 * earlier allows a racing dio read to find unwritten extents before
+	 * they are converted.
+	 */
+	if (flags & IOMAP_DIO_UNWRITTEN)
+		return xfs_iomap_write_unwritten(ip, offset, size, true);
+
 	/*
 	 * We need to update the in-core inode size here so that we don't end up
 	 * with the on-disk inode size being outside the in-core inode size. We
@@ -461,20 +476,11 @@
 	spin_lock(&ip->i_flags_lock);
 	if (offset + size > i_size_read(inode)) {
 		i_size_write(inode, offset + size);
-		update_size = true;
-	}
-	spin_unlock(&ip->i_flags_lock);
-
-	if (flags & IOMAP_DIO_COW) {
-		error = xfs_reflink_end_cow(ip, offset, size);
-		if (error)
-			return error;
-	}
-
-	if (flags & IOMAP_DIO_UNWRITTEN)
-		error = xfs_iomap_write_unwritten(ip, offset, size);
-	else if (update_size)
+		spin_unlock(&ip->i_flags_lock);
 		error = xfs_setfilesize(ip, offset, size);
+	} else {
+		spin_unlock(&ip->i_flags_lock);
+	}
 
 	return error;
 }
@@ -549,9 +555,10 @@
 		iolock = XFS_IOLOCK_SHARED;
 	}
 
-	if (!xfs_ilock_nowait(ip, iolock)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, iolock))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, iolock);
 	}
 
@@ -603,9 +610,10 @@
 	size_t			count;
 	loff_t			pos;
 
-	if (!xfs_ilock_nowait(ip, iolock)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, iolock))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, iolock);
 	}
 
@@ -761,7 +769,7 @@
 	enum xfs_prealloc_flags	flags = 0;
 	uint			iolock = XFS_IOLOCK_EXCL;
 	loff_t			new_size = 0;
-	bool			do_file_insert = 0;
+	bool			do_file_insert = false;
 
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
@@ -822,7 +830,7 @@
 			error = -EINVAL;
 			goto out_unlock;
 		}
-		do_file_insert = 1;
+		do_file_insert = true;
 	} else {
 		flags |= XFS_PREALLOC_SET;
 
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 814ed729..43cfc07 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -367,29 +367,6 @@
 	return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr);
 }
 
-/* Transform a rtbitmap "record" into a fsmap */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap_helper(
-	struct xfs_trans		*tp,
-	struct xfs_rtalloc_rec		*rec,
-	void				*priv)
-{
-	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_getfsmap_info	*info = priv;
-	struct xfs_rmap_irec		irec;
-	xfs_daddr_t			rec_daddr;
-
-	rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock);
-
-	irec.rm_startblock = rec->ar_startblock;
-	irec.rm_blockcount = rec->ar_blockcount;
-	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
-	irec.rm_offset = 0;
-	irec.rm_flags = 0;
-
-	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr);
-}
-
 /* Transform a bnobt irec into a fsmap */
 STATIC int
 xfs_getfsmap_datadev_bnobt_helper(
@@ -475,6 +452,30 @@
 	return xfs_getfsmap_helper(tp, info, &rmap, 0);
 }
 
+#ifdef CONFIG_XFS_RT
+/* Transform a rtbitmap "record" into a fsmap */
+STATIC int
+xfs_getfsmap_rtdev_rtbitmap_helper(
+	struct xfs_trans		*tp,
+	struct xfs_rtalloc_rec		*rec,
+	void				*priv)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_getfsmap_info	*info = priv;
+	struct xfs_rmap_irec		irec;
+	xfs_daddr_t			rec_daddr;
+
+	rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock);
+
+	irec.rm_startblock = rec->ar_startblock;
+	irec.rm_blockcount = rec->ar_blockcount;
+	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
+	irec.rm_offset = 0;
+	irec.rm_flags = 0;
+
+	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr);
+}
+
 /* Execute a getfsmap query against the realtime device. */
 STATIC int
 __xfs_getfsmap_rtdev(
@@ -561,6 +562,7 @@
 	return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query,
 			info);
 }
+#endif /* CONFIG_XFS_RT */
 
 /* Execute a getfsmap query against the regular data device. */
 STATIC int
@@ -795,7 +797,15 @@
 	return false;
 }
 
+/*
+ * There are only two devices if we didn't configure RT devices at build time.
+ */
+#ifdef CONFIG_XFS_RT
 #define XFS_GETFSMAP_DEVS	3
+#else
+#define XFS_GETFSMAP_DEVS	2
+#endif /* CONFIG_XFS_RT */
+
 /*
  * Get filesystem's extents as described in head, and format for
  * output.  Calls formatter to fill the user's buffer until all
@@ -853,10 +863,12 @@
 		handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev);
 		handlers[1].fn = xfs_getfsmap_logdev;
 	}
+#ifdef CONFIG_XFS_RT
 	if (mp->m_rtdev_targp) {
 		handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
 		handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
 	}
+#endif /* CONFIG_XFS_RT */
 
 	xfs_sort(handlers, XFS_GETFSMAP_DEVS, sizeof(struct xfs_getfsmap_dev),
 			xfs_getfsmap_dev_compare);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5599dda..4ec5b7f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1624,10 +1624,12 @@
 		goto out;
 
 	/*
-	 * Clear the reflink flag if we truncated everything.
+	 * Clear the reflink flag if there are no data fork blocks and
+	 * there are no extents staged in the cow fork.
 	 */
-	if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) {
-		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+	if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) {
+		if (ip->i_d.di_nblocks == 0)
+			ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
 		xfs_inode_clear_cowblocks_tag(ip);
 	}
 
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 6d0f74e..9bbc2d7 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -364,6 +364,9 @@
 	to->di_dmstate = from->di_dmstate;
 	to->di_flags = from->di_flags;
 
+	/* log a dummy value to ensure log structure is fully initialised */
+	to->di_next_unlinked = NULLAGINO;
+
 	if (from->di_version == 3) {
 		to->di_changecount = inode->i_version;
 		to->di_crtime.t_sec = from->di_crtime.t_sec;
@@ -404,6 +407,11 @@
  * the second with the on-disk inode structure, and a possible third and/or
  * fourth with the inode data/extents/b-tree root and inode attributes
  * data/extents/b-tree root.
+ *
+ * Note: Always use the 64 bit inode log format structure so we don't
+ * leave an uninitialised hole in the format item on 64 bit systems. Log
+ * recovery on 32 bit systems handles this just fine, so there's no reason
+ * for not using an initialising the properly padded structure all the time.
  */
 STATIC void
 xfs_inode_item_format(
@@ -412,8 +420,8 @@
 {
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
-	struct xfs_inode_log_format *ilf;
 	struct xfs_log_iovec	*vecp = NULL;
+	struct xfs_inode_log_format *ilf;
 
 	ASSERT(ip->i_d.di_version > 1);
 
@@ -425,7 +433,17 @@
 	ilf->ilf_boffset = ip->i_imap.im_boffset;
 	ilf->ilf_fields = XFS_ILOG_CORE;
 	ilf->ilf_size = 2; /* format + core */
-	xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
+
+	/*
+	 * make sure we don't leak uninitialised data into the log in the case
+	 * when we don't log every field in the inode.
+	 */
+	ilf->ilf_dsize = 0;
+	ilf->ilf_asize = 0;
+	ilf->ilf_pad = 0;
+	uuid_copy(&ilf->ilf_u.ilfu_uuid, &uuid_null);
+
+	xlog_finish_iovec(lv, vecp, sizeof(*ilf));
 
 	xfs_inode_item_format_core(ip, lv, &vecp);
 	xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
@@ -745,7 +763,7 @@
 		 */
 		iip = INODE_ITEM(blip);
 		if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
-		    lip->li_flags & XFS_LI_FAILED)
+		    (blip->li_flags & XFS_LI_FAILED))
 			need_ail++;
 
 		blip = next;
@@ -855,44 +873,29 @@
 }
 
 /*
- * convert an xfs_inode_log_format struct from either 32 or 64 bit versions
- * (which can have different field alignments) to the native version
+ * convert an xfs_inode_log_format struct from the old 32 bit version
+ * (which can have different field alignments) to the native 64 bit version
  */
 int
 xfs_inode_item_format_convert(
-	xfs_log_iovec_t		*buf,
-	xfs_inode_log_format_t	*in_f)
+	struct xfs_log_iovec		*buf,
+	struct xfs_inode_log_format	*in_f)
 {
-	if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) {
-		xfs_inode_log_format_32_t *in_f32 = buf->i_addr;
+	struct xfs_inode_log_format_32	*in_f32 = buf->i_addr;
 
-		in_f->ilf_type = in_f32->ilf_type;
-		in_f->ilf_size = in_f32->ilf_size;
-		in_f->ilf_fields = in_f32->ilf_fields;
-		in_f->ilf_asize = in_f32->ilf_asize;
-		in_f->ilf_dsize = in_f32->ilf_dsize;
-		in_f->ilf_ino = in_f32->ilf_ino;
-		/* copy biggest field of ilf_u */
-		uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid);
-		in_f->ilf_blkno = in_f32->ilf_blkno;
-		in_f->ilf_len = in_f32->ilf_len;
-		in_f->ilf_boffset = in_f32->ilf_boffset;
-		return 0;
-	} else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){
-		xfs_inode_log_format_64_t *in_f64 = buf->i_addr;
+	if (buf->i_len != sizeof(*in_f32))
+		return -EFSCORRUPTED;
 
-		in_f->ilf_type = in_f64->ilf_type;
-		in_f->ilf_size = in_f64->ilf_size;
-		in_f->ilf_fields = in_f64->ilf_fields;
-		in_f->ilf_asize = in_f64->ilf_asize;
-		in_f->ilf_dsize = in_f64->ilf_dsize;
-		in_f->ilf_ino = in_f64->ilf_ino;
-		/* copy biggest field of ilf_u */
-		uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f64->ilf_u.ilfu_uuid);
-		in_f->ilf_blkno = in_f64->ilf_blkno;
-		in_f->ilf_len = in_f64->ilf_len;
-		in_f->ilf_boffset = in_f64->ilf_boffset;
-		return 0;
-	}
-	return -EFSCORRUPTED;
+	in_f->ilf_type = in_f32->ilf_type;
+	in_f->ilf_size = in_f32->ilf_size;
+	in_f->ilf_fields = in_f32->ilf_fields;
+	in_f->ilf_asize = in_f32->ilf_asize;
+	in_f->ilf_dsize = in_f32->ilf_dsize;
+	in_f->ilf_ino = in_f32->ilf_ino;
+	/* copy biggest field of ilf_u */
+	uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid);
+	in_f->ilf_blkno = in_f32->ilf_blkno;
+	in_f->ilf_len = in_f32->ilf_len;
+	in_f->ilf_boffset = in_f32->ilf_boffset;
+	return 0;
 }
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 5049e8a..aa75389 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1088,6 +1088,7 @@
 	int			*join_flags)
 {
 	struct inode		*inode = VFS_I(ip);
+	struct super_block	*sb = inode->i_sb;
 	int			error;
 
 	*join_flags = 0;
@@ -1100,7 +1101,7 @@
 	if (fa->fsx_xflags & FS_XFLAG_DAX) {
 		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
 			return -EINVAL;
-		if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+		if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
 			return -EINVAL;
 	}
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index a1909bc..f179bdf 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -829,7 +829,8 @@
 xfs_iomap_write_unwritten(
 	xfs_inode_t	*ip,
 	xfs_off_t	offset,
-	xfs_off_t	count)
+	xfs_off_t	count,
+	bool		update_isize)
 {
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb;
@@ -840,6 +841,7 @@
 	xfs_trans_t	*tp;
 	xfs_bmbt_irec_t imap;
 	struct xfs_defer_ops dfops;
+	struct inode	*inode = VFS_I(ip);
 	xfs_fsize_t	i_size;
 	uint		resblks;
 	int		error;
@@ -899,7 +901,8 @@
 		i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb);
 		if (i_size > offset + count)
 			i_size = offset + count;
-
+		if (update_isize && i_size > i_size_read(inode))
+			i_size_write(inode, i_size);
 		i_size = xfs_new_eof(ip, i_size);
 		if (i_size) {
 			ip->i_d.di_size = i_size;
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 00db3ec..ee53506 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -27,7 +27,7 @@
 			struct xfs_bmbt_irec *, int);
 int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t,
 			struct xfs_bmbt_irec *);
-int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t);
+int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
 		struct xfs_bmbt_irec *);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index c5107c7..dc95a49 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2515,7 +2515,7 @@
 				if (lv)
 					vecp = lv->lv_iovecp;
 			}
-			if (record_cnt == 0 && ordered == false) {
+			if (record_cnt == 0 && !ordered) {
 				if (!lv)
 					return 0;
 				break;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index ea7d4b4..e9727d0 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -704,7 +704,7 @@
 	xfs_set_maxicount(mp);
 
 	/* enable fail_at_unmount as default */
-	mp->m_fail_unmount = 1;
+	mp->m_fail_unmount = true;
 
 	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname);
 	if (error)
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index 0c381d7..0492436 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -134,7 +134,7 @@
 	XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log,		28);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp,		8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32,	52);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64,	56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format,	56);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat,	20);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header,		16);
 }
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 2f2dc3c..4246876 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -274,7 +274,7 @@
 					(end - 1) >> PAGE_SHIFT);
 		WARN_ON_ONCE(error);
 
-		error = xfs_iomap_write_unwritten(ip, start, length);
+		error = xfs_iomap_write_unwritten(ip, start, length, false);
 		if (error)
 			goto out_drop_iolock;
 	}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 3246815..37e603b 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -736,7 +736,13 @@
 	/* If there is a hole at end_fsb - 1 go to the previous extent */
 	if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
 	    got.br_startoff > end_fsb) {
-		ASSERT(idx > 0);
+		/*
+		 * In case of racing, overlapping AIO writes no COW extents
+		 * might be left by the time I/O completes for the loser of
+		 * the race.  In that case we are done.
+		 */
+		if (idx <= 0)
+			goto out_cancel;
 		xfs_iext_get_extent(ifp, --idx, &got);
 	}
 
@@ -809,6 +815,7 @@
 
 out_defer:
 	xfs_defer_cancel(&dfops);
+out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index c996f4a..f663022 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1637,7 +1637,7 @@
 
 	/* version 5 superblocks support inode version counters. */
 	if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
-		sb->s_flags |= MS_I_VERSION;
+		sb->s_flags |= SB_I_VERSION;
 
 	if (mp->m_flags & XFS_MOUNT_DAX) {
 		xfs_warn(mp,
@@ -1654,6 +1654,16 @@
 		"DAX and reflink have not been tested together!");
 	}
 
+	if (mp->m_flags & XFS_MOUNT_DISCARD) {
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
+
+		if (!blk_queue_discard(q)) {
+			xfs_warn(mp, "mounting with \"discard\" option, but "
+					"the device does not support discard");
+			mp->m_flags &= ~XFS_MOUNT_DISCARD;
+		}
+	}
+
 	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
 		if (mp->m_sb.sb_rblocks) {
 			xfs_alert(mp,
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index dedf9d7..fa15052 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -399,17 +399,12 @@
 extern const struct fwnode_operations acpi_data_fwnode_ops;
 extern const struct fwnode_operations acpi_static_fwnode_ops;
 
+bool is_acpi_device_node(const struct fwnode_handle *fwnode);
+bool is_acpi_data_node(const struct fwnode_handle *fwnode);
+
 static inline bool is_acpi_node(const struct fwnode_handle *fwnode)
 {
-	return !IS_ERR_OR_NULL(fwnode) &&
-		(fwnode->ops == &acpi_device_fwnode_ops
-		 || fwnode->ops == &acpi_data_fwnode_ops);
-}
-
-static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode)
-{
-	return !IS_ERR_OR_NULL(fwnode) &&
-		fwnode->ops == &acpi_device_fwnode_ops;
+	return (is_acpi_device_node(fwnode) || is_acpi_data_node(fwnode));
 }
 
 #define to_acpi_device_node(__fwnode)					\
@@ -422,11 +417,6 @@
 			NULL;						\
 	})
 
-static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode)
-{
-	return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops;
-}
-
 #define to_acpi_data_node(__fwnode)					\
 	({								\
 		typeof(__fwnode) __to_acpi_data_node_fwnode = __fwnode;	\
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 0504ef8..976f8ac 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -115,15 +115,35 @@
 	(__ret);							\
 })
 
-#define this_cpu_generic_read(pcp)					\
+#define __this_cpu_generic_read_nopreempt(pcp)				\
 ({									\
 	typeof(pcp) __ret;						\
 	preempt_disable_notrace();					\
-	__ret = raw_cpu_generic_read(pcp);				\
+	__ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
 	preempt_enable_notrace();					\
 	__ret;								\
 })
 
+#define __this_cpu_generic_read_noirq(pcp)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_generic_read(pcp);				\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_read(pcp)					\
+({									\
+	typeof(pcp) __ret;						\
+	if (__native_word(pcp))						\
+		__ret = __this_cpu_generic_read_nopreempt(pcp);		\
+	else								\
+		__ret = __this_cpu_generic_read_noirq(pcp);		\
+	__ret;								\
+})
+
 #define this_cpu_generic_to_op(pcp, val, op)				\
 do {									\
 	unsigned long __flags;						\
diff --git a/include/dt-bindings/reset/snps,hsdk-reset.h b/include/dt-bindings/reset/snps,hsdk-reset.h
new file mode 100644
index 0000000..e1a643e
--- /dev/null
+++ b/include/dt-bindings/reset/snps,hsdk-reset.h
@@ -0,0 +1,17 @@
+/**
+ * This header provides index for the HSDK reset controller.
+ */
+#ifndef _DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK
+#define _DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK
+
+#define HSDK_APB_RESET	0
+#define HSDK_AXI_RESET	1
+#define HSDK_ETH_RESET	2
+#define HSDK_USB_RESET	3
+#define HSDK_SDIO_RESET	4
+#define HSDK_HDMI_RESET	5
+#define HSDK_GFX_RESET	6
+#define HSDK_DMAC_RESET	7
+#define HSDK_EBI_RESET	8
+
+#endif /*_DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK*/
diff --git a/include/dt-bindings/reset/snps,hsdk-v1-reset.h b/include/dt-bindings/reset/snps,hsdk-v1-reset.h
deleted file mode 100644
index d898c89..0000000
--- a/include/dt-bindings/reset/snps,hsdk-v1-reset.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/**
- * This header provides index for the HSDK v1 reset controller.
- */
-#ifndef _DT_BINDINGS_RESET_CONTROLLER_HSDK_V1
-#define _DT_BINDINGS_RESET_CONTROLLER_HSDK_V1
-
-#define HSDK_V1_APB_RESET	0
-#define HSDK_V1_AXI_RESET	1
-#define HSDK_V1_ETH_RESET	2
-#define HSDK_V1_USB_RESET	3
-#define HSDK_V1_SDIO_RESET	4
-#define HSDK_V1_HDMI_RESET	5
-#define HSDK_V1_GFX_RESET	6
-#define HSDK_V1_DMAC_RESET	7
-#define HSDK_V1_EBI_RESET	8
-
-#endif /*_DT_BINDINGS_RESET_CONTROLLER_HSDK_V1*/
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 74d4d4e..cb708eb 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -314,11 +314,7 @@
 
 static inline void audit_seccomp(unsigned long syscall, long signr, int code)
 {
-	if (!audit_enabled)
-		return;
-
-	/* Force a record to be reported if a signal was delivered. */
-	if (signr || unlikely(!audit_dummy_context()))
+	if (audit_enabled && unlikely(!audit_dummy_context()))
 		__audit_seccomp(syscall, signr, code);
 }
 
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index fb44d61..18d05b5 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -131,7 +131,7 @@
 			   int executable_stack);
 extern int transfer_args_to_stack(struct linux_binprm *bprm,
 				  unsigned long *sp_location);
-extern int bprm_change_interp(char *interp, struct linux_binprm *bprm);
+extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm);
 extern int copy_strings_kernel(int argc, const char *const *argv,
 			       struct linux_binprm *bprm);
 extern int prepare_bprm_creds(struct linux_binprm *bprm);
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 8b9d6ff..f2deb71 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -92,7 +92,7 @@
 /**
  * FIELD_GET() - extract a bitfield element
  * @_mask: shifted mask defining the field's length and position
- * @_reg:  32bit value of entire bitfield
+ * @_reg:  value of entire bitfield
  *
  * FIELD_GET() extracts the field specified by @_mask from the
  * bitfield passed in as @_reg by masking and shifting it down.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 460294b..02fa42d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -551,6 +551,7 @@
 	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace	*blk_trace;
+	struct mutex		blk_trace_mutex;
 #endif
 	/*
 	 * for flush operations
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8390859..f1af7d6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -368,6 +368,11 @@
 {
 }
 
+static inline int bpf_obj_get_user(const char __user *pathname)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline struct net_device  *__dev_map_lookup_elem(struct bpf_map *map,
 						       u32 key)
 {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index c8dae555..446b24c 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -232,6 +232,7 @@
 				loff_t, unsigned, unsigned,
 				struct page *, void *);
 void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
+void clean_page_buffers(struct page *page);
 int cont_write_begin(struct file *, struct address_space *, loff_t,
 			unsigned, unsigned, struct page **, void **,
 			get_block_t *, loff_t *);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index f24bfb2..6d50876 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -3,8 +3,27 @@
 
 #include <linux/types.h>
 
+/*
+ * CPU-up			CPU-down
+ *
+ * BP		AP		BP		AP
+ *
+ * OFFLINE			OFFLINE
+ *   |				  ^
+ *   v				  |
+ * BRINGUP_CPU->AP_OFFLINE	BRINGUP_CPU  <- AP_IDLE_DEAD (idle thread/play_dead)
+ *		  |				AP_OFFLINE
+ *		  v (IRQ-off)	  ,---------------^
+ *		AP_ONLNE	  | (stop_machine)
+ *		  |		TEARDOWN_CPU <-	AP_ONLINE_IDLE
+ *		  |				  ^
+ *		  v				  |
+ *              AP_ACTIVE			AP_ACTIVE
+ */
+
 enum cpuhp_state {
-	CPUHP_OFFLINE,
+	CPUHP_INVALID = -1,
+	CPUHP_OFFLINE = 0,
 	CPUHP_CREATE_THREADS,
 	CPUHP_PERF_PREPARE,
 	CPUHP_PERF_X86_PREPARE,
diff --git a/include/linux/device.h b/include/linux/device.h
index c6f2720..66fe271 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -307,8 +307,6 @@
 			 size_t count);
 };
 
-#define DRIVER_ATTR(_name, _mode, _show, _store) \
-	struct driver_attribute driver_attr_##_name = __ATTR(_name, _mode, _show, _store)
 #define DRIVER_ATTR_RW(_name) \
 	struct driver_attribute driver_attr_##_name = __ATTR_RW(_name)
 #define DRIVER_ATTR_RO(_name) \
@@ -838,7 +836,7 @@
  * @driver_data: Private pointer for driver specific info.
  * @links:	Links to suppliers and consumers of this device.
  * @power:	For device power management.
- * 		See Documentation/power/admin-guide/devices.rst for details.
+ *		See Documentation/driver-api/pm/devices.rst for details.
  * @pm_domain:	Provide callbacks that are executed during system suspend,
  * 		hibernation, system resume and during runtime PM transitions
  * 		along with subsystem-level and driver-level callbacks.
diff --git a/include/linux/filter.h b/include/linux/filter.h
index d29e58f..818a0b2 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -728,7 +728,7 @@
 void bpf_warn_invalid_xdp_action(u32 act);
 void bpf_warn_invalid_xdp_redirect(u32 ifindex);
 
-struct sock *do_sk_redirect_map(void);
+struct sock *do_sk_redirect_map(struct sk_buff *skb);
 
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 339e737..13dab19 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -403,7 +403,7 @@
 	unsigned long		flags;		/* error bits */
 	spinlock_t		private_lock;	/* for use by the address_space */
 	gfp_t			gfp_mask;	/* implicit gfp mask for allocations */
-	struct list_head	private_list;	/* ditto */
+	struct list_head	private_list;	/* for use by the address_space */
 	void			*private_data;	/* ditto */
 	errseq_t		wb_err;
 } __attribute__((aligned(sizeof(long)))) __randomize_layout;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index c458d7b..6431087 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1403,7 +1403,7 @@
 				const int *srv_version, int srv_vercnt,
 				int *nego_fw_version, int *nego_srv_version);
 
-void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
+void hv_process_channel_removal(u32 relid);
 
 void vmbus_setevent(struct vmbus_channel *channel);
 /*
diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h
index 4837157..9ae41cd 100644
--- a/include/linux/if_tap.h
+++ b/include/linux/if_tap.h
@@ -73,8 +73,8 @@
 int tap_get_minor(dev_t major, struct tap_dev *tap);
 void tap_free_minor(dev_t major, struct tap_dev *tap);
 int tap_queue_resize(struct tap_dev *tap);
-int tap_create_cdev(struct cdev *tap_cdev,
-		    dev_t *tap_major, const char *device_name);
+int tap_create_cdev(struct cdev *tap_cdev, dev_t *tap_major,
+		    const char *device_name, struct module *module);
 void tap_destroy_cdev(dev_t major, struct cdev *tap_cdev);
 
 #endif /*_LINUX_IF_TAP_H_*/
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index 5ba430c..1fc7abd 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -111,6 +111,9 @@
 int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 	unsigned int size, unsigned int *val);
 
+int ad_sd_reset(struct ad_sigma_delta *sigma_delta,
+	unsigned int reset_length);
+
 int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, int *val);
 int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta,
diff --git a/include/linux/input.h b/include/linux/input.h
index a65e3b2..7c7516e 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -234,6 +234,10 @@
 #error "SW_MAX and INPUT_DEVICE_ID_SW_MAX do not match"
 #endif
 
+#if INPUT_PROP_MAX != INPUT_DEVICE_ID_PROP_MAX
+#error "INPUT_PROP_MAX and INPUT_DEVICE_ID_PROP_MAX do not match"
+#endif
+
 #define INPUT_DEVICE_ID_MATCH_DEVICE \
 	(INPUT_DEVICE_ID_MATCH_BUS | INPUT_DEVICE_ID_MATCH_VENDOR | INPUT_DEVICE_ID_MATCH_PRODUCT)
 #define INPUT_DEVICE_ID_MATCH_DEVICE_AND_VERSION \
@@ -469,6 +473,9 @@
 int input_set_keycode(struct input_dev *dev,
 		      const struct input_keymap_entry *ke);
 
+bool input_match_device_id(const struct input_dev *dev,
+			   const struct input_device_id *id);
+
 void input_enable_softrepeat(struct input_dev *dev, int delay, int period);
 
 extern struct class input_class;
@@ -529,6 +536,7 @@
 
 int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file);
 int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file);
+int input_ff_flush(struct input_dev *dev, struct file *file);
 
 int input_ff_create_memless(struct input_dev *dev, void *data,
 		int (*play_effect)(struct input_dev *, void *, struct ff_effect *));
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index a7f2ac6..41b8c57 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -167,11 +167,11 @@
  * @map: map a physically contiguous memory region to an iommu domain
  * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @map_sg: map a scatter-gather list of physically contiguous memory chunks
+ *          to an iommu domain
  * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain
  * @tlb_range_add: Add a given iova range to the flush queue for this domain
  * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
- * to an iommu domain
  * @iova_to_phys: translate iova to physical address
  * @add_device: add device to iommu grouping
  * @remove_device: remove device from iommu grouping
diff --git a/include/linux/irq.h b/include/linux/irq.h
index b99a784..5ad1094 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -783,10 +783,7 @@
 static inline
 struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d)
 {
-	if (!cpumask_empty(d->common->effective_affinity))
-		return d->common->effective_affinity;
-
-	return d->common->affinity;
+	return d->common->effective_affinity;
 }
 static inline void irq_data_update_effective_affinity(struct irq_data *d,
 						      const struct cpumask *m)
@@ -1012,7 +1009,7 @@
 void irq_gc_unmask_enable_reg(struct irq_data *d);
 void irq_gc_ack_set_bit(struct irq_data *d);
 void irq_gc_ack_clr_bit(struct irq_data *d);
-void irq_gc_mask_disable_reg_and_ack(struct irq_data *d);
+void irq_gc_mask_disable_and_ack_set(struct irq_data *d);
 void irq_gc_eoi(struct irq_data *d);
 int irq_gc_set_wake(struct irq_data *d, unsigned int on);
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 1ea576c..14b74f2 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -372,6 +372,8 @@
 #define GITS_BASER_ENTRY_SIZE_SHIFT		(48)
 #define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
 #define GITS_BASER_ENTRY_SIZE_MASK	GENMASK_ULL(52, 48)
+#define GITS_BASER_PHYS_52_to_48(phys)					\
+	(((phys) & GENMASK_ULL(47, 16)) | (((phys) >> 48) & 0xf) << 12)
 #define GITS_BASER_SHAREABILITY_SHIFT	(10)
 #define GITS_BASER_InnerShareable					\
 	GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 0ad4c30..91189bb 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -44,6 +44,12 @@
 
 #define STACK_MAGIC	0xdeadbeef
 
+/**
+ * REPEAT_BYTE - repeat the value @x multiple times as an unsigned long value
+ * @x: value to repeat
+ *
+ * NOTE: @x is not checked for > 0xff; larger values produce odd results.
+ */
 #define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
 
 /* @a is a power of 2 value */
@@ -57,6 +63,10 @@
 #define READ			0
 #define WRITE			1
 
+/**
+ * ARRAY_SIZE - get the number of elements in array @arr
+ * @arr: array to be sized
+ */
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
 
 #define u64_to_user_ptr(x) (		\
@@ -76,7 +86,15 @@
 #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
 #define round_down(x, y) ((x) & ~__round_mask(x, y))
 
+/**
+ * FIELD_SIZEOF - get the size of a struct's field
+ * @t: the target struct
+ * @f: the target struct's field
+ * Return: the size of @f in the struct definition without having a
+ * declared instance of @t.
+ */
 #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
+
 #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
 
 #define DIV_ROUND_DOWN_ULL(ll, d) \
@@ -107,7 +125,7 @@
 /*
  * Divide positive or negative dividend by positive or negative divisor
  * and round to closest integer. Result is undefined for negative
- * divisors if he dividend variable type is unsigned and for negative
+ * divisors if the dividend variable type is unsigned and for negative
  * dividends if the divisor variable type is unsigned.
  */
 #define DIV_ROUND_CLOSEST(x, divisor)(			\
@@ -247,13 +265,13 @@
  * @ep_ro: right open interval endpoint
  *
  * Perform a "reciprocal multiplication" in order to "scale" a value into
- * range [0, ep_ro), where the upper interval endpoint is right-open.
+ * range [0, @ep_ro), where the upper interval endpoint is right-open.
  * This is useful, e.g. for accessing a index of an array containing
- * ep_ro elements, for example. Think of it as sort of modulus, only that
+ * @ep_ro elements, for example. Think of it as sort of modulus, only that
  * the result isn't that of modulo. ;) Note that if initial input is a
  * small value, then result will return 0.
  *
- * Return: a result based on val in interval [0, ep_ro).
+ * Return: a result based on @val in interval [0, @ep_ro).
  */
 static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
 {
@@ -618,8 +636,8 @@
  * trace_printk - printf formatting in the ftrace buffer
  * @fmt: the printf format for printing
  *
- * Note: __trace_printk is an internal function for trace_printk and
- *       the @ip is passed in via the trace_printk macro.
+ * Note: __trace_printk is an internal function for trace_printk() and
+ *       the @ip is passed in via the trace_printk() macro.
  *
  * This function allows a kernel developer to debug fast path sections
  * that printk is not appropriate for. By scattering in various
@@ -629,7 +647,7 @@
  * This is intended as a debugging tool for the developer only.
  * Please refrain from leaving trace_printks scattered around in
  * your code. (Extra memory is used for special buffers that are
- * allocated when trace_printk() is used)
+ * allocated when trace_printk() is used.)
  *
  * A little optization trick is done here. If there's only one
  * argument, there's no need to scan the string for printf formats.
@@ -681,7 +699,7 @@
  *       the @ip is passed in via the trace_puts macro.
  *
  * This is similar to trace_printk() but is made for those really fast
- * paths that a developer wants the least amount of "Heisenbug" affects,
+ * paths that a developer wants the least amount of "Heisenbug" effects,
  * where the processing of the print format is still too much.
  *
  * This function allows a kernel developer to debug fast path sections
@@ -692,7 +710,7 @@
  * This is intended as a debugging tool for the developer only.
  * Please refrain from leaving trace_puts scattered around in
  * your code. (Extra memory is used for special buffers that are
- * allocated when trace_puts() is used)
+ * allocated when trace_puts() is used.)
  *
  * Returns: 0 if nothing was written, positive # if string was.
  *  (1 when __trace_bputs is used, strlen(str) when __trace_puts is used)
@@ -771,6 +789,12 @@
 	t2 min2 = (y);					\
 	(void) (&min1 == &min2);			\
 	min1 < min2 ? min1 : min2; })
+
+/**
+ * min - return minimum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
 #define min(x, y)					\
 	__min(typeof(x), typeof(y),			\
 	      __UNIQUE_ID(min1_), __UNIQUE_ID(min2_),	\
@@ -781,12 +805,31 @@
 	t2 max2 = (y);					\
 	(void) (&max1 == &max2);			\
 	max1 > max2 ? max1 : max2; })
+
+/**
+ * max - return maximum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
 #define max(x, y)					\
 	__max(typeof(x), typeof(y),			\
 	      __UNIQUE_ID(max1_), __UNIQUE_ID(max2_),	\
 	      x, y)
 
+/**
+ * min3 - return minimum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
 #define min3(x, y, z) min((typeof(x))min(x, y), z)
+
+/**
+ * max3 - return maximum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
 #define max3(x, y, z) max((typeof(x))max(x, y), z)
 
 /**
@@ -805,8 +848,8 @@
  * @lo: lowest allowable value
  * @hi: highest allowable value
  *
- * This macro does strict typechecking of lo/hi to make sure they are of the
- * same type as val.  See the unnecessary pointer comparisons.
+ * This macro does strict typechecking of @lo/@hi to make sure they are of the
+ * same type as @val.  See the unnecessary pointer comparisons.
  */
 #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
 
@@ -816,11 +859,24 @@
  *
  * Or not use min/max/clamp at all, of course.
  */
+
+/**
+ * min_t - return minimum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
 #define min_t(type, x, y)				\
 	__min(type, type,				\
 	      __UNIQUE_ID(min1_), __UNIQUE_ID(min2_),	\
 	      x, y)
 
+/**
+ * max_t - return maximum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
 #define max_t(type, x, y)				\
 	__max(type, type,				\
 	      __UNIQUE_ID(min1_), __UNIQUE_ID(min2_),	\
@@ -834,7 +890,7 @@
  * @hi: maximum allowable value
  *
  * This macro does no typechecking and uses temporary variables of type
- * 'type' to make all the comparisons.
+ * @type to make all the comparisons.
  */
 #define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
 
@@ -845,15 +901,17 @@
  * @hi: maximum allowable value
  *
  * This macro does no typechecking and uses temporary variables of whatever
- * type the input argument 'val' is.  This is useful when val is an unsigned
- * type and min and max are literals that will otherwise be assigned a signed
+ * type the input argument @val is.  This is useful when @val is an unsigned
+ * type and @lo and @hi are literals that will otherwise be assigned a signed
  * integer type.
  */
 #define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
 
 
-/*
- * swap - swap value of @a and @b
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
  */
 #define swap(a, b) \
 	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
diff --git a/include/linux/key.h b/include/linux/key.h
index 0441141..8a15cab 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -138,6 +138,11 @@
 	struct key_type *keytype;
 };
 
+enum key_state {
+	KEY_IS_UNINSTANTIATED,
+	KEY_IS_POSITIVE,		/* Positively instantiated */
+};
+
 /*****************************************************************************/
 /*
  * authentication token / access credential / keyring
@@ -169,6 +174,7 @@
 						 * - may not match RCU dereferenced payload
 						 * - payload should contain own length
 						 */
+	short			state;		/* Key state (+) or rejection error (-) */
 
 #ifdef KEY_DEBUGGING
 	unsigned		magic;
@@ -176,17 +182,16 @@
 #endif
 
 	unsigned long		flags;		/* status flags (change with bitops) */
-#define KEY_FLAG_INSTANTIATED	0	/* set if key has been instantiated */
-#define KEY_FLAG_DEAD		1	/* set if key type has been deleted */
-#define KEY_FLAG_REVOKED	2	/* set if key had been revoked */
-#define KEY_FLAG_IN_QUOTA	3	/* set if key consumes quota */
-#define KEY_FLAG_USER_CONSTRUCT	4	/* set if key is being constructed in userspace */
-#define KEY_FLAG_NEGATIVE	5	/* set if key is negative */
-#define KEY_FLAG_ROOT_CAN_CLEAR	6	/* set if key can be cleared by root without permission */
-#define KEY_FLAG_INVALIDATED	7	/* set if key has been invalidated */
-#define KEY_FLAG_BUILTIN	8	/* set if key is built in to the kernel */
-#define KEY_FLAG_ROOT_CAN_INVAL	9	/* set if key can be invalidated by root without permission */
-#define KEY_FLAG_KEEP		10	/* set if key should not be removed */
+#define KEY_FLAG_DEAD		0	/* set if key type has been deleted */
+#define KEY_FLAG_REVOKED	1	/* set if key had been revoked */
+#define KEY_FLAG_IN_QUOTA	2	/* set if key consumes quota */
+#define KEY_FLAG_USER_CONSTRUCT	3	/* set if key is being constructed in userspace */
+#define KEY_FLAG_ROOT_CAN_CLEAR	4	/* set if key can be cleared by root without permission */
+#define KEY_FLAG_INVALIDATED	5	/* set if key has been invalidated */
+#define KEY_FLAG_BUILTIN	6	/* set if key is built in to the kernel */
+#define KEY_FLAG_ROOT_CAN_INVAL	7	/* set if key can be invalidated by root without permission */
+#define KEY_FLAG_KEEP		8	/* set if key should not be removed */
+#define KEY_FLAG_UID_KEYRING	9	/* set if key is a user or user session keyring */
 
 	/* the key type and key description string
 	 * - the desc is used to match a key against search criteria
@@ -212,7 +217,6 @@
 			struct list_head name_link;
 			struct assoc_array keys;
 		};
-		int reject_error;
 	};
 
 	/* This is set on a keyring to restrict the addition of a link to a key
@@ -243,6 +247,7 @@
 #define KEY_ALLOC_NOT_IN_QUOTA		0x0002	/* not in quota */
 #define KEY_ALLOC_BUILT_IN		0x0004	/* Key is built into kernel */
 #define KEY_ALLOC_BYPASS_RESTRICTION	0x0008	/* Override the check on restricted keyrings */
+#define KEY_ALLOC_UID_KEYRING		0x0010	/* allocating a user or user session keyring */
 
 extern void key_revoke(struct key *key);
 extern void key_invalidate(struct key *key);
@@ -351,17 +356,27 @@
 #define	KEY_NEED_SETATTR 0x20	/* Require permission to change attributes */
 #define	KEY_NEED_ALL	0x3f	/* All the above permissions */
 
+static inline short key_read_state(const struct key *key)
+{
+	/* Barrier versus mark_key_instantiated(). */
+	return smp_load_acquire(&key->state);
+}
+
 /**
- * key_is_instantiated - Determine if a key has been positively instantiated
+ * key_is_positive - Determine if a key has been positively instantiated
  * @key: The key to check.
  *
  * Return true if the specified key has been positively instantiated, false
  * otherwise.
  */
-static inline bool key_is_instantiated(const struct key *key)
+static inline bool key_is_positive(const struct key *key)
 {
-	return test_bit(KEY_FLAG_INSTANTIATED, &key->flags) &&
-		!test_bit(KEY_FLAG_NEGATIVE, &key->flags);
+	return key_read_state(key) == KEY_IS_POSITIVE;
+}
+
+static inline bool key_is_negative(const struct key *key)
+{
+	return key_read_state(key) < 0;
 }
 
 #define dereference_key_rcu(KEY)					\
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index 0d3f14f..4773145 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -31,8 +31,8 @@
 	struct mbus_dram_window {
 		u8	cs_index;
 		u8	mbus_attr;
-		u32	base;
-		u32	size;
+		u64	base;
+		u64	size;
 	} cs[4];
 };
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index eaf4ad2..e32dbc4 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -980,7 +980,6 @@
 	MLX5_CAP_RESERVED,
 	MLX5_CAP_VECTOR_CALC,
 	MLX5_CAP_QOS,
-	MLX5_CAP_FPGA,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1110,10 +1109,10 @@
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
 
 #define MLX5_CAP_FPGA(mdev, cap) \
-	MLX5_GET(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap)
+	MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap)
 
 #define MLX5_CAP64_FPGA(mdev, cap) \
-	MLX5_GET64(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap)
+	MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap)
 
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 02ff700..401c897 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -774,6 +774,7 @@
 		u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
 		u32 pcam[MLX5_ST_SZ_DW(pcam_reg)];
 		u32 mcam[MLX5_ST_SZ_DW(mcam_reg)];
+		u32 fpga[MLX5_ST_SZ_DW(fpga_cap)];
 	} caps;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index a528b35..6977234 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -327,7 +327,8 @@
 	u8         reserved_at_80[0x18];
 	u8         log_max_destination[0x8];
 
-	u8         reserved_at_a0[0x18];
+	u8         log_max_flow_counter[0x8];
+	u8         reserved_at_a8[0x10];
 	u8         log_max_flow[0x8];
 
 	u8         reserved_at_c0[0x40];
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index c57d4b7..c59af8a 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -157,6 +157,8 @@
 int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
 			    u8 prio, u8 *tc);
 int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group);
+int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
+			     u8 tc, u8 *tc_group);
 int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw);
 int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
 				u8 tc, u8 *bw_pct);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f8c10d3..065d99d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -240,7 +240,7 @@
 
 #if defined(CONFIG_X86_INTEL_MPX)
 /* MPX specific bounds table or bounds directory */
-# define VM_MPX		VM_HIGH_ARCH_BIT_4
+# define VM_MPX		VM_HIGH_ARCH_4
 #else
 # define VM_MPX		VM_NONE
 #endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 46f4ecf5..1861ea8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -445,6 +445,9 @@
 	unsigned long flags; /* Must use atomic bitops to access the bits */
 
 	struct core_state *core_state; /* coredumping support */
+#ifdef CONFIG_MEMBARRIER
+	atomic_t membarrier_state;
+#endif
 #ifdef CONFIG_AIO
 	spinlock_t			ioctx_lock;
 	struct kioctx_table __rcu	*ioctx_table;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index f3f2d07..9a43763 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -316,7 +316,7 @@
 #define MMC_CAP_UHS_SDR50	(1 << 18)	/* Host supports UHS SDR50 mode */
 #define MMC_CAP_UHS_SDR104	(1 << 19)	/* Host supports UHS SDR104 mode */
 #define MMC_CAP_UHS_DDR50	(1 << 20)	/* Host supports UHS DDR50 mode */
-#define MMC_CAP_NO_BOUNCE_BUFF	(1 << 21)	/* Disable bounce buffers on host */
+/* (1 << 21) is free for reuse */
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
 #define MMC_CAP_DRIVER_TYPE_D	(1 << 25)	/* Host supports Driver Type D */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 7b2e31b..6866e81 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -400,6 +400,11 @@
 
 #else /* CONFIG_MMU_NOTIFIER */
 
+static inline int mm_has_notifiers(struct mm_struct *mm)
+{
+	return 0;
+}
+
 static inline void mmu_notifier_release(struct mm_struct *mm)
 {
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 356a814..c8f8941 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1094,8 +1094,14 @@
 #error Allocator MAX_ORDER exceeds SECTION_SIZE
 #endif
 
-#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT)
-#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT)
+static inline unsigned long pfn_to_section_nr(unsigned long pfn)
+{
+	return pfn >> PFN_SECTION_SHIFT;
+}
+static inline unsigned long section_nr_to_pfn(unsigned long sec)
+{
+	return sec << PFN_SECTION_SHIFT;
+}
 
 #define SECTION_ALIGN_UP(pfn)	(((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 694cebb..2657f9f 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -293,6 +293,7 @@
 #define INPUT_DEVICE_ID_SND_MAX		0x07
 #define INPUT_DEVICE_ID_FF_MAX		0x7f
 #define INPUT_DEVICE_ID_SW_MAX		0x0f
+#define INPUT_DEVICE_ID_PROP_MAX	0x1f
 
 #define INPUT_DEVICE_ID_MATCH_BUS	1
 #define INPUT_DEVICE_ID_MATCH_VENDOR	2
@@ -308,6 +309,7 @@
 #define INPUT_DEVICE_ID_MATCH_SNDBIT	0x0400
 #define INPUT_DEVICE_ID_MATCH_FFBIT	0x0800
 #define INPUT_DEVICE_ID_MATCH_SWBIT	0x1000
+#define INPUT_DEVICE_ID_MATCH_PROPBIT	0x2000
 
 struct input_device_id {
 
@@ -327,6 +329,7 @@
 	kernel_ulong_t sndbit[INPUT_DEVICE_ID_SND_MAX / BITS_PER_LONG + 1];
 	kernel_ulong_t ffbit[INPUT_DEVICE_ID_FF_MAX / BITS_PER_LONG + 1];
 	kernel_ulong_t swbit[INPUT_DEVICE_ID_SW_MAX / BITS_PER_LONG + 1];
+	kernel_ulong_t propbit[INPUT_DEVICE_ID_PROP_MAX / BITS_PER_LONG + 1];
 
 	kernel_ulong_t driver_info;
 };
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f535779..2eaac7d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3694,6 +3694,9 @@
 				    unsigned char name_assign_type,
 				    void (*setup)(struct net_device *),
 				    unsigned int txqs, unsigned int rxqs);
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name);
+
 #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \
 	alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)
 
diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index 2c2a551..528b24c 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -108,9 +108,10 @@
 
 #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \
 		     ~(__alignof__(struct _xt_align)-1))
-extern struct ebt_table *ebt_register_table(struct net *net,
-					    const struct ebt_table *table,
-					    const struct nf_hook_ops *);
+extern int ebt_register_table(struct net *net,
+			      const struct ebt_table *table,
+			      const struct nf_hook_ops *ops,
+			      struct ebt_table **res);
 extern void ebt_unregister_table(struct net *net, struct ebt_table *table,
 				 const struct nf_hook_ops *);
 extern unsigned int ebt_do_table(struct sk_buff *skb,
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index a36abe2..27e249e 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -12,11 +12,31 @@
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 void lockup_detector_init(void);
+void lockup_detector_soft_poweroff(void);
+void lockup_detector_cleanup(void);
+bool is_hardlockup(void);
+
+extern int watchdog_user_enabled;
+extern int nmi_watchdog_user_enabled;
+extern int soft_watchdog_user_enabled;
+extern int watchdog_thresh;
+extern unsigned long watchdog_enabled;
+
+extern struct cpumask watchdog_cpumask;
+extern unsigned long *watchdog_cpumask_bits;
+#ifdef CONFIG_SMP
+extern int sysctl_softlockup_all_cpu_backtrace;
+extern int sysctl_hardlockup_all_cpu_backtrace;
 #else
-static inline void lockup_detector_init(void)
-{
-}
-#endif
+#define sysctl_softlockup_all_cpu_backtrace 0
+#define sysctl_hardlockup_all_cpu_backtrace 0
+#endif /* !CONFIG_SMP */
+
+#else /* CONFIG_LOCKUP_DETECTOR */
+static inline void lockup_detector_init(void) { }
+static inline void lockup_detector_soft_poweroff(void) { }
+static inline void lockup_detector_cleanup(void) { }
+#endif /* !CONFIG_LOCKUP_DETECTOR */
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 extern void touch_softlockup_watchdog_sched(void);
@@ -24,29 +44,17 @@
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern unsigned int  softlockup_panic;
-extern int soft_watchdog_enabled;
-extern atomic_t watchdog_park_in_progress;
 #else
-static inline void touch_softlockup_watchdog_sched(void)
-{
-}
-static inline void touch_softlockup_watchdog(void)
-{
-}
-static inline void touch_softlockup_watchdog_sync(void)
-{
-}
-static inline void touch_all_softlockup_watchdogs(void)
-{
-}
+static inline void touch_softlockup_watchdog_sched(void) { }
+static inline void touch_softlockup_watchdog(void) { }
+static inline void touch_softlockup_watchdog_sync(void) { }
+static inline void touch_all_softlockup_watchdogs(void) { }
 #endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK
 void reset_hung_task_detector(void);
 #else
-static inline void reset_hung_task_detector(void)
-{
-}
+static inline void reset_hung_task_detector(void) { }
 #endif
 
 /*
@@ -54,12 +62,12 @@
  * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
  * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
  *
- * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled'
- * are variables that are only used as an 'interface' between the parameters
- * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The
- * 'watchdog_thresh' variable is handled differently because its value is not
- * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh'
- * is equal zero.
+ * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and
+ * 'soft_watchdog_user_enabled' are variables that are only used as an
+ * 'interface' between the parameters in /proc/sys/kernel and the internal
+ * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is
+ * handled differently because its value is not boolean, and the lockup
+ * detectors are 'suspended' while 'watchdog_thresh' is equal zero.
  */
 #define NMI_WATCHDOG_ENABLED_BIT   0
 #define SOFT_WATCHDOG_ENABLED_BIT  1
@@ -73,17 +81,41 @@
 static inline void hardlockup_detector_disable(void) {}
 #endif
 
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+# define NMI_WATCHDOG_SYSCTL_PERM	0644
+#else
+# define NMI_WATCHDOG_SYSCTL_PERM	0444
+#endif
+
 #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void arch_touch_nmi_watchdog(void);
+extern void hardlockup_detector_perf_stop(void);
+extern void hardlockup_detector_perf_restart(void);
+extern void hardlockup_detector_perf_disable(void);
+extern void hardlockup_detector_perf_enable(void);
+extern void hardlockup_detector_perf_cleanup(void);
+extern int hardlockup_detector_perf_init(void);
 #else
-#if !defined(CONFIG_HAVE_NMI_WATCHDOG)
+static inline void hardlockup_detector_perf_stop(void) { }
+static inline void hardlockup_detector_perf_restart(void) { }
+static inline void hardlockup_detector_perf_disable(void) { }
+static inline void hardlockup_detector_perf_enable(void) { }
+static inline void hardlockup_detector_perf_cleanup(void) { }
+# if !defined(CONFIG_HAVE_NMI_WATCHDOG)
+static inline int hardlockup_detector_perf_init(void) { return -ENODEV; }
 static inline void arch_touch_nmi_watchdog(void) {}
+# else
+static inline int hardlockup_detector_perf_init(void) { return 0; }
+# endif
 #endif
-#endif
+
+void watchdog_nmi_stop(void);
+void watchdog_nmi_start(void);
+int watchdog_nmi_probe(void);
 
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
- * 
+ *
  * If the architecture supports the NMI watchdog, touch_nmi_watchdog()
  * may be used to reset the timeout - for code which intentionally
  * disables interrupts for a long time. This call is stateless.
@@ -153,22 +185,6 @@
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
 #endif
 
-#ifdef CONFIG_LOCKUP_DETECTOR
-extern int nmi_watchdog_enabled;
-extern int watchdog_user_enabled;
-extern int watchdog_thresh;
-extern unsigned long watchdog_enabled;
-extern struct cpumask watchdog_cpumask;
-extern unsigned long *watchdog_cpumask_bits;
-extern int __read_mostly watchdog_suspended;
-#ifdef CONFIG_SMP
-extern int sysctl_softlockup_all_cpu_backtrace;
-extern int sysctl_hardlockup_all_cpu_backtrace;
-#else
-#define sysctl_softlockup_all_cpu_backtrace 0
-#define sysctl_hardlockup_all_cpu_backtrace 0
-#endif
-
 #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \
     defined(CONFIG_HARDLOCKUP_DETECTOR)
 void watchdog_update_hrtimer_threshold(u64 period);
@@ -176,7 +192,6 @@
 static inline void watchdog_update_hrtimer_threshold(u64 period) { }
 #endif
 
-extern bool is_hardlockup(void);
 struct ctl_table;
 extern int proc_watchdog(struct ctl_table *, int ,
 			 void __user *, size_t *, loff_t *);
@@ -188,18 +203,6 @@
 				void __user *, size_t *, loff_t *);
 extern int proc_watchdog_cpumask(struct ctl_table *, int,
 				 void __user *, size_t *, loff_t *);
-extern int lockup_detector_suspend(void);
-extern void lockup_detector_resume(void);
-#else
-static inline int lockup_detector_suspend(void)
-{
-	return 0;
-}
-
-static inline void lockup_detector_resume(void)
-{
-}
-#endif
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
 #include <asm/nmi.h>
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 9c5cb44..a726f96 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -346,11 +346,6 @@
  *       indicating an FC transport Aborted status.
  *       Entrypoint is Mandatory.
  *
- * @defer_rcv:  Called by the transport to signal the LLLD that it has
- *       begun processing of a previously received NVME CMD IU. The LLDD
- *       is now free to re-use the rcv buffer associated with the
- *       nvmefc_tgt_fcp_req.
- *
  * @max_hw_queues:  indicates the maximum number of hw queues the LLDD
  *       supports for cpu affinitization.
  *       Value is Mandatory. Must be at least 1.
@@ -806,11 +801,19 @@
  *       outstanding operation (if there was one) to complete, then will
  *       call the fcp_req_release() callback to return the command's
  *       exchange context back to the LLDD.
+ *       Entrypoint is Mandatory.
  *
  * @fcp_req_release:  Called by the transport to return a nvmefc_tgt_fcp_req
  *       to the LLDD after all operations on the fcp operation are complete.
  *       This may be due to the command completing or upon completion of
  *       abort cleanup.
+ *       Entrypoint is Mandatory.
+ *
+ * @defer_rcv:  Called by the transport to signal the LLLD that it has
+ *       begun processing of a previously received NVME CMD IU. The LLDD
+ *       is now free to re-use the rcv buffer associated with the
+ *       nvmefc_tgt_fcp_req.
+ *       Entrypoint is Optional.
  *
  * @max_hw_queues:  indicates the maximum number of hw queues the LLDD
  *       supports for cpu affinitization.
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 87723c8..9310ce77 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -471,12 +471,14 @@
  *
  * @NVME_SGL_FMT_ADDRESS:     absolute address of the data block
  * @NVME_SGL_FMT_OFFSET:      relative offset of the in-capsule data block
+ * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA
  * @NVME_SGL_FMT_INVALIDATE:  RDMA transport specific remote invalidation
  *                            request subtype
  */
 enum {
 	NVME_SGL_FMT_ADDRESS		= 0x00,
 	NVME_SGL_FMT_OFFSET		= 0x01,
+	NVME_SGL_FMT_TRANSPORT_A	= 0x0A,
 	NVME_SGL_FMT_INVALIDATE		= 0x0f,
 };
 
@@ -490,12 +492,16 @@
  *
  * For struct nvme_keyed_sgl_desc:
  *   @NVME_KEY_SGL_FMT_DATA_DESC:	keyed data block descriptor
+ *
+ * Transport-specific SGL types:
+ *   @NVME_TRANSPORT_SGL_DATA_DESC:	Transport SGL data dlock descriptor
  */
 enum {
 	NVME_SGL_FMT_DATA_DESC		= 0x00,
 	NVME_SGL_FMT_SEG_DESC		= 0x02,
 	NVME_SGL_FMT_LAST_SEG_DESC	= 0x03,
 	NVME_KEY_SGL_FMT_DATA_DESC	= 0x04,
+	NVME_TRANSPORT_SGL_DATA_DESC	= 0x05,
 };
 
 struct nvme_sgl_desc {
@@ -1127,19 +1133,6 @@
 	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
 	NVME_SC_DNR			= 0x4000,
-
-
-	/*
-	 * FC Transport-specific error status values for NVME commands
-	 *
-	 * Transport-specific status code values must be in the range 0xB0..0xBF
-	 */
-
-	/* Generic FC failure - catchall */
-	NVME_SC_FC_TRANSPORT_ERROR	= 0x00B0,
-
-	/* I/O failure due to FC ABTS'd */
-	NVME_SC_FC_TRANSPORT_ABORTED	= 0x00B1,
 };
 
 struct nvme_completion {
diff --git a/include/linux/of.h b/include/linux/of.h
index cfc34117..b240ed6 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -734,6 +734,16 @@
 	return NULL;
 }
 
+static inline int of_n_addr_cells(struct device_node *np)
+{
+	return 0;
+
+}
+static inline int of_n_size_cells(struct device_node *np)
+{
+	return 0;
+}
+
 static inline int of_property_read_u64(const struct device_node *np,
 				       const char *propname, u64 *out_value)
 {
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index e0d1946..fb908e5 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -57,7 +57,14 @@
 extern struct platform_device *of_device_alloc(struct device_node *np,
 					 const char *bus_id,
 					 struct device *parent);
+#ifdef CONFIG_OF
 extern struct platform_device *of_find_device_by_node(struct device_node *np);
+#else
+static inline struct platform_device *of_find_device_by_node(struct device_node *np)
+{
+	return NULL;
+}
+#endif
 
 /* Platform devices and busses creation */
 extern struct platform_device *of_platform_device_create(struct device_node *np,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index f68c58a..f4f8ee5 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1685,6 +1685,8 @@
 
 #define dev_is_pci(d) (false)
 #define dev_is_pf(d) (false)
+static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
+{ return false; }
 #endif /* CONFIG_PCI */
 
 /* Include architecture-dependent settings and functions */
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 032b559..6737a8c 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -27,16 +27,17 @@
 	PM_QOS_FLAGS_ALL,
 };
 
-#define PM_QOS_DEFAULT_VALUE -1
+#define PM_QOS_DEFAULT_VALUE	(-1)
+#define PM_QOS_LATENCY_ANY	S32_MAX
 
 #define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_NETWORK_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE	0
 #define PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE	0
 #define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE	0
+#define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT	PM_QOS_LATENCY_ANY
 #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE	0
 #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT	(-1)
-#define PM_QOS_LATENCY_ANY			((s32)(~(__u32)0 >> 1))
 
 #define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
 #define PM_QOS_FLAG_REMOTE_WAKEUP	(1 << 1)
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index b1fd8bf..2bea1d5 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -276,7 +276,7 @@
 #define list_entry_rcu(ptr, type, member) \
 	container_of(lockless_dereference(ptr), type, member)
 
-/**
+/*
  * Where are list_empty_rcu() and list_first_entry_rcu()?
  *
  * Implementing those functions following their counterparts list_empty() and
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index de50d8a..1a9f70d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -523,7 +523,7 @@
  * Return the value of the specified RCU-protected pointer, but omit
  * both the smp_read_barrier_depends() and the READ_ONCE().  This
  * is useful in cases where update-side locks prevent the value of the
- * pointer from changing.  Please note that this primitive does -not-
+ * pointer from changing.  Please note that this primitive does *not*
  * prevent the compiler from repeating this reference or combining it
  * with other references, so it should not be used without protection
  * of appropriate locks.
@@ -568,7 +568,7 @@
  * is handed off from RCU to some other synchronization mechanism, for
  * example, reference counting or locking.  In C11, it would map to
  * kill_dependency().  It could be used as follows:
- *
+ * ``
  *	rcu_read_lock();
  *	p = rcu_dereference(gp);
  *	long_lived = is_long_lived(p);
@@ -579,6 +579,7 @@
  *			p = rcu_pointer_handoff(p);
  *	}
  *	rcu_read_unlock();
+ *``
  */
 #define rcu_pointer_handoff(p) (p)
 
@@ -778,18 +779,21 @@
 
 /**
  * RCU_INIT_POINTER() - initialize an RCU protected pointer
+ * @p: The pointer to be initialized.
+ * @v: The value to initialized the pointer to.
  *
  * Initialize an RCU-protected pointer in special cases where readers
  * do not need ordering constraints on the CPU or the compiler.  These
  * special cases are:
  *
- * 1.	This use of RCU_INIT_POINTER() is NULLing out the pointer -or-
+ * 1.	This use of RCU_INIT_POINTER() is NULLing out the pointer *or*
  * 2.	The caller has taken whatever steps are required to prevent
- *	RCU readers from concurrently accessing this pointer -or-
+ *	RCU readers from concurrently accessing this pointer *or*
  * 3.	The referenced data structure has already been exposed to
- *	readers either at compile time or via rcu_assign_pointer() -and-
- *	a.	You have not made -any- reader-visible changes to
- *		this structure since then -or-
+ *	readers either at compile time or via rcu_assign_pointer() *and*
+ *
+ *	a.	You have not made *any* reader-visible changes to
+ *		this structure since then *or*
  *	b.	It is OK for readers accessing this structure from its
  *		new location to see the old state of the structure.  (For
  *		example, the changes were to statistical counters or to
@@ -805,7 +809,7 @@
  * by a single external-to-structure RCU-protected pointer, then you may
  * use RCU_INIT_POINTER() to initialize the internal RCU-protected
  * pointers, but you must use rcu_assign_pointer() to initialize the
- * external-to-structure pointer -after- you have completely initialized
+ * external-to-structure pointer *after* you have completely initialized
  * the reader-accessible portions of the linked structure.
  *
  * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no
@@ -819,6 +823,8 @@
 
 /**
  * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer
+ * @p: The pointer to be initialized.
+ * @v: The value to initialized the pointer to.
  *
  * GCC-style initialization for an RCU-protected pointer in a structure field.
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 92fb8dd..26a7df4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -65,25 +65,23 @@
  */
 
 /* Used in tsk->state: */
-#define TASK_RUNNING			0
-#define TASK_INTERRUPTIBLE		1
-#define TASK_UNINTERRUPTIBLE		2
-#define __TASK_STOPPED			4
-#define __TASK_TRACED			8
+#define TASK_RUNNING			0x0000
+#define TASK_INTERRUPTIBLE		0x0001
+#define TASK_UNINTERRUPTIBLE		0x0002
+#define __TASK_STOPPED			0x0004
+#define __TASK_TRACED			0x0008
 /* Used in tsk->exit_state: */
-#define EXIT_DEAD			16
-#define EXIT_ZOMBIE			32
+#define EXIT_DEAD			0x0010
+#define EXIT_ZOMBIE			0x0020
 #define EXIT_TRACE			(EXIT_ZOMBIE | EXIT_DEAD)
 /* Used in tsk->state again: */
-#define TASK_DEAD			64
-#define TASK_WAKEKILL			128
-#define TASK_WAKING			256
-#define TASK_PARKED			512
-#define TASK_NOLOAD			1024
-#define TASK_NEW			2048
-#define TASK_STATE_MAX			4096
-
-#define TASK_STATE_TO_CHAR_STR		"RSDTtXZxKWPNn"
+#define TASK_PARKED			0x0040
+#define TASK_DEAD			0x0080
+#define TASK_WAKEKILL			0x0100
+#define TASK_WAKING			0x0200
+#define TASK_NOLOAD			0x0400
+#define TASK_NEW			0x0800
+#define TASK_STATE_MAX			0x1000
 
 /* Convenience macros for the sake of set_current_state: */
 #define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
@@ -99,7 +97,8 @@
 /* get_task_state(): */
 #define TASK_REPORT			(TASK_RUNNING | TASK_INTERRUPTIBLE | \
 					 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
-					 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
+					 __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
+					 TASK_PARKED)
 
 #define task_is_traced(task)		((task->state & __TASK_TRACED) != 0)
 
@@ -1243,17 +1242,34 @@
 	return task_pgrp_nr_ns(tsk, &init_pid_ns);
 }
 
-static inline char task_state_to_char(struct task_struct *task)
+#define TASK_REPORT_IDLE	(TASK_REPORT + 1)
+#define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
+
+static inline unsigned int __get_task_state(struct task_struct *tsk)
 {
-	const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
-	unsigned long state = task->state;
+	unsigned int tsk_state = READ_ONCE(tsk->state);
+	unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
 
-	state = state ? __ffs(state) + 1 : 0;
+	BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
 
-	/* Make sure the string lines up properly with the number of task states: */
-	BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1);
+	if (tsk_state == TASK_IDLE)
+		state = TASK_REPORT_IDLE;
 
-	return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?';
+	return fls(state);
+}
+
+static inline char __task_state_to_char(unsigned int state)
+{
+	static const char state_char[] = "RSDTtXZPI";
+
+	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);
+
+	return state_char[state];
+}
+
+static inline char task_state_to_char(struct task_struct *tsk)
+{
+	return __task_state_to_char(__get_task_state(tsk));
 }
 
 /**
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3a19c25..ab9bf7b 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -84,6 +84,12 @@
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
+#ifdef CONFIG_MMU
+/* same as above but performs the slow path from the async context. Can
+ * be called from the atomic context as well
+ */
+void mmput_async(struct mm_struct *);
+#endif
 
 /* Grab a reference to a task's mm, if it is not already going away */
 extern struct mm_struct *get_task_mm(struct task_struct *task);
@@ -205,4 +211,20 @@
 	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
 }
 
+#ifdef CONFIG_MEMBARRIER
+enum {
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY	= (1U << 0),
+	MEMBARRIER_STATE_SWITCH_MM			= (1U << 1),
+};
+
+static inline void membarrier_execve(struct task_struct *t)
+{
+	atomic_set(&t->mm->membarrier_state, 0);
+}
+#else
+static inline void membarrier_execve(struct task_struct *t)
+{
+}
+#endif
+
 #endif /* _LINUX_SCHED_MM_H */
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index d7b6dab..7d065ab 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -71,14 +71,6 @@
 	atomic_t	ref;
 	atomic_t	nr_busy_cpus;
 	int		has_idle_cores;
-
-	/*
-	 * Some variables from the most recent sd_lb_stats for this domain,
-	 * used by wake_affine().
-	 */
-	unsigned long	nr_running;
-	unsigned long	load;
-	unsigned long	capacity;
 };
 
 struct sched_domain {
diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index 82b171e..da803df 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -231,7 +231,7 @@
 	__be32 tsn;
 	__be16 stream;
 	__be16 ssn;
-	__be32 ppid;
+	__u32 ppid;
 	__u8  payload[0];
 };
 
@@ -716,28 +716,28 @@
 
 struct sctp_strreset_outreq {
 	struct sctp_paramhdr param_hdr;
-	__u32 request_seq;
-	__u32 response_seq;
-	__u32 send_reset_at_tsn;
-	__u16 list_of_streams[0];
+	__be32 request_seq;
+	__be32 response_seq;
+	__be32 send_reset_at_tsn;
+	__be16 list_of_streams[0];
 };
 
 struct sctp_strreset_inreq {
 	struct sctp_paramhdr param_hdr;
-	__u32 request_seq;
-	__u16 list_of_streams[0];
+	__be32 request_seq;
+	__be16 list_of_streams[0];
 };
 
 struct sctp_strreset_tsnreq {
 	struct sctp_paramhdr param_hdr;
-	__u32 request_seq;
+	__be32 request_seq;
 };
 
 struct sctp_strreset_addstrm {
 	struct sctp_paramhdr param_hdr;
-	__u32 request_seq;
-	__u16 number_of_streams;
-	__u16 reserved;
+	__be32 request_seq;
+	__be16 number_of_streams;
+	__be16 reserved;
 };
 
 enum {
@@ -752,16 +752,16 @@
 
 struct sctp_strreset_resp {
 	struct sctp_paramhdr param_hdr;
-	__u32 response_seq;
-	__u32 result;
+	__be32 response_seq;
+	__be32 result;
 };
 
 struct sctp_strreset_resptsn {
 	struct sctp_paramhdr param_hdr;
-	__u32 response_seq;
-	__u32 result;
-	__u32 senders_next_tsn;
-	__u32 receivers_next_tsn;
+	__be32 response_seq;
+	__be32 result;
+	__be32 senders_next_tsn;
+	__be32 receivers_next_tsn;
 };
 
 #endif /* __LINUX_SCTP_H__ */
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index ecc296c..c8bef43 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -3,7 +3,8 @@
 
 #include <uapi/linux/seccomp.h>
 
-#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC)
+#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC | \
+					 SECCOMP_FILTER_FLAG_LOG)
 
 #ifdef CONFIG_SECCOMP
 
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index 12910cf..c149aa7 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -55,7 +55,7 @@
 }
 
 void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
-int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					 const struct cpumask *);
+void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
+					  const struct cpumask *);
 
 #endif
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 39af9bc..62be896 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -78,6 +78,7 @@
 
 /**
  * srcu_read_lock_held - might we be in SRCU read-side critical section?
+ * @sp: The srcu_struct structure to check
  *
  * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
  * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
diff --git a/include/linux/swait.h b/include/linux/swait.h
index 73e97a0..cf30f502 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -9,13 +9,16 @@
 /*
  * Simple wait queues
  *
- * While these are very similar to the other/complex wait queues (wait.h) the
- * most important difference is that the simple waitqueue allows for
- * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold
- * times.
+ * While these are very similar to regular wait queues (wait.h) the most
+ * important difference is that the simple waitqueue allows for deterministic
+ * behaviour -- IOW it has strictly bounded IRQ and lock hold times.
  *
- * In order to make this so, we had to drop a fair number of features of the
- * other waitqueue code; notably:
+ * Mainly, this is accomplished by two things. Firstly not allowing swake_up_all
+ * from IRQ disabled, and dropping the lock upon every wakeup, giving a higher
+ * priority task a chance to run.
+ *
+ * Secondly, we had to drop a fair number of features of the other waitqueue
+ * code; notably:
  *
  *  - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue;
  *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
@@ -24,12 +27,14 @@
  *  - the exclusive mode; because this requires preserving the list order
  *    and this is hard.
  *
- *  - custom wake functions; because you cannot give any guarantees about
- *    random code.
+ *  - custom wake callback functions; because you cannot give any guarantees
+ *    about random code. This also allows swait to be used in RT, such that
+ *    raw spinlock can be used for the swait queue head.
  *
- * As a side effect of this; the data structures are slimmer.
- *
- * One would recommend using this wait queue where possible.
+ * As a side effect of these; the data structures are slimmer albeit more ad-hoc.
+ * For all the above, note that simple wait queues should _only_ be used under
+ * very specific realtime constraints -- it is best to stick with the regular
+ * wait queues in most cases.
  */
 
 struct task_struct;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 95606a2..a78186d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -221,22 +221,26 @@
 	}								\
 	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
-#ifdef TIF_FSCHECK
 /*
  * Called before coming back to user-mode. Returning to user-mode with an
  * address limit different than USER_DS can allow to overwrite kernel memory.
  */
 static inline void addr_limit_user_check(void)
 {
-
+#ifdef TIF_FSCHECK
 	if (!test_thread_flag(TIF_FSCHECK))
 		return;
-
-	BUG_ON(!segment_eq(get_fs(), USER_DS));
-	clear_thread_flag(TIF_FSCHECK);
-}
 #endif
 
+	if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
+				  "Invalid address limit on user-mode return"))
+		force_sig(SIGKILL, current);
+
+#ifdef TIF_FSCHECK
+	clear_thread_flag(TIF_FSCHECK);
+#endif
+}
+
 asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
 			       qid_t id, void __user *addr);
 asmlinkage long sys_time(time_t __user *tloc);
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 905d769..5f7eeab 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -42,7 +42,7 @@
 #define THREAD_ALIGN	THREAD_SIZE
 #endif
 
-#ifdef CONFIG_DEBUG_STACK_USAGE
+#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
 # define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \
 				 __GFP_ZERO)
 #else
diff --git a/include/linux/timer.h b/include/linux/timer.h
index e6789b8..6383c52 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -168,6 +168,20 @@
 #define setup_pinned_deferrable_timer_on_stack(timer, fn, data)		\
 	__setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED)
 
+#define TIMER_DATA_TYPE		unsigned long
+#define TIMER_FUNC_TYPE		void (*)(TIMER_DATA_TYPE)
+
+static inline void timer_setup(struct timer_list *timer,
+			       void (*callback)(struct timer_list *),
+			       unsigned int flags)
+{
+	__setup_timer(timer, (TIMER_FUNC_TYPE)callback,
+		      (TIMER_DATA_TYPE)timer, flags);
+}
+
+#define from_timer(var, callback_timer, timer_fieldname) \
+	container_of(callback_timer, typeof(*var), timer_fieldname)
+
 /**
  * timer_pending - is a timer pending?
  * @timer: the timer in question
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 7f11050..2e0f222 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -272,6 +272,7 @@
 	int				perf_refcount;
 	struct hlist_head __percpu	*perf_events;
 	struct bpf_prog			*prog;
+	struct perf_event		*bpf_prog_owner;
 
 	int	(*perf_perm)(struct trace_event_call *,
 			     struct perf_event *);
diff --git a/include/net/dst.h b/include/net/dst.h
index 93568bd..06a6765 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -271,7 +271,7 @@
 static inline struct dst_entry *dst_clone(struct dst_entry *dst)
 {
 	if (dst)
-		atomic_inc(&dst->__refcnt);
+		dst_hold(dst);
 	return dst;
 }
 
@@ -312,21 +312,6 @@
 }
 
 /**
- * skb_dst_force - makes sure skb dst is refcounted
- * @skb: buffer
- *
- * If dst is not yet refcounted, let's do it
- */
-static inline void skb_dst_force(struct sk_buff *skb)
-{
-	if (skb_dst_is_noref(skb)) {
-		WARN_ON(!rcu_read_lock_held());
-		skb->_skb_refdst &= ~SKB_DST_NOREF;
-		dst_clone(skb_dst(skb));
-	}
-}
-
-/**
  * dst_hold_safe - Take a reference on a dst if possible
  * @dst: pointer to dst entry
  *
@@ -339,16 +324,17 @@
 }
 
 /**
- * skb_dst_force_safe - makes sure skb dst is refcounted
+ * skb_dst_force - makes sure skb dst is refcounted
  * @skb: buffer
  *
  * If dst is not yet refcounted and not destroyed, grab a ref on it.
  */
-static inline void skb_dst_force_safe(struct sk_buff *skb)
+static inline void skb_dst_force(struct sk_buff *skb)
 {
 	if (skb_dst_is_noref(skb)) {
 		struct dst_entry *dst = skb_dst(skb);
 
+		WARN_ON(!rcu_read_lock_held());
 		if (!dst_hold_safe(dst))
 			dst = NULL;
 
diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h
index 4e6131c..ac1a231 100644
--- a/include/net/fq_impl.h
+++ b/include/net/fq_impl.h
@@ -146,6 +146,7 @@
 			   fq_flow_get_default_t get_default_func)
 {
 	struct fq_flow *flow;
+	bool oom;
 
 	lockdep_assert_held(&fq->lock);
 
@@ -167,8 +168,8 @@
 	}
 
 	__skb_queue_tail(&flow->queue, skb);
-
-	if (fq->backlog > fq->limit || fq->memory_usage > fq->memory_limit) {
+	oom = (fq->memory_usage > fq->memory_limit);
+	while (fq->backlog > fq->limit || oom) {
 		flow = list_first_entry_or_null(&fq->backlogs,
 						struct fq_flow,
 						backlogchain);
@@ -183,8 +184,10 @@
 
 		flow->tin->overlimit++;
 		fq->overlimit++;
-		if (fq->memory_usage > fq->memory_limit)
+		if (oom) {
 			fq->overmemory++;
+			oom = (fq->memory_usage > fq->memory_limit);
+		}
 	}
 }
 
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index aa95053..db8162d 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -96,7 +96,7 @@
 	kmemcheck_bitfield_end(flags);
 	u32                     ir_mark;
 	union {
-		struct ip_options_rcu	*opt;
+		struct ip_options_rcu __rcu	*ireq_opt;
 #if IS_ENABLED(CONFIG_IPV6)
 		struct {
 			struct ipv6_txoptions	*ipv6_opt;
@@ -132,6 +132,12 @@
 	return sk->sk_bound_dev_if;
 }
 
+static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq)
+{
+	return rcu_dereference_check(ireq->ireq_opt,
+				     refcount_read(&ireq->req.rsk_refcnt) > 0);
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;
diff --git a/include/net/netlink.h b/include/net/netlink.h
index e51cf5f..14c2893 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -773,7 +773,10 @@
  */
 static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value)
 {
-	return nla_put(skb, attrtype, sizeof(u8), &value);
+	/* temporary variables to work around GCC PR81715 with asan-stack=1 */
+	u8 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(u8), &tmp);
 }
 
 /**
@@ -784,7 +787,9 @@
  */
 static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value)
 {
-	return nla_put(skb, attrtype, sizeof(u16), &value);
+	u16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(u16), &tmp);
 }
 
 /**
@@ -795,7 +800,9 @@
  */
 static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value)
 {
-	return nla_put(skb, attrtype, sizeof(__be16), &value);
+	__be16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__be16), &tmp);
 }
 
 /**
@@ -806,7 +813,9 @@
  */
 static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value)
 {
-	return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, value);
+	__be16 tmp = value;
+
+	return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp);
 }
 
 /**
@@ -817,7 +826,9 @@
  */
 static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value)
 {
-	return nla_put(skb, attrtype, sizeof(__le16), &value);
+	__le16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__le16), &tmp);
 }
 
 /**
@@ -828,7 +839,9 @@
  */
 static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value)
 {
-	return nla_put(skb, attrtype, sizeof(u32), &value);
+	u32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(u32), &tmp);
 }
 
 /**
@@ -839,7 +852,9 @@
  */
 static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value)
 {
-	return nla_put(skb, attrtype, sizeof(__be32), &value);
+	__be32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__be32), &tmp);
 }
 
 /**
@@ -850,7 +865,9 @@
  */
 static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value)
 {
-	return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, value);
+	__be32 tmp = value;
+
+	return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp);
 }
 
 /**
@@ -861,7 +878,9 @@
  */
 static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value)
 {
-	return nla_put(skb, attrtype, sizeof(__le32), &value);
+	__le32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__le32), &tmp);
 }
 
 /**
@@ -874,7 +893,9 @@
 static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype,
 				    u64 value, int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(u64), &value, padattr);
+	u64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr);
 }
 
 /**
@@ -887,7 +908,9 @@
 static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value,
 			       int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(__be64), &value, padattr);
+	__be64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr);
 }
 
 /**
@@ -900,7 +923,9 @@
 static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value,
 				int padattr)
 {
-	return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, value,
+	__be64 tmp = value;
+
+	return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp,
 			    padattr);
 }
 
@@ -914,7 +939,9 @@
 static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value,
 			       int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(__le64), &value, padattr);
+	__le64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr);
 }
 
 /**
@@ -925,7 +952,9 @@
  */
 static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value)
 {
-	return nla_put(skb, attrtype, sizeof(s8), &value);
+	s8 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(s8), &tmp);
 }
 
 /**
@@ -936,7 +965,9 @@
  */
 static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value)
 {
-	return nla_put(skb, attrtype, sizeof(s16), &value);
+	s16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(s16), &tmp);
 }
 
 /**
@@ -947,7 +978,9 @@
  */
 static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value)
 {
-	return nla_put(skb, attrtype, sizeof(s32), &value);
+	s32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(s32), &tmp);
 }
 
 /**
@@ -960,7 +993,9 @@
 static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value,
 			      int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(s64), &value, padattr);
+	s64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr);
 }
 
 /**
@@ -1010,7 +1045,9 @@
 static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype,
 				  __be32 addr)
 {
-	return nla_put_be32(skb, attrtype, addr);
+	__be32 tmp = addr;
+
+	return nla_put_be32(skb, attrtype, tmp);
 }
 
 /**
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e80edd8..3009547 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -2,6 +2,7 @@
 #define __NET_PKT_CLS_H
 
 #include <linux/pkt_cls.h>
+#include <linux/workqueue.h>
 #include <net/sch_generic.h>
 #include <net/act_api.h>
 
@@ -17,6 +18,8 @@
 int register_tcf_proto_ops(struct tcf_proto_ops *ops);
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
 
+bool tcf_queue_work(struct work_struct *work);
+
 #ifdef CONFIG_NET_CLS
 struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
 				bool create);
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 65ba335..4fc75f7 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -39,8 +39,8 @@
 
 /* This is used to register protocols. */
 struct net_protocol {
-	void			(*early_demux)(struct sk_buff *skb);
-	void                    (*early_demux_handler)(struct sk_buff *skb);
+	int			(*early_demux)(struct sk_buff *skb);
+	int			(*early_demux_handler)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	unsigned int		no_policy:1,
diff --git a/include/net/route.h b/include/net/route.h
index 1b09a93..d538e6d 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -175,7 +175,9 @@
 	fl4->fl4_gre_key = gre_key;
 	return ip_route_output_key(net, fl4);
 }
-
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag);
 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
 			 u8 tos, struct net_device *devin);
 int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src,
@@ -190,7 +192,7 @@
 	rcu_read_lock();
 	err = ip_route_input_noref(skb, dst, src, tos, devin);
 	if (!err) {
-		skb_dst_force_safe(skb);
+		skb_dst_force(skb);
 		if (!skb_dst(skb))
 			err = -EINVAL;
 	}
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 135f5a2..0dec8a2 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -10,6 +10,7 @@
 #include <linux/dynamic_queue_limits.h>
 #include <linux/list.h>
 #include <linux/refcount.h>
+#include <linux/workqueue.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 
@@ -271,6 +272,7 @@
 
 struct tcf_block {
 	struct list_head chain_list;
+	struct work_struct work;
 };
 
 static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 2db3d3a..88233cf 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -261,7 +261,7 @@
 				    struct sctp_fwdtsn_skip *skiplist);
 struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc);
 struct sctp_chunk *sctp_make_strreset_req(const struct sctp_association *asoc,
-					  __u16 stream_num, __u16 *stream_list,
+					  __u16 stream_num, __be16 *stream_list,
 					  bool out, bool in);
 struct sctp_chunk *sctp_make_strreset_tsnreq(
 					const struct sctp_association *asoc);
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index b8c86ec..231dc42 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -130,7 +130,7 @@
 
 struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
 	const struct sctp_association *asoc, __u16 flags,
-	__u16 stream_num, __u16 *stream_list, gfp_t gfp);
+	__u16 stream_num, __be16 *stream_list, gfp_t gfp);
 
 struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event(
 	const struct sctp_association *asoc, __u16 flags,
diff --git a/include/net/sock.h b/include/net/sock.h
index 03a3625..a6b9a8d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -856,7 +856,7 @@
 static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	/* dont let skb dst not refcounted, we are going to leave rcu lock */
-	skb_dst_force_safe(skb);
+	skb_dst_force(skb);
 
 	if (!sk->sk_backlog.tail)
 		sk->sk_backlog.head = skb;
diff --git a/include/net/strparser.h b/include/net/strparser.h
index 7dc131d..d96b59f 100644
--- a/include/net/strparser.h
+++ b/include/net/strparser.h
@@ -74,10 +74,9 @@
 	u32 unrecov_intr : 1;
 
 	struct sk_buff **skb_nextp;
-	struct timer_list msg_timer;
 	struct sk_buff *skb_head;
 	unsigned int need_bytes;
-	struct delayed_work delayed_work;
+	struct delayed_work msg_timer_work;
 	struct work_struct work;
 	struct strp_stats stats;
 	struct strp_callbacks cb;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b510f28..33599d17 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -345,7 +345,7 @@
 
 void tcp_shutdown(struct sock *sk, int how);
 
-void tcp_v4_early_demux(struct sk_buff *skb);
+int tcp_v4_early_demux(struct sk_buff *skb);
 int tcp_v4_rcv(struct sk_buff *skb);
 
 int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
@@ -544,7 +544,6 @@
 		     int min_tso_segs);
 void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
 			       int nonagle);
-bool tcp_may_send_now(struct sock *sk);
 int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
 int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
 void tcp_retransmit_timer(struct sock *sk);
@@ -841,6 +840,12 @@
 			struct inet6_skb_parm	h6;
 #endif
 		} header;	/* For incoming skbs */
+		struct {
+			__u32 key;
+			__u32 flags;
+			struct bpf_map *map;
+			void *data_end;
+		} bpf;
 	};
 };
 
diff --git a/include/net/udp.h b/include/net/udp.h
index 12dfbfe..6c759c8 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -259,7 +259,7 @@
 	return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err);
 }
 
-void udp_v4_early_demux(struct sk_buff *skb);
+int udp_v4_early_demux(struct sk_buff *skb);
 bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index bdb1279..e8608b2 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -285,7 +285,7 @@
 	IB_TM_CAP_RC		    = 1 << 0,
 };
 
-struct ib_xrq_caps {
+struct ib_tm_caps {
 	/* Max size of RNDV header */
 	u32 max_rndv_hdr_size;
 	/* Max number of entries in tag matching list */
@@ -358,7 +358,7 @@
 	struct ib_rss_caps	rss_caps;
 	u32			max_wq_type_rq;
 	u32			raw_packet_caps; /* Use ib_raw_packet_caps enum */
-	struct ib_xrq_caps	xrq_caps;
+	struct ib_tm_caps	tm_caps;
 };
 
 enum ib_mtu {
@@ -1739,7 +1739,7 @@
 	u32		   lkey;
 	u32		   rkey;
 	u64		   iova;
-	u32		   length;
+	u64		   length;
 	unsigned int	   page_size;
 	bool		   need_inval;
 	union {
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 82e93ee..67c5a9f 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -192,6 +192,7 @@
 	unsigned no_dif:1;	/* T10 PI (DIF) should be disabled */
 	unsigned broken_fua:1;		/* Don't set FUA bit */
 	unsigned lun_in_cdb:1;		/* Store LUN bits in CDB[1] */
+	unsigned unmap_limit_for_ws:1;	/* Use the UNMAP limit for WRITE SAME */
 
 	atomic_t disk_events_disable_depth; /* disable depth for disk events */
 
diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h
index 9592570..36b0301 100644
--- a/include/scsi/scsi_devinfo.h
+++ b/include/scsi/scsi_devinfo.h
@@ -29,5 +29,6 @@
 #define BLIST_TRY_VPD_PAGES	0x10000000 /* Attempt to read VPD pages */
 #define BLIST_NO_RSOC		0x20000000 /* don't try to issue RSOC */
 #define BLIST_MAX_1024		0x40000000 /* maximum 1024 sector cdb length */
+#define BLIST_UNMAP_LIMIT_WS	0x80000000 /* Use UNMAP limit for WRITE SAME */
 
 #endif
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 6183d20..b266d2a 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -434,7 +434,6 @@
 						unsigned int target_id);
 extern void iscsi_remove_session(struct iscsi_cls_session *session);
 extern void iscsi_free_session(struct iscsi_cls_session *session);
-extern int iscsi_destroy_session(struct iscsi_cls_session *session);
 extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess,
 						int dd_size, uint32_t cid);
 extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn);
diff --git a/include/sound/control.h b/include/sound/control.h
index bd7246d..a1f1152 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -248,6 +248,9 @@
 			     void *private_data);
 void snd_ctl_sync_vmaster(struct snd_kcontrol *kctl, bool hook_only);
 #define snd_ctl_sync_vmaster_hook(kctl)	snd_ctl_sync_vmaster(kctl, true)
+int snd_ctl_apply_vmaster_slaves(struct snd_kcontrol *kctl,
+				 int (*func)(struct snd_kcontrol *, void *),
+				 void *arg);
 
 /*
  * Helper functions for jack-detection controls
diff --git a/include/sound/hda_verbs.h b/include/sound/hda_verbs.h
index d0509db..f89cd5e 100644
--- a/include/sound/hda_verbs.h
+++ b/include/sound/hda_verbs.h
@@ -95,6 +95,7 @@
 #define AC_VERB_SET_EAPD_BTLENABLE		0x70c
 #define AC_VERB_SET_DIGI_CONVERT_1		0x70d
 #define AC_VERB_SET_DIGI_CONVERT_2		0x70e
+#define AC_VERB_SET_DIGI_CONVERT_3		0x73e
 #define AC_VERB_SET_VOLUME_KNOB_CONTROL		0x70f
 #define AC_VERB_SET_GPIO_DATA			0x715
 #define AC_VERB_SET_GPIO_MASK			0x716
diff --git a/include/sound/seq_virmidi.h b/include/sound/seq_virmidi.h
index a03acd0..695257a 100644
--- a/include/sound/seq_virmidi.h
+++ b/include/sound/seq_virmidi.h
@@ -60,6 +60,7 @@
 	int port;			/* created/attached port */
 	unsigned int flags;		/* SNDRV_VIRMIDI_* */
 	rwlock_t filelist_lock;
+	struct rw_semaphore filelist_sem;
 	struct list_head filelist;
 };
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index ae1409f..3c8b7f6 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -114,7 +114,10 @@
 	 * Preemption ignores task state, therefore preempted tasks are always
 	 * RUNNING (we will not have dequeued if state != RUNNING).
 	 */
-	return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
+	if (preempt)
+		return TASK_STATE_MAX;
+
+	return __get_task_state(p);
 }
 #endif /* CREATE_TRACE_POINTS */
 
@@ -152,12 +155,14 @@
 
 	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
-		__entry->prev_state & (TASK_STATE_MAX-1) ?
-		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
-				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
-				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
-				{ 128, "K" }, { 256, "W" }, { 512, "P" },
-				{ 1024, "N" }) : "R",
+
+		(__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
+		  __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
+				{ 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" },
+				{ 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" },
+				{ 0x40, "P" }, { 0x80, "I" }) :
+		  "R",
+
 		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 43ab5c4..0d7948c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -312,7 +312,7 @@
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
@@ -575,7 +575,7 @@
  *     @map: pointer to sockmap
  *     @key: key to lookup sock in map
  *     @flags: reserved for future use
- *     Return: SK_REDIRECT
+ *     Return: SK_PASS
  *
  * int bpf_sock_map_update(skops, map, key, flags)
  *	@skops: pointer to bpf_sock_ops
@@ -786,8 +786,8 @@
 };
 
 enum sk_action {
-	SK_ABORTED = 0,
-	SK_DROP,
+	SK_DROP = 0,
+	SK_PASS,
 	SK_REDIRECT,
 };
 
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 412c06a..ccaea52 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -269,9 +269,9 @@
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	36
+#define DM_VERSION_MINOR	37
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2017-06-09)"
+#define DM_VERSION_EXTRA	"-ioctl (2017-09-20)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 9c041da..5bd1b1d 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1753,6 +1753,8 @@
  *	%ethtool_link_mode_bit_indices for the link modes, and other
  *	link features that the link partner advertised through
  *	autonegotiation; 0 if unknown or not applicable.  Read-only.
+ * @transceiver: Used to distinguish different possible PHY types,
+ *	reported consistently by PHYLIB.  Read-only.
  *
  * If autonegotiation is disabled, the speed and @duplex represent the
  * fixed link mode and are writable if the driver supports multiple
@@ -1804,7 +1806,9 @@
 	__u8	eth_tp_mdix;
 	__u8	eth_tp_mdix_ctrl;
 	__s8	link_mode_masks_nwords;
-	__u32	reserved[8];
+	__u8	transceiver;
+	__u8	reserved1[3];
+	__u32	reserved[7];
 	__u32	link_mode_masks[0];
 	/* layout of link_mode_masks fields:
 	 * __u32 map_supported[link_mode_masks_nwords];
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 7b4567b..26283fe 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -23,15 +23,15 @@
 #ifndef KFD_IOCTL_H_INCLUDED
 #define KFD_IOCTL_H_INCLUDED
 
-#include <linux/types.h>
+#include <drm/drm.h>
 #include <linux/ioctl.h>
 
 #define KFD_IOCTL_MAJOR_VERSION 1
 #define KFD_IOCTL_MINOR_VERSION 1
 
 struct kfd_ioctl_get_version_args {
-	uint32_t major_version;	/* from KFD */
-	uint32_t minor_version;	/* from KFD */
+	__u32 major_version;	/* from KFD */
+	__u32 minor_version;	/* from KFD */
 };
 
 /* For kfd_ioctl_create_queue_args.queue_type. */
@@ -43,36 +43,36 @@
 #define KFD_MAX_QUEUE_PRIORITY		15
 
 struct kfd_ioctl_create_queue_args {
-	uint64_t ring_base_address;	/* to KFD */
-	uint64_t write_pointer_address;	/* from KFD */
-	uint64_t read_pointer_address;	/* from KFD */
-	uint64_t doorbell_offset;	/* from KFD */
+	__u64 ring_base_address;	/* to KFD */
+	__u64 write_pointer_address;	/* from KFD */
+	__u64 read_pointer_address;	/* from KFD */
+	__u64 doorbell_offset;	/* from KFD */
 
-	uint32_t ring_size;		/* to KFD */
-	uint32_t gpu_id;		/* to KFD */
-	uint32_t queue_type;		/* to KFD */
-	uint32_t queue_percentage;	/* to KFD */
-	uint32_t queue_priority;	/* to KFD */
-	uint32_t queue_id;		/* from KFD */
+	__u32 ring_size;		/* to KFD */
+	__u32 gpu_id;		/* to KFD */
+	__u32 queue_type;		/* to KFD */
+	__u32 queue_percentage;	/* to KFD */
+	__u32 queue_priority;	/* to KFD */
+	__u32 queue_id;		/* from KFD */
 
-	uint64_t eop_buffer_address;	/* to KFD */
-	uint64_t eop_buffer_size;	/* to KFD */
-	uint64_t ctx_save_restore_address; /* to KFD */
-	uint64_t ctx_save_restore_size;	/* to KFD */
+	__u64 eop_buffer_address;	/* to KFD */
+	__u64 eop_buffer_size;	/* to KFD */
+	__u64 ctx_save_restore_address; /* to KFD */
+	__u64 ctx_save_restore_size;	/* to KFD */
 };
 
 struct kfd_ioctl_destroy_queue_args {
-	uint32_t queue_id;		/* to KFD */
-	uint32_t pad;
+	__u32 queue_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_update_queue_args {
-	uint64_t ring_base_address;	/* to KFD */
+	__u64 ring_base_address;	/* to KFD */
 
-	uint32_t queue_id;		/* to KFD */
-	uint32_t ring_size;		/* to KFD */
-	uint32_t queue_percentage;	/* to KFD */
-	uint32_t queue_priority;	/* to KFD */
+	__u32 queue_id;		/* to KFD */
+	__u32 ring_size;		/* to KFD */
+	__u32 queue_percentage;	/* to KFD */
+	__u32 queue_priority;	/* to KFD */
 };
 
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
@@ -80,13 +80,13 @@
 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
 
 struct kfd_ioctl_set_memory_policy_args {
-	uint64_t alternate_aperture_base;	/* to KFD */
-	uint64_t alternate_aperture_size;	/* to KFD */
+	__u64 alternate_aperture_base;	/* to KFD */
+	__u64 alternate_aperture_size;	/* to KFD */
 
-	uint32_t gpu_id;			/* to KFD */
-	uint32_t default_policy;		/* to KFD */
-	uint32_t alternate_policy;		/* to KFD */
-	uint32_t pad;
+	__u32 gpu_id;			/* to KFD */
+	__u32 default_policy;		/* to KFD */
+	__u32 alternate_policy;		/* to KFD */
+	__u32 pad;
 };
 
 /*
@@ -97,26 +97,26 @@
  */
 
 struct kfd_ioctl_get_clock_counters_args {
-	uint64_t gpu_clock_counter;	/* from KFD */
-	uint64_t cpu_clock_counter;	/* from KFD */
-	uint64_t system_clock_counter;	/* from KFD */
-	uint64_t system_clock_freq;	/* from KFD */
+	__u64 gpu_clock_counter;	/* from KFD */
+	__u64 cpu_clock_counter;	/* from KFD */
+	__u64 system_clock_counter;	/* from KFD */
+	__u64 system_clock_freq;	/* from KFD */
 
-	uint32_t gpu_id;		/* to KFD */
-	uint32_t pad;
+	__u32 gpu_id;		/* to KFD */
+	__u32 pad;
 };
 
 #define NUM_OF_SUPPORTED_GPUS 7
 
 struct kfd_process_device_apertures {
-	uint64_t lds_base;		/* from KFD */
-	uint64_t lds_limit;		/* from KFD */
-	uint64_t scratch_base;		/* from KFD */
-	uint64_t scratch_limit;		/* from KFD */
-	uint64_t gpuvm_base;		/* from KFD */
-	uint64_t gpuvm_limit;		/* from KFD */
-	uint32_t gpu_id;		/* from KFD */
-	uint32_t pad;
+	__u64 lds_base;		/* from KFD */
+	__u64 lds_limit;		/* from KFD */
+	__u64 scratch_base;		/* from KFD */
+	__u64 scratch_limit;		/* from KFD */
+	__u64 gpuvm_base;		/* from KFD */
+	__u64 gpuvm_limit;		/* from KFD */
+	__u32 gpu_id;		/* from KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_get_process_apertures_args {
@@ -124,8 +124,8 @@
 			process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */
 
 	/* from KFD, should be in the range [1 - NUM_OF_SUPPORTED_GPUS] */
-	uint32_t num_of_nodes;
-	uint32_t pad;
+	__u32 num_of_nodes;
+	__u32 pad;
 };
 
 #define MAX_ALLOWED_NUM_POINTS    100
@@ -133,25 +133,25 @@
 #define MAX_ALLOWED_WAC_BUFF_SIZE  128
 
 struct kfd_ioctl_dbg_register_args {
-	uint32_t gpu_id;		/* to KFD */
-	uint32_t pad;
+	__u32 gpu_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_dbg_unregister_args {
-	uint32_t gpu_id;		/* to KFD */
-	uint32_t pad;
+	__u32 gpu_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_dbg_address_watch_args {
-	uint64_t content_ptr;		/* a pointer to the actual content */
-	uint32_t gpu_id;		/* to KFD */
-	uint32_t buf_size_in_bytes;	/*including gpu_id and buf_size */
+	__u64 content_ptr;		/* a pointer to the actual content */
+	__u32 gpu_id;		/* to KFD */
+	__u32 buf_size_in_bytes;	/*including gpu_id and buf_size */
 };
 
 struct kfd_ioctl_dbg_wave_control_args {
-	uint64_t content_ptr;		/* a pointer to the actual content */
-	uint32_t gpu_id;		/* to KFD */
-	uint32_t buf_size_in_bytes;	/*including gpu_id and buf_size */
+	__u64 content_ptr;		/* a pointer to the actual content */
+	__u32 gpu_id;		/* to KFD */
+	__u32 buf_size_in_bytes;	/*including gpu_id and buf_size */
 };
 
 /* Matching HSA_EVENTTYPE */
@@ -172,44 +172,44 @@
 #define KFD_SIGNAL_EVENT_LIMIT			256
 
 struct kfd_ioctl_create_event_args {
-	uint64_t event_page_offset;	/* from KFD */
-	uint32_t event_trigger_data;	/* from KFD - signal events only */
-	uint32_t event_type;		/* to KFD */
-	uint32_t auto_reset;		/* to KFD */
-	uint32_t node_id;		/* to KFD - only valid for certain
+	__u64 event_page_offset;	/* from KFD */
+	__u32 event_trigger_data;	/* from KFD - signal events only */
+	__u32 event_type;		/* to KFD */
+	__u32 auto_reset;		/* to KFD */
+	__u32 node_id;		/* to KFD - only valid for certain
 							event types */
-	uint32_t event_id;		/* from KFD */
-	uint32_t event_slot_index;	/* from KFD */
+	__u32 event_id;		/* from KFD */
+	__u32 event_slot_index;	/* from KFD */
 };
 
 struct kfd_ioctl_destroy_event_args {
-	uint32_t event_id;		/* to KFD */
-	uint32_t pad;
+	__u32 event_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_set_event_args {
-	uint32_t event_id;		/* to KFD */
-	uint32_t pad;
+	__u32 event_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_reset_event_args {
-	uint32_t event_id;		/* to KFD */
-	uint32_t pad;
+	__u32 event_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_memory_exception_failure {
-	uint32_t NotPresent;	/* Page not present or supervisor privilege */
-	uint32_t ReadOnly;	/* Write access to a read-only page */
-	uint32_t NoExecute;	/* Execute access to a page marked NX */
-	uint32_t pad;
+	__u32 NotPresent;	/* Page not present or supervisor privilege */
+	__u32 ReadOnly;	/* Write access to a read-only page */
+	__u32 NoExecute;	/* Execute access to a page marked NX */
+	__u32 pad;
 };
 
 /* memory exception data*/
 struct kfd_hsa_memory_exception_data {
 	struct kfd_memory_exception_failure failure;
-	uint64_t va;
-	uint32_t gpu_id;
-	uint32_t pad;
+	__u64 va;
+	__u32 gpu_id;
+	__u32 pad;
 };
 
 /* Event data*/
@@ -217,19 +217,19 @@
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
 	};				/* From KFD */
-	uint64_t kfd_event_data_ext;	/* pointer to an extension structure
+	__u64 kfd_event_data_ext;	/* pointer to an extension structure
 					   for future exception types */
-	uint32_t event_id;		/* to KFD */
-	uint32_t pad;
+	__u32 event_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_wait_events_args {
-	uint64_t events_ptr;		/* pointed to struct
+	__u64 events_ptr;		/* pointed to struct
 					   kfd_event_data array, to KFD */
-	uint32_t num_events;		/* to KFD */
-	uint32_t wait_for_all;		/* to KFD */
-	uint32_t timeout;		/* to KFD */
-	uint32_t wait_result;		/* from KFD */
+	__u32 num_events;		/* to KFD */
+	__u32 wait_for_all;		/* to KFD */
+	__u32 timeout;		/* to KFD */
+	__u32 wait_result;		/* from KFD */
 };
 
 struct kfd_ioctl_set_scratch_backing_va_args {
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 6d47b32..4e01ad7 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -52,21 +52,30 @@
  *                          (non-running threads are de facto in such a
  *                          state). This only covers threads from the
  *                          same processes as the caller thread. This
- *                          command returns 0. The "expedited" commands
- *                          complete faster than the non-expedited ones,
- *                          they never block, but have the downside of
- *                          causing extra overhead.
+ *                          command returns 0 on success. The
+ *                          "expedited" commands complete faster than
+ *                          the non-expedited ones, they never block,
+ *                          but have the downside of causing extra
+ *                          overhead. A process needs to register its
+ *                          intent to use the private expedited command
+ *                          prior to using it, otherwise this command
+ *                          returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+ *                          Register the process intent to use
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always
+ *                          returns 0.
  *
  * Command to be passed to the membarrier system call. The commands need to
  * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
  * the value 0.
  */
 enum membarrier_cmd {
-	MEMBARRIER_CMD_QUERY			= 0,
-	MEMBARRIER_CMD_SHARED			= (1 << 0),
+	MEMBARRIER_CMD_QUERY				= 0,
+	MEMBARRIER_CMD_SHARED				= (1 << 0),
 	/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
 	/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
-	MEMBARRIER_CMD_PRIVATE_EXPEDITED	= (1 << 3),
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED		= (1 << 3),
+	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED	= (1 << 4),
 };
 
 #endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h
index b97725a..da161b5 100644
--- a/include/uapi/linux/netfilter/xt_bpf.h
+++ b/include/uapi/linux/netfilter/xt_bpf.h
@@ -23,6 +23,7 @@
 	XT_BPF_MODE_FD_PINNED,
 	XT_BPF_MODE_FD_ELF,
 };
+#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED
 
 struct xt_bpf_info_v1 {
 	__u16 mode;
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 6217ff8..84fc291 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -376,7 +376,7 @@
 	__u16 sre_type;
 	__u16 sre_flags;
 	__u32 sre_length;
-	__u16 sre_error;
+	__be16 sre_error;
 	sctp_assoc_t sre_assoc_id;
 	__u8 sre_data[0];
 };
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 0f238a4..f6bc1de 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -11,27 +11,34 @@
 #define SECCOMP_MODE_FILTER	2 /* uses user-supplied filter. */
 
 /* Valid operations for seccomp syscall. */
-#define SECCOMP_SET_MODE_STRICT	0
-#define SECCOMP_SET_MODE_FILTER	1
+#define SECCOMP_SET_MODE_STRICT		0
+#define SECCOMP_SET_MODE_FILTER		1
+#define SECCOMP_GET_ACTION_AVAIL	2
 
 /* Valid flags for SECCOMP_SET_MODE_FILTER */
 #define SECCOMP_FILTER_FLAG_TSYNC	1
+#define SECCOMP_FILTER_FLAG_LOG		2
 
 /*
  * All BPF programs must return a 32-bit value.
  * The bottom 16-bits are for optional return data.
- * The upper 16-bits are ordered from least permissive values to most.
+ * The upper 16-bits are ordered from least permissive values to most,
+ * as a signed value (so 0x8000000 is negative).
  *
  * The ordering ensures that a min_t() over composed return values always
  * selects the least permissive choice.
  */
-#define SECCOMP_RET_KILL	0x00000000U /* kill the task immediately */
-#define SECCOMP_RET_TRAP	0x00030000U /* disallow and force a SIGSYS */
-#define SECCOMP_RET_ERRNO	0x00050000U /* returns an errno */
-#define SECCOMP_RET_TRACE	0x7ff00000U /* pass to a tracer or disallow */
-#define SECCOMP_RET_ALLOW	0x7fff0000U /* allow */
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD	 0x00000000U /* kill the thread */
+#define SECCOMP_RET_KILL	 SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP	 0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO	 0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE	 0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_LOG		 0x7ffc0000U /* allow after logging */
+#define SECCOMP_RET_ALLOW	 0x7fff0000U /* allow */
 
 /* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION_FULL	0xffff0000U
 #define SECCOMP_RET_ACTION	0x7fff0000U
 #define SECCOMP_RET_DATA	0x0000ffffU
 
diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h
index dd5f21e..856de39 100644
--- a/include/uapi/linux/spi/spidev.h
+++ b/include/uapi/linux/spi/spidev.h
@@ -23,6 +23,7 @@
 #define SPIDEV_H
 
 #include <linux/types.h>
+#include <linux/ioctl.h>
 
 /* User space versions of kernel symbols for SPI clocking modes,
  * matching <linux/spi/spi.h>
diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index ce1169a..2a5d630 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -780,6 +780,7 @@
 	__u8  iFunction;
 } __attribute__ ((packed));
 
+#define USB_DT_INTERFACE_ASSOCIATION_SIZE	8
 
 /*-------------------------------------------------------------------------*/
 
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 9a0b647..d4e0b53 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -261,7 +261,7 @@
 	struct ib_uverbs_rss_caps rss_caps;
 	__u32  max_wq_type_rq;
 	__u32 raw_packet_caps;
-	struct ib_uverbs_tm_caps xrq_caps;
+	struct ib_uverbs_tm_caps tm_caps;
 };
 
 struct ib_uverbs_query_port {
diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h
index 415dbc6..6adc2a9 100644
--- a/include/xen/arm/page.h
+++ b/include/xen/arm/page.h
@@ -84,16 +84,6 @@
 	BUG();
 }
 
-/* TODO: this shouldn't be here but it is because the frontend drivers
- * are using it (its rolled in headers) even though we won't hit the code path.
- * So for right now just punt with this.
- */
-static inline pte_t *lookup_address(unsigned long address, unsigned int *level)
-{
-	BUG();
-	return NULL;
-}
-
 extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 				   struct gnttab_map_grant_ref *kmap_ops,
 				   struct page **pages, unsigned int count);
diff --git a/init/Kconfig b/init/Kconfig
index 78cb246..3c1faaa 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1033,7 +1033,7 @@
 
 choice
 	prompt "Compiler optimization level"
-	default CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
+	default CC_OPTIMIZE_FOR_PERFORMANCE
 
 config CC_OPTIMIZE_FOR_PERFORMANCE
 	bool "Optimize for performance"
diff --git a/ipc/shm.c b/ipc/shm.c
index 1b3adfe..badac46 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1154,7 +1154,7 @@
 	info.shm_swp = ip->shm_swp;
 	info.swap_attempts = ip->swap_attempts;
 	info.swap_successes = ip->swap_successes;
-	return copy_to_user(up, &info, sizeof(info));
+	return copy_to_user(uip, &info, sizeof(info));
 }
 
 static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in,
@@ -1237,7 +1237,7 @@
 		err = shmctl_stat(ns, shmid, cmd, &sem64);
 		if (err < 0)
 			return err;
-		if (copy_compat_shmid_to_user(&sem64, uptr, version))
+		if (copy_compat_shmid_to_user(uptr, &sem64, version))
 			err = -EFAULT;
 		return err;
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 98c0f00..e263673 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -98,7 +98,7 @@
 	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
 
 	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
+	    bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 917cc04..7b62df8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1022,7 +1022,7 @@
 		struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
 		struct bpf_array *array = container_of(map, struct bpf_array, map);
 		struct bpf_prog *prog;
-		u64 index = BPF_R3;
+		u32 index = BPF_R3;
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 959c9a0..e745d6a 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -69,14 +69,17 @@
 
 static u64 dev_map_bitmap_size(const union bpf_attr *attr)
 {
-	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
 }
 
 static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_dtab *dtab;
+	int err = -EINVAL;
 	u64 cost;
-	int err;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -108,9 +111,12 @@
 	if (err)
 		goto free_dtab;
 
+	err = -ENOMEM;
+
 	/* A per cpu bitfield with a bit per possible net device */
-	dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr),
-					    __alignof__(unsigned long));
+	dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr),
+						__alignof__(unsigned long),
+						GFP_KERNEL | __GFP_NOWARN);
 	if (!dtab->flush_needed)
 		goto free_dtab;
 
@@ -128,7 +134,7 @@
 free_dtab:
 	free_percpu(dtab->flush_needed);
 	kfree(dtab);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(err);
 }
 
 static void dev_map_free(struct bpf_map *map)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 431126f..6533f08 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -317,10 +317,6 @@
 		 */
 		goto free_htab;
 
-	if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE)
-		/* make sure the size for pcpu_alloc() is reasonable */
-		goto free_htab;
-
 	htab->elem_size = sizeof(struct htab_elem) +
 			  round_up(htab->map.key_size, 8);
 	if (percpu)
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index e833ed9..be1dde9 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -363,6 +363,7 @@
 	putname(pname);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(bpf_obj_get_user);
 
 static void bpf_evict_inode(struct inode *inode)
 {
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 6424ce0..66f00a2 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -39,6 +39,7 @@
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <net/strparser.h>
+#include <net/tcp.h>
 
 struct bpf_stab {
 	struct bpf_map map;
@@ -92,6 +93,14 @@
 	return rcu_dereference_sk_user_data(sk);
 }
 
+/* compute the linear packet data range [data, data_end) for skb when
+ * sk_skb type programs are in use.
+ */
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
+
 static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 {
 	struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
@@ -101,12 +110,20 @@
 		return SK_DROP;
 
 	skb_orphan(skb);
+	/* We need to ensure that BPF metadata for maps is also cleared
+	 * when we orphan the skb so that we don't have the possibility
+	 * to reference a stale map.
+	 */
+	TCP_SKB_CB(skb)->bpf.map = NULL;
 	skb->sk = psock->sock;
-	bpf_compute_data_end(skb);
+	bpf_compute_data_end_sk_skb(skb);
+	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
+	preempt_enable();
 	skb->sk = NULL;
 
-	return rc;
+	return rc == SK_PASS ?
+		(TCP_SKB_CB(skb)->bpf.map ? SK_REDIRECT : SK_PASS) : SK_DROP;
 }
 
 static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
@@ -114,17 +131,10 @@
 	struct sock *sk;
 	int rc;
 
-	/* Because we use per cpu values to feed input from sock redirect
-	 * in BPF program to do_sk_redirect_map() call we need to ensure we
-	 * are not preempted. RCU read lock is not sufficient in this case
-	 * with CONFIG_PREEMPT_RCU enabled so we must be explicit here.
-	 */
-	preempt_disable();
 	rc = smap_verdict_func(psock, skb);
 	switch (rc) {
 	case SK_REDIRECT:
-		sk = do_sk_redirect_map();
-		preempt_enable();
+		sk = do_sk_redirect_map(skb);
 		if (likely(sk)) {
 			struct smap_psock *peer = smap_psock_sk(sk);
 
@@ -141,8 +151,6 @@
 	/* Fall through and free skb otherwise */
 	case SK_DROP:
 	default:
-		if (rc != SK_REDIRECT)
-			preempt_enable();
 		kfree_skb(skb);
 	}
 }
@@ -369,7 +377,7 @@
 	 * any socket yet.
 	 */
 	skb->sk = psock->sock;
-	bpf_compute_data_end(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	skb->sk = NULL;
 	rcu_read_unlock();
@@ -487,6 +495,9 @@
 	int err = -EINVAL;
 	u64 cost;
 
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
@@ -840,6 +851,12 @@
 		return -EINVAL;
 	}
 
+	if (skops.sk->sk_type != SOCK_STREAM ||
+	    skops.sk->sk_protocol != IPPROTO_TCP) {
+		fput(socket->file);
+		return -EOPNOTSUPP;
+	}
+
 	err = sock_map_ctx_update_elem(&skops, map, key, flags);
 	fput(socket->file);
 	return err;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cb17e1c..25d0749 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -186,15 +186,17 @@
 
 static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
 {
+	unsigned long flags;
+
 	if (do_idr_lock)
-		spin_lock_bh(&map_idr_lock);
+		spin_lock_irqsave(&map_idr_lock, flags);
 	else
 		__acquire(&map_idr_lock);
 
 	idr_remove(&map_idr, map->id);
 
 	if (do_idr_lock)
-		spin_unlock_bh(&map_idr_lock);
+		spin_unlock_irqrestore(&map_idr_lock, flags);
 	else
 		__release(&map_idr_lock);
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 799b245..c48ca2a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -653,6 +653,10 @@
 {
 	struct bpf_verifier_state *parent = state->parent;
 
+	if (regno == BPF_REG_FP)
+		/* We don't need to worry about FP liveness because it's read-only */
+		return;
+
 	while (parent) {
 		/* if read wasn't screened by an earlier write ... */
 		if (state->regs[regno].live & REG_LIVE_WRITTEN)
@@ -1112,7 +1116,12 @@
 		/* ctx accesses must be at a fixed offset, so that we can
 		 * determine what type of data were returned.
 		 */
-		if (!tnum_is_const(reg->var_off)) {
+		if (reg->off) {
+			verbose("dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
+				regno, reg->off, off - reg->off);
+			return -EACCES;
+		}
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
@@ -1120,7 +1129,6 @@
 				tn_buf, off, size);
 			return -EACCES;
 		}
-		off += reg->var_off.value;
 		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			/* ctx access returns either a scalar, or a
@@ -2345,6 +2353,7 @@
 				 * copy register state to dest reg
 				 */
 				regs[insn->dst_reg] = regs[insn->src_reg];
+				regs[insn->dst_reg].live |= REG_LIVE_WRITTEN;
 			} else {
 				/* R1 = (u32) R2 */
 				if (is_pointer_value(env, insn->src_reg)) {
@@ -2421,12 +2430,15 @@
 }
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *state,
-				   struct bpf_reg_state *dst_reg)
+				   struct bpf_reg_state *dst_reg,
+				   bool range_right_open)
 {
 	struct bpf_reg_state *regs = state->regs, *reg;
+	u16 new_range;
 	int i;
 
-	if (dst_reg->off < 0)
+	if (dst_reg->off < 0 ||
+	    (dst_reg->off == 0 && range_right_open))
 		/* This doesn't give us any range */
 		return;
 
@@ -2437,9 +2449,13 @@
 		 */
 		return;
 
-	/* LLVM can generate four kind of checks:
+	new_range = dst_reg->off;
+	if (range_right_open)
+		new_range--;
+
+	/* Examples for register markings:
 	 *
-	 * Type 1/2:
+	 * pkt_data in dst register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2456,7 +2472,7 @@
 	 *     r2=pkt(id=n,off=8,r=0)
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
-	 * Type 3/4:
+	 * pkt_data in src register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2474,7 +2490,9 @@
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
 	 * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
-	 * so that range of bytes [r3, r3 + 8) is safe to access.
+	 * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
+	 * and [r3, r3 + 8-1) respectively is safe to access depending on
+	 * the check.
 	 */
 
 	/* If our ids match, then we must have the same max_value.  And we
@@ -2485,14 +2503,14 @@
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
 			/* keep the maximum range already checked */
-			regs[i].range = max_t(u16, regs[i].range, dst_reg->off);
+			regs[i].range = max(regs[i].range, new_range);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = max_t(u16, reg->range, dst_reg->off);
+			reg->range = max(reg->range, new_range);
 	}
 }
 
@@ -2856,19 +2874,43 @@
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(this_branch, dst_reg);
+		/* pkt_data' > pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end > pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(other_branch, dst_reg);
+		/* pkt_data' < pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, true);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end < pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' >= pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(other_branch, &regs[insn->src_reg]);
+		/* pkt_end >= pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' <= pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, false);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(this_branch, &regs[insn->src_reg]);
+		/* pkt_end <= pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], true);
 	} else if (is_pointer_value(env, insn->dst_reg)) {
 		verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
 		return -EACCES;
@@ -4205,7 +4247,12 @@
 		}
 
 		if (insn->imm == BPF_FUNC_redirect_map) {
-			u64 addr = (unsigned long)prog;
+			/* Note, we cannot use prog directly as imm as subsequent
+			 * rewrites would still change the prog pointer. The only
+			 * stable address we can use is aux, which also works with
+			 * prog clones during blinding.
+			 */
+			u64 addr = (unsigned long)prog->aux;
 			struct bpf_insn r4_ld[] = {
 				BPF_LD_IMM64(BPF_REG_4, addr),
 				*insn,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index d6551cd..4485727 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2311,6 +2311,14 @@
 		list_del_init(&cset->mg_node);
 	}
 	spin_unlock_irq(&css_set_lock);
+
+	/*
+	 * Re-initialize the cgroup_taskset structure in case it is reused
+	 * again in another cgroup_migrate_add_task()/cgroup_migrate_execute()
+	 * iteration.
+	 */
+	tset->nr_tasks = 0;
+	tset->csets    = &tset->src_csets;
 	return ret;
 }
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index acf5308..04892a8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -24,6 +24,7 @@
 #include <linux/lockdep.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/nmi.h>
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
@@ -46,11 +47,13 @@
  * @bringup:	Single callback bringup or teardown selector
  * @cb_state:	The state for a single callback (install/uninstall)
  * @result:	Result of the operation
- * @done:	Signal completion to the issuer of the task
+ * @done_up:	Signal completion to the issuer of the task for cpu-up
+ * @done_down:	Signal completion to the issuer of the task for cpu-down
  */
 struct cpuhp_cpu_state {
 	enum cpuhp_state	state;
 	enum cpuhp_state	target;
+	enum cpuhp_state	fail;
 #ifdef CONFIG_SMP
 	struct task_struct	*thread;
 	bool			should_run;
@@ -58,18 +61,39 @@
 	bool			single;
 	bool			bringup;
 	struct hlist_node	*node;
+	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
 	int			result;
-	struct completion	done;
+	struct completion	done_up;
+	struct completion	done_down;
 #endif
 };
 
-static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
+static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
+	.fail = CPUHP_INVALID,
+};
 
 #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
-static struct lock_class_key cpuhp_state_key;
-static struct lockdep_map cpuhp_state_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key);
+static struct lockdep_map cpuhp_state_up_map =
+	STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map);
+static struct lockdep_map cpuhp_state_down_map =
+	STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);
+
+
+static void inline cpuhp_lock_acquire(bool bringup)
+{
+	lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
+}
+
+static void inline cpuhp_lock_release(bool bringup)
+{
+	lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
+}
+#else
+
+static void inline cpuhp_lock_acquire(bool bringup) { }
+static void inline cpuhp_lock_release(bool bringup) { }
+
 #endif
 
 /**
@@ -123,13 +147,16 @@
 /**
  * cpuhp_invoke_callback _ Invoke the callbacks for a given state
  * @cpu:	The cpu for which the callback should be invoked
- * @step:	The step in the state machine
+ * @state:	The state to do callbacks for
  * @bringup:	True if the bringup callback should be invoked
+ * @node:	For multi-instance, do a single entry callback for install/remove
+ * @lastp:	For multi-instance rollback, remember how far we got
  *
  * Called from cpu hotplug and from the state register machinery.
  */
 static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
-				 bool bringup, struct hlist_node *node)
+				 bool bringup, struct hlist_node *node,
+				 struct hlist_node **lastp)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	struct cpuhp_step *step = cpuhp_get_step(state);
@@ -137,7 +164,17 @@
 	int (*cb)(unsigned int cpu);
 	int ret, cnt;
 
+	if (st->fail == state) {
+		st->fail = CPUHP_INVALID;
+
+		if (!(bringup ? step->startup.single : step->teardown.single))
+			return 0;
+
+		return -EAGAIN;
+	}
+
 	if (!step->multi_instance) {
+		WARN_ON_ONCE(lastp && *lastp);
 		cb = bringup ? step->startup.single : step->teardown.single;
 		if (!cb)
 			return 0;
@@ -152,6 +189,7 @@
 
 	/* Single invocation for instance add/remove */
 	if (node) {
+		WARN_ON_ONCE(lastp && *lastp);
 		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
 		ret = cbm(cpu, node);
 		trace_cpuhp_exit(cpu, st->state, state, ret);
@@ -161,13 +199,23 @@
 	/* State transition. Invoke on all instances */
 	cnt = 0;
 	hlist_for_each(node, &step->list) {
+		if (lastp && node == *lastp)
+			break;
+
 		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
 		ret = cbm(cpu, node);
 		trace_cpuhp_exit(cpu, st->state, state, ret);
-		if (ret)
-			goto err;
+		if (ret) {
+			if (!lastp)
+				goto err;
+
+			*lastp = node;
+			return ret;
+		}
 		cnt++;
 	}
+	if (lastp)
+		*lastp = NULL;
 	return 0;
 err:
 	/* Rollback the instances if one failed */
@@ -178,12 +226,39 @@
 	hlist_for_each(node, &step->list) {
 		if (!cnt--)
 			break;
-		cbm(cpu, node);
+
+		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
+		ret = cbm(cpu, node);
+		trace_cpuhp_exit(cpu, st->state, state, ret);
+		/*
+		 * Rollback must not fail,
+		 */
+		WARN_ON_ONCE(ret);
 	}
 	return ret;
 }
 
 #ifdef CONFIG_SMP
+static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
+{
+	struct completion *done = bringup ? &st->done_up : &st->done_down;
+	wait_for_completion(done);
+}
+
+static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
+{
+	struct completion *done = bringup ? &st->done_up : &st->done_down;
+	complete(done);
+}
+
+/*
+ * The former STARTING/DYING states, ran with IRQs disabled and must not fail.
+ */
+static bool cpuhp_is_atomic_state(enum cpuhp_state state)
+{
+	return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE;
+}
+
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
 static DEFINE_MUTEX(cpu_add_remove_lock);
 bool cpuhp_tasks_frozen;
@@ -271,14 +346,79 @@
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st);
+static inline enum cpuhp_state
+cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
+{
+	enum cpuhp_state prev_state = st->state;
+
+	st->rollback = false;
+	st->last = NULL;
+
+	st->target = target;
+	st->single = false;
+	st->bringup = st->state < target;
+
+	return prev_state;
+}
+
+static inline void
+cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
+{
+	st->rollback = true;
+
+	/*
+	 * If we have st->last we need to undo partial multi_instance of this
+	 * state first. Otherwise start undo at the previous state.
+	 */
+	if (!st->last) {
+		if (st->bringup)
+			st->state--;
+		else
+			st->state++;
+	}
+
+	st->target = prev_state;
+	st->bringup = !st->bringup;
+}
+
+/* Regular hotplug invocation of the AP hotplug thread */
+static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st)
+{
+	if (!st->single && st->state == st->target)
+		return;
+
+	st->result = 0;
+	/*
+	 * Make sure the above stores are visible before should_run becomes
+	 * true. Paired with the mb() above in cpuhp_thread_fun()
+	 */
+	smp_mb();
+	st->should_run = true;
+	wake_up_process(st->thread);
+	wait_for_ap_thread(st, st->bringup);
+}
+
+static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target)
+{
+	enum cpuhp_state prev_state;
+	int ret;
+
+	prev_state = cpuhp_set_state(st, target);
+	__cpuhp_kick_ap(st);
+	if ((ret = st->result)) {
+		cpuhp_reset_state(st, prev_state);
+		__cpuhp_kick_ap(st);
+	}
+
+	return ret;
+}
 
 static int bringup_wait_for_ap(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 
 	/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
-	wait_for_completion(&st->done);
+	wait_for_ap_thread(st, true);
 	if (WARN_ON_ONCE((!cpu_online(cpu))))
 		return -ECANCELED;
 
@@ -286,12 +426,10 @@
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
 
-	/* Should we go further up ? */
-	if (st->target > CPUHP_AP_ONLINE_IDLE) {
-		__cpuhp_kick_ap_work(st);
-		wait_for_completion(&st->done);
-	}
-	return st->result;
+	if (st->target <= CPUHP_AP_ONLINE_IDLE)
+		return 0;
+
+	return cpuhp_kick_ap(st, st->target);
 }
 
 static int bringup_cpu(unsigned int cpu)
@@ -317,32 +455,6 @@
 /*
  * Hotplug state machine related functions
  */
-static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
-{
-	for (st->state++; st->state < st->target; st->state++) {
-		struct cpuhp_step *step = cpuhp_get_step(st->state);
-
-		if (!step->skip_onerr)
-			cpuhp_invoke_callback(cpu, st->state, true, NULL);
-	}
-}
-
-static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
-				enum cpuhp_state target)
-{
-	enum cpuhp_state prev_state = st->state;
-	int ret = 0;
-
-	for (; st->state > target; st->state--) {
-		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL);
-		if (ret) {
-			st->target = prev_state;
-			undo_cpu_down(cpu, st);
-			break;
-		}
-	}
-	return ret;
-}
 
 static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
 {
@@ -350,7 +462,7 @@
 		struct cpuhp_step *step = cpuhp_get_step(st->state);
 
 		if (!step->skip_onerr)
-			cpuhp_invoke_callback(cpu, st->state, false, NULL);
+			cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
 	}
 }
 
@@ -362,7 +474,7 @@
 
 	while (st->state < target) {
 		st->state++;
-		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL);
+		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
 		if (ret) {
 			st->target = prev_state;
 			undo_cpu_up(cpu, st);
@@ -379,7 +491,8 @@
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 
-	init_completion(&st->done);
+	init_completion(&st->done_up);
+	init_completion(&st->done_down);
 }
 
 static int cpuhp_should_run(unsigned int cpu)
@@ -389,69 +502,90 @@
 	return st->should_run;
 }
 
-/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */
-static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st)
-{
-	enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU);
-
-	return cpuhp_down_callbacks(cpu, st, target);
-}
-
-/* Execute the online startup callbacks. Used to be CPU_ONLINE */
-static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st)
-{
-	return cpuhp_up_callbacks(cpu, st, st->target);
-}
-
 /*
  * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
  * callbacks when a state gets [un]installed at runtime.
+ *
+ * Each invocation of this function by the smpboot thread does a single AP
+ * state callback.
+ *
+ * It has 3 modes of operation:
+ *  - single: runs st->cb_state
+ *  - up:     runs ++st->state, while st->state < st->target
+ *  - down:   runs st->state--, while st->state > st->target
+ *
+ * When complete or on error, should_run is cleared and the completion is fired.
  */
 static void cpuhp_thread_fun(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
-	int ret = 0;
+	bool bringup = st->bringup;
+	enum cpuhp_state state;
 
 	/*
-	 * Paired with the mb() in cpuhp_kick_ap_work and
-	 * cpuhp_invoke_ap_callback, so the work set is consistent visible.
+	 * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures
+	 * that if we see ->should_run we also see the rest of the state.
 	 */
 	smp_mb();
-	if (!st->should_run)
+
+	if (WARN_ON_ONCE(!st->should_run))
 		return;
 
-	st->should_run = false;
+	cpuhp_lock_acquire(bringup);
 
-	lock_map_acquire(&cpuhp_state_lock_map);
-	/* Single callback invocation for [un]install ? */
 	if (st->single) {
-		if (st->cb_state < CPUHP_AP_ONLINE) {
-			local_irq_disable();
-			ret = cpuhp_invoke_callback(cpu, st->cb_state,
-						    st->bringup, st->node);
-			local_irq_enable();
-		} else {
-			ret = cpuhp_invoke_callback(cpu, st->cb_state,
-						    st->bringup, st->node);
-		}
-	} else if (st->rollback) {
-		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
-
-		undo_cpu_down(cpu, st);
-		st->rollback = false;
+		state = st->cb_state;
+		st->should_run = false;
 	} else {
-		/* Cannot happen .... */
-		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
-
-		/* Regular hotplug work */
-		if (st->state < st->target)
-			ret = cpuhp_ap_online(cpu, st);
-		else if (st->state > st->target)
-			ret = cpuhp_ap_offline(cpu, st);
+		if (bringup) {
+			st->state++;
+			state = st->state;
+			st->should_run = (st->state < st->target);
+			WARN_ON_ONCE(st->state > st->target);
+		} else {
+			state = st->state;
+			st->state--;
+			st->should_run = (st->state > st->target);
+			WARN_ON_ONCE(st->state < st->target);
+		}
 	}
-	lock_map_release(&cpuhp_state_lock_map);
-	st->result = ret;
-	complete(&st->done);
+
+	WARN_ON_ONCE(!cpuhp_is_ap_state(state));
+
+	if (st->rollback) {
+		struct cpuhp_step *step = cpuhp_get_step(state);
+		if (step->skip_onerr)
+			goto next;
+	}
+
+	if (cpuhp_is_atomic_state(state)) {
+		local_irq_disable();
+		st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
+		local_irq_enable();
+
+		/*
+		 * STARTING/DYING must not fail!
+		 */
+		WARN_ON_ONCE(st->result);
+	} else {
+		st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
+	}
+
+	if (st->result) {
+		/*
+		 * If we fail on a rollback, we're up a creek without no
+		 * paddle, no way forward, no way back. We loose, thanks for
+		 * playing.
+		 */
+		WARN_ON_ONCE(st->rollback);
+		st->should_run = false;
+	}
+
+next:
+	cpuhp_lock_release(bringup);
+
+	if (!st->should_run)
+		complete_ap_thread(st, bringup);
 }
 
 /* Invoke a single callback on a remote cpu */
@@ -460,62 +594,69 @@
 			 struct hlist_node *node)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+	int ret;
 
 	if (!cpu_online(cpu))
 		return 0;
 
-	lock_map_acquire(&cpuhp_state_lock_map);
-	lock_map_release(&cpuhp_state_lock_map);
+	cpuhp_lock_acquire(false);
+	cpuhp_lock_release(false);
+
+	cpuhp_lock_acquire(true);
+	cpuhp_lock_release(true);
 
 	/*
 	 * If we are up and running, use the hotplug thread. For early calls
 	 * we invoke the thread function directly.
 	 */
 	if (!st->thread)
-		return cpuhp_invoke_callback(cpu, state, bringup, node);
+		return cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
 
+	st->rollback = false;
+	st->last = NULL;
+
+	st->node = node;
+	st->bringup = bringup;
 	st->cb_state = state;
 	st->single = true;
-	st->bringup = bringup;
-	st->node = node;
+
+	__cpuhp_kick_ap(st);
 
 	/*
-	 * Make sure the above stores are visible before should_run becomes
-	 * true. Paired with the mb() above in cpuhp_thread_fun()
+	 * If we failed and did a partial, do a rollback.
 	 */
-	smp_mb();
-	st->should_run = true;
-	wake_up_process(st->thread);
-	wait_for_completion(&st->done);
-	return st->result;
-}
+	if ((ret = st->result) && st->last) {
+		st->rollback = true;
+		st->bringup = !bringup;
 
-/* Regular hotplug invocation of the AP hotplug thread */
-static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st)
-{
-	st->result = 0;
-	st->single = false;
+		__cpuhp_kick_ap(st);
+	}
+
 	/*
-	 * Make sure the above stores are visible before should_run becomes
-	 * true. Paired with the mb() above in cpuhp_thread_fun()
+	 * Clean up the leftovers so the next hotplug operation wont use stale
+	 * data.
 	 */
-	smp_mb();
-	st->should_run = true;
-	wake_up_process(st->thread);
+	st->node = st->last = NULL;
+	return ret;
 }
 
 static int cpuhp_kick_ap_work(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
-	enum cpuhp_state state = st->state;
+	enum cpuhp_state prev_state = st->state;
+	int ret;
 
-	trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work);
-	lock_map_acquire(&cpuhp_state_lock_map);
-	lock_map_release(&cpuhp_state_lock_map);
-	__cpuhp_kick_ap_work(st);
-	wait_for_completion(&st->done);
-	trace_cpuhp_exit(cpu, st->state, state, st->result);
-	return st->result;
+	cpuhp_lock_acquire(false);
+	cpuhp_lock_release(false);
+
+	cpuhp_lock_acquire(true);
+	cpuhp_lock_release(true);
+
+	trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work);
+	ret = cpuhp_kick_ap(st, st->target);
+	trace_cpuhp_exit(cpu, st->state, prev_state, ret);
+
+	return ret;
 }
 
 static struct smp_hotplug_thread cpuhp_threads = {
@@ -581,6 +722,7 @@
 	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
 	enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
 	int err, cpu = smp_processor_id();
+	int ret;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
@@ -594,8 +736,13 @@
 	WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
 	st->state--;
 	/* Invoke the former CPU_DYING callbacks */
-	for (; st->state > target; st->state--)
-		cpuhp_invoke_callback(cpu, st->state, false, NULL);
+	for (; st->state > target; st->state--) {
+		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
+		/*
+		 * DYING must not fail!
+		 */
+		WARN_ON_ONCE(ret);
+	}
 
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
@@ -639,7 +786,7 @@
 	 *
 	 * Wait for the stop thread to go away.
 	 */
-	wait_for_completion(&st->done);
+	wait_for_ap_thread(st, false);
 	BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
 
 	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
@@ -658,7 +805,7 @@
 {
 	struct cpuhp_cpu_state *st = arg;
 
-	complete(&st->done);
+	complete_ap_thread(st, false);
 }
 
 void cpuhp_report_idle_dead(void)
@@ -676,11 +823,32 @@
 				 cpuhp_complete_idle_dead, st, 0);
 }
 
-#else
-#define takedown_cpu		NULL
-#endif
+static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
+{
+	for (st->state++; st->state < st->target; st->state++) {
+		struct cpuhp_step *step = cpuhp_get_step(st->state);
 
-#ifdef CONFIG_HOTPLUG_CPU
+		if (!step->skip_onerr)
+			cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
+	}
+}
+
+static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
+				enum cpuhp_state target)
+{
+	enum cpuhp_state prev_state = st->state;
+	int ret = 0;
+
+	for (; st->state > target; st->state--) {
+		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
+		if (ret) {
+			st->target = prev_state;
+			undo_cpu_down(cpu, st);
+			break;
+		}
+	}
+	return ret;
+}
 
 /* Requires cpu_add_remove_lock to be held */
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
@@ -699,13 +867,13 @@
 
 	cpuhp_tasks_frozen = tasks_frozen;
 
-	prev_state = st->state;
-	st->target = target;
+	prev_state = cpuhp_set_state(st, target);
 	/*
 	 * If the current CPU state is in the range of the AP hotplug thread,
 	 * then we need to kick the thread.
 	 */
 	if (st->state > CPUHP_TEARDOWN_CPU) {
+		st->target = max((int)target, CPUHP_TEARDOWN_CPU);
 		ret = cpuhp_kick_ap_work(cpu);
 		/*
 		 * The AP side has done the error rollback already. Just
@@ -720,6 +888,8 @@
 		 */
 		if (st->state > CPUHP_TEARDOWN_CPU)
 			goto out;
+
+		st->target = target;
 	}
 	/*
 	 * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
@@ -727,13 +897,17 @@
 	 */
 	ret = cpuhp_down_callbacks(cpu, st, target);
 	if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
-		st->target = prev_state;
-		st->rollback = true;
-		cpuhp_kick_ap_work(cpu);
+		cpuhp_reset_state(st, prev_state);
+		__cpuhp_kick_ap(st);
 	}
 
 out:
 	cpus_write_unlock();
+	/*
+	 * Do post unplug cleanup. This is still protected against
+	 * concurrent CPU hotplug via cpu_add_remove_lock.
+	 */
+	lockup_detector_cleanup();
 	return ret;
 }
 
@@ -754,11 +928,15 @@
 	cpu_maps_update_done();
 	return err;
 }
+
 int cpu_down(unsigned int cpu)
 {
 	return do_cpu_down(cpu, CPUHP_OFFLINE);
 }
 EXPORT_SYMBOL(cpu_down);
+
+#else
+#define takedown_cpu		NULL
 #endif /*CONFIG_HOTPLUG_CPU*/
 
 /**
@@ -772,11 +950,16 @@
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
+	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
 	while (st->state < target) {
 		st->state++;
-		cpuhp_invoke_callback(cpu, st->state, true, NULL);
+		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
+		/*
+		 * STARTING must not fail!
+		 */
+		WARN_ON_ONCE(ret);
 	}
 }
 
@@ -794,7 +977,7 @@
 		return;
 
 	st->state = CPUHP_AP_ONLINE_IDLE;
-	complete(&st->done);
+	complete_ap_thread(st, true);
 }
 
 /* Requires cpu_add_remove_lock to be held */
@@ -829,7 +1012,7 @@
 
 	cpuhp_tasks_frozen = tasks_frozen;
 
-	st->target = target;
+	cpuhp_set_state(st, target);
 	/*
 	 * If the current CPU state is in the range of the AP hotplug thread,
 	 * then we need to kick the thread once more.
@@ -1296,6 +1479,10 @@
 	struct cpuhp_step *sp = cpuhp_get_step(state);
 	int ret;
 
+	/*
+	 * If there's nothing to do, we done.
+	 * Relies on the union for multi_instance.
+	 */
 	if ((bringup && !sp->startup.single) ||
 	    (!bringup && !sp->teardown.single))
 		return 0;
@@ -1307,9 +1494,9 @@
 	if (cpuhp_is_ap_state(state))
 		ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
 	else
-		ret = cpuhp_invoke_callback(cpu, state, bringup, node);
+		ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
 #else
-	ret = cpuhp_invoke_callback(cpu, state, bringup, node);
+	ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
 #endif
 	BUG_ON(ret && !bringup);
 	return ret;
@@ -1641,9 +1828,55 @@
 }
 static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);
 
+
+static ssize_t write_cpuhp_fail(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+	struct cpuhp_step *sp;
+	int fail, ret;
+
+	ret = kstrtoint(buf, 10, &fail);
+	if (ret)
+		return ret;
+
+	/*
+	 * Cannot fail STARTING/DYING callbacks.
+	 */
+	if (cpuhp_is_atomic_state(fail))
+		return -EINVAL;
+
+	/*
+	 * Cannot fail anything that doesn't have callbacks.
+	 */
+	mutex_lock(&cpuhp_state_mutex);
+	sp = cpuhp_get_step(fail);
+	if (!sp->startup.single && !sp->teardown.single)
+		ret = -EINVAL;
+	mutex_unlock(&cpuhp_state_mutex);
+	if (ret)
+		return ret;
+
+	st->fail = fail;
+
+	return count;
+}
+
+static ssize_t show_cpuhp_fail(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+
+	return sprintf(buf, "%d\n", st->fail);
+}
+
+static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail);
+
 static struct attribute *cpuhp_cpu_attrs[] = {
 	&dev_attr_state.attr,
 	&dev_attr_target.attr,
+	&dev_attr_fail.attr,
 	NULL
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3e691b7..9d93db8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -662,7 +662,7 @@
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgrp == event->cgrp)
+       if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 		__update_cgrp_time(event->cgrp);
 }
 
@@ -8171,6 +8171,7 @@
 		}
 	}
 	event->tp_event->prog = prog;
+	event->tp_event->bpf_prog_owner = event;
 
 	return 0;
 }
@@ -8185,7 +8186,7 @@
 		return;
 
 	prog = event->tp_event->prog;
-	if (prog) {
+	if (prog && event->tp_event->bpf_prog_owner == event) {
 		event->tp_event->prog = NULL;
 		bpf_prog_put(prog);
 	}
@@ -8954,6 +8955,14 @@
 
 static void free_pmu_context(struct pmu *pmu)
 {
+	/*
+	 * Static contexts such as perf_sw_context have a global lifetime
+	 * and may be shared between different PMUs. Avoid freeing them
+	 * when a single PMU is going away.
+	 */
+	if (pmu->task_ctx_nr > perf_invalid_context)
+		return;
+
 	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
 	mutex_unlock(&pmus_lock);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index af71a84e..f684d8e 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -412,6 +412,19 @@
 	return NULL;
 }
 
+static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
+{
+	if (rb->aux_overwrite)
+		return false;
+
+	if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+		rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Commit the data written by hardware into the ring buffer by adjusting
  * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
@@ -451,10 +464,8 @@
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
-	if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+	if (rb_need_aux_wakeup(rb))
 		wakeup = true;
-		rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
-	}
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
@@ -484,9 +495,8 @@
 	rb->aux_head += size;
 
 	rb->user_page->aux_head = rb->aux_head;
-	if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+	if (rb_need_aux_wakeup(rb)) {
 		perf_output_wakeup(handle);
-		rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
 		handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 3481aba..f6cad39 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1600,18 +1600,19 @@
 	struct waitid_info info = {.status = 0};
 	long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL);
 	int signo = 0;
+
 	if (err > 0) {
 		signo = SIGCHLD;
 		err = 0;
-	}
-
-	if (!err) {
 		if (ru && copy_to_user(ru, &r, sizeof(struct rusage)))
 			return -EFAULT;
 	}
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
@@ -1723,21 +1724,23 @@
 	if (err > 0) {
 		signo = SIGCHLD;
 		err = 0;
-	}
-
-	if (!err && uru) {
-		/* kernel_waitid() overwrites everything in ru */
-		if (COMPAT_USE_64BIT_TIME)
-			err = copy_to_user(uru, &ru, sizeof(ru));
-		else
-			err = put_compat_rusage(&ru, uru);
-		if (err)
-			return -EFAULT;
+		if (uru) {
+			/* kernel_waitid() overwrites everything in ru */
+			if (COMPAT_USE_64BIT_TIME)
+				err = copy_to_user(uru, &ru, sizeof(ru));
+			else
+				err = put_compat_rusage(&ru, uru);
+			if (err)
+				return -EFAULT;
+		}
 	}
 
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
diff --git a/kernel/extable.c b/kernel/extable.c
index 38c2412..9aa1cc4 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -102,15 +102,7 @@
 
 int __kernel_text_address(unsigned long addr)
 {
-	if (core_kernel_text(addr))
-		return 1;
-	if (is_module_text_address(addr))
-		return 1;
-	if (is_ftrace_trampoline(addr))
-		return 1;
-	if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
-		return 1;
-	if (is_bpf_text_address(addr))
+	if (kernel_text_address(addr))
 		return 1;
 	/*
 	 * There might be init symbols in saved stacktraces.
@@ -127,17 +119,42 @@
 
 int kernel_text_address(unsigned long addr)
 {
+	bool no_rcu;
+	int ret = 1;
+
 	if (core_kernel_text(addr))
 		return 1;
+
+	/*
+	 * If a stack dump happens while RCU is not watching, then
+	 * RCU needs to be notified that it requires to start
+	 * watching again. This can happen either by tracing that
+	 * triggers a stack trace, or a WARN() that happens during
+	 * coming back from idle, or cpu on or offlining.
+	 *
+	 * is_module_text_address() as well as the kprobe slots
+	 * and is_bpf_text_address() require RCU to be watching.
+	 */
+	no_rcu = !rcu_is_watching();
+
+	/* Treat this like an NMI as it can happen anywhere */
+	if (no_rcu)
+		rcu_nmi_enter();
+
 	if (is_module_text_address(addr))
-		return 1;
+		goto out;
 	if (is_ftrace_trampoline(addr))
-		return 1;
+		goto out;
 	if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
-		return 1;
+		goto out;
 	if (is_bpf_text_address(addr))
-		return 1;
-	return 0;
+		goto out;
+	ret = 0;
+out:
+	if (no_rcu)
+		rcu_nmi_exit();
+
+	return ret;
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 1064618..07cc743 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -215,6 +215,10 @@
 		if (!s)
 			continue;
 
+#ifdef CONFIG_DEBUG_KMEMLEAK
+		/* Clear stale pointers from reused stack. */
+		memset(s->addr, 0, THREAD_SIZE);
+#endif
 		tsk->stack_vm_area = s;
 		return s->addr;
 	}
@@ -946,6 +950,24 @@
 }
 EXPORT_SYMBOL_GPL(mmput);
 
+#ifdef CONFIG_MMU
+static void mmput_async_fn(struct work_struct *work)
+{
+	struct mm_struct *mm = container_of(work, struct mm_struct,
+					    async_put_work);
+
+	__mmput(mm);
+}
+
+void mmput_async(struct mm_struct *mm)
+{
+	if (atomic_dec_and_test(&mm->mm_users)) {
+		INIT_WORK(&mm->async_put_work, mmput_async_fn);
+		schedule_work(&mm->async_put_work);
+	}
+}
+#endif
+
 /**
  * set_mm_exe_file - change a reference to the mm's executable file
  *
diff --git a/kernel/futex.c b/kernel/futex.c
index 3d38eaf..0518a0b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -821,8 +821,6 @@
 /*
  * Drops a reference to the pi_state object and frees or caches it
  * when the last reference is gone.
- *
- * Must be called with the hb lock held.
  */
 static void put_pi_state(struct futex_pi_state *pi_state)
 {
@@ -837,16 +835,22 @@
 	 * and has cleaned up the pi_state already
 	 */
 	if (pi_state->owner) {
-		raw_spin_lock_irq(&pi_state->owner->pi_lock);
-		list_del_init(&pi_state->list);
-		raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+		struct task_struct *owner;
 
-		rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner);
+		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		owner = pi_state->owner;
+		if (owner) {
+			raw_spin_lock(&owner->pi_lock);
+			list_del_init(&pi_state->list);
+			raw_spin_unlock(&owner->pi_lock);
+		}
+		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	}
 
-	if (current->pi_state_cache)
+	if (current->pi_state_cache) {
 		kfree(pi_state);
-	else {
+	} else {
 		/*
 		 * pi_state->list is already empty.
 		 * clear pi_state->owner.
@@ -907,13 +911,14 @@
 		raw_spin_unlock_irq(&curr->pi_lock);
 
 		spin_lock(&hb->lock);
-
-		raw_spin_lock_irq(&curr->pi_lock);
+		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_lock(&curr->pi_lock);
 		/*
 		 * We dropped the pi-lock, so re-check whether this
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
 			continue;
 		}
@@ -922,9 +927,10 @@
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		pi_state->owner = NULL;
-		raw_spin_unlock_irq(&curr->pi_lock);
+		raw_spin_unlock(&curr->pi_lock);
 
 		get_pi_state(pi_state);
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
 		rt_mutex_futex_unlock(&pi_state->pi_mutex);
@@ -1208,6 +1214,10 @@
 
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &p->pi_state_list);
+	/*
+	 * Assignment without holding pi_state->pi_mutex.wait_lock is safe
+	 * because there is no concurrency as the object is not published yet.
+	 */
 	pi_state->owner = p;
 	raw_spin_unlock_irq(&p->pi_lock);
 
@@ -2878,6 +2888,7 @@
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
+		/* drops pi_state->pi_mutex.wait_lock */
 		ret = wake_futex_pi(uaddr, uval, pi_state);
 
 		put_pi_state(pi_state);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f51b7b6..5a2ef92c 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -202,7 +202,7 @@
 
 	irqd_clr_managed_shutdown(d);
 
-	if (cpumask_any_and(aff, cpu_online_mask) > nr_cpu_ids) {
+	if (cpumask_any_and(aff, cpu_online_mask) >= nr_cpu_ids) {
 		/*
 		 * Catch code which fiddles with enable_irq() on a managed
 		 * and potentially shutdown IRQ. Chained interrupt
@@ -265,8 +265,8 @@
 			irq_setup_affinity(desc);
 			break;
 		case IRQ_STARTUP_MANAGED:
+			irq_do_set_affinity(d, aff, false);
 			ret = __irq_startup(desc);
-			irq_set_affinity_locked(d, aff, false);
 			break;
 		case IRQ_STARTUP_ABORT:
 			return 0;
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 638eb9c..9eb09ae 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -18,8 +18,34 @@
 static inline bool irq_needs_fixup(struct irq_data *d)
 {
 	const struct cpumask *m = irq_data_get_effective_affinity_mask(d);
+	unsigned int cpu = smp_processor_id();
 
-	return cpumask_test_cpu(smp_processor_id(), m);
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	/*
+	 * The cpumask_empty() check is a workaround for interrupt chips,
+	 * which do not implement effective affinity, but the architecture has
+	 * enabled the config switch. Use the general affinity mask instead.
+	 */
+	if (cpumask_empty(m))
+		m = irq_data_get_affinity_mask(d);
+
+	/*
+	 * Sanity check. If the mask is not empty when excluding the outgoing
+	 * CPU then it must contain at least one online CPU. The outgoing CPU
+	 * has been removed from the online mask already.
+	 */
+	if (cpumask_any_but(m, cpu) < nr_cpu_ids &&
+	    cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) {
+		/*
+		 * If this happens then there was a missed IRQ fixup at some
+		 * point. Warn about it and enforce fixup.
+		 */
+		pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n",
+			cpumask_pr_args(m), d->irq, cpu);
+		return true;
+	}
+#endif
+	return cpumask_test_cpu(cpu, m);
 }
 
 static bool migrate_one_irq(struct irq_desc *desc)
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index f7086b7..c26c5bb 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -135,17 +135,26 @@
 }
 
 /**
- * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt
+ * irq_gc_mask_disable_and_ack_set - Mask and ack pending interrupt
  * @d: irq_data
+ *
+ * This generic implementation of the irq_mask_ack method is for chips
+ * with separate enable/disable registers instead of a single mask
+ * register and where a pending interrupt is acknowledged by setting a
+ * bit.
+ *
+ * Note: This is the only permutation currently used.  Similar generic
+ * functions should be added here if other permutations are required.
  */
-void irq_gc_mask_disable_reg_and_ack(struct irq_data *d)
+void irq_gc_mask_disable_and_ack_set(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(gc, mask, ct->regs.mask);
+	irq_reg_writel(gc, mask, ct->regs.disable);
+	*ct->mask_cache &= ~mask;
 	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }
@@ -322,7 +331,6 @@
 		/* Calc pointer to the next generic chip */
 		tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type);
 	}
-	d->name = name;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index e84b705..ac4644e 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -945,7 +945,7 @@
 	struct irq_desc *desc;
 	struct irq_domain *domain;
 	struct radix_tree_iter iter;
-	void **slot;
+	void __rcu **slot;
 	int i;
 
 	seq_printf(m, " %-16s  %-6s  %-10s  %-10s  %s\n",
@@ -1453,7 +1453,7 @@
 /* The irq_data was moved, fix the revmap to refer to the new location */
 static void irq_domain_fix_revmap(struct irq_data *d)
 {
-	void **slot;
+	void __rcu **slot;
 
 	if (d->hwirq < d->domain->revmap_size)
 		return; /* Not using radix tree. */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 573dc52..4bff6a1 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -168,6 +168,19 @@
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 }
 
+static void irq_validate_effective_affinity(struct irq_data *data)
+{
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+
+	if (!cpumask_empty(m))
+		return;
+	pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
+		     chip->name, data->irq);
+#endif
+}
+
 int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
@@ -175,12 +188,16 @@
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	int ret;
 
+	if (!chip || !chip->irq_set_affinity)
+		return -EINVAL;
+
 	ret = chip->irq_set_affinity(data, mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
 		cpumask_copy(desc->irq_common_data.affinity, mask);
 	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_validate_effective_affinity(data);
 		irq_set_thread_affinity(desc);
 		ret = 0;
 	}
@@ -1643,6 +1660,10 @@
 #endif
 
 	action = __free_irq(irq, dev_id);
+
+	if (!action)
+		return NULL;
+
 	devname = action->name;
 	kfree(action);
 	return devname;
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index ea34ed8..055bb29 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -131,7 +131,7 @@
 	if (filp_epoll) {
 		filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff);
 		fput(filp_epoll);
-	} else
+	}
 
 	if (IS_ERR(filp_tgt))
 		return PTR_ERR(filp_tgt);
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index b9628e4..bf8c8fd 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -830,6 +830,41 @@
 }
 EXPORT_SYMBOL_GPL(klp_register_patch);
 
+/*
+ * Remove parts of patches that touch a given kernel module. The list of
+ * patches processed might be limited. When limit is NULL, all patches
+ * will be handled.
+ */
+static void klp_cleanup_module_patches_limited(struct module *mod,
+					       struct klp_patch *limit)
+{
+	struct klp_patch *patch;
+	struct klp_object *obj;
+
+	list_for_each_entry(patch, &klp_patches, list) {
+		if (patch == limit)
+			break;
+
+		klp_for_each_object(patch, obj) {
+			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
+				continue;
+
+			/*
+			 * Only unpatch the module if the patch is enabled or
+			 * is in transition.
+			 */
+			if (patch->enabled || patch == klp_transition_patch) {
+				pr_notice("reverting patch '%s' on unloading module '%s'\n",
+					  patch->mod->name, obj->mod->name);
+				klp_unpatch_object(obj);
+			}
+
+			klp_free_object_loaded(obj);
+			break;
+		}
+	}
+}
+
 int klp_module_coming(struct module *mod)
 {
 	int ret;
@@ -894,7 +929,7 @@
 	pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n",
 		patch->mod->name, obj->mod->name, obj->mod->name);
 	mod->klp_alive = false;
-	klp_free_object_loaded(obj);
+	klp_cleanup_module_patches_limited(mod, patch);
 	mutex_unlock(&klp_mutex);
 
 	return ret;
@@ -902,9 +937,6 @@
 
 void klp_module_going(struct module *mod)
 {
-	struct klp_patch *patch;
-	struct klp_object *obj;
-
 	if (WARN_ON(mod->state != MODULE_STATE_GOING &&
 		    mod->state != MODULE_STATE_COMING))
 		return;
@@ -917,25 +949,7 @@
 	 */
 	mod->klp_alive = false;
 
-	list_for_each_entry(patch, &klp_patches, list) {
-		klp_for_each_object(patch, obj) {
-			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
-				continue;
-
-			/*
-			 * Only unpatch the module if the patch is enabled or
-			 * is in transition.
-			 */
-			if (patch->enabled || patch == klp_transition_patch) {
-				pr_notice("reverting patch '%s' on unloading module '%s'\n",
-					  patch->mod->name, obj->mod->name);
-				klp_unpatch_object(obj);
-			}
-
-			klp_free_object_loaded(obj);
-			break;
-		}
-	}
+	klp_cleanup_module_patches_limited(mod, NULL);
 
 	mutex_unlock(&klp_mutex);
 }
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 44c8d0d..e36e652 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1873,10 +1873,10 @@
 	       struct held_lock *next, int distance, struct stack_trace *trace,
 	       int (*save)(struct stack_trace *trace))
 {
-	struct lock_list *entry;
-	int ret;
-	struct lock_list this;
 	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *entry;
+	struct lock_list this;
+	int ret;
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1890,8 +1890,17 @@
 	this.class = hlock_class(next);
 	this.parent = NULL;
 	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
-	if (unlikely(!ret))
+	if (unlikely(!ret)) {
+		if (!trace->entries) {
+			/*
+			 * If @save fails here, the printing might trigger
+			 * a WARN but because of the !nr_entries it should
+			 * not do bad things.
+			 */
+			save(trace);
+		}
 		return print_circular_bug(&this, target_entry, next, prev, trace);
+	}
 	else if (unlikely(ret < 0))
 		return print_bfs_bug(ret);
 
@@ -1938,7 +1947,7 @@
 		return print_bfs_bug(ret);
 
 
-	if (save && !save(trace))
+	if (!trace->entries && !save(trace))
 		return 0;
 
 	/*
@@ -1958,20 +1967,6 @@
 	if (!ret)
 		return 0;
 
-	/*
-	 * Debugging printouts:
-	 */
-	if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
-		graph_unlock();
-		printk("\n new dependency: ");
-		print_lock_name(hlock_class(prev));
-		printk(KERN_CONT " => ");
-		print_lock_name(hlock_class(next));
-		printk(KERN_CONT "\n");
-		dump_stack();
-		if (!graph_lock())
-			return 0;
-	}
 	return 2;
 }
 
@@ -1986,8 +1981,12 @@
 {
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
-	struct stack_trace trace;
-	int (*save)(struct stack_trace *trace) = save_trace;
+	struct stack_trace trace = {
+		.nr_entries = 0,
+		.max_entries = 0,
+		.entries = NULL,
+		.skip = 0,
+	};
 
 	/*
 	 * Debugging checks.
@@ -2018,18 +2017,11 @@
 			 */
 			if (hlock->read != 2 && hlock->check) {
 				int ret = check_prev_add(curr, hlock, next,
-							 distance, &trace, save);
+							 distance, &trace, save_trace);
 				if (!ret)
 					return 0;
 
 				/*
-				 * Stop saving stack_trace if save_trace() was
-				 * called at least once:
-				 */
-				if (save && ret == 2)
-					save = NULL;
-
-				/*
 				 * Stop after the first non-trylock entry,
 				 * as non-trylock entries have added their
 				 * own direct dependencies already, so this
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 02f6606..1fefe6d 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -613,6 +613,33 @@
 	DEFINE_WAKE_Q(wake_q);
 
 	/*
+	* __rwsem_down_write_failed_common(sem)
+	*   rwsem_optimistic_spin(sem)
+	*     osq_unlock(sem->osq)
+	*   ...
+	*   atomic_long_add_return(&sem->count)
+	*
+	*      - VS -
+	*
+	*              __up_write()
+	*                if (atomic_long_sub_return_release(&sem->count) < 0)
+	*                  rwsem_wake(sem)
+	*                    osq_is_locked(&sem->osq)
+	*
+	* And __up_write() must observe !osq_is_locked() when it observes the
+	* atomic_long_add_return() in order to not miss a wakeup.
+	*
+	* This boils down to:
+	*
+	* [S.rel] X = 1                [RmW] r0 = (Y += 0)
+	*         MB                         RMB
+	* [RmW]   Y += 1               [L]   r1 = X
+	*
+	* exists (r0=1 /\ r1=0)
+	*/
+	smp_rmb();
+
+	/*
 	 * If a spinner is present, it is not necessary to do the wakeup.
 	 * Try to do wakeup only if the trylock succeeds to minimize
 	 * spinlock contention which may introduce too much delay in the
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 6bcbfbf..403ab9c 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -350,7 +350,7 @@
 	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
-	int error, nid, is_ram;
+	int error, nid, is_ram, i = 0;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -448,6 +448,8 @@
 		list_del(&page->lru);
 		page->pgmap = pgmap;
 		percpu_ref_get(ref);
+		if (!(++i % 1024))
+			cond_resched();
 	}
 	devres_add(dev, page_map);
 	return __va(res->start);
diff --git a/kernel/params.c b/kernel/params.c
index 60b2d81..cc9108c 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -224,7 +224,7 @@
 	}								\
 	int param_get_##name(char *buffer, const struct kernel_param *kp) \
 	{								\
-		return scnprintf(buffer, PAGE_SIZE, format,		\
+		return scnprintf(buffer, PAGE_SIZE, format "\n",	\
 				*((type *)kp->arg));			\
 	}								\
 	const struct kernel_param_ops param_ops_##name = {			\
@@ -236,14 +236,14 @@
 	EXPORT_SYMBOL(param_ops_##name)
 
 
-STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8);
-STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16);
-STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16);
-STANDARD_PARAM_DEF(int, int, "%i", kstrtoint);
-STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint);
-STANDARD_PARAM_DEF(long, long, "%li", kstrtol);
-STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul);
-STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull);
+STANDARD_PARAM_DEF(byte,	unsigned char,		"%hhu", kstrtou8);
+STANDARD_PARAM_DEF(short,	short,			"%hi",  kstrtos16);
+STANDARD_PARAM_DEF(ushort,	unsigned short,		"%hu",  kstrtou16);
+STANDARD_PARAM_DEF(int,		int,			"%i",   kstrtoint);
+STANDARD_PARAM_DEF(uint,	unsigned int,		"%u",   kstrtouint);
+STANDARD_PARAM_DEF(long,	long,			"%li",  kstrtol);
+STANDARD_PARAM_DEF(ulong,	unsigned long,		"%lu",  kstrtoul);
+STANDARD_PARAM_DEF(ullong,	unsigned long long,	"%llu", kstrtoull);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)
 {
@@ -270,7 +270,7 @@
 
 int param_get_charp(char *buffer, const struct kernel_param *kp)
 {
-	return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg));
+	return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg));
 }
 EXPORT_SYMBOL(param_get_charp);
 
@@ -301,7 +301,7 @@
 int param_get_bool(char *buffer, const struct kernel_param *kp)
 {
 	/* Y and N chosen as being relatively non-coder friendly */
-	return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N');
+	return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N');
 }
 EXPORT_SYMBOL(param_get_bool);
 
@@ -360,7 +360,7 @@
 
 int param_get_invbool(char *buffer, const struct kernel_param *kp)
 {
-	return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y');
+	return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y');
 }
 EXPORT_SYMBOL(param_get_invbool);
 
@@ -460,8 +460,9 @@
 	struct kernel_param p = *kp;
 
 	for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) {
+		/* Replace \n with comma */
 		if (i)
-			buffer[off++] = ',';
+			buffer[off - 1] = ',';
 		p.arg = arr->elem + arr->elemsize * i;
 		check_kparam_locked(p.mod);
 		ret = arr->ops->get(buffer + off, &p);
@@ -507,7 +508,7 @@
 int param_get_string(char *buffer, const struct kernel_param *kp)
 {
 	const struct kparam_string *kps = kp->str;
-	return strlcpy(buffer, kps->string, kps->maxlen);
+	return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string);
 }
 EXPORT_SYMBOL(param_get_string);
 
@@ -549,10 +550,6 @@
 	kernel_param_lock(mk->mod);
 	count = attribute->param->ops->get(buf, attribute->param);
 	kernel_param_unlock(mk->mod);
-	if (count > 0) {
-		strcat(buf, "\n");
-		++count;
-	}
 	return count;
 }
 
@@ -600,7 +597,7 @@
 /*
  * add_sysfs_param - add a parameter to sysfs
  * @mk: struct module_kobject
- * @kparam: the actual parameter definition to add to sysfs
+ * @kp: the actual parameter definition to add to sysfs
  * @name: name of parameter
  *
  * Create a kobject if for a (per-module) parameter if mp NULL, and
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 3e2b4f5..ccd2d20 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -120,22 +120,26 @@
 		 * frozen processes + suspended devices + idle processors.
 		 * Thus s2idle_enter() should be called right after
 		 * all devices have been suspended.
+		 *
+		 * Wakeups during the noirq suspend of devices may be spurious,
+		 * so prevent them from terminating the loop right away.
 		 */
 		error = dpm_noirq_suspend_devices(PMSG_SUSPEND);
 		if (!error)
 			s2idle_enter();
+		else if (error == -EBUSY && pm_wakeup_pending())
+			error = 0;
 
-		dpm_noirq_resume_devices(PMSG_RESUME);
-		if (error && (error != -EBUSY || !pm_wakeup_pending())) {
-			dpm_noirq_end();
-			break;
-		}
-
-		if (s2idle_ops && s2idle_ops->wake)
+		if (!error && s2idle_ops && s2idle_ops->wake)
 			s2idle_ops->wake();
 
+		dpm_noirq_resume_devices(PMSG_RESUME);
+
 		dpm_noirq_end();
 
+		if (error)
+			break;
+
 		if (s2idle_ops && s2idle_ops->sync)
 			s2idle_ops->sync();
 
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 729a870..6d58800 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -854,7 +854,7 @@
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
  * @sp: srcu_struct in queue the callback
- * @head: structure to be used for queueing the SRCU callback.
+ * @rhp: structure to be used for queueing the SRCU callback.
  * @func: function to be invoked after the SRCU grace period
  *
  * The callback function will be invoked some time after a full SRCU
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index 50d1861..3f943ef 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -85,6 +85,9 @@
 }
 
 /**
+ * rcu_sync_enter_start - Force readers onto slow path for multiple updates
+ * @rsp: Pointer to rcu_sync structure to use for synchronization
+ *
  * Must be called after rcu_sync_init() and before first use.
  *
  * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
@@ -142,7 +145,7 @@
 
 /**
  * rcu_sync_func() - Callback function managing reader access to fastpath
- * @rsp: Pointer to rcu_sync structure to use for synchronization
+ * @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization
  *
  * This function is passed to one of the call_rcu() functions by
  * rcu_sync_exit(), so that it is invoked after a grace period following the
@@ -158,9 +161,9 @@
  * rcu_sync_exit().  Otherwise, set all state back to idle so that readers
  * can again use their fastpaths.
  */
-static void rcu_sync_func(struct rcu_head *rcu)
+static void rcu_sync_func(struct rcu_head *rhp)
 {
-	struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head);
+	struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
 	unsigned long flags;
 
 	BUG_ON(rsp->gp_state != GP_PASSED);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1250e4b..3e3650e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -882,6 +882,11 @@
 
 	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
+
+	/* Page faults can happen in NMI handlers, so check... */
+	if (rdtp->dynticks_nmi_nesting)
+		return;
+
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     rdtp->dynticks_nesting < 1);
 	if (rdtp->dynticks_nesting <= 1) {
@@ -1015,6 +1020,11 @@
 
 	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
+
+	/* Page faults can happen in NMI handlers, so check... */
+	if (rdtp->dynticks_nmi_nesting)
+		return;
+
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -3087,9 +3097,10 @@
  * read-side critical sections have completed. call_rcu_sched() assumes
  * that the read-side critical sections end on enabling of preemption
  * or on voluntary preemption.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
- *  - anything that disables preemption.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
+ * - anything that disables preemption.
  *
  *  These may be nested.
  *
@@ -3114,11 +3125,12 @@
  * handler. This means that read-side critical sections in process
  * context must not be interrupted by softirqs. This interface is to be
  * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
- *  OR
- *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
- *  These may be nested.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context, OR
+ * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
+ *
+ * These may be nested.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 18a6966..d17c5da 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5166,6 +5166,28 @@
 	put_task_stack(p);
 }
 
+static inline bool
+state_filter_match(unsigned long state_filter, struct task_struct *p)
+{
+	/* no filter, everything matches */
+	if (!state_filter)
+		return true;
+
+	/* filter, but doesn't match */
+	if (!(p->state & state_filter))
+		return false;
+
+	/*
+	 * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
+	 * TASK_KILLABLE).
+	 */
+	if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE)
+		return false;
+
+	return true;
+}
+
+
 void show_state_filter(unsigned long state_filter)
 {
 	struct task_struct *g, *p;
@@ -5188,7 +5210,7 @@
 		 */
 		touch_nmi_watchdog();
 		touch_all_softlockup_watchdogs();
-		if (!state_filter || (p->state & state_filter))
+		if (state_filter_match(state_filter, p))
 			sched_show_task(p);
 	}
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 01217fb..2f93e4a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -466,8 +466,6 @@
 }
 #endif
 
-static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
-
 static void
 print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 70ba32e..d3f3094 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5356,91 +5356,62 @@
 	return 1;
 }
 
-struct llc_stats {
-	unsigned long	nr_running;
-	unsigned long	load;
-	unsigned long	capacity;
-	int		has_capacity;
-};
+/*
+ * The purpose of wake_affine() is to quickly determine on which CPU we can run
+ * soonest. For the purpose of speed we only consider the waking and previous
+ * CPU.
+ *
+ * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or
+ *			will be) idle.
+ *
+ * wake_affine_weight() - considers the weight to reflect the average
+ *			  scheduling latency of the CPUs. This seems to work
+ *			  for the overloaded case.
+ */
 
-static bool get_llc_stats(struct llc_stats *stats, int cpu)
+static bool
+wake_affine_idle(struct sched_domain *sd, struct task_struct *p,
+		 int this_cpu, int prev_cpu, int sync)
 {
-	struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
+	if (idle_cpu(this_cpu))
+		return true;
 
-	if (!sds)
-		return false;
+	if (sync && cpu_rq(this_cpu)->nr_running == 1)
+		return true;
 
-	stats->nr_running	= READ_ONCE(sds->nr_running);
-	stats->load		= READ_ONCE(sds->load);
-	stats->capacity		= READ_ONCE(sds->capacity);
-	stats->has_capacity	= stats->nr_running < per_cpu(sd_llc_size, cpu);
-
-	return true;
+	return false;
 }
 
-/*
- * Can a task be moved from prev_cpu to this_cpu without causing a load
- * imbalance that would trigger the load balancer?
- *
- * Since we're running on 'stale' values, we might in fact create an imbalance
- * but recomputing these values is expensive, as that'd mean iteration 2 cache
- * domains worth of CPUs.
- */
 static bool
-wake_affine_llc(struct sched_domain *sd, struct task_struct *p,
-		int this_cpu, int prev_cpu, int sync)
+wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
+		   int this_cpu, int prev_cpu, int sync)
 {
-	struct llc_stats prev_stats, this_stats;
 	s64 this_eff_load, prev_eff_load;
 	unsigned long task_load;
 
-	if (!get_llc_stats(&prev_stats, prev_cpu) ||
-	    !get_llc_stats(&this_stats, this_cpu))
-		return false;
+	this_eff_load = target_load(this_cpu, sd->wake_idx);
+	prev_eff_load = source_load(prev_cpu, sd->wake_idx);
 
-	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current LLC.
-	 */
 	if (sync) {
 		unsigned long current_load = task_h_load(current);
 
-		/* in this case load hits 0 and this LLC is considered 'idle' */
-		if (current_load > this_stats.load)
+		if (current_load > this_eff_load)
 			return true;
 
-		this_stats.load -= current_load;
+		this_eff_load -= current_load;
 	}
 
-	/*
-	 * The has_capacity stuff is not SMT aware, but by trying to balance
-	 * the nr_running on both ends we try and fill the domain at equal
-	 * rates, thereby first consuming cores before siblings.
-	 */
-
-	/* if the old cache has capacity, stay there */
-	if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1)
-		return false;
-
-	/* if this cache has capacity, come here */
-	if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running)
-		return true;
-
-	/*
-	 * Check to see if we can move the load without causing too much
-	 * imbalance.
-	 */
 	task_load = task_h_load(p);
 
-	this_eff_load = 100;
-	this_eff_load *= prev_stats.capacity;
+	this_eff_load += task_load;
+	if (sched_feat(WA_BIAS))
+		this_eff_load *= 100;
+	this_eff_load *= capacity_of(prev_cpu);
 
-	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-	prev_eff_load *= this_stats.capacity;
-
-	this_eff_load *= this_stats.load + task_load;
-	prev_eff_load *= prev_stats.load - task_load;
+	prev_eff_load -= task_load;
+	if (sched_feat(WA_BIAS))
+		prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
+	prev_eff_load *= capacity_of(this_cpu);
 
 	return this_eff_load <= prev_eff_load;
 }
@@ -5449,22 +5420,13 @@
 		       int prev_cpu, int sync)
 {
 	int this_cpu = smp_processor_id();
-	bool affine;
+	bool affine = false;
 
-	/*
-	 * Default to no affine wakeups; wake_affine() should not effect a task
-	 * placement the load-balancer feels inclined to undo. The conservative
-	 * option is therefore to not move tasks when they wake up.
-	 */
-	affine = false;
+	if (sched_feat(WA_IDLE) && !affine)
+		affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync);
 
-	/*
-	 * If the wakeup is across cache domains, try to evaluate if movement
-	 * makes sense, otherwise rely on select_idle_siblings() to do
-	 * placement inside the cache domain.
-	 */
-	if (!cpus_share_cache(prev_cpu, this_cpu))
-		affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync);
+	if (sched_feat(WA_WEIGHT) && !affine)
+		affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
 	if (affine) {
@@ -7600,7 +7562,6 @@
  */
 static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
 {
-	struct sched_domain_shared *shared = env->sd->shared;
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
@@ -7672,22 +7633,6 @@
 		if (env->dst_rq->rd->overload != overload)
 			env->dst_rq->rd->overload = overload;
 	}
-
-	if (!shared)
-		return;
-
-	/*
-	 * Since these are sums over groups they can contain some CPUs
-	 * multiple times for the NUMA domains.
-	 *
-	 * Currently only wake_affine_llc() and find_busiest_group()
-	 * uses these numbers, only the last is affected by this problem.
-	 *
-	 * XXX fix that.
-	 */
-	WRITE_ONCE(shared->nr_running,	sds->total_running);
-	WRITE_ONCE(shared->load,	sds->total_load);
-	WRITE_ONCE(shared->capacity,	sds->total_capacity);
 }
 
 /**
@@ -8098,6 +8043,13 @@
 	int cpu, balance_cpu = -1;
 
 	/*
+	 * Ensure the balancing environment is consistent; can happen
+	 * when the softirq triggers 'during' hotplug.
+	 */
+	if (!cpumask_test_cpu(env->dst_cpu, env->cpus))
+		return 0;
+
+	/*
 	 * In the newly idle case, we will allow all the cpu's
 	 * to do the newly idle load balance.
 	 */
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index d3fb155..319ed0e 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -81,3 +81,6 @@
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
 
+SCHED_FEAT(WA_IDLE, true)
+SCHED_FEAT(WA_WEIGHT, true)
+SCHED_FEAT(WA_BIAS, true)
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a92fddc..dd79087 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,6 +18,7 @@
 #include <linux/membarrier.h>
 #include <linux/tick.h>
 #include <linux/cpumask.h>
+#include <linux/atomic.h>
 
 #include "sched.h"	/* for cpu_rq(). */
 
@@ -26,21 +27,26 @@
  * except MEMBARRIER_CMD_QUERY.
  */
 #define MEMBARRIER_CMD_BITMASK	\
-	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED	\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
 
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
-static void membarrier_private_expedited(void)
+static int membarrier_private_expedited(void)
 {
 	int cpu;
 	bool fallback = false;
 	cpumask_var_t tmpmask;
 
+	if (!(atomic_read(&current->mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
+		return -EPERM;
+
 	if (num_online_cpus() == 1)
-		return;
+		return 0;
 
 	/*
 	 * Matches memory barriers around rq->curr modification in
@@ -94,6 +100,24 @@
 	 * rq->curr modification in scheduler.
 	 */
 	smp_mb();	/* exit from system call is not a mb */
+	return 0;
+}
+
+static void membarrier_register_private_expedited(void)
+{
+	struct task_struct *p = current;
+	struct mm_struct *mm = p->mm;
+
+	/*
+	 * We need to consider threads belonging to different thread
+	 * groups, which use the same mm. (CLONE_VM but not
+	 * CLONE_THREAD).
+	 */
+	if (atomic_read(&mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)
+		return;
+	atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY,
+			&mm->membarrier_state);
 }
 
 /**
@@ -144,7 +168,9 @@
 			synchronize_sched();
 		return 0;
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		membarrier_private_expedited();
+		return membarrier_private_expedited();
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+		membarrier_register_private_expedited();
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 98b59b5..0ae832e 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -17,11 +17,13 @@
 #include <linux/audit.h>
 #include <linux/compat.h>
 #include <linux/coredump.h>
+#include <linux/kmemleak.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/seccomp.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
+#include <linux/sysctl.h>
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 #include <asm/syscall.h>
@@ -42,6 +44,7 @@
  *         get/put helpers should be used when accessing an instance
  *         outside of a lifetime-guarded section.  In general, this
  *         is only needed for handling filters shared across tasks.
+ * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
  * @prev: points to a previously installed, or inherited, filter
  * @prog: the BPF program to evaluate
  *
@@ -57,6 +60,7 @@
  */
 struct seccomp_filter {
 	refcount_t usage;
+	bool log;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
 };
@@ -171,10 +175,15 @@
 /**
  * seccomp_run_filters - evaluates all seccomp filters against @sd
  * @sd: optional seccomp data to be passed to filters
+ * @match: stores struct seccomp_filter that resulted in the return value,
+ *         unless filter returned SECCOMP_RET_ALLOW, in which case it will
+ *         be unchanged.
  *
  * Returns valid seccomp BPF response codes.
  */
-static u32 seccomp_run_filters(const struct seccomp_data *sd)
+#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL)))
+static u32 seccomp_run_filters(const struct seccomp_data *sd,
+			       struct seccomp_filter **match)
 {
 	struct seccomp_data sd_local;
 	u32 ret = SECCOMP_RET_ALLOW;
@@ -184,7 +193,7 @@
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
 	if (unlikely(WARN_ON(f == NULL)))
-		return SECCOMP_RET_KILL;
+		return SECCOMP_RET_KILL_PROCESS;
 
 	if (!sd) {
 		populate_seccomp_data(&sd_local);
@@ -198,8 +207,10 @@
 	for (; f; f = f->prev) {
 		u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
 
-		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+		if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) {
 			ret = cur_ret;
+			*match = f;
+		}
 	}
 	return ret;
 }
@@ -444,6 +455,10 @@
 			return ret;
 	}
 
+	/* Set log flag, if present. */
+	if (flags & SECCOMP_FILTER_FLAG_LOG)
+		filter->log = true;
+
 	/*
 	 * If there is an existing filter, make it the prev and don't drop its
 	 * task reference.
@@ -458,14 +473,19 @@
 	return 0;
 }
 
+static void __get_seccomp_filter(struct seccomp_filter *filter)
+{
+	/* Reference count is bounded by the number of total processes. */
+	refcount_inc(&filter->usage);
+}
+
 /* get_seccomp_filter - increments the reference count of the filter on @tsk */
 void get_seccomp_filter(struct task_struct *tsk)
 {
 	struct seccomp_filter *orig = tsk->seccomp.filter;
 	if (!orig)
 		return;
-	/* Reference count is bounded by the number of total processes. */
-	refcount_inc(&orig->usage);
+	__get_seccomp_filter(orig);
 }
 
 static inline void seccomp_filter_free(struct seccomp_filter *filter)
@@ -476,10 +496,8 @@
 	}
 }
 
-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
+static void __put_seccomp_filter(struct seccomp_filter *orig)
 {
-	struct seccomp_filter *orig = tsk->seccomp.filter;
 	/* Clean up single-reference branches iteratively. */
 	while (orig && refcount_dec_and_test(&orig->usage)) {
 		struct seccomp_filter *freeme = orig;
@@ -488,6 +506,12 @@
 	}
 }
 
+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+	__put_seccomp_filter(tsk->seccomp.filter);
+}
+
 static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason)
 {
 	memset(info, 0, sizeof(*info));
@@ -514,6 +538,65 @@
 }
 #endif	/* CONFIG_SECCOMP_FILTER */
 
+/* For use with seccomp_actions_logged */
+#define SECCOMP_LOG_KILL_PROCESS	(1 << 0)
+#define SECCOMP_LOG_KILL_THREAD		(1 << 1)
+#define SECCOMP_LOG_TRAP		(1 << 2)
+#define SECCOMP_LOG_ERRNO		(1 << 3)
+#define SECCOMP_LOG_TRACE		(1 << 4)
+#define SECCOMP_LOG_LOG			(1 << 5)
+#define SECCOMP_LOG_ALLOW		(1 << 6)
+
+static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS |
+				    SECCOMP_LOG_KILL_THREAD  |
+				    SECCOMP_LOG_TRAP  |
+				    SECCOMP_LOG_ERRNO |
+				    SECCOMP_LOG_TRACE |
+				    SECCOMP_LOG_LOG;
+
+static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
+			       bool requested)
+{
+	bool log = false;
+
+	switch (action) {
+	case SECCOMP_RET_ALLOW:
+		break;
+	case SECCOMP_RET_TRAP:
+		log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP;
+		break;
+	case SECCOMP_RET_ERRNO:
+		log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO;
+		break;
+	case SECCOMP_RET_TRACE:
+		log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE;
+		break;
+	case SECCOMP_RET_LOG:
+		log = seccomp_actions_logged & SECCOMP_LOG_LOG;
+		break;
+	case SECCOMP_RET_KILL_THREAD:
+		log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD;
+		break;
+	case SECCOMP_RET_KILL_PROCESS:
+	default:
+		log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS;
+	}
+
+	/*
+	 * Force an audit message to be emitted when the action is RET_KILL_*,
+	 * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is
+	 * allowed to be logged by the admin.
+	 */
+	if (log)
+		return __audit_seccomp(syscall, signr, action);
+
+	/*
+	 * Let the audit subsystem decide if the action should be audited based
+	 * on whether the current task itself is being audited.
+	 */
+	return audit_seccomp(syscall, signr, action);
+}
+
 /*
  * Secure computing mode 1 allows only read/write/exit/sigreturn.
  * To be fully secure this must be combined with rlimit
@@ -539,7 +622,7 @@
 #ifdef SECCOMP_DEBUG
 	dump_stack();
 #endif
-	audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL);
+	seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true);
 	do_exit(SIGKILL);
 }
 
@@ -566,6 +649,7 @@
 			    const bool recheck_after_trace)
 {
 	u32 filter_ret, action;
+	struct seccomp_filter *match = NULL;
 	int data;
 
 	/*
@@ -574,9 +658,9 @@
 	 */
 	rmb();
 
-	filter_ret = seccomp_run_filters(sd);
+	filter_ret = seccomp_run_filters(sd, &match);
 	data = filter_ret & SECCOMP_RET_DATA;
-	action = filter_ret & SECCOMP_RET_ACTION;
+	action = filter_ret & SECCOMP_RET_ACTION_FULL;
 
 	switch (action) {
 	case SECCOMP_RET_ERRNO:
@@ -637,14 +721,25 @@
 
 		return 0;
 
-	case SECCOMP_RET_ALLOW:
+	case SECCOMP_RET_LOG:
+		seccomp_log(this_syscall, 0, action, true);
 		return 0;
 
-	case SECCOMP_RET_KILL:
+	case SECCOMP_RET_ALLOW:
+		/*
+		 * Note that the "match" filter will always be NULL for
+		 * this action since SECCOMP_RET_ALLOW is the starting
+		 * state in seccomp_run_filters().
+		 */
+		return 0;
+
+	case SECCOMP_RET_KILL_THREAD:
+	case SECCOMP_RET_KILL_PROCESS:
 	default:
-		audit_seccomp(this_syscall, SIGSYS, action);
+		seccomp_log(this_syscall, SIGSYS, action, true);
 		/* Dump core only if this is the last remaining thread. */
-		if (get_nr_threads(current) == 1) {
+		if (action == SECCOMP_RET_KILL_PROCESS ||
+		    get_nr_threads(current) == 1) {
 			siginfo_t info;
 
 			/* Show the original registers in the dump. */
@@ -653,13 +748,16 @@
 			seccomp_init_siginfo(&info, this_syscall, data);
 			do_coredump(&info);
 		}
-		do_exit(SIGSYS);
+		if (action == SECCOMP_RET_KILL_PROCESS)
+			do_group_exit(SIGSYS);
+		else
+			do_exit(SIGSYS);
 	}
 
 	unreachable();
 
 skip:
-	audit_seccomp(this_syscall, 0, action);
+	seccomp_log(this_syscall, 0, action, match ? match->log : false);
 	return -1;
 }
 #else
@@ -794,6 +892,29 @@
 }
 #endif
 
+static long seccomp_get_action_avail(const char __user *uaction)
+{
+	u32 action;
+
+	if (copy_from_user(&action, uaction, sizeof(action)))
+		return -EFAULT;
+
+	switch (action) {
+	case SECCOMP_RET_KILL_PROCESS:
+	case SECCOMP_RET_KILL_THREAD:
+	case SECCOMP_RET_TRAP:
+	case SECCOMP_RET_ERRNO:
+	case SECCOMP_RET_TRACE:
+	case SECCOMP_RET_LOG:
+	case SECCOMP_RET_ALLOW:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 /* Common entry point for both prctl and syscall. */
 static long do_seccomp(unsigned int op, unsigned int flags,
 		       const char __user *uargs)
@@ -805,6 +926,11 @@
 		return seccomp_set_mode_strict();
 	case SECCOMP_SET_MODE_FILTER:
 		return seccomp_set_mode_filter(flags, uargs);
+	case SECCOMP_GET_ACTION_AVAIL:
+		if (flags != 0)
+			return -EINVAL;
+
+		return seccomp_get_action_avail(uargs);
 	default:
 		return -EINVAL;
 	}
@@ -908,13 +1034,13 @@
 	if (!data)
 		goto out;
 
-	get_seccomp_filter(task);
+	__get_seccomp_filter(filter);
 	spin_unlock_irq(&task->sighand->siglock);
 
 	if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
 		ret = -EFAULT;
 
-	put_seccomp_filter(task);
+	__put_seccomp_filter(filter);
 	return ret;
 
 out:
@@ -922,3 +1048,185 @@
 	return ret;
 }
 #endif
+
+#ifdef CONFIG_SYSCTL
+
+/* Human readable action names for friendly sysctl interaction */
+#define SECCOMP_RET_KILL_PROCESS_NAME	"kill_process"
+#define SECCOMP_RET_KILL_THREAD_NAME	"kill_thread"
+#define SECCOMP_RET_TRAP_NAME		"trap"
+#define SECCOMP_RET_ERRNO_NAME		"errno"
+#define SECCOMP_RET_TRACE_NAME		"trace"
+#define SECCOMP_RET_LOG_NAME		"log"
+#define SECCOMP_RET_ALLOW_NAME		"allow"
+
+static const char seccomp_actions_avail[] =
+				SECCOMP_RET_KILL_PROCESS_NAME	" "
+				SECCOMP_RET_KILL_THREAD_NAME	" "
+				SECCOMP_RET_TRAP_NAME		" "
+				SECCOMP_RET_ERRNO_NAME		" "
+				SECCOMP_RET_TRACE_NAME		" "
+				SECCOMP_RET_LOG_NAME		" "
+				SECCOMP_RET_ALLOW_NAME;
+
+struct seccomp_log_name {
+	u32		log;
+	const char	*name;
+};
+
+static const struct seccomp_log_name seccomp_log_names[] = {
+	{ SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME },
+	{ SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME },
+	{ SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME },
+	{ SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME },
+	{ SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME },
+	{ SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME },
+	{ SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME },
+	{ }
+};
+
+static bool seccomp_names_from_actions_logged(char *names, size_t size,
+					      u32 actions_logged)
+{
+	const struct seccomp_log_name *cur;
+	bool append_space = false;
+
+	for (cur = seccomp_log_names; cur->name && size; cur++) {
+		ssize_t ret;
+
+		if (!(actions_logged & cur->log))
+			continue;
+
+		if (append_space) {
+			ret = strscpy(names, " ", size);
+			if (ret < 0)
+				return false;
+
+			names += ret;
+			size -= ret;
+		} else
+			append_space = true;
+
+		ret = strscpy(names, cur->name, size);
+		if (ret < 0)
+			return false;
+
+		names += ret;
+		size -= ret;
+	}
+
+	return true;
+}
+
+static bool seccomp_action_logged_from_name(u32 *action_logged,
+					    const char *name)
+{
+	const struct seccomp_log_name *cur;
+
+	for (cur = seccomp_log_names; cur->name; cur++) {
+		if (!strcmp(cur->name, name)) {
+			*action_logged = cur->log;
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names)
+{
+	char *name;
+
+	*actions_logged = 0;
+	while ((name = strsep(&names, " ")) && *name) {
+		u32 action_logged = 0;
+
+		if (!seccomp_action_logged_from_name(&action_logged, name))
+			return false;
+
+		*actions_logged |= action_logged;
+	}
+
+	return true;
+}
+
+static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write,
+					  void __user *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	char names[sizeof(seccomp_actions_avail)];
+	struct ctl_table table;
+	int ret;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	memset(names, 0, sizeof(names));
+
+	if (!write) {
+		if (!seccomp_names_from_actions_logged(names, sizeof(names),
+						       seccomp_actions_logged))
+			return -EINVAL;
+	}
+
+	table = *ro_table;
+	table.data = names;
+	table.maxlen = sizeof(names);
+	ret = proc_dostring(&table, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
+
+	if (write) {
+		u32 actions_logged;
+
+		if (!seccomp_actions_logged_from_names(&actions_logged,
+						       table.data))
+			return -EINVAL;
+
+		if (actions_logged & SECCOMP_LOG_ALLOW)
+			return -EINVAL;
+
+		seccomp_actions_logged = actions_logged;
+	}
+
+	return 0;
+}
+
+static struct ctl_path seccomp_sysctl_path[] = {
+	{ .procname = "kernel", },
+	{ .procname = "seccomp", },
+	{ }
+};
+
+static struct ctl_table seccomp_sysctl_table[] = {
+	{
+		.procname	= "actions_avail",
+		.data		= (void *) &seccomp_actions_avail,
+		.maxlen		= sizeof(seccomp_actions_avail),
+		.mode		= 0444,
+		.proc_handler	= proc_dostring,
+	},
+	{
+		.procname	= "actions_logged",
+		.mode		= 0644,
+		.proc_handler	= seccomp_actions_logged_handler,
+	},
+	{ }
+};
+
+static int __init seccomp_sysctl_init(void)
+{
+	struct ctl_table_header *hdr;
+
+	hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table);
+	if (!hdr)
+		pr_warn("seccomp: sysctl registration failed\n");
+	else
+		kmemleak_not_leak(hdr);
+
+	return 0;
+}
+
+device_initcall(seccomp_sysctl_init)
+
+#endif /* CONFIG_SYSCTL */
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 1d71c05..5043e74 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -344,39 +344,30 @@
  * by the client, but only by calling this function.
  * This function can only be called on a registered smp_hotplug_thread.
  */
-int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					 const struct cpumask *new)
+void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
+					  const struct cpumask *new)
 {
 	struct cpumask *old = plug_thread->cpumask;
-	cpumask_var_t tmp;
+	static struct cpumask tmp;
 	unsigned int cpu;
 
-	if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
-		return -ENOMEM;
-
-	get_online_cpus();
+	lockdep_assert_cpus_held();
 	mutex_lock(&smpboot_threads_lock);
 
 	/* Park threads that were exclusively enabled on the old mask. */
-	cpumask_andnot(tmp, old, new);
-	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+	cpumask_andnot(&tmp, old, new);
+	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
 		smpboot_park_thread(plug_thread, cpu);
 
 	/* Unpark threads that are exclusively enabled on the new mask. */
-	cpumask_andnot(tmp, new, old);
-	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+	cpumask_andnot(&tmp, new, old);
+	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
 		smpboot_unpark_thread(plug_thread, cpu);
 
 	cpumask_copy(old, new);
 
 	mutex_unlock(&smpboot_threads_lock);
-	put_online_cpus();
-
-	free_cpumask_var(tmp);
-
-	return 0;
 }
-EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread);
 
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6648fbb..d9c31bc 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -367,7 +367,8 @@
 		.data		= &sysctl_sched_time_avg,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
 	},
 #ifdef CONFIG_SCHEDSTATS
 	{
@@ -871,9 +872,9 @@
 #if defined(CONFIG_LOCKUP_DETECTOR)
 	{
 		.procname       = "watchdog",
-		.data           = &watchdog_user_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler   = proc_watchdog,
 		.extra1		= &zero,
 		.extra2		= &one,
@@ -889,16 +890,12 @@
 	},
 	{
 		.procname       = "nmi_watchdog",
-		.data           = &nmi_watchdog_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &nmi_watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= NMI_WATCHDOG_SYSCTL_PERM,
 		.proc_handler   = proc_nmi_watchdog,
 		.extra1		= &zero,
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
 		.extra2		= &one,
-#else
-		.extra2		= &zero,
-#endif
 	},
 	{
 		.procname	= "watchdog_cpumask",
@@ -910,9 +907,9 @@
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 	{
 		.procname       = "soft_watchdog",
-		.data           = &soft_watchdog_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &soft_watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler   = proc_soft_watchdog,
 		.extra1		= &zero,
 		.extra2		= &one,
@@ -2187,8 +2184,6 @@
 	if (write) {
 		if (*lvalp > UINT_MAX)
 			return -EINVAL;
-		if (*lvalp > UINT_MAX)
-			return -EINVAL;
 		*valp = *lvalp;
 	} else {
 		unsigned int val = *valp;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 2a685b4..45a3928 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -648,6 +648,12 @@
 }
 EXPORT_SYMBOL_GPL(blk_trace_startstop);
 
+/*
+ * When reading or writing the blktrace sysfs files, the references to the
+ * opened sysfs or device files should prevent the underlying block device
+ * from being removed. So no further delete protection is really needed.
+ */
+
 /**
  * blk_trace_ioctl: - handle the ioctls associated with tracing
  * @bdev:	the block device
@@ -665,7 +671,7 @@
 	if (!q)
 		return -ENXIO;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	switch (cmd) {
 	case BLKTRACESETUP:
@@ -691,7 +697,7 @@
 		break;
 	}
 
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 	return ret;
 }
 
@@ -1727,7 +1733,7 @@
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	if (attr == &dev_attr_enable) {
 		ret = sprintf(buf, "%u\n", !!q->blk_trace);
@@ -1746,7 +1752,7 @@
 		ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
 
 out_unlock_bdev:
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 out_bdput:
 	bdput(bdev);
 out:
@@ -1788,7 +1794,7 @@
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	if (attr == &dev_attr_enable) {
 		if (value)
@@ -1814,7 +1820,7 @@
 	}
 
 out_unlock_bdev:
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 out_bdput:
 	bdput(bdev);
 out:
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6abfafd..8319e09 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4954,9 +4954,6 @@
 static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
 static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer);
 
-static unsigned long save_global_trampoline;
-static unsigned long save_global_flags;
-
 static int __init set_graph_function(char *str)
 {
 	strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -6808,17 +6805,6 @@
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/*
-	 * Function graph does not allocate the trampoline, but
-	 * other global_ops do. We need to reset the ALLOC_TRAMP flag
-	 * if one was used.
-	 */
-	global_ops.trampoline = save_global_trampoline;
-	if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP)
-		global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
-#endif
-
  out:
 	mutex_unlock(&ftrace_lock);
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5360b7a..752e5da 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4020,11 +4020,17 @@
 	/* If this file was open for write, then erase contents */
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
 		int cpu = tracing_get_cpu(inode);
+		struct trace_buffer *trace_buf = &tr->trace_buffer;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+		if (tr->current_trace->print_max)
+			trace_buf = &tr->max_buffer;
+#endif
 
 		if (cpu == RING_BUFFER_ALL_CPUS)
-			tracing_reset_online_cpus(&tr->trace_buffer);
+			tracing_reset_online_cpus(trace_buf);
 		else
-			tracing_reset(&tr->trace_buffer, cpu);
+			tracing_reset(trace_buf, cpu);
 	}
 
 	if (file->f_mode & FMODE_READ) {
@@ -5358,6 +5364,13 @@
 	if (t == tr->current_trace)
 		goto out;
 
+	/* Some tracers won't work on kernel command line */
+	if (system_state < SYSTEM_RUNNING && t->noboot) {
+		pr_warn("Tracer '%s' is not allowed on command line, ignored\n",
+			t->name);
+		goto out;
+	}
+
 	/* Some tracers are only allowed for the top level buffer */
 	if (!trace_ok_for_array(t, tr)) {
 		ret = -EINVAL;
@@ -5667,7 +5680,7 @@
 		 *
 		 * iter->pos will be 0 if we haven't read anything.
 		 */
-		if (!tracing_is_on() && iter->pos)
+		if (!tracer_tracing_is_on(iter->tr) && iter->pos)
 			break;
 
 		mutex_unlock(&iter->mutex);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index fb5d54d..652c682 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -444,6 +444,8 @@
 #ifdef CONFIG_TRACER_MAX_TRACE
 	bool			use_max_tr;
 #endif
+	/* True if tracer cannot be enabled in kernel param */
+	bool			noboot;
 };
 
 
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index cd7480d..dca78fc 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -282,6 +282,7 @@
 	.close		= mmio_close,
 	.read		= mmio_read,
 	.print_line	= mmio_print_line,
+	.noboot		= true,
 };
 
 __init static int init_mmio_trace(void)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index bac629a..c738e76 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -656,15 +656,6 @@
 	return !trace_seq_has_overflowed(s);
 }
 
-static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
-
-static int task_state_char(unsigned long state)
-{
-	int bit = state ? __ffs(state) + 1 : 0;
-
-	return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
-}
-
 /**
  * ftrace_find_event - find a registered event
  * @type: the type of event to look for
@@ -930,8 +921,8 @@
 
 	trace_assign_type(field, iter->ent);
 
-	T = task_state_char(field->next_state);
-	S = task_state_char(field->prev_state);
+	T = __task_state_to_char(field->next_state);
+	S = __task_state_to_char(field->prev_state);
 	trace_find_cmdline(field->next_pid, comm);
 	trace_seq_printf(&iter->seq,
 			 " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
@@ -966,8 +957,8 @@
 	trace_assign_type(field, iter->ent);
 
 	if (!S)
-		S = task_state_char(field->prev_state);
-	T = task_state_char(field->next_state);
+		S = __task_state_to_char(field->prev_state);
+	T = __task_state_to_char(field->next_state);
 	trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
 			 field->prev_pid,
 			 field->prev_prio,
@@ -1002,8 +993,8 @@
 	trace_assign_type(field, iter->ent);
 
 	if (!S)
-		S = task_state_char(field->prev_state);
-	T = task_state_char(field->next_state);
+		S = __task_state_to_char(field->prev_state);
+	T = __task_state_to_char(field->next_state);
 
 	SEQ_PUT_HEX_FIELD(s, field->prev_pid);
 	SEQ_PUT_HEX_FIELD(s, field->prev_prio);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index ddec53b..0c33197 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -397,10 +397,10 @@
 	entry	= ring_buffer_event_data(event);
 	entry->prev_pid			= prev->pid;
 	entry->prev_prio		= prev->prio;
-	entry->prev_state		= prev->state;
+	entry->prev_state		= __get_task_state(prev);
 	entry->next_pid			= next->pid;
 	entry->next_prio		= next->prio;
-	entry->next_state		= next->state;
+	entry->next_state		= __get_task_state(next);
 	entry->next_cpu	= task_cpu(next);
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
@@ -425,10 +425,10 @@
 	entry	= ring_buffer_event_data(event);
 	entry->prev_pid			= curr->pid;
 	entry->prev_prio		= curr->prio;
-	entry->prev_state		= curr->state;
+	entry->prev_state		= __get_task_state(curr);
 	entry->next_pid			= wakee->pid;
 	entry->next_prio		= wakee->prio;
-	entry->next_state		= wakee->state;
+	entry->next_state		= __get_task_state(wakee);
 	entry->next_cpu			= task_cpu(wakee);
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index a4df67c..49cb414 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -96,23 +96,9 @@
 	if (in_nmi())
 		return;
 
-	/*
-	 * There's a slight chance that we are tracing inside the
-	 * RCU infrastructure, and rcu_irq_enter() will not work
-	 * as expected.
-	 */
-	if (unlikely(rcu_irq_enter_disabled()))
-		return;
-
 	local_irq_save(flags);
 	arch_spin_lock(&stack_trace_max_lock);
 
-	/*
-	 * RCU may not be watching, make it see us.
-	 * The stack trace code uses rcu_sched.
-	 */
-	rcu_irq_enter();
-
 	/* In case another CPU set the tracer_frame on us */
 	if (unlikely(!frame_size))
 		this_size -= tracer_frame;
@@ -205,7 +191,6 @@
 	}
 
  out:
-	rcu_irq_exit();
 	arch_spin_unlock(&stack_trace_max_lock);
 	local_irq_restore(flags);
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f5d5202..6bcb854 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,20 +29,29 @@
 #include <linux/kvm_para.h>
 #include <linux/kthread.h>
 
-/* Watchdog configuration */
-static DEFINE_MUTEX(watchdog_proc_mutex);
-
-int __read_mostly nmi_watchdog_enabled;
+static DEFINE_MUTEX(watchdog_mutex);
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED |
-						NMI_WATCHDOG_ENABLED;
+# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED)
+# define NMI_WATCHDOG_DEFAULT	1
 #else
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
+# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED)
+# define NMI_WATCHDOG_DEFAULT	0
 #endif
 
+unsigned long __read_mostly watchdog_enabled;
+int __read_mostly watchdog_user_enabled = 1;
+int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT;
+int __read_mostly soft_watchdog_user_enabled = 1;
+int __read_mostly watchdog_thresh = 10;
+int __read_mostly nmi_watchdog_available;
+
+struct cpumask watchdog_allowed_mask __read_mostly;
+
+struct cpumask watchdog_cpumask __read_mostly;
+unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
+
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
-/* boot commands */
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:
  */
@@ -56,9 +65,9 @@
  * kernel command line parameters are parsed, because otherwise it is not
  * possible to override this in hardlockup_panic_setup().
  */
-void hardlockup_detector_disable(void)
+void __init hardlockup_detector_disable(void)
 {
-	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+	nmi_watchdog_user_enabled = 0;
 }
 
 static int __init hardlockup_panic_setup(char *str)
@@ -68,48 +77,24 @@
 	else if (!strncmp(str, "nopanic", 7))
 		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
-		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+		nmi_watchdog_user_enabled = 0;
 	else if (!strncmp(str, "1", 1))
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+		nmi_watchdog_user_enabled = 1;
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
-#endif
-
-#ifdef CONFIG_SOFTLOCKUP_DETECTOR
-int __read_mostly soft_watchdog_enabled;
-#endif
-
-int __read_mostly watchdog_user_enabled;
-int __read_mostly watchdog_thresh = 10;
-
-#ifdef CONFIG_SMP
-int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+# ifdef CONFIG_SMP
 int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
-#endif
-struct cpumask watchdog_cpumask __read_mostly;
-unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
-/*
- * The 'watchdog_running' variable is set to 1 when the watchdog threads
- * are registered/started and is set to 0 when the watchdog threads are
- * unregistered/stopped, so it is an indicator whether the threads exist.
- */
-static int __read_mostly watchdog_running;
-/*
- * If a subsystem has a need to deactivate the watchdog temporarily, it
- * can use the suspend/resume interface to achieve this. The content of
- * the 'watchdog_suspended' variable reflects this state. Existing threads
- * are parked/unparked by the lockup_detector_{suspend|resume} functions
- * (see comment blocks pertaining to those functions for further details).
- *
- * 'watchdog_suspended' also prevents threads from being registered/started
- * or unregistered/stopped via parameters in /proc/sys/kernel, so the state
- * of 'watchdog_running' cannot change while the watchdog is deactivated
- * temporarily (see related code in 'proc' handlers).
- */
-int __read_mostly watchdog_suspended;
+static int __init hardlockup_all_cpu_backtrace_setup(char *str)
+{
+	sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
+	return 1;
+}
+__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
+# endif /* CONFIG_SMP */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /*
  * These functions can be overridden if an architecture implements its
@@ -121,36 +106,68 @@
  */
 int __weak watchdog_nmi_enable(unsigned int cpu)
 {
+	hardlockup_detector_perf_enable();
 	return 0;
 }
+
 void __weak watchdog_nmi_disable(unsigned int cpu)
 {
+	hardlockup_detector_perf_disable();
 }
 
-/*
- * watchdog_nmi_reconfigure can be implemented to be notified after any
- * watchdog configuration change. The arch hardlockup watchdog should
- * respond to the following variables:
- * - nmi_watchdog_enabled
+/* Return 0, if a NMI watchdog is available. Error code otherwise */
+int __weak __init watchdog_nmi_probe(void)
+{
+	return hardlockup_detector_perf_init();
+}
+
+/**
+ * watchdog_nmi_stop - Stop the watchdog for reconfiguration
+ *
+ * The reconfiguration steps are:
+ * watchdog_nmi_stop();
+ * update_variables();
+ * watchdog_nmi_start();
+ */
+void __weak watchdog_nmi_stop(void) { }
+
+/**
+ * watchdog_nmi_start - Start the watchdog after reconfiguration
+ *
+ * Counterpart to watchdog_nmi_stop().
+ *
+ * The following variables have been updated in update_variables() and
+ * contain the currently valid configuration:
+ * - watchdog_enabled
  * - watchdog_thresh
  * - watchdog_cpumask
- * - sysctl_hardlockup_all_cpu_backtrace
- * - hardlockup_panic
- * - watchdog_suspended
  */
-void __weak watchdog_nmi_reconfigure(void)
-{
-}
+void __weak watchdog_nmi_start(void) { }
 
+/**
+ * lockup_detector_update_enable - Update the sysctl enable bit
+ *
+ * Caller needs to make sure that the NMI/perf watchdogs are off, so this
+ * can't race with watchdog_nmi_disable().
+ */
+static void lockup_detector_update_enable(void)
+{
+	watchdog_enabled = 0;
+	if (!watchdog_user_enabled)
+		return;
+	if (nmi_watchdog_available && nmi_watchdog_user_enabled)
+		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+	if (soft_watchdog_user_enabled)
+		watchdog_enabled |= SOFT_WATCHDOG_ENABLED;
+}
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 
-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
-	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+/* Global variables, exported for sysctl */
+unsigned int __read_mostly softlockup_panic =
+			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
-atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
-
+static bool softlockup_threads_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -164,49 +181,39 @@
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
-unsigned int __read_mostly softlockup_panic =
-			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
-
 static int __init softlockup_panic_setup(char *str)
 {
 	softlockup_panic = simple_strtoul(str, NULL, 0);
-
 	return 1;
 }
 __setup("softlockup_panic=", softlockup_panic_setup);
 
 static int __init nowatchdog_setup(char *str)
 {
-	watchdog_enabled = 0;
+	watchdog_user_enabled = 0;
 	return 1;
 }
 __setup("nowatchdog", nowatchdog_setup);
 
 static int __init nosoftlockup_setup(char *str)
 {
-	watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED;
+	soft_watchdog_user_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);
 
 #ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+
 static int __init softlockup_all_cpu_backtrace_setup(char *str)
 {
-	sysctl_softlockup_all_cpu_backtrace =
-		!!simple_strtol(str, NULL, 0);
+	sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
 	return 1;
 }
 __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-static int __init hardlockup_all_cpu_backtrace_setup(char *str)
-{
-	sysctl_hardlockup_all_cpu_backtrace =
-		!!simple_strtol(str, NULL, 0);
-	return 1;
-}
-__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
 #endif
-#endif
+
+static void __lockup_detector_cleanup(void);
 
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -278,11 +285,15 @@
 	int cpu;
 
 	/*
-	 * this is done lockless
-	 * do we care if a 0 races with a timestamp?
-	 * all it means is the softlock check starts one cycle later
+	 * watchdog_mutex cannpt be taken here, as this might be called
+	 * from (soft)interrupt context, so the access to
+	 * watchdog_allowed_cpumask might race with a concurrent update.
+	 *
+	 * The watchdog time stamp can race against a concurrent real
+	 * update as well, the only side effect might be a cycle delay for
+	 * the softlockup check.
 	 */
-	for_each_watchdog_cpu(cpu)
+	for_each_cpu(cpu, &watchdog_allowed_mask)
 		per_cpu(watchdog_touch_ts, cpu) = 0;
 	wq_watchdog_touch(-1);
 }
@@ -322,9 +333,6 @@
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
-static int watchdog_enable_all_cpus(void);
-static void watchdog_disable_all_cpus(void);
-
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -333,7 +341,7 @@
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
-	if (atomic_read(&watchdog_park_in_progress) != 0)
+	if (!watchdog_enabled)
 		return HRTIMER_NORESTART;
 
 	/* kick the hardlockup detector */
@@ -447,32 +455,38 @@
 
 static void watchdog_enable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
-	/* kick off the timer for the hardlockup detector */
+	/*
+	 * Start the timer first to prevent the NMI watchdog triggering
+	 * before the timer has a chance to fire.
+	 */
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = watchdog_timer_fn;
-
-	/* Enable the perf event */
-	watchdog_nmi_enable(cpu);
-
-	/* done here because hrtimer_start can only pin to smp_processor_id() */
 	hrtimer_start(hrtimer, ns_to_ktime(sample_period),
 		      HRTIMER_MODE_REL_PINNED);
 
-	/* initialize timestamp */
-	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
+	/* Initialize timestamp */
 	__touch_watchdog();
+	/* Enable the perf event */
+	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
+		watchdog_nmi_enable(cpu);
+
+	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
 
 static void watchdog_disable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
 	watchdog_set_prio(SCHED_NORMAL, 0);
-	hrtimer_cancel(hrtimer);
-	/* disable the perf event */
+	/*
+	 * Disable the perf event first. That prevents that a large delay
+	 * between disabling the timer and disabling the perf event causes
+	 * the perf NMI to detect a false positive.
+	 */
 	watchdog_nmi_disable(cpu);
+	hrtimer_cancel(hrtimer);
 }
 
 static void watchdog_cleanup(unsigned int cpu, bool online)
@@ -499,21 +513,6 @@
 	__this_cpu_write(soft_lockup_hrtimer_cnt,
 			 __this_cpu_read(hrtimer_interrupts));
 	__touch_watchdog();
-
-	/*
-	 * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the
-	 * failure path. Check for failures that can occur asynchronously -
-	 * for example, when CPUs are on-lined - and shut down the hardware
-	 * perf event on each CPU accordingly.
-	 *
-	 * The only non-obvious place this bit can be cleared is through
-	 * watchdog_nmi_enable(), so a pr_info() is placed there.  Placing a
-	 * pr_info here would be too noisy as it would result in a message
-	 * every few seconds if the hardlockup was disabled but the softlockup
-	 * enabled.
-	 */
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		watchdog_nmi_disable(cpu);
 }
 
 static struct smp_hotplug_thread watchdog_threads = {
@@ -527,295 +526,174 @@
 	.unpark			= watchdog_enable,
 };
 
-/*
- * park all watchdog threads that are specified in 'watchdog_cpumask'
- *
- * This function returns an error if kthread_park() of a watchdog thread
- * fails. In this situation, the watchdog threads of some CPUs can already
- * be parked and the watchdog threads of other CPUs can still be runnable.
- * Callers are expected to handle this special condition as appropriate in
- * their context.
- *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
- */
-static int watchdog_park_threads(void)
+static void softlockup_update_smpboot_threads(void)
 {
-	int cpu, ret = 0;
+	lockdep_assert_held(&watchdog_mutex);
 
-	atomic_set(&watchdog_park_in_progress, 1);
+	if (!softlockup_threads_initialized)
+		return;
 
-	for_each_watchdog_cpu(cpu) {
-		ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
-		if (ret)
-			break;
-	}
+	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
+					     &watchdog_allowed_mask);
+}
 
-	atomic_set(&watchdog_park_in_progress, 0);
+/* Temporarily park all watchdog threads */
+static void softlockup_park_all_threads(void)
+{
+	cpumask_clear(&watchdog_allowed_mask);
+	softlockup_update_smpboot_threads();
+}
 
-	return ret;
+/* Unpark enabled threads */
+static void softlockup_unpark_threads(void)
+{
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	softlockup_update_smpboot_threads();
+}
+
+static void lockup_detector_reconfigure(void)
+{
+	cpus_read_lock();
+	watchdog_nmi_stop();
+	softlockup_park_all_threads();
+	set_sample_period();
+	lockup_detector_update_enable();
+	if (watchdog_enabled && watchdog_thresh)
+		softlockup_unpark_threads();
+	watchdog_nmi_start();
+	cpus_read_unlock();
+	/*
+	 * Must be called outside the cpus locked section to prevent
+	 * recursive locking in the perf code.
+	 */
+	__lockup_detector_cleanup();
 }
 
 /*
- * unpark all watchdog threads that are specified in 'watchdog_cpumask'
+ * Create the watchdog thread infrastructure and configure the detector(s).
  *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
+ * The threads are not unparked as watchdog_allowed_mask is empty.  When
+ * the threads are sucessfully initialized, take the proper locks and
+ * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
  */
-static void watchdog_unpark_threads(void)
-{
-	int cpu;
-
-	for_each_watchdog_cpu(cpu)
-		kthread_unpark(per_cpu(softlockup_watchdog, cpu));
-}
-
-static int update_watchdog_all_cpus(void)
+static __init void lockup_detector_setup(void)
 {
 	int ret;
 
-	ret = watchdog_park_threads();
-	if (ret)
-		return ret;
-
-	watchdog_unpark_threads();
-
-	return 0;
-}
-
-static int watchdog_enable_all_cpus(void)
-{
-	int err = 0;
-
-	if (!watchdog_running) {
-		err = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-							     &watchdog_cpumask);
-		if (err)
-			pr_err("Failed to create watchdog threads, disabled\n");
-		else
-			watchdog_running = 1;
-	} else {
-		/*
-		 * Enable/disable the lockup detectors or
-		 * change the sample period 'on the fly'.
-		 */
-		err = update_watchdog_all_cpus();
-
-		if (err) {
-			watchdog_disable_all_cpus();
-			pr_err("Failed to update lockup detectors, disabled\n");
-		}
-	}
-
-	if (err)
-		watchdog_enabled = 0;
-
-	return err;
-}
-
-static void watchdog_disable_all_cpus(void)
-{
-	if (watchdog_running) {
-		watchdog_running = 0;
-		smpboot_unregister_percpu_thread(&watchdog_threads);
-	}
-}
-
-#ifdef CONFIG_SYSCTL
-static int watchdog_update_cpus(void)
-{
-	return smpboot_update_cpumask_percpu_thread(
-		    &watchdog_threads, &watchdog_cpumask);
-}
-#endif
-
-#else /* SOFTLOCKUP */
-static int watchdog_park_threads(void)
-{
-	return 0;
-}
-
-static void watchdog_unpark_threads(void)
-{
-}
-
-static int watchdog_enable_all_cpus(void)
-{
-	return 0;
-}
-
-static void watchdog_disable_all_cpus(void)
-{
-}
-
-#ifdef CONFIG_SYSCTL
-static int watchdog_update_cpus(void)
-{
-	return 0;
-}
-#endif
-
-static void set_sample_period(void)
-{
-}
-#endif /* SOFTLOCKUP */
-
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
-	int ret = 0;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
 	/*
-	 * Multiple suspend requests can be active in parallel (counted by
-	 * the 'watchdog_suspended' variable). If the watchdog threads are
-	 * running, the first caller takes care that they will be parked.
-	 * The state of 'watchdog_running' cannot change while a suspend
-	 * request is active (see related code in 'proc' handlers).
+	 * If sysctl is off and watchdog got disabled on the command line,
+	 * nothing to do here.
 	 */
-	if (watchdog_running && !watchdog_suspended)
-		ret = watchdog_park_threads();
+	lockup_detector_update_enable();
 
-	if (ret == 0)
-		watchdog_suspended++;
-	else {
-		watchdog_disable_all_cpus();
-		pr_err("Failed to suspend lockup detectors, disabled\n");
-		watchdog_enabled = 0;
+	if (!IS_ENABLED(CONFIG_SYSCTL) &&
+	    !(watchdog_enabled && watchdog_thresh))
+		return;
+
+	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
+						     &watchdog_allowed_mask);
+	if (ret) {
+		pr_err("Failed to initialize soft lockup detector threads\n");
+		return;
 	}
 
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-
-	return ret;
+	mutex_lock(&watchdog_mutex);
+	softlockup_threads_initialized = true;
+	lockup_detector_reconfigure();
+	mutex_unlock(&watchdog_mutex);
 }
 
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
+static inline int watchdog_park_threads(void) { return 0; }
+static inline void watchdog_unpark_threads(void) { }
+static inline int watchdog_enable_all_cpus(void) { return 0; }
+static inline void watchdog_disable_all_cpus(void) { }
+static void lockup_detector_reconfigure(void)
 {
-	mutex_lock(&watchdog_proc_mutex);
+	cpus_read_lock();
+	watchdog_nmi_stop();
+	lockup_detector_update_enable();
+	watchdog_nmi_start();
+	cpus_read_unlock();
+}
+static inline void lockup_detector_setup(void)
+{
+	lockup_detector_reconfigure();
+}
+#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
-	watchdog_suspended--;
-	/*
-	 * The watchdog threads are unparked if they were previously running
-	 * and if there is no more active suspend request.
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		watchdog_unpark_threads();
+static void __lockup_detector_cleanup(void)
+{
+	lockdep_assert_held(&watchdog_mutex);
+	hardlockup_detector_perf_cleanup();
+}
 
-	watchdog_nmi_reconfigure();
+/**
+ * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes
+ *
+ * Caller must not hold the cpu hotplug rwsem.
+ */
+void lockup_detector_cleanup(void)
+{
+	mutex_lock(&watchdog_mutex);
+	__lockup_detector_cleanup();
+	mutex_unlock(&watchdog_mutex);
+}
 
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+/**
+ * lockup_detector_soft_poweroff - Interface to stop lockup detector(s)
+ *
+ * Special interface for parisc. It prevents lockup detector warnings from
+ * the default pm_poweroff() function which busy loops forever.
+ */
+void lockup_detector_soft_poweroff(void)
+{
+	watchdog_enabled = 0;
 }
 
 #ifdef CONFIG_SYSCTL
 
-/*
- * Update the run state of the lockup detectors.
- */
-static int proc_watchdog_update(void)
+/* Propagate any changes to the watchdog threads */
+static void proc_watchdog_update(void)
 {
-	int err = 0;
-
-	/*
-	 * Watchdog threads won't be started if they are already active.
-	 * The 'watchdog_running' variable in watchdog_*_all_cpus() takes
-	 * care of this. If those threads are already active, the sample
-	 * period will be updated and the lockup detectors will be enabled
-	 * or disabled 'on the fly'.
-	 */
-	if (watchdog_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
-	else
-		watchdog_disable_all_cpus();
-
-	watchdog_nmi_reconfigure();
-
-	return err;
-
+	/* Remove impossible cpus to keep sysctl output clean. */
+	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
+	lockup_detector_reconfigure();
 }
 
 /*
  * common function for watchdog, nmi_watchdog and soft_watchdog parameter
  *
- * caller             | table->data points to | 'which' contains the flag(s)
- * -------------------|-----------------------|-----------------------------
- * proc_watchdog      | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed
- *                    |                       | with SOFT_WATCHDOG_ENABLED
- * -------------------|-----------------------|-----------------------------
- * proc_nmi_watchdog  | nmi_watchdog_enabled  | NMI_WATCHDOG_ENABLED
- * -------------------|-----------------------|-----------------------------
- * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED
+ * caller             | table->data points to      | 'which'
+ * -------------------|----------------------------|--------------------------
+ * proc_watchdog      | watchdog_user_enabled      | NMI_WATCHDOG_ENABLED |
+ *                    |                            | SOFT_WATCHDOG_ENABLED
+ * -------------------|----------------------------|--------------------------
+ * proc_nmi_watchdog  | nmi_watchdog_user_enabled  | NMI_WATCHDOG_ENABLED
+ * -------------------|----------------------------|--------------------------
+ * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED
  */
 static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old, new;
-	int *watchdog_param = (int *)table->data;
+	int err, old, *param = table->data;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
+	mutex_lock(&watchdog_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
-	/*
-	 * If the parameter is being read return the state of the corresponding
-	 * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the
-	 * run state of the lockup detectors.
-	 */
 	if (!write) {
-		*watchdog_param = (watchdog_enabled & which) != 0;
+		/*
+		 * On read synchronize the userspace interface. This is a
+		 * racy snapshot.
+		 */
+		*param = (watchdog_enabled & which) != 0;
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	} else {
+		old = READ_ONCE(*param);
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-		if (err)
-			goto out;
-
-		/*
-		 * There is a race window between fetching the current value
-		 * from 'watchdog_enabled' and storing the new value. During
-		 * this race window, watchdog_nmi_enable() can sneak in and
-		 * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'.
-		 * The 'cmpxchg' detects this race and the loop retries.
-		 */
-		do {
-			old = watchdog_enabled;
-			/*
-			 * If the parameter value is not zero set the
-			 * corresponding bit(s), else clear it(them).
-			 */
-			if (*watchdog_param)
-				new = old | which;
-			else
-				new = old & ~which;
-		} while (cmpxchg(&watchdog_enabled, old, new) != old);
-
-		/*
-		 * Update the run state of the lockup detectors. There is _no_
-		 * need to check the value returned by proc_watchdog_update()
-		 * and to restore the previous value of 'watchdog_enabled' as
-		 * both lockup detectors are disabled if proc_watchdog_update()
-		 * returns an error.
-		 */
-		if (old == new)
-			goto out;
-
-		err = proc_watchdog_update();
+		if (!err && old != READ_ONCE(*param))
+			proc_watchdog_update();
 	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
 
@@ -835,6 +713,8 @@
 int proc_nmi_watchdog(struct ctl_table *table, int write,
 		      void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	if (!nmi_watchdog_available && write)
+		return -ENOTSUPP;
 	return proc_watchdog_common(NMI_WATCHDOG_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
@@ -855,39 +735,17 @@
 int proc_watchdog_thresh(struct ctl_table *table, int write,
 			 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old, new;
+	int err, old;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
+	mutex_lock(&watchdog_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
-	old = ACCESS_ONCE(watchdog_thresh);
+	old = READ_ONCE(watchdog_thresh);
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (err || !write)
-		goto out;
+	if (!err && write && old != READ_ONCE(watchdog_thresh))
+		proc_watchdog_update();
 
-	/*
-	 * Update the sample period. Restore on failure.
-	 */
-	new = ACCESS_ONCE(watchdog_thresh);
-	if (old == new)
-		goto out;
-
-	set_sample_period();
-	err = proc_watchdog_update();
-	if (err) {
-		watchdog_thresh = old;
-		set_sample_period();
-	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
 
@@ -902,45 +760,19 @@
 {
 	int err;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
+	mutex_lock(&watchdog_mutex);
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
-	if (!err && write) {
-		/* Remove impossible cpus to keep sysctl output cleaner. */
-		cpumask_and(&watchdog_cpumask, &watchdog_cpumask,
-			    cpu_possible_mask);
+	if (!err && write)
+		proc_watchdog_update();
 
-		if (watchdog_running) {
-			/*
-			 * Failure would be due to being unable to allocate
-			 * a temporary cpumask, so we are likely not in a
-			 * position to do much else to make things better.
-			 */
-			if (watchdog_update_cpus() != 0)
-				pr_err("cpumask update failed\n");
-		}
-
-		watchdog_nmi_reconfigure();
-	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
-
 #endif /* CONFIG_SYSCTL */
 
 void __init lockup_detector_init(void)
 {
-	set_sample_period();
-
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_enabled()) {
 		pr_info("Disabling watchdog on nohz_full cores by default\n");
@@ -951,6 +783,7 @@
 	cpumask_copy(&watchdog_cpumask, cpu_possible_mask);
 #endif
 
-	if (watchdog_enabled)
-		watchdog_enable_all_cpus();
+	if (!watchdog_nmi_probe())
+		nmi_watchdog_available = true;
+	lockup_detector_setup();
 }
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 3a09ea1..71a62ce 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -21,8 +21,10 @@
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
+static unsigned int watchdog_cpus;
 
 void arch_touch_nmi_watchdog(void)
 {
@@ -103,15 +105,12 @@
 
 /* Callback function for perf event subsystem */
 static void watchdog_overflow_callback(struct perf_event *event,
-		 struct perf_sample_data *data,
-		 struct pt_regs *regs)
+				       struct perf_sample_data *data,
+				       struct pt_regs *regs)
 {
 	/* Ensure the watchdog never gets throttled */
 	event->hw.interrupts = 0;
 
-	if (atomic_read(&watchdog_park_in_progress) != 0)
-		return;
-
 	if (__this_cpu_read(watchdog_nmi_touch) == true) {
 		__this_cpu_write(watchdog_nmi_touch, false);
 		return;
@@ -160,104 +159,131 @@
 	return;
 }
 
-/*
- * People like the simple clean cpu node info on boot.
- * Reduce the watchdog noise by only printing messages
- * that are different from what cpu0 displayed.
- */
-static unsigned long firstcpu_err;
-static atomic_t watchdog_cpus;
-
-int watchdog_nmi_enable(unsigned int cpu)
+static int hardlockup_detector_event_create(void)
 {
+	unsigned int cpu = smp_processor_id();
 	struct perf_event_attr *wd_attr;
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
-	int firstcpu = 0;
-
-	/* nothing to do if the hard lockup detector is disabled */
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		goto out;
-
-	/* is it already setup and enabled? */
-	if (event && event->state > PERF_EVENT_STATE_OFF)
-		goto out;
-
-	/* it is setup but not enabled */
-	if (event != NULL)
-		goto out_enable;
-
-	if (atomic_inc_return(&watchdog_cpus) == 1)
-		firstcpu = 1;
+	struct perf_event *evt;
 
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
 
 	/* Try to register using hardware perf events */
-	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
-
-	/* save the first cpu's error for future comparision */
-	if (firstcpu && IS_ERR(event))
-		firstcpu_err = PTR_ERR(event);
-
-	if (!IS_ERR(event)) {
-		/* only print for the first cpu initialized */
-		if (firstcpu || firstcpu_err)
-			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
-		goto out_save;
+	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
+					       watchdog_overflow_callback, NULL);
+	if (IS_ERR(evt)) {
+		pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
+			PTR_ERR(evt));
+		return PTR_ERR(evt);
 	}
-
-	/*
-	 * Disable the hard lockup detector if _any_ CPU fails to set up
-	 * set up the hardware perf event. The watchdog() function checks
-	 * the NMI_WATCHDOG_ENABLED bit periodically.
-	 *
-	 * The barriers are for syncing up watchdog_enabled across all the
-	 * cpus, as clear_bit() does not use barriers.
-	 */
-	smp_mb__before_atomic();
-	clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled);
-	smp_mb__after_atomic();
-
-	/* skip displaying the same error again */
-	if (!firstcpu && (PTR_ERR(event) == firstcpu_err))
-		return PTR_ERR(event);
-
-	/* vary the KERN level based on the returned errno */
-	if (PTR_ERR(event) == -EOPNOTSUPP)
-		pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
-	else if (PTR_ERR(event) == -ENOENT)
-		pr_warn("disabled (cpu%i): hardware events not enabled\n",
-			 cpu);
-	else
-		pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
-			cpu, PTR_ERR(event));
-
-	pr_info("Shutting down hard lockup detector on all cpus\n");
-
-	return PTR_ERR(event);
-
-	/* success path */
-out_save:
-	per_cpu(watchdog_ev, cpu) = event;
-out_enable:
-	perf_event_enable(per_cpu(watchdog_ev, cpu));
-out:
+	this_cpu_write(watchdog_ev, evt);
 	return 0;
 }
 
-void watchdog_nmi_disable(unsigned int cpu)
+/**
+ * hardlockup_detector_perf_enable - Enable the local event
+ */
+void hardlockup_detector_perf_enable(void)
 {
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+	if (hardlockup_detector_event_create())
+		return;
+
+	if (!watchdog_cpus++)
+		pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
+
+	perf_event_enable(this_cpu_read(watchdog_ev));
+}
+
+/**
+ * hardlockup_detector_perf_disable - Disable the local event
+ */
+void hardlockup_detector_perf_disable(void)
+{
+	struct perf_event *event = this_cpu_read(watchdog_ev);
 
 	if (event) {
 		perf_event_disable(event);
-		per_cpu(watchdog_ev, cpu) = NULL;
-
-		/* should be in cleanup, but blocks oprofile */
-		perf_event_release_kernel(event);
-
-		/* watchdog_nmi_enable() expects this to be zero initially. */
-		if (atomic_dec_and_test(&watchdog_cpus))
-			firstcpu_err = 0;
+		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
+		watchdog_cpus--;
 	}
 }
+
+/**
+ * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them
+ *
+ * Called from lockup_detector_cleanup(). Serialized by the caller.
+ */
+void hardlockup_detector_perf_cleanup(void)
+{
+	int cpu;
+
+	for_each_cpu(cpu, &dead_events_mask) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		/*
+		 * Required because for_each_cpu() reports  unconditionally
+		 * CPU0 as set on UP kernels. Sigh.
+		 */
+		if (event)
+			perf_event_release_kernel(event);
+		per_cpu(watchdog_ev, cpu) = NULL;
+	}
+	cpumask_clear(&dead_events_mask);
+}
+
+/**
+ * hardlockup_detector_perf_stop - Globally stop watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_stop(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_disable(event);
+	}
+}
+
+/**
+ * hardlockup_detector_perf_restart - Globally restart watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_restart(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return;
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_enable(event);
+	}
+}
+
+/**
+ * hardlockup_detector_perf_init - Probe whether NMI event is available at all
+ */
+int __init hardlockup_detector_perf_init(void)
+{
+	int ret = hardlockup_detector_event_create();
+
+	if (ret) {
+		pr_info("Perf NMI watchdog permanently disabled\n");
+	} else {
+		perf_event_release_kernel(this_cpu_read(watchdog_ev));
+		this_cpu_write(watchdog_ev, NULL);
+	}
+	return ret;
+}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 64d0edf..a2dccfe 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -68,6 +68,7 @@
 	 * attach_mutex to avoid changing binding state while
 	 * worker_attach_to_pool() is in progress.
 	 */
+	POOL_MANAGER_ACTIVE	= 1 << 0,	/* being managed */
 	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
 
 	/* worker flags */
@@ -165,7 +166,6 @@
 						/* L: hash of busy workers */
 
 	/* see manage_workers() for details on the two manager mutexes */
-	struct mutex		manager_arb;	/* manager arbitration */
 	struct worker		*manager;	/* L: purely informational */
 	struct mutex		attach_mutex;	/* attach/detach exclusion */
 	struct list_head	workers;	/* A: attached workers */
@@ -299,6 +299,7 @@
 
 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
 static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
+static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
 
 static LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
@@ -801,7 +802,7 @@
 /* Do we have too many workers and should some go away? */
 static bool too_many_workers(struct worker_pool *pool)
 {
-	bool managing = mutex_is_locked(&pool->manager_arb);
+	bool managing = pool->flags & POOL_MANAGER_ACTIVE;
 	int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
 	int nr_busy = pool->nr_workers - nr_idle;
 
@@ -1980,24 +1981,17 @@
 {
 	struct worker_pool *pool = worker->pool;
 
-	/*
-	 * Anyone who successfully grabs manager_arb wins the arbitration
-	 * and becomes the manager.  mutex_trylock() on pool->manager_arb
-	 * failure while holding pool->lock reliably indicates that someone
-	 * else is managing the pool and the worker which failed trylock
-	 * can proceed to executing work items.  This means that anyone
-	 * grabbing manager_arb is responsible for actually performing
-	 * manager duties.  If manager_arb is grabbed and released without
-	 * actual management, the pool may stall indefinitely.
-	 */
-	if (!mutex_trylock(&pool->manager_arb))
+	if (pool->flags & POOL_MANAGER_ACTIVE)
 		return false;
+
+	pool->flags |= POOL_MANAGER_ACTIVE;
 	pool->manager = worker;
 
 	maybe_create_worker(pool);
 
 	pool->manager = NULL;
-	mutex_unlock(&pool->manager_arb);
+	pool->flags &= ~POOL_MANAGER_ACTIVE;
+	wake_up(&wq_manager_wait);
 	return true;
 }
 
@@ -3248,7 +3242,6 @@
 	setup_timer(&pool->mayday_timer, pool_mayday_timeout,
 		    (unsigned long)pool);
 
-	mutex_init(&pool->manager_arb);
 	mutex_init(&pool->attach_mutex);
 	INIT_LIST_HEAD(&pool->workers);
 
@@ -3318,13 +3311,15 @@
 	hash_del(&pool->hash_node);
 
 	/*
-	 * Become the manager and destroy all workers.  Grabbing
-	 * manager_arb prevents @pool's workers from blocking on
-	 * attach_mutex.
+	 * Become the manager and destroy all workers.  This prevents
+	 * @pool's workers from blocking on attach_mutex.  We're the last
+	 * manager and @pool gets freed with the flag set.
 	 */
-	mutex_lock(&pool->manager_arb);
-
 	spin_lock_irq(&pool->lock);
+	wait_event_lock_irq(wq_manager_wait,
+			    !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock);
+	pool->flags |= POOL_MANAGER_ACTIVE;
+
 	while ((worker = first_idle_worker(pool)))
 		destroy_worker(worker);
 	WARN_ON(pool->nr_workers || pool->nr_idle);
@@ -3338,8 +3333,6 @@
 	if (pool->detach_completion)
 		wait_for_completion(pool->detach_completion);
 
-	mutex_unlock(&pool->manager_arb);
-
 	/* shut down the timers */
 	del_timer_sync(&pool->idle_timer);
 	del_timer_sync(&pool->mayday_timer);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b19c491..dfdad67 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -219,7 +219,8 @@
 	range 0 8192
 	default 0 if KASAN
 	default 2048 if GCC_PLUGIN_LATENT_ENTROPY
-	default 1024 if !64BIT
+	default 1280 if (!64BIT && PARISC)
+	default 1024 if (!64BIT && !PARISC)
 	default 2048 if 64BIT
 	help
 	  Tell gcc to warn at build time for stack frames larger than this.
@@ -1091,8 +1092,8 @@
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
 	select DEBUG_LOCK_ALLOC
-	select LOCKDEP_CROSSRELEASE
-	select LOCKDEP_COMPLETIONS
+	select LOCKDEP_CROSSRELEASE if BROKEN
+	select LOCKDEP_COMPLETIONS if BROKEN
 	select TRACE_IRQFLAGS
 	default n
 	help
@@ -1589,6 +1590,54 @@
 
 source kernel/trace/Kconfig
 
+config PROVIDE_OHCI1394_DMA_INIT
+	bool "Remote debugging over FireWire early on boot"
+	depends on PCI && X86
+	help
+	  If you want to debug problems which hang or crash the kernel early
+	  on boot and the crashing machine has a FireWire port, you can use
+	  this feature to remotely access the memory of the crashed machine
+	  over FireWire. This employs remote DMA as part of the OHCI1394
+	  specification which is now the standard for FireWire controllers.
+
+	  With remote DMA, you can monitor the printk buffer remotely using
+	  firescope and access all memory below 4GB using fireproxy from gdb.
+	  Even controlling a kernel debugger is possible using remote DMA.
+
+	  Usage:
+
+	  If ohci1394_dma=early is used as boot parameter, it will initialize
+	  all OHCI1394 controllers which are found in the PCI config space.
+
+	  As all changes to the FireWire bus such as enabling and disabling
+	  devices cause a bus reset and thereby disable remote DMA for all
+	  devices, be sure to have the cable plugged and FireWire enabled on
+	  the debugging host before booting the debug target for debugging.
+
+	  This code (~1k) is freed after boot. By then, the firewire stack
+	  in charge of the OHCI-1394 controllers should be used instead.
+
+	  See Documentation/debugging-via-ohci1394.txt for more information.
+
+config DMA_API_DEBUG
+	bool "Enable debugging of DMA-API usage"
+	depends on HAVE_DMA_API_DEBUG
+	help
+	  Enable this option to debug the use of the DMA API by device drivers.
+	  With this option you will be able to detect common bugs in device
+	  drivers like double-freeing of DMA mappings or freeing mappings that
+	  were never allocated.
+
+	  This also attempts to catch cases where a page owned by DMA is
+	  accessed by the cpu in a way that could cause data corruption.  For
+	  example, this enables cow_user_page() to check that the source page is
+	  not undergoing DMA.
+
+	  This option causes a performance degradation.  Use only if you want to
+	  debug device drivers and dma interactions.
+
+	  If unsure, say N.
+
 menu "Runtime Testing"
 
 config LKDTM
@@ -1748,56 +1797,6 @@
 
 	  If unsure, say N.
 
-endmenu # runtime tests
-
-config PROVIDE_OHCI1394_DMA_INIT
-	bool "Remote debugging over FireWire early on boot"
-	depends on PCI && X86
-	help
-	  If you want to debug problems which hang or crash the kernel early
-	  on boot and the crashing machine has a FireWire port, you can use
-	  this feature to remotely access the memory of the crashed machine
-	  over FireWire. This employs remote DMA as part of the OHCI1394
-	  specification which is now the standard for FireWire controllers.
-
-	  With remote DMA, you can monitor the printk buffer remotely using
-	  firescope and access all memory below 4GB using fireproxy from gdb.
-	  Even controlling a kernel debugger is possible using remote DMA.
-
-	  Usage:
-
-	  If ohci1394_dma=early is used as boot parameter, it will initialize
-	  all OHCI1394 controllers which are found in the PCI config space.
-
-	  As all changes to the FireWire bus such as enabling and disabling
-	  devices cause a bus reset and thereby disable remote DMA for all
-	  devices, be sure to have the cable plugged and FireWire enabled on
-	  the debugging host before booting the debug target for debugging.
-
-	  This code (~1k) is freed after boot. By then, the firewire stack
-	  in charge of the OHCI-1394 controllers should be used instead.
-
-	  See Documentation/debugging-via-ohci1394.txt for more information.
-
-config DMA_API_DEBUG
-	bool "Enable debugging of DMA-API usage"
-	depends on HAVE_DMA_API_DEBUG
-	help
-	  Enable this option to debug the use of the DMA API by device drivers.
-	  With this option you will be able to detect common bugs in device
-	  drivers like double-freeing of DMA mappings or freeing mappings that
-	  were never allocated.
-
-	  This also attempts to catch cases where a page owned by DMA is
-	  accessed by the cpu in a way that could cause data corruption.  For
-	  example, this enables cow_user_page() to check that the source page is
-	  not undergoing DMA.
-
-	  This option causes a performance degradation.  Use only if you want to
-	  debug device drivers and dma interactions.
-
-	  If unsure, say N.
-
 config TEST_LKM
 	tristate "Test module loading with 'hello world' module"
 	default n
@@ -1872,18 +1871,6 @@
 
 	  If unsure, say N.
 
-config MEMTEST
-	bool "Memtest"
-	depends on HAVE_MEMBLOCK
-	---help---
-	  This option adds a kernel parameter 'memtest', which allows memtest
-	  to be set.
-	        memtest=0, mean disabled; -- default
-	        memtest=1, mean do 1 test pattern;
-	        ...
-	        memtest=17, mean do 17 test patterns.
-	  If you are unsure how to answer this question, answer N.
-
 config TEST_STATIC_KEYS
 	tristate "Test static keys"
 	default n
@@ -1893,16 +1880,6 @@
 
 	  If unsure, say N.
 
-config BUG_ON_DATA_CORRUPTION
-	bool "Trigger a BUG when data corruption is detected"
-	select DEBUG_LIST
-	help
-	  Select this option if the kernel should BUG when it encounters
-	  data corruption in kernel memory structures when they get checked
-	  for validity.
-
-	  If unsure, say N.
-
 config TEST_KMOD
 	tristate "kmod stress tester"
 	default n
@@ -1940,6 +1917,29 @@
 
 	  If unsure, say N.
 
+endmenu # runtime tests
+
+config MEMTEST
+	bool "Memtest"
+	depends on HAVE_MEMBLOCK
+	---help---
+	  This option adds a kernel parameter 'memtest', which allows memtest
+	  to be set.
+	        memtest=0, mean disabled; -- default
+	        memtest=1, mean do 1 test pattern;
+	        ...
+	        memtest=17, mean do 17 test patterns.
+	  If you are unsure how to answer this question, answer N.
+
+config BUG_ON_DATA_CORRUPTION
+	bool "Trigger a BUG when data corruption is detected"
+	select DEBUG_LIST
+	help
+	  Select this option if the kernel should BUG when it encounters
+	  data corruption in kernel memory structures when they get checked
+	  for validity.
+
+	  If unsure, say N.
 
 source "samples/Kconfig"
 
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 155c55d..4e53be8 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -598,21 +598,31 @@
 		if ((edit->segment_cache[ASSOC_ARRAY_FAN_OUT] ^ base_seg) == 0)
 			goto all_leaves_cluster_together;
 
-		/* Otherwise we can just insert a new node ahead of the old
-		 * one.
+		/* Otherwise all the old leaves cluster in the same slot, but
+		 * the new leaf wants to go into a different slot - so we
+		 * create a new node (n0) to hold the new leaf and a pointer to
+		 * a new node (n1) holding all the old leaves.
+		 *
+		 * This can be done by falling through to the node splitting
+		 * path.
 		 */
-		goto present_leaves_cluster_but_not_new_leaf;
+		pr_devel("present leaves cluster but not new leaf\n");
 	}
 
 split_node:
 	pr_devel("split node\n");
 
-	/* We need to split the current node; we know that the node doesn't
-	 * simply contain a full set of leaves that cluster together (it
-	 * contains meta pointers and/or non-clustering leaves).
+	/* We need to split the current node.  The node must contain anything
+	 * from a single leaf (in the one leaf case, this leaf will cluster
+	 * with the new leaf) and the rest meta-pointers, to all leaves, some
+	 * of which may cluster.
+	 *
+	 * It won't contain the case in which all the current leaves plus the
+	 * new leaves want to cluster in the same slot.
 	 *
 	 * We need to expel at least two leaves out of a set consisting of the
-	 * leaves in the node and the new leaf.
+	 * leaves in the node and the new leaf.  The current meta pointers can
+	 * just be copied as they shouldn't cluster with any of the leaves.
 	 *
 	 * We need a new node (n0) to replace the current one and a new node to
 	 * take the expelled nodes (n1).
@@ -717,33 +727,6 @@
 	pr_devel("<--%s() = ok [split node]\n", __func__);
 	return true;
 
-present_leaves_cluster_but_not_new_leaf:
-	/* All the old leaves cluster in the same slot, but the new leaf wants
-	 * to go into a different slot, so we create a new node to hold the new
-	 * leaf and a pointer to a new node holding all the old leaves.
-	 */
-	pr_devel("present leaves cluster but not new leaf\n");
-
-	new_n0->back_pointer = node->back_pointer;
-	new_n0->parent_slot = node->parent_slot;
-	new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch;
-	new_n1->back_pointer = assoc_array_node_to_ptr(new_n0);
-	new_n1->parent_slot = edit->segment_cache[0];
-	new_n1->nr_leaves_on_branch = node->nr_leaves_on_branch;
-	edit->adjust_count_on = new_n0;
-
-	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++)
-		new_n1->slots[i] = node->slots[i];
-
-	new_n0->slots[edit->segment_cache[0]] = assoc_array_node_to_ptr(new_n0);
-	edit->leaf_p = &new_n0->slots[edit->segment_cache[ASSOC_ARRAY_FAN_OUT]];
-
-	edit->set[0].ptr = &assoc_array_ptr_to_node(node->back_pointer)->slots[node->parent_slot];
-	edit->set[0].to = assoc_array_node_to_ptr(new_n0);
-	edit->excised_meta[0] = assoc_array_node_to_ptr(node);
-	pr_devel("<--%s() = ok [insert node before]\n", __func__);
-	return true;
-
 all_leaves_cluster_together:
 	/* All the leaves, new and old, want to cluster together in this node
 	 * in the same slot, so we have to replace this node with a shortcut to
diff --git a/lib/digsig.c b/lib/digsig.c
index 03d7c63..6ba6fcd 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -87,6 +87,12 @@
 	down_read(&key->sem);
 	ukp = user_key_payload_locked(key);
 
+	if (!ukp) {
+		/* key was revoked before we acquired its semaphore */
+		err = -EKEYREVOKED;
+		goto err1;
+	}
+
 	if (ukp->datalen < sizeof(*pkh))
 		goto err1;
 
diff --git a/lib/idr.c b/lib/idr.c
index f9adf48..edd9b2b 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -146,8 +146,8 @@
  * idr_alloc() and idr_remove() (as long as the ID being removed is not
  * the one being replaced!).
  *
- * Returns: 0 on success.  %-ENOENT indicates that @id was not found.
- * %-EINVAL indicates that @id or @ptr were not valid.
+ * Returns: the old value on success.  %-ENOENT indicates that @id was not
+ * found.  %-EINVAL indicates that @id or @ptr were not valid.
  */
 void *idr_replace(struct idr *idr, void *ptr, int id)
 {
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 52c8dd6..1c1c06d 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -687,8 +687,10 @@
 
 static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
 {
-	size_t v = n + offset;
-	if (likely(n <= v && v <= (PAGE_SIZE << compound_order(page))))
+	struct page *head = compound_head(page);
+	size_t v = n + offset + page_address(page) - page_address(head);
+
+	if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head))))
 		return true;
 	WARN_ON(1);
 	return false;
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index e590523..f237a09 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -294,6 +294,26 @@
 }
 #endif
 
+static void zap_modalias_env(struct kobj_uevent_env *env)
+{
+	static const char modalias_prefix[] = "MODALIAS=";
+	int i;
+
+	for (i = 0; i < env->envp_idx;) {
+		if (strncmp(env->envp[i], modalias_prefix,
+			    sizeof(modalias_prefix) - 1)) {
+			i++;
+			continue;
+		}
+
+		if (i != env->envp_idx - 1)
+			memmove(&env->envp[i], &env->envp[i + 1],
+				sizeof(env->envp[i]) * env->envp_idx - 1);
+
+		env->envp_idx--;
+	}
+}
+
 /**
  * kobject_uevent_env - send an uevent with environmental data
  *
@@ -409,16 +429,29 @@
 		}
 	}
 
-	/*
-	 * Mark "add" and "remove" events in the object to ensure proper
-	 * events to userspace during automatic cleanup. If the object did
-	 * send an "add" event, "remove" will automatically generated by
-	 * the core, if not already done by the caller.
-	 */
-	if (action == KOBJ_ADD)
+	switch (action) {
+	case KOBJ_ADD:
+		/*
+		 * Mark "add" event so we can make sure we deliver "remove"
+		 * event to userspace during automatic cleanup. If
+		 * the object did send an "add" event, "remove" will
+		 * automatically generated by the core, if not already done
+		 * by the caller.
+		 */
 		kobj->state_add_uevent_sent = 1;
-	else if (action == KOBJ_REMOVE)
+		break;
+
+	case KOBJ_REMOVE:
 		kobj->state_remove_uevent_sent = 1;
+		break;
+
+	case KOBJ_UNBIND:
+		zap_modalias_env(env);
+		break;
+
+	default:
+		break;
+	}
 
 	mutex_lock(&uevent_sock_mutex);
 	/* we will send an event, so request a new sequence number */
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index cd0b5c9..2b827b8 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -2031,11 +2031,13 @@
 	print_testname("mixed read-lock/lock-write ABBA");
 	pr_cont("             |");
 	dotest(rlock_ABBA1, FAILURE, LOCKTYPE_RWLOCK);
+#ifdef CONFIG_PROVE_LOCKING
 	/*
 	 * Lockdep does indeed fail here, but there's nothing we can do about
 	 * that now.  Don't kill lockdep for it.
 	 */
 	unexpected_testcase_failures--;
+#endif
 
 	pr_cont("             |");
 	dotest(rwsem_ABBA1, FAILURE, LOCKTYPE_RWSEM);
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index bd35743..141734d 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -85,8 +85,8 @@
 	const BYTE * const lowLimit = lowPrefix - dictSize;
 
 	const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize;
-	const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };
-	const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 };
+	static const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };
+	static const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 };
 
 	const int safeDecode = (endOnInput == endOnInputSize);
 	const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB)));
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 08f8043..d01f471 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -48,7 +48,9 @@
 	if (time_is_before_jiffies(rs->begin + rs->interval)) {
 		if (rs->missed) {
 			if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) {
-				pr_warn("%s: %d callbacks suppressed\n", func, rs->missed);
+				printk_deferred(KERN_WARNING
+						"%s: %d callbacks suppressed\n",
+						func, rs->missed);
 				rs->missed = 0;
 			}
 		}
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 707ca5d..ddd7dde 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -735,9 +735,9 @@
  * rhashtable_walk_start - Start a hash table walk
  * @iter:	Hash table iterator
  *
- * Start a hash table walk.  Note that we take the RCU lock in all
- * cases including when we return an error.  So you must always call
- * rhashtable_walk_stop to clean up.
+ * Start a hash table walk at the current iterator position.  Note that we take
+ * the RCU lock in all cases including when we return an error.  So you must
+ * always call rhashtable_walk_stop to clean up.
  *
  * Returns zero if successful.
  *
@@ -846,7 +846,8 @@
  * rhashtable_walk_stop - Finish a hash table walk
  * @iter:	Hash table iterator
  *
- * Finish a hash table walk.
+ * Finish a hash table walk.  Does not reset the iterator to the start of the
+ * hash table.
  */
 void rhashtable_walk_stop(struct rhashtable_iter *iter)
 	__releases(RCU)
diff --git a/lib/ts_fsm.c b/lib/ts_fsm.c
index 5696a35..69557c7 100644
--- a/lib/ts_fsm.c
+++ b/lib/ts_fsm.c
@@ -11,7 +11,7 @@
  * ==========================================================================
  *
  *   A finite state machine consists of n states (struct ts_fsm_token)
- *   representing the pattern as a finite automation. The data is read
+ *   representing the pattern as a finite automaton. The data is read
  *   sequentially on an octet basis. Every state token specifies the number
  *   of recurrences and the type of value accepted which can be either a
  *   specific character or ctype based set of characters. The available
diff --git a/lib/ts_kmp.c b/lib/ts_kmp.c
index 632f783..ffbe66c 100644
--- a/lib/ts_kmp.c
+++ b/lib/ts_kmp.c
@@ -27,7 +27,7 @@
  *
  *   [1] Cormen, Leiserson, Rivest, Stein
  *       Introdcution to Algorithms, 2nd Edition, MIT Press
- *   [2] See finite automation theory
+ *   [2] See finite automaton theory
  */
 
 #include <linux/module.h>
diff --git a/mm/cma.c b/mm/cma.c
index c0da318..022e52b 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -460,7 +460,7 @@
 
 	trace_cma_alloc(pfn, page, count, align);
 
-	if (ret) {
+	if (ret && !(gfp_mask & __GFP_NOWARN)) {
 		pr_info("%s: alloc failed, req-size: %zu pages, ret: %d\n",
 			__func__, count, ret);
 		cma_debug_show_areas(cma);
diff --git a/mm/compaction.c b/mm/compaction.c
index fb548e4..03d31a8 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1999,17 +1999,14 @@
 	if (pgdat->kcompactd_max_order < order)
 		pgdat->kcompactd_max_order = order;
 
-	/*
-	 * Pairs with implicit barrier in wait_event_freezable()
-	 * such that wakeups are not missed in the lockless
-	 * waitqueue_active() call.
-	 */
-	smp_acquire__after_ctrl_dep();
-
 	if (pgdat->kcompactd_classzone_idx > classzone_idx)
 		pgdat->kcompactd_classzone_idx = classzone_idx;
 
-	if (!waitqueue_active(&pgdat->kcompactd_wait))
+	/*
+	 * Pairs with implicit barrier in wait_event_freezable()
+	 * such that wakeups are not missed.
+	 */
+	if (!wq_has_sleeper(&pgdat->kcompactd_wait))
 		return;
 
 	if (!kcompactd_node_suitable(pgdat))
diff --git a/mm/filemap.c b/mm/filemap.c
index 870971e..594d73f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -620,6 +620,14 @@
 		trace_file_check_and_advance_wb_err(file, old);
 		spin_unlock(&file->f_lock);
 	}
+
+	/*
+	 * We're mostly using this function as a drop in replacement for
+	 * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
+	 * that the legacy code would have had on these flags.
+	 */
+	clear_bit(AS_EIO, &mapping->flags);
+	clear_bit(AS_ENOSPC, &mapping->flags);
 	return err;
 }
 EXPORT_SYMBOL(file_check_and_advance_wb_err);
@@ -2926,9 +2934,15 @@
 	 * we're writing.  Either one is a pretty crazy thing to do,
 	 * so we don't support it 100%.  If this invalidation
 	 * fails, tough, the write still worked...
+	 *
+	 * Most of the time we do not need this since dio_complete() will do
+	 * the invalidation for us. However there are some file systems that
+	 * do not end up with dio_complete() being called, so let's not break
+	 * them by removing it completely
 	 */
-	invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT, end);
+	if (mapping->nrpages)
+		invalidate_inode_pages2_range(mapping,
+					pos >> PAGE_SHIFT, end);
 
 	if (written > 0) {
 		pos += written;
diff --git a/mm/ksm.c b/mm/ksm.c
index 15dd741..6cb60f4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1990,6 +1990,7 @@
  */
 static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 {
+	struct mm_struct *mm = rmap_item->mm;
 	struct rmap_item *tree_rmap_item;
 	struct page *tree_page = NULL;
 	struct stable_node *stable_node;
@@ -2062,9 +2063,11 @@
 	if (ksm_use_zero_pages && (checksum == zero_checksum)) {
 		struct vm_area_struct *vma;
 
-		vma = find_mergeable_vma(rmap_item->mm, rmap_item->address);
+		down_read(&mm->mmap_sem);
+		vma = find_mergeable_vma(mm, rmap_item->address);
 		err = try_to_merge_one_page(vma, page,
 					    ZERO_PAGE(rmap_item->address));
+		up_read(&mm->mmap_sem);
 		/*
 		 * In case of failure, the page was not really empty, so we
 		 * need to continue. Otherwise we're done.
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 7a40fa2..f141f0c 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -325,12 +325,12 @@
 {
 	int size = memcg_nr_cache_ids;
 
-	nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL);
+	nlru->memcg_lrus = kvmalloc(size * sizeof(void *), GFP_KERNEL);
 	if (!nlru->memcg_lrus)
 		return -ENOMEM;
 
 	if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) {
-		kfree(nlru->memcg_lrus);
+		kvfree(nlru->memcg_lrus);
 		return -ENOMEM;
 	}
 
@@ -340,7 +340,7 @@
 static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
 {
 	__memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids);
-	kfree(nlru->memcg_lrus);
+	kvfree(nlru->memcg_lrus);
 }
 
 static int memcg_update_list_lru_node(struct list_lru_node *nlru,
@@ -351,12 +351,12 @@
 	BUG_ON(old_size > new_size);
 
 	old = nlru->memcg_lrus;
-	new = kmalloc(new_size * sizeof(void *), GFP_KERNEL);
+	new = kvmalloc(new_size * sizeof(void *), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
 	if (__memcg_init_list_lru_node(new, old_size, new_size)) {
-		kfree(new);
+		kvfree(new);
 		return -ENOMEM;
 	}
 
@@ -373,7 +373,7 @@
 	nlru->memcg_lrus = new;
 	spin_unlock_irq(&nlru->lock);
 
-	kfree(old);
+	kvfree(old);
 	return 0;
 }
 
diff --git a/mm/madvise.c b/mm/madvise.c
index 21261ff..fd70d6a 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -625,18 +625,26 @@
 {
 	struct page *page;
 	struct zone *zone;
+	unsigned int order;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	for (; start < end; start += PAGE_SIZE <<
-				compound_order(compound_head(page))) {
+
+	for (; start < end; start += PAGE_SIZE << order) {
 		int ret;
 
 		ret = get_user_pages_fast(start, 1, 0, &page);
 		if (ret != 1)
 			return ret;
 
+		/*
+		 * When soft offlining hugepages, after migrating the page
+		 * we dissolve it, therefore in the second loop "page" will
+		 * no longer be a compound page, and order will be 0.
+		 */
+		order = compound_order(compound_head(page));
+
 		if (PageHWPoison(page)) {
 			put_page(page);
 			continue;
@@ -749,6 +757,9 @@
  *  MADV_DONTFORK - omit this area from child's address space when forking:
  *		typically, to avoid COWing pages pinned by get_user_pages().
  *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
+ *  MADV_WIPEONFORK - present the child process with zero-filled memory in this
+ *              range after a fork.
+ *  MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK
  *  MADV_HWPOISON - trigger memory error handler as if the given memory range
  *		were corrupted by unrecoverable hardware memory failure.
  *  MADV_SOFT_OFFLINE - try to soft-offline the given range of memory.
@@ -769,7 +780,9 @@
  *  zero    - success
  *  -EINVAL - start + len < 0, start is not page-aligned,
  *		"behavior" is not a valid value, or application
- *		is attempting to release locked or shared pages.
+ *		is attempting to release locked or shared pages,
+ *		or the specified address range includes file, Huge TLB,
+ *		MAP_SHARED or VMPFNMAP range.
  *  -ENOMEM - addresses in the specified range are not currently
  *		mapped, or are outside the AS of the process.
  *  -EIO    - an I/O error occurred while paging in data.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 15af3da..661f046 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1777,6 +1777,10 @@
 	struct memcg_stock_pcp *stock;
 	unsigned long flags;
 
+	/*
+	 * The only protection from memory hotplug vs. drain_stock races is
+	 * that we always operate on local CPU stock here with IRQ disabled
+	 */
 	local_irq_save(flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
@@ -1821,27 +1825,33 @@
 	/* If someone's already draining, avoid adding running more workers. */
 	if (!mutex_trylock(&percpu_charge_mutex))
 		return;
-	/* Notify other cpus that system-wide "drain" is running */
-	get_online_cpus();
+	/*
+	 * Notify other cpus that system-wide "drain" is running
+	 * We do not care about races with the cpu hotplug because cpu down
+	 * as well as workers from this path always operate on the local
+	 * per-cpu data. CPU up doesn't touch memcg_stock at all.
+	 */
 	curcpu = get_cpu();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *memcg;
 
 		memcg = stock->cached;
-		if (!memcg || !stock->nr_pages)
+		if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css))
 			continue;
-		if (!mem_cgroup_is_descendant(memcg, root_memcg))
+		if (!mem_cgroup_is_descendant(memcg, root_memcg)) {
+			css_put(&memcg->css);
 			continue;
+		}
 		if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
 			if (cpu == curcpu)
 				drain_local_stock(&stock->work);
 			else
 				schedule_work_on(cpu, &stock->work);
 		}
+		css_put(&memcg->css);
 	}
 	put_cpu();
-	put_online_cpus();
 	mutex_unlock(&percpu_charge_mutex);
 }
 
@@ -5648,7 +5658,8 @@
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 {
 	VM_BUG_ON_PAGE(PageLRU(page), page);
-	VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
+	VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) &&
+			!PageHWPoison(page) , page);
 
 	if (!page->mem_cgroup)
 		return;
@@ -5817,21 +5828,6 @@
 	if (!mem_cgroup_sockets_enabled)
 		return;
 
-	/*
-	 * Socket cloning can throw us here with sk_memcg already
-	 * filled. It won't however, necessarily happen from
-	 * process context. So the test for root memcg given
-	 * the current task's memcg won't help us in this case.
-	 *
-	 * Respecting the original socket's memcg is a better
-	 * decision in this case.
-	 */
-	if (sk->sk_memcg) {
-		BUG_ON(mem_cgroup_is_root(sk->sk_memcg));
-		css_get(&sk->sk_memcg->css);
-		return;
-	}
-
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);
 	if (memcg == root_mem_cgroup)
diff --git a/mm/memory.c b/mm/memory.c
index ec4e154..a728bed 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -845,7 +845,7 @@
 		 * vm_normal_page() so that we do not have to special case all
 		 * call site of vm_normal_page().
 		 */
-		if (likely(pfn < highest_memmap_pfn)) {
+		if (likely(pfn <= highest_memmap_pfn)) {
 			struct page *page = pfn_to_page(pfn);
 
 			if (is_device_public_page(page)) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e882cb6..d4b5f29 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -328,6 +328,7 @@
 		if (err && (err != -EEXIST))
 			break;
 		err = 0;
+		cond_resched();
 	}
 	vmemmap_populate_print_last();
 out:
@@ -337,7 +338,7 @@
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
-static int find_smallest_section_pfn(int nid, struct zone *zone,
+static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long start_pfn,
 				     unsigned long end_pfn)
 {
@@ -362,7 +363,7 @@
 }
 
 /* find the biggest valid pfn in the range [start_pfn, end_pfn). */
-static int find_biggest_section_pfn(int nid, struct zone *zone,
+static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 				    unsigned long start_pfn,
 				    unsigned long end_pfn)
 {
@@ -550,7 +551,7 @@
 		return ret;
 
 	scn_nr = __section_nr(ms);
-	start_pfn = section_nr_to_pfn(scn_nr);
+	start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
 	__remove_zone(zone, start_pfn);
 
 	sparse_remove_one_section(zone, ms, map_offset);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 006ba62..a2af6d5 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1920,8 +1920,11 @@
 	struct page *page;
 
 	page = __alloc_pages(gfp, order, nid);
-	if (page && page_to_nid(page) == nid)
-		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
+	if (page && page_to_nid(page) == nid) {
+		preempt_disable();
+		__inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT);
+		preempt_enable();
+	}
 	return page;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 6954c14..e00814c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2146,8 +2146,9 @@
 	unsigned long addr;
 
 	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
-		migrate->src[migrate->npages++] = MIGRATE_PFN_MIGRATE;
+		migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
 		migrate->dst[migrate->npages] = 0;
+		migrate->npages++;
 		migrate->cpages++;
 	}
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e0..dee0f75 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -40,6 +40,7 @@
 #include <linux/ratelimit.h>
 #include <linux/kthread.h>
 #include <linux/init.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlb.h>
 #include "internal.h"
@@ -495,6 +496,21 @@
 	}
 
 	/*
+	 * If the mm has notifiers then we would need to invalidate them around
+	 * unmap_page_range and that is risky because notifiers can sleep and
+	 * what they do is basically undeterministic.  So let's have a short
+	 * sleep to give the oom victim some more time.
+	 * TODO: we really want to get rid of this ugly hack and make sure that
+	 * notifiers cannot block for unbounded amount of time and add
+	 * mmu_notifier_invalidate_range_{start,end} around unmap_page_range
+	 */
+	if (mm_has_notifiers(mm)) {
+		up_read(&mm->mmap_sem);
+		schedule_timeout_idle(HZ);
+		goto unlock_oom;
+	}
+
+	/*
 	 * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
 	 * work on the mm anymore. The check for MMF_OOM_SKIP must run
 	 * under mmap_sem for reading because it serializes against the
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c841af8..77e4d3c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1190,7 +1190,7 @@
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void init_reserved_page(unsigned long pfn)
+static void __meminit init_reserved_page(unsigned long pfn)
 {
 	pg_data_t *pgdat;
 	int nid, zid;
@@ -5367,6 +5367,7 @@
 
 			__init_single_page(page, pfn, zone, nid);
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+			cond_resched();
 		} else {
 			__init_single_pfn(pfn, zone, nid);
 		}
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 6a03946..53afbb9 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -6,17 +6,6 @@
 
 #include "internal.h"
 
-static inline bool check_pmd(struct page_vma_mapped_walk *pvmw)
-{
-	pmd_t pmde;
-	/*
-	 * Make sure we don't re-load pmd between present and !trans_huge check.
-	 * We need a consistent view.
-	 */
-	pmde = READ_ONCE(*pvmw->pmd);
-	return pmd_present(pmde) && !pmd_trans_huge(pmde);
-}
-
 static inline bool not_found(struct page_vma_mapped_walk *pvmw)
 {
 	page_vma_mapped_walk_done(pvmw);
@@ -116,6 +105,7 @@
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
+	pmd_t pmde;
 
 	/* The only possible pmd mapping has been handled on last iteration */
 	if (pvmw->pmd && !pvmw->pte)
@@ -148,7 +138,13 @@
 	if (!pud_present(*pud))
 		return false;
 	pvmw->pmd = pmd_offset(pud, pvmw->address);
-	if (pmd_trans_huge(*pvmw->pmd) || is_pmd_migration_entry(*pvmw->pmd)) {
+	/*
+	 * Make sure the pmd value isn't cached in a register by the
+	 * compiler and used as a stale value after we've observed a
+	 * subsequent update.
+	 */
+	pmde = READ_ONCE(*pvmw->pmd);
+	if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
 		pvmw->ptl = pmd_lock(mm, pvmw->pmd);
 		if (likely(pmd_trans_huge(*pvmw->pmd))) {
 			if (pvmw->flags & PVMW_MIGRATION)
@@ -167,17 +163,15 @@
 						return not_found(pvmw);
 					return true;
 				}
-			} else
-				WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");
+			}
 			return not_found(pvmw);
 		} else {
 			/* THP pmd was split under us: handle on pte level */
 			spin_unlock(pvmw->ptl);
 			pvmw->ptl = NULL;
 		}
-	} else {
-		if (!check_pmd(pvmw))
-			return false;
+	} else if (!pmd_present(pmde)) {
+		return false;
 	}
 	if (!map_pte(pvmw))
 		goto next_pte;
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index 6142484..7a58460 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -73,7 +73,7 @@
 		     last_alloc + 1 : 0;
 
 	as_len = 0;
-	start = chunk->start_offset;
+	start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE;
 
 	/*
 	 * If a bit is set in the allocation map, the bound_map identifies
diff --git a/mm/percpu.c b/mm/percpu.c
index 59d44d6..a0e0c82 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -353,6 +353,8 @@
 					block->contig_hint_start);
 			return;
 		}
+		/* reset to satisfy the second predicate above */
+		block_off = 0;
 
 		*bits = block->right_free;
 		*bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free;
@@ -407,6 +409,8 @@
 			*bit_off = pcpu_block_off_to_off(i, block->first_free);
 			return;
 		}
+		/* reset to satisfy the second predicate above */
+		block_off = 0;
 
 		*bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free,
 				 align);
@@ -1325,7 +1329,9 @@
  * @gfp: allocation flags
  *
  * Allocate percpu area of @size bytes aligned at @align.  If @gfp doesn't
- * contain %GFP_KERNEL, the allocation is atomic.
+ * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN
+ * then no warning will be triggered on invalid or failed allocation
+ * requests.
  *
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
@@ -1333,10 +1339,11 @@
 static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
+	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+	bool do_warn = !(gfp & __GFP_NOWARN);
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk;
 	const char *err;
-	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
 	int slot, off, cpu, ret;
 	unsigned long flags;
 	void __percpu *ptr;
@@ -1357,7 +1364,7 @@
 
 	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE ||
 		     !is_power_of_2(align))) {
-		WARN(true, "illegal size (%zu) or align (%zu) for percpu allocation\n",
+		WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n",
 		     size, align);
 		return NULL;
 	}
@@ -1478,7 +1485,7 @@
 fail:
 	trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);
 
-	if (!is_atomic && warn_limit) {
+	if (!is_atomic && do_warn && warn_limit) {
 		pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
 			size, align, is_atomic, err);
 		dump_stack();
@@ -1503,7 +1510,9 @@
  *
  * Allocate zero-filled percpu area of @size bytes aligned at @align.  If
  * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
- * be called from any context but is a lot more likely to fail.
+ * be called from any context but is a lot more likely to fail. If @gfp
+ * has __GFP_NOWARN then no warning will be triggered on invalid or failed
+ * allocation requests.
  *
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
diff --git a/mm/rodata_test.c b/mm/rodata_test.c
index 6bb4deb..d908c87 100644
--- a/mm/rodata_test.c
+++ b/mm/rodata_test.c
@@ -14,7 +14,7 @@
 #include <linux/uaccess.h>
 #include <asm/sections.h>
 
-const int rodata_test_data = 0xC3;
+static const int rodata_test_data = 0xC3;
 
 void rodata_test(void)
 {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83b..8016459 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -165,9 +165,9 @@
 	if (!memcg_nr_cache_ids)
 		return 0;
 
-	arr = kzalloc(sizeof(struct memcg_cache_array) +
-		      memcg_nr_cache_ids * sizeof(void *),
-		      GFP_KERNEL);
+	arr = kvzalloc(sizeof(struct memcg_cache_array) +
+		       memcg_nr_cache_ids * sizeof(void *),
+		       GFP_KERNEL);
 	if (!arr)
 		return -ENOMEM;
 
@@ -178,15 +178,23 @@
 static void destroy_memcg_params(struct kmem_cache *s)
 {
 	if (is_root_cache(s))
-		kfree(rcu_access_pointer(s->memcg_params.memcg_caches));
+		kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
+}
+
+static void free_memcg_params(struct rcu_head *rcu)
+{
+	struct memcg_cache_array *old;
+
+	old = container_of(rcu, struct memcg_cache_array, rcu);
+	kvfree(old);
 }
 
 static int update_memcg_params(struct kmem_cache *s, int new_array_size)
 {
 	struct memcg_cache_array *old, *new;
 
-	new = kzalloc(sizeof(struct memcg_cache_array) +
-		      new_array_size * sizeof(void *), GFP_KERNEL);
+	new = kvzalloc(sizeof(struct memcg_cache_array) +
+		       new_array_size * sizeof(void *), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -198,7 +206,7 @@
 
 	rcu_assign_pointer(s->memcg_params.memcg_caches, new);
 	if (old)
-		kfree_rcu(old, rcu);
+		call_rcu(&old->rcu, free_memcg_params);
 	return 0;
 }
 
diff --git a/mm/swap.c b/mm/swap.c
index 9295ae9..a77d68f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -575,7 +575,7 @@
 			    void *arg)
 {
 	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
-	    !PageUnevictable(page)) {
+	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		bool active = PageActive(page);
 
 		del_page_from_lru_list(page, lruvec,
@@ -665,7 +665,7 @@
 void mark_page_lazyfree(struct page *page)
 {
 	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
-	    !PageUnevictable(page)) {
+	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs);
 
 		get_page(page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 71ce2d1..05b6803 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -39,10 +39,6 @@
 static unsigned int nr_swapper_spaces[MAX_SWAPFILES];
 bool swap_vma_readahead = true;
 
-#define SWAP_RA_MAX_ORDER_DEFAULT	3
-
-static int swap_ra_max_order = SWAP_RA_MAX_ORDER_DEFAULT;
-
 #define SWAP_RA_WIN_SHIFT	(PAGE_SHIFT / 2)
 #define SWAP_RA_HITS_MASK	((1UL << SWAP_RA_WIN_SHIFT) - 1)
 #define SWAP_RA_HITS_MAX	SWAP_RA_HITS_MASK
@@ -242,6 +238,17 @@
 		 * clear SWAP_HAS_CACHE flag.
 		 */
 		goto fail;
+	/*
+	 * Normally the page will be dirtied in unmap because its pte should be
+	 * dirty. A special case is MADV_FREE page. The page'e pte could have
+	 * dirty bit cleared but the page's SwapBacked bit is still set because
+	 * clearing the dirty bit and SwapBacked bit has no lock protected. For
+	 * such page, unmap will not set dirty bit for it, so page reclaim will
+	 * not write the page out. This can cause data corruption when the page
+	 * is swap in later. Always setting the dirty bit for the page solves
+	 * the problem.
+	 */
+	set_page_dirty(page);
 
 	return 1;
 
@@ -653,6 +660,13 @@
 	pte_t *tpte;
 #endif
 
+	max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster),
+			     SWAP_RA_ORDER_CEILING);
+	if (max_win == 1) {
+		swap_ra->win = 1;
+		return NULL;
+	}
+
 	faddr = vmf->address;
 	entry = pte_to_swp_entry(vmf->orig_pte);
 	if ((unlikely(non_swap_entry(entry))))
@@ -661,12 +675,6 @@
 	if (page)
 		return page;
 
-	max_win = 1 << READ_ONCE(swap_ra_max_order);
-	if (max_win == 1) {
-		swap_ra->win = 1;
-		return NULL;
-	}
-
 	fpfn = PFN_DOWN(faddr);
 	swap_ra_info = GET_SWAP_RA_VAL(vma);
 	pfn = PFN_DOWN(SWAP_RA_ADDR(swap_ra_info));
@@ -775,32 +783,8 @@
 	__ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show,
 	       vma_ra_enabled_store);
 
-static ssize_t vma_ra_max_order_show(struct kobject *kobj,
-				     struct kobj_attribute *attr, char *buf)
-{
-	return sprintf(buf, "%d\n", swap_ra_max_order);
-}
-static ssize_t vma_ra_max_order_store(struct kobject *kobj,
-				      struct kobj_attribute *attr,
-				      const char *buf, size_t count)
-{
-	int err, v;
-
-	err = kstrtoint(buf, 10, &v);
-	if (err || v > SWAP_RA_ORDER_CEILING || v <= 0)
-		return -EINVAL;
-
-	swap_ra_max_order = v;
-
-	return count;
-}
-static struct kobj_attribute vma_ra_max_order_attr =
-	__ATTR(vma_ra_max_order, 0644, vma_ra_max_order_show,
-	       vma_ra_max_order_store);
-
 static struct attribute *swap_attrs[] = {
 	&vma_ra_enabled_attr.attr,
-	&vma_ra_max_order_attr.attr,
 	NULL,
 };
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 8a43db6..6739420 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1695,11 +1695,6 @@
 	for (i = 0; i < area->nr_pages; i++) {
 		struct page *page;
 
-		if (fatal_signal_pending(current)) {
-			area->nr_pages = i;
-			goto fail_no_warn;
-		}
-
 		if (node == NUMA_NO_NODE)
 			page = alloc_page(alloc_mask|highmem_mask);
 		else
@@ -1723,7 +1718,6 @@
 	warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure, allocated %ld of %ld bytes",
 			  (area->nr_pages*PAGE_SIZE), area->size);
-fail_no_warn:
 	vfree(area->addr);
 	return NULL;
 }
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 486550d..b2ba2ba 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -250,6 +250,7 @@
 
 	WARN_ON(!list_empty(&zhdr->buddy));
 	set_bit(PAGE_STALE, &page->private);
+	clear_bit(NEEDS_COMPACTING, &page->private);
 	spin_lock(&pool->lock);
 	if (!list_empty(&page->lru))
 		list_del(&page->lru);
@@ -303,7 +304,6 @@
 		list_del(&zhdr->buddy);
 		if (WARN_ON(!test_bit(PAGE_STALE, &page->private)))
 			continue;
-		clear_bit(NEEDS_COMPACTING, &page->private);
 		spin_unlock(&pool->stale_lock);
 		cancel_work_sync(&zhdr->work);
 		free_z3fold_page(page);
@@ -624,10 +624,8 @@
 	 * stale pages list. cancel_work_sync() can sleep so we must make
 	 * sure it won't be called in case we're in atomic context.
 	 */
-	if (zhdr && (can_sleep || !work_pending(&zhdr->work) ||
-	    !unlikely(work_busy(&zhdr->work)))) {
+	if (zhdr && (can_sleep || !work_pending(&zhdr->work))) {
 		list_del(&zhdr->buddy);
-		clear_bit(NEEDS_COMPACTING, &page->private);
 		spin_unlock(&pool->stale_lock);
 		if (can_sleep)
 			cancel_work_sync(&zhdr->work);
@@ -875,16 +873,18 @@
 				goto next;
 		}
 next:
+		spin_lock(&pool->lock);
 		if (test_bit(PAGE_HEADLESS, &page->private)) {
 			if (ret == 0) {
+				spin_unlock(&pool->lock);
 				free_z3fold_page(page);
 				return 0;
 			}
 		} else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
 			atomic64_dec(&pool->pages_nr);
+			spin_unlock(&pool->lock);
 			return 0;
 		}
-		spin_lock(&pool->lock);
 
 		/*
 		 * Add to the beginning of LRU.
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index e2ed698..0bc31de 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -21,6 +21,12 @@
 	if (unlikely(!skb))
 		return false;
 
+	if (unlikely(!(vlan_dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		*skbp = NULL;
+		return false;
+	}
+
 	skb->dev = vlan_dev;
 	if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
 		/* Our lower layer thinks this is not local, let's make sure.
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index c18115d..db82a40 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -126,14 +126,4 @@
 	  Provide extensive information about internal Bluetooth states
 	  in debugfs.
 
-config BT_LEGACY_IOCTL
-	bool "Enable legacy ioctl interfaces"
-	depends on BT && BT_BREDR
-	default y
-	help
-	  Enable support for legacy ioctl interfaces.  This is only needed
-	  for old and deprecated applications using direct ioctl calls for
-	  controller management.  Since Linux 3.4 all configuration and
-	  setup is done via mgmt interface and this is no longer needed.
-
 source "drivers/bluetooth/Kconfig"
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 0bad296..65d734c 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -878,7 +878,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_BT_LEGACY_IOCTL
 static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg)
 {
 	bdaddr_t bdaddr;
@@ -1050,7 +1049,6 @@
 	release_sock(sk);
 	return err;
 }
-#endif
 
 static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
 			 int addr_len)
@@ -1971,11 +1969,7 @@
 	.getname	= hci_sock_getname,
 	.sendmsg	= hci_sock_sendmsg,
 	.recvmsg	= hci_sock_recvmsg,
-#ifdef CONFIG_BT_LEGACY_IOCTL
 	.ioctl		= hci_sock_ioctl,
-#else
-	.ioctl		= sock_no_ioctl,
-#endif
 	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 3bc8907..de21527 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -573,7 +573,7 @@
 		}
 		*vinfo_last = NULL;
 
-		return 0;
+		return err;
 	}
 
 	return br_vlan_info(br, p, cmd, vinfo_curr);
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 2585b10..276b602 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -65,8 +65,8 @@
 
 static int __net_init broute_net_init(struct net *net)
 {
-	net->xt.broute_table = ebt_register_table(net, &broute_table, NULL);
-	return PTR_ERR_OR_ZERO(net->xt.broute_table);
+	return ebt_register_table(net, &broute_table, NULL,
+				  &net->xt.broute_table);
 }
 
 static void __net_exit broute_net_exit(struct net *net)
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 45a00db..c41da5f 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -93,8 +93,8 @@
 
 static int __net_init frame_filter_net_init(struct net *net)
 {
-	net->xt.frame_filter = ebt_register_table(net, &frame_filter, ebt_ops_filter);
-	return PTR_ERR_OR_ZERO(net->xt.frame_filter);
+	return ebt_register_table(net, &frame_filter, ebt_ops_filter,
+				  &net->xt.frame_filter);
 }
 
 static void __net_exit frame_filter_net_exit(struct net *net)
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 57cd5bb..08df740 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -93,8 +93,8 @@
 
 static int __net_init frame_nat_net_init(struct net *net)
 {
-	net->xt.frame_nat = ebt_register_table(net, &frame_nat, ebt_ops_nat);
-	return PTR_ERR_OR_ZERO(net->xt.frame_nat);
+	return ebt_register_table(net, &frame_nat, ebt_ops_nat,
+				  &net->xt.frame_nat);
 }
 
 static void __net_exit frame_nat_net_exit(struct net *net)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 83951f9..3b3dcf7 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1169,9 +1169,8 @@
 	kfree(table);
 }
 
-struct ebt_table *
-ebt_register_table(struct net *net, const struct ebt_table *input_table,
-		   const struct nf_hook_ops *ops)
+int ebt_register_table(struct net *net, const struct ebt_table *input_table,
+		       const struct nf_hook_ops *ops, struct ebt_table **res)
 {
 	struct ebt_table_info *newinfo;
 	struct ebt_table *t, *table;
@@ -1183,7 +1182,7 @@
 	    repl->entries == NULL || repl->entries_size == 0 ||
 	    repl->counters != NULL || input_table->private != NULL) {
 		BUGPRINT("Bad table data for ebt_register_table!!!\n");
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	}
 
 	/* Don't add one table to multiple lists. */
@@ -1252,16 +1251,18 @@
 	list_add(&table->list, &net->xt.tables[NFPROTO_BRIDGE]);
 	mutex_unlock(&ebt_mutex);
 
+	WRITE_ONCE(*res, table);
+
 	if (!ops)
-		return table;
+		return 0;
 
 	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
 	if (ret) {
 		__ebt_unregister_table(net, table);
-		return ERR_PTR(ret);
+		*res = NULL;
 	}
 
-	return table;
+	return ret;
 free_unlock:
 	mutex_unlock(&ebt_mutex);
 free_chainstack:
@@ -1276,7 +1277,7 @@
 free_table:
 	kfree(table);
 out:
-	return ERR_PTR(ret);
+	return ret;
 }
 
 void ebt_unregister_table(struct net *net, struct ebt_table *table,
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 88edac0..ecd5c70 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -78,7 +78,7 @@
 static struct kmem_cache *rcv_cache __read_mostly;
 
 /* table of registered CAN protocols */
-static const struct can_proto *proto_tab[CAN_NPROTO] __read_mostly;
+static const struct can_proto __rcu *proto_tab[CAN_NPROTO] __read_mostly;
 static DEFINE_MUTEX(proto_tab_lock);
 
 static atomic_t skbcounter = ATOMIC_INIT(0);
@@ -788,7 +788,7 @@
 
 	mutex_lock(&proto_tab_lock);
 
-	if (proto_tab[proto]) {
+	if (rcu_access_pointer(proto_tab[proto])) {
 		pr_err("can: protocol %d already registered\n", proto);
 		err = -EBUSY;
 	} else
@@ -812,7 +812,7 @@
 	int proto = cp->protocol;
 
 	mutex_lock(&proto_tab_lock);
-	BUG_ON(proto_tab[proto] != cp);
+	BUG_ON(rcu_access_pointer(proto_tab[proto]) != cp);
 	RCU_INIT_POINTER(proto_tab[proto], NULL);
 	mutex_unlock(&proto_tab_lock);
 
@@ -875,9 +875,14 @@
 	spin_lock_init(&net->can.can_rcvlists_lock);
 	net->can.can_rx_alldev_list =
 		kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL);
-
+	if (!net->can.can_rx_alldev_list)
+		goto out;
 	net->can.can_stats = kzalloc(sizeof(struct s_stats), GFP_KERNEL);
+	if (!net->can.can_stats)
+		goto out_free_alldev_list;
 	net->can.can_pstats = kzalloc(sizeof(struct s_pstats), GFP_KERNEL);
+	if (!net->can.can_pstats)
+		goto out_free_can_stats;
 
 	if (IS_ENABLED(CONFIG_PROC_FS)) {
 		/* the statistics are updated every second (timer triggered) */
@@ -892,6 +897,13 @@
 	}
 
 	return 0;
+
+ out_free_can_stats:
+	kfree(net->can.can_stats);
+ out_free_alldev_list:
+	kfree(net->can.can_rx_alldev_list);
+ out:
+	return -ENOMEM;
 }
 
 static void can_pernet_exit(struct net *net)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 47a8748d..13690334 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1493,13 +1493,14 @@
 static int bcm_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-	struct net *net = sock_net(sk);
+	struct net *net;
 	struct bcm_sock *bo;
 	struct bcm_op *op, *next;
 
-	if (sk == NULL)
+	if (!sk)
 		return 0;
 
+	net = sock_net(sk);
 	bo = bcm_sk(sk);
 
 	/* remove bcm_ops, timer, rx_unregister(), etc. */
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index f358d0b..79d14d7 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -2445,19 +2445,34 @@
 
 	pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid);
 	if (pg) {
-		for (i = 0; i < raw->size; i++) {
-			for (j = 0; j < pg->pg_upmap_items.len; j++) {
-				int from = pg->pg_upmap_items.from_to[j][0];
-				int to = pg->pg_upmap_items.from_to[j][1];
+		/*
+		 * Note: this approach does not allow a bidirectional swap,
+		 * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1].
+		 */
+		for (i = 0; i < pg->pg_upmap_items.len; i++) {
+			int from = pg->pg_upmap_items.from_to[i][0];
+			int to = pg->pg_upmap_items.from_to[i][1];
+			int pos = -1;
+			bool exists = false;
 
-				if (from == raw->osds[i]) {
-					if (!(to != CRUSH_ITEM_NONE &&
-					      to < osdmap->max_osd &&
-					      osdmap->osd_weight[to] == 0))
-						raw->osds[i] = to;
+			/* make sure replacement doesn't already appear */
+			for (j = 0; j < raw->size; j++) {
+				int osd = raw->osds[j];
+
+				if (osd == to) {
+					exists = true;
 					break;
 				}
+				/* ignore mapping if target is marked out */
+				if (osd == from && pos < 0 &&
+				    !(to != CRUSH_ITEM_NONE &&
+				      to < osdmap->max_osd &&
+				      osdmap->osd_weight[to] == 0)) {
+					pos = j;
+				}
 			}
+			if (!exists && pos >= 0)
+				raw->osds[pos] = to;
 		}
 	}
 }
diff --git a/net/compat.c b/net/compat.c
index 6ded6c8..2238171 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -185,6 +185,13 @@
 		ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen);
 	}
 
+	/*
+	 * check the length of messages copied in is the same as the
+	 * what we get from the first loop
+	 */
+	if ((char *)kcmsg - (char *)kcmsg_base != kcmlen)
+		goto Einval;
+
 	/* Ok, looks like we made it.  Hook it up and return success. */
 	kmsg->msg_control = kcmsg_base;
 	kmsg->msg_controllen = kcmlen;
diff --git a/net/core/dev.c b/net/core/dev.c
index fb766d9..11596a3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1147,9 +1147,8 @@
 	return ret;
 }
 
-static int dev_get_valid_name(struct net *net,
-			      struct net_device *dev,
-			      const char *name)
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name)
 {
 	BUG_ON(!net);
 
@@ -1165,6 +1164,7 @@
 
 	return 0;
 }
+EXPORT_SYMBOL(dev_get_valid_name);
 
 /**
  *	dev_change_name - change name of a device
@@ -1948,8 +1948,12 @@
 		goto again;
 	}
 out_unlock:
-	if (pt_prev)
-		pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
+	if (pt_prev) {
+		if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC))
+			pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
+		else
+			kfree_skb(skb2);
+	}
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(dev_queue_xmit_nit);
@@ -3892,6 +3896,7 @@
 		__skb_pull(skb, off);
 	else if (off < 0)
 		__skb_push(skb, -off);
+	skb->mac_header += off;
 
 	switch (act) {
 	case XDP_REDIRECT:
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 709a4e6..f9c7a88 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -303,7 +303,18 @@
 	case SIOCSIFTXQLEN:
 		if (ifr->ifr_qlen < 0)
 			return -EINVAL;
-		dev->tx_queue_len = ifr->ifr_qlen;
+		if (dev->tx_queue_len ^ ifr->ifr_qlen) {
+			unsigned int orig_len = dev->tx_queue_len;
+
+			dev->tx_queue_len = ifr->ifr_qlen;
+			err = call_netdevice_notifiers(
+					NETDEV_CHANGE_TX_QUEUE_LEN, dev);
+			err = notifier_to_errno(err);
+			if (err) {
+				dev->tx_queue_len = orig_len;
+				return err;
+			}
+		}
 		return 0;
 
 	case SIOCSIFNAME:
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6a582ae..9a9a3d7 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -436,7 +436,7 @@
 EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32);
 
 /* return false if legacy contained non-0 deprecated fields
- * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated
+ * maxtxpkt/maxrxpkt. rest of ksettings always updated
  */
 static bool
 convert_legacy_settings_to_link_ksettings(
@@ -451,8 +451,7 @@
 	 * deprecated legacy fields, and they should not use
 	 * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS
 	 */
-	if (legacy_settings->transceiver ||
-	    legacy_settings->maxtxpkt ||
+	if (legacy_settings->maxtxpkt ||
 	    legacy_settings->maxrxpkt)
 		retval = false;
 
@@ -525,6 +524,8 @@
 		= link_ksettings->base.eth_tp_mdix;
 	legacy_settings->eth_tp_mdix_ctrl
 		= link_ksettings->base.eth_tp_mdix_ctrl;
+	legacy_settings->transceiver
+		= link_ksettings->base.transceiver;
 	return retval;
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 24dd33d..6ae94f8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -989,10 +989,14 @@
 
 bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
-	bool ret = __sk_filter_charge(sk, fp);
-	if (ret)
-		refcount_inc(&fp->refcnt);
-	return ret;
+	if (!refcount_inc_not_zero(&fp->refcnt))
+		return false;
+
+	if (!__sk_filter_charge(sk, fp)) {
+		sk_filter_release(fp);
+		return false;
+	}
+	return true;
 }
 
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
@@ -1794,7 +1798,7 @@
 	u32 flags;
 	struct bpf_map *map;
 	struct bpf_map *map_to_flush;
-	const struct bpf_prog *map_owner;
+	unsigned long   map_owner;
 };
 
 static DEFINE_PER_CPU(struct redirect_info, redirect_info);
@@ -1835,31 +1839,32 @@
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags)
+BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
+	   struct bpf_map *, map, u32, key, u64, flags)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
+	/* If user passes invalid input drop the packet. */
 	if (unlikely(flags))
-		return SK_ABORTED;
+		return SK_DROP;
 
-	ri->ifindex = key;
-	ri->flags = flags;
-	ri->map = map;
+	tcb->bpf.key = key;
+	tcb->bpf.flags = flags;
+	tcb->bpf.map = map;
 
-	return SK_REDIRECT;
+	return SK_PASS;
 }
 
-struct sock *do_sk_redirect_map(void)
+struct sock *do_sk_redirect_map(struct sk_buff *skb)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 	struct sock *sk = NULL;
 
-	if (ri->map) {
-		sk = __sock_map_lookup_elem(ri->map, ri->ifindex);
+	if (tcb->bpf.map) {
+		sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key);
 
-		ri->ifindex = 0;
-		ri->map = NULL;
-		/* we do not clear flags for future lookup */
+		tcb->bpf.key = 0;
+		tcb->bpf.map = NULL;
 	}
 
 	return sk;
@@ -1869,9 +1874,10 @@
 	.func           = bpf_sk_redirect_map,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_CONST_MAP_PTR,
-	.arg2_type      = ARG_ANYTHING,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
 	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_ANYTHING,
 };
 
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
@@ -2500,11 +2506,17 @@
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush_map);
 
+static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
+				   unsigned long aux)
+{
+	return (unsigned long)xdp_prog->aux != aux;
+}
+
 static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 			       struct bpf_prog *xdp_prog)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
-	const struct bpf_prog *map_owner = ri->map_owner;
+	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	struct net_device *fwd = NULL;
 	u32 index = ri->ifindex;
@@ -2512,9 +2524,9 @@
 
 	ri->ifindex = 0;
 	ri->map = NULL;
-	ri->map_owner = NULL;
+	ri->map_owner = 0;
 
-	if (unlikely(map_owner != xdp_prog)) {
+	if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
 		err = -EFAULT;
 		map = NULL;
 		goto err;
@@ -2574,7 +2586,7 @@
 			    struct bpf_prog *xdp_prog)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
-	const struct bpf_prog *map_owner = ri->map_owner;
+	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	struct net_device *fwd = NULL;
 	u32 index = ri->ifindex;
@@ -2583,10 +2595,10 @@
 
 	ri->ifindex = 0;
 	ri->map = NULL;
-	ri->map_owner = NULL;
+	ri->map_owner = 0;
 
 	if (map) {
-		if (unlikely(map_owner != xdp_prog)) {
+		if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
 			err = -EFAULT;
 			map = NULL;
 			goto err;
@@ -2632,7 +2644,7 @@
 	ri->ifindex = ifindex;
 	ri->flags = flags;
 	ri->map = NULL;
-	ri->map_owner = NULL;
+	ri->map_owner = 0;
 
 	return XDP_REDIRECT;
 }
@@ -2646,7 +2658,7 @@
 };
 
 BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags,
-	   const struct bpf_prog *, map_owner)
+	   unsigned long, map_owner)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
 
@@ -3673,7 +3685,6 @@
 {
 	if (type == BPF_WRITE) {
 		switch (off) {
-		case bpf_ctx_range(struct __sk_buff, mark):
 		case bpf_ctx_range(struct __sk_buff, tc_index):
 		case bpf_ctx_range(struct __sk_buff, priority):
 			break;
@@ -3683,6 +3694,7 @@
 	}
 
 	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, mark):
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
@@ -4232,6 +4244,31 @@
 	return insn - insn_buf;
 }
 
+static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
+				     const struct bpf_insn *si,
+				     struct bpf_insn *insn_buf,
+				     struct bpf_prog *prog, u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+	int off;
+
+	switch (si->off) {
+	case offsetof(struct __sk_buff, data_end):
+		off  = si->off;
+		off -= offsetof(struct __sk_buff, data_end);
+		off += offsetof(struct sk_buff, cb);
+		off += offsetof(struct tcp_skb_cb, bpf.data_end);
+		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
+				      si->src_reg, off);
+		break;
+	default:
+		return bpf_convert_ctx_access(type, si, insn_buf, prog,
+					      target_size);
+	}
+
+	return insn - insn_buf;
+}
+
 const struct bpf_verifier_ops sk_filter_prog_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
@@ -4290,7 +4327,7 @@
 const struct bpf_verifier_ops sk_skb_prog_ops = {
 	.get_func_proto		= sk_skb_func_proto,
 	.is_valid_access	= sk_skb_is_valid_access,
-	.convert_ctx_access	= bpf_convert_ctx_access,
+	.convert_ctx_access	= sk_skb_convert_ctx_access,
 	.gen_prologue		= sk_skb_prologue,
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a78fd61..5ace489 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1483,7 +1483,10 @@
 	[IFLA_LINKINFO]		= { .type = NLA_NESTED },
 	[IFLA_NET_NS_PID]	= { .type = NLA_U32 },
 	[IFLA_NET_NS_FD]	= { .type = NLA_U32 },
-	[IFLA_IFALIAS]	        = { .type = NLA_STRING, .len = IFALIASZ-1 },
+	/* IFLA_IFALIAS is a string, but policy is set to NLA_BINARY to
+	 * allow 0-length string (needed to remove an alias).
+	 */
+	[IFLA_IFALIAS]	        = { .type = NLA_BINARY, .len = IFALIASZ - 1 },
 	[IFLA_VFINFO_LIST]	= {. type = NLA_NESTED },
 	[IFLA_VF_PORTS]		= { .type = NLA_NESTED },
 	[IFLA_PORT_SELF]	= { .type = NLA_NESTED },
@@ -2093,7 +2096,7 @@
 				dev->tx_queue_len = orig_len;
 				goto errout;
 			}
-			status |= DO_SETLINK_NOTIFY;
+			status |= DO_SETLINK_MODIFIED;
 		}
 	}
 
@@ -2248,7 +2251,7 @@
 
 errout:
 	if (status & DO_SETLINK_MODIFIED) {
-		if (status & DO_SETLINK_NOTIFY)
+		if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
 			netdev_state_change(dev);
 
 		if (err < 0)
@@ -3854,6 +3857,9 @@
 		return -EMSGSIZE;
 
 	ifsm = nlmsg_data(nlh);
+	ifsm->family = PF_UNSPEC;
+	ifsm->pad1 = 0;
+	ifsm->pad2 = 0;
 	ifsm->ifindex = dev->ifindex;
 	ifsm->filter_mask = filter_mask;
 
@@ -4276,13 +4282,17 @@
 
 	switch (event) {
 	case NETDEV_REBOOT:
+	case NETDEV_CHANGEMTU:
 	case NETDEV_CHANGEADDR:
 	case NETDEV_CHANGENAME:
 	case NETDEV_FEAT_CHANGE:
 	case NETDEV_BONDING_FAILOVER:
+	case NETDEV_POST_TYPE_CHANGE:
 	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_CHANGEUPPER:
 	case NETDEV_RESEND_IGMP:
 	case NETDEV_CHANGEINFODATA:
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
 		rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
 				   GFP_KERNEL);
 		break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 16982de..2465607 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1124,9 +1124,13 @@
 
 	err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len);
 	if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
+		struct sock *save_sk = skb->sk;
+
 		/* Streams do not free skb on error. Reset to prev state. */
 		msg->msg_iter = orig_iter;
+		skb->sk = sk;
 		___pskb_trim(skb, orig_len);
+		skb->sk = save_sk;
 		return err;
 	}
 
@@ -1896,7 +1900,7 @@
 	}
 
 	/* If we need update frag list, we are in troubles.
-	 * Certainly, it possible to add an offset to skb data,
+	 * Certainly, it is possible to add an offset to skb data,
 	 * but taking into account that pulling is expected to
 	 * be very rare operation, it is worth to fight against
 	 * further bloating skb head and crucify ourselves here instead.
diff --git a/net/core/sock.c b/net/core/sock.c
index 9b7b6bb..415f441 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1654,6 +1654,8 @@
 
 		sock_copy(newsk, sk);
 
+		newsk->sk_prot_creator = sk->sk_prot;
+
 		/* SANITY */
 		if (likely(newsk->sk_net_refcnt))
 			get_net(sock_net(newsk));
@@ -1675,20 +1677,28 @@
 		newsk->sk_dst_pending_confirm = 0;
 		newsk->sk_wmem_queued	= 0;
 		newsk->sk_forward_alloc = 0;
+
+		/* sk->sk_memcg will be populated at accept() time */
+		newsk->sk_memcg = NULL;
+
 		atomic_set(&newsk->sk_drops, 0);
 		newsk->sk_send_head	= NULL;
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 		atomic_set(&newsk->sk_zckey, 0);
 
 		sock_reset_flag(newsk, SOCK_DONE);
+		cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
-		filter = rcu_dereference_protected(newsk->sk_filter, 1);
+		rcu_read_lock();
+		filter = rcu_dereference(sk->sk_filter);
 		if (filter != NULL)
 			/* though it's an empty new sock, the charging may fail
 			 * if sysctl_optmem_max was changed between creation of
 			 * original socket and cloning
 			 */
 			is_charged = sk_filter_charge(newsk, filter);
+		RCU_INIT_POINTER(newsk->sk_filter, filter);
+		rcu_read_unlock();
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
 			/* We need to make sure that we don't uncharge the new
@@ -1709,9 +1719,6 @@
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);
 
-		mem_cgroup_sk_alloc(newsk);
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
-
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
 		 * (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index eed1ebf..b1e0dbe 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -36,9 +36,14 @@
 	 * soft irq of receive path or setsockopt from process context
 	 */
 	spin_lock_bh(&reuseport_lock);
-	WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-					    lockdep_is_held(&reuseport_lock)),
-		  "multiple allocations for the same socket");
+
+	/* Allocation attempts can occur concurrently via the setsockopt path
+	 * and the bind/hash path.  Nothing to do when we lose the race.
+	 */
+	if (rcu_dereference_protected(sk->sk_reuseport_cb,
+				      lockdep_is_held(&reuseport_lock)))
+		goto out;
+
 	reuse = __reuseport_alloc(INIT_SOCKS);
 	if (!reuse) {
 		spin_unlock_bh(&reuseport_lock);
@@ -49,6 +54,7 @@
 	reuse->num_socks = 1;
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
+out:
 	spin_unlock_bh(&reuseport_lock);
 
 	return 0;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 001c086..e65fcb4 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -414,8 +414,7 @@
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newinet->inet_saddr	= ireq->ir_loc_addr;
-	newinet->inet_opt	= ireq->opt;
-	ireq->opt	   = NULL;
+	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
 	newinet->inet_id   = jiffies;
@@ -430,7 +429,10 @@
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-
+	if (*own_req)
+		ireq->ireq_opt = NULL;
+	else
+		newinet->inet_opt = NULL;
 	return newsk;
 
 exit_overflow:
@@ -441,6 +443,7 @@
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	dccp_done(newsk);
 	goto exit;
@@ -492,7 +495,7 @@
 							      ireq->ir_rmt_addr);
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
@@ -548,7 +551,7 @@
 static void dccp_v4_reqsk_destructor(struct request_sock *req)
 {
 	dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 void dccp_syn_ack_timeout(const struct request_sock *req)
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 8737412..e1d4d89 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -224,7 +224,7 @@
 static void dns_resolver_describe(const struct key *key, struct seq_file *m)
 {
 	seq_puts(m, key->description);
-	if (key_is_instantiated(key)) {
+	if (key_is_positive(key)) {
 		int err = PTR_ERR(key->payload.data[dns_key_error]);
 
 		if (err)
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 873af01..045d8a1 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -496,14 +496,15 @@
 		if (!ethernet)
 			return -EINVAL;
 		ethernet_dev = of_find_net_device_by_node(ethernet);
+		if (!ethernet_dev)
+			return -EPROBE_DEFER;
 	} else {
 		ethernet_dev = dsa_dev_to_net_device(ds->cd->netdev[index]);
+		if (!ethernet_dev)
+			return -EPROBE_DEFER;
 		dev_put(ethernet_dev);
 	}
 
-	if (!ethernet_dev)
-		return -EPROBE_DEFER;
-
 	if (!dst->cpu_dp) {
 		dst->cpu_dp = port;
 		dst->cpu_dp->netdev = ethernet_dev;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 2afa995..865e29e 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1301,28 +1301,33 @@
 	p->old_duplex = -1;
 
 	port->netdev = slave_dev;
-	ret = register_netdev(slave_dev);
-	if (ret) {
-		netdev_err(master, "error %d registering interface %s\n",
-			   ret, slave_dev->name);
-		port->netdev = NULL;
-		free_percpu(p->stats64);
-		free_netdev(slave_dev);
-		return ret;
-	}
 
 	netif_carrier_off(slave_dev);
 
 	ret = dsa_slave_phy_setup(p, slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d setting up slave phy\n", ret);
-		unregister_netdev(slave_dev);
-		free_percpu(p->stats64);
-		free_netdev(slave_dev);
-		return ret;
+		goto out_free;
+	}
+
+	ret = register_netdev(slave_dev);
+	if (ret) {
+		netdev_err(master, "error %d registering interface %s\n",
+			   ret, slave_dev->name);
+		goto out_phy;
 	}
 
 	return 0;
+
+out_phy:
+	phy_disconnect(p->phy);
+	if (of_phy_is_fixed_link(p->dp->dn))
+		of_phy_deregister_fixed_link(p->dp->dn);
+out_free:
+	free_percpu(p->stats64);
+	free_netdev(slave_dev);
+	port->netdev = NULL;
+	return ret;
 }
 
 void dsa_slave_destroy(struct net_device *slave_dev)
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 91a2557..f48fe6f 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -70,11 +70,9 @@
 	  address into account. Furthermore, the TOS (Type-Of-Service) field
 	  of the packet can be used for routing decisions as well.
 
-	  If you are interested in this, please see the preliminary
-	  documentation at <http://www.compendium.com.ar/policy-routing.txt>
-	  and <ftp://post.tepkom.ru/pub/vol2/Linux/docs/advanced-routing.tex>.
-	  You will need supporting software from
-	  <ftp://ftp.tux.org/pub/net/ip-routing/>.
+	  If you need more information, see the Linux Advanced
+	  Routing and Traffic Control documentation at
+	  <http://lartc.org/howto/lartc.rpdb.html>
 
 	  If unsure, say N.
 
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 2ae8f54..82178cc 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1951,7 +1951,7 @@
 	buf = NULL;
 
 	req_inet = inet_rsk(req);
-	opt = xchg(&req_inet->opt, opt);
+	opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt);
 	if (opt)
 		kfree_rcu(opt, rcu);
 
@@ -1973,11 +1973,13 @@
  * values on failure.
  *
  */
-static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
+static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr)
 {
+	struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1);
 	int hdr_delta = 0;
-	struct ip_options_rcu *opt = *opt_ptr;
 
+	if (!opt || opt->opt.cipso == 0)
+		return 0;
 	if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) {
 		u8 cipso_len;
 		u8 cipso_off;
@@ -2039,14 +2041,10 @@
  */
 void cipso_v4_sock_delattr(struct sock *sk)
 {
-	int hdr_delta;
-	struct ip_options_rcu *opt;
 	struct inet_sock *sk_inet;
+	int hdr_delta;
 
 	sk_inet = inet_sk(sk);
-	opt = rcu_dereference_protected(sk_inet->inet_opt, 1);
-	if (!opt || opt->opt.cipso == 0)
-		return;
 
 	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
 	if (sk_inet->is_icsk && hdr_delta > 0) {
@@ -2066,15 +2064,7 @@
  */
 void cipso_v4_req_delattr(struct request_sock *req)
 {
-	struct ip_options_rcu *opt;
-	struct inet_request_sock *req_inet;
-
-	req_inet = inet_rsk(req);
-	opt = req_inet->opt;
-	if (!opt || opt->opt.cipso == 0)
-		return;
-
-	cipso_v4_delopt(&req_inet->opt);
+	cipso_v4_delopt(&inet_rsk(req)->ireq_opt);
 }
 
 /**
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 416bb30..1859c47 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -86,7 +86,7 @@
 		greh = (struct gre_base_hdr *)skb_transport_header(skb);
 		pcsum = (__sum16 *)(greh + 1);
 
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			unsigned int partial_adj;
 
 			/* Adjust checksum to account for the fact that
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b9c64b4..b47a59c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -266,7 +266,7 @@
 #if IS_ENABLED(CONFIG_IPV6)
 	if (tb->fast_sk_family == AF_INET6)
 		return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr,
-					    &sk->sk_v6_rcv_saddr,
+					    inet6_rcv_saddr(sk),
 					    tb->fast_rcv_saddr,
 					    sk->sk_rcv_saddr,
 					    tb->fast_ipv6_only,
@@ -321,13 +321,14 @@
 			goto fail_unlock;
 	}
 success:
-	if (!hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->owners)) {
 		tb->fastreuse = reuse;
 		if (sk->sk_reuseport) {
 			tb->fastreuseport = FASTREUSEPORT_ANY;
 			tb->fastuid = uid;
 			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
 			tb->fast_ipv6_only = ipv6_only_sock(sk);
+			tb->fast_sk_family = sk->sk_family;
 #if IS_ENABLED(CONFIG_IPV6)
 			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 #endif
@@ -354,6 +355,7 @@
 				tb->fastuid = uid;
 				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
 				tb->fast_ipv6_only = ipv6_only_sock(sk);
+				tb->fast_sk_family = sk->sk_family;
 #if IS_ENABLED(CONFIG_IPV6)
 				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 #endif
@@ -473,6 +475,7 @@
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
+	mem_cgroup_sk_alloc(newsk);
 out:
 	release_sock(sk);
 	if (req)
@@ -537,9 +540,11 @@
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct net *net = read_pnet(&ireq->ireq_net);
-	struct ip_options_rcu *opt = ireq->opt;
+	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
+	opt = ireq_opt_deref(ireq);
+
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -573,10 +578,9 @@
 	struct flowi4 *fl4;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	fl4 = &newinet->cork.fl.u.ip4;
 
-	rcu_read_lock();
-	opt = rcu_dereference(newinet->inet_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -589,13 +593,11 @@
 		goto no_route;
 	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
-	rcu_read_unlock();
 	return &rt->dst;
 
 route_err:
 	ip_rt_put(rt);
 no_route:
-	rcu_read_unlock();
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 597bb4c..e7d15fb0 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -456,10 +456,7 @@
 			return reuseport_add_sock(sk, sk2);
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk)
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index e7eb590..b20c8ac 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -128,9 +128,9 @@
 			break;
 		}
 		if (cmp == -1)
-			pp = &(*pp)->rb_left;
+			pp = &next->rb_left;
 		else
-			pp = &(*pp)->rb_right;
+			pp = &next->rb_right;
 	}
 	*parent_p = parent;
 	*pp_p = pp;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0162fb9..467e44d 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -259,7 +259,6 @@
 	struct ip_tunnel *tunnel;
 	struct erspanhdr *ershdr;
 	const struct iphdr *iph;
-	__be32 session_id;
 	__be32 index;
 	int len;
 
@@ -275,8 +274,7 @@
 	/* The original GRE header does not have key field,
 	 * Use ERSPAN 10-bit session ID as key.
 	 */
-	session_id = cpu_to_be32(ntohs(ershdr->session_id));
-	tpi->key = session_id;
+	tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK);
 	index = ershdr->md.index;
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
 				  tpi->flags | TUNNEL_KEY,
@@ -733,7 +731,7 @@
 	if (skb_cow_head(skb, dev->needed_headroom))
 		goto free_skb;
 
-	if (skb->len > dev->mtu) {
+	if (skb->len - dev->hard_header_len > dev->mtu) {
 		pskb_trim(skb, dev->mtu);
 		truncate = true;
 	}
@@ -1223,6 +1221,7 @@
 {
 	__gre_tunnel_init(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
 }
@@ -1246,13 +1245,16 @@
 
 	tunnel->tun_hlen = 8;
 	tunnel->parms.iph.protocol = IPPROTO_GRE;
-	t_hlen = tunnel->hlen + sizeof(struct iphdr) + sizeof(struct erspanhdr);
+	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
+		       sizeof(struct erspanhdr);
+	t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 	dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4;
 	dev->mtu = ETH_DATA_LEN - t_hlen - 4;
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
 }
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index fa2dc8f..57fc13c 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -311,9 +311,10 @@
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	struct rtable *rt;
+	int (*edemux)(struct sk_buff *skb);
 	struct net_device *dev = skb->dev;
-	void (*edemux)(struct sk_buff *skb);
+	struct rtable *rt;
+	int err;
 
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -331,7 +332,9 @@
 
 		ipprot = rcu_dereference(inet_protos[protocol]);
 		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
-			edemux(skb);
+			err = edemux(skb);
+			if (unlikely(err))
+				goto drop_error;
 			/* must reload iph, skb->head might have changed */
 			iph = ip_hdr(skb);
 		}
@@ -342,13 +345,10 @@
 	 *	how the packet travels inside Linux networking.
 	 */
 	if (!skb_valid_dst(skb)) {
-		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					       iph->tos, dev);
-		if (unlikely(err)) {
-			if (err == -EXDEV)
-				__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
-			goto drop;
-		}
+		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+					   iph->tos, dev);
+		if (unlikely(err))
+			goto drop_error;
 	}
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -399,6 +399,11 @@
 drop:
 	kfree_skb(skb);
 	return NET_RX_DROP;
+
+drop_error:
+	if (err == -EXDEV)
+		__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
+	goto drop;
 }
 
 /*
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5ed63d2..89453cf 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -168,6 +168,7 @@
 	struct ip_tunnel_parm *parms = &tunnel->parms;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
+	int pkt_len = skb->len;
 	int err;
 	int mtu;
 
@@ -229,7 +230,7 @@
 
 	err = dst_output(tunnel->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0)
-		err = skb->len;
+		err = pkt_len;
 	iptunnel_xmit_stats(dev, err);
 	return NETDEV_TX_OK;
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index fb1ad22..cdd6273 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -128,43 +128,68 @@
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
-
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
- */
+	/* All the routers (except for Linux) return only
+	 * 8 bytes of packet payload. It means, that precise relaying of
+	 * ICMP in the real Internet is absolutely infeasible.
+	 */
 	struct net *net = dev_net(skb->dev);
 	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
-	struct ip_tunnel *t;
-	int err;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	struct ip_tunnel *t;
+	int err = 0;
 
-	err = -ENOENT;
+	switch (type) {
+	case ICMP_DEST_UNREACH:
+		switch (code) {
+		case ICMP_SR_FAILED:
+			/* Impossible event. */
+			goto out;
+		default:
+			/* All others are translated to HOST_UNREACH.
+			 * rfc2003 contains "deep thoughts" about NET_UNREACH,
+			 * I believe they are just ether pollution. --ANK
+			 */
+			break;
+		}
+		break;
+
+	case ICMP_TIME_EXCEEDED:
+		if (code != ICMP_EXC_TTL)
+			goto out;
+		break;
+
+	case ICMP_REDIRECT:
+		break;
+
+	default:
+		goto out;
+	}
+
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 			     iph->daddr, iph->saddr, 0);
-	if (!t)
+	if (!t) {
+		err = -ENOENT;
 		goto out;
+	}
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, iph->protocol, 0);
-		err = 0;
+		ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
+				 iph->protocol, 0);
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      iph->protocol, 0);
-		err = 0;
+		ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
 		goto out;
 	}
 
-	if (t->parms.iph.daddr == 0)
+	if (t->parms.iph.daddr == 0) {
+		err = -ENOENT;
 		goto out;
+	}
 
-	err = 0;
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 811689e..f75fc6b 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -330,7 +330,8 @@
 	if (synproxy == NULL)
 		return NF_ACCEPT;
 
-	if (nf_is_loopback_packet(skb))
+	if (nf_is_loopback_packet(skb) ||
+	    ip_hdr(skb)->protocol != IPPROTO_TCP)
 		return NF_ACCEPT;
 
 	thoff = ip_hdrlen(skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 94d4cd2..3d9f1c2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1520,43 +1520,56 @@
 EXPORT_SYMBOL(rt_dst_alloc);
 
 /* called in rcu_read_lock() section */
-static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-				u8 tos, struct net_device *dev, int our)
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag)
 {
-	struct rtable *rth;
-	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	unsigned int flags = RTCF_MULTICAST;
-	u32 itag = 0;
 	int err;
 
 	/* Primary sanity checks. */
-
 	if (!in_dev)
 		return -EINVAL;
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
 	    skb->protocol != htons(ETH_P_IP))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_zeronet(saddr)) {
 		if (!ipv4_is_local_multicast(daddr))
-			goto e_inval;
+			return -EINVAL;
 	} else {
 		err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
-					  in_dev, &itag);
+					  in_dev, itag);
 		if (err < 0)
-			goto e_err;
+			return err;
 	}
+	return 0;
+}
+
+/* called in rcu_read_lock() section */
+static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			     u8 tos, struct net_device *dev, int our)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	unsigned int flags = RTCF_MULTICAST;
+	struct rtable *rth;
+	u32 itag = 0;
+	int err;
+
+	err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag);
+	if (err)
+		return err;
+
 	if (our)
 		flags |= RTCF_LOCAL;
 
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
 	if (!rth)
-		goto e_nobufs;
+		return -ENOBUFS;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
@@ -1572,13 +1585,6 @@
 
 	skb_dst_set(skb, &rth->dst);
 	return 0;
-
-e_nobufs:
-	return -ENOBUFS;
-e_inval:
-	return -EINVAL;
-e_err:
-	return err;
 }
 
 
@@ -2507,7 +2513,7 @@
 	struct rtable *ort = (struct rtable *) dst_orig;
 	struct rtable *rt;
 
-	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
+	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0);
 	if (rt) {
 		struct dst_entry *new = &rt->dst;
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b1bb1b3..77cf32a 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -355,7 +355,7 @@
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	ireq->opt = tcp_v4_save_options(sock_net(sk), skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
 
 	if (security_inet_conn_request(sk, skb, req)) {
 		reqsk_free(req);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5d7656..7eec338 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6196,7 +6196,7 @@
 		struct inet_request_sock *ireq = inet_rsk(req);
 
 		kmemcheck_annotate_bitfield(ireq, flags);
-		ireq->opt = NULL;
+		ireq->ireq_opt = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
 		ireq->pktopts = NULL;
 #endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d9416b5..5b027c6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -877,7 +877,7 @@
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
@@ -889,7 +889,7 @@
  */
 static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1265,10 +1265,11 @@
 			    struct sk_buff *skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
+	struct net *net = sock_net(sk_listener);
 
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1355,10 +1356,9 @@
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newsk->sk_bound_dev_if = ireq->ir_iif;
-	newinet->inet_saddr	      = ireq->ir_loc_addr;
-	inet_opt	      = ireq->opt;
-	rcu_assign_pointer(newinet->inet_opt, inet_opt);
-	ireq->opt	      = NULL;
+	newinet->inet_saddr   = ireq->ir_loc_addr;
+	inet_opt	      = rcu_dereference(ireq->ireq_opt);
+	RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	newinet->rcv_tos      = ip_hdr(skb)->tos;
@@ -1403,9 +1403,12 @@
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-	if (*own_req)
+	if (likely(*own_req)) {
 		tcp_move_syn(newtp, req);
-
+		ireq->ireq_opt = NULL;
+	} else {
+		newinet->inet_opt = NULL;
+	}
 	return newsk;
 
 exit_overflow:
@@ -1416,6 +1419,7 @@
 	tcp_listendrop(sk);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	tcp_done(newsk);
 	goto exit;
@@ -1503,23 +1507,23 @@
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
-void tcp_v4_early_demux(struct sk_buff *skb)
+int tcp_v4_early_demux(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	struct sock *sk;
 
 	if (skb->pkt_type != PACKET_HOST)
-		return;
+		return 0;
 
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	th = tcp_hdr(skb);
 
 	if (th->doff < sizeof(struct tcphdr) / 4)
-		return;
+		return 0;
 
 	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 				       iph->saddr, th->source,
@@ -1538,6 +1542,7 @@
 				skb_dst_set_noref(skb, dst);
 		}
 	}
+	return 0;
 }
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1c839c9..ae60dd3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -739,8 +739,10 @@
 		struct tcp_sock *tp = tcp_sk(sk);
 
 		if (tp->lost_out > tp->retrans_out &&
-		    tp->snd_cwnd > tcp_packets_in_flight(tp))
+		    tp->snd_cwnd > tcp_packets_in_flight(tp)) {
+			tcp_mstamp_refresh(tp);
 			tcp_xmit_retransmit_queue(sk);
+		}
 
 		tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle,
 			       0, GFP_ATOMIC);
@@ -1806,40 +1808,6 @@
 	return !after(end_seq, tcp_wnd_end(tp));
 }
 
-/* This checks if the data bearing packet SKB (usually tcp_send_head(sk))
- * should be put on the wire right now.  If so, it returns the number of
- * packets allowed by the congestion window.
- */
-static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
-				 unsigned int cur_mss, int nonagle)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	unsigned int cwnd_quota;
-
-	tcp_init_tso_segs(skb, cur_mss);
-
-	if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
-		return 0;
-
-	cwnd_quota = tcp_cwnd_test(tp, skb);
-	if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss))
-		cwnd_quota = 0;
-
-	return cwnd_quota;
-}
-
-/* Test if sending is allowed right now. */
-bool tcp_may_send_now(struct sock *sk)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_send_head(sk);
-
-	return skb &&
-		tcp_snd_test(sk, skb, tcp_current_mss(sk),
-			     (tcp_skb_is_last(sk, skb) ?
-			      tp->nonagle : TCP_NAGLE_PUSH));
-}
-
 /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
  * which is put after SKB on the list.  It is very much like
  * tcp_fragment() except that it may make several kinds of assumptions
@@ -2271,6 +2239,7 @@
 
 	sent_pkts = 0;
 
+	tcp_mstamp_refresh(tp);
 	if (!push_one) {
 		/* Do MTU probing. */
 		result = tcp_mtu_probe(sk);
@@ -2282,7 +2251,6 @@
 	}
 
 	max_segs = tcp_tso_segs(sk, mss_now);
-	tcp_mstamp_refresh(tp);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
@@ -2875,8 +2843,10 @@
 		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
-		if (!err)
+		if (!err) {
 			skb->skb_mstamp = tp->tcp_mstamp;
+			tcp_rate_skb_sent(sk, skb);
+		}
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
@@ -3423,6 +3393,10 @@
 		goto done;
 	}
 
+	/* data was not sent, this is our new send_head */
+	sk->sk_send_head = syn_data;
+	tp->packets_out -= tcp_skb_pcount(syn_data);
+
 fallback:
 	/* Send a regular SYN with Fast Open cookie request option */
 	if (fo->cookie.len > 0)
@@ -3475,6 +3449,11 @@
 	 */
 	tp->snd_nxt = tp->write_seq;
 	tp->pushed_seq = tp->write_seq;
+	buff = tcp_send_head(sk);
+	if (unlikely(buff)) {
+		tp->snd_nxt	= TCP_SKB_CB(buff)->seq;
+		tp->pushed_seq	= TCP_SKB_CB(buff)->seq;
+	}
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
 
 	/* Timer for repeating the SYN until an answer. */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ef29df8..ebfbcca 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -231,10 +231,7 @@
 		}
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 /**
@@ -1061,7 +1058,7 @@
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		net_dbg_ratelimited("cork app bug 2\n");
+		net_dbg_ratelimited("socket already corked\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1144,7 +1141,7 @@
 	if (unlikely(!up->pending)) {
 		release_sock(sk);
 
-		net_dbg_ratelimited("udp cork app bug 3\n");
+		net_dbg_ratelimited("cork failed\n");
 		return -EINVAL;
 	}
 
@@ -2221,9 +2218,10 @@
 	return NULL;
 }
 
-void udp_v4_early_demux(struct sk_buff *skb)
+int udp_v4_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct in_device *in_dev = NULL;
 	const struct iphdr *iph;
 	const struct udphdr *uh;
 	struct sock *sk = NULL;
@@ -2234,25 +2232,21 @@
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	uh = udp_hdr(skb);
 
-	if (skb->pkt_type == PACKET_BROADCAST ||
-	    skb->pkt_type == PACKET_MULTICAST) {
-		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+	if (skb->pkt_type == PACKET_MULTICAST) {
+		in_dev = __in_dev_get_rcu(skb->dev);
 
 		if (!in_dev)
-			return;
+			return 0;
 
-		/* we are supposed to accept bcast packets */
-		if (skb->pkt_type == PACKET_MULTICAST) {
-			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-					       iph->protocol);
-			if (!ours)
-				return;
-		}
+		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+				       iph->protocol);
+		if (!ours)
+			return 0;
 
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr,
@@ -2263,7 +2257,7 @@
 	}
 
 	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
-		return;
+		return 0;
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
@@ -2272,12 +2266,23 @@
 	if (dst)
 		dst = dst_check(dst, 0);
 	if (dst) {
+		u32 itag = 0;
+
 		/* set noref for now.
 		 * any place which wants to hold dst has to call
 		 * dst_hold_safe()
 		 */
 		skb_dst_set_noref(skb, dst);
+
+		/* for unconnected multicast sockets we need to validate
+		 * the source on each packet
+		 */
+		if (!inet_sk(sk)->inet_daddr && in_dev)
+			return ip_mc_validate_source(skb, iph->daddr,
+						     iph->saddr, iph->tos,
+						     skb->dev, in_dev, &itag);
 	}
+	return 0;
 }
 
 int udp_rcv(struct sk_buff *skb)
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 97658bf..e360d55 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -120,7 +120,7 @@
 		 * will be using a length value equal to only one MSS sized
 		 * segment instead of the entire frame.
 		 */
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			uh->len = htons(skb_shinfo(skb)->gso_size +
 					SKB_GSO_CB(skb)->data_offset +
 					skb->head - (unsigned char *)uh);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c2e2a78..4a96ebb 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1399,10 +1399,18 @@
 	return 0;
 }
 
-static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev)
+static bool ipv6_use_optimistic_addr(struct net *net,
+				     struct inet6_dev *idev)
 {
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
-	return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic;
+	if (!idev)
+		return false;
+	if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad)
+		return false;
+	if (!net->ipv6.devconf_all->use_optimistic && !idev->cnf.use_optimistic)
+		return false;
+
+	return true;
 #else
 	return false;
 #endif
@@ -1472,7 +1480,7 @@
 		/* Rule 3: Avoid deprecated and optimistic addresses */
 		u8 avoid = IFA_F_DEPRECATED;
 
-		if (!ipv6_use_optimistic_addr(score->ifa->idev))
+		if (!ipv6_use_optimistic_addr(net, score->ifa->idev))
 			avoid |= IFA_F_OPTIMISTIC;
 		ret = ipv6_saddr_preferred(score->addr_type) ||
 		      !(score->ifa->flags & avoid);
@@ -2460,7 +2468,8 @@
 		int max_addresses = in6_dev->cnf.max_addresses;
 
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
-		if (in6_dev->cnf.optimistic_dad &&
+		if ((net->ipv6.devconf_all->optimistic_dad ||
+		     in6_dev->cnf.optimistic_dad) &&
 		    !net->ipv6.devconf_all->forwarding && sllao)
 			addr_flags |= IFA_F_OPTIMISTIC;
 #endif
@@ -3051,7 +3060,8 @@
 	u32 addr_flags = flags | IFA_F_PERMANENT;
 
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
-	if (idev->cnf.optimistic_dad &&
+	if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad ||
+	     idev->cnf.optimistic_dad) &&
 	    !dev_net(idev->dev)->ipv6.devconf_all->forwarding)
 		addr_flags |= IFA_F_OPTIMISTIC;
 #endif
@@ -3810,7 +3820,8 @@
 		goto out;
 
 	if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
-	    idev->cnf.accept_dad < 1 ||
+	    (dev_net(dev)->ipv6.devconf_all->accept_dad < 1 &&
+	     idev->cnf.accept_dad < 1) ||
 	    !(ifp->flags&IFA_F_TENTATIVE) ||
 	    ifp->flags & IFA_F_NODAD) {
 		bump_id = ifp->flags & IFA_F_TENTATIVE;
@@ -3841,7 +3852,7 @@
 	 */
 	if (ifp->flags & IFA_F_OPTIMISTIC) {
 		ip6_ins_rt(ifp->rt);
-		if (ipv6_use_optimistic_addr(idev)) {
+		if (ipv6_use_optimistic_addr(dev_net(dev), idev)) {
 			/* Because optimistic nodes can use this address,
 			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
 			 */
@@ -3897,7 +3908,9 @@
 		action = DAD_ABORT;
 		ifp->state = INET6_IFADDR_STATE_POSTDAD;
 
-		if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 &&
+		if ((dev_net(idev->dev)->ipv6.devconf_all->accept_dad > 1 ||
+		     idev->cnf.accept_dad > 1) &&
+		    !idev->cnf.disable_ipv6 &&
 		    !(ifp->flags & IFA_F_STABLE_PRIVACY)) {
 			struct in6_addr addr;
 
@@ -4940,9 +4953,10 @@
 
 	/* Don't send DELADDR notification for TENTATIVE address,
 	 * since NEWADDR notification is sent only after removing
-	 * TENTATIVE flag.
+	 * TENTATIVE flag, if DAD has not failed.
 	 */
-	if (ifa->flags & IFA_F_TENTATIVE && event == RTM_DELADDR)
+	if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_DADFAILED) &&
+	    event == RTM_DELADDR)
 		return;
 
 	skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 8081baf..15535ee 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -315,6 +315,7 @@
 	}
 	opt_space->dst1opt = fopt->dst1opt;
 	opt_space->opt_flen = fopt->opt_flen;
+	opt_space->tot_len = fopt->tot_len;
 	return opt_space;
 }
 EXPORT_SYMBOL_GPL(fl6_merge_options);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b7a72d4..59c121b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -408,13 +408,16 @@
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
-		break;
+		if (code != ICMPV6_PORT_UNREACH)
+			break;
+		return;
 	case ICMPV6_TIME_EXCEED:
 		if (code == ICMPV6_EXC_HOPLIMIT) {
 			net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
 					    t->parms.name);
+			break;
 		}
-		break;
+		return;
 	case ICMPV6_PARAMPROB:
 		teli = 0;
 		if (code == ICMPV6_HDR_FIELD)
@@ -430,7 +433,7 @@
 			net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
 					    t->parms.name);
 		}
-		break;
+		return;
 	case ICMPV6_PKT_TOOBIG:
 		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
 		if (t->dev->type == ARPHRD_ETHER)
@@ -438,7 +441,7 @@
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
-		break;
+		return;
 	}
 
 	if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO))
@@ -500,8 +503,8 @@
 			       __u32 *pmtu, __be16 proto)
 {
 	struct ip6_tnl *tunnel = netdev_priv(dev);
-	__be16 protocol = (dev->type == ARPHRD_ETHER) ?
-			  htons(ETH_P_TEB) : proto;
+	struct dst_entry *dst = skb_dst(skb);
+	__be16 protocol;
 
 	if (dev->type == ARPHRD_ETHER)
 		IPCB(skb)->flags = 0;
@@ -515,9 +518,14 @@
 		tunnel->o_seqno++;
 
 	/* Push GRE header. */
+	protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
 	gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
 			 protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno));
 
+	/* TooBig packet may have updated dst->dev's mtu */
+	if (dst && dst_mtu(dst) > dst->dev->mtu)
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+
 	return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu,
 			    NEXTHDR_GRE);
 }
@@ -940,24 +948,25 @@
 }
 
 static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
-			unsigned short type,
-			const void *daddr, const void *saddr, unsigned int len)
+			 unsigned short type, const void *daddr,
+			 const void *saddr, unsigned int len)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct ipv6hdr *ipv6h = skb_push(skb, t->hlen);
-	__be16 *p = (__be16 *)(ipv6h+1);
+	struct ipv6hdr *ipv6h;
+	__be16 *p;
 
-	ip6_flow_hdr(ipv6h, 0,
-		     ip6_make_flowlabel(dev_net(dev), skb,
-					t->fl.u.ip6.flowlabel, true,
-					&t->fl.u.ip6));
+	ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h));
+	ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb,
+						  t->fl.u.ip6.flowlabel,
+						  true, &t->fl.u.ip6));
 	ipv6h->hop_limit = t->parms.hop_limit;
 	ipv6h->nexthdr = NEXTHDR_GRE;
 	ipv6h->saddr = t->parms.laddr;
 	ipv6h->daddr = t->parms.raddr;
 
-	p[0]		= t->parms.o_flags;
-	p[1]		= htons(type);
+	p = (__be16 *)(ipv6h + 1);
+	p[0] = t->parms.o_flags;
+	p[1] = htons(type);
 
 	/*
 	 *	Set the source hardware address.
@@ -1310,6 +1319,7 @@
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 }
 
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index cdb3728..4a87f94 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -105,7 +105,7 @@
 
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
-		if (gso_partial)
+		if (gso_partial && skb_is_gso(skb))
 			payload_len = skb_shinfo(skb)->gso_size +
 				      SKB_GSO_CB(skb)->data_offset +
 				      skb->head - (unsigned char *)(ipv6h + 1);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 43ca864..5110a41 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1161,11 +1161,11 @@
 		if (WARN_ON(v6_cork->opt))
 			return -EINVAL;
 
-		v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation);
+		v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation);
 		if (unlikely(!v6_cork->opt))
 			return -ENOBUFS;
 
-		v6_cork->opt->tot_len = opt->tot_len;
+		v6_cork->opt->tot_len = sizeof(*opt);
 		v6_cork->opt->opt_flen = opt->opt_flen;
 		v6_cork->opt->opt_nflen = opt->opt_nflen;
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ae73164..a1c2444 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1043,6 +1043,7 @@
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
 	int mtu;
+	unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0;
 	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
 	unsigned int max_headroom = psh_hlen;
 	bool use_cache = false;
@@ -1124,7 +1125,7 @@
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen;
+	mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
@@ -1133,7 +1134,7 @@
 		mtu = IPV6_MIN_MTU;
 	if (skb_dst(skb) && !t->parms.collect_md)
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-	if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) {
+	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
 		goto tx_err_dst_release;
@@ -2259,6 +2260,9 @@
 {
 	int  err;
 
+	if (!ipv6_mod_enabled())
+		return -EOPNOTSUPP;
+
 	err = register_pernet_device(&ip6_tnl_net_ops);
 	if (err < 0)
 		goto out_pernet;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 79444a4..bcdc2d5 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -445,6 +445,7 @@
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
 	struct xfrm_state *x;
+	int pkt_len = skb->len;
 	int err = -1;
 	int mtu;
 
@@ -502,7 +503,7 @@
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
 
 		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += skb->len;
+		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
 	} else {
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index a5cd43d..437af8c 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -353,7 +353,7 @@
 	nexthdr = ipv6_hdr(skb)->nexthdr;
 	thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
 				 &frag_off);
-	if (thoff < 0)
+	if (thoff < 0 || nexthdr != IPPROTO_TCP)
 		return NF_ACCEPT;
 
 	th = skb_header_pointer(skb, thoff, sizeof(_th), &_th);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 26cc9f4..a96d5b3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1325,7 +1325,7 @@
 	struct dst_entry *new = NULL;
 
 	rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1,
-		       DST_OBSOLETE_NONE, 0);
+		       DST_OBSOLETE_DEAD, 0);
 	if (rt) {
 		rt6_info_init(rt);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e2ecfb1..40d7234 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1015,6 +1015,7 @@
 		 */
 		offset = skb_transport_offset(skb);
 		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+		csum = skb->csum;
 
 		skb->ip_summed = CHECKSUM_NONE;
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ee485df..02d6110 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1314,6 +1314,9 @@
 
 			hlist_del_init(&session->hlist);
 
+			if (test_and_set_bit(0, &session->dead))
+				goto again;
+
 			if (session->ref != NULL)
 				(*session->ref)(session);
 
@@ -1685,14 +1688,12 @@
 
 /* This function is used by the netlink TUNNEL_DELETE command.
  */
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
-	l2tp_tunnel_inc_refcount(tunnel);
-	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
-		l2tp_tunnel_dec_refcount(tunnel);
-		return 1;
+	if (!test_and_set_bit(0, &tunnel->dead)) {
+		l2tp_tunnel_inc_refcount(tunnel);
+		queue_work(l2tp_wq, &tunnel->del_work);
 	}
-	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
@@ -1750,6 +1751,9 @@
  */
 int l2tp_session_delete(struct l2tp_session *session)
 {
+	if (test_and_set_bit(0, &session->dead))
+		return 0;
+
 	if (session->ref)
 		(*session->ref)(session);
 	__l2tp_session_unhash(session);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a305e0c..67c79d9 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -76,6 +76,7 @@
 struct l2tp_session {
 	int			magic;		/* should be
 						 * L2TP_SESSION_MAGIC */
+	long			dead;
 
 	struct l2tp_tunnel	*tunnel;	/* back pointer to tunnel
 						 * context */
@@ -160,6 +161,9 @@
 
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
+
+	unsigned long		dead;
+
 	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
 	bool			acpt_newsess;	/* Indicates whether this
@@ -254,7 +258,7 @@
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
 void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
 					 u32 session_id, u32 peer_session_id,
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 87da9ef..014a7bc 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -44,7 +44,6 @@
 	struct net_device	*dev;
 	struct sock		*tunnel_sock;
 	struct l2tp_session	*session;
-	struct list_head	list;
 	atomic_long_t		tx_bytes;
 	atomic_long_t		tx_packets;
 	atomic_long_t		tx_dropped;
@@ -58,17 +57,6 @@
 	struct net_device	*dev;
 };
 
-/* per-net private data for this module */
-static unsigned int l2tp_eth_net_id;
-struct l2tp_eth_net {
-	struct list_head l2tp_eth_dev_list;
-	spinlock_t l2tp_eth_lock;
-};
-
-static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
-{
-	return net_generic(net, l2tp_eth_net_id);
-}
 
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
@@ -84,12 +72,6 @@
 
 static void l2tp_eth_dev_uninit(struct net_device *dev)
 {
-	struct l2tp_eth *priv = netdev_priv(dev);
-	struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev));
-
-	spin_lock(&pn->l2tp_eth_lock);
-	list_del_init(&priv->list);
-	spin_unlock(&pn->l2tp_eth_lock);
 	dev_put(dev);
 }
 
@@ -273,7 +255,6 @@
 	struct l2tp_eth *priv;
 	struct l2tp_eth_sess *spriv;
 	int rc;
-	struct l2tp_eth_net *pn;
 
 	if (cfg->ifname) {
 		strlcpy(name, cfg->ifname, IFNAMSIZ);
@@ -305,7 +286,6 @@
 	priv = netdev_priv(dev);
 	priv->dev = dev;
 	priv->session = session;
-	INIT_LIST_HEAD(&priv->list);
 
 	priv->tunnel_sock = tunnel->sock;
 	session->recv_skb = l2tp_eth_dev_recv;
@@ -326,10 +306,6 @@
 	strlcpy(session->ifname, dev->name, IFNAMSIZ);
 
 	dev_hold(dev);
-	pn = l2tp_eth_pernet(dev_net(dev));
-	spin_lock(&pn->l2tp_eth_lock);
-	list_add(&priv->list, &pn->l2tp_eth_dev_list);
-	spin_unlock(&pn->l2tp_eth_lock);
 
 	return 0;
 
@@ -342,22 +318,6 @@
 	return rc;
 }
 
-static __net_init int l2tp_eth_init_net(struct net *net)
-{
-	struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id);
-
-	INIT_LIST_HEAD(&pn->l2tp_eth_dev_list);
-	spin_lock_init(&pn->l2tp_eth_lock);
-
-	return 0;
-}
-
-static struct pernet_operations l2tp_eth_net_ops = {
-	.init = l2tp_eth_init_net,
-	.id   = &l2tp_eth_net_id,
-	.size = sizeof(struct l2tp_eth_net),
-};
-
 
 static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = {
 	.session_create	= l2tp_eth_create,
@@ -371,25 +331,18 @@
 
 	err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops);
 	if (err)
-		goto out;
-
-	err = register_pernet_device(&l2tp_eth_net_ops);
-	if (err)
-		goto out_unreg;
+		goto err;
 
 	pr_info("L2TP ethernet pseudowire support (L2TPv3)\n");
 
 	return 0;
 
-out_unreg:
-	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
-out:
+err:
 	return err;
 }
 
 static void __exit l2tp_eth_exit(void)
 {
-	unregister_pernet_device(&l2tp_eth_net_ops);
 	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
 }
 
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 50e3ee9..0c27383 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -437,11 +437,11 @@
 
 	BUG_ON(session->magic != L2TP_SESSION_MAGIC);
 
-	if (sock) {
+	if (sock)
 		inet_shutdown(sock, SEND_SHUTDOWN);
-		/* Don't let the session go away before our socket does */
-		l2tp_session_inc_refcount(session);
-	}
+
+	/* Don't let the session go away before our socket does */
+	l2tp_session_inc_refcount(session);
 }
 
 /* Really kill the session socket. (Called from sock_put() if
@@ -584,6 +584,7 @@
 	u32 tunnel_id, peer_tunnel_id;
 	u32 session_id, peer_session_id;
 	bool drop_refcnt = false;
+	bool drop_tunnel = false;
 	int ver = 2;
 	int fd;
 
@@ -652,7 +653,9 @@
 	if (tunnel_id == 0)
 		goto end;
 
-	tunnel = l2tp_tunnel_find(sock_net(sk), tunnel_id);
+	tunnel = l2tp_tunnel_get(sock_net(sk), tunnel_id);
+	if (tunnel)
+		drop_tunnel = true;
 
 	/* Special case: create tunnel context if session_id and
 	 * peer_session_id is 0. Otherwise look up tunnel using supplied
@@ -781,6 +784,8 @@
 end:
 	if (drop_refcnt)
 		l2tp_session_dec_refcount(session);
+	if (drop_tunnel)
+		l2tp_tunnel_dec_refcount(tunnel);
 	release_sock(sk);
 
 	return error;
@@ -988,6 +993,9 @@
 		 session->name, cmd, arg);
 
 	sk = ps->sock;
+	if (!sk)
+		return -EBADR;
+
 	sock_hold(sk);
 
 	switch (cmd) {
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index a354f19..fb15d3b9 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2727,12 +2727,6 @@
 	if (!ieee80211_sdata_running(sdata))
 		return -ENETDOWN;
 
-	if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) {
-		ret = drv_set_bitrate_mask(local, sdata, mask);
-		if (ret)
-			return ret;
-	}
-
 	/*
 	 * If active validate the setting and reject it if it doesn't leave
 	 * at least one basic rate usable, since we really have to be able
@@ -2748,6 +2742,12 @@
 			return -EINVAL;
 	}
 
+	if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) {
+		ret = drv_set_bitrate_mask(local, sdata, mask);
+		if (ret)
+			return ret;
+	}
+
 	for (i = 0; i < NUM_NL80211_BANDS; i++) {
 		struct ieee80211_supported_band *sband = wiphy->bands[i];
 		int j;
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index a98fc2b..9380493 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -4,7 +4,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2008	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright 2015	Intel Deutschland GmbH
+ * Copyright 2015-2017	Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -19,6 +19,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <net/mac80211.h>
+#include <crypto/algapi.h>
 #include <asm/unaligned.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
@@ -609,6 +610,39 @@
 	ieee80211_key_free_common(key);
 }
 
+static bool ieee80211_key_identical(struct ieee80211_sub_if_data *sdata,
+				    struct ieee80211_key *old,
+				    struct ieee80211_key *new)
+{
+	u8 tkip_old[WLAN_KEY_LEN_TKIP], tkip_new[WLAN_KEY_LEN_TKIP];
+	u8 *tk_old, *tk_new;
+
+	if (!old || new->conf.keylen != old->conf.keylen)
+		return false;
+
+	tk_old = old->conf.key;
+	tk_new = new->conf.key;
+
+	/*
+	 * In station mode, don't compare the TX MIC key, as it's never used
+	 * and offloaded rekeying may not care to send it to the host. This
+	 * is the case in iwlwifi, for example.
+	 */
+	if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+	    new->conf.cipher == WLAN_CIPHER_SUITE_TKIP &&
+	    new->conf.keylen == WLAN_KEY_LEN_TKIP &&
+	    !(new->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) {
+		memcpy(tkip_old, tk_old, WLAN_KEY_LEN_TKIP);
+		memcpy(tkip_new, tk_new, WLAN_KEY_LEN_TKIP);
+		memset(tkip_old + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8);
+		memset(tkip_new + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8);
+		tk_old = tkip_old;
+		tk_new = tkip_new;
+	}
+
+	return !crypto_memneq(tk_old, tk_new, new->conf.keylen);
+}
+
 int ieee80211_key_link(struct ieee80211_key *key,
 		       struct ieee80211_sub_if_data *sdata,
 		       struct sta_info *sta)
@@ -620,9 +654,6 @@
 
 	pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE;
 	idx = key->conf.keyidx;
-	key->local = sdata->local;
-	key->sdata = sdata;
-	key->sta = sta;
 
 	mutex_lock(&sdata->local->key_mtx);
 
@@ -633,6 +664,20 @@
 	else
 		old_key = key_mtx_dereference(sdata->local, sdata->keys[idx]);
 
+	/*
+	 * Silently accept key re-installation without really installing the
+	 * new version of the key to avoid nonce reuse or replay issues.
+	 */
+	if (ieee80211_key_identical(sdata, old_key, key)) {
+		ieee80211_key_free_unused(key);
+		ret = 0;
+		goto out;
+	}
+
+	key->local = sdata->local;
+	key->sdata = sdata;
+	key->sta = sta;
+
 	increment_tailroom_need_count(sdata);
 
 	ieee80211_key_replace(sdata, sta, pairwise, old_key, key);
@@ -648,6 +693,7 @@
 		ret = 0;
 	}
 
+ out:
 	mutex_unlock(&sdata->local->key_mtx);
 
 	return ret;
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index af3d636..d30f7bd 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -286,6 +286,7 @@
 	struct work_struct  work;            /* For channel management     */
 	struct packet_type  ptype;           /* NCSI packet Rx handler     */
 	struct list_head    node;            /* Form NCSI device list      */
+#define NCSI_MAX_VLAN_VIDS	15
 	struct list_head    vlan_vids;       /* List of active VLAN IDs */
 };
 
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index 6898e72..f135938 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -187,7 +187,7 @@
 } ncsi_aen_handlers[] = {
 	{ NCSI_PKT_AEN_LSC,    12, ncsi_aen_handler_lsc    },
 	{ NCSI_PKT_AEN_CR,      4, ncsi_aen_handler_cr     },
-	{ NCSI_PKT_AEN_HNCDSC,  4, ncsi_aen_handler_hncdsc }
+	{ NCSI_PKT_AEN_HNCDSC,  8, ncsi_aen_handler_hncdsc }
 };
 
 int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb)
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 3fd3c39..28c42b2 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -189,6 +189,7 @@
 	struct ncsi_channel *nc = (struct ncsi_channel *)data;
 	struct ncsi_package *np = nc->package;
 	struct ncsi_dev_priv *ndp = np->ndp;
+	struct ncsi_channel_mode *ncm;
 	struct ncsi_cmd_arg nca;
 	bool enabled, chained;
 	unsigned int monitor_state;
@@ -202,11 +203,15 @@
 	monitor_state = nc->monitor.state;
 	spin_unlock_irqrestore(&nc->lock, flags);
 
-	if (!enabled || chained)
+	if (!enabled || chained) {
+		ncsi_stop_channel_monitor(nc);
 		return;
+	}
 	if (state != NCSI_CHANNEL_INACTIVE &&
-	    state != NCSI_CHANNEL_ACTIVE)
+	    state != NCSI_CHANNEL_ACTIVE) {
+		ncsi_stop_channel_monitor(nc);
 		return;
+	}
 
 	switch (monitor_state) {
 	case NCSI_CHANNEL_MONITOR_START:
@@ -217,28 +222,28 @@
 		nca.type = NCSI_PKT_CMD_GLS;
 		nca.req_flags = 0;
 		ret = ncsi_xmit_cmd(&nca);
-		if (ret) {
+		if (ret)
 			netdev_err(ndp->ndev.dev, "Error %d sending GLS\n",
 				   ret);
-			return;
-		}
-
 		break;
 	case NCSI_CHANNEL_MONITOR_WAIT ... NCSI_CHANNEL_MONITOR_WAIT_MAX:
 		break;
 	default:
-		if (!(ndp->flags & NCSI_DEV_HWA) &&
-		    state == NCSI_CHANNEL_ACTIVE) {
+		if (!(ndp->flags & NCSI_DEV_HWA)) {
 			ncsi_report_link(ndp, true);
 			ndp->flags |= NCSI_DEV_RESHUFFLE;
 		}
 
+		ncsi_stop_channel_monitor(nc);
+
+		ncm = &nc->modes[NCSI_MODE_LINK];
 		spin_lock_irqsave(&nc->lock, flags);
 		nc->state = NCSI_CHANNEL_INVISIBLE;
+		ncm->data[2] &= ~0x1;
 		spin_unlock_irqrestore(&nc->lock, flags);
 
 		spin_lock_irqsave(&ndp->lock, flags);
-		nc->state = NCSI_CHANNEL_INACTIVE;
+		nc->state = NCSI_CHANNEL_ACTIVE;
 		list_add_tail_rcu(&nc->link, &ndp->channel_queue);
 		spin_unlock_irqrestore(&ndp->lock, flags);
 		ncsi_process_next_channel(ndp);
@@ -732,6 +737,10 @@
 	if (index < 0) {
 		netdev_err(ndp->ndev.dev,
 			   "Failed to add new VLAN tag, error %d\n", index);
+		if (index == -ENOSPC)
+			netdev_err(ndp->ndev.dev,
+				   "Channel %u already has all VLAN filters set\n",
+				   nc->id);
 		return -1;
 	}
 
@@ -998,12 +1007,15 @@
 	struct ncsi_package *np;
 	struct ncsi_channel *nc;
 	unsigned int cap;
+	bool has_channel = false;
 
 	/* The hardware arbitration is disabled if any one channel
 	 * doesn't support explicitly.
 	 */
 	NCSI_FOR_EACH_PACKAGE(ndp, np) {
 		NCSI_FOR_EACH_CHANNEL(np, nc) {
+			has_channel = true;
+
 			cap = nc->caps[NCSI_CAP_GENERIC].cap;
 			if (!(cap & NCSI_CAP_GENERIC_HWA) ||
 			    (cap & NCSI_CAP_GENERIC_HWA_MASK) !=
@@ -1014,8 +1026,13 @@
 		}
 	}
 
-	ndp->flags |= NCSI_DEV_HWA;
-	return true;
+	if (has_channel) {
+		ndp->flags |= NCSI_DEV_HWA;
+		return true;
+	}
+
+	ndp->flags &= ~NCSI_DEV_HWA;
+	return false;
 }
 
 static int ncsi_enable_hwa(struct ncsi_dev_priv *ndp)
@@ -1403,7 +1420,6 @@
 
 int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 {
-	struct ncsi_channel_filter *ncf;
 	struct ncsi_dev_priv *ndp;
 	unsigned int n_vids = 0;
 	struct vlan_vid *vlan;
@@ -1420,7 +1436,6 @@
 	}
 
 	ndp = TO_NCSI_DEV_PRIV(nd);
-	ncf = ndp->hot_channel->filters[NCSI_FILTER_VLAN];
 
 	/* Add the VLAN id to our internal list */
 	list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) {
@@ -1431,12 +1446,11 @@
 			return 0;
 		}
 	}
-
-	if (n_vids >= ncf->total) {
-		netdev_info(dev,
-			    "NCSI Channel supports up to %u VLAN tags but %u are already set\n",
-			    ncf->total, n_vids);
-		return -EINVAL;
+	if (n_vids >= NCSI_MAX_VLAN_VIDS) {
+		netdev_warn(dev,
+			    "tried to add vlan id %u but NCSI max already registered (%u)\n",
+			    vid, NCSI_MAX_VLAN_VIDS);
+		return -ENOSPC;
 	}
 
 	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 265b9a8..927dad4 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -959,7 +959,7 @@
 	{ NCSI_PKT_RSP_EGMF,    4, ncsi_rsp_handler_egmf    },
 	{ NCSI_PKT_RSP_DGMF,    4, ncsi_rsp_handler_dgmf    },
 	{ NCSI_PKT_RSP_SNFC,    4, ncsi_rsp_handler_snfc    },
-	{ NCSI_PKT_RSP_GVI,    36, ncsi_rsp_handler_gvi     },
+	{ NCSI_PKT_RSP_GVI,    40, ncsi_rsp_handler_gvi     },
 	{ NCSI_PKT_RSP_GC,     32, ncsi_rsp_handler_gc      },
 	{ NCSI_PKT_RSP_GP,     -1, ncsi_rsp_handler_gp      },
 	{ NCSI_PKT_RSP_GCPS,  172, ncsi_rsp_handler_gcps    },
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e495b5e..cf84f7b 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1191,14 +1191,17 @@
 	      from->family == to->family))
 		return -IPSET_ERR_TYPE_MISMATCH;
 
-	if (from->ref_netlink || to->ref_netlink)
+	write_lock_bh(&ip_set_ref_lock);
+
+	if (from->ref_netlink || to->ref_netlink) {
+		write_unlock_bh(&ip_set_ref_lock);
 		return -EBUSY;
+	}
 
 	strncpy(from_name, from->name, IPSET_MAXNAMELEN);
 	strncpy(from->name, to->name, IPSET_MAXNAMELEN);
 	strncpy(to->name, from_name, IPSET_MAXNAMELEN);
 
-	write_lock_bh(&ip_set_ref_lock);
 	swap(from->ref, to->ref);
 	ip_set(inst, from_id) = to;
 	ip_set(inst, to_id) = from;
@@ -2072,25 +2075,28 @@
 static int __init
 ip_set_init(void)
 {
-	int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
+	int ret = register_pernet_subsys(&ip_set_net_ops);
 
-	if (ret != 0) {
-		pr_err("ip_set: cannot register with nfnetlink.\n");
+	if (ret) {
+		pr_err("ip_set: cannot register pernet_subsys.\n");
 		return ret;
 	}
+
+	ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
+	if (ret != 0) {
+		pr_err("ip_set: cannot register with nfnetlink.\n");
+		unregister_pernet_subsys(&ip_set_net_ops);
+		return ret;
+	}
+
 	ret = nf_register_sockopt(&so_set);
 	if (ret != 0) {
 		pr_err("SO_SET registry failed: %d\n", ret);
 		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+		unregister_pernet_subsys(&ip_set_net_ops);
 		return ret;
 	}
-	ret = register_pernet_subsys(&ip_set_net_ops);
-	if (ret) {
-		pr_err("ip_set: cannot register pernet_subsys.\n");
-		nf_unregister_sockopt(&so_set);
-		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-		return ret;
-	}
+
 	pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL);
 	return 0;
 }
@@ -2098,9 +2104,10 @@
 static void __exit
 ip_set_fini(void)
 {
-	unregister_pernet_subsys(&ip_set_net_ops);
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+
+	unregister_pernet_subsys(&ip_set_net_ops);
 	pr_debug("these are the famous last words\n");
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index f236c0b..51063d9 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -1041,12 +1041,24 @@
 static int
 mtype_head(struct ip_set *set, struct sk_buff *skb)
 {
-	const struct htype *h = set->data;
+	struct htype *h = set->data;
 	const struct htable *t;
 	struct nlattr *nested;
 	size_t memsize;
 	u8 htable_bits;
 
+	/* If any members have expired, set->elements will be wrong
+	 * mytype_expire function will update it with the right count.
+	 * we do not hold set->lock here, so grab it first.
+	 * set->elements can still be incorrect in the case of a huge set,
+	 * because elements might time out during the listing.
+	 */
+	if (SET_WITH_TIMEOUT(set)) {
+		spin_lock_bh(&set->lock);
+		mtype_expire(set, h);
+		spin_unlock_bh(&set->lock);
+	}
+
 	rcu_read_lock_bh();
 	t = rcu_dereference_bh_nfnl(h->table);
 	memsize = mtype_ahash_memsize(h, t) + set->ext_size;
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index 20bfbd3..613eb21 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -123,13 +123,12 @@
 		return ret;
 
 	ip &= ip_set_hostmask(h->netmask);
+	e.ip = htonl(ip);
+	if (e.ip == 0)
+		return -IPSET_ERR_HASH_ELEM;
 
-	if (adt == IPSET_TEST) {
-		e.ip = htonl(ip);
-		if (e.ip == 0)
-			return -IPSET_ERR_HASH_ELEM;
+	if (adt == IPSET_TEST)
 		return adtfn(set, &e, &ext, &ext, flags);
-	}
 
 	ip_to = ip;
 	if (tb[IPSET_ATTR_IP_TO]) {
@@ -148,17 +147,20 @@
 
 	hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
 
-	if (retried)
+	if (retried) {
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip += hosts) {
 		e.ip = htonl(ip);
-		if (e.ip == 0)
-			return -IPSET_ERR_HASH_ELEM;
+	}
+	for (; ip <= ip_to;) {
 		ret = adtfn(set, &e, &ext, &ext, flags);
-
 		if (ret && !ip_set_eexist(ret, flags))
 			return ret;
 
+		ip += hosts;
+		e.ip = htonl(ip);
+		if (e.ip == 0)
+			return 0;
+
 		ret = 0;
 	}
 	return ret;
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index b64cf14..f3ba834 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -149,7 +149,7 @@
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		e.ip = htonl(ip);
 		ret = adtfn(set, &e, &ext, &ext, flags);
 
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index f438740..ddb8039 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -178,7 +178,7 @@
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
 		for (; p <= port_to; p++) {
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 6215fb8..a7f4d7a 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -185,7 +185,7 @@
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
 		for (; p <= port_to; p++) {
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 5ab1b99..a2f19b9 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -271,7 +271,7 @@
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		e.ip = htonl(ip);
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
@@ -281,7 +281,7 @@
 			      ip == ntohl(h->next.ip) &&
 			      p == ntohs(h->next.port)
 				? ntohl(h->next.ip2) : ip2_from;
-			while (!after(ip2, ip2_to)) {
+			while (ip2 <= ip2_to) {
 				e.ip2 = htonl(ip2);
 				ip2_last = ip_set_range_to_cidr(ip2, ip2_to,
 								&cidr);
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 5d9e8954..1c67a17 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -193,7 +193,7 @@
 	}
 	if (retried)
 		ip = ntohl(h->next.ip);
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
 		ret = adtfn(set, &e, &ext, &ext, flags);
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 44cf119..d417074 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -255,7 +255,7 @@
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
 		ret = adtfn(set, &e, &ext, &ext, flags);
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index db614e1..7f9ae2e 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -250,13 +250,13 @@
 	if (retried)
 		ip = ntohl(h->next.ip[0]);
 
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip[0] = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
 		ip2 = (retried &&
 		       ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1])
 						   : ip2_from;
-		while (!after(ip2, ip2_to)) {
+		while (ip2 <= ip2_to) {
 			e.ip[1] = htonl(ip2);
 			last2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]);
 			ret = adtfn(set, &e, &ext, &ext, flags);
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 54b64b6..e6ef382 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -241,7 +241,7 @@
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &cidr);
 		e.cidr = cidr - 1;
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index aff8469..8602f25 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -291,7 +291,7 @@
 	if (retried)
 		ip = ntohl(h->next.ip[0]);
 
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip[0] = htonl(ip);
 		ip_last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
 		p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port)
@@ -301,7 +301,7 @@
 			ip2 = (retried && ip == ntohl(h->next.ip[0]) &&
 			       p == ntohs(h->next.port)) ? ntohl(h->next.ip[1])
 							 : ip2_from;
-			while (!after(ip2, ip2_to)) {
+			while (ip2 <= ip2_to) {
 				e.ip[1] = htonl(ip2);
 				ip2_last = ip_set_range_to_cidr(ip2, ip2_to,
 								&e.cidr[1]);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 90d3968..4527921 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -921,6 +921,7 @@
 {
 	struct sk_buff *new_skb = NULL;
 	struct iphdr *old_iph = NULL;
+	__u8 old_dsfield;
 #ifdef CONFIG_IP_VS_IPV6
 	struct ipv6hdr *old_ipv6h = NULL;
 #endif
@@ -945,7 +946,7 @@
 			*payload_len =
 				ntohs(old_ipv6h->payload_len) +
 				sizeof(*old_ipv6h);
-		*dsfield = ipv6_get_dsfield(old_ipv6h);
+		old_dsfield = ipv6_get_dsfield(old_ipv6h);
 		*ttl = old_ipv6h->hop_limit;
 		if (df)
 			*df = 0;
@@ -960,12 +961,15 @@
 
 		/* fix old IP header checksum */
 		ip_send_check(old_iph);
-		*dsfield = ipv4_get_dsfield(old_iph);
+		old_dsfield = ipv4_get_dsfield(old_iph);
 		*ttl = old_iph->ttl;
 		if (payload_len)
 			*payload_len = ntohs(old_iph->tot_len);
 	}
 
+	/* Implement full-functionality option for ECN encapsulation */
+	*dsfield = INET_ECN_encapsulate(old_dsfield, old_dsfield);
+
 	return skb;
 error:
 	kfree_skb(skb);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index f393a70..af8345f 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -429,7 +429,7 @@
 
 		srchash = hash_by_src(net,
 				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
-		lock = &nf_nat_locks[srchash % ARRAY_SIZE(nf_nat_locks)];
+		lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS];
 		spin_lock_bh(lock);
 		hlist_add_head_rcu(&ct->nat_bysource,
 				   &nf_nat_bysource[srchash]);
@@ -532,9 +532,9 @@
 	unsigned int h;
 
 	h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
-	spin_lock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]);
+	spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
 	hlist_del_rcu(&ct->nat_bysource);
-	spin_unlock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]);
+	spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
 }
 
 static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
@@ -807,8 +807,8 @@
 
 	/* Leave them the same for the moment. */
 	nf_nat_htable_size = nf_conntrack_htable_size;
-	if (nf_nat_htable_size < ARRAY_SIZE(nf_nat_locks))
-		nf_nat_htable_size = ARRAY_SIZE(nf_nat_locks);
+	if (nf_nat_htable_size < CONNTRACK_LOCKS)
+		nf_nat_htable_size = CONNTRACK_LOCKS;
 
 	nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0);
 	if (!nf_nat_bysource)
@@ -821,7 +821,7 @@
 		return ret;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(nf_nat_locks); i++)
+	for (i = 0; i < CONNTRACK_LOCKS; i++)
 		spin_lock_init(&nf_nat_locks[i]);
 
 	nf_ct_helper_expectfn_register(&follow_master_nat);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9299271..64e1ee0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1048,7 +1048,7 @@
 		if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name))
 			goto nla_put_failure;
 
-		if (nft_dump_stats(skb, nft_base_chain(chain)->stats))
+		if (basechain->stats && nft_dump_stats(skb, basechain->stats))
 			goto nla_put_failure;
 	}
 
@@ -1487,8 +1487,8 @@
 
 		chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME],
 						genmask);
-		if (IS_ERR(chain2))
-			return PTR_ERR(chain2);
+		if (!IS_ERR(chain2))
+			return -EEXIST;
 	}
 
 	if (nla[NFTA_CHAIN_COUNTERS]) {
@@ -2741,8 +2741,10 @@
 	list_for_each_entry(i, &ctx->table->sets, list) {
 		if (!nft_is_active_next(ctx->net, i))
 			continue;
-		if (!strcmp(set->name, i->name))
+		if (!strcmp(set->name, i->name)) {
+			kfree(set->name);
 			return -ENFILE;
+		}
 	}
 	return 0;
 }
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index c83a3b5..d8571f4 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -892,7 +892,7 @@
 		if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0)
 			return ERR_PTR(-EFAULT);
 
-		strlcpy(info->name, compat_tmp.name, sizeof(info->name));
+		memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1);
 		info->num_counters = compat_tmp.num_counters;
 		user += sizeof(compat_tmp);
 	} else
@@ -905,9 +905,9 @@
 		if (copy_from_user(info, user, sizeof(*info)) != 0)
 			return ERR_PTR(-EFAULT);
 
-		info->name[sizeof(info->name) - 1] = '\0';
 		user += sizeof(*info);
 	}
+	info->name[sizeof(info->name) - 1] = '\0';
 
 	size = sizeof(struct xt_counters);
 	size *= info->num_counters;
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 38986a9..2912393 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/syscalls.h>
 #include <linux/skbuff.h>
 #include <linux/filter.h>
 #include <linux/bpf.h>
@@ -49,6 +50,22 @@
 	return 0;
 }
 
+static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret)
+{
+	mm_segment_t oldfs = get_fs();
+	int retval, fd;
+
+	set_fs(KERNEL_DS);
+	fd = bpf_obj_get_user(path);
+	set_fs(oldfs);
+	if (fd < 0)
+		return fd;
+
+	retval = __bpf_mt_check_fd(fd, ret);
+	sys_close(fd);
+	return retval;
+}
+
 static int bpf_mt_check(const struct xt_mtchk_param *par)
 {
 	struct xt_bpf_info *info = par->matchinfo;
@@ -66,9 +83,10 @@
 		return __bpf_mt_check_bytecode(info->bpf_program,
 					       info->bpf_program_num_elem,
 					       &info->filter);
-	else if (info->mode == XT_BPF_MODE_FD_PINNED ||
-		 info->mode == XT_BPF_MODE_FD_ELF)
+	else if (info->mode == XT_BPF_MODE_FD_ELF)
 		return __bpf_mt_check_fd(info->fd, &info->filter);
+	else if (info->mode == XT_BPF_MODE_PATH_PINNED)
+		return __bpf_mt_check_path(info->path, &info->filter);
 	else
 		return -EINVAL;
 }
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index e75ef39..575d215 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -76,7 +76,7 @@
 			transparent = nf_sk_is_transparent(sk);
 
 		if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
-		    transparent)
+		    transparent && sk_fullsock(sk))
 			pskb->mark = sk->sk_mark;
 
 		if (sk != skb->sk)
@@ -133,7 +133,7 @@
 			transparent = nf_sk_is_transparent(sk);
 
 		if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
-		    transparent)
+		    transparent && sk_fullsock(sk))
 			pskb->mark = sk->sk_mark;
 
 		if (sk != skb->sk)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 3278077..b93148e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2266,14 +2266,18 @@
 	cb->min_dump_alloc = control->min_dump_alloc;
 	cb->skb = skb;
 
+	if (cb->start) {
+		ret = cb->start(cb);
+		if (ret)
+			goto error_unlock;
+	}
+
 	nlk->cb_running = true;
 
 	mutex_unlock(nlk->cb_mutex);
 
-	if (cb->start)
-		cb->start(cb);
-
 	ret = netlink_dump(sk);
+
 	sock_put(sk);
 
 	if (ret)
@@ -2303,6 +2307,7 @@
 	size_t tlvlen = 0;
 	struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk);
 	unsigned int flags = 0;
+	bool nlk_has_extack = nlk->flags & NETLINK_F_EXT_ACK;
 
 	/* Error messages get the original request appened, unless the user
 	 * requests to cap the error message, and get extra error data if
@@ -2313,7 +2318,7 @@
 			payload += nlmsg_len(nlh);
 		else
 			flags |= NLM_F_CAPPED;
-		if (nlk->flags & NETLINK_F_EXT_ACK && extack) {
+		if (nlk_has_extack && extack) {
 			if (extack->_msg)
 				tlvlen += nla_total_size(strlen(extack->_msg) + 1);
 			if (extack->bad_attr)
@@ -2322,8 +2327,7 @@
 	} else {
 		flags |= NLM_F_CAPPED;
 
-		if (nlk->flags & NETLINK_F_EXT_ACK &&
-		    extack && extack->cookie_len)
+		if (nlk_has_extack && extack && extack->cookie_len)
 			tlvlen += nla_total_size(extack->cookie_len);
 	}
 
@@ -2351,7 +2355,7 @@
 	errmsg->error = err;
 	memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh));
 
-	if (nlk->flags & NETLINK_F_EXT_ACK && extack) {
+	if (nlk_has_extack && extack) {
 		if (err) {
 			if (extack->_msg)
 				WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c261729..2986941 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1684,10 +1684,6 @@
 
 	mutex_lock(&fanout_mutex);
 
-	err = -EINVAL;
-	if (!po->running)
-		goto out;
-
 	err = -EALREADY;
 	if (po->fanout)
 		goto out;
@@ -1749,7 +1745,10 @@
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
-	if (match->type == type &&
+
+	spin_lock(&po->bind_lock);
+	if (po->running &&
+	    match->type == type &&
 	    match->prot_hook.type == po->prot_hook.type &&
 	    match->prot_hook.dev == po->prot_hook.dev) {
 		err = -ENOSPC;
@@ -1761,9 +1760,16 @@
 			err = 0;
 		}
 	}
+	spin_unlock(&po->bind_lock);
+
+	if (err && !refcount_read(&match->sk_ref)) {
+		list_del(&match->list);
+		kfree(match);
+	}
+
 out:
 	if (err && rollover) {
-		kfree(rollover);
+		kfree_rcu(rollover, rcu);
 		po->rollover = NULL;
 	}
 	mutex_unlock(&fanout_mutex);
@@ -1790,8 +1796,10 @@
 		else
 			f = NULL;
 
-		if (po->rollover)
+		if (po->rollover) {
 			kfree_rcu(po->rollover, rcu);
+			po->rollover = NULL;
+		}
 	}
 	mutex_unlock(&fanout_mutex);
 
@@ -2834,6 +2842,7 @@
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	struct packet_sock *po = pkt_sk(sk);
+	bool has_vnet_hdr = false;
 	int hlen, tlen, linear;
 	int extra_len = 0;
 
@@ -2877,6 +2886,7 @@
 		err = packet_snd_vnet_parse(msg, &len, &vnet_hdr);
 		if (err)
 			goto out_unlock;
+		has_vnet_hdr = true;
 	}
 
 	if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
@@ -2935,7 +2945,7 @@
 	skb->priority = sk->sk_priority;
 	skb->mark = sockc.mark;
 
-	if (po->has_vnet_hdr) {
+	if (has_vnet_hdr) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
 		if (err)
 			goto out_free;
@@ -3063,13 +3073,15 @@
 	int ret = 0;
 	bool unlisted = false;
 
-	if (po->fanout)
-		return -EINVAL;
-
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
 	rcu_read_lock();
 
+	if (po->fanout) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	if (name) {
 		dev = dev_get_by_name_rcu(sock_net(sk), name);
 		if (!dev) {
@@ -3841,6 +3853,7 @@
 	void *data = &val;
 	union tpacket_stats_u st;
 	struct tpacket_rollover_stats rstats;
+	struct packet_rollover *rollover;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3919,13 +3932,18 @@
 		       0);
 		break;
 	case PACKET_ROLLOVER_STATS:
-		if (!po->rollover)
+		rcu_read_lock();
+		rollover = rcu_dereference(po->rollover);
+		if (rollover) {
+			rstats.tp_all = atomic_long_read(&rollover->num);
+			rstats.tp_huge = atomic_long_read(&rollover->num_huge);
+			rstats.tp_failed = atomic_long_read(&rollover->num_failed);
+			data = &rstats;
+			lv = sizeof(rstats);
+		}
+		rcu_read_unlock();
+		if (!rollover)
 			return -EINVAL;
-		rstats.tp_all = atomic_long_read(&po->rollover->num);
-		rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
-		rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
-		data = &rstats;
-		lv = sizeof(rstats);
 		break;
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 6ab39db..8557a1c 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -661,13 +661,15 @@
 			}
 		}
 
-		rds_ib_set_wr_signal_state(ic, send, 0);
+		rds_ib_set_wr_signal_state(ic, send, false);
 
 		/*
 		 * Always signal the last one if we're stopping due to flow control.
 		 */
-		if (ic->i_flowctl && flow_controlled && i == (work_alloc-1))
-			send->s_wr.send_flags |= IB_SEND_SIGNALED | IB_SEND_SOLICITED;
+		if (ic->i_flowctl && flow_controlled && i == (work_alloc - 1)) {
+			rds_ib_set_wr_signal_state(ic, send, true);
+			send->s_wr.send_flags |= IB_SEND_SOLICITED;
+		}
 
 		if (send->s_wr.send_flags & IB_SEND_SIGNALED)
 			nr_sig++;
@@ -705,11 +707,8 @@
 	if (scat == &rm->data.op_sg[rm->data.op_count]) {
 		prev->s_op = ic->i_data_op;
 		prev->s_wr.send_flags |= IB_SEND_SOLICITED;
-		if (!(prev->s_wr.send_flags & IB_SEND_SIGNALED)) {
-			ic->i_unsignaled_wrs = rds_ib_sysctl_max_unsig_wrs;
-			prev->s_wr.send_flags |= IB_SEND_SIGNALED;
-			nr_sig++;
-		}
+		if (!(prev->s_wr.send_flags & IB_SEND_SIGNALED))
+			nr_sig += rds_ib_set_wr_signal_state(ic, prev, true);
 		ic->i_data_op = NULL;
 	}
 
@@ -792,6 +791,7 @@
 		send->s_atomic_wr.compare_add_mask = op->op_m_fadd.nocarry_mask;
 		send->s_atomic_wr.swap_mask = 0;
 	}
+	send->s_wr.send_flags = 0;
 	nr_sig = rds_ib_set_wr_signal_state(ic, send, op->op_notify);
 	send->s_atomic_wr.wr.num_sge = 1;
 	send->s_atomic_wr.wr.next = NULL;
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index fb17552..4b0a828 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -308,10 +308,11 @@
 	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len,
 				     gfp);
 	/* The socket has been unlocked. */
-	if (!IS_ERR(call))
+	if (!IS_ERR(call)) {
 		call->notify_rx = notify_rx;
+		mutex_unlock(&call->user_mutex);
+	}
 
-	mutex_unlock(&call->user_mutex);
 	_leave(" = %p", call);
 	return call;
 }
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index ec986ae..a9f9a2cc 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -264,6 +264,7 @@
 
 static void __exit sample_cleanup_module(void)
 {
+	rcu_barrier();
 	tcf_unregister_action(&act_sample_ops, &sample_net_ops);
 }
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0b2219a..b2d3107 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -77,6 +77,8 @@
 }
 EXPORT_SYMBOL(register_tcf_proto_ops);
 
+static struct workqueue_struct *tc_filter_wq;
+
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 {
 	struct tcf_proto_ops *t;
@@ -86,6 +88,7 @@
 	 * tcf_proto_ops's destroy() handler.
 	 */
 	rcu_barrier();
+	flush_workqueue(tc_filter_wq);
 
 	write_lock(&cls_mod_lock);
 	list_for_each_entry(t, &tcf_proto_base, head) {
@@ -100,6 +103,12 @@
 }
 EXPORT_SYMBOL(unregister_tcf_proto_ops);
 
+bool tcf_queue_work(struct work_struct *work)
+{
+	return queue_work(tc_filter_wq, work);
+}
+EXPORT_SYMBOL(tcf_queue_work);
+
 /* Select new prio value from the range, managed by kernel. */
 
 static inline u32 tcf_auto_prio(struct tcf_proto *tp)
@@ -266,6 +275,23 @@
 }
 EXPORT_SYMBOL(tcf_block_get);
 
+static void tcf_block_put_final(struct work_struct *work)
+{
+	struct tcf_block *block = container_of(work, struct tcf_block, work);
+	struct tcf_chain *chain, *tmp;
+
+	rtnl_lock();
+	/* Only chain 0 should be still here. */
+	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+		tcf_chain_put(chain);
+	rtnl_unlock();
+	kfree(block);
+}
+
+/* XXX: Standalone actions are not allowed to jump to any chain, and bound
+ * actions should be all removed after flushing. However, filters are now
+ * destroyed in tc filter workqueue with RTNL lock, they can not race here.
+ */
 void tcf_block_put(struct tcf_block *block)
 {
 	struct tcf_chain *chain, *tmp;
@@ -273,32 +299,15 @@
 	if (!block)
 		return;
 
-	/* XXX: Standalone actions are not allowed to jump to any chain, and
-	 * bound actions should be all removed after flushing. However,
-	 * filters are destroyed in RCU callbacks, we have to hold the chains
-	 * first, otherwise we would always race with RCU callbacks on this list
-	 * without proper locking.
-	 */
-
-	/* Wait for existing RCU callbacks to cool down. */
-	rcu_barrier();
-
-	/* Hold a refcnt for all chains, except 0, in case they are gone. */
-	list_for_each_entry(chain, &block->chain_list, list)
-		if (chain->index)
-			tcf_chain_hold(chain);
-
-	/* No race on the list, because no chain could be destroyed. */
-	list_for_each_entry(chain, &block->chain_list, list)
+	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
 		tcf_chain_flush(chain);
 
-	/* Wait for RCU callbacks to release the reference count. */
+	INIT_WORK(&block->work, tcf_block_put_final);
+	/* Wait for RCU callbacks to release the reference count and make
+	 * sure their works have been queued before this.
+	 */
 	rcu_barrier();
-
-	/* At this point, all the chains should have refcnt == 1. */
-	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
-		tcf_chain_put(chain);
-	kfree(block);
+	tcf_queue_work(&block->work);
 }
 EXPORT_SYMBOL(tcf_block_put);
 
@@ -879,6 +888,7 @@
 #ifdef CONFIG_NET_CLS_ACT
 	LIST_HEAD(actions);
 
+	ASSERT_RTNL();
 	tcf_exts_to_list(exts, &actions);
 	tcf_action_destroy(&actions, TCA_ACT_UNBIND);
 	kfree(exts->actions);
@@ -1030,6 +1040,10 @@
 
 static int __init tc_filter_init(void)
 {
+	tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0);
+	if (!tc_filter_wq)
+		return -ENOMEM;
+
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter,
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index d89ebaf..f177649 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -34,7 +34,10 @@
 	struct tcf_result	res;
 	struct tcf_proto	*tp;
 	struct list_head	link;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -82,13 +85,24 @@
 	return 0;
 }
 
+static void basic_delete_filter_work(struct work_struct *work)
+{
+	struct basic_filter *f = container_of(work, struct basic_filter, work);
+
+	rtnl_lock();
+	tcf_exts_destroy(&f->exts);
+	tcf_em_tree_destroy(&f->ematches);
+	rtnl_unlock();
+
+	kfree(f);
+}
+
 static void basic_delete_filter(struct rcu_head *head)
 {
 	struct basic_filter *f = container_of(head, struct basic_filter, rcu);
 
-	tcf_exts_destroy(&f->exts);
-	tcf_em_tree_destroy(&f->ematches);
-	kfree(f);
+	INIT_WORK(&f->work, basic_delete_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void basic_destroy(struct tcf_proto *tp)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 520c502..037a3ae 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -49,7 +49,10 @@
 	struct sock_filter *bpf_ops;
 	const char *bpf_name;
 	struct tcf_proto *tp;
-	struct rcu_head rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 };
 
 static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
@@ -257,9 +260,21 @@
 	kfree(prog);
 }
 
+static void cls_bpf_delete_prog_work(struct work_struct *work)
+{
+	struct cls_bpf_prog *prog = container_of(work, struct cls_bpf_prog, work);
+
+	rtnl_lock();
+	__cls_bpf_delete_prog(prog);
+	rtnl_unlock();
+}
+
 static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu)
 {
-	__cls_bpf_delete_prog(container_of(rcu, struct cls_bpf_prog, rcu));
+	struct cls_bpf_prog *prog = container_of(rcu, struct cls_bpf_prog, rcu);
+
+	INIT_WORK(&prog->work, cls_bpf_delete_prog_work);
+	tcf_queue_work(&prog->work);
 }
 
 static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog)
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index d48452f..a97e069 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -23,7 +23,10 @@
 	struct tcf_exts		exts;
 	struct tcf_ematch_tree	ematches;
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -57,15 +60,26 @@
 	[TCA_CGROUP_EMATCHES]	= { .type = NLA_NESTED },
 };
 
+static void cls_cgroup_destroy_work(struct work_struct *work)
+{
+	struct cls_cgroup_head *head = container_of(work,
+						    struct cls_cgroup_head,
+						    work);
+	rtnl_lock();
+	tcf_exts_destroy(&head->exts);
+	tcf_em_tree_destroy(&head->ematches);
+	kfree(head);
+	rtnl_unlock();
+}
+
 static void cls_cgroup_destroy_rcu(struct rcu_head *root)
 {
 	struct cls_cgroup_head *head = container_of(root,
 						    struct cls_cgroup_head,
 						    rcu);
 
-	tcf_exts_destroy(&head->exts);
-	tcf_em_tree_destroy(&head->ematches);
-	kfree(head);
+	INIT_WORK(&head->work, cls_cgroup_destroy_work);
+	tcf_queue_work(&head->work);
 }
 
 static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 2a3a60e..67f3a2a 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -57,7 +57,10 @@
 	u32			divisor;
 	u32			baseclass;
 	u32			hashrnd;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static inline u32 addr_fold(void *addr)
@@ -369,14 +372,24 @@
 	[TCA_FLOW_PERTURB]	= { .type = NLA_U32 },
 };
 
-static void flow_destroy_filter(struct rcu_head *head)
+static void flow_destroy_filter_work(struct work_struct *work)
 {
-	struct flow_filter *f = container_of(head, struct flow_filter, rcu);
+	struct flow_filter *f = container_of(work, struct flow_filter, work);
 
+	rtnl_lock();
 	del_timer_sync(&f->perturb_timer);
 	tcf_exts_destroy(&f->exts);
 	tcf_em_tree_destroy(&f->ematches);
 	kfree(f);
+	rtnl_unlock();
+}
+
+static void flow_destroy_filter(struct rcu_head *head)
+{
+	struct flow_filter *f = container_of(head, struct flow_filter, rcu);
+
+	INIT_WORK(&f->work, flow_destroy_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static int flow_change(struct net *net, struct sk_buff *in_skb,
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 1a267e7..5b5722c 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -87,7 +87,10 @@
 	struct list_head list;
 	u32 handle;
 	u32 flags;
-	struct rcu_head	rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head	rcu;
+	};
 	struct net_device *hw_dev;
 };
 
@@ -215,12 +218,22 @@
 	return 0;
 }
 
+static void fl_destroy_filter_work(struct work_struct *work)
+{
+	struct cls_fl_filter *f = container_of(work, struct cls_fl_filter, work);
+
+	rtnl_lock();
+	tcf_exts_destroy(&f->exts);
+	kfree(f);
+	rtnl_unlock();
+}
+
 static void fl_destroy_filter(struct rcu_head *head)
 {
 	struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu);
 
-	tcf_exts_destroy(&f->exts);
-	kfree(f);
+	INIT_WORK(&f->work, fl_destroy_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
@@ -234,6 +247,7 @@
 	tc_cls_common_offload_init(&cls_flower.common, tp);
 	cls_flower.command = TC_CLSFLOWER_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
+	cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev;
 
 	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, &cls_flower);
 }
@@ -289,6 +303,7 @@
 	cls_flower.command = TC_CLSFLOWER_STATS;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.exts = &f->exts;
+	cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev;
 
 	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER,
 				      &cls_flower);
@@ -922,28 +937,28 @@
 
 		if (!tc_flags_valid(fnew->flags)) {
 			err = -EINVAL;
-			goto errout;
+			goto errout_idr;
 		}
 	}
 
 	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
 	if (err)
-		goto errout;
+		goto errout_idr;
 
 	err = fl_check_assign_mask(head, &mask);
 	if (err)
-		goto errout;
+		goto errout_idr;
 
 	if (!tc_skip_sw(fnew->flags)) {
 		if (!fold && fl_lookup(head, &fnew->mkey)) {
 			err = -EEXIST;
-			goto errout;
+			goto errout_idr;
 		}
 
 		err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
 					     head->ht_params);
 		if (err)
-			goto errout;
+			goto errout_idr;
 	}
 
 	if (!tc_skip_hw(fnew->flags)) {
@@ -952,7 +967,7 @@
 					   &mask.key,
 					   fnew);
 		if (err)
-			goto errout;
+			goto errout_idr;
 	}
 
 	if (!tc_in_hw(fnew->flags))
@@ -981,6 +996,9 @@
 	kfree(tb);
 	return 0;
 
+errout_idr:
+	if (fnew->handle)
+		idr_remove_ext(&head->handle_idr, fnew->handle);
 errout:
 	tcf_exts_destroy(&fnew->exts);
 	kfree(fnew);
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 941245a..99183b8 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -46,7 +46,10 @@
 #endif /* CONFIG_NET_CLS_IND */
 	struct tcf_exts		exts;
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static u32 fw_hash(u32 handle)
@@ -119,12 +122,22 @@
 	return 0;
 }
 
+static void fw_delete_filter_work(struct work_struct *work)
+{
+	struct fw_filter *f = container_of(work, struct fw_filter, work);
+
+	rtnl_lock();
+	tcf_exts_destroy(&f->exts);
+	kfree(f);
+	rtnl_unlock();
+}
+
 static void fw_delete_filter(struct rcu_head *head)
 {
 	struct fw_filter *f = container_of(head, struct fw_filter, rcu);
 
-	tcf_exts_destroy(&f->exts);
-	kfree(f);
+	INIT_WORK(&f->work, fw_delete_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void fw_destroy(struct tcf_proto *tp)
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 21cc45ca..c33f711 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -21,7 +21,10 @@
 	struct tcf_result res;
 	u32 handle;
 	u32 flags;
-	struct rcu_head	rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head	rcu;
+	};
 };
 
 static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -32,6 +35,7 @@
 	if (tc_skip_sw(head->flags))
 		return -1;
 
+	*res = head->res;
 	return tcf_exts_exec(skb, &head->exts, res);
 }
 
@@ -40,13 +44,23 @@
 	return 0;
 }
 
+static void mall_destroy_work(struct work_struct *work)
+{
+	struct cls_mall_head *head = container_of(work, struct cls_mall_head,
+						  work);
+	rtnl_lock();
+	tcf_exts_destroy(&head->exts);
+	kfree(head);
+	rtnl_unlock();
+}
+
 static void mall_destroy_rcu(struct rcu_head *rcu)
 {
 	struct cls_mall_head *head = container_of(rcu, struct cls_mall_head,
 						  rcu);
 
-	tcf_exts_destroy(&head->exts);
-	kfree(head);
+	INIT_WORK(&head->work, mall_destroy_work);
+	tcf_queue_work(&head->work);
 }
 
 static int mall_replace_hw_filter(struct tcf_proto *tp,
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 9ddde65..4b14ccd 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -57,7 +57,10 @@
 	u32			handle;
 	struct route4_bucket	*bkt;
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 #define ROUTE4_FAILURE ((struct route4_filter *)(-1L))
@@ -254,12 +257,22 @@
 	return 0;
 }
 
+static void route4_delete_filter_work(struct work_struct *work)
+{
+	struct route4_filter *f = container_of(work, struct route4_filter, work);
+
+	rtnl_lock();
+	tcf_exts_destroy(&f->exts);
+	kfree(f);
+	rtnl_unlock();
+}
+
 static void route4_delete_filter(struct rcu_head *head)
 {
 	struct route4_filter *f = container_of(head, struct route4_filter, rcu);
 
-	tcf_exts_destroy(&f->exts);
-	kfree(f);
+	INIT_WORK(&f->work, route4_delete_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void route4_destroy(struct tcf_proto *tp)
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index b1f6ed4..bdbc541 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -97,7 +97,10 @@
 
 	u32				handle;
 	struct rsvp_session		*sess;
-	struct rcu_head			rcu;
+	union {
+		struct work_struct		work;
+		struct rcu_head			rcu;
+	};
 };
 
 static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid)
@@ -282,12 +285,22 @@
 	return -ENOBUFS;
 }
 
+static void rsvp_delete_filter_work(struct work_struct *work)
+{
+	struct rsvp_filter *f = container_of(work, struct rsvp_filter, work);
+
+	rtnl_lock();
+	tcf_exts_destroy(&f->exts);
+	kfree(f);
+	rtnl_unlock();
+}
+
 static void rsvp_delete_filter_rcu(struct rcu_head *head)
 {
 	struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu);
 
-	tcf_exts_destroy(&f->exts);
-	kfree(f);
+	INIT_WORK(&f->work, rsvp_delete_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 14a7e08..beaa95e 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -27,14 +27,20 @@
 struct tcindex_filter_result {
 	struct tcf_exts		exts;
 	struct tcf_result	res;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 struct tcindex_filter {
 	u16 key;
 	struct tcindex_filter_result result;
 	struct tcindex_filter __rcu *next;
-	struct rcu_head rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 };
 
 
@@ -133,12 +139,34 @@
 	return 0;
 }
 
+static void tcindex_destroy_rexts_work(struct work_struct *work)
+{
+	struct tcindex_filter_result *r;
+
+	r = container_of(work, struct tcindex_filter_result, work);
+	rtnl_lock();
+	tcf_exts_destroy(&r->exts);
+	rtnl_unlock();
+}
+
 static void tcindex_destroy_rexts(struct rcu_head *head)
 {
 	struct tcindex_filter_result *r;
 
 	r = container_of(head, struct tcindex_filter_result, rcu);
-	tcf_exts_destroy(&r->exts);
+	INIT_WORK(&r->work, tcindex_destroy_rexts_work);
+	tcf_queue_work(&r->work);
+}
+
+static void tcindex_destroy_fexts_work(struct work_struct *work)
+{
+	struct tcindex_filter *f = container_of(work, struct tcindex_filter,
+						work);
+
+	rtnl_lock();
+	tcf_exts_destroy(&f->result.exts);
+	kfree(f);
+	rtnl_unlock();
 }
 
 static void tcindex_destroy_fexts(struct rcu_head *head)
@@ -146,8 +174,8 @@
 	struct tcindex_filter *f = container_of(head, struct tcindex_filter,
 						rcu);
 
-	tcf_exts_destroy(&f->result.exts);
-	kfree(f);
+	INIT_WORK(&f->work, tcindex_destroy_fexts_work);
+	tcf_queue_work(&f->work);
 }
 
 static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last)
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 10b8d85..dadd1b3 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -68,7 +68,10 @@
 	u32 __percpu		*pcpu_success;
 #endif
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 	/* The 'sel' field MUST be the last field in structure to allow for
 	 * tc_u32_keys allocated at end of structure.
 	 */
@@ -418,11 +421,21 @@
  * this the u32_delete_key_rcu variant does not free the percpu
  * statistics.
  */
+static void u32_delete_key_work(struct work_struct *work)
+{
+	struct tc_u_knode *key = container_of(work, struct tc_u_knode, work);
+
+	rtnl_lock();
+	u32_destroy_key(key->tp, key, false);
+	rtnl_unlock();
+}
+
 static void u32_delete_key_rcu(struct rcu_head *rcu)
 {
 	struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu);
 
-	u32_destroy_key(key->tp, key, false);
+	INIT_WORK(&key->work, u32_delete_key_work);
+	tcf_queue_work(&key->work);
 }
 
 /* u32_delete_key_freepf_rcu is the rcu callback variant
@@ -432,11 +445,21 @@
  * for the variant that should be used with keys return from
  * u32_init_knode()
  */
+static void u32_delete_key_freepf_work(struct work_struct *work)
+{
+	struct tc_u_knode *key = container_of(work, struct tc_u_knode, work);
+
+	rtnl_lock();
+	u32_destroy_key(key->tp, key, true);
+	rtnl_unlock();
+}
+
 static void u32_delete_key_freepf_rcu(struct rcu_head *rcu)
 {
 	struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu);
 
-	u32_destroy_key(key->tp, key, true);
+	INIT_WORK(&key->work, u32_delete_key_freepf_work);
+	tcf_queue_work(&key->work);
 }
 
 static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c6deb74..22bc6fc 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -301,6 +301,8 @@
 {
 	struct Qdisc *q;
 
+	if (!handle)
+		return NULL;
 	q = qdisc_match_from_root(dev->qdisc, handle);
 	if (q)
 		goto out;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 92237e7..bf8c81e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -685,6 +685,7 @@
 		qdisc->gso_skb = NULL;
 	}
 	qdisc->q.qlen = 0;
+	qdisc->qstats.backlog = 0;
 }
 EXPORT_SYMBOL(qdisc_reset);
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index daaf214..3f88b75 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -958,6 +958,8 @@
 	}
 
 	if (cl != NULL) {
+		int old_flags;
+
 		if (parentid) {
 			if (cl->cl_parent &&
 			    cl->cl_parent->cl_common.classid != parentid)
@@ -978,6 +980,8 @@
 		}
 
 		sch_tree_lock(sch);
+		old_flags = cl->cl_flags;
+
 		if (rsc != NULL)
 			hfsc_change_rsc(cl, rsc, cur_time);
 		if (fsc != NULL)
@@ -986,10 +990,21 @@
 			hfsc_change_usc(cl, usc, cur_time);
 
 		if (cl->qdisc->q.qlen != 0) {
-			if (cl->cl_flags & HFSC_RSC)
-				update_ed(cl, qdisc_peek_len(cl->qdisc));
-			if (cl->cl_flags & HFSC_FSC)
-				update_vf(cl, 0, cur_time);
+			int len = qdisc_peek_len(cl->qdisc);
+
+			if (cl->cl_flags & HFSC_RSC) {
+				if (old_flags & HFSC_RSC)
+					update_ed(cl, len);
+				else
+					init_ed(cl, len);
+			}
+
+			if (cl->cl_flags & HFSC_FSC) {
+				if (old_flags & HFSC_FSC)
+					update_vf(cl, 0, cur_time);
+				else
+					init_vf(cl, len);
+			}
 		}
 		sch_tree_unlock(sch);
 
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 92a0714..621b5ca 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -421,7 +421,7 @@
 {
 	struct dst_entry *dst;
 
-	if (!t)
+	if (sock_owned_by_user(sk) || !t)
 		return;
 	dst = sctp_transport_dst_check(t);
 	if (dst)
@@ -794,7 +794,7 @@
 struct sctp_hash_cmp_arg {
 	const union sctp_addr	*paddr;
 	const struct net	*net;
-	u16			lport;
+	__be16			lport;
 };
 
 static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -820,37 +820,37 @@
 	return err;
 }
 
-static inline u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
+static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
 {
 	const struct sctp_transport *t = data;
 	const union sctp_addr *paddr = &t->ipaddr;
 	const struct net *net = sock_net(t->asoc->base.sk);
-	u16 lport = htons(t->asoc->base.bind_addr.port);
-	u32 addr;
+	__be16 lport = htons(t->asoc->base.bind_addr.port);
+	__u32 addr;
 
 	if (paddr->sa.sa_family == AF_INET6)
 		addr = jhash(&paddr->v6.sin6_addr, 16, seed);
 	else
-		addr = paddr->v4.sin_addr.s_addr;
+		addr = (__force __u32)paddr->v4.sin_addr.s_addr;
 
-	return  jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 |
+	return  jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
 			     (__force __u32)lport, net_hash_mix(net), seed);
 }
 
-static inline u32 sctp_hash_key(const void *data, u32 len, u32 seed)
+static inline __u32 sctp_hash_key(const void *data, u32 len, u32 seed)
 {
 	const struct sctp_hash_cmp_arg *x = data;
 	const union sctp_addr *paddr = x->paddr;
 	const struct net *net = x->net;
-	u16 lport = x->lport;
-	u32 addr;
+	__be16 lport = x->lport;
+	__u32 addr;
 
 	if (paddr->sa.sa_family == AF_INET6)
 		addr = jhash(&paddr->v6.sin6_addr, 16, seed);
 	else
-		addr = paddr->v4.sin_addr.s_addr;
+		addr = (__force __u32)paddr->v4.sin_addr.s_addr;
 
-	return  jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 |
+	return  jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
 			     (__force __u32)lport, net_hash_mix(net), seed);
 }
 
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 51c4887..a6dfa86 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -738,7 +738,7 @@
 /* Was this packet marked by Explicit Congestion Notification? */
 static int sctp_v6_is_ce(const struct sk_buff *skb)
 {
-	return *((__u32 *)(ipv6_hdr(skb))) & htonl(1 << 20);
+	return *((__u32 *)(ipv6_hdr(skb))) & (__force __u32)htonl(1 << 20);
 }
 
 /* Dump the v6 addr to the seq file. */
@@ -882,8 +882,10 @@
 			net = sock_net(&opt->inet.sk);
 			rcu_read_lock();
 			dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id);
-			if (!dev ||
-			    !ipv6_chk_addr(net, &addr->v6.sin6_addr, dev, 0)) {
+			if (!dev || !(opt->inet.freebind ||
+				      net->ipv6.sysctl.ip_nonlocal_bind ||
+				      ipv6_chk_addr(net, &addr->v6.sin6_addr,
+						    dev, 0))) {
 				rcu_read_unlock();
 				return 0;
 			}
diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index 22ed01a..a72a7d9 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -463,6 +463,7 @@
 		.r = r,
 		.net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN),
 	};
+	int pos = cb->args[2];
 
 	/* eps hashtable dumps
 	 * args:
@@ -493,7 +494,8 @@
 		goto done;
 
 	sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
-				net, (int *)&cb->args[2], &commp);
+				net, &pos, &commp);
+	cb->args[2] = pos;
 
 done:
 	cb->args[1] = cb->args[4];
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index ca8f196..514465b 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2854,7 +2854,7 @@
 		addr_param_len = af->to_addr_param(addr, &addr_param);
 		param.param_hdr.type = flags;
 		param.param_hdr.length = htons(paramlen + addr_param_len);
-		param.crr_id = i;
+		param.crr_id = htonl(i);
 
 		sctp_addto_chunk(retval, paramlen, &param);
 		sctp_addto_chunk(retval, addr_param_len, &addr_param);
@@ -2867,7 +2867,7 @@
 		addr_param_len = af->to_addr_param(addr, &addr_param);
 		param.param_hdr.type = SCTP_PARAM_DEL_IP;
 		param.param_hdr.length = htons(paramlen + addr_param_len);
-		param.crr_id = i;
+		param.crr_id = htonl(i);
 
 		sctp_addto_chunk(retval, paramlen, &param);
 		sctp_addto_chunk(retval, addr_param_len, &addr_param);
@@ -3591,7 +3591,7 @@
  */
 struct sctp_chunk *sctp_make_strreset_req(
 					const struct sctp_association *asoc,
-					__u16 stream_num, __u16 *stream_list,
+					__u16 stream_num, __be16 *stream_list,
 					bool out, bool in)
 {
 	struct sctp_strreset_outreq outreq;
@@ -3788,7 +3788,8 @@
 {
 	struct sctp_reconf_chunk *hdr;
 	union sctp_params param;
-	__u16 last = 0, cnt = 0;
+	__be16 last = 0;
+	__u16 cnt = 0;
 
 	hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr;
 	sctp_walk_params(param, hdr, params) {
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index e6a2974..e2d9a4b 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1607,12 +1607,12 @@
 			break;
 
 		case SCTP_CMD_INIT_FAILED:
-			sctp_cmd_init_failed(commands, asoc, cmd->obj.err);
+			sctp_cmd_init_failed(commands, asoc, cmd->obj.u32);
 			break;
 
 		case SCTP_CMD_ASSOC_FAILED:
 			sctp_cmd_assoc_failed(commands, asoc, event_type,
-					      subtype, chunk, cmd->obj.err);
+					      subtype, chunk, cmd->obj.u32);
 			break;
 
 		case SCTP_CMD_INIT_COUNTER_INC:
@@ -1680,8 +1680,8 @@
 		case SCTP_CMD_PROCESS_CTSN:
 			/* Dummy up a SACK for processing. */
 			sackh.cum_tsn_ack = cmd->obj.be32;
-			sackh.a_rwnd = asoc->peer.rwnd +
-					asoc->outqueue.outstanding_bytes;
+			sackh.a_rwnd = htonl(asoc->peer.rwnd +
+					     asoc->outqueue.outstanding_bytes);
 			sackh.num_gap_ack_blocks = 0;
 			sackh.num_dup_tsns = 0;
 			chunk->subh.sack_hdr = &sackh;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d4730ad..6f45d17 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -170,6 +170,36 @@
 	sk_mem_charge(sk, chunk->skb->truesize);
 }
 
+static void sctp_clear_owner_w(struct sctp_chunk *chunk)
+{
+	skb_orphan(chunk->skb);
+}
+
+static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
+				       void (*cb)(struct sctp_chunk *))
+
+{
+	struct sctp_outq *q = &asoc->outqueue;
+	struct sctp_transport *t;
+	struct sctp_chunk *chunk;
+
+	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports)
+		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
+			cb(chunk);
+
+	list_for_each_entry(chunk, &q->retransmit, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->sacked, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->abandoned, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->out_chunk_list, list)
+		cb(chunk);
+}
+
 /* Verify that this is a valid address. */
 static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr,
 				   int len)
@@ -4906,6 +4936,10 @@
 	struct socket *sock;
 	int err = 0;
 
+	/* Do not peel off from one netns to another one. */
+	if (!net_eq(current->nsproxy->net_ns, sock_net(sk)))
+		return -EINVAL;
+
 	if (!asoc)
 		return -EINVAL;
 
@@ -8208,7 +8242,9 @@
 	 * paths won't try to lock it and then oldsk.
 	 */
 	lock_sock_nested(newsk, SINGLE_DEPTH_NESTING);
+	sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w);
 	sctp_assoc_migrate(assoc, newsk);
+	sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w);
 
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 63ea155..fa8371f 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -118,6 +118,7 @@
 	__u16 i, str_nums, *str_list;
 	struct sctp_chunk *chunk;
 	int retval = -EINVAL;
+	__be16 *nstr_list;
 	bool out, in;
 
 	if (!asoc->peer.reconf_capable ||
@@ -148,13 +149,18 @@
 			if (str_list[i] >= stream->incnt)
 				goto out;
 
-	for (i = 0; i < str_nums; i++)
-		str_list[i] = htons(str_list[i]);
-
-	chunk = sctp_make_strreset_req(asoc, str_nums, str_list, out, in);
+	nstr_list = kcalloc(str_nums, sizeof(__be16), GFP_KERNEL);
+	if (!nstr_list) {
+		retval = -ENOMEM;
+		goto out;
+	}
 
 	for (i = 0; i < str_nums; i++)
-		str_list[i] = ntohs(str_list[i]);
+		nstr_list[i] = htons(str_list[i]);
+
+	chunk = sctp_make_strreset_req(asoc, str_nums, nstr_list, out, in);
+
+	kfree(nstr_list);
 
 	if (!chunk) {
 		retval = -ENOMEM;
@@ -305,7 +311,7 @@
 }
 
 static struct sctp_paramhdr *sctp_chunk_lookup_strreset_param(
-			struct sctp_association *asoc, __u32 resp_seq,
+			struct sctp_association *asoc, __be32 resp_seq,
 			__be16 type)
 {
 	struct sctp_chunk *chunk = asoc->strreset_chunk;
@@ -345,8 +351,9 @@
 {
 	struct sctp_strreset_outreq *outreq = param.v;
 	struct sctp_stream *stream = &asoc->stream;
-	__u16 i, nums, flags = 0, *str_p = NULL;
 	__u32 result = SCTP_STRRESET_DENIED;
+	__u16 i, nums, flags = 0;
+	__be16 *str_p = NULL;
 	__u32 request_seq;
 
 	request_seq = ntohl(outreq->request_seq);
@@ -439,8 +446,9 @@
 	struct sctp_stream *stream = &asoc->stream;
 	__u32 result = SCTP_STRRESET_DENIED;
 	struct sctp_chunk *chunk = NULL;
-	__u16 i, nums, *str_p;
 	__u32 request_seq;
+	__u16 i, nums;
+	__be16 *str_p;
 
 	request_seq = ntohl(inreq->request_seq);
 	if (TSN_lt(asoc->strreset_inseq, request_seq) ||
@@ -769,7 +777,7 @@
 
 	if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) {
 		struct sctp_strreset_outreq *outreq;
-		__u16 *str_p;
+		__be16 *str_p;
 
 		outreq = (struct sctp_strreset_outreq *)req;
 		str_p = outreq->list_of_streams;
@@ -794,7 +802,7 @@
 			nums, str_p, GFP_ATOMIC);
 	} else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) {
 		struct sctp_strreset_inreq *inreq;
-		__u16 *str_p;
+		__be16 *str_p;
 
 		/* if the result is performed, it's impossible for inreq */
 		if (result == SCTP_STRRESET_PERFORMED)
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 67abc01..5447228 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -847,7 +847,7 @@
 
 struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
 	const struct sctp_association *asoc, __u16 flags, __u16 stream_num,
-	__u16 *stream_list, gfp_t gfp)
+	__be16 *stream_list, gfp_t gfp)
 {
 	struct sctp_stream_reset_event *sreset;
 	struct sctp_ulpevent *event;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 8c6d24b..745f145 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -282,6 +282,7 @@
 			 __be32 *subnet, u8 *prefix_len)
 {
 	struct dst_entry *dst = sk_dst_get(clcsock->sk);
+	struct in_device *in_dev;
 	struct sockaddr_in addr;
 	int rc = -ENOENT;
 	int len;
@@ -298,14 +299,17 @@
 	/* get address to which the internal TCP socket is bound */
 	kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len);
 	/* analyze IPv4 specific data of net_device belonging to TCP socket */
-	for_ifa(dst->dev->ip_ptr) {
-		if (ifa->ifa_address != addr.sin_addr.s_addr)
+	rcu_read_lock();
+	in_dev = __in_dev_get_rcu(dst->dev);
+	for_ifa(in_dev) {
+		if (!inet_ifa_match(addr.sin_addr.s_addr, ifa))
 			continue;
 		*prefix_len = inet_mask_len(ifa->ifa_mask);
 		*subnet = ifa->ifa_address & ifa->ifa_mask;
 		rc = 0;
 		break;
-	} endfor_ifa(dst->dev->ip_ptr);
+	} endfor_ifa(in_dev);
+	rcu_read_unlock();
 
 out_rel:
 	dst_release(dst);
@@ -509,7 +513,7 @@
 	/* RDMA setup failed, switch back to TCP */
 	smc->use_fallback = true;
 	if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
-		rc = smc_clc_send_decline(smc, reason_code, 0);
+		rc = smc_clc_send_decline(smc, reason_code);
 		if (rc < sizeof(struct smc_clc_msg_decline))
 			goto out_err;
 	}
@@ -804,8 +808,6 @@
 		rc = local_contact;
 		if (rc == -ENOMEM)
 			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
-		else if (rc == -ENOLINK)
-			reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
 		goto decline_rdma;
 	}
 	link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
@@ -899,7 +901,7 @@
 	smc_conn_free(&new_smc->conn);
 	new_smc->use_fallback = true;
 	if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
-		rc = smc_clc_send_decline(new_smc, reason_code, 0);
+		rc = smc_clc_send_decline(new_smc, reason_code);
 		if (rc < sizeof(struct smc_clc_msg_decline))
 			goto out_err;
 	}
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 6e44313e..0ccd6fa 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -149,7 +149,7 @@
 	atomic_t		sndbuf_space;	/* remaining space in sndbuf */
 	u16			tx_cdc_seq;	/* sequence # for CDC send */
 	spinlock_t		send_lock;	/* protect wr_sends */
-	struct work_struct	tx_work;	/* retry of smc_cdc_msg_send */
+	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
 
 	struct smc_host_cdc_msg	local_rx_ctrl;	/* filled during event_handl.
 						 * .prod cf. TCP rcv_nxt
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 3934913..b7dd274 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -95,9 +95,10 @@
 	}
 	if (clcm->type == SMC_CLC_DECLINE) {
 		reason_code = SMC_CLC_DECL_REPLY;
-		if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis)
-			== SMC_CLC_DECL_SYNCERR)
+		if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
 			smc->conn.lgr->sync_err = true;
+			smc_lgr_terminate(smc->conn.lgr);
+		}
 	}
 
 out:
@@ -105,8 +106,7 @@
 }
 
 /* send CLC DECLINE message across internal TCP socket */
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
-			 u8 out_of_sync)
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 {
 	struct smc_clc_msg_decline dclc;
 	struct msghdr msg;
@@ -118,7 +118,7 @@
 	dclc.hdr.type = SMC_CLC_DECLINE;
 	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
 	dclc.hdr.version = SMC_CLC_V1;
-	dclc.hdr.flag = out_of_sync ? 1 : 0;
+	dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
 	memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
 	dclc.peer_diagnosis = htonl(peer_diag_info);
 	memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 13db8ce..1c55414 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -106,8 +106,7 @@
 
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type);
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
-			 u8 out_of_sync);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
 int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
 			  u8 ibport);
 int smc_clc_send_confirm(struct smc_sock *smc);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 3c2e166..f0d16fb 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -174,15 +174,15 @@
 {
 	struct smc_cdc_conn_state_flags *txflags =
 		&smc->conn.local_tx_ctrl.conn_state_flags;
-	long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
 	struct smc_connection *conn = &smc->conn;
 	struct sock *sk = &smc->sk;
 	int old_state;
+	long timeout;
 	int rc = 0;
 
-	if (sock_flag(sk, SOCK_LINGER) &&
-	    !(current->flags & PF_EXITING))
-		timeout = sk->sk_lingertime;
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
 
 again:
 	old_state = sk->sk_state;
@@ -208,7 +208,7 @@
 	case SMC_ACTIVE:
 		smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		if (sk->sk_state == SMC_ACTIVE) {
 			/* send close request */
@@ -234,7 +234,7 @@
 		if (!smc_cdc_rxed_any_close(conn))
 			smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		if (sk->sk_err != ECONNABORTED) {
 			/* confirm close from peer */
@@ -263,7 +263,9 @@
 		/* peer sending PeerConnectionClosed will cause transition */
 		break;
 	case SMC_PROCESSABORT:
-		cancel_work_sync(&conn->tx_work);
+		release_sock(sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(sk);
 		smc_close_abort(conn);
 		sk->sk_state = SMC_CLOSED;
 		smc_close_wait_tx_pends(smc);
@@ -411,13 +413,14 @@
 int smc_close_shutdown_write(struct smc_sock *smc)
 {
 	struct smc_connection *conn = &smc->conn;
-	long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
 	struct sock *sk = &smc->sk;
 	int old_state;
+	long timeout;
 	int rc = 0;
 
-	if (sock_flag(sk, SOCK_LINGER))
-		timeout = sk->sk_lingertime;
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
 
 again:
 	old_state = sk->sk_state;
@@ -425,7 +428,7 @@
 	case SMC_ACTIVE:
 		smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		/* send close wr request */
 		rc = smc_close_wr(conn);
@@ -439,7 +442,7 @@
 		if (!smc_cdc_rxed_any_close(conn))
 			smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		/* confirm close from peer */
 		rc = smc_close_wr(conn);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 1a16d51..20b66e7 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -25,8 +25,9 @@
 #include "smc_cdc.h"
 #include "smc_close.h"
 
-#define SMC_LGR_NUM_INCR	256
-#define SMC_LGR_FREE_DELAY	(600 * HZ)
+#define SMC_LGR_NUM_INCR		256
+#define SMC_LGR_FREE_DELAY_SERV		(600 * HZ)
+#define SMC_LGR_FREE_DELAY_CLNT		(SMC_LGR_FREE_DELAY_SERV + 10)
 
 static u32 smc_lgr_num;			/* unique link group number */
 
@@ -107,8 +108,15 @@
 		__smc_lgr_unregister_conn(conn);
 	}
 	write_unlock_bh(&lgr->conns_lock);
-	if (reduced && !lgr->conns_num)
-		schedule_delayed_work(&lgr->free_work, SMC_LGR_FREE_DELAY);
+	if (!reduced || lgr->conns_num)
+		return;
+	/* client link group creation always follows the server link group
+	 * creation. For client use a somewhat higher removal delay time,
+	 * otherwise there is a risk of out-of-sync link groups.
+	 */
+	mod_delayed_work(system_wq, &lgr->free_work,
+			 lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT :
+						 SMC_LGR_FREE_DELAY_SERV);
 }
 
 static void smc_lgr_free_work(struct work_struct *work)
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 547e0e1..0b58522 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -380,6 +380,7 @@
 	ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
 	if (ndev) {
 		memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
+		dev_put(ndev);
 	} else if (!rc) {
 		memcpy(&smcibdev->mac[ibport - 1][0],
 		       &smcibdev->gid[ibport - 1].raw[8], 3);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 78f7af2..31f8453 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -181,8 +181,10 @@
 			     sizeof(new_pnetelem->ndev->name)) ||
 		    smc_pnet_same_ibname(pnetelem,
 					 new_pnetelem->smcibdev->ibdev->name,
-					 new_pnetelem->ib_port))
+					 new_pnetelem->ib_port)) {
+			dev_put(pnetelem->ndev);
 			goto found;
+		}
 	}
 	list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
 	rc = 0;
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index b17a333..3e631ae 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -148,6 +148,8 @@
 				read_done = sock_intr_errno(timeo);
 				break;
 			}
+			if (!timeo)
+				return -EAGAIN;
 		}
 
 		if (!atomic_read(&conn->bytes_to_rcv)) {
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 3c656be..38665732 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -24,6 +24,8 @@
 #include "smc_cdc.h"
 #include "smc_tx.h"
 
+#define SMC_TX_WORK_DELAY	HZ
+
 /***************************** sndbuf producer *******************************/
 
 /* callback implementation for sk.sk_write_space()
@@ -406,7 +408,8 @@
 				goto out_unlock;
 			}
 			rc = 0;
-			schedule_work(&conn->tx_work);
+			schedule_delayed_work(&conn->tx_work,
+					      SMC_TX_WORK_DELAY);
 		}
 		goto out_unlock;
 	}
@@ -430,7 +433,7 @@
  */
 static void smc_tx_work(struct work_struct *work)
 {
-	struct smc_connection *conn = container_of(work,
+	struct smc_connection *conn = container_of(to_delayed_work(work),
 						   struct smc_connection,
 						   tx_work);
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
@@ -468,7 +471,8 @@
 		if (!rc)
 			rc = smc_cdc_msg_send(conn, wr_buf, pend);
 		if (rc < 0) {
-			schedule_work(&conn->tx_work);
+			schedule_delayed_work(&conn->tx_work,
+					      SMC_TX_WORK_DELAY);
 			return;
 		}
 		smc_curs_write(&conn->rx_curs_confirmed,
@@ -487,6 +491,6 @@
 void smc_tx_init(struct smc_sock *smc)
 {
 	smc->sk.sk_write_space = smc_tx_write_space;
-	INIT_WORK(&smc->conn.tx_work, smc_tx_work);
+	INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
 	spin_lock_init(&smc->conn.send_lock);
 }
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index ab56bda..525d91e 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -244,7 +244,7 @@
 	int rc;
 
 	ib_req_notify_cq(link->smcibdev->roce_cq_send,
-			 IB_CQ_SOLICITED_MASK | IB_CQ_REPORT_MISSED_EVENTS);
+			 IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
 	pend = container_of(priv, struct smc_wr_tx_pend, priv);
 	rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx],
 			  &failed_wr);
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index d4ea46a..c5fda15 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -49,7 +49,7 @@
 {
 	/* Unrecoverable error in receive */
 
-	del_timer(&strp->msg_timer);
+	cancel_delayed_work(&strp->msg_timer_work);
 
 	if (strp->stopped)
 		return;
@@ -68,7 +68,7 @@
 static void strp_start_timer(struct strparser *strp, long timeo)
 {
 	if (timeo)
-		mod_timer(&strp->msg_timer, timeo);
+		mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
 }
 
 /* Lower lock held */
@@ -319,7 +319,7 @@
 		eaten += (cand_len - extra);
 
 		/* Hurray, we have a new message! */
-		del_timer(&strp->msg_timer);
+		cancel_delayed_work(&strp->msg_timer_work);
 		strp->skb_head = NULL;
 		STRP_STATS_INCR(strp->stats.msgs);
 
@@ -450,9 +450,10 @@
 	do_strp_work(container_of(w, struct strparser, work));
 }
 
-static void strp_msg_timeout(unsigned long arg)
+static void strp_msg_timeout(struct work_struct *w)
 {
-	struct strparser *strp = (struct strparser *)arg;
+	struct strparser *strp = container_of(w, struct strparser,
+					      msg_timer_work.work);
 
 	/* Message assembly timed out */
 	STRP_STATS_INCR(strp->stats.msg_timeouts);
@@ -505,9 +506,7 @@
 	strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done;
 	strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp;
 
-	setup_timer(&strp->msg_timer, strp_msg_timeout,
-		    (unsigned long)strp);
-
+	INIT_DELAYED_WORK(&strp->msg_timer_work, strp_msg_timeout);
 	INIT_WORK(&strp->work, strp_work);
 
 	return 0;
@@ -532,7 +531,7 @@
 {
 	WARN_ON(!strp->stopped);
 
-	del_timer_sync(&strp->msg_timer);
+	cancel_delayed_work_sync(&strp->msg_timer_work);
 	cancel_work_sync(&strp->work);
 
 	if (strp->skb_head) {
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index e741ec2..898485e 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1333,7 +1333,7 @@
 		rpc_count_iostats(task, task->tk_client->cl_metrics);
 	spin_lock(&xprt->recv_lock);
 	if (!list_empty(&req->rq_list)) {
-		list_del(&req->rq_list);
+		list_del_init(&req->rq_list);
 		xprt_wait_on_pinned_rqst(req);
 	}
 	spin_unlock(&xprt->recv_lock);
@@ -1445,6 +1445,23 @@
 	return xprt;
 }
 
+static void xprt_destroy_cb(struct work_struct *work)
+{
+	struct rpc_xprt *xprt =
+		container_of(work, struct rpc_xprt, task_cleanup);
+
+	rpc_xprt_debugfs_unregister(xprt);
+	rpc_destroy_wait_queue(&xprt->binding);
+	rpc_destroy_wait_queue(&xprt->pending);
+	rpc_destroy_wait_queue(&xprt->sending);
+	rpc_destroy_wait_queue(&xprt->backlog);
+	kfree(xprt->servername);
+	/*
+	 * Tear down transport state and free the rpc_xprt
+	 */
+	xprt->ops->destroy(xprt);
+}
+
 /**
  * xprt_destroy - destroy an RPC transport, killing off all requests.
  * @xprt: transport to destroy
@@ -1454,22 +1471,19 @@
 {
 	dprintk("RPC:       destroying transport %p\n", xprt);
 
-	/* Exclude transport connect/disconnect handlers */
+	/*
+	 * Exclude transport connect/disconnect handlers and autoclose
+	 */
 	wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE);
 
 	del_timer_sync(&xprt->timer);
 
-	rpc_xprt_debugfs_unregister(xprt);
-	rpc_destroy_wait_queue(&xprt->binding);
-	rpc_destroy_wait_queue(&xprt->pending);
-	rpc_destroy_wait_queue(&xprt->sending);
-	rpc_destroy_wait_queue(&xprt->backlog);
-	cancel_work_sync(&xprt->task_cleanup);
-	kfree(xprt->servername);
 	/*
-	 * Tear down transport state and free the rpc_xprt
+	 * Destroy sockets etc from the system workqueue so they can
+	 * safely flush receive work running on rpciod.
 	 */
-	xprt->ops->destroy(xprt);
+	INIT_WORK(&xprt->task_cleanup, xprt_destroy_cb);
+	schedule_work(&xprt->task_cleanup);
 }
 
 static void xprt_destroy_kref(struct kref *kref)
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 5a936a6..df062e0 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -401,7 +401,7 @@
 	if (unlikely(n != mw->mw_nents))
 		goto out_mapmr_err;
 
-	dprintk("RPC:       %s: Using frmr %p to map %u segments (%u bytes)\n",
+	dprintk("RPC:       %s: Using frmr %p to map %u segments (%llu bytes)\n",
 		__func__, frmr, mw->mw_nents, mr->length);
 
 	key = (u8)(mr->rkey & 0x000000FF);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9b5de31..c1841f2 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2203,7 +2203,7 @@
 	struct sock_xprt *transport =
 		container_of(work, struct sock_xprt, connect_worker.work);
 	struct rpc_xprt *xprt = &transport->xprt;
-	struct socket *sock = transport->sock;
+	struct socket *sock;
 	int status = -EIO;
 
 	sock = xs_create_sock(xprt, transport,
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 7d99029..a140dd4 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -233,7 +233,7 @@
 	struct sk_buff_head xmitq;
 	int rc = 0;
 
-	__skb_queue_head_init(&xmitq);
+	skb_queue_head_init(&xmitq);
 	tipc_bcast_lock(net);
 	if (tipc_link_bc_peers(l))
 		rc = tipc_link_xmit(l, pkts, &xmitq);
@@ -263,7 +263,7 @@
 	u32 dst, selector;
 
 	selector = msg_link_selector(buf_msg(skb_peek(pkts)));
-	__skb_queue_head_init(&_pkts);
+	skb_queue_head_init(&_pkts);
 
 	list_for_each_entry_safe(n, tmp, &dests->list, list) {
 		dst = n->value;
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 6ef379f..17146c1 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -551,7 +551,7 @@
 		return false;
 	if (msg_errcode(msg))
 		return false;
-	*err = -TIPC_ERR_NO_NAME;
+	*err = TIPC_ERR_NO_NAME;
 	if (skb_linearize(skb))
 		return false;
 	msg = buf_msg(skb);
@@ -568,6 +568,14 @@
 	msg_set_destnode(msg, dnode);
 	msg_set_destport(msg, dport);
 	*err = TIPC_OK;
+
+	if (!skb_cloned(skb))
+		return true;
+
+	/* Unclone buffer in case it was bundled */
+	if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC))
+		return false;
+
 	return true;
 }
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 4d96797..384c84e 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -257,6 +257,8 @@
 	err = -ENOENT;
 	if (sk == NULL)
 		goto out_nosk;
+	if (!net_eq(sock_net(sk), net))
+		goto out;
 
 	err = sock_diag_check_cookie(sk, req->udiag_cookie);
 	if (err)
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 14ed5a3..e21991f 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -310,11 +310,15 @@
 	struct sock *sk = get_per_channel_state(chan);
 	struct vsock_sock *vsk = vsock_sk(sk);
 
+	lock_sock(sk);
+
 	sk->sk_state = SS_UNCONNECTED;
 	sock_set_flag(sk, SOCK_DONE);
 	vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN;
 
 	sk->sk_state_change(sk);
+
+	release_sock(sk);
 }
 
 static void hvs_open_connection(struct vmbus_channel *chan)
@@ -344,6 +348,8 @@
 	if (!sk)
 		return;
 
+	lock_sock(sk);
+
 	if ((conn_from_host && sk->sk_state != VSOCK_SS_LISTEN) ||
 	    (!conn_from_host && sk->sk_state != SS_CONNECTING))
 		goto out;
@@ -395,9 +401,7 @@
 
 		vsock_insert_connected(vnew);
 
-		lock_sock(sk);
 		vsock_enqueue_accept(sk, new);
-		release_sock(sk);
 	} else {
 		sk->sk_state = SS_CONNECTED;
 		sk->sk_socket->state = SS_CONNECTED;
@@ -410,6 +414,8 @@
 out:
 	/* Release refcnt obtained when we called vsock_find_bound_socket() */
 	sock_put(sk);
+
+	release_sock(sk);
 }
 
 static u32 hvs_get_local_cid(void)
@@ -476,13 +482,21 @@
 
 static void hvs_release(struct vsock_sock *vsk)
 {
+	struct sock *sk = sk_vsock(vsk);
 	struct hvsock *hvs = vsk->trans;
-	struct vmbus_channel *chan = hvs->chan;
+	struct vmbus_channel *chan;
 
+	lock_sock(sk);
+
+	sk->sk_state = SS_DISCONNECTING;
+	vsock_remove_sock(vsk);
+
+	release_sock(sk);
+
+	chan = hvs->chan;
 	if (chan)
 		hvs_shutdown(vsk, RCV_SHUTDOWN | SEND_SHUTDOWN);
 
-	vsock_remove_sock(vsk);
 }
 
 static void hvs_destruct(struct vsock_sock *vsk)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0df8023..d396cb6 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -549,6 +549,14 @@
 	[NL80211_NAN_SRF_MAC_ADDRS] = { .type = NLA_NESTED },
 };
 
+/* policy for packet pattern attributes */
+static const struct nla_policy
+nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = {
+	[NL80211_PKTPAT_MASK] = { .type = NLA_BINARY, },
+	[NL80211_PKTPAT_PATTERN] = { .type = NLA_BINARY, },
+	[NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 },
+};
+
 static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 				     struct netlink_callback *cb,
 				     struct cfg80211_registered_device **rdev,
@@ -9987,6 +9995,9 @@
 		if (err)
 			return err;
 
+		if (!setup.chandef.chan)
+			return -EINVAL;
+
 		err = validate_beacon_tx_rate(rdev, setup.chandef.chan->band,
 					      &setup.beacon_rate);
 		if (err)
@@ -10529,7 +10540,8 @@
 			u8 *mask_pat;
 
 			nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-					 NULL, info->extack);
+					 nl80211_packet_pattern_policy,
+					 info->extack);
 			err = -EINVAL;
 			if (!pat_tb[NL80211_PKTPAT_MASK] ||
 			    !pat_tb[NL80211_PKTPAT_PATTERN])
@@ -10778,7 +10790,8 @@
 			    rem) {
 		u8 *mask_pat;
 
-		nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, NULL, NULL);
+		nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+				 nl80211_packet_pattern_policy, NULL);
 		if (!pat_tb[NL80211_PKTPAT_MASK] ||
 		    !pat_tb[NL80211_PKTPAT_PATTERN])
 			return -EINVAL;
@@ -10903,6 +10916,9 @@
 	if (err)
 		return err;
 
+	if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] ||
+	    !tb[NL80211_REKEY_DATA_KCK])
+		return -EINVAL;
 	if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN)
 		return -ERANGE;
 	if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN)
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 0a49b88..b6533ec 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -522,11 +522,6 @@
 		return -EOPNOTSUPP;
 
 	if (wdev->current_bss) {
-		if (!prev_bssid)
-			return -EALREADY;
-		if (prev_bssid &&
-		    !ether_addr_equal(prev_bssid, wdev->current_bss->pub.bssid))
-			return -ENOTCONN;
 		cfg80211_unhold_bss(wdev->current_bss);
 		cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub);
 		wdev->current_bss = NULL;
@@ -1063,11 +1058,35 @@
 
 	ASSERT_WDEV_LOCK(wdev);
 
-	if (WARN_ON(wdev->connect_keys)) {
-		kzfree(wdev->connect_keys);
-		wdev->connect_keys = NULL;
+	/*
+	 * If we have an ssid_len, we're trying to connect or are
+	 * already connected, so reject a new SSID unless it's the
+	 * same (which is the case for re-association.)
+	 */
+	if (wdev->ssid_len &&
+	    (wdev->ssid_len != connect->ssid_len ||
+	     memcmp(wdev->ssid, connect->ssid, wdev->ssid_len)))
+		return -EALREADY;
+
+	/*
+	 * If connected, reject (re-)association unless prev_bssid
+	 * matches the current BSSID.
+	 */
+	if (wdev->current_bss) {
+		if (!prev_bssid)
+			return -EALREADY;
+		if (!ether_addr_equal(prev_bssid, wdev->current_bss->pub.bssid))
+			return -ENOTCONN;
 	}
 
+	/*
+	 * Reject if we're in the process of connecting with WEP,
+	 * this case isn't very interesting and trying to handle
+	 * it would make the code much more complex.
+	 */
+	if (wdev->connect_keys)
+		return -EINPROGRESS;
+
 	cfg80211_oper_and_ht_capa(&connect->ht_capa_mask,
 				  rdev->wiphy.ht_capa_mod_mask);
 
@@ -1118,7 +1137,12 @@
 
 	if (err) {
 		wdev->connect_keys = NULL;
-		wdev->ssid_len = 0;
+		/*
+		 * This could be reassoc getting refused, don't clear
+		 * ssid_len in that case.
+		 */
+		if (!wdev->current_bss)
+			wdev->ssid_len = 0;
 		return err;
 	}
 
@@ -1145,6 +1169,14 @@
 	else if (wdev->ssid_len)
 		err = rdev_disconnect(rdev, dev, reason);
 
+	/*
+	 * Clear ssid_len unless we actually were fully connected,
+	 * in which case cfg80211_disconnected() will take care of
+	 * this later.
+	 */
+	if (!wdev->current_bss)
+		wdev->ssid_len = 0;
+
 	return err;
 }
 
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index acf0010..30e5746 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -91,6 +91,7 @@
 	}
 
 	if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) {
+		xso->dev = NULL;
 		dev_put(dev);
 		return 0;
 	}
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 2515cd2..8ac9d32 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -429,7 +429,8 @@
 	nf_reset(skb);
 
 	if (decaps) {
-		skb->sp->olen = 0;
+		if (skb->sp)
+			skb->sp->olen = 0;
 		skb_dst_drop(skb);
 		gro_cells_receive(&gro_cells, skb);
 		return 0;
@@ -440,7 +441,8 @@
 
 		err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async);
 		if (xfrm_gro) {
-			skb->sp->olen = 0;
+			if (skb->sp)
+				skb->sp->olen = 0;
 			skb_dst_drop(skb);
 			gro_cells_receive(&gro_cells, skb);
 			return err;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f062539..2746b62 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1573,6 +1573,14 @@
 			goto put_states;
 		}
 
+		if (!dst_prev)
+			dst0 = dst1;
+		else
+			/* Ref count is taken during xfrm_alloc_dst()
+			 * No need to do dst_clone() on dst1
+			 */
+			dst_prev->child = dst1;
+
 		if (xfrm[i]->sel.family == AF_UNSPEC) {
 			inner_mode = xfrm_ip2inner_mode(xfrm[i],
 							xfrm_af2proto(family));
@@ -1584,14 +1592,6 @@
 		} else
 			inner_mode = xfrm[i]->inner_mode;
 
-		if (!dst_prev)
-			dst0 = dst1;
-		else
-			/* Ref count is taken during xfrm_alloc_dst()
-			 * No need to do dst_clone() on dst1
-			 */
-			dst_prev->child = dst1;
-
 		xdst->route = dst;
 		dst_copy_metrics(dst1, dst);
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 0dab1cd..1221347 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -732,12 +732,12 @@
 			}
 		}
 	}
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	if (cnt) {
 		err = 0;
 		xfrm_policy_cache_flush();
 	}
-out:
-	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_flush);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 2bfbd91..e44a0fe 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -657,6 +657,7 @@
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
+		xfrm_dev_state_delete(x);
 		__xfrm_state_put(x);
 		goto out;
 	}
@@ -1692,32 +1693,34 @@
 
 static int xfrm_dump_policy_done(struct netlink_callback *cb)
 {
-	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1];
+	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
 	struct net *net = sock_net(cb->skb->sk);
 
 	xfrm_policy_walk_done(walk, net);
 	return 0;
 }
 
+static int xfrm_dump_policy_start(struct netlink_callback *cb)
+{
+	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
+
+	BUILD_BUG_ON(sizeof(*walk) > sizeof(cb->args));
+
+	xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY);
+	return 0;
+}
+
 static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
-	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1];
+	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
 	struct xfrm_dump_info info;
 
-	BUILD_BUG_ON(sizeof(struct xfrm_policy_walk) >
-		     sizeof(cb->args) - sizeof(cb->args[0]));
-
 	info.in_skb = cb->skb;
 	info.out_skb = skb;
 	info.nlmsg_seq = cb->nlh->nlmsg_seq;
 	info.nlmsg_flags = NLM_F_MULTI;
 
-	if (!cb->args[0]) {
-		cb->args[0] = 1;
-		xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY);
-	}
-
 	(void) xfrm_policy_walk(net, walk, dump_one_policy, &info);
 
 	return skb->len;
@@ -2473,6 +2476,7 @@
 
 static const struct xfrm_link {
 	int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **);
+	int (*start)(struct netlink_callback *);
 	int (*dump)(struct sk_buff *, struct netlink_callback *);
 	int (*done)(struct netlink_callback *);
 	const struct nla_policy *nla_pol;
@@ -2486,6 +2490,7 @@
 	[XFRM_MSG_NEWPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_add_policy    },
 	[XFRM_MSG_DELPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_get_policy    },
 	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_get_policy,
+						   .start = xfrm_dump_policy_start,
 						   .dump = xfrm_dump_policy,
 						   .done = xfrm_dump_policy_done },
 	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi },
@@ -2538,6 +2543,7 @@
 
 		{
 			struct netlink_dump_control c = {
+				.start = link->start,
 				.dump = link->dump,
 				.done = link->done,
 			};
diff --git a/samples/sockmap/sockmap_kern.c b/samples/sockmap/sockmap_kern.c
index f9b38ef..52b0053 100644
--- a/samples/sockmap/sockmap_kern.c
+++ b/samples/sockmap/sockmap_kern.c
@@ -62,7 +62,7 @@
 		ret = 1;
 
 	bpf_printk("sockmap: %d -> %d @ %d\n", lport, bpf_ntohl(rport), ret);
-	return bpf_sk_redirect_map(&sock_map, ret, 0);
+	return bpf_sk_redirect_map(skb, &sock_map, ret, 0);
 }
 
 SEC("sockops")
diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c
index bc7fcf0..5522692 100644
--- a/samples/trace_events/trace-events-sample.c
+++ b/samples/trace_events/trace-events-sample.c
@@ -78,29 +78,37 @@
 }
 
 static DEFINE_MUTEX(thread_mutex);
+static int simple_thread_cnt;
 
 int foo_bar_reg(void)
 {
+	mutex_lock(&thread_mutex);
+	if (simple_thread_cnt++)
+		goto out;
+
 	pr_info("Starting thread for foo_bar_fn\n");
 	/*
 	 * We shouldn't be able to start a trace when the module is
 	 * unloading (there's other locks to prevent that). But
 	 * for consistency sake, we still take the thread_mutex.
 	 */
-	mutex_lock(&thread_mutex);
 	simple_tsk_fn = kthread_run(simple_thread_fn, NULL, "event-sample-fn");
+ out:
 	mutex_unlock(&thread_mutex);
 	return 0;
 }
 
 void foo_bar_unreg(void)
 {
-	pr_info("Killing thread for foo_bar_fn\n");
-	/* protect against module unloading */
 	mutex_lock(&thread_mutex);
+	if (--simple_thread_cnt)
+		goto out;
+
+	pr_info("Killing thread for foo_bar_fn\n");
 	if (simple_tsk_fn)
 		kthread_stop(simple_tsk_fn);
 	simple_tsk_fn = NULL;
+ out:
 	mutex_unlock(&thread_mutex);
 }
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 2e3a10e7..061d0c3 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -265,6 +265,8 @@
 endif
 ifdef CONFIG_GCOV_KERNEL
 objtool_args += --no-unreachable
+else
+objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable)
 endif
 
 # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 16923ba..756d14f 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -97,7 +97,6 @@
 	$(call cmd,kernel-mod)
 
 # Declare generated files as targets for modpost
-$(symverfile):         __modpost ;
 $(modules:.ko=.mod.c): __modpost ;
 
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index dd2c262..8b80bac 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6390,7 +6390,7 @@
 		exit(0);
 	}
 
-	if (!$is_patch && $file !~ /cover-letter\.patch$/) {
+	if (!$is_patch && $filename !~ /cover-letter\.patch$/) {
 		ERROR("NOT_UNIFIED_DIFF",
 		      "Does not appear to be a unified-diff format patch\n");
 	}
diff --git a/scripts/dtc/dtx_diff b/scripts/dtc/dtx_diff
index f9a3d8d..8c4fbad 100755
--- a/scripts/dtc/dtx_diff
+++ b/scripts/dtc/dtx_diff
@@ -86,6 +86,7 @@
 compile_to_dts() {
 
 	dtx="$1"
+	dtc_include="$2"
 
 	if [ -d "${dtx}" ] ; then
 
@@ -113,7 +114,7 @@
 		# -----  input is DTS (source)
 
 		if ( cpp ${cpp_flags} -x assembler-with-cpp ${dtx} \
-			| ${DTC} -I dts ) ; then
+			| ${DTC} ${dtc_include} -I dts ) ; then
 			return
 		fi
 
@@ -320,18 +321,13 @@
 
 cpp_flags="\
 	-nostdinc                                  \
-	-I${srctree}/arch/${ARCH}/boot/dts         \
 	-I${srctree}/scripts/dtc/include-prefixes  \
-	-I${srctree}/drivers/of/testcase-data      \
 	-undef -D__DTS__"
 
-dtc_flags="\
-	-i ${srctree}/arch/${ARCH}/boot/dts/ \
-	-i ${srctree}/kernel/dts             \
-	${dtx_path_1_dtc_include}            \
-	${dtx_path_2_dtc_include}"
-
-DTC="${DTC} ${dtc_flags} -O dts -qq -f ${dtc_sort} -o -"
+DTC="\
+	${DTC}                                     \
+	-i ${srctree}/scripts/dtc/include-prefixes \
+	-O dts -qq -f ${dtc_sort} -o -"
 
 
 # -----  do the diff or decompile
@@ -339,11 +335,11 @@
 if (( ${cmd_diff} )) ; then
 
 	diff ${diff_flags} --label "${dtx_file_1}" --label "${dtx_file_2}" \
-		<(compile_to_dts "${dtx_file_1}") \
-		<(compile_to_dts "${dtx_file_2}")
+		<(compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}") \
+		<(compile_to_dts "${dtx_file_2}" "${dtx_path_2_dtc_include}")
 
 else
 
-	compile_to_dts "${dtx_file_1}"
+	compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}"
 
 fi
diff --git a/scripts/faddr2line b/scripts/faddr2line
index 29df825..2f6ce80 100755
--- a/scripts/faddr2line
+++ b/scripts/faddr2line
@@ -103,11 +103,12 @@
 
 	# Go through each of the object's symbols which match the func name.
 	# In rare cases there might be duplicates.
+	file_end=$(size -Ax $objfile | awk '$1 == ".text" {print $2}')
 	while read symbol; do
 		local fields=($symbol)
 		local sym_base=0x${fields[0]}
 		local sym_type=${fields[1]}
-		local sym_end=0x${fields[3]}
+		local sym_end=${fields[3]}
 
 		# calculate the size
 		local sym_size=$(($sym_end - $sym_base))
@@ -157,7 +158,7 @@
 		addr2line -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;"
 		DONE=1
 
-	done < <(nm -n $objfile | awk -v fn=$func '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, $1 }')
+	done < <(nm -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }')
 }
 
 [[ $# -lt 2 ]] && usage
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 5d55441..9ee9bf7 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -158,7 +158,7 @@
 	else if (str[0] == '$')
 		return -1;
 	/* exclude debugging symbols */
-	else if (stype == 'N')
+	else if (stype == 'N' || stype == 'n')
 		return -1;
 
 	/* include the type field in the symbol name, so that it gets
diff --git a/scripts/mkversion b/scripts/mkversion
deleted file mode 100644
index c12addc..0000000
--- a/scripts/mkversion
+++ /dev/null
@@ -1,6 +0,0 @@
-if [ ! -f .version ]
-then
-    echo 1
-else
-    expr 0`cat .version` + 1
-fi
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index 71b4a8a..73f9f31 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -50,8 +50,6 @@
 	$(MAKE) clean
 	$(CONFIG_SHELL) $(MKSPEC) >$(objtree)/kernel.spec
 	$(call cmd,src_tar,$(KERNELPATH),kernel.spec)
-	$(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
-	mv -f $(objtree)/.tmp_version $(objtree)/.version
 	rpmbuild $(RPMOPTS) --target $(UTS_MACHINE) -ta $(KERNELPATH).tar.gz
 	rm $(KERNELPATH).tar.gz kernel.spec
 
@@ -60,9 +58,6 @@
 binrpm-pkg: FORCE
 	$(MAKE) KBUILD_SRC=
 	$(CONFIG_SHELL) $(MKSPEC) prebuilt > $(objtree)/binkernel.spec
-	$(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
-	mv -f $(objtree)/.tmp_version $(objtree)/.version
-
 	rpmbuild $(RPMOPTS) --define "_builddir $(objtree)" --target \
 		$(UTS_MACHINE) -bb $(objtree)/binkernel.spec
 	rm binkernel.spec
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index aad6700..0bc8747 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -92,12 +92,10 @@
 fi
 sourcename=$KDEB_SOURCENAME
 tmpdir="$objtree/debian/tmp"
-fwdir="$objtree/debian/fwtmp"
 kernel_headers_dir="$objtree/debian/hdrtmp"
 libc_headers_dir="$objtree/debian/headertmp"
 dbg_dir="$objtree/debian/dbgtmp"
 packagename=linux-image-$version
-fwpackagename=linux-firmware-image-$version
 kernel_headers_packagename=linux-headers-$version
 libc_headers_packagename=linux-libc-dev
 dbg_packagename=$packagename-dbg
@@ -126,10 +124,9 @@
 BUILD_DEBUG="$(grep -s '^CONFIG_DEBUG_INFO=y' $KCONFIG_CONFIG || true)"
 
 # Setup the directory structure
-rm -rf "$tmpdir" "$fwdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files
+rm -rf "$tmpdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files
 mkdir -m 755 -p "$tmpdir/DEBIAN"
 mkdir -p "$tmpdir/lib" "$tmpdir/boot"
-mkdir -p "$fwdir/lib/firmware/$version/"
 mkdir -p "$kernel_headers_dir/lib/modules/$version/"
 
 # Build and install the kernel
@@ -306,7 +303,6 @@
 	cat <<EOF >> debian/control
 
 Package: $packagename
-Suggests: $fwpackagename
 Architecture: any
 Description: Linux kernel, version $version
  This package contains the Linux kernel, modules and corresponding other
@@ -345,22 +341,6 @@
  This is useful for people who need to build external modules
 EOF
 
-# Do we have firmware? Move it out of the way and build it into a package.
-if [ -e "$tmpdir/lib/firmware" ]; then
-	mv "$tmpdir/lib/firmware"/* "$fwdir/lib/firmware/$version/"
-	rmdir "$tmpdir/lib/firmware"
-
-	cat <<EOF >> debian/control
-
-Package: $fwpackagename
-Architecture: all
-Description: Linux kernel firmware, version $version
- This package contains firmware from the Linux kernel, version $version.
-EOF
-
-	create_package "$fwpackagename" "$fwdir"
-fi
-
 cat <<EOF >> debian/control
 
 Package: $libc_headers_packagename
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index bb43f15..f47f17a 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -27,9 +27,7 @@
 echo "Name: kernel"
 echo "Summary: The Linux Kernel"
 echo "Version: $__KERNELRELEASE"
-# we need to determine the NEXT version number so that uname and
-# rpm -q will agree
-echo "Release: `. $srctree/scripts/mkversion`"
+echo "Release: $(cat .version 2>/dev/null || echo 1)"
 echo "License: GPL"
 echo "Group: System Environment/Kernel"
 echo "Vendor: The Linux Community"
@@ -77,7 +75,7 @@
 echo "%build"
 
 if ! $PREBUILT; then
-echo "make clean && make %{?_smp_mflags}"
+echo "make clean && make %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release}"
 echo ""
 fi
 
@@ -88,11 +86,8 @@
 echo "%else"
 echo 'mkdir -p $RPM_BUILD_ROOT/boot $RPM_BUILD_ROOT/lib/modules'
 echo "%endif"
-echo 'mkdir -p $RPM_BUILD_ROOT'"/lib/firmware/$KERNELRELEASE"
 
-echo 'INSTALL_MOD_PATH=$RPM_BUILD_ROOT make %{?_smp_mflags} KBUILD_SRC= mod-fw= modules_install'
-echo 'INSTALL_FW_PATH=$RPM_BUILD_ROOT'"/lib/firmware/$KERNELRELEASE"
-echo 'make INSTALL_FW_PATH=$INSTALL_FW_PATH' firmware_install
+echo 'INSTALL_MOD_PATH=$RPM_BUILD_ROOT make %{?_smp_mflags} KBUILD_SRC= modules_install'
 echo "%ifarch ia64"
 echo 'cp $KBUILD_IMAGE $RPM_BUILD_ROOT'"/boot/efi/vmlinuz-$KERNELRELEASE"
 echo 'ln -s '"efi/vmlinuz-$KERNELRELEASE" '$RPM_BUILD_ROOT'"/boot/"
@@ -119,7 +114,7 @@
 echo 'rm -f $RPM_BUILD_ROOT'"/lib/modules/$KERNELRELEASE/build"
 echo 'rm -f $RPM_BUILD_ROOT'"/lib/modules/$KERNELRELEASE/source"
 echo "mkdir -p "'$RPM_BUILD_ROOT'"/usr/src/kernels/$KERNELRELEASE"
-echo "EXCLUDES=\"$RCS_TAR_IGNORE --exclude .tmp_versions --exclude=*vmlinux* --exclude=*.o --exclude=*.ko --exclude=*.cmd --exclude=Documentation --exclude=firmware --exclude .config.old --exclude .missing-syscalls.d\""
+echo "EXCLUDES=\"$RCS_TAR_IGNORE --exclude .tmp_versions --exclude=*vmlinux* --exclude=*.o --exclude=*.ko --exclude=*.cmd --exclude=Documentation --exclude .config.old --exclude .missing-syscalls.d\""
 echo "tar "'$EXCLUDES'" -cf- . | (cd "'$RPM_BUILD_ROOT'"/usr/src/kernels/$KERNELRELEASE;tar xvf -)"
 echo 'cd $RPM_BUILD_ROOT'"/lib/modules/$KERNELRELEASE"
 echo "ln -sf /usr/src/kernels/$KERNELRELEASE build"
@@ -154,7 +149,6 @@
 echo "/lib/modules/$KERNELRELEASE"
 echo "%exclude /lib/modules/$KERNELRELEASE/build"
 echo "%exclude /lib/modules/$KERNELRELEASE/source"
-echo "/lib/firmware/$KERNELRELEASE"
 echo "/boot/*"
 echo ""
 echo "%files headers"
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 400ef35..aa0cc49 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -53,6 +53,7 @@
 adapater||adapter
 addional||additional
 additionaly||additionally
+additonal||additional
 addres||address
 adddress||address
 addreses||addresses
@@ -67,6 +68,8 @@
 afecting||affecting
 againt||against
 agaist||against
+aggreataon||aggregation
+aggreation||aggregation
 albumns||albums
 alegorical||allegorical
 algined||aligned
@@ -80,6 +83,8 @@
 alignement||alignment
 allign||align
 alligned||aligned
+alllocate||allocate
+alloated||allocated
 allocatote||allocate
 allocatrd||allocated
 allocte||allocate
@@ -171,6 +176,7 @@
 availavility||availability
 availble||available
 availiable||available
+availible||available
 avalable||available
 avaliable||available
 aysnc||async
@@ -203,6 +209,7 @@
 cacluated||calculated
 caculation||calculation
 calender||calendar
+calescing||coalescing
 calle||called
 callibration||calibration
 calucate||calculate
@@ -210,6 +217,7 @@
 cancelation||cancellation
 cancle||cancel
 capabilites||capabilities
+capabilty||capability
 capabitilies||capabilities
 capatibilities||capabilities
 capapbilities||capabilities
@@ -302,6 +310,7 @@
 contaisn||contains
 contant||contact
 contence||contents
+continious||continuous
 continous||continuous
 continously||continuously
 continueing||continuing
@@ -393,6 +402,7 @@
 diffrent||different
 diffrentiate||differentiate
 difinition||definition
+dimesions||dimensions
 diplay||display
 direectly||directly
 disassocation||disassociation
@@ -449,6 +459,7 @@
 equivelant||equivalent
 equivilant||equivalent
 eror||error
+errorr||error
 estbalishment||establishment
 etsablishment||establishment
 etsbalishment||establishment
@@ -481,6 +492,7 @@
 faillure||failure
 failue||failure
 failuer||failure
+failng||failing
 faireness||fairness
 falied||failed
 faliure||failure
@@ -493,6 +505,7 @@
 fetaures||features
 fileystem||filesystem
 fimware||firmware
+firware||firmware
 finanize||finalize
 findn||find
 finilizes||finalizes
@@ -502,6 +515,7 @@
 followign||following
 followings||following
 follwing||following
+fonud||found
 forseeable||foreseeable
 forse||force
 fortan||fortran
@@ -532,6 +546,7 @@
 grahical||graphical
 grahpical||graphical
 grapic||graphic
+grranted||granted
 guage||gauge
 guarenteed||guaranteed
 guarentee||guarantee
@@ -543,6 +558,7 @@
 harware||hardware
 heirarchically||hierarchically
 helpfull||helpful
+hybernate||hibernate
 hierachy||hierarchy
 hierarchie||hierarchy
 howver||however
@@ -565,16 +581,19 @@
 implementaiton||implementation
 implementated||implemented
 implemention||implementation
+implementd||implemented
 implemetation||implementation
 implemntation||implementation
 implentation||implementation
 implmentation||implementation
 implmenting||implementing
+incative||inactive
 incomming||incoming
 incompatabilities||incompatibilities
 incompatable||incompatible
 inconsistant||inconsistent
 increas||increase
+incremeted||incremented
 incrment||increment
 indendation||indentation
 indended||intended
@@ -619,6 +638,7 @@
 intermittant||intermittent
 internel||internal
 interoprability||interoperability
+interuupt||interrupt
 interrface||interface
 interrrupt||interrupt
 interrup||interrupt
@@ -638,8 +658,10 @@
 intterrupt||interrupt
 intuative||intuitive
 invaid||invalid
+invald||invalid
 invalde||invalid
 invalide||invalid
+invalidiate||invalidate
 invalud||invalid
 invididual||individual
 invokation||invocation
@@ -713,6 +735,7 @@
 mispelled||misspelled
 mispelt||misspelt
 mising||missing
+mismactch||mismatch
 missmanaged||mismanaged
 missmatch||mismatch
 miximum||maximum
@@ -731,6 +754,7 @@
 multple||multiple
 mumber||number
 muticast||multicast
+mutilcast||multicast
 mutiple||multiple
 mutli||multi
 nams||names
@@ -834,6 +858,7 @@
 positon||position
 possibilites||possibilities
 powerfull||powerful
+preample||preamble
 preapre||prepare
 preceeded||preceded
 preceeding||preceding
@@ -1059,6 +1084,7 @@
 subdirectoires||subdirectories
 suble||subtle
 substract||subtract
+submition||submission
 succesfully||successfully
 succesful||successful
 successed||succeeded
@@ -1078,6 +1104,7 @@
 suppported||supported
 suppport||support
 supress||suppress
+surpressed||suppressed
 surpresses||suppresses
 susbsystem||subsystem
 suspeneded||suspended
@@ -1091,6 +1118,7 @@
 swithcing||switching
 swithed||switched
 swithing||switching
+swtich||switch
 symetric||symmetric
 synax||syntax
 synchonized||synchronized
@@ -1111,7 +1139,9 @@
 thier||their
 threds||threads
 threshhold||threshold
+thresold||threshold
 throught||through
+troughput||throughput
 thses||these
 tiggered||triggered
 tipically||typically
@@ -1120,6 +1150,7 @@
 torerable||tolerable
 tramsmitted||transmitted
 tramsmit||transmit
+tranasction||transaction
 tranfer||transfer
 transciever||transceiver
 transferd||transferred
@@ -1133,6 +1164,7 @@
 treshold||threshold
 trigerring||triggering
 trun||turn
+tunning||tuning
 ture||true
 tyep||type
 udpate||update
@@ -1199,6 +1231,7 @@
 vitual||virtual
 wakeus||wakeups
 wating||waiting
+wiat||wait
 wether||whether
 whataver||whatever
 whcih||which
diff --git a/security/apparmor/Makefile b/security/apparmor/Makefile
index a16b195..81a3442 100644
--- a/security/apparmor/Makefile
+++ b/security/apparmor/Makefile
@@ -4,7 +4,7 @@
 
 apparmor-y := apparmorfs.o audit.o capability.o context.o ipc.o lib.o match.o \
               path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \
-              resource.o secid.o file.o policy_ns.o label.o
+              resource.o secid.o file.o policy_ns.o label.o mount.o
 apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o
 
 clean-files := capability_names.h rlim_names.h
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 853c2ec..caaf51d 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -32,6 +32,7 @@
 #include "include/audit.h"
 #include "include/context.h"
 #include "include/crypto.h"
+#include "include/ipc.h"
 #include "include/policy_ns.h"
 #include "include/label.h"
 #include "include/policy.h"
@@ -248,8 +249,10 @@
 
 	inode_lock(dir);
 	dentry = lookup_one_len(name, parent, strlen(name));
-	if (IS_ERR(dentry))
+	if (IS_ERR(dentry)) {
+		error = PTR_ERR(dentry);
 		goto fail_lock;
+	}
 
 	if (d_really_is_positive(dentry)) {
 		error = -EEXIST;
@@ -1443,6 +1446,10 @@
 {
 	int i;
 
+	AA_BUG(!old);
+	AA_BUG(!new);
+	AA_BUG(!mutex_is_locked(&profiles_ns(old)->lock));
+
 	for (i = 0; i < AAFS_PROF_SIZEOF; i++) {
 		new->dents[i] = old->dents[i];
 		if (new->dents[i])
@@ -1506,6 +1513,9 @@
 	struct dentry *dent = NULL, *dir;
 	int error;
 
+	AA_BUG(!profile);
+	AA_BUG(!mutex_is_locked(&profiles_ns(profile)->lock));
+
 	if (!parent) {
 		struct aa_profile *p;
 		p = aa_deref_parent(profile);
@@ -1731,6 +1741,7 @@
 
 	if (!ns)
 		return;
+	AA_BUG(!mutex_is_locked(&ns->lock));
 
 	list_for_each_entry(child, &ns->base.profiles, base.list)
 		__aafs_profile_rmdir(child);
@@ -1903,6 +1914,10 @@
 {
 	struct aa_ns *parent, *next;
 
+	AA_BUG(!root);
+	AA_BUG(!ns);
+	AA_BUG(ns != root && !mutex_is_locked(&ns->parent->lock));
+
 	/* is next namespace a child */
 	if (!list_empty(&ns->sub_ns)) {
 		next = list_first_entry(&ns->sub_ns, typeof(*ns), base.list);
@@ -1937,6 +1952,9 @@
 static struct aa_profile *__first_profile(struct aa_ns *root,
 					  struct aa_ns *ns)
 {
+	AA_BUG(!root);
+	AA_BUG(ns && !mutex_is_locked(&ns->lock));
+
 	for (; ns; ns = __next_ns(root, ns)) {
 		if (!list_empty(&ns->base.profiles))
 			return list_first_entry(&ns->base.profiles,
@@ -1959,6 +1977,8 @@
 	struct aa_profile *parent;
 	struct aa_ns *ns = p->ns;
 
+	AA_BUG(!mutex_is_locked(&profiles_ns(p)->lock));
+
 	/* is next profile a child */
 	if (!list_empty(&p->base.profiles))
 		return list_first_entry(&p->base.profiles, typeof(*p),
@@ -2127,6 +2147,11 @@
 	{ }
 };
 
+static struct aa_sfs_entry aa_sfs_entry_signal[] = {
+	AA_SFS_FILE_STRING("mask", AA_SFS_SIG_MASK),
+	{ }
+};
+
 static struct aa_sfs_entry aa_sfs_entry_domain[] = {
 	AA_SFS_FILE_BOOLEAN("change_hat",	1),
 	AA_SFS_FILE_BOOLEAN("change_hatv",	1),
@@ -2151,9 +2176,14 @@
 	{ }
 };
 
+static struct aa_sfs_entry aa_sfs_entry_mount[] = {
+	AA_SFS_FILE_STRING("mask", "mount umount pivot_root"),
+	{ }
+};
+
 static struct aa_sfs_entry aa_sfs_entry_ns[] = {
 	AA_SFS_FILE_BOOLEAN("profile",		1),
-	AA_SFS_FILE_BOOLEAN("pivot_root",	1),
+	AA_SFS_FILE_BOOLEAN("pivot_root",	0),
 	{ }
 };
 
@@ -2172,22 +2202,24 @@
 	AA_SFS_DIR("policy",			aa_sfs_entry_policy),
 	AA_SFS_DIR("domain",			aa_sfs_entry_domain),
 	AA_SFS_DIR("file",			aa_sfs_entry_file),
+	AA_SFS_DIR("mount",			aa_sfs_entry_mount),
 	AA_SFS_DIR("namespaces",		aa_sfs_entry_ns),
 	AA_SFS_FILE_U64("capability",		VFS_CAP_FLAGS_MASK),
 	AA_SFS_DIR("rlimit",			aa_sfs_entry_rlimit),
 	AA_SFS_DIR("caps",			aa_sfs_entry_caps),
 	AA_SFS_DIR("ptrace",			aa_sfs_entry_ptrace),
+	AA_SFS_DIR("signal",			aa_sfs_entry_signal),
 	AA_SFS_DIR("query",			aa_sfs_entry_query),
 	{ }
 };
 
 static struct aa_sfs_entry aa_sfs_entry_apparmor[] = {
-	AA_SFS_FILE_FOPS(".access", 0640, &aa_sfs_access),
+	AA_SFS_FILE_FOPS(".access", 0666, &aa_sfs_access),
 	AA_SFS_FILE_FOPS(".stacked", 0444, &seq_ns_stacked_fops),
 	AA_SFS_FILE_FOPS(".ns_stacked", 0444, &seq_ns_nsstacked_fops),
-	AA_SFS_FILE_FOPS(".ns_level", 0666, &seq_ns_level_fops),
-	AA_SFS_FILE_FOPS(".ns_name", 0640, &seq_ns_name_fops),
-	AA_SFS_FILE_FOPS("profiles", 0440, &aa_sfs_profiles_fops),
+	AA_SFS_FILE_FOPS(".ns_level", 0444, &seq_ns_level_fops),
+	AA_SFS_FILE_FOPS(".ns_name", 0444, &seq_ns_name_fops),
+	AA_SFS_FILE_FOPS("profiles", 0444, &aa_sfs_profiles_fops),
 	AA_SFS_DIR("features", aa_sfs_entry_features),
 	{ }
 };
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 17a601c..dd754b7 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -374,8 +374,8 @@
  *
  * Returns: refcounted label, or NULL on failure (MAYBE NULL)
  */
-static struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
-				       const char **name)
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+				const char **name)
 {
 	struct aa_label *label = NULL;
 	u32 xtype = xindex & AA_X_TYPE_MASK;
diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h
index aaf893f..829082c 100644
--- a/security/apparmor/include/apparmor.h
+++ b/security/apparmor/include/apparmor.h
@@ -27,7 +27,9 @@
 #define AA_CLASS_NET		4
 #define AA_CLASS_RLIMITS	5
 #define AA_CLASS_DOMAIN		6
+#define AA_CLASS_MOUNT		7
 #define AA_CLASS_PTRACE		9
+#define AA_CLASS_SIGNAL		10
 #define AA_CLASS_LABEL		16
 
 #define AA_CLASS_LAST		AA_CLASS_LABEL
diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h
index c68839a..620e811 100644
--- a/security/apparmor/include/audit.h
+++ b/security/apparmor/include/audit.h
@@ -71,6 +71,10 @@
 #define OP_FMPROT "file_mprotect"
 #define OP_INHERIT "file_inherit"
 
+#define OP_PIVOTROOT "pivotroot"
+#define OP_MOUNT "mount"
+#define OP_UMOUNT "umount"
+
 #define OP_CREATE "create"
 #define OP_POST_CREATE "post_create"
 #define OP_BIND "bind"
@@ -86,6 +90,7 @@
 #define OP_SHUTDOWN "socket_shutdown"
 
 #define OP_PTRACE "ptrace"
+#define OP_SIGNAL "signal"
 
 #define OP_EXEC "exec"
 
@@ -122,14 +127,22 @@
 			} fs;
 		};
 		struct {
-			const char *name;
-			long pos;
+			struct aa_profile *profile;
 			const char *ns;
+			long pos;
 		} iface;
+		int signal;
 		struct {
 			int rlim;
 			unsigned long max;
 		} rlim;
+		struct {
+			const char *src_name;
+			const char *type;
+			const char *trans;
+			const char *data;
+			unsigned long flags;
+		} mnt;
 	};
 };
 
diff --git a/security/apparmor/include/domain.h b/security/apparmor/include/domain.h
index 24c5976..ac9862f 100644
--- a/security/apparmor/include/domain.h
+++ b/security/apparmor/include/domain.h
@@ -15,6 +15,8 @@
 #include <linux/binfmts.h>
 #include <linux/types.h>
 
+#include "label.h"
+
 #ifndef __AA_DOMAIN_H
 #define __AA_DOMAIN_H
 
@@ -29,6 +31,9 @@
 #define AA_CHANGE_ONEXEC  4
 #define AA_CHANGE_STACK 8
 
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+				const char **name);
+
 int apparmor_bprm_set_creds(struct linux_binprm *bprm);
 
 void aa_free_domain_entries(struct aa_domain *domain);
diff --git a/security/apparmor/include/ipc.h b/security/apparmor/include/ipc.h
index 656fdb8..5ffc218 100644
--- a/security/apparmor/include/ipc.h
+++ b/security/apparmor/include/ipc.h
@@ -27,8 +27,14 @@
 
 #define AA_PTRACE_PERM_MASK (AA_PTRACE_READ | AA_PTRACE_TRACE | \
 			     AA_MAY_BE_READ | AA_MAY_BE_TRACED)
+#define AA_SIGNAL_PERM_MASK (MAY_READ | MAY_WRITE)
+
+#define AA_SFS_SIG_MASK "hup int quit ill trap abrt bus fpe kill usr1 " \
+	"segv usr2 pipe alrm term stkflt chld cont stop stp ttin ttou urg " \
+	"xcpu xfsz vtalrm prof winch io pwr sys emt lost"
 
 int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee,
 		  u32 request);
+int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig);
 
 #endif /* __AA_IPC_H */
diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h
index 9a283b7..af22dcb 100644
--- a/security/apparmor/include/label.h
+++ b/security/apparmor/include/label.h
@@ -310,6 +310,7 @@
 #define FLAG_SHOW_MODE 1
 #define FLAG_VIEW_SUBNS 2
 #define FLAG_HIDDEN_UNCONFINED 4
+#define FLAG_ABS_ROOT 8
 int aa_label_snxprint(char *str, size_t size, struct aa_ns *view,
 		      struct aa_label *label, int flags);
 int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label,
diff --git a/security/apparmor/include/mount.h b/security/apparmor/include/mount.h
new file mode 100644
index 0000000..25d6067
--- /dev/null
+++ b/security/apparmor/include/mount.h
@@ -0,0 +1,54 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor file mediation function definitions.
+ *
+ * Copyright 2017 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_MOUNT_H
+#define __AA_MOUNT_H
+
+#include <linux/fs.h>
+#include <linux/path.h>
+
+#include "domain.h"
+#include "policy.h"
+
+/* mount perms */
+#define AA_MAY_PIVOTROOT	0x01
+#define AA_MAY_MOUNT		0x02
+#define AA_MAY_UMOUNT		0x04
+#define AA_AUDIT_DATA		0x40
+#define AA_MNT_CONT_MATCH	0x40
+
+#define AA_MS_IGNORE_MASK (MS_KERNMOUNT | MS_NOSEC | MS_ACTIVE | MS_BORN)
+
+int aa_remount(struct aa_label *label, const struct path *path,
+	       unsigned long flags, void *data);
+
+int aa_bind_mount(struct aa_label *label, const struct path *path,
+		  const char *old_name, unsigned long flags);
+
+
+int aa_mount_change_type(struct aa_label *label, const struct path *path,
+			 unsigned long flags);
+
+int aa_move_mount(struct aa_label *label, const struct path *path,
+		  const char *old_name);
+
+int aa_new_mount(struct aa_label *label, const char *dev_name,
+		 const struct path *path, const char *type, unsigned long flags,
+		 void *data);
+
+int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags);
+
+int aa_pivotroot(struct aa_label *label, const struct path *old_path,
+		 const struct path *new_path);
+
+#endif /* __AA_MOUNT_H */
diff --git a/security/apparmor/include/sig_names.h b/security/apparmor/include/sig_names.h
new file mode 100644
index 0000000..92e62fe
--- /dev/null
+++ b/security/apparmor/include/sig_names.h
@@ -0,0 +1,98 @@
+#include <linux/signal.h>
+
+#define SIGUNKNOWN 0
+#define MAXMAPPED_SIG 35
+/* provide a mapping of arch signal to internal signal # for mediation
+ * those that are always an alias SIGCLD for SIGCLHD and SIGPOLL for SIGIO
+ * map to the same entry those that may/or may not get a separate entry
+ */
+static const int sig_map[MAXMAPPED_SIG] = {
+	[0] = MAXMAPPED_SIG,	/* existence test */
+	[SIGHUP] = 1,
+	[SIGINT] = 2,
+	[SIGQUIT] = 3,
+	[SIGILL] = 4,
+	[SIGTRAP] = 5,		/* -, 5, - */
+	[SIGABRT] = 6,		/*  SIGIOT: -, 6, - */
+	[SIGBUS] = 7,		/* 10, 7, 10 */
+	[SIGFPE] = 8,
+	[SIGKILL] = 9,
+	[SIGUSR1] = 10,		/* 30, 10, 16 */
+	[SIGSEGV] = 11,
+	[SIGUSR2] = 12,		/* 31, 12, 17 */
+	[SIGPIPE] = 13,
+	[SIGALRM] = 14,
+	[SIGTERM] = 15,
+#ifdef SIGSTKFLT
+	[SIGSTKFLT] = 16,	/* -, 16, - */
+#endif
+	[SIGCHLD] = 17,		/* 20, 17, 18.  SIGCHLD -, -, 18 */
+	[SIGCONT] = 18,		/* 19, 18, 25 */
+	[SIGSTOP] = 19,		/* 17, 19, 23 */
+	[SIGTSTP] = 20,		/* 18, 20, 24 */
+	[SIGTTIN] = 21,		/* 21, 21, 26 */
+	[SIGTTOU] = 22,		/* 22, 22, 27 */
+	[SIGURG] = 23,		/* 16, 23, 21 */
+	[SIGXCPU] = 24,		/* 24, 24, 30 */
+	[SIGXFSZ] = 25,		/* 25, 25, 31 */
+	[SIGVTALRM] = 26,	/* 26, 26, 28 */
+	[SIGPROF] = 27,		/* 27, 27, 29 */
+	[SIGWINCH] = 28,	/* 28, 28, 20 */
+	[SIGIO] = 29,		/* SIGPOLL: 23, 29, 22 */
+	[SIGPWR] = 30,		/* 29, 30, 19.  SIGINFO 29, -, - */
+#ifdef SIGSYS
+	[SIGSYS] = 31,		/* 12, 31, 12. often SIG LOST/UNUSED */
+#endif
+#ifdef SIGEMT
+	[SIGEMT] = 32,		/* 7, - , 7 */
+#endif
+#if defined(SIGLOST) && SIGPWR != SIGLOST		/* sparc */
+	[SIGLOST] = 33,		/* unused on Linux */
+#endif
+#if defined(SIGUNUSED) && \
+    defined(SIGLOST) && defined(SIGSYS) && SIGLOST != SIGSYS
+	[SIGUNUSED] = 34,	/* -, 31, - */
+#endif
+};
+
+/* this table is ordered post sig_map[sig] mapping */
+static const char *const sig_names[MAXMAPPED_SIG + 1] = {
+	"unknown",
+	"hup",
+	"int",
+	"quit",
+	"ill",
+	"trap",
+	"abrt",
+	"bus",
+	"fpe",
+	"kill",
+	"usr1",
+	"segv",
+	"usr2",
+	"pipe",
+	"alrm",
+	"term",
+	"stkflt",
+	"chld",
+	"cont",
+	"stop",
+	"stp",
+	"ttin",
+	"ttou",
+	"urg",
+	"xcpu",
+	"xfsz",
+	"vtalrm",
+	"prof",
+	"winch",
+	"io",
+	"pwr",
+	"sys",
+	"emt",
+	"lost",
+	"unused",
+
+	"exists",	/* always last existence test mapped to MAXMAPPED_SIG */
+};
+
diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c
index 11e66b5..66fb9ed 100644
--- a/security/apparmor/ipc.c
+++ b/security/apparmor/ipc.c
@@ -20,6 +20,7 @@
 #include "include/context.h"
 #include "include/policy.h"
 #include "include/ipc.h"
+#include "include/sig_names.h"
 
 /**
  * audit_ptrace_mask - convert mask to permission string
@@ -121,3 +122,101 @@
 }
 
 
+static inline int map_signal_num(int sig)
+{
+	if (sig > SIGRTMAX)
+		return SIGUNKNOWN;
+	else if (sig >= SIGRTMIN)
+		return sig - SIGRTMIN + 128;	/* rt sigs mapped to 128 */
+	else if (sig <= MAXMAPPED_SIG)
+		return sig_map[sig];
+	return SIGUNKNOWN;
+}
+
+/**
+ * audit_file_mask - convert mask to permission string
+ * @buffer: buffer to write string to (NOT NULL)
+ * @mask: permission mask to convert
+ */
+static void audit_signal_mask(struct audit_buffer *ab, u32 mask)
+{
+	if (mask & MAY_READ)
+		audit_log_string(ab, "receive");
+	if (mask & MAY_WRITE)
+		audit_log_string(ab, "send");
+}
+
+/**
+ * audit_cb - call back for signal specific audit fields
+ * @ab: audit_buffer  (NOT NULL)
+ * @va: audit struct to audit values of  (NOT NULL)
+ */
+static void audit_signal_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+
+	if (aad(sa)->request & AA_SIGNAL_PERM_MASK) {
+		audit_log_format(ab, " requested_mask=");
+		audit_signal_mask(ab, aad(sa)->request);
+		if (aad(sa)->denied & AA_SIGNAL_PERM_MASK) {
+			audit_log_format(ab, " denied_mask=");
+			audit_signal_mask(ab, aad(sa)->denied);
+		}
+	}
+	if (aad(sa)->signal <= MAXMAPPED_SIG)
+		audit_log_format(ab, " signal=%s", sig_names[aad(sa)->signal]);
+	else
+		audit_log_format(ab, " signal=rtmin+%d",
+				 aad(sa)->signal - 128);
+	audit_log_format(ab, " peer=");
+	aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer,
+			FLAGS_NONE, GFP_ATOMIC);
+}
+
+/* TODO: update to handle compound name&name2, conditionals */
+static void profile_match_signal(struct aa_profile *profile, const char *label,
+				 int signal, struct aa_perms *perms)
+{
+	unsigned int state;
+
+	/* TODO: secondary cache check <profile, profile, perm> */
+	state = aa_dfa_next(profile->policy.dfa,
+			    profile->policy.start[AA_CLASS_SIGNAL],
+			    signal);
+	state = aa_dfa_match(profile->policy.dfa, state, label);
+	aa_compute_perms(profile->policy.dfa, state, perms);
+}
+
+static int profile_signal_perm(struct aa_profile *profile,
+			       struct aa_profile *peer, u32 request,
+			       struct common_audit_data *sa)
+{
+	struct aa_perms perms;
+
+	if (profile_unconfined(profile) ||
+	    !PROFILE_MEDIATES(profile, AA_CLASS_SIGNAL))
+		return 0;
+
+	aad(sa)->peer = &peer->label;
+	profile_match_signal(profile, peer->base.hname, aad(sa)->signal,
+			     &perms);
+	aa_apply_modes_to_perms(profile, &perms);
+	return aa_check_perms(profile, &perms, request, sa, audit_signal_cb);
+}
+
+static int aa_signal_cross_perm(struct aa_profile *sender,
+				struct aa_profile *target,
+				struct common_audit_data *sa)
+{
+	return xcheck(profile_signal_perm(sender, target, MAY_WRITE, sa),
+		      profile_signal_perm(target, sender, MAY_READ, sa));
+}
+
+int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig)
+{
+	DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, OP_SIGNAL);
+
+	aad(&sa)->signal = map_signal_num(sig);
+	return xcheck_labels_profiles(sender, target, aa_signal_cross_perm,
+				      &sa);
+}
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index e052eab..c5b99b9 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -49,7 +49,7 @@
 		/* p->label will not updated any more as p is dead */
 		aa_put_label(rcu_dereference_protected(proxy->label, true));
 		memset(proxy, 0, sizeof(*proxy));
-		proxy->label = (struct aa_label *) PROXY_POISON;
+		RCU_INIT_POINTER(proxy->label, (struct aa_label *)PROXY_POISON);
 		kfree(proxy);
 	}
 }
@@ -1450,9 +1450,11 @@
  * cached label name is present and visible
  * @label->hname only exists if label is namespace hierachical
  */
-static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label)
+static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label,
+				   int flags)
 {
-	if (label->hname && labels_ns(label) == ns)
+	if (label->hname && (!ns || labels_ns(label) == ns) &&
+	    !(flags & ~FLAG_SHOW_MODE))
 		return true;
 
 	return false;
@@ -1495,7 +1497,7 @@
 		view = profiles_ns(profile);
 
 	if (view != profile->ns &&
-	    (!prev_ns || (prev_ns && *prev_ns != profile->ns))) {
+	    (!prev_ns || (*prev_ns != profile->ns))) {
 		if (prev_ns)
 			*prev_ns = profile->ns;
 		ns_name = aa_ns_name(view, profile->ns,
@@ -1605,8 +1607,13 @@
 	AA_BUG(!str && size != 0);
 	AA_BUG(!label);
 
-	if (!ns)
+	if (flags & FLAG_ABS_ROOT) {
+		ns = root_ns;
+		len = snprintf(str, size, "=");
+		update_for_len(total, len, size, str);
+	} else if (!ns) {
 		ns = labels_ns(label);
+	}
 
 	label_for_each(i, label, profile) {
 		if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) {
@@ -1710,10 +1717,8 @@
 	AA_BUG(!ab);
 	AA_BUG(!label);
 
-	if (!ns)
-		ns = labels_ns(label);
-
-	if (!use_label_hname(ns, label) || display_mode(ns, label, flags)) {
+	if (!use_label_hname(ns, label, flags) ||
+	    display_mode(ns, label, flags)) {
 		len  = aa_label_asxprint(&name, ns, label, flags, gfp);
 		if (len == -1) {
 			AA_DEBUG("label print error");
@@ -1738,10 +1743,7 @@
 	AA_BUG(!f);
 	AA_BUG(!label);
 
-	if (!ns)
-		ns = labels_ns(label);
-
-	if (!use_label_hname(ns, label)) {
+	if (!use_label_hname(ns, label, flags)) {
 		char *str;
 		int len;
 
@@ -1764,10 +1766,7 @@
 {
 	AA_BUG(!label);
 
-	if (!ns)
-		ns = labels_ns(label);
-
-	if (!use_label_hname(ns, label)) {
+	if (!use_label_hname(ns, label, flags)) {
 		char *str;
 		int len;
 
@@ -1874,6 +1873,9 @@
 		if (*str == '&')
 			str++;
 	}
+	if (*str == '=')
+		base = &root_ns->unconfined->label;
+
 	error = vec_setup(profile, vec, len, gfp);
 	if (error)
 		return ERR_PTR(error);
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 7a82c0f..1346ee5 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -38,6 +38,7 @@
 #include "include/policy.h"
 #include "include/policy_ns.h"
 #include "include/procattr.h"
+#include "include/mount.h"
 
 /* Flag indicating whether initialization completed */
 int apparmor_initialized;
@@ -511,6 +512,65 @@
 			   !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0);
 }
 
+static int apparmor_sb_mount(const char *dev_name, const struct path *path,
+			     const char *type, unsigned long flags, void *data)
+{
+	struct aa_label *label;
+	int error = 0;
+
+	/* Discard magic */
+	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+		flags &= ~MS_MGC_MSK;
+
+	flags &= ~AA_MS_IGNORE_MASK;
+
+	label = __begin_current_label_crit_section();
+	if (!unconfined(label)) {
+		if (flags & MS_REMOUNT)
+			error = aa_remount(label, path, flags, data);
+		else if (flags & MS_BIND)
+			error = aa_bind_mount(label, path, dev_name, flags);
+		else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE |
+				  MS_UNBINDABLE))
+			error = aa_mount_change_type(label, path, flags);
+		else if (flags & MS_MOVE)
+			error = aa_move_mount(label, path, dev_name);
+		else
+			error = aa_new_mount(label, dev_name, path, type,
+					     flags, data);
+	}
+	__end_current_label_crit_section(label);
+
+	return error;
+}
+
+static int apparmor_sb_umount(struct vfsmount *mnt, int flags)
+{
+	struct aa_label *label;
+	int error = 0;
+
+	label = __begin_current_label_crit_section();
+	if (!unconfined(label))
+		error = aa_umount(label, mnt, flags);
+	__end_current_label_crit_section(label);
+
+	return error;
+}
+
+static int apparmor_sb_pivotroot(const struct path *old_path,
+				 const struct path *new_path)
+{
+	struct aa_label *label;
+	int error = 0;
+
+	label = aa_get_current_label();
+	if (!unconfined(label))
+		error = aa_pivotroot(label, old_path, new_path);
+	aa_put_label(label);
+
+	return error;
+}
+
 static int apparmor_getprocattr(struct task_struct *task, char *name,
 				char **value)
 {
@@ -656,12 +716,36 @@
 	return error;
 }
 
+static int apparmor_task_kill(struct task_struct *target, struct siginfo *info,
+			      int sig, u32 secid)
+{
+	struct aa_label *cl, *tl;
+	int error;
+
+	if (secid)
+		/* TODO: after secid to label mapping is done.
+		 *  Dealing with USB IO specific behavior
+		 */
+		return 0;
+	cl = __begin_current_label_crit_section();
+	tl = aa_get_task_label(target);
+	error = aa_may_signal(cl, tl, sig);
+	aa_put_label(tl);
+	__end_current_label_crit_section(cl);
+
+	return error;
+}
+
 static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check),
 	LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme),
 	LSM_HOOK_INIT(capget, apparmor_capget),
 	LSM_HOOK_INIT(capable, apparmor_capable),
 
+	LSM_HOOK_INIT(sb_mount, apparmor_sb_mount),
+	LSM_HOOK_INIT(sb_umount, apparmor_sb_umount),
+	LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot),
+
 	LSM_HOOK_INIT(path_link, apparmor_path_link),
 	LSM_HOOK_INIT(path_unlink, apparmor_path_unlink),
 	LSM_HOOK_INIT(path_symlink, apparmor_path_symlink),
@@ -696,6 +780,7 @@
 	LSM_HOOK_INIT(bprm_committed_creds, apparmor_bprm_committed_creds),
 
 	LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit),
+	LSM_HOOK_INIT(task_kill, apparmor_task_kill),
 };
 
 /*
diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c
new file mode 100644
index 0000000..82a64b5
--- /dev/null
+++ b/security/apparmor/mount.c
@@ -0,0 +1,696 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor mediation of files
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/domain.h"
+#include "include/file.h"
+#include "include/match.h"
+#include "include/mount.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+
+static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags)
+{
+	if (flags & MS_RDONLY)
+		audit_log_format(ab, "ro");
+	else
+		audit_log_format(ab, "rw");
+	if (flags & MS_NOSUID)
+		audit_log_format(ab, ", nosuid");
+	if (flags & MS_NODEV)
+		audit_log_format(ab, ", nodev");
+	if (flags & MS_NOEXEC)
+		audit_log_format(ab, ", noexec");
+	if (flags & MS_SYNCHRONOUS)
+		audit_log_format(ab, ", sync");
+	if (flags & MS_REMOUNT)
+		audit_log_format(ab, ", remount");
+	if (flags & MS_MANDLOCK)
+		audit_log_format(ab, ", mand");
+	if (flags & MS_DIRSYNC)
+		audit_log_format(ab, ", dirsync");
+	if (flags & MS_NOATIME)
+		audit_log_format(ab, ", noatime");
+	if (flags & MS_NODIRATIME)
+		audit_log_format(ab, ", nodiratime");
+	if (flags & MS_BIND)
+		audit_log_format(ab, flags & MS_REC ? ", rbind" : ", bind");
+	if (flags & MS_MOVE)
+		audit_log_format(ab, ", move");
+	if (flags & MS_SILENT)
+		audit_log_format(ab, ", silent");
+	if (flags & MS_POSIXACL)
+		audit_log_format(ab, ", acl");
+	if (flags & MS_UNBINDABLE)
+		audit_log_format(ab, flags & MS_REC ? ", runbindable" :
+				 ", unbindable");
+	if (flags & MS_PRIVATE)
+		audit_log_format(ab, flags & MS_REC ? ", rprivate" :
+				 ", private");
+	if (flags & MS_SLAVE)
+		audit_log_format(ab, flags & MS_REC ? ", rslave" :
+				 ", slave");
+	if (flags & MS_SHARED)
+		audit_log_format(ab, flags & MS_REC ? ", rshared" :
+				 ", shared");
+	if (flags & MS_RELATIME)
+		audit_log_format(ab, ", relatime");
+	if (flags & MS_I_VERSION)
+		audit_log_format(ab, ", iversion");
+	if (flags & MS_STRICTATIME)
+		audit_log_format(ab, ", strictatime");
+	if (flags & MS_NOUSER)
+		audit_log_format(ab, ", nouser");
+}
+
+/**
+ * audit_cb - call back for mount specific audit fields
+ * @ab: audit_buffer  (NOT NULL)
+ * @va: audit struct to audit values of  (NOT NULL)
+ */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+
+	if (aad(sa)->mnt.type) {
+		audit_log_format(ab, " fstype=");
+		audit_log_untrustedstring(ab, aad(sa)->mnt.type);
+	}
+	if (aad(sa)->mnt.src_name) {
+		audit_log_format(ab, " srcname=");
+		audit_log_untrustedstring(ab, aad(sa)->mnt.src_name);
+	}
+	if (aad(sa)->mnt.trans) {
+		audit_log_format(ab, " trans=");
+		audit_log_untrustedstring(ab, aad(sa)->mnt.trans);
+	}
+	if (aad(sa)->mnt.flags) {
+		audit_log_format(ab, " flags=\"");
+		audit_mnt_flags(ab, aad(sa)->mnt.flags);
+		audit_log_format(ab, "\"");
+	}
+	if (aad(sa)->mnt.data) {
+		audit_log_format(ab, " options=");
+		audit_log_untrustedstring(ab, aad(sa)->mnt.data);
+	}
+}
+
+/**
+ * audit_mount - handle the auditing of mount operations
+ * @profile: the profile being enforced  (NOT NULL)
+ * @op: operation being mediated (NOT NULL)
+ * @name: name of object being mediated (MAYBE NULL)
+ * @src_name: src_name of object being mediated (MAYBE_NULL)
+ * @type: type of filesystem (MAYBE_NULL)
+ * @trans: name of trans (MAYBE NULL)
+ * @flags: filesystem idependent mount flags
+ * @data: filesystem mount flags
+ * @request: permissions requested
+ * @perms: the permissions computed for the request (NOT NULL)
+ * @info: extra information message (MAYBE NULL)
+ * @error: 0 if operation allowed else failure error code
+ *
+ * Returns: %0 or error on failure
+ */
+static int audit_mount(struct aa_profile *profile, const char *op,
+		       const char *name, const char *src_name,
+		       const char *type, const char *trans,
+		       unsigned long flags, const void *data, u32 request,
+		       struct aa_perms *perms, const char *info, int error)
+{
+	int audit_type = AUDIT_APPARMOR_AUTO;
+	DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, op);
+
+	if (likely(!error)) {
+		u32 mask = perms->audit;
+
+		if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL))
+			mask = 0xffff;
+
+		/* mask off perms that are not being force audited */
+		request &= mask;
+
+		if (likely(!request))
+			return 0;
+		audit_type = AUDIT_APPARMOR_AUDIT;
+	} else {
+		/* only report permissions that were denied */
+		request = request & ~perms->allow;
+
+		if (request & perms->kill)
+			audit_type = AUDIT_APPARMOR_KILL;
+
+		/* quiet known rejects, assumes quiet and kill do not overlap */
+		if ((request & perms->quiet) &&
+		    AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+		    AUDIT_MODE(profile) != AUDIT_ALL)
+			request &= ~perms->quiet;
+
+		if (!request)
+			return error;
+	}
+
+	aad(&sa)->name = name;
+	aad(&sa)->mnt.src_name = src_name;
+	aad(&sa)->mnt.type = type;
+	aad(&sa)->mnt.trans = trans;
+	aad(&sa)->mnt.flags = flags;
+	if (data && (perms->audit & AA_AUDIT_DATA))
+		aad(&sa)->mnt.data = data;
+	aad(&sa)->info = info;
+	aad(&sa)->error = error;
+
+	return aa_audit(audit_type, profile, &sa, audit_cb);
+}
+
+/**
+ * match_mnt_flags - Do an ordered match on mount flags
+ * @dfa: dfa to match against
+ * @state: state to start in
+ * @flags: mount flags to match against
+ *
+ * Mount flags are encoded as an ordered match. This is done instead of
+ * checking against a simple bitmask, to allow for logical operations
+ * on the flags.
+ *
+ * Returns: next state after flags match
+ */
+static unsigned int match_mnt_flags(struct aa_dfa *dfa, unsigned int state,
+				    unsigned long flags)
+{
+	unsigned int i;
+
+	for (i = 0; i <= 31 ; ++i) {
+		if ((1 << i) & flags)
+			state = aa_dfa_next(dfa, state, i + 1);
+	}
+
+	return state;
+}
+
+/**
+ * compute_mnt_perms - compute mount permission associated with @state
+ * @dfa: dfa to match against (NOT NULL)
+ * @state: state match finished in
+ *
+ * Returns: mount permissions
+ */
+static struct aa_perms compute_mnt_perms(struct aa_dfa *dfa,
+					   unsigned int state)
+{
+	struct aa_perms perms;
+
+	perms.kill = 0;
+	perms.allow = dfa_user_allow(dfa, state);
+	perms.audit = dfa_user_audit(dfa, state);
+	perms.quiet = dfa_user_quiet(dfa, state);
+	perms.xindex = dfa_user_xindex(dfa, state);
+
+	return perms;
+}
+
+static const char * const mnt_info_table[] = {
+	"match succeeded",
+	"failed mntpnt match",
+	"failed srcname match",
+	"failed type match",
+	"failed flags match",
+	"failed data match"
+};
+
+/*
+ * Returns 0 on success else element that match failed in, this is the
+ * index into the mnt_info_table above
+ */
+static int do_match_mnt(struct aa_dfa *dfa, unsigned int start,
+			const char *mntpnt, const char *devname,
+			const char *type, unsigned long flags,
+			void *data, bool binary, struct aa_perms *perms)
+{
+	unsigned int state;
+
+	AA_BUG(!dfa);
+	AA_BUG(!perms);
+
+	state = aa_dfa_match(dfa, start, mntpnt);
+	state = aa_dfa_null_transition(dfa, state);
+	if (!state)
+		return 1;
+
+	if (devname)
+		state = aa_dfa_match(dfa, state, devname);
+	state = aa_dfa_null_transition(dfa, state);
+	if (!state)
+		return 2;
+
+	if (type)
+		state = aa_dfa_match(dfa, state, type);
+	state = aa_dfa_null_transition(dfa, state);
+	if (!state)
+		return 3;
+
+	state = match_mnt_flags(dfa, state, flags);
+	if (!state)
+		return 4;
+	*perms = compute_mnt_perms(dfa, state);
+	if (perms->allow & AA_MAY_MOUNT)
+		return 0;
+
+	/* only match data if not binary and the DFA flags data is expected */
+	if (data && !binary && (perms->allow & AA_MNT_CONT_MATCH)) {
+		state = aa_dfa_null_transition(dfa, state);
+		if (!state)
+			return 4;
+
+		state = aa_dfa_match(dfa, state, data);
+		if (!state)
+			return 5;
+		*perms = compute_mnt_perms(dfa, state);
+		if (perms->allow & AA_MAY_MOUNT)
+			return 0;
+	}
+
+	/* failed at end of flags match */
+	return 4;
+}
+
+
+static int path_flags(struct aa_profile *profile, const struct path *path)
+{
+	AA_BUG(!profile);
+	AA_BUG(!path);
+
+	return profile->path_flags |
+		(S_ISDIR(path->dentry->d_inode->i_mode) ? PATH_IS_DIR : 0);
+}
+
+/**
+ * match_mnt_path_str - handle path matching for mount
+ * @profile: the confining profile
+ * @mntpath: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devnme: string for the devname/src_name (MAY BE NULL OR ERRPTR)
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ * @devinfo: error str if (IS_ERR(@devname))
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt_path_str(struct aa_profile *profile,
+			      const struct path *mntpath, char *buffer,
+			      const char *devname, const char *type,
+			      unsigned long flags, void *data, bool binary,
+			      const char *devinfo)
+{
+	struct aa_perms perms = { };
+	const char *mntpnt = NULL, *info = NULL;
+	int pos, error;
+
+	AA_BUG(!profile);
+	AA_BUG(!mntpath);
+	AA_BUG(!buffer);
+
+	error = aa_path_name(mntpath, path_flags(profile, mntpath), buffer,
+			     &mntpnt, &info, profile->disconnected);
+	if (error)
+		goto audit;
+	if (IS_ERR(devname)) {
+		error = PTR_ERR(devname);
+		devname = NULL;
+		info = devinfo;
+		goto audit;
+	}
+
+	error = -EACCES;
+	pos = do_match_mnt(profile->policy.dfa,
+			   profile->policy.start[AA_CLASS_MOUNT],
+			   mntpnt, devname, type, flags, data, binary, &perms);
+	if (pos) {
+		info = mnt_info_table[pos];
+		goto audit;
+	}
+	error = 0;
+
+audit:
+	return audit_mount(profile, OP_MOUNT, mntpnt, devname, type, NULL,
+			   flags, data, AA_MAY_MOUNT, &perms, info, error);
+}
+
+/**
+ * match_mnt - handle path matching for mount
+ * @profile: the confining profile
+ * @mntpath: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devpath: path devname/src_name (MAYBE NULL)
+ * @devbuffer: buffer to be used to lookup devname/src_name
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt(struct aa_profile *profile, const struct path *path,
+		     char *buffer, struct path *devpath, char *devbuffer,
+		     const char *type, unsigned long flags, void *data,
+		     bool binary)
+{
+	const char *devname = NULL, *info = NULL;
+	int error = -EACCES;
+
+	AA_BUG(!profile);
+	AA_BUG(devpath && !devbuffer);
+
+	if (devpath) {
+		error = aa_path_name(devpath, path_flags(profile, devpath),
+				     devbuffer, &devname, &info,
+				     profile->disconnected);
+		if (error)
+			devname = ERR_PTR(error);
+	}
+
+	return match_mnt_path_str(profile, path, buffer, devname, type, flags,
+				  data, binary, info);
+}
+
+int aa_remount(struct aa_label *label, const struct path *path,
+	       unsigned long flags, void *data)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	bool binary;
+	int error;
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	binary = path->dentry->d_sb->s_type->fs_flags & FS_BINARY_MOUNTDATA;
+
+	get_buffers(buffer);
+	error = fn_for_each_confined(label, profile,
+			match_mnt(profile, path, buffer, NULL, NULL, NULL,
+				  flags, data, binary));
+	put_buffers(buffer);
+
+	return error;
+}
+
+int aa_bind_mount(struct aa_label *label, const struct path *path,
+		  const char *dev_name, unsigned long flags)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL, *old_buffer = NULL;
+	struct path old_path;
+	int error;
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	if (!dev_name || !*dev_name)
+		return -EINVAL;
+
+	flags &= MS_REC | MS_BIND;
+
+	error = kern_path(dev_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
+	if (error)
+		return error;
+
+	get_buffers(buffer, old_buffer);
+	error = fn_for_each_confined(label, profile,
+			match_mnt(profile, path, buffer, &old_path, old_buffer,
+				  NULL, flags, NULL, false));
+	put_buffers(buffer, old_buffer);
+	path_put(&old_path);
+
+	return error;
+}
+
+int aa_mount_change_type(struct aa_label *label, const struct path *path,
+			 unsigned long flags)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	int error;
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	/* These are the flags allowed by do_change_type() */
+	flags &= (MS_REC | MS_SILENT | MS_SHARED | MS_PRIVATE | MS_SLAVE |
+		  MS_UNBINDABLE);
+
+	get_buffers(buffer);
+	error = fn_for_each_confined(label, profile,
+			match_mnt(profile, path, buffer, NULL, NULL, NULL,
+				  flags, NULL, false));
+	put_buffers(buffer);
+
+	return error;
+}
+
+int aa_move_mount(struct aa_label *label, const struct path *path,
+		  const char *orig_name)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL, *old_buffer = NULL;
+	struct path old_path;
+	int error;
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	if (!orig_name || !*orig_name)
+		return -EINVAL;
+
+	error = kern_path(orig_name, LOOKUP_FOLLOW, &old_path);
+	if (error)
+		return error;
+
+	get_buffers(buffer, old_buffer);
+	error = fn_for_each_confined(label, profile,
+			match_mnt(profile, path, buffer, &old_path, old_buffer,
+				  NULL, MS_MOVE, NULL, false));
+	put_buffers(buffer, old_buffer);
+	path_put(&old_path);
+
+	return error;
+}
+
+int aa_new_mount(struct aa_label *label, const char *dev_name,
+		 const struct path *path, const char *type, unsigned long flags,
+		 void *data)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL, *dev_buffer = NULL;
+	bool binary = true;
+	int error;
+	int requires_dev = 0;
+	struct path tmp_path, *dev_path = NULL;
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	if (type) {
+		struct file_system_type *fstype;
+
+		fstype = get_fs_type(type);
+		if (!fstype)
+			return -ENODEV;
+		binary = fstype->fs_flags & FS_BINARY_MOUNTDATA;
+		requires_dev = fstype->fs_flags & FS_REQUIRES_DEV;
+		put_filesystem(fstype);
+
+		if (requires_dev) {
+			if (!dev_name || !*dev_name)
+				return -ENOENT;
+
+			error = kern_path(dev_name, LOOKUP_FOLLOW, &tmp_path);
+			if (error)
+				return error;
+			dev_path = &tmp_path;
+		}
+	}
+
+	get_buffers(buffer, dev_buffer);
+	if (dev_path) {
+		error = fn_for_each_confined(label, profile,
+			match_mnt(profile, path, buffer, dev_path, dev_buffer,
+				  type, flags, data, binary));
+	} else {
+		error = fn_for_each_confined(label, profile,
+			match_mnt_path_str(profile, path, buffer, dev_name,
+					   type, flags, data, binary, NULL));
+	}
+	put_buffers(buffer, dev_buffer);
+	if (dev_path)
+		path_put(dev_path);
+
+	return error;
+}
+
+static int profile_umount(struct aa_profile *profile, struct path *path,
+			  char *buffer)
+{
+	struct aa_perms perms = { };
+	const char *name = NULL, *info = NULL;
+	unsigned int state;
+	int error;
+
+	AA_BUG(!profile);
+	AA_BUG(!path);
+
+	error = aa_path_name(path, path_flags(profile, path), buffer, &name,
+			     &info, profile->disconnected);
+	if (error)
+		goto audit;
+
+	state = aa_dfa_match(profile->policy.dfa,
+			     profile->policy.start[AA_CLASS_MOUNT],
+			     name);
+	perms = compute_mnt_perms(profile->policy.dfa, state);
+	if (AA_MAY_UMOUNT & ~perms.allow)
+		error = -EACCES;
+
+audit:
+	return audit_mount(profile, OP_UMOUNT, name, NULL, NULL, NULL, 0, NULL,
+			   AA_MAY_UMOUNT, &perms, info, error);
+}
+
+int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	int error;
+	struct path path = { .mnt = mnt, .dentry = mnt->mnt_root };
+
+	AA_BUG(!label);
+	AA_BUG(!mnt);
+
+	get_buffers(buffer);
+	error = fn_for_each_confined(label, profile,
+			profile_umount(profile, &path, buffer));
+	put_buffers(buffer);
+
+	return error;
+}
+
+/* helper fn for transition on pivotroot
+ *
+ * Returns: label for transition or ERR_PTR. Does not return NULL
+ */
+static struct aa_label *build_pivotroot(struct aa_profile *profile,
+					const struct path *new_path,
+					char *new_buffer,
+					const struct path *old_path,
+					char *old_buffer)
+{
+	const char *old_name, *new_name = NULL, *info = NULL;
+	const char *trans_name = NULL;
+	struct aa_perms perms = { };
+	unsigned int state;
+	int error;
+
+	AA_BUG(!profile);
+	AA_BUG(!new_path);
+	AA_BUG(!old_path);
+
+	if (profile_unconfined(profile))
+		return aa_get_newest_label(&profile->label);
+
+	error = aa_path_name(old_path, path_flags(profile, old_path),
+			     old_buffer, &old_name, &info,
+			     profile->disconnected);
+	if (error)
+		goto audit;
+	error = aa_path_name(new_path, path_flags(profile, new_path),
+			     new_buffer, &new_name, &info,
+			     profile->disconnected);
+	if (error)
+		goto audit;
+
+	error = -EACCES;
+	state = aa_dfa_match(profile->policy.dfa,
+			     profile->policy.start[AA_CLASS_MOUNT],
+			     new_name);
+	state = aa_dfa_null_transition(profile->policy.dfa, state);
+	state = aa_dfa_match(profile->policy.dfa, state, old_name);
+	perms = compute_mnt_perms(profile->policy.dfa, state);
+
+	if (AA_MAY_PIVOTROOT & perms.allow)
+		error = 0;
+
+audit:
+	error = audit_mount(profile, OP_PIVOTROOT, new_name, old_name,
+			    NULL, trans_name, 0, NULL, AA_MAY_PIVOTROOT,
+			    &perms, info, error);
+	if (error)
+		return ERR_PTR(error);
+
+	return aa_get_newest_label(&profile->label);
+}
+
+int aa_pivotroot(struct aa_label *label, const struct path *old_path,
+		 const struct path *new_path)
+{
+	struct aa_profile *profile;
+	struct aa_label *target = NULL;
+	char *old_buffer = NULL, *new_buffer = NULL, *info = NULL;
+	int error;
+
+	AA_BUG(!label);
+	AA_BUG(!old_path);
+	AA_BUG(!new_path);
+
+	get_buffers(old_buffer, new_buffer);
+	target = fn_label_build(label, profile, GFP_ATOMIC,
+			build_pivotroot(profile, new_path, new_buffer,
+					old_path, old_buffer));
+	if (!target) {
+		info = "label build failed";
+		error = -ENOMEM;
+		goto fail;
+	} else if (!IS_ERR(target)) {
+		error = aa_replace_current_label(target);
+		if (error) {
+			/* TODO: audit target */
+			aa_put_label(target);
+			goto out;
+		}
+	} else
+		/* already audited error */
+		error = PTR_ERR(target);
+out:
+	put_buffers(old_buffer, new_buffer);
+
+	return error;
+
+fail:
+	/* TODO: add back in auditing of new_name and old_name */
+	error = fn_for_each(label, profile,
+			audit_mount(profile, OP_PIVOTROOT, NULL /*new_name */,
+				    NULL /* old_name */,
+				    NULL, NULL,
+				    0, NULL, AA_MAY_PIVOTROOT, &nullperms, info,
+				    error));
+	goto out;
+}
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 244ea4a..4243b0c 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -289,85 +289,6 @@
 	return NULL;
 }
 
-/**
- * aa_new_null_profile - create or find a null-X learning profile
- * @parent: profile that caused this profile to be created (NOT NULL)
- * @hat: true if the null- learning profile is a hat
- * @base: name to base the null profile off of
- * @gfp: type of allocation
- *
- * Find/Create a null- complain mode profile used in learning mode.  The
- * name of the profile is unique and follows the format of parent//null-XXX.
- * where XXX is based on the @name or if that fails or is not supplied
- * a unique number
- *
- * null profiles are added to the profile list but the list does not
- * hold a count on them so that they are automatically released when
- * not in use.
- *
- * Returns: new refcounted profile else NULL on failure
- */
-struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat,
-				       const char *base, gfp_t gfp)
-{
-	struct aa_profile *profile;
-	char *name;
-
-	AA_BUG(!parent);
-
-	if (base) {
-		name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base),
-			       gfp);
-		if (name) {
-			sprintf(name, "%s//null-%s", parent->base.hname, base);
-			goto name;
-		}
-		/* fall through to try shorter uniq */
-	}
-
-	name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp);
-	if (!name)
-		return NULL;
-	sprintf(name, "%s//null-%x", parent->base.hname,
-		atomic_inc_return(&parent->ns->uniq_null));
-
-name:
-	/* lookup to see if this is a dup creation */
-	profile = aa_find_child(parent, basename(name));
-	if (profile)
-		goto out;
-
-	profile = aa_alloc_profile(name, NULL, gfp);
-	if (!profile)
-		goto fail;
-
-	profile->mode = APPARMOR_COMPLAIN;
-	profile->label.flags |= FLAG_NULL;
-	if (hat)
-		profile->label.flags |= FLAG_HAT;
-	profile->path_flags = parent->path_flags;
-
-	/* released on free_profile */
-	rcu_assign_pointer(profile->parent, aa_get_profile(parent));
-	profile->ns = aa_get_ns(parent->ns);
-	profile->file.dfa = aa_get_dfa(nulldfa);
-	profile->policy.dfa = aa_get_dfa(nulldfa);
-
-	mutex_lock(&profile->ns->lock);
-	__add_profile(&parent->base.profiles, profile);
-	mutex_unlock(&profile->ns->lock);
-
-	/* refcount released by caller */
-out:
-	kfree(name);
-
-	return profile;
-
-fail:
-	aa_free_profile(profile);
-	return NULL;
-}
-
 /* TODO: profile accounting - setup in remove */
 
 /**
@@ -559,6 +480,93 @@
 }
 
 /**
+ * aa_new_null_profile - create or find a null-X learning profile
+ * @parent: profile that caused this profile to be created (NOT NULL)
+ * @hat: true if the null- learning profile is a hat
+ * @base: name to base the null profile off of
+ * @gfp: type of allocation
+ *
+ * Find/Create a null- complain mode profile used in learning mode.  The
+ * name of the profile is unique and follows the format of parent//null-XXX.
+ * where XXX is based on the @name or if that fails or is not supplied
+ * a unique number
+ *
+ * null profiles are added to the profile list but the list does not
+ * hold a count on them so that they are automatically released when
+ * not in use.
+ *
+ * Returns: new refcounted profile else NULL on failure
+ */
+struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat,
+				       const char *base, gfp_t gfp)
+{
+	struct aa_profile *p, *profile;
+	const char *bname;
+	char *name;
+
+	AA_BUG(!parent);
+
+	if (base) {
+		name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base),
+			       gfp);
+		if (name) {
+			sprintf(name, "%s//null-%s", parent->base.hname, base);
+			goto name;
+		}
+		/* fall through to try shorter uniq */
+	}
+
+	name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp);
+	if (!name)
+		return NULL;
+	sprintf(name, "%s//null-%x", parent->base.hname,
+		atomic_inc_return(&parent->ns->uniq_null));
+
+name:
+	/* lookup to see if this is a dup creation */
+	bname = basename(name);
+	profile = aa_find_child(parent, bname);
+	if (profile)
+		goto out;
+
+	profile = aa_alloc_profile(name, NULL, gfp);
+	if (!profile)
+		goto fail;
+
+	profile->mode = APPARMOR_COMPLAIN;
+	profile->label.flags |= FLAG_NULL;
+	if (hat)
+		profile->label.flags |= FLAG_HAT;
+	profile->path_flags = parent->path_flags;
+
+	/* released on free_profile */
+	rcu_assign_pointer(profile->parent, aa_get_profile(parent));
+	profile->ns = aa_get_ns(parent->ns);
+	profile->file.dfa = aa_get_dfa(nulldfa);
+	profile->policy.dfa = aa_get_dfa(nulldfa);
+
+	mutex_lock(&profile->ns->lock);
+	p = __find_child(&parent->base.profiles, bname);
+	if (p) {
+		aa_free_profile(profile);
+		profile = aa_get_profile(p);
+	} else {
+		__add_profile(&parent->base.profiles, profile);
+	}
+	mutex_unlock(&profile->ns->lock);
+
+	/* refcount released by caller */
+out:
+	kfree(name);
+
+	return profile;
+
+fail:
+	aa_free_profile(profile);
+	return NULL;
+}
+
+/**
  * replacement_allowed - test to see if replacement is allowed
  * @profile: profile to test if it can be replaced  (MAYBE NULL)
  * @noreplace: true if replacement shouldn't be allowed but addition is okay
diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c
index 351d3ba..62a3589 100644
--- a/security/apparmor/policy_ns.c
+++ b/security/apparmor/policy_ns.c
@@ -112,6 +112,8 @@
 	ns->unconfined->label.flags |= FLAG_IX_ON_NAME_ERROR |
 		FLAG_IMMUTIBLE | FLAG_NS_COUNT | FLAG_UNCONFINED;
 	ns->unconfined->mode = APPARMOR_UNCONFINED;
+	ns->unconfined->file.dfa = aa_get_dfa(nulldfa);
+	ns->unconfined->policy.dfa = aa_get_dfa(nulldfa);
 
 	/* ns and ns->unconfined share ns->unconfined refcount */
 	ns->unconfined->ns = ns;
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index c600f4d..4ede87c 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -85,9 +85,9 @@
 		audit_log_format(ab, " ns=");
 		audit_log_untrustedstring(ab, aad(sa)->iface.ns);
 	}
-	if (aad(sa)->iface.name) {
+	if (aad(sa)->name) {
 		audit_log_format(ab, " name=");
-		audit_log_untrustedstring(ab, aad(sa)->iface.name);
+		audit_log_untrustedstring(ab, aad(sa)->name);
 	}
 	if (aad(sa)->iface.pos)
 		audit_log_format(ab, " offset=%ld", aad(sa)->iface.pos);
@@ -114,9 +114,9 @@
 		aad(&sa)->iface.pos = e->pos - e->start;
 	aad(&sa)->iface.ns = ns_name;
 	if (new)
-		aad(&sa)->iface.name = new->base.hname;
+		aad(&sa)->name = new->base.hname;
 	else
-		aad(&sa)->iface.name = name;
+		aad(&sa)->name = name;
 	aad(&sa)->info = info;
 	aad(&sa)->error = error;
 
@@ -448,7 +448,7 @@
  */
 static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile)
 {
-	void *pos = e->pos;
+	void *saved_pos = e->pos;
 
 	/* exec table is optional */
 	if (unpack_nameX(e, AA_STRUCT, "xtable")) {
@@ -511,7 +511,7 @@
 
 fail:
 	aa_free_domain_entries(&profile->file.trans);
-	e->pos = pos;
+	e->pos = saved_pos;
 	return 0;
 }
 
@@ -583,6 +583,7 @@
 {
 	struct aa_profile *profile = NULL;
 	const char *tmpname, *tmpns = NULL, *name = NULL;
+	const char *info = "failed to unpack profile";
 	size_t ns_len;
 	struct rhashtable_params params = { 0 };
 	char *key = NULL;
@@ -604,8 +605,10 @@
 	tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len);
 	if (tmpns) {
 		*ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL);
-		if (!*ns_name)
+		if (!*ns_name) {
+			info = "out of memory";
 			goto fail;
+		}
 		name = tmpname;
 	}
 
@@ -624,12 +627,15 @@
 	if (IS_ERR(profile->xmatch)) {
 		error = PTR_ERR(profile->xmatch);
 		profile->xmatch = NULL;
+		info = "bad xmatch";
 		goto fail;
 	}
 	/* xmatch_len is not optional if xmatch is set */
 	if (profile->xmatch) {
-		if (!unpack_u32(e, &tmp, NULL))
+		if (!unpack_u32(e, &tmp, NULL)) {
+			info = "missing xmatch len";
 			goto fail;
+		}
 		profile->xmatch_len = tmp;
 	}
 
@@ -637,8 +643,11 @@
 	(void) unpack_str(e, &profile->disconnected, "disconnected");
 
 	/* per profile debug flags (complain, audit) */
-	if (!unpack_nameX(e, AA_STRUCT, "flags"))
+	if (!unpack_nameX(e, AA_STRUCT, "flags")) {
+		info = "profile missing flags";
 		goto fail;
+	}
+	info = "failed to unpack profile flags";
 	if (!unpack_u32(e, &tmp, NULL))
 		goto fail;
 	if (tmp & PACKED_FLAG_HAT)
@@ -667,6 +676,7 @@
 		/* set a default value if path_flags field is not present */
 		profile->path_flags = PATH_MEDIATE_DELETED;
 
+	info = "failed to unpack profile capabilities";
 	if (!unpack_u32(e, &(profile->caps.allow.cap[0]), NULL))
 		goto fail;
 	if (!unpack_u32(e, &(profile->caps.audit.cap[0]), NULL))
@@ -676,6 +686,7 @@
 	if (!unpack_u32(e, &tmpcap.cap[0], NULL))
 		goto fail;
 
+	info = "failed to unpack upper profile capabilities";
 	if (unpack_nameX(e, AA_STRUCT, "caps64")) {
 		/* optional upper half of 64 bit caps */
 		if (!unpack_u32(e, &(profile->caps.allow.cap[1]), NULL))
@@ -690,6 +701,7 @@
 			goto fail;
 	}
 
+	info = "failed to unpack extended profile capabilities";
 	if (unpack_nameX(e, AA_STRUCT, "capsx")) {
 		/* optional extended caps mediation mask */
 		if (!unpack_u32(e, &(profile->caps.extended.cap[0]), NULL))
@@ -700,11 +712,14 @@
 			goto fail;
 	}
 
-	if (!unpack_rlimits(e, profile))
+	if (!unpack_rlimits(e, profile)) {
+		info = "failed to unpack profile rlimits";
 		goto fail;
+	}
 
 	if (unpack_nameX(e, AA_STRUCT, "policydb")) {
 		/* generic policy dfa - optional and may be NULL */
+		info = "failed to unpack policydb";
 		profile->policy.dfa = unpack_dfa(e);
 		if (IS_ERR(profile->policy.dfa)) {
 			error = PTR_ERR(profile->policy.dfa);
@@ -734,6 +749,7 @@
 	if (IS_ERR(profile->file.dfa)) {
 		error = PTR_ERR(profile->file.dfa);
 		profile->file.dfa = NULL;
+		info = "failed to unpack profile file rules";
 		goto fail;
 	} else if (profile->file.dfa) {
 		if (!unpack_u32(e, &profile->file.start, "dfa_start"))
@@ -746,10 +762,13 @@
 	} else
 		profile->file.dfa = aa_get_dfa(nulldfa);
 
-	if (!unpack_trans_table(e, profile))
+	if (!unpack_trans_table(e, profile)) {
+		info = "failed to unpack profile transition table";
 		goto fail;
+	}
 
 	if (unpack_nameX(e, AA_STRUCT, "data")) {
+		info = "out of memory";
 		profile->data = kzalloc(sizeof(*profile->data), GFP_KERNEL);
 		if (!profile->data)
 			goto fail;
@@ -761,8 +780,10 @@
 		params.hashfn = strhash;
 		params.obj_cmpfn = datacmp;
 
-		if (rhashtable_init(profile->data, &params))
+		if (rhashtable_init(profile->data, &params)) {
+			info = "failed to init key, value hash table";
 			goto fail;
+		}
 
 		while (unpack_strdup(e, &key, NULL)) {
 			data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -784,12 +805,16 @@
 					       profile->data->p);
 		}
 
-		if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+		if (!unpack_nameX(e, AA_STRUCTEND, NULL)) {
+			info = "failed to unpack end of key, value data table";
 			goto fail;
+		}
 	}
 
-	if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+	if (!unpack_nameX(e, AA_STRUCTEND, NULL)) {
+		info = "failed to unpack end of profile";
 		goto fail;
+	}
 
 	return profile;
 
@@ -798,8 +823,7 @@
 		name = NULL;
 	else if (!name)
 		name = "unknown";
-	audit_iface(profile, NULL, name, "failed to unpack profile", e,
-		    error);
+	audit_iface(profile, NULL, name, info, e, error);
 	aa_free_profile(profile);
 
 	return ERR_PTR(error);
@@ -832,7 +856,7 @@
 	 * if not specified use previous version
 	 * Mask off everything that is not kernel abi version
 	 */
-	if (VERSION_LT(e->version, v5) && VERSION_GT(e->version, v7)) {
+	if (VERSION_LT(e->version, v5) || VERSION_GT(e->version, v7)) {
 		audit_iface(NULL, NULL, NULL, "unsupported interface version",
 			    e, error);
 		return error;
diff --git a/security/commoncap.c b/security/commoncap.c
index 6bf72b1..fc46f5b 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -294,10 +294,10 @@
  *
  * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV
  * affects the security markings on that inode, and if it is, should
- * inode_killpriv() be invoked or the change rejected?
+ * inode_killpriv() be invoked or the change rejected.
  *
- * Returns 0 if granted; +ve if granted, but inode_killpriv() is required; and
- * -ve to deny the change.
+ * Returns 1 if security.capability has a value, meaning inode_killpriv()
+ * is required, 0 otherwise, meaning inode_killpriv() is not required.
  */
 int cap_inode_need_killpriv(struct dentry *dentry)
 {
@@ -585,13 +585,14 @@
 	struct vfs_ns_cap_data data, *nscaps = &data;
 	struct vfs_cap_data *caps = (struct vfs_cap_data *) &data;
 	kuid_t rootkuid;
-	struct user_namespace *fs_ns = inode->i_sb->s_user_ns;
+	struct user_namespace *fs_ns;
 
 	memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
 
 	if (!inode)
 		return -ENODATA;
 
+	fs_ns = inode->i_sb->s_user_ns;
 	size = __vfs_getxattr((struct dentry *)dentry, inode,
 			      XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ);
 	if (size == -ENODATA || size == -EOPNOTSUPP)
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index a7a23b5..6462e66 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -45,10 +45,9 @@
 	bool "Large payload keys"
 	depends on KEYS
 	depends on TMPFS
-	depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y)
+	select CRYPTO
 	select CRYPTO_AES
-	select CRYPTO_ECB
-	select CRYPTO_RNG
+	select CRYPTO_GCM
 	help
 	  This option provides support for holding large keys within the kernel
 	  (for example Kerberos ticket caches).  The data may be stored out to
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 6acb00f..929e149 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -1,5 +1,6 @@
 /* Large capacity key type
  *
+ * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
@@ -16,10 +17,10 @@
 #include <linux/shmem_fs.h>
 #include <linux/err.h>
 #include <linux/scatterlist.h>
+#include <linux/random.h>
 #include <keys/user-type.h>
 #include <keys/big_key-type.h>
-#include <crypto/rng.h>
-#include <crypto/skcipher.h>
+#include <crypto/aead.h>
 
 /*
  * Layout of key payload words.
@@ -49,7 +50,12 @@
 /*
  * Key size for big_key data encryption
  */
-#define ENC_KEY_SIZE	16
+#define ENC_KEY_SIZE 32
+
+/*
+ * Authentication tag length
+ */
+#define ENC_AUTHTAG_SIZE 16
 
 /*
  * big_key defined keys take an arbitrary string as the description and an
@@ -64,57 +70,62 @@
 	.destroy		= big_key_destroy,
 	.describe		= big_key_describe,
 	.read			= big_key_read,
+	/* no ->update(); don't add it without changing big_key_crypt() nonce */
 };
 
 /*
- * Crypto names for big_key data encryption
+ * Crypto names for big_key data authenticated encryption
  */
-static const char big_key_rng_name[] = "stdrng";
-static const char big_key_alg_name[] = "ecb(aes)";
+static const char big_key_alg_name[] = "gcm(aes)";
 
 /*
- * Crypto algorithms for big_key data encryption
+ * Crypto algorithms for big_key data authenticated encryption
  */
-static struct crypto_rng *big_key_rng;
-static struct crypto_skcipher *big_key_skcipher;
+static struct crypto_aead *big_key_aead;
 
 /*
- * Generate random key to encrypt big_key data
+ * Since changing the key affects the entire object, we need a mutex.
  */
-static inline int big_key_gen_enckey(u8 *key)
-{
-	return crypto_rng_get_bytes(big_key_rng, key, ENC_KEY_SIZE);
-}
+static DEFINE_MUTEX(big_key_aead_lock);
 
 /*
  * Encrypt/decrypt big_key data
  */
 static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key)
 {
-	int ret = -EINVAL;
+	int ret;
 	struct scatterlist sgio;
-	SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher);
+	struct aead_request *aead_req;
+	/* We always use a zero nonce. The reason we can get away with this is
+	 * because we're using a different randomly generated key for every
+	 * different encryption. Notably, too, key_type_big_key doesn't define
+	 * an .update function, so there's no chance we'll wind up reusing the
+	 * key to encrypt updated data. Simply put: one key, one encryption.
+	 */
+	u8 zero_nonce[crypto_aead_ivsize(big_key_aead)];
 
-	if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) {
+	aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL);
+	if (!aead_req)
+		return -ENOMEM;
+
+	memset(zero_nonce, 0, sizeof(zero_nonce));
+	sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0));
+	aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce);
+	aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+	aead_request_set_ad(aead_req, 0);
+
+	mutex_lock(&big_key_aead_lock);
+	if (crypto_aead_setkey(big_key_aead, key, ENC_KEY_SIZE)) {
 		ret = -EAGAIN;
 		goto error;
 	}
-
-	skcipher_request_set_tfm(req, big_key_skcipher);
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
-				      NULL, NULL);
-
-	sg_init_one(&sgio, data, datalen);
-	skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL);
-
 	if (op == BIG_KEY_ENC)
-		ret = crypto_skcipher_encrypt(req);
+		ret = crypto_aead_encrypt(aead_req);
 	else
-		ret = crypto_skcipher_decrypt(req);
-
-	skcipher_request_zero(req);
-
+		ret = crypto_aead_decrypt(aead_req);
 error:
+	mutex_unlock(&big_key_aead_lock);
+	aead_request_free(aead_req);
 	return ret;
 }
 
@@ -146,16 +157,13 @@
 		 *
 		 * File content is stored encrypted with randomly generated key.
 		 */
-		size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
+		size_t enclen = datalen + ENC_AUTHTAG_SIZE;
 		loff_t pos = 0;
 
-		/* prepare aligned data to encrypt */
 		data = kmalloc(enclen, GFP_KERNEL);
 		if (!data)
 			return -ENOMEM;
-
 		memcpy(data, prep->data, datalen);
-		memset(data + datalen, 0x00, enclen - datalen);
 
 		/* generate random key */
 		enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL);
@@ -163,13 +171,12 @@
 			ret = -ENOMEM;
 			goto error;
 		}
-
-		ret = big_key_gen_enckey(enckey);
-		if (ret)
+		ret = get_random_bytes_wait(enckey, ENC_KEY_SIZE);
+		if (unlikely(ret))
 			goto err_enckey;
 
 		/* encrypt aligned data */
-		ret = big_key_crypt(BIG_KEY_ENC, data, enclen, enckey);
+		ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey);
 		if (ret)
 			goto err_enckey;
 
@@ -195,7 +202,7 @@
 		*path = file->f_path;
 		path_get(path);
 		fput(file);
-		kfree(data);
+		kzfree(data);
 	} else {
 		/* Just store the data in a buffer */
 		void *data = kmalloc(datalen, GFP_KERNEL);
@@ -211,9 +218,9 @@
 err_fput:
 	fput(file);
 err_enckey:
-	kfree(enckey);
+	kzfree(enckey);
 error:
-	kfree(data);
+	kzfree(data);
 	return ret;
 }
 
@@ -227,7 +234,7 @@
 
 		path_put(path);
 	}
-	kfree(prep->payload.data[big_key_data]);
+	kzfree(prep->payload.data[big_key_data]);
 }
 
 /*
@@ -240,7 +247,7 @@
 
 	/* clear the quota */
 	key_payload_reserve(key, 0);
-	if (key_is_instantiated(key) &&
+	if (key_is_positive(key) &&
 	    (size_t)key->payload.data[big_key_len] > BIG_KEY_FILE_THRESHOLD)
 		vfs_truncate(path, 0);
 }
@@ -259,7 +266,7 @@
 		path->mnt = NULL;
 		path->dentry = NULL;
 	}
-	kfree(key->payload.data[big_key_data]);
+	kzfree(key->payload.data[big_key_data]);
 	key->payload.data[big_key_data] = NULL;
 }
 
@@ -272,7 +279,7 @@
 
 	seq_puts(m, key->description);
 
-	if (key_is_instantiated(key))
+	if (key_is_positive(key))
 		seq_printf(m, ": %zu [%s]",
 			   datalen,
 			   datalen > BIG_KEY_FILE_THRESHOLD ? "file" : "buff");
@@ -295,7 +302,7 @@
 		struct file *file;
 		u8 *data;
 		u8 *enckey = (u8 *)key->payload.data[big_key_data];
-		size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
+		size_t enclen = datalen + ENC_AUTHTAG_SIZE;
 		loff_t pos = 0;
 
 		data = kmalloc(enclen, GFP_KERNEL);
@@ -328,7 +335,7 @@
 err_fput:
 		fput(file);
 error:
-		kfree(data);
+		kzfree(data);
 	} else {
 		ret = datalen;
 		if (copy_to_user(buffer, key->payload.data[big_key_data],
@@ -344,47 +351,31 @@
  */
 static int __init big_key_init(void)
 {
-	struct crypto_skcipher *cipher;
-	struct crypto_rng *rng;
 	int ret;
 
-	rng = crypto_alloc_rng(big_key_rng_name, 0, 0);
-	if (IS_ERR(rng)) {
-		pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng));
-		return PTR_ERR(rng);
-	}
-
-	big_key_rng = rng;
-
-	/* seed RNG */
-	ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng));
-	if (ret) {
-		pr_err("Can't reset rng: %d\n", ret);
-		goto error_rng;
-	}
-
 	/* init block cipher */
-	cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(cipher)) {
-		ret = PTR_ERR(cipher);
+	big_key_aead = crypto_alloc_aead(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(big_key_aead)) {
+		ret = PTR_ERR(big_key_aead);
 		pr_err("Can't alloc crypto: %d\n", ret);
-		goto error_rng;
+		return ret;
 	}
-
-	big_key_skcipher = cipher;
+	ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE);
+	if (ret < 0) {
+		pr_err("Can't set crypto auth tag len: %d\n", ret);
+		goto free_aead;
+	}
 
 	ret = register_key_type(&key_type_big_key);
 	if (ret < 0) {
 		pr_err("Can't register type: %d\n", ret);
-		goto error_cipher;
+		goto free_aead;
 	}
 
 	return 0;
 
-error_cipher:
-	crypto_free_skcipher(big_key_skcipher);
-error_rng:
-	crypto_free_rng(big_key_rng);
+free_aead:
+	crypto_free_aead(big_key_aead);
 	return ret;
 }
 
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 69855ba..d92cbf9 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -309,6 +309,13 @@
 
 	down_read(&ukey->sem);
 	upayload = user_key_payload_locked(ukey);
+	if (!upayload) {
+		/* key was revoked before we acquired its semaphore */
+		up_read(&ukey->sem);
+		key_put(ukey);
+		ukey = ERR_PTR(-EKEYREVOKED);
+		goto error;
+	}
 	*master_key = upayload->data;
 	*master_keylen = upayload->datalen;
 error:
@@ -847,7 +854,7 @@
 	size_t datalen = prep->datalen;
 	int ret = 0;
 
-	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+	if (key_is_negative(key))
 		return -ENOKEY;
 	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		return -EINVAL;
diff --git a/security/keys/gc.c b/security/keys/gc.c
index 87cb260..f01d48c 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -129,15 +129,15 @@
 	while (!list_empty(keys)) {
 		struct key *key =
 			list_entry(keys->next, struct key, graveyard_link);
+		short state = key->state;
+
 		list_del(&key->graveyard_link);
 
 		kdebug("- %u", key->serial);
 		key_check(key);
 
 		/* Throw away the key data if the key is instantiated */
-		if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags) &&
-		    !test_bit(KEY_FLAG_NEGATIVE, &key->flags) &&
-		    key->type->destroy)
+		if (state == KEY_IS_POSITIVE && key->type->destroy)
 			key->type->destroy(key);
 
 		security_key_free(key);
@@ -151,7 +151,7 @@
 		}
 
 		atomic_dec(&key->user->nkeys);
-		if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
+		if (state != KEY_IS_UNINSTANTIATED)
 			atomic_dec(&key->user->nikeys);
 
 		key_user_put(key->user);
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 1c02c65..503adba 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -141,7 +141,7 @@
 extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx);
 extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx);
 
-extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
+extern struct key *find_keyring_by_name(const char *name, bool uid_keyring);
 
 extern int install_user_keyrings(void);
 extern int install_thread_keyring_to_cred(struct cred *);
diff --git a/security/keys/key.c b/security/keys/key.c
index 83da68d..83bf4b4 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -54,10 +54,10 @@
 struct key_user *key_user_lookup(kuid_t uid)
 {
 	struct key_user *candidate = NULL, *user;
-	struct rb_node *parent = NULL;
-	struct rb_node **p;
+	struct rb_node *parent, **p;
 
 try_again:
+	parent = NULL;
 	p = &key_user_tree.rb_node;
 	spin_lock(&key_user_lock);
 
@@ -302,6 +302,8 @@
 		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
 	if (flags & KEY_ALLOC_BUILT_IN)
 		key->flags |= 1 << KEY_FLAG_BUILTIN;
+	if (flags & KEY_ALLOC_UID_KEYRING)
+		key->flags |= 1 << KEY_FLAG_UID_KEYRING;
 
 #ifdef KEY_DEBUGGING
 	key->magic = KEY_DEBUG_MAGIC;
@@ -400,6 +402,18 @@
 EXPORT_SYMBOL(key_payload_reserve);
 
 /*
+ * Change the key state to being instantiated.
+ */
+static void mark_key_instantiated(struct key *key, int reject_error)
+{
+	/* Commit the payload before setting the state; barrier versus
+	 * key_read_state().
+	 */
+	smp_store_release(&key->state,
+			  (reject_error < 0) ? reject_error : KEY_IS_POSITIVE);
+}
+
+/*
  * Instantiate a key and link it into the target keyring atomically.  Must be
  * called with the target keyring's semaphore writelocked.  The target key's
  * semaphore need not be locked as instantiation is serialised by
@@ -422,14 +436,14 @@
 	mutex_lock(&key_construction_mutex);
 
 	/* can't instantiate twice */
-	if (!test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) {
+	if (key->state == KEY_IS_UNINSTANTIATED) {
 		/* instantiate the key */
 		ret = key->type->instantiate(key, prep);
 
 		if (ret == 0) {
 			/* mark the key as being instantiated */
 			atomic_inc(&key->user->nikeys);
-			set_bit(KEY_FLAG_INSTANTIATED, &key->flags);
+			mark_key_instantiated(key, 0);
 
 			if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags))
 				awaken = 1;
@@ -575,13 +589,10 @@
 	mutex_lock(&key_construction_mutex);
 
 	/* can't instantiate twice */
-	if (!test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) {
+	if (key->state == KEY_IS_UNINSTANTIATED) {
 		/* mark the key as being negatively instantiated */
 		atomic_inc(&key->user->nikeys);
-		key->reject_error = -error;
-		smp_wmb();
-		set_bit(KEY_FLAG_NEGATIVE, &key->flags);
-		set_bit(KEY_FLAG_INSTANTIATED, &key->flags);
+		mark_key_instantiated(key, -error);
 		now = current_kernel_time();
 		key->expiry = now.tv_sec + timeout;
 		key_schedule_gc(key->expiry + key_gc_delay);
@@ -750,8 +761,8 @@
 
 	ret = key->type->update(key, prep);
 	if (ret == 0)
-		/* updating a negative key instantiates it */
-		clear_bit(KEY_FLAG_NEGATIVE, &key->flags);
+		/* Updating a negative key positively instantiates it */
+		mark_key_instantiated(key, 0);
 
 	up_write(&key->sem);
 
@@ -934,6 +945,16 @@
 	 */
 	__key_link_end(keyring, &index_key, edit);
 
+	key = key_ref_to_ptr(key_ref);
+	if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) {
+		ret = wait_for_key_construction(key, true);
+		if (ret < 0) {
+			key_ref_put(key_ref);
+			key_ref = ERR_PTR(ret);
+			goto error_free_prep;
+		}
+	}
+
 	key_ref = __key_update(key_ref, &prep);
 	goto error_free_prep;
 }
@@ -984,8 +1005,8 @@
 
 	ret = key->type->update(key, &prep);
 	if (ret == 0)
-		/* updating a negative key instantiates it */
-		clear_bit(KEY_FLAG_NEGATIVE, &key->flags);
+		/* Updating a negative key positively instantiates it */
+		mark_key_instantiated(key, 0);
 
 	up_write(&key->sem);
 
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index ab0b337..76d22f72 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -766,12 +766,16 @@
 
 	key = key_ref_to_ptr(key_ref);
 
+	ret = key_read_state(key);
+	if (ret < 0)
+		goto error2; /* Negatively instantiated */
+
 	/* see if we can read it directly */
 	ret = key_permission(key_ref, KEY_NEED_READ);
 	if (ret == 0)
 		goto can_read_key;
 	if (ret != -EACCES)
-		goto error;
+		goto error2;
 
 	/* we can't; see if it's searchable from this process's keyrings
 	 * - we automatically take account of the fact that it may be
@@ -896,7 +900,7 @@
 		atomic_dec(&key->user->nkeys);
 		atomic_inc(&newowner->nkeys);
 
-		if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) {
+		if (key->state != KEY_IS_UNINSTANTIATED) {
 			atomic_dec(&key->user->nikeys);
 			atomic_inc(&newowner->nikeys);
 		}
@@ -1406,11 +1410,9 @@
 	}
 
 	ret = keyctl_change_reqkey_auth(authkey);
-	if (ret < 0)
-		goto error;
+	if (ret == 0)
+		ret = authkey->serial;
 	key_put(authkey);
-
-	ret = authkey->serial;
 error:
 	return ret;
 }
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index de81793..a7e51f7 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -414,7 +414,7 @@
 	else
 		seq_puts(m, "[anon]");
 
-	if (key_is_instantiated(keyring)) {
+	if (key_is_positive(keyring)) {
 		if (keyring->keys.nr_leaves_on_tree != 0)
 			seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree);
 		else
@@ -423,7 +423,7 @@
 }
 
 struct keyring_read_iterator_context {
-	size_t			qty;
+	size_t			buflen;
 	size_t			count;
 	key_serial_t __user	*buffer;
 };
@@ -435,9 +435,9 @@
 	int ret;
 
 	kenter("{%s,%d},,{%zu/%zu}",
-	       key->type->name, key->serial, ctx->count, ctx->qty);
+	       key->type->name, key->serial, ctx->count, ctx->buflen);
 
-	if (ctx->count >= ctx->qty)
+	if (ctx->count >= ctx->buflen)
 		return 1;
 
 	ret = put_user(key->serial, ctx->buffer);
@@ -472,16 +472,12 @@
 		return 0;
 
 	/* Calculate how much data we could return */
-	ctx.qty = nr_keys * sizeof(key_serial_t);
-
 	if (!buffer || !buflen)
-		return ctx.qty;
-
-	if (buflen > ctx.qty)
-		ctx.qty = buflen;
+		return nr_keys * sizeof(key_serial_t);
 
 	/* Copy the IDs of the subscribed keys into the buffer */
 	ctx.buffer = (key_serial_t __user *)buffer;
+	ctx.buflen = buflen;
 	ctx.count = 0;
 	ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
 	if (ret < 0) {
@@ -557,7 +553,8 @@
 {
 	struct keyring_search_context *ctx = iterator_data;
 	const struct key *key = keyring_ptr_to_key(object);
-	unsigned long kflags = key->flags;
+	unsigned long kflags = READ_ONCE(key->flags);
+	short state = READ_ONCE(key->state);
 
 	kenter("{%d}", key->serial);
 
@@ -569,6 +566,8 @@
 
 	/* skip invalidated, revoked and expired keys */
 	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+		time_t expiry = READ_ONCE(key->expiry);
+
 		if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
 			      (1 << KEY_FLAG_REVOKED))) {
 			ctx->result = ERR_PTR(-EKEYREVOKED);
@@ -576,7 +575,7 @@
 			goto skipped;
 		}
 
-		if (key->expiry && ctx->now.tv_sec >= key->expiry) {
+		if (expiry && ctx->now.tv_sec >= expiry) {
 			if (!(ctx->flags & KEYRING_SEARCH_SKIP_EXPIRED))
 				ctx->result = ERR_PTR(-EKEYEXPIRED);
 			kleave(" = %d [expire]", ctx->skipped_ret);
@@ -601,9 +600,8 @@
 
 	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
 		/* we set a different error code if we pass a negative key */
-		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
-			smp_rmb();
-			ctx->result = ERR_PTR(key->reject_error);
+		if (state < 0) {
+			ctx->result = ERR_PTR(state);
 			kleave(" = %d [neg]", ctx->skipped_ret);
 			goto skipped;
 		}
@@ -1101,15 +1099,15 @@
 /*
  * Find a keyring with the specified name.
  *
- * All named keyrings in the current user namespace are searched, provided they
- * grant Search permission directly to the caller (unless this check is
- * skipped).  Keyrings whose usage points have reached zero or who have been
- * revoked are skipped.
+ * Only keyrings that have nonzero refcount, are not revoked, and are owned by a
+ * user in the current user namespace are considered.  If @uid_keyring is %true,
+ * the keyring additionally must have been allocated as a user or user session
+ * keyring; otherwise, it must grant Search permission directly to the caller.
  *
  * Returns a pointer to the keyring with the keyring's refcount having being
  * incremented on success.  -ENOKEY is returned if a key could not be found.
  */
-struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
+struct key *find_keyring_by_name(const char *name, bool uid_keyring)
 {
 	struct key *keyring;
 	int bucket;
@@ -1137,10 +1135,15 @@
 			if (strcmp(keyring->description, name) != 0)
 				continue;
 
-			if (!skip_perm_check &&
-			    key_permission(make_key_ref(keyring, 0),
-					   KEY_NEED_SEARCH) < 0)
-				continue;
+			if (uid_keyring) {
+				if (!test_bit(KEY_FLAG_UID_KEYRING,
+					      &keyring->flags))
+					continue;
+			} else {
+				if (key_permission(make_key_ref(keyring, 0),
+						   KEY_NEED_SEARCH) < 0)
+					continue;
+			}
 
 			/* we've got a match but we might end up racing with
 			 * key_cleanup() if the keyring is currently 'dead'
diff --git a/security/keys/permission.c b/security/keys/permission.c
index 732cc0b..a72b4dd 100644
--- a/security/keys/permission.c
+++ b/security/keys/permission.c
@@ -88,7 +88,8 @@
  */
 int key_validate(const struct key *key)
 {
-	unsigned long flags = key->flags;
+	unsigned long flags = READ_ONCE(key->flags);
+	time_t expiry = READ_ONCE(key->expiry);
 
 	if (flags & (1 << KEY_FLAG_INVALIDATED))
 		return -ENOKEY;
@@ -99,9 +100,9 @@
 		return -EKEYREVOKED;
 
 	/* check it hasn't expired */
-	if (key->expiry) {
+	if (expiry) {
 		struct timespec now = current_kernel_time();
-		if (now.tv_sec >= key->expiry)
+		if (now.tv_sec >= expiry)
 			return -EKEYEXPIRED;
 	}
 
diff --git a/security/keys/proc.c b/security/keys/proc.c
index bf08d02..6d1fcbb 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -179,15 +179,18 @@
 	struct rb_node *_p = v;
 	struct key *key = rb_entry(_p, struct key, serial_node);
 	struct timespec now;
+	time_t expiry;
 	unsigned long timo;
+	unsigned long flags;
 	key_ref_t key_ref, skey_ref;
 	char xbuf[16];
+	short state;
 	int rc;
 
 	struct keyring_search_context ctx = {
 		.index_key.type		= key->type,
 		.index_key.description	= key->description,
-		.cred			= current_cred(),
+		.cred			= m->file->f_cred,
 		.match_data.cmp		= lookup_user_key_possessed,
 		.match_data.raw_data	= key,
 		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
@@ -207,11 +210,7 @@
 		}
 	}
 
-	/* check whether the current task is allowed to view the key (assuming
-	 * non-possession)
-	 * - the caller holds a spinlock, and thus the RCU read lock, making our
-	 *   access to __current_cred() safe
-	 */
+	/* check whether the current task is allowed to view the key */
 	rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW);
 	if (rc < 0)
 		return 0;
@@ -221,12 +220,13 @@
 	rcu_read_lock();
 
 	/* come up with a suitable timeout value */
-	if (key->expiry == 0) {
+	expiry = READ_ONCE(key->expiry);
+	if (expiry == 0) {
 		memcpy(xbuf, "perm", 5);
-	} else if (now.tv_sec >= key->expiry) {
+	} else if (now.tv_sec >= expiry) {
 		memcpy(xbuf, "expd", 5);
 	} else {
-		timo = key->expiry - now.tv_sec;
+		timo = expiry - now.tv_sec;
 
 		if (timo < 60)
 			sprintf(xbuf, "%lus", timo);
@@ -240,18 +240,21 @@
 			sprintf(xbuf, "%luw", timo / (60*60*24*7));
 	}
 
-#define showflag(KEY, LETTER, FLAG) \
-	(test_bit(FLAG,	&(KEY)->flags) ? LETTER : '-')
+	state = key_read_state(key);
 
+#define showflag(FLAGS, LETTER, FLAG) \
+	((FLAGS & (1 << FLAG)) ? LETTER : '-')
+
+	flags = READ_ONCE(key->flags);
 	seq_printf(m, "%08x %c%c%c%c%c%c%c %5d %4s %08x %5d %5d %-9.9s ",
 		   key->serial,
-		   showflag(key, 'I', KEY_FLAG_INSTANTIATED),
-		   showflag(key, 'R', KEY_FLAG_REVOKED),
-		   showflag(key, 'D', KEY_FLAG_DEAD),
-		   showflag(key, 'Q', KEY_FLAG_IN_QUOTA),
-		   showflag(key, 'U', KEY_FLAG_USER_CONSTRUCT),
-		   showflag(key, 'N', KEY_FLAG_NEGATIVE),
-		   showflag(key, 'i', KEY_FLAG_INVALIDATED),
+		   state != KEY_IS_UNINSTANTIATED ? 'I' : '-',
+		   showflag(flags, 'R', KEY_FLAG_REVOKED),
+		   showflag(flags, 'D', KEY_FLAG_DEAD),
+		   showflag(flags, 'Q', KEY_FLAG_IN_QUOTA),
+		   showflag(flags, 'U', KEY_FLAG_USER_CONSTRUCT),
+		   state < 0 ? 'N' : '-',
+		   showflag(flags, 'i', KEY_FLAG_INVALIDATED),
 		   refcount_read(&key->usage),
 		   xbuf,
 		   key->perm,
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 86bced9..740affd 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -77,7 +77,8 @@
 		if (IS_ERR(uid_keyring)) {
 			uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID,
 						    cred, user_keyring_perm,
-						    KEY_ALLOC_IN_QUOTA,
+						    KEY_ALLOC_UID_KEYRING |
+							KEY_ALLOC_IN_QUOTA,
 						    NULL, NULL);
 			if (IS_ERR(uid_keyring)) {
 				ret = PTR_ERR(uid_keyring);
@@ -94,7 +95,8 @@
 			session_keyring =
 				keyring_alloc(buf, user->uid, INVALID_GID,
 					      cred, user_keyring_perm,
-					      KEY_ALLOC_IN_QUOTA,
+					      KEY_ALLOC_UID_KEYRING |
+						  KEY_ALLOC_IN_QUOTA,
 					      NULL, NULL);
 			if (IS_ERR(session_keyring)) {
 				ret = PTR_ERR(session_keyring);
@@ -728,7 +730,7 @@
 
 	ret = -EIO;
 	if (!(lflags & KEY_LOOKUP_PARTIAL) &&
-	    !test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
+	    key_read_state(key) == KEY_IS_UNINSTANTIATED)
 		goto invalid_key;
 
 	/* check the permissions */
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 63e63a4..e8036cd 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -595,10 +595,9 @@
 			  intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 	if (ret)
 		return -ERESTARTSYS;
-	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
-		smp_rmb();
-		return key->reject_error;
-	}
+	ret = key_read_state(key);
+	if (ret < 0)
+		return ret;
 	return key_validate(key);
 }
 EXPORT_SYMBOL(wait_for_key_construction);
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index afe9d22..424e1d9 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -73,7 +73,7 @@
 
 	seq_puts(m, "key:");
 	seq_puts(m, key->description);
-	if (key_is_instantiated(key))
+	if (key_is_positive(key))
 		seq_printf(m, " pid:%d ci:%zu", rka->pid, rka->callout_len);
 }
 
@@ -120,6 +120,18 @@
 	}
 }
 
+static void free_request_key_auth(struct request_key_auth *rka)
+{
+	if (!rka)
+		return;
+	key_put(rka->target_key);
+	key_put(rka->dest_keyring);
+	if (rka->cred)
+		put_cred(rka->cred);
+	kfree(rka->callout_info);
+	kfree(rka);
+}
+
 /*
  * Destroy an instantiation authorisation token key.
  */
@@ -129,15 +141,7 @@
 
 	kenter("{%d}", key->serial);
 
-	if (rka->cred) {
-		put_cred(rka->cred);
-		rka->cred = NULL;
-	}
-
-	key_put(rka->target_key);
-	key_put(rka->dest_keyring);
-	kfree(rka->callout_info);
-	kfree(rka);
+	free_request_key_auth(rka);
 }
 
 /*
@@ -151,22 +155,18 @@
 	const struct cred *cred = current->cred;
 	struct key *authkey = NULL;
 	char desc[20];
-	int ret;
+	int ret = -ENOMEM;
 
 	kenter("%d,", target->serial);
 
 	/* allocate a auth record */
-	rka = kmalloc(sizeof(*rka), GFP_KERNEL);
-	if (!rka) {
-		kleave(" = -ENOMEM");
-		return ERR_PTR(-ENOMEM);
-	}
-	rka->callout_info = kmalloc(callout_len, GFP_KERNEL);
-	if (!rka->callout_info) {
-		kleave(" = -ENOMEM");
-		kfree(rka);
-		return ERR_PTR(-ENOMEM);
-	}
+	rka = kzalloc(sizeof(*rka), GFP_KERNEL);
+	if (!rka)
+		goto error;
+	rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL);
+	if (!rka->callout_info)
+		goto error_free_rka;
+	rka->callout_len = callout_len;
 
 	/* see if the calling process is already servicing the key request of
 	 * another process */
@@ -176,8 +176,12 @@
 
 		/* if the auth key has been revoked, then the key we're
 		 * servicing is already instantiated */
-		if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags))
-			goto auth_key_revoked;
+		if (test_bit(KEY_FLAG_REVOKED,
+			     &cred->request_key_auth->flags)) {
+			up_read(&cred->request_key_auth->sem);
+			ret = -EKEYREVOKED;
+			goto error_free_rka;
+		}
 
 		irka = cred->request_key_auth->payload.data[0];
 		rka->cred = get_cred(irka->cred);
@@ -193,8 +197,6 @@
 
 	rka->target_key = key_get(target);
 	rka->dest_keyring = key_get(dest_keyring);
-	memcpy(rka->callout_info, callout_info, callout_len);
-	rka->callout_len = callout_len;
 
 	/* allocate the auth key */
 	sprintf(desc, "%x", target->serial);
@@ -205,32 +207,22 @@
 			    KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL);
 	if (IS_ERR(authkey)) {
 		ret = PTR_ERR(authkey);
-		goto error_alloc;
+		goto error_free_rka;
 	}
 
 	/* construct the auth key */
 	ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL);
 	if (ret < 0)
-		goto error_inst;
+		goto error_put_authkey;
 
 	kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage));
 	return authkey;
 
-auth_key_revoked:
-	up_read(&cred->request_key_auth->sem);
-	kfree(rka->callout_info);
-	kfree(rka);
-	kleave("= -EKEYREVOKED");
-	return ERR_PTR(-EKEYREVOKED);
-
-error_inst:
-	key_revoke(authkey);
+error_put_authkey:
 	key_put(authkey);
-error_alloc:
-	key_put(rka->target_key);
-	key_put(rka->dest_keyring);
-	kfree(rka->callout_info);
-	kfree(rka);
+error_free_rka:
+	free_request_key_auth(rka);
+error:
 	kleave("= %d", ret);
 	return ERR_PTR(ret);
 }
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index ddfaebf..bd85315 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1066,7 +1066,7 @@
 	char *datablob;
 	int ret = 0;
 
-	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+	if (key_is_negative(key))
 		return -ENOKEY;
 	p = key->payload.data[0];
 	if (!p->migratable)
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 3d8c68e..9f558be 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -114,7 +114,7 @@
 
 	/* attach the new data, displacing the old */
 	key->expiry = prep->expiry;
-	if (!test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+	if (key_is_positive(key))
 		zap = dereference_key_locked(key);
 	rcu_assign_keypointer(key, prep->payload.data[0]);
 	prep->payload.data[0] = NULL;
@@ -162,7 +162,7 @@
 void user_describe(const struct key *key, struct seq_file *m)
 {
 	seq_puts(m, key->description);
-	if (key_is_instantiated(key))
+	if (key_is_positive(key))
 		seq_printf(m, ": %u", key->datalen);
 }
 
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 319add3..286171a 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1473,7 +1473,7 @@
  * @inode: the object
  * @name: attribute name
  * @buffer: where to put the result
- * @alloc: unused
+ * @alloc: duplicate memory
  *
  * Returns the size of the attribute or an error code
  */
@@ -1486,43 +1486,38 @@
 	struct super_block *sbp;
 	struct inode *ip = (struct inode *)inode;
 	struct smack_known *isp;
-	int ilen;
-	int rc = 0;
 
-	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) {
+	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0)
 		isp = smk_of_inode(inode);
-		ilen = strlen(isp->smk_known);
-		*buffer = isp->smk_known;
-		return ilen;
+	else {
+		/*
+		 * The rest of the Smack xattrs are only on sockets.
+		 */
+		sbp = ip->i_sb;
+		if (sbp->s_magic != SOCKFS_MAGIC)
+			return -EOPNOTSUPP;
+
+		sock = SOCKET_I(ip);
+		if (sock == NULL || sock->sk == NULL)
+			return -EOPNOTSUPP;
+
+		ssp = sock->sk->sk_security;
+
+		if (strcmp(name, XATTR_SMACK_IPIN) == 0)
+			isp = ssp->smk_in;
+		else if (strcmp(name, XATTR_SMACK_IPOUT) == 0)
+			isp = ssp->smk_out;
+		else
+			return -EOPNOTSUPP;
 	}
 
-	/*
-	 * The rest of the Smack xattrs are only on sockets.
-	 */
-	sbp = ip->i_sb;
-	if (sbp->s_magic != SOCKFS_MAGIC)
-		return -EOPNOTSUPP;
-
-	sock = SOCKET_I(ip);
-	if (sock == NULL || sock->sk == NULL)
-		return -EOPNOTSUPP;
-
-	ssp = sock->sk->sk_security;
-
-	if (strcmp(name, XATTR_SMACK_IPIN) == 0)
-		isp = ssp->smk_in;
-	else if (strcmp(name, XATTR_SMACK_IPOUT) == 0)
-		isp = ssp->smk_out;
-	else
-		return -EOPNOTSUPP;
-
-	ilen = strlen(isp->smk_known);
-	if (rc == 0) {
-		*buffer = isp->smk_known;
-		rc = ilen;
+	if (alloc) {
+		*buffer = kstrdup(isp->smk_known, GFP_KERNEL);
+		if (*buffer == NULL)
+			return -ENOMEM;
 	}
 
-	return rc;
+	return strlen(isp->smk_known);
 }
 
 
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index fec1dfd..4490a69 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -948,14 +948,13 @@
 static int snd_compress_dev_register(struct snd_device *device)
 {
 	int ret = -EINVAL;
-	char str[16];
 	struct snd_compr *compr;
 
 	if (snd_BUG_ON(!device || !device->device_data))
 		return -EBADFD;
 	compr = device->device_data;
 
-	pr_debug("reg %s for device %s, direction %d\n", str, compr->name,
+	pr_debug("reg device %s, direction %d\n", compr->name,
 			compr->direction);
 	/* register compressed device */
 	ret = snd_register_device(SNDRV_DEVICE_TYPE_COMPRESS,
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index 3a1cc7b..b719d0b 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -547,6 +547,7 @@
 	u32 pad2; /* alignment */
 	struct timespec tstamp;
 	s32 suspended_state;
+	s32 pad3;
 	struct timespec audio_tstamp;
 } __packed;
 
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index ea2d0ae..6c9cba2 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1259,6 +1259,7 @@
 	struct snd_seq_port_info *info = arg;
 	struct snd_seq_client_port *port;
 	struct snd_seq_port_callback *callback;
+	int port_idx;
 
 	/* it is not allowed to create the port for an another client */
 	if (info->addr.client != client->number)
@@ -1269,7 +1270,9 @@
 		return -ENOMEM;
 
 	if (client->type == USER_CLIENT && info->kernel) {
-		snd_seq_delete_port(client, port->addr.port);
+		port_idx = port->addr.port;
+		snd_seq_port_unlock(port);
+		snd_seq_delete_port(client, port_idx);
 		return -EINVAL;
 	}
 	if (client->type == KERNEL_CLIENT) {
@@ -1290,6 +1293,7 @@
 
 	snd_seq_set_port_info(port, info);
 	snd_seq_system_client_ev_port_start(port->addr.client, port->addr.port);
+	snd_seq_port_unlock(port);
 
 	return 0;
 }
diff --git a/sound/core/seq/seq_lock.c b/sound/core/seq/seq_lock.c
index 0ff7926..cda64b4 100644
--- a/sound/core/seq/seq_lock.c
+++ b/sound/core/seq/seq_lock.c
@@ -23,8 +23,6 @@
 #include <sound/core.h>
 #include "seq_lock.h"
 
-#if defined(CONFIG_SMP) || defined(CONFIG_SND_DEBUG)
-
 /* wait until all locks are released */
 void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line)
 {
@@ -41,5 +39,3 @@
 	}
 }
 EXPORT_SYMBOL(snd_use_lock_sync_helper);
-
-#endif
diff --git a/sound/core/seq/seq_lock.h b/sound/core/seq/seq_lock.h
index 54044bc..ac38031 100644
--- a/sound/core/seq/seq_lock.h
+++ b/sound/core/seq/seq_lock.h
@@ -3,8 +3,6 @@
 
 #include <linux/sched.h>
 
-#if defined(CONFIG_SMP) || defined(CONFIG_SND_DEBUG)
-
 typedef atomic_t snd_use_lock_t;
 
 /* initialize lock */
@@ -20,14 +18,4 @@
 void snd_use_lock_sync_helper(snd_use_lock_t *lock, const char *file, int line);
 #define snd_use_lock_sync(lockp) snd_use_lock_sync_helper(lockp, __BASE_FILE__, __LINE__)
 
-#else /* SMP || CONFIG_SND_DEBUG */
-
-typedef spinlock_t snd_use_lock_t;	/* dummy */
-#define snd_use_lock_init(lockp) /**/
-#define snd_use_lock_use(lockp) /**/
-#define snd_use_lock_free(lockp) /**/
-#define snd_use_lock_sync(lockp) /**/
-
-#endif /* SMP || CONFIG_SND_DEBUG */
-
 #endif /* __SND_SEQ_LOCK_H */
diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c
index 0a7020c..d21ece9 100644
--- a/sound/core/seq/seq_ports.c
+++ b/sound/core/seq/seq_ports.c
@@ -122,7 +122,9 @@
 }
 
 
-/* create a port, port number is returned (-1 on failure) */
+/* create a port, port number is returned (-1 on failure);
+ * the caller needs to unref the port via snd_seq_port_unlock() appropriately
+ */
 struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client,
 						int port)
 {
@@ -151,6 +153,7 @@
 	snd_use_lock_init(&new_port->use_lock);
 	port_subs_info_init(&new_port->c_src);
 	port_subs_info_init(&new_port->c_dest);
+	snd_use_lock_use(&new_port->use_lock);
 
 	num = port >= 0 ? port : 0;
 	mutex_lock(&client->ports_mutex);
@@ -165,9 +168,9 @@
 	list_add_tail(&new_port->list, &p->list);
 	client->num_ports++;
 	new_port->addr.port = num;	/* store the port number in the port */
+	sprintf(new_port->name, "port-%d", num);
 	write_unlock_irqrestore(&client->ports_lock, flags);
 	mutex_unlock(&client->ports_mutex);
-	sprintf(new_port->name, "port-%d", num);
 
 	return new_port;
 }
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 8d93a40..f48a4cd 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -77,13 +77,17 @@
  * decode input event and put to read buffer of each opened file
  */
 static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev,
-					 struct snd_seq_event *ev)
+					 struct snd_seq_event *ev,
+					 bool atomic)
 {
 	struct snd_virmidi *vmidi;
 	unsigned char msg[4];
 	int len;
 
-	read_lock(&rdev->filelist_lock);
+	if (atomic)
+		read_lock(&rdev->filelist_lock);
+	else
+		down_read(&rdev->filelist_sem);
 	list_for_each_entry(vmidi, &rdev->filelist, list) {
 		if (!vmidi->trigger)
 			continue;
@@ -97,7 +101,10 @@
 				snd_rawmidi_receive(vmidi->substream, msg, len);
 		}
 	}
-	read_unlock(&rdev->filelist_lock);
+	if (atomic)
+		read_unlock(&rdev->filelist_lock);
+	else
+		up_read(&rdev->filelist_sem);
 
 	return 0;
 }
@@ -115,7 +122,7 @@
 	struct snd_virmidi_dev *rdev;
 
 	rdev = rmidi->private_data;
-	return snd_virmidi_dev_receive_event(rdev, ev);
+	return snd_virmidi_dev_receive_event(rdev, ev, true);
 }
 #endif  /*  0  */
 
@@ -130,7 +137,7 @@
 	rdev = private_data;
 	if (!(rdev->flags & SNDRV_VIRMIDI_USE))
 		return 0; /* ignored */
-	return snd_virmidi_dev_receive_event(rdev, ev);
+	return snd_virmidi_dev_receive_event(rdev, ev, atomic);
 }
 
 /*
@@ -209,7 +216,6 @@
 	struct snd_virmidi_dev *rdev = substream->rmidi->private_data;
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 	struct snd_virmidi *vmidi;
-	unsigned long flags;
 
 	vmidi = kzalloc(sizeof(*vmidi), GFP_KERNEL);
 	if (vmidi == NULL)
@@ -223,9 +229,11 @@
 	vmidi->client = rdev->client;
 	vmidi->port = rdev->port;	
 	runtime->private_data = vmidi;
-	write_lock_irqsave(&rdev->filelist_lock, flags);
+	down_write(&rdev->filelist_sem);
+	write_lock_irq(&rdev->filelist_lock);
 	list_add_tail(&vmidi->list, &rdev->filelist);
-	write_unlock_irqrestore(&rdev->filelist_lock, flags);
+	write_unlock_irq(&rdev->filelist_lock);
+	up_write(&rdev->filelist_sem);
 	vmidi->rdev = rdev;
 	return 0;
 }
@@ -264,9 +272,11 @@
 	struct snd_virmidi_dev *rdev = substream->rmidi->private_data;
 	struct snd_virmidi *vmidi = substream->runtime->private_data;
 
+	down_write(&rdev->filelist_sem);
 	write_lock_irq(&rdev->filelist_lock);
 	list_del(&vmidi->list);
 	write_unlock_irq(&rdev->filelist_lock);
+	up_write(&rdev->filelist_sem);
 	snd_midi_event_free(vmidi->parser);
 	substream->runtime->private_data = NULL;
 	kfree(vmidi);
@@ -520,6 +530,7 @@
 	rdev->rmidi = rmidi;
 	rdev->device = device;
 	rdev->client = -1;
+	init_rwsem(&rdev->filelist_sem);
 	rwlock_init(&rdev->filelist_lock);
 	INIT_LIST_HEAD(&rdev->filelist);
 	rdev->seq_mode = SNDRV_VIRMIDI_SEQ_DISPATCH;
diff --git a/sound/core/vmaster.c b/sound/core/vmaster.c
index 6c58e6f..e43af18 100644
--- a/sound/core/vmaster.c
+++ b/sound/core/vmaster.c
@@ -484,3 +484,34 @@
 		master->hook(master->hook_private_data, master->val);
 }
 EXPORT_SYMBOL_GPL(snd_ctl_sync_vmaster);
+
+/**
+ * snd_ctl_apply_vmaster_slaves - Apply function to each vmaster slave
+ * @kctl: vmaster kctl element
+ * @func: function to apply
+ * @arg: optional function argument
+ *
+ * Apply the function @func to each slave kctl of the given vmaster kctl.
+ * Returns 0 if successful, or a negative error code.
+ */
+int snd_ctl_apply_vmaster_slaves(struct snd_kcontrol *kctl,
+				 int (*func)(struct snd_kcontrol *, void *),
+				 void *arg)
+{
+	struct link_master *master;
+	struct link_slave *slave;
+	int err;
+
+	master = snd_kcontrol_chip(kctl);
+	err = master_init(master);
+	if (err < 0)
+		return err;
+	list_for_each_entry(slave, &master->slaves, list) {
+		err = func(&slave->slave, arg);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_ctl_apply_vmaster_slaves);
diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c
index 978dc18..f6d2985 100644
--- a/sound/hda/hdac_controller.c
+++ b/sound/hda/hdac_controller.c
@@ -284,6 +284,11 @@
 		dev_dbg(bus->dev, "HDA capability ID: 0x%x\n",
 			(cur_cap & AZX_CAP_HDR_ID_MASK) >> AZX_CAP_HDR_ID_OFF);
 
+		if (cur_cap == -1) {
+			dev_dbg(bus->dev, "Invalid capability reg read\n");
+			break;
+		}
+
 		switch ((cur_cap & AZX_CAP_HDR_ID_MASK) >> AZX_CAP_HDR_ID_OFF) {
 		case AZX_ML_CAP_ID:
 			dev_dbg(bus->dev, "Found ML capability\n");
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index 7e3aa50..5badd08 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -103,6 +103,7 @@
 	void __user *puhr;
 	union hpi_message_buffer_v1 *hm;
 	union hpi_response_buffer_v1 *hr;
+	u16 msg_size;
 	u16 res_max_size;
 	u32 uncopied_bytes;
 	int err = 0;
@@ -127,22 +128,25 @@
 	}
 
 	/* Now read the message size and data from user space.  */
-	if (get_user(hm->h.size, (u16 __user *)puhm)) {
+	if (get_user(msg_size, (u16 __user *)puhm)) {
 		err = -EFAULT;
 		goto out;
 	}
-	if (hm->h.size > sizeof(*hm))
-		hm->h.size = sizeof(*hm);
+	if (msg_size > sizeof(*hm))
+		msg_size = sizeof(*hm);
 
 	/* printk(KERN_INFO "message size %d\n", hm->h.wSize); */
 
-	uncopied_bytes = copy_from_user(hm, puhm, hm->h.size);
+	uncopied_bytes = copy_from_user(hm, puhm, msg_size);
 	if (uncopied_bytes) {
 		HPI_DEBUG_LOG(ERROR, "uncopied bytes %d\n", uncopied_bytes);
 		err = -EFAULT;
 		goto out;
 	}
 
+	/* Override h.size in case it is changed between two userspace fetches */
+	hm->h.size = msg_size;
+
 	if (get_user(res_max_size, (u16 __user *)puhr)) {
 		err = -EFAULT;
 		goto out;
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 7326695..d68f99e 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -1272,11 +1272,11 @@
 
 	chip = snd_kcontrol_chip(kcontrol);
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
+	uinfo->count = 1;
 	uinfo->value.integer.min = ECHOGAIN_MINOUT;
 	uinfo->value.integer.max = ECHOGAIN_MAXOUT;
 	uinfo->dimen.d[0] = num_busses_out(chip);
 	uinfo->dimen.d[1] = num_busses_in(chip);
-	uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1];
 	return 0;
 }
 
@@ -1344,11 +1344,11 @@
 
 	chip = snd_kcontrol_chip(kcontrol);
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
+	uinfo->count = 1;
 	uinfo->value.integer.min = ECHOGAIN_MINOUT;
 	uinfo->value.integer.max = ECHOGAIN_MAXOUT;
 	uinfo->dimen.d[0] = num_busses_out(chip);
 	uinfo->dimen.d[1] = num_pipes_out(chip);
-	uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1];
 	return 0;
 }
 
@@ -1728,6 +1728,7 @@
 				  struct snd_ctl_elem_info *uinfo)
 {
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
+	uinfo->count = 96;
 	uinfo->value.integer.min = ECHOGAIN_MINOUT;
 	uinfo->value.integer.max = 0;
 #ifdef ECHOCARD_HAS_VMIXER
@@ -1737,7 +1738,6 @@
 #endif
 	uinfo->dimen.d[1] = 16;	/* 16 channels */
 	uinfo->dimen.d[2] = 2;	/* 0=level, 1=peak */
-	uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1] * uinfo->dimen.d[2];
 	return 0;
 }
 
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 3db26c4..a0989d2 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -1803,36 +1803,6 @@
 	return 1;
 }
 
-/* guess the value corresponding to 0dB */
-static int get_kctl_0dB_offset(struct hda_codec *codec,
-			       struct snd_kcontrol *kctl, int *step_to_check)
-{
-	int _tlv[4];
-	const int *tlv = NULL;
-	int val = -1;
-
-	if ((kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK) &&
-	    kctl->tlv.c == snd_hda_mixer_amp_tlv) {
-		get_ctl_amp_tlv(kctl, _tlv);
-		tlv = _tlv;
-	} else if (kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_READ)
-		tlv = kctl->tlv.p;
-	if (tlv && tlv[0] == SNDRV_CTL_TLVT_DB_SCALE) {
-		int step = tlv[3];
-		step &= ~TLV_DB_SCALE_MUTE;
-		if (!step)
-			return -1;
-		if (*step_to_check && *step_to_check != step) {
-			codec_err(codec, "Mismatching dB step for vmaster slave (%d!=%d)\n",
--				   *step_to_check, step);
-			return -1;
-		}
-		*step_to_check = step;
-		val = -tlv[2] / step;
-	}
-	return val;
-}
-
 /* call kctl->put with the given value(s) */
 static int put_kctl_with_value(struct snd_kcontrol *kctl, int val)
 {
@@ -1847,19 +1817,58 @@
 	return 0;
 }
 
-/* initialize the slave volume with 0dB */
-static int init_slave_0dB(struct hda_codec *codec,
-			  void *data, struct snd_kcontrol *slave)
+struct slave_init_arg {
+	struct hda_codec *codec;
+	int step;
+};
+
+/* initialize the slave volume with 0dB via snd_ctl_apply_vmaster_slaves() */
+static int init_slave_0dB(struct snd_kcontrol *kctl, void *_arg)
 {
-	int offset = get_kctl_0dB_offset(codec, slave, data);
-	if (offset > 0)
-		put_kctl_with_value(slave, offset);
+	struct slave_init_arg *arg = _arg;
+	int _tlv[4];
+	const int *tlv = NULL;
+	int step;
+	int val;
+
+	if (kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK) {
+		if (kctl->tlv.c != snd_hda_mixer_amp_tlv) {
+			codec_err(arg->codec,
+				  "Unexpected TLV callback for slave %s:%d\n",
+				  kctl->id.name, kctl->id.index);
+			return 0; /* ignore */
+		}
+		get_ctl_amp_tlv(kctl, _tlv);
+		tlv = _tlv;
+	} else if (kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_READ)
+		tlv = kctl->tlv.p;
+
+	if (!tlv || tlv[0] != SNDRV_CTL_TLVT_DB_SCALE)
+		return 0;
+
+	step = tlv[3];
+	step &= ~TLV_DB_SCALE_MUTE;
+	if (!step)
+		return 0;
+	if (arg->step && arg->step != step) {
+		codec_err(arg->codec,
+			  "Mismatching dB step for vmaster slave (%d!=%d)\n",
+			  arg->step, step);
+		return 0;
+	}
+
+	arg->step = step;
+	val = -tlv[2] / step;
+	if (val > 0) {
+		put_kctl_with_value(kctl, val);
+		return val;
+	}
+
 	return 0;
 }
 
-/* unmute the slave */
-static int init_slave_unmute(struct hda_codec *codec,
-			     void *data, struct snd_kcontrol *slave)
+/* unmute the slave via snd_ctl_apply_vmaster_slaves() */
+static int init_slave_unmute(struct snd_kcontrol *slave, void *_arg)
 {
 	return put_kctl_with_value(slave, 1);
 }
@@ -1919,9 +1928,13 @@
 	/* init with master mute & zero volume */
 	put_kctl_with_value(kctl, 0);
 	if (init_slave_vol) {
-		int step = 0;
-		map_slaves(codec, slaves, suffix,
-			   tlv ? init_slave_0dB : init_slave_unmute, &step);
+		struct slave_init_arg arg = {
+			.codec = codec,
+			.step = 0,
+		};
+		snd_ctl_apply_vmaster_slaves(kctl,
+					     tlv ? init_slave_0dB : init_slave_unmute,
+					     &arg);
 	}
 
 	if (ctl_ret)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 2b64fab..c19c81d 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -906,6 +906,7 @@
 			      hda_nid_t pin_nid, u32 stream_tag, int format)
 {
 	struct hdmi_spec *spec = codec->spec;
+	unsigned int param;
 	int err;
 
 	err = spec->ops.pin_hbr_setup(codec, pin_nid, is_hbr_format(format));
@@ -915,6 +916,26 @@
 		return err;
 	}
 
+	if (is_haswell_plus(codec)) {
+
+		/*
+		 * on recent platforms IEC Coding Type is required for HBR
+		 * support, read current Digital Converter settings and set
+		 * ICT bitfield if needed.
+		 */
+		param = snd_hda_codec_read(codec, cvt_nid, 0,
+					   AC_VERB_GET_DIGI_CONVERT_1, 0);
+
+		param = (param >> 16) & ~(AC_DIG3_ICT);
+
+		/* on recent platforms ICT mode is required for HBR support */
+		if (is_hbr_format(format))
+			param |= 0x1;
+
+		snd_hda_codec_write(codec, cvt_nid, 0,
+				    AC_VERB_SET_DIGI_CONVERT_3, param);
+	}
+
 	snd_hda_codec_setup_stream(codec, cvt_nid, stream_tag, 0, format);
 	return 0;
 }
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 0ce7111..546d515 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -327,6 +327,7 @@
 	case 0x10ec0215:
 	case 0x10ec0225:
 	case 0x10ec0233:
+	case 0x10ec0236:
 	case 0x10ec0255:
 	case 0x10ec0256:
 	case 0x10ec0282:
@@ -911,6 +912,7 @@
 	{ 0x10ec0275, 0x1028, 0, "ALC3260" },
 	{ 0x10ec0899, 0x1028, 0, "ALC3861" },
 	{ 0x10ec0298, 0x1028, 0, "ALC3266" },
+	{ 0x10ec0236, 0x1028, 0, "ALC3204" },
 	{ 0x10ec0256, 0x1028, 0, "ALC3246" },
 	{ 0x10ec0225, 0x1028, 0, "ALC3253" },
 	{ 0x10ec0295, 0x1028, 0, "ALC3254" },
@@ -3930,6 +3932,7 @@
 		alc_process_coef_fw(codec, coef0255_1);
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0236:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0256);
 		alc_process_coef_fw(codec, coef0255);
@@ -4028,6 +4031,7 @@
 	};
 
 	switch (codec->core.vendor_id) {
+	case 0x10ec0236:
 	case 0x10ec0255:
 	case 0x10ec0256:
 		alc_write_coef_idx(codec, 0x45, 0xc489);
@@ -4160,6 +4164,7 @@
 		alc_process_coef_fw(codec, alc225_pre_hsmode);
 		alc_process_coef_fw(codec, coef0225);
 		break;
+	case 0x10ec0236:
 	case 0x10ec0255:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
@@ -4256,6 +4261,7 @@
 	case 0x10ec0255:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0236:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0256);
 		break;
@@ -4366,6 +4372,7 @@
 	case 0x10ec0255:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0236:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0256);
 		break;
@@ -4451,6 +4458,7 @@
 	};
 
 	switch (codec->core.vendor_id) {
+	case 0x10ec0236:
 	case 0x10ec0255:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
@@ -4705,6 +4713,7 @@
 	case 0x10ec0255:
 		alc_process_coef_fw(codec, alc255fw);
 		break;
+	case 0x10ec0236:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, alc256fw);
 		break;
@@ -6419,6 +6428,14 @@
 		ALC225_STANDARD_PINS,
 		{0x12, 0xb7a60130},
 		{0x1b, 0x90170110}),
+	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60140},
+		{0x14, 0x90170110},
+		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60140},
+		{0x14, 0x90170150},
+		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
 		{0x14, 0x90170110},
 		{0x21, 0x02211020}),
@@ -6806,6 +6823,7 @@
 	case 0x10ec0255:
 		spec->codec_variant = ALC269_TYPE_ALC255;
 		break;
+	case 0x10ec0236:
 	case 0x10ec0256:
 		spec->codec_variant = ALC269_TYPE_ALC256;
 		spec->shutup = alc256_shutup;
@@ -7857,6 +7875,7 @@
 	HDA_CODEC_ENTRY(0x10ec0233, "ALC233", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0234, "ALC234", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0236, "ALC236", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0255, "ALC255", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0256, "ALC256", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0260, "ALC260", patch_alc260),
diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c
index 0fb6b1b7..d8409d9 100644
--- a/sound/usb/caiaq/device.c
+++ b/sound/usb/caiaq/device.c
@@ -469,10 +469,12 @@
 
 	err = snd_usb_caiaq_send_command(cdev, EP1_CMD_GET_DEVICE_INFO, NULL, 0);
 	if (err)
-		return err;
+		goto err_kill_urb;
 
-	if (!wait_event_timeout(cdev->ep1_wait_queue, cdev->spec_received, HZ))
-		return -ENODEV;
+	if (!wait_event_timeout(cdev->ep1_wait_queue, cdev->spec_received, HZ)) {
+		err = -ENODEV;
+		goto err_kill_urb;
+	}
 
 	usb_string(usb_dev, usb_dev->descriptor.iManufacturer,
 		   cdev->vendor_name, CAIAQ_USB_STR_LEN);
@@ -507,6 +509,10 @@
 
 	setup_card(cdev);
 	return 0;
+
+ err_kill_urb:
+	usb_kill_urb(&cdev->ep1_in_urb);
+	return err;
 }
 
 static int snd_probe(struct usb_interface *intf,
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 3dc36d9..23d1d23 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -221,6 +221,7 @@
 	struct usb_interface_descriptor *altsd;
 	void *control_header;
 	int i, protocol;
+	int rest_bytes;
 
 	/* find audiocontrol interface */
 	host_iface = &usb_ifnum_to_if(dev, ctrlif)->altsetting[0];
@@ -235,6 +236,15 @@
 		return -EINVAL;
 	}
 
+	rest_bytes = (void *)(host_iface->extra + host_iface->extralen) -
+		control_header;
+
+	/* just to be sure -- this shouldn't hit at all */
+	if (rest_bytes <= 0) {
+		dev_err(&dev->dev, "invalid control header\n");
+		return -EINVAL;
+	}
+
 	switch (protocol) {
 	default:
 		dev_warn(&dev->dev,
@@ -245,11 +255,21 @@
 	case UAC_VERSION_1: {
 		struct uac1_ac_header_descriptor *h1 = control_header;
 
+		if (rest_bytes < sizeof(*h1)) {
+			dev_err(&dev->dev, "too short v1 buffer descriptor\n");
+			return -EINVAL;
+		}
+
 		if (!h1->bInCollection) {
 			dev_info(&dev->dev, "skipping empty audio interface (v1)\n");
 			return -EINVAL;
 		}
 
+		if (rest_bytes < h1->bLength) {
+			dev_err(&dev->dev, "invalid buffer length (v1)\n");
+			return -EINVAL;
+		}
+
 		if (h1->bLength < sizeof(*h1) + h1->bInCollection) {
 			dev_err(&dev->dev, "invalid UAC_HEADER (v1)\n");
 			return -EINVAL;
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 0ff5a7d..c8f723c 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -779,9 +779,10 @@
 	return 0;
 
  error:
-	if (line6->disconnect)
-		line6->disconnect(line6);
-	snd_card_free(card);
+	/* we can call disconnect callback here because no close-sync is
+	 * needed yet at this point
+	 */
+	line6_disconnect(interface);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(line6_probe);
diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c
index 956f847..451007c 100644
--- a/sound/usb/line6/podhd.c
+++ b/sound/usb/line6/podhd.c
@@ -301,7 +301,8 @@
 
 		intf = usb_ifnum_to_if(line6->usbdev,
 					pod->line6.properties->ctrl_if);
-		usb_driver_release_interface(&podhd_driver, intf);
+		if (intf)
+			usb_driver_release_interface(&podhd_driver, intf);
 	}
 }
 
@@ -317,6 +318,9 @@
 
 	line6->disconnect = podhd_disconnect;
 
+	init_timer(&pod->startup_timer);
+	INIT_WORK(&pod->startup_work, podhd_startup_workqueue);
+
 	if (pod->line6.properties->capabilities & LINE6_CAP_CONTROL) {
 		/* claim the data interface */
 		intf = usb_ifnum_to_if(line6->usbdev,
@@ -358,8 +362,6 @@
 	}
 
 	/* init device and delay registering */
-	init_timer(&pod->startup_timer);
-	INIT_WORK(&pod->startup_work, podhd_startup_workqueue);
 	podhd_startup(pod);
 	return 0;
 }
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 9732edf..91bc8f1 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -2234,6 +2234,9 @@
 
 static void snd_usb_mixer_free(struct usb_mixer_interface *mixer)
 {
+	/* kill pending URBs */
+	snd_usb_mixer_disconnect(mixer);
+
 	kfree(mixer->id_elems);
 	if (mixer->urb) {
 		kfree(mixer->urb->transfer_buffer);
@@ -2584,8 +2587,13 @@
 
 void snd_usb_mixer_disconnect(struct usb_mixer_interface *mixer)
 {
-	usb_kill_urb(mixer->urb);
-	usb_kill_urb(mixer->rc_urb);
+	if (mixer->disconnected)
+		return;
+	if (mixer->urb)
+		usb_kill_urb(mixer->urb);
+	if (mixer->rc_urb)
+		usb_kill_urb(mixer->rc_urb);
+	mixer->disconnected = true;
 }
 
 #ifdef CONFIG_PM
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index 2b4b067..545d99b 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -22,6 +22,8 @@
 	struct urb *rc_urb;
 	struct usb_ctrlrequest *rc_setup_packet;
 	u8 rc_buffer[6];
+
+	bool disconnected;
 };
 
 #define MAX_CHANNELS	16	/* max logical channels */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 9135520..4f5f18f 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1137,6 +1137,9 @@
 	case USB_ID(0x047F, 0x02F7): /* Plantronics BT-600 */
 	case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */
 	case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */
+	case USB_ID(0x047F, 0xC022): /* Plantronics C310 */
+	case USB_ID(0x047F, 0xC02F): /* Plantronics P610 */
+	case USB_ID(0x047F, 0xC036): /* Plantronics C520-M */
 	case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
 	case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */
 	case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */
@@ -1351,6 +1354,7 @@
 	case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */
 	case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */
 	case USB_ID(0x22d9, 0x0416): /* OPPO HA-1 */
+	case USB_ID(0x2772, 0x0230): /* Pro-Ject Pre Box S2 Digital */
 		if (fp->altsetting == 2)
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
 		break;
diff --git a/sound/usb/usx2y/usb_stream.c b/sound/usb/usx2y/usb_stream.c
index 4dab490..e229abd 100644
--- a/sound/usb/usx2y/usb_stream.c
+++ b/sound/usb/usx2y/usb_stream.c
@@ -191,7 +191,8 @@
 	}
 
 	pg = get_order(read_size);
-	sk->s = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO, pg);
+	sk->s = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO|
+					  __GFP_NOWARN, pg);
 	if (!sk->s) {
 		snd_printk(KERN_WARNING "couldn't __get_free_pages()\n");
 		goto out;
@@ -211,7 +212,8 @@
 	pg = get_order(write_size);
 
 	sk->write_page =
-		(void *)__get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO, pg);
+		(void *)__get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO|
+					 __GFP_NOWARN, pg);
 	if (!sk->write_page) {
 		snd_printk(KERN_WARNING "couldn't __get_free_pages()\n");
 		usb_stream_free(sk);
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 69d09c3..cd7359e 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -88,6 +88,12 @@
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1
+#define KVM_S390_VM_TOD_EXT		2
+
+struct kvm_s390_vm_tod_clock {
+	__u8  epoch_idx;
+	__u64 tod;
+};
 
 /* kvm attributes for KVM_S390_VM_CPU_MODEL */
 /* processor related attributes are r/w */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 8ea315a1..2519c6c 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -196,6 +196,7 @@
 
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME		( 7*32+10) /* AMD Secure Memory Encryption */
 
 #define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
@@ -287,6 +288,7 @@
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
 #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 5dff775..c10c912 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -21,11 +21,13 @@
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
 # define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
 # define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
+# define DISABLE_PCID		0
 #else
 # define DISABLE_VME		0
 # define DISABLE_K6_MTRR	0
 # define DISABLE_CYRIX_ARR	0
 # define DISABLE_CENTAUR_MCR	0
+# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
 #endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
@@ -49,7 +51,7 @@
 #define DISABLED_MASK1	0
 #define DISABLED_MASK2	0
 #define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	0
+#define DISABLED_MASK4	(DISABLE_PCID)
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	0
diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h
new file mode 100644
index 0000000..e4732d3
--- /dev/null
+++ b/tools/include/asm-generic/hugetlb_encode.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size.  If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments.  The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments.  System call specific header files
+ * that use this encoding should include this file.  They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT	26
+#define HUGETLB_FLAG_ENCODE_MASK	0x3f
+
+#define HUGETLB_FLAG_ENCODE_64KB	(16 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB	(19 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB		(20 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB		(21 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB		(23 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB	(24 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB	(28 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB		(30 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB		(31 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB	(34 << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 8c27db0..203268f 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -58,20 +58,12 @@
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_DONTDUMP flag */
 
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT	26
-#define MAP_HUGE_MASK	0x3f
-
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 101593a..97677cd 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -700,6 +700,7 @@
 
 struct drm_syncobj_create {
 	__u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
 	__u32 flags;
 };
 
@@ -718,6 +719,24 @@
 	__u32 pad;
 };
 
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+struct drm_syncobj_wait {
+	__u64 handles;
+	/* absolute timeout */
+	__s64 timeout_nsec;
+	__u32 count_handles;
+	__u32 flags;
+	__u32 first_signaled; /* only valid when not waiting all */
+	__u32 pad;
+};
+
+struct drm_syncobj_array {
+	__u64 handles;
+	__u32 count_handles;
+	__u32 pad;
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -840,6 +859,9 @@
 #define DRM_IOCTL_SYNCOBJ_DESTROY	DRM_IOWR(0xC0, struct drm_syncobj_destroy)
 #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD	DRM_IOWR(0xC1, struct drm_syncobj_handle)
 #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE	DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT		DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
 
 /**
  * Device specific ioctls should only be in their respective headers
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7ccbd6a..6598fb7 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -260,6 +260,8 @@
 #define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
 #define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
 #define DRM_I915_PERF_OPEN		0x36
+#define DRM_I915_PERF_ADD_CONFIG	0x37
+#define DRM_I915_PERF_REMOVE_CONFIG	0x38
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -315,6 +317,8 @@
 #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -431,6 +435,11 @@
  */
 #define I915_PARAM_HAS_EXEC_BATCH_FIRST	 48
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
@@ -812,6 +821,17 @@
 	__u64 rsvd2;
 };
 
+struct drm_i915_gem_exec_fence {
+	/**
+	 * User's handle for a drm_syncobj to wait on or signal.
+	 */
+	__u32 handle;
+
+#define I915_EXEC_FENCE_WAIT            (1<<0)
+#define I915_EXEC_FENCE_SIGNAL          (1<<1)
+	__u32 flags;
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -826,7 +846,11 @@
 	__u32 DR1;
 	__u32 DR4;
 	__u32 num_cliprects;
-	/** This is a struct drm_clip_rect *cliprects */
+	/**
+	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
+	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
+	 * struct drm_i915_gem_exec_fence *fences.
+	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (7<<0)
 #define I915_EXEC_DEFAULT                (0<<0)
@@ -927,7 +951,14 @@
  * element).
  */
 #define I915_EXEC_BATCH_FIRST		(1<<18)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1))
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY   (1<<19)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -1467,6 +1498,22 @@
 	DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };
 
+/**
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+	/** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+	char uuid[36];
+
+	__u32 n_mux_regs;
+	__u32 n_boolean_regs;
+	__u32 n_flex_regs;
+
+	__u64 __user mux_regs_ptr;
+	__u64 __user boolean_regs_ptr;
+	__u64 __user flex_regs_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 461811e..c174971 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -143,12 +143,6 @@
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-enum bpf_sockmap_flags {
-	BPF_SOCKMAP_UNSPEC,
-	BPF_SOCKMAP_STRPARSER,
-	__MAX_BPF_SOCKMAP_FLAG
-};
-
 /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
  * to the given target_fd cgroup the descendent cgroup will be able to
  * override effective bpf program that was inherited from this cgroup
@@ -318,7 +312,7 @@
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
@@ -368,9 +362,20 @@
  * int bpf_redirect(ifindex, flags)
  *     redirect to another netdev
  *     @ifindex: ifindex of the net device
- *     @flags: bit 0 - if set, redirect to ingress instead of egress
- *             other bits - reserved
- *     Return: TC_ACT_REDIRECT
+ *     @flags:
+ *	  cls_bpf:
+ *          bit 0 - if set, redirect to ingress instead of egress
+ *          other bits - reserved
+ *	  xdp_bpf:
+ *	    all bits - reserved
+ *     Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
+ *	       xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
+ * int bpf_redirect_map(map, key, flags)
+ *     redirect to endpoint in map
+ *     @map: pointer to dev map
+ *     @key: index in map to lookup
+ *     @flags: --
+ *     Return: XDP_REDIRECT on success or XDP_ABORT on error
  *
  * u32 bpf_get_route_realm(skb)
  *     retrieve a dst's tclassid
@@ -564,9 +569,10 @@
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
  *
- * int bpf_sk_redirect_map(map, key, flags)
+ * int bpf_sk_redirect_map(skb, map, key, flags)
  *     Redirect skb to a sock in map using key as a lookup key for the
  *     sock in map.
+ *     @skb: pointer to skb
  *     @map: pointer to sockmap
  *     @key: key to lookup sock in map
  *     @flags: reserved for future use
@@ -632,7 +638,7 @@
 	FN(skb_adjust_room),		\
 	FN(redirect_map),		\
 	FN(sk_redirect_map),		\
-	FN(sock_map_update),
+	FN(sock_map_update),		\
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -753,20 +759,23 @@
 	__u32 family;
 	__u32 type;
 	__u32 protocol;
+	__u32 mark;
+	__u32 priority;
 };
 
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
- * return codes are reserved for future use. Unknown return codes will result
- * in packet drop.
+ * return codes are reserved for future use. Unknown return codes will
+ * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
  */
 enum xdp_action {
 	XDP_ABORTED = 0,
 	XDP_DROP,
 	XDP_PASS,
 	XDP_TX,
+	XDP_REDIRECT,
 };
 
 /* user accessible metadata for XDP packet hook
@@ -778,8 +787,8 @@
 };
 
 enum sk_action {
-	SK_ABORTED = 0,
-	SK_DROP,
+	SK_DROP = 0,
+	SK_PASS,
 	SK_REDIRECT,
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 6cd63c1..8388875 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -711,7 +711,8 @@
 struct kvm_ppc_smmu_info {
 	__u64 flags;
 	__u32 slb_size;
-	__u32 pad;
+	__u16 data_keys;	/* # storage keys supported for data */
+	__u16 instr_keys;	/* # storage keys supported for instructions */
 	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 81d8edf..a937480 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -1,7 +1,8 @@
 #ifndef _UAPI_LINUX_MMAN_H
 #define _UAPI_LINUX_MMAN_H
 
-#include <uapi/asm/mman.h>
+#include <asm/mman.h>
+#include <asm-generic/hugetlb_encode.h>
 
 #define MREMAP_MAYMOVE	1
 #define MREMAP_FIXED	2
@@ -10,4 +11,25 @@
 #define OVERCOMMIT_ALWAYS		1
 #define OVERCOMMIT_NEVER		2
 
+/*
+ * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
+ * size other than the default is desired.  See hugetlb_encode.h.
+ * All known huge page size encodings are provided here.  It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system.  See mmap(2) man page for details.
+ */
+#define MAP_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
+#define MAP_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
+
+#define MAP_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
+#define MAP_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
+#define MAP_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB
+#define MAP_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
+#define MAP_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
+#define MAP_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
+#define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
+#define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
+
 #endif /* _UAPI_LINUX_MMAN_H */
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
index 6a1af43..3995735 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -194,10 +194,10 @@
    If it's a GCC-compiled .c file, the error may be because the function
    uses an inline asm() statement which has a "call" instruction.  An
    asm() statement with a call instruction must declare the use of the
-   stack pointer in its output operand.  For example, on x86_64:
+   stack pointer in its output operand.  On x86_64, this means adding
+   the ASM_CALL_CONSTRAINT as an output constraint:
 
-     register void *__sp asm("rsp");
-     asm volatile("call func" : "+r" (__sp));
+     asm volatile("call func" : ASM_CALL_CONSTRAINT);
 
    Otherwise the stack frame may not get created before the call.
 
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0e8c8ec..34a579f 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -208,14 +208,14 @@
 		break;
 
 	case 0x89:
-		if (rex == 0x48 && modrm == 0xe5) {
+		if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) {
 
-			/* mov %rsp, %rbp */
+			/* mov %rsp, reg */
 			*type = INSN_STACK;
 			op->src.type = OP_SRC_REG;
 			op->src.reg = CFI_SP;
 			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_BP;
+			op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b];
 			break;
 		}
 
@@ -284,11 +284,16 @@
 	case 0x8d:
 		if (sib == 0x24 && rex_w && !rex_b && !rex_x) {
 
-			/* lea disp(%rsp), reg */
 			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
+			if (!insn.displacement.value) {
+				/* lea (%rsp), reg */
+				op->src.type = OP_SRC_REG;
+			} else {
+				/* lea disp(%rsp), reg */
+				op->src.type = OP_SRC_ADD;
+				op->src.offset = insn.displacement.value;
+			}
 			op->src.reg = CFI_SP;
-			op->src.offset = insn.displacement.value;
 			op->dest.type = OP_DEST_REG;
 			op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f744617..c0e26ad 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -267,12 +267,13 @@
 						      &insn->immediate,
 						      &insn->stack_op);
 			if (ret)
-				return ret;
+				goto err;
 
 			if (!insn->type || insn->type > INSN_LAST) {
 				WARN_FUNC("invalid instruction type %d",
 					  insn->sec, insn->offset, insn->type);
-				return -1;
+				ret = -1;
+				goto err;
 			}
 
 			hash_add(file->insn_hash, &insn->hash, insn->offset);
@@ -296,6 +297,10 @@
 	}
 
 	return 0;
+
+err:
+	free(insn);
+	return ret;
 }
 
 /*
@@ -1203,24 +1208,39 @@
 		switch (op->src.type) {
 
 		case OP_SRC_REG:
-			if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) {
+			if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP &&
+			    cfa->base == CFI_SP &&
+			    regs[CFI_BP].base == CFI_CFA &&
+			    regs[CFI_BP].offset == -cfa->offset) {
 
-				if (cfa->base == CFI_SP &&
-				    regs[CFI_BP].base == CFI_CFA &&
-				    regs[CFI_BP].offset == -cfa->offset) {
+				/* mov %rsp, %rbp */
+				cfa->base = op->dest.reg;
+				state->bp_scratch = false;
+			}
 
-					/* mov %rsp, %rbp */
-					cfa->base = op->dest.reg;
-					state->bp_scratch = false;
-				}
+			else if (op->src.reg == CFI_SP &&
+				 op->dest.reg == CFI_BP && state->drap) {
 
-				else if (state->drap) {
+				/* drap: mov %rsp, %rbp */
+				regs[CFI_BP].base = CFI_BP;
+				regs[CFI_BP].offset = -state->stack_size;
+				state->bp_scratch = false;
+			}
 
-					/* drap: mov %rsp, %rbp */
-					regs[CFI_BP].base = CFI_BP;
-					regs[CFI_BP].offset = -state->stack_size;
-					state->bp_scratch = false;
-				}
+			else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
+
+				/*
+				 * mov %rsp, %reg
+				 *
+				 * This is needed for the rare case where GCC
+				 * does:
+				 *
+				 *   mov    %rsp, %rax
+				 *   ...
+				 *   mov    %rax, %rsp
+				 */
+				state->vals[op->dest.reg].base = CFI_CFA;
+				state->vals[op->dest.reg].offset = -state->stack_size;
 			}
 
 			else if (op->dest.reg == cfa->base) {
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 6e9f980..2446015 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -175,19 +175,20 @@
 			return -1;
 		}
 
-		sec->data = elf_getdata(s, NULL);
-		if (!sec->data) {
-			WARN_ELF("elf_getdata");
-			return -1;
+		if (sec->sh.sh_size != 0) {
+			sec->data = elf_getdata(s, NULL);
+			if (!sec->data) {
+				WARN_ELF("elf_getdata");
+				return -1;
+			}
+			if (sec->data->d_off != 0 ||
+			    sec->data->d_size != sec->sh.sh_size) {
+				WARN("unexpected data attributes for %s",
+				     sec->name);
+				return -1;
+			}
 		}
-
-		if (sec->data->d_off != 0 ||
-		    sec->data->d_size != sec->sh.sh_size) {
-			WARN("unexpected data attributes for %s", sec->name);
-			return -1;
-		}
-
-		sec->len = sec->data->d_size;
+		sec->len = sec->sh.sh_size;
 	}
 
 	/* sanity check, one more call to elf_nextscn() should return NULL */
@@ -508,6 +509,7 @@
 	strcat(relaname, base->name);
 
 	sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0);
+	free(relaname);
 	if (!sec)
 		return NULL;
 
@@ -561,6 +563,7 @@
 	struct section *sec;
 	Elf_Scn *s;
 
+	/* Update section headers for changed sections: */
 	list_for_each_entry(sec, &elf->sections, list) {
 		if (sec->changed) {
 			s = elf_getscn(elf->elf, sec->idx);
@@ -568,13 +571,17 @@
 				WARN_ELF("elf_getscn");
 				return -1;
 			}
-			if (!gelf_update_shdr (s, &sec->sh)) {
+			if (!gelf_update_shdr(s, &sec->sh)) {
 				WARN_ELF("gelf_update_shdr");
 				return -1;
 			}
 		}
 	}
 
+	/* Make sure the new section header entries get updated properly. */
+	elf_flagelf(elf->elf, ELF_C_SET, ELF_F_DIRTY);
+
+	/* Write all changes to the file. */
 	if (elf_update(elf->elf, ELF_C_WRITE) < 0) {
 		WARN_ELF("elf_update");
 		return -1;
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e397453..63526f4 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -8,8 +8,8 @@
 SYNOPSIS
 --------
 [verse]
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
+'perf record' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf record' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 
 DESCRIPTION
 -----------
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 6207282..627b7ca 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,34 +1,8 @@
 tools/perf
-tools/arch/alpha/include/asm/barrier.h
-tools/arch/arm/include/asm/barrier.h
-tools/arch/arm64/include/asm/barrier.h
-tools/arch/ia64/include/asm/barrier.h
-tools/arch/mips/include/asm/barrier.h
-tools/arch/powerpc/include/asm/barrier.h
-tools/arch/s390/include/asm/barrier.h
-tools/arch/sh/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier_32.h
-tools/arch/sparc/include/asm/barrier_64.h
-tools/arch/tile/include/asm/barrier.h
-tools/arch/x86/include/asm/barrier.h
-tools/arch/x86/include/asm/cmpxchg.h
-tools/arch/x86/include/asm/cpufeatures.h
-tools/arch/x86/include/asm/disabled-features.h
-tools/arch/x86/include/asm/required-features.h
-tools/arch/x86/include/uapi/asm/svm.h
-tools/arch/x86/include/uapi/asm/vmx.h
-tools/arch/x86/include/uapi/asm/kvm.h
-tools/arch/x86/include/uapi/asm/kvm_perf.h
-tools/arch/x86/lib/memcpy_64.S
-tools/arch/x86/lib/memset_64.S
-tools/arch/s390/include/uapi/asm/kvm_perf.h
-tools/arch/s390/include/uapi/asm/sie.h
-tools/arch/xtensa/include/asm/barrier.h
+tools/arch
 tools/scripts
 tools/build
-tools/arch/x86/include/asm/atomic.h
-tools/arch/x86/include/asm/rmwcc.h
+tools/include
 tools/lib/traceevent
 tools/lib/api
 tools/lib/bpf
@@ -42,60 +16,3 @@
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
-tools/include/asm/alternative-asm.h
-tools/include/asm/atomic.h
-tools/include/asm/barrier.h
-tools/include/asm/bug.h
-tools/include/asm-generic/atomic-gcc.h
-tools/include/asm-generic/barrier.h
-tools/include/asm-generic/bitops/arch_hweight.h
-tools/include/asm-generic/bitops/atomic.h
-tools/include/asm-generic/bitops/const_hweight.h
-tools/include/asm-generic/bitops/__ffs.h
-tools/include/asm-generic/bitops/__ffz.h
-tools/include/asm-generic/bitops/__fls.h
-tools/include/asm-generic/bitops/find.h
-tools/include/asm-generic/bitops/fls64.h
-tools/include/asm-generic/bitops/fls.h
-tools/include/asm-generic/bitops/hweight.h
-tools/include/asm-generic/bitops.h
-tools/include/linux/atomic.h
-tools/include/linux/bitops.h
-tools/include/linux/compiler.h
-tools/include/linux/compiler-gcc.h
-tools/include/linux/coresight-pmu.h
-tools/include/linux/bug.h
-tools/include/linux/filter.h
-tools/include/linux/hash.h
-tools/include/linux/kernel.h
-tools/include/linux/list.h
-tools/include/linux/log2.h
-tools/include/uapi/asm-generic/fcntl.h
-tools/include/uapi/asm-generic/ioctls.h
-tools/include/uapi/asm-generic/mman-common.h
-tools/include/uapi/asm-generic/mman.h
-tools/include/uapi/drm/drm.h
-tools/include/uapi/drm/i915_drm.h
-tools/include/uapi/linux/bpf.h
-tools/include/uapi/linux/bpf_common.h
-tools/include/uapi/linux/fcntl.h
-tools/include/uapi/linux/hw_breakpoint.h
-tools/include/uapi/linux/kvm.h
-tools/include/uapi/linux/mman.h
-tools/include/uapi/linux/perf_event.h
-tools/include/uapi/linux/sched.h
-tools/include/uapi/linux/stat.h
-tools/include/uapi/linux/vhost.h
-tools/include/uapi/sound/asound.h
-tools/include/linux/poison.h
-tools/include/linux/rbtree.h
-tools/include/linux/rbtree_augmented.h
-tools/include/linux/refcount.h
-tools/include/linux/string.h
-tools/include/linux/stringify.h
-tools/include/linux/types.h
-tools/include/linux/err.h
-tools/include/linux/bitmap.h
-tools/include/linux/time64.h
-tools/arch/*/include/uapi/asm/mman.h
-tools/arch/*/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index bd518b6..5bd7b92 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -1,5 +1,4 @@
 libperf-y += header.o
-libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c
deleted file mode 100644
index e103f6e..0000000
--- a/tools/perf/arch/s390/util/sym-handling.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Architecture specific ELF symbol handling and relocation mapping.
- *
- * Copyright 2017 IBM Corp.
- * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- */
-
-#include "symbol.h"
-
-#ifdef HAVE_LIBELF_SUPPORT
-bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
-{
-	if (ehdr.e_type == ET_EXEC)
-		return false;
-	return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN;
-}
-
-void arch__adjust_sym_map_offset(GElf_Sym *sym,
-				 GElf_Shdr *shdr __maybe_unused,
-				 struct map *map)
-{
-	if (map->type == MAP__FUNCTION)
-		sym->st_value += map->start;
-}
-#endif
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3d4c3b5..0c977b6 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -586,7 +586,7 @@
 			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		}
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
@@ -681,7 +681,7 @@
 		if (alt.map && !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 462fc75..7a84d73 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,6 +10,9 @@
 
 . $(dirname $0)/lib/probe.sh
 
+ld=$(realpath /lib64/ld*.so.* | uniq)
+libc=$(echo $ld | sed 's/ld/libc/g')
+
 trace_libc_inet_pton_backtrace() {
 	idx=0
 	expected[0]="PING.*bytes"
@@ -18,8 +21,8 @@
 	expected[3]=".*packets transmitted.*"
 	expected[4]="rtt min.*"
 	expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
-	expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
-	expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
+	expected[6]=".*inet_pton[[:space:]]\($libc\)$"
+	expected[7]="getaddrinfo[[:space:]]\($libc\)$"
 	expected[8]=".*\(.*/bin/ping.*\)$"
 
 	perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
@@ -35,7 +38,7 @@
 }
 
 skip_if_no_perf_probe && \
-perf probe -q /lib64/libc-*.so inet_pton && \
+perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
 err=$?
 rm -f ${file}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ddb2c6f..db79017 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -532,7 +532,7 @@
 
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-	list_del(&format->list);
+	list_del_init(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
@@ -606,6 +606,13 @@
 
 static void fmt_free(struct perf_hpp_fmt *fmt)
 {
+	/*
+	 * At this point fmt should be completely
+	 * unhooked, if not it's a bug.
+	 */
+	BUG_ON(!list_empty(&fmt->list));
+	BUG_ON(!list_empty(&fmt->sort_list));
+
 	if (fmt->free)
 		fmt->free(fmt);
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 510b513..a971caf 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -65,8 +65,6 @@
 		callchain_param.mode = CHAIN_FOLDED;
 		return 0;
 	}
-
-	pr_err("Invalid callchain mode: %s\n", value);
 	return -1;
 }
 
@@ -82,8 +80,6 @@
 		callchain_param.order_set = true;
 		return 0;
 	}
-
-	pr_err("Invalid callchain order: %s\n", value);
 	return -1;
 }
 
@@ -105,8 +101,6 @@
 		callchain_param.branch_callstack = 1;
 		return 0;
 	}
-
-	pr_err("Invalid callchain sort key: %s\n", value);
 	return -1;
 }
 
@@ -124,8 +118,6 @@
 		callchain_param.value = CCVAL_COUNT;
 		return 0;
 	}
-
-	pr_err("Invalid callchain config key: %s\n", value);
 	return -1;
 }
 
@@ -319,12 +311,27 @@
 
 		return ret;
 	}
-	if (!strcmp(var, "print-type"))
-		return parse_callchain_mode(value);
-	if (!strcmp(var, "order"))
-		return parse_callchain_order(value);
-	if (!strcmp(var, "sort-key"))
-		return parse_callchain_sort_key(value);
+	if (!strcmp(var, "print-type")){
+		int ret;
+		ret = parse_callchain_mode(value);
+		if (ret == -1)
+			pr_err("Invalid callchain mode: %s\n", value);
+		return ret;
+	}
+	if (!strcmp(var, "order")){
+		int ret;
+		ret = parse_callchain_order(value);
+		if (ret == -1)
+			pr_err("Invalid callchain order: %s\n", value);
+		return ret;
+	}
+	if (!strcmp(var, "sort-key")){
+		int ret;
+		ret = parse_callchain_sort_key(value);
+		if (ret == -1)
+			pr_err("Invalid callchain sort key: %s\n", value);
+		return ret;
+	}
 	if (!strcmp(var, "threshold")) {
 		callchain_param.min_percent = strtod(value, &endptr);
 		if (value == endptr) {
@@ -678,6 +685,8 @@
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
+	struct dso *left_dso = NULL;
+	struct dso *right_dso = NULL;
 
 	if (callchain_param.key == CCKEY_SRCLINE) {
 		enum match_result match = match_chain_srcline(node, cnode);
@@ -689,12 +698,14 @@
 	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
+		left_dso = cnode->ms.map->dso;
+		right_dso = node->map->dso;
 	} else {
 		left = cnode->ip;
 		right = node->ip;
 	}
 
-	if (left == right) {
+	if (left == right && left_dso == right_dso) {
 		if (node->branch) {
 			cnode->branch_count++;
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4bb8937..0dccdb8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -271,12 +271,17 @@
 	return evsel;
 }
 
+static bool perf_event_can_profile_kernel(void)
+{
+	return geteuid() == 0 || perf_event_paranoid() == -1;
+}
+
 struct perf_evsel *perf_evsel__new_cycles(bool precise)
 {
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= geteuid() != 0,
+		.exclude_kernel	= !perf_event_can_profile_kernel(),
 	};
 	struct perf_evsel *evsel;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f6257fb..39b1596 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -309,10 +309,11 @@
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
-	    char *name, struct cpu_map *cpus,
+	    char *name, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats)
 {
 	struct perf_evsel *evsel;
+	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
 
 	event_attr_init(attr);
 
@@ -323,7 +324,7 @@
 	(*idx)++;
 	evsel->cpus        = cpu_map__get(cpus);
 	evsel->own_cpus    = cpu_map__get(cpus);
-	evsel->system_wide = !!cpus;
+	evsel->system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)
@@ -1233,7 +1234,7 @@
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -1254,7 +1255,7 @@
 		return -EINVAL;
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
-			    get_config_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats);
 	if (evsel) {
 		evsel->unit = info.unit;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index c42edea..dcfdafd 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -8,6 +8,9 @@
 
 %{
 #include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 #include "../perf.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
@@ -53,9 +56,8 @@
 	return token;
 }
 
-static bool isbpf(yyscan_t scanner)
+static bool isbpf_suffix(char *text)
 {
-	char *text = parse_events_get_text(scanner);
 	int len = strlen(text);
 
 	if (len < 2)
@@ -68,6 +70,17 @@
 	return false;
 }
 
+static bool isbpf(yyscan_t scanner)
+{
+	char *text = parse_events_get_text(scanner);
+	struct stat st;
+
+	if (!isbpf_suffix(text))
+		return false;
+
+	return stat(text, &st) == 0;
+}
+
 /*
  * This function is called when the parser gets two kind of input:
  *
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ac16a9d..1c4d7b4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -470,31 +470,10 @@
 	closedir(dir);
 }
 
-static struct cpu_map *pmu_cpumask(const char *name)
+static struct cpu_map *__pmu_cpumask(const char *path)
 {
-	struct stat st;
-	char path[PATH_MAX];
 	FILE *file;
 	struct cpu_map *cpus;
-	const char *sysfs = sysfs__mountpoint();
-	const char *templates[] = {
-		 "%s/bus/event_source/devices/%s/cpumask",
-		 "%s/bus/event_source/devices/%s/cpus",
-		 NULL
-	};
-	const char **template;
-
-	if (!sysfs)
-		return NULL;
-
-	for (template = templates; *template; template++) {
-		snprintf(path, PATH_MAX, *template, sysfs, name);
-		if (stat(path, &st) == 0)
-			break;
-	}
-
-	if (!*template)
-		return NULL;
 
 	file = fopen(path, "r");
 	if (!file)
@@ -506,6 +485,51 @@
 }
 
 /*
+ * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
+ * may have a "cpus" file.
+ */
+#define CPUS_TEMPLATE_UNCORE	"%s/bus/event_source/devices/%s/cpumask"
+#define CPUS_TEMPLATE_CPU	"%s/bus/event_source/devices/%s/cpus"
+
+static struct cpu_map *pmu_cpumask(const char *name)
+{
+	char path[PATH_MAX];
+	struct cpu_map *cpus;
+	const char *sysfs = sysfs__mountpoint();
+	const char *templates[] = {
+		CPUS_TEMPLATE_UNCORE,
+		CPUS_TEMPLATE_CPU,
+		NULL
+	};
+	const char **template;
+
+	if (!sysfs)
+		return NULL;
+
+	for (template = templates; *template; template++) {
+		snprintf(path, PATH_MAX, *template, sysfs, name);
+		cpus = __pmu_cpumask(path);
+		if (cpus)
+			return cpus;
+	}
+
+	return NULL;
+}
+
+static bool pmu_is_uncore(const char *name)
+{
+	char path[PATH_MAX];
+	struct cpu_map *cpus;
+	const char *sysfs = sysfs__mountpoint();
+
+	snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
+	cpus = __pmu_cpumask(path);
+	cpu_map__put(cpus);
+
+	return !!cpus;
+}
+
+/*
  * Return the CPU id as a raw string.
  *
  * Each architecture should provide a more precise id string that
@@ -617,6 +641,8 @@
 
 	pmu->cpus = pmu_cpumask(name);
 
+	pmu->is_uncore = pmu_is_uncore(name);
+
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 389e972..fe0de05 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -22,6 +22,7 @@
 	char *name;
 	__u32 type;
 	bool selectable;
+	bool is_uncore;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index a7ebd9f..76ab070 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -374,6 +374,8 @@
 		tool->mmap2 = process_event_stub;
 	if (tool->comm == NULL)
 		tool->comm = process_event_stub;
+	if (tool->namespaces == NULL)
+		tool->namespaces = process_event_stub;
 	if (tool->fork == NULL)
 		tool->fork = process_event_stub;
 	if (tool->exit == NULL)
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 5c39f42..9cf781f 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -810,12 +810,6 @@
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
 		GElf_Sym *sym __maybe_unused) { }
 
-void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr,
-				       struct map *map __maybe_unused)
-{
-	sym->st_value -= shdr->sh_addr - shdr->sh_offset;
-}
-
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, int kmodule)
 {
@@ -996,7 +990,7 @@
 
 			/* Adjust symbol to map to file offset */
 			if (adjust_kernel_syms)
-				arch__adjust_sym_map_offset(&sym, &shdr, map);
+				sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 
 			if (strcmp(section_name,
 				   (curr_dso->short_name +
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2bd6a1f..aad99e7 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -344,9 +344,6 @@
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
 void arch__sym_update(struct symbol *s, GElf_Sym *sym);
-void arch__adjust_sym_map_offset(GElf_Sym *sym,
-				 GElf_Shdr *shdr __maybe_unused,
-				 struct map *map __maybe_unused);
 #endif
 
 #define SYMBOL_A 0
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 19e5db9..6eea7cf 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -15,9 +15,9 @@
 
 #include "syscalltbl.h"
 #include <stdlib.h>
+#include <linux/compiler.h>
 
 #ifdef HAVE_SYSCALL_TABLE
-#include <linux/compiler.h>
 #include <string.h>
 #include "string2.h"
 #include "util.h"
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index 4ba726c..54af6046 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -23,12 +23,12 @@
 
 static inline int xyarray__max_y(struct xyarray *xy)
 {
-	return xy->max_x;
+	return xy->max_y;
 }
 
 static inline int xyarray__max_x(struct xyarray *xy)
 {
-	return xy->max_y;
+	return xy->max_x;
 }
 
 #endif /* _PERF_XYARRAY_H_ */
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index 4c5a481..d6e1c02 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -26,7 +26,7 @@
 
 ifneq ($(OUTPUT),)
 # check that the output directory actually exists
-OUTDIR := $(realpath $(OUTPUT))
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 0dafba2..bd9c6b3 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -92,7 +92,6 @@
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
-int do_migrate;
 double discover_bclk(unsigned int family, unsigned int model);
 unsigned int has_hwp;	/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
 			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
@@ -303,9 +302,6 @@
 
 int cpu_migrate(int cpu)
 {
-	if (!do_migrate)
-		return 0;
-
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
 	CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set);
 	if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1)
@@ -5007,7 +5003,6 @@
 		{"hide",	required_argument,	0, 'H'},	// meh, -h taken by --help
 		{"Joules",	no_argument,		0, 'J'},
 		{"list",	no_argument,		0, 'l'},
-		{"migrate",	no_argument,		0, 'm'},
 		{"out",		required_argument,	0, 'o'},
 		{"quiet",	no_argument,		0, 'q'},
 		{"show",	required_argument,	0, 's'},
@@ -5019,7 +5014,7 @@
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:Jmo:qST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -5062,9 +5057,6 @@
 			list_header_only++;
 			quiet++;
 			break;
-		case 'm':
-			do_migrate = 1;
-			break;
 		case 'o':
 			outf = fopen_or_die(optarg, "w");
 			break;
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 9dc8f07..1e8b611 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,7 +1,7 @@
 ifneq ($(O),)
 ifeq ($(origin O), command line)
-	ABSOLUTE_O := $(realpath $(O))
-	dummy := $(if $(ABSOLUTE_O),,$(error O=$(O) does not exist))
+	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
+	ABSOLUTE_O := $(shell cd $(O) ; pwd)
 	OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
 	COMMAND_O := O=$(ABSOLUTE_O)
 ifeq ($(objtree),)
@@ -12,7 +12,7 @@
 
 # check that the output directory actually exists
 ifneq ($(OUTPUT),)
-OUTDIR := $(realpath $(OUTPUT))
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index d20791c..bef419d 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1527,9 +1527,6 @@
 	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
-	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
-	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
-	set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 26ce4f7..ff80564 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -52,6 +52,10 @@
 override MAKEFLAGS =
 endif
 
+ifneq ($(KBUILD_SRC),)
+override LDFLAGS =
+endif
+
 BUILD := $(O)
 ifndef BUILD
   BUILD := $(KBUILD_OUTPUT)
@@ -62,32 +66,32 @@
 
 export BUILD
 all:
-	for TARGET in $(TARGETS); do		\
+	@for TARGET in $(TARGETS); do		\
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		mkdir $$BUILD_TARGET  -p;	\
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
 	done;
 
 run_tests: all
-	for TARGET in $(TARGETS); do \
+	@for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
 	done;
 
 hotplug:
-	for TARGET in $(TARGETS_HOTPLUG); do \
+	@for TARGET in $(TARGETS_HOTPLUG); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
 	done;
 
 run_hotplug: hotplug
-	for TARGET in $(TARGETS_HOTPLUG); do \
+	@for TARGET in $(TARGETS_HOTPLUG); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\
 	done;
 
 clean_hotplug:
-	for TARGET in $(TARGETS_HOTPLUG); do \
+	@for TARGET in $(TARGETS_HOTPLUG); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
 	done;
@@ -103,7 +107,7 @@
 ifdef INSTALL_PATH
 	@# Ask all targets to install their files
 	mkdir -p $(INSTALL_PATH)
-	for TARGET in $(TARGETS); do \
+	@for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
 	done;
@@ -128,7 +132,7 @@
 endif
 
 clean:
-	for TARGET in $(TARGETS); do \
+	@for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
 	done;
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 36fb916..b2e02bd 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -65,7 +65,7 @@
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_setsockopt;
-static int (*bpf_sk_redirect_map)(void *map, int key, int flags) =
+static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
 				  unsigned long long flags) =
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 20ecbaa..6c53a89 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -12,6 +12,7 @@
 	unsigned int start, end, possible_cpus = 0;
 	char buff[128];
 	FILE *fp;
+	int n;
 
 	fp = fopen(fcpu, "r");
 	if (!fp) {
@@ -20,17 +21,17 @@
 	}
 
 	while (fgets(buff, sizeof(buff), fp)) {
-		if (sscanf(buff, "%u-%u", &start, &end) == 2) {
-			possible_cpus = start == 0 ? end + 1 : 0;
-			break;
+		n = sscanf(buff, "%u-%u", &start, &end);
+		if (n == 0) {
+			printf("Failed to retrieve # possible CPUs!\n");
+			exit(1);
+		} else if (n == 1) {
+			end = start;
 		}
+		possible_cpus = start == 0 ? end + 1 : 0;
+		break;
 	}
-
 	fclose(fp);
-	if (!possible_cpus) {
-		printf("Failed to retrieve # possible CPUs!\n");
-		exit(1);
-	}
 
 	return possible_cpus;
 }
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
index 9b99bd1..2cd2d55 100644
--- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
@@ -61,8 +61,8 @@
 	bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk);
 
 	if (!map)
-		return bpf_sk_redirect_map(&sock_map_rx, sk, 0);
-	return bpf_sk_redirect_map(&sock_map_tx, sk, 0);
+		return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
+	return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index fe3a443..50ce52d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -466,7 +466,7 @@
 	int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc;
 	struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break;
 	int ports[] = {50200, 50201, 50202, 50204};
-	int err, i, fd, sfd[6] = {0xdeadbeef};
+	int err, i, fd, udp, sfd[6] = {0xdeadbeef};
 	u8 buf[20] = {0x0, 0x5, 0x3, 0x2, 0x1, 0x0};
 	int parse_prog, verdict_prog;
 	struct sockaddr_in addr;
@@ -548,6 +548,16 @@
 		goto out_sockmap;
 	}
 
+	/* Test update with unsupported UDP socket */
+	udp = socket(AF_INET, SOCK_DGRAM, 0);
+	i = 0;
+	err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY);
+	if (!err) {
+		printf("Failed socket SOCK_DGRAM allowed '%i:%i'\n",
+		       i, udp);
+		goto out_sockmap;
+	}
+
 	/* Test update without programs */
 	for (i = 0; i < 6; i++) {
 		err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 26f3250..64ae21f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1130,15 +1130,27 @@
 		.errstr = "invalid bpf_context access",
 	},
 	{
-		"check skb->mark is writeable by SK_SKB",
+		"invalid access of skb->mark for SK_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.result =  REJECT,
+		.prog_type = BPF_PROG_TYPE_SK_SKB,
+		.errstr = "invalid bpf_context access",
+	},
+	{
+		"check skb->mark is not writeable by SK_SKB",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
 				    offsetof(struct __sk_buff, mark)),
 			BPF_EXIT_INSN(),
 		},
-		.result = ACCEPT,
+		.result =  REJECT,
 		.prog_type = BPF_PROG_TYPE_SK_SKB,
+		.errstr = "invalid bpf_context access",
 	},
 	{
 		"check skb->tc_index is writeable by SK_SKB",
@@ -6645,6 +6657,500 @@
 		.errstr = "BPF_END uses reserved fields",
 		.result = REJECT,
 	},
+	{
+		"arithmetic ops make PTR_TO_CTX unusable",
+		.insns = {
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+				      offsetof(struct __sk_buff, data) -
+				      offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "dereference of modified ctx ptr R1 off=68+8, ctx+const is allowed, ctx+const+const is not",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"XDP pkt read, pkt_end mangling, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end mangling, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_ALU64_IMM(BPF_SUB, BPF_REG_3, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' > pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' > pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' > pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end > pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end > pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end > pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' < pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' < pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' < pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end < pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end < pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end < pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' >= pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' >= pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' >= pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end >= pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end >= pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end >= pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' <= pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' <= pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' <= pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end <= pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end <= pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end <= pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
index 6b214b7..247b0a1 100644
--- a/tools/testing/selftests/breakpoints/Makefile
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -2,14 +2,14 @@
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
+TEST_GEN_PROGS := step_after_suspend_test
+
 ifeq ($(ARCH),x86)
-TEST_GEN_PROGS := breakpoint_test
+TEST_GEN_PROGS += breakpoint_test
 endif
 ifneq (,$(filter $(ARCH),aarch64 arm64))
-TEST_GEN_PROGS := breakpoint_test_arm64
+TEST_GEN_PROGS += breakpoint_test_arm64
 endif
 
-TEST_GEN_PROGS += step_after_suspend_test
-
 include ../lib.mk
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
index 2a1cb99..a4fd4c8 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
@@ -1,6 +1,8 @@
 #!/bin/sh
 # description: Register/unregister many kprobe events
 
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
 # ftrace fentry skip size depends on the machine architecture.
 # Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le
 case `uname -m` in
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 7c647f6..f0c0369 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -7,14 +7,17 @@
 include ../lib.mk
 
 all:
-	for DIR in $(SUBDIRS); do		\
+	@for DIR in $(SUBDIRS); do		\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
 		mkdir $$BUILD_TARGET  -p;	\
 		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+		if [ -e $$DIR/$(TEST_PROGS) ]; then
+			rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/;
+		fi
 	done
 
 override define RUN_TESTS
-	$(OUTPUT)/run.sh
+	@cd $(OUTPUT); ./run.sh
 endef
 
 override define INSTALL_RULE
@@ -33,7 +36,7 @@
 endef
 
 override define CLEAN
-	for DIR in $(SUBDIRS); do		\
+	@for DIR in $(SUBDIRS); do		\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
 		mkdir $$BUILD_TARGET  -p;	\
 		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile
index 849a90f..a97e24e 100644
--- a/tools/testing/selftests/intel_pstate/Makefile
+++ b/tools/testing/selftests/intel_pstate/Makefile
@@ -1,7 +1,9 @@
 CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
 LDLIBS := $(LDLIBS) -lm
 
+ifeq (,$(filter $(ARCH),x86))
 TEST_GEN_FILES := msr aperf
+endif
 
 TEST_PROGS := run.sh
 
diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh
index 7868c10..d3ab48f 100755
--- a/tools/testing/selftests/intel_pstate/run.sh
+++ b/tools/testing/selftests/intel_pstate/run.sh
@@ -29,13 +29,12 @@
 
 EVALUATE_ONLY=0
 
-max_cpus=$(($(nproc)-1))
+if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then
+	echo "$0 # Skipped: Test can only run on x86 architectures."
+	exit 0
+fi
 
-# compile programs
-gcc aperf.c -Wall -D_GNU_SOURCE -o aperf  -lm
-[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1
-gcc -o msr msr.c -lm
-[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1
+max_cpus=$(($(nproc)-1))
 
 function run_test () {
 
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 6936166..f65886a 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -6,7 +6,14 @@
 OUTPUT := $(shell pwd)
 endif
 
+# The following are built by lib.mk common compile rules.
+# TEST_CUSTOM_PROGS should be used by tests that require
+# custom build rule and prevent common build rule use.
+# TEST_PROGS are for test shell scripts.
+# TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests
+# and install targets. Common clean doesn't touch them.
 TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
+TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
 all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
@@ -20,17 +27,28 @@
 		test_num=`echo $$test_num+1 | bc`;	\
 		echo "selftests: $$BASENAME_TEST";	\
 		echo "========================================";	\
-		if [ ! -x $$BASENAME_TEST ]; then	\
+		if [ ! -x $$TEST ]; then	\
 			echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\
 			echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \
 		else					\
-			cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests:  $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
+			cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests:  $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
 		fi;					\
 	done;
 endef
 
 run_tests: all
-	$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_PROGS))
+ifneq ($(KBUILD_SRC),)
+	@if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then
+		@rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT)
+	fi
+	@if [ "X$(TEST_PROGS)" != "X" ]; then
+		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS))
+	else
+		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS))
+	fi
+else
+	$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
+endif
 
 define INSTALL_RULE
 	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then					\
@@ -38,10 +56,10 @@
 		echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/";	\
 		rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/;		\
 	fi
-	@if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then					\
+	@if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then					\
 		mkdir -p ${INSTALL_PATH};										\
-		echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/";	\
-		rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/;		\
+		echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/";	\
+		rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/;		\
 	fi
 endef
 
@@ -53,15 +71,20 @@
 endif
 
 define EMIT_TESTS
-	@for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \
+	@for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \
 		BASENAME_TEST=`basename $$TEST`;	\
-		echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
+		echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
 	done;
 endef
 
 emit_tests:
 	$(EMIT_TESTS)
 
+# define if isn't already. It is undefined in make O= case.
+ifeq ($(RM),)
+RM := rm -f
+endif
+
 define CLEAN
 	$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
 endef
@@ -69,6 +92,15 @@
 clean:
 	$(CLEAN)
 
+# When make O= with kselftest target from main level
+# the following aren't defined.
+#
+ifneq ($(KBUILD_SRC),)
+LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)
+COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c
+LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)
+endif
+
 $(OUTPUT)/%:%.c
 	$(LINK.c) $^ $(LDLIBS) -o $@
 
diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh
old mode 100644
new mode 100755
diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index 79a664a..152823b 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -5,8 +5,8 @@
 include ../lib.mk
 
 override define RUN_TESTS
-	@./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
-	@./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
+	@$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
+	@$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
 endef
 
 override define EMIT_TESTS
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 9801253..c612d6e 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -6,3 +6,4 @@
 reuseport_bpf_cpu
 reuseport_bpf_numa
 reuseport_dualstack
+reuseaddr_conflict
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index de1f577..d86bca9 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,9 +5,9 @@
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_GEN_FILES =  socket
-TEST_GEN_FILES += psock_fanout psock_tpacket
-TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_FILES += reuseport_dualstack msg_zerocopy
+TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 40232af..3ab6ec4 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -55,7 +55,7 @@
 #include <unistd.h>
 
 #ifndef SO_EE_ORIGIN_ZEROCOPY
-#define SO_EE_ORIGIN_ZEROCOPY		SO_EE_ORIGIN_UPAGE
+#define SO_EE_ORIGIN_ZEROCOPY		5
 #endif
 
 #ifndef SO_ZEROCOPY
diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
index 4e00568..90cb903 100755
--- a/tools/testing/selftests/net/netdevice.sh
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -178,7 +178,7 @@
 	exit 0
 fi
 
-ip -Version 2>/dev/null >/dev/null
+ip link show 2>/dev/null >/dev/null
 if [ $? -ne 0 ];then
 	echo "SKIP: Could not run test without the ip tool"
 	exit 0
diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c
new file mode 100644
index 0000000..7c5b126
--- /dev/null
+++ b/tools/testing/selftests/net/reuseaddr_conflict.c
@@ -0,0 +1,114 @@
+/*
+ * Test for the regression introduced by
+ *
+ * b9470c27607b ("inet: kill smallest_size and smallest_port")
+ *
+ * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb
+ * when we open the ipv6 conterpart, which is what was happening previously.
+ */
+#include <errno.h>
+#include <error.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#define PORT 9999
+
+int open_port(int ipv6, int any)
+{
+	int fd = -1;
+	int reuseaddr = 1;
+	int v6only = 1;
+	int addrlen;
+	int ret = -1;
+	struct sockaddr *addr;
+	int family = ipv6 ? AF_INET6 : AF_INET;
+
+	struct sockaddr_in6 addr6 = {
+		.sin6_family = AF_INET6,
+		.sin6_port = htons(PORT),
+		.sin6_addr = in6addr_any
+	};
+	struct sockaddr_in addr4 = {
+		.sin_family = AF_INET,
+		.sin_port = htons(PORT),
+		.sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"),
+	};
+
+
+	if (ipv6) {
+		addr = (struct sockaddr*)&addr6;
+		addrlen = sizeof(addr6);
+	} else {
+		addr = (struct sockaddr*)&addr4;
+		addrlen = sizeof(addr4);
+	}
+
+	if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) {
+		perror("socket");
+		goto out;
+	}
+
+	if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only,
+			       sizeof(v6only)) < 0) {
+		perror("setsockopt IPV6_V6ONLY");
+		goto out;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr,
+		       sizeof(reuseaddr)) < 0) {
+		perror("setsockopt SO_REUSEADDR");
+		goto out;
+	}
+
+	if (bind(fd, addr, addrlen) < 0) {
+		perror("bind");
+		goto out;
+	}
+
+	if (any)
+		return fd;
+
+	if (listen(fd, 1) < 0) {
+		perror("listen");
+		goto out;
+	}
+	return fd;
+out:
+	close(fd);
+	return ret;
+}
+
+int main(void)
+{
+	int listenfd;
+	int fd1, fd2;
+
+	fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT);
+	listenfd = open_port(0, 0);
+	if (listenfd < 0)
+		error(1, errno, "Couldn't open listen socket");
+	fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+	fd1 = open_port(0, 1);
+	if (fd1 >= 0)
+		error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+	fprintf(stderr, "Opening in6addr_any:%d\n", PORT);
+	fd1 = open_port(1, 1);
+	if (fd1 < 0)
+		error(1, errno, "Couldn't open ipv6 reuseport");
+	fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+	fd2 = open_port(0, 1);
+	if (fd2 >= 0)
+		error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+	close(fd1);
+	fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT);
+	fd1 = open_port(0, 1);
+	if (fd1 >= 0)
+		error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6");
+	fprintf(stderr, "Success");
+	return 0;
+}
diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
index 00f2866..dd4162f 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -341,7 +341,7 @@
 			return 0;
 		case 'n':
 			t = atoi(optarg);
-			if (t > ARRAY_SIZE(test_cases))
+			if (t >= ARRAY_SIZE(test_cases))
 				error(1, 0, "Invalid test case: %d", t);
 			all_tests = false;
 			test_cases[t].enabled = true;
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index aeb0c80..553d870 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,8 +1,16 @@
-TEST_GEN_PROGS := seccomp_bpf
-CFLAGS += -Wl,-no-as-needed -Wall
-LDFLAGS += -lpthread
+all:
 
 include ../lib.mk
 
-$(TEST_GEN_PROGS): seccomp_bpf.c ../kselftest_harness.h
-	$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+.PHONY: all clean
+
+BINARIES := seccomp_bpf seccomp_benchmark
+CFLAGS += -Wl,-no-as-needed -Wall
+
+seccomp_bpf: seccomp_bpf.c ../kselftest_harness.h
+	$(CC) $(CFLAGS) $(LDFLAGS) -lpthread $< -o $@
+
+TEST_PROGS += $(BINARIES)
+EXTRA_CLEAN := $(BINARIES)
+
+all: $(BINARIES)
diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
new file mode 100644
index 0000000..5838c86
--- /dev/null
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -0,0 +1,99 @@
+/*
+ * Strictly speaking, this is not a test. But it can report during test
+ * runs so relative performace can be measured.
+ */
+#define _GNU_SOURCE
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+
+#define ARRAY_SIZE(a)    (sizeof(a) / sizeof(a[0]))
+
+unsigned long long timing(clockid_t clk_id, unsigned long long samples)
+{
+	pid_t pid, ret;
+	unsigned long long i;
+	struct timespec start, finish;
+
+	pid = getpid();
+	assert(clock_gettime(clk_id, &start) == 0);
+	for (i = 0; i < samples; i++) {
+		ret = syscall(__NR_getpid);
+		assert(pid == ret);
+	}
+	assert(clock_gettime(clk_id, &finish) == 0);
+
+	i = finish.tv_sec - start.tv_sec;
+	i *= 1000000000;
+	i += finish.tv_nsec - start.tv_nsec;
+
+	printf("%lu.%09lu - %lu.%09lu = %llu\n",
+		finish.tv_sec, finish.tv_nsec,
+		start.tv_sec, start.tv_nsec,
+		i);
+
+	return i;
+}
+
+unsigned long long calibrate(void)
+{
+	unsigned long long i;
+
+	printf("Calibrating reasonable sample size...\n");
+
+	for (i = 5; ; i++) {
+		unsigned long long samples = 1 << i;
+
+		/* Find something that takes more than 5 seconds to run. */
+		if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5)
+			return samples;
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+	long ret;
+	unsigned long long samples;
+	unsigned long long native, filtered;
+
+	if (argc > 1)
+		samples = strtoull(argv[1], NULL, 0);
+	else
+		samples = calibrate();
+
+	printf("Benchmarking %llu samples...\n", samples);
+
+	native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid native: %llu ns\n", native);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	assert(ret == 0);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	assert(ret == 0);
+
+	filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW: %llu ns\n", filtered);
+
+	printf("Estimated seccomp overhead per syscall: %llu ns\n",
+		filtered - native);
+
+	if (filtered == native)
+		printf("Trying running again with more samples.\n");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 4d6f92a..24dbf63 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -6,10 +6,18 @@
  */
 
 #include <sys/types.h>
-#include <asm/siginfo.h>
-#define __have_siginfo_t 1
-#define __have_sigval_t 1
-#define __have_sigevent_t 1
+
+/*
+ * glibc 2.26 and later have SIGSYS in siginfo_t. Before that,
+ * we need to use the kernel's siginfo.h file and trick glibc
+ * into accepting it.
+ */
+#if !__GLIBC_PREREQ(2, 26)
+# include <asm/siginfo.h>
+# define __have_siginfo_t 1
+# define __have_sigval_t 1
+# define __have_sigevent_t 1
+#endif
 
 #include <errno.h>
 #include <linux/filter.h>
@@ -68,17 +76,7 @@
 #define SECCOMP_MODE_FILTER 2
 #endif
 
-#ifndef SECCOMP_RET_KILL
-#define SECCOMP_RET_KILL        0x00000000U /* kill the task immediately */
-#define SECCOMP_RET_TRAP        0x00030000U /* disallow and force a SIGSYS */
-#define SECCOMP_RET_ERRNO       0x00050000U /* returns an errno */
-#define SECCOMP_RET_TRACE       0x7ff00000U /* pass to a tracer or disallow */
-#define SECCOMP_RET_ALLOW       0x7fff0000U /* allow */
-
-/* Masks for the return value sections. */
-#define SECCOMP_RET_ACTION      0x7fff0000U
-#define SECCOMP_RET_DATA        0x0000ffffU
-
+#ifndef SECCOMP_RET_ALLOW
 struct seccomp_data {
 	int nr;
 	__u32 arch;
@@ -87,6 +85,70 @@
 };
 #endif
 
+#ifndef SECCOMP_RET_KILL_PROCESS
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD	 0x00000000U /* kill the thread */
+#endif
+#ifndef SECCOMP_RET_KILL
+#define SECCOMP_RET_KILL	 SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP	 0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO	 0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE	 0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_ALLOW	 0x7fff0000U /* allow */
+#endif
+#ifndef SECCOMP_RET_LOG
+#define SECCOMP_RET_LOG		 0x7ffc0000U /* allow after logging */
+#endif
+
+#ifndef __NR_seccomp
+# if defined(__i386__)
+#  define __NR_seccomp 354
+# elif defined(__x86_64__)
+#  define __NR_seccomp 317
+# elif defined(__arm__)
+#  define __NR_seccomp 383
+# elif defined(__aarch64__)
+#  define __NR_seccomp 277
+# elif defined(__hppa__)
+#  define __NR_seccomp 338
+# elif defined(__powerpc__)
+#  define __NR_seccomp 358
+# elif defined(__s390__)
+#  define __NR_seccomp 348
+# else
+#  warning "seccomp syscall number unknown for this architecture"
+#  define __NR_seccomp 0xffff
+# endif
+#endif
+
+#ifndef SECCOMP_SET_MODE_STRICT
+#define SECCOMP_SET_MODE_STRICT 0
+#endif
+
+#ifndef SECCOMP_SET_MODE_FILTER
+#define SECCOMP_SET_MODE_FILTER 1
+#endif
+
+#ifndef SECCOMP_GET_ACTION_AVAIL
+#define SECCOMP_GET_ACTION_AVAIL 2
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_TSYNC
+#define SECCOMP_FILTER_FLAG_TSYNC 1
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_LOG
+#define SECCOMP_FILTER_FLAG_LOG 2
+#endif
+
+#ifndef seccomp
+int seccomp(unsigned int op, unsigned int flags, void *args)
+{
+	errno = 0;
+	return syscall(__NR_seccomp, op, flags, args);
+}
+#endif
+
 #if __BYTE_ORDER == __LITTLE_ENDIAN
 #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
 #elif __BYTE_ORDER == __BIG_ENDIAN
@@ -136,7 +198,7 @@
 	}
 }
 
-/* Tests kernel support by checking for a copy_from_user() fault on * NULL. */
+/* Tests kernel support by checking for a copy_from_user() fault on NULL. */
 TEST(mode_filter_support)
 {
 	long ret;
@@ -342,6 +404,28 @@
 	EXPECT_EQ(EINVAL, errno);
 }
 
+TEST(log_all)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+	long ret;
+	pid_t parent = getppid();
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ASSERT_EQ(0, ret);
+
+	/* getppid() should succeed and be logged (no check for logging) */
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+}
+
 TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS)
 {
 	struct sock_filter filter[] = {
@@ -520,6 +604,117 @@
 	close(fd);
 }
 
+/* This is a thread task to die via seccomp filter violation. */
+void *kill_thread(void *data)
+{
+	bool die = (bool)data;
+
+	if (die) {
+		prctl(PR_GET_SECCOMP, 0, 0, 0, 0);
+		return (void *)SIBLING_EXIT_FAILURE;
+	}
+
+	return (void *)SIBLING_EXIT_UNKILLED;
+}
+
+/* Prepare a thread that will kill itself or both of us. */
+void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process)
+{
+	pthread_t thread;
+	void *status;
+	/* Kill only when calling __NR_prctl. */
+	struct sock_filter filter_thread[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_THREAD),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog_thread = {
+		.len = (unsigned short)ARRAY_SIZE(filter_thread),
+		.filter = filter_thread,
+	};
+	struct sock_filter filter_process[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_PROCESS),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog_process = {
+		.len = (unsigned short)ARRAY_SIZE(filter_process),
+		.filter = filter_process,
+	};
+
+	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0,
+			     kill_process ? &prog_process : &prog_thread));
+
+	/*
+	 * Add the KILL_THREAD rule again to make sure that the KILL_PROCESS
+	 * flag cannot be downgraded by a new filter.
+	 */
+	ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread));
+
+	/* Start a thread that will exit immediately. */
+	ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)false));
+	ASSERT_EQ(0, pthread_join(thread, &status));
+	ASSERT_EQ(SIBLING_EXIT_UNKILLED, (unsigned long)status);
+
+	/* Start a thread that will die immediately. */
+	ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)true));
+	ASSERT_EQ(0, pthread_join(thread, &status));
+	ASSERT_NE(SIBLING_EXIT_FAILURE, (unsigned long)status);
+
+	/*
+	 * If we get here, only the spawned thread died. Let the parent know
+	 * the whole process didn't die (i.e. this thread, the spawner,
+	 * stayed running).
+	 */
+	exit(42);
+}
+
+TEST(KILL_thread)
+{
+	int status;
+	pid_t child_pid;
+
+	child_pid = fork();
+	ASSERT_LE(0, child_pid);
+	if (child_pid == 0) {
+		kill_thread_or_group(_metadata, false);
+		_exit(38);
+	}
+
+	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+	/* If only the thread was killed, we'll see exit 42. */
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(42, WEXITSTATUS(status));
+}
+
+TEST(KILL_process)
+{
+	int status;
+	pid_t child_pid;
+
+	child_pid = fork();
+	ASSERT_LE(0, child_pid);
+	if (child_pid == 0) {
+		kill_thread_or_group(_metadata, true);
+		_exit(38);
+	}
+
+	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+	/* If the entire process was killed, we'll see SIGSYS. */
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_EQ(SIGSYS, WTERMSIG(status));
+}
+
 /* TODO(wad) add 64-bit versus 32-bit arg tests. */
 TEST(arg_out_of_range)
 {
@@ -541,26 +736,30 @@
 	EXPECT_EQ(EINVAL, errno);
 }
 
+#define ERRNO_FILTER(name, errno)					\
+	struct sock_filter _read_filter_##name[] = {			\
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,				\
+			offsetof(struct seccomp_data, nr)),		\
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),	\
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | errno),	\
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),		\
+	};								\
+	struct sock_fprog prog_##name = {				\
+		.len = (unsigned short)ARRAY_SIZE(_read_filter_##name),	\
+		.filter = _read_filter_##name,				\
+	}
+
+/* Make sure basic errno values are correctly passed through a filter. */
 TEST(ERRNO_valid)
 {
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | E2BIG),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
+	ERRNO_FILTER(valid, E2BIG);
 	long ret;
 	pid_t parent = getppid();
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_valid);
 	ASSERT_EQ(0, ret);
 
 	EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -568,26 +767,17 @@
 	EXPECT_EQ(E2BIG, errno);
 }
 
+/* Make sure an errno of zero is correctly handled by the arch code. */
 TEST(ERRNO_zero)
 {
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 0),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
+	ERRNO_FILTER(zero, 0);
 	long ret;
 	pid_t parent = getppid();
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_zero);
 	ASSERT_EQ(0, ret);
 
 	EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -595,26 +785,21 @@
 	EXPECT_EQ(0, read(0, NULL, 0));
 }
 
+/*
+ * The SECCOMP_RET_DATA mask is 16 bits wide, but errno is smaller.
+ * This tests that the errno value gets capped correctly, fixed by
+ * 580c57f10768 ("seccomp: cap SECCOMP_RET_ERRNO data to MAX_ERRNO").
+ */
 TEST(ERRNO_capped)
 {
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 4096),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
+	ERRNO_FILTER(capped, 4096);
 	long ret;
 	pid_t parent = getppid();
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_capped);
 	ASSERT_EQ(0, ret);
 
 	EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -622,6 +807,37 @@
 	EXPECT_EQ(4095, errno);
 }
 
+/*
+ * Filters are processed in reverse order: last applied is executed first.
+ * Since only the SECCOMP_RET_ACTION mask is tested for return values, the
+ * SECCOMP_RET_DATA mask results will follow the most recently applied
+ * matching filter return (and not the lowest or highest value).
+ */
+TEST(ERRNO_order)
+{
+	ERRNO_FILTER(first,  11);
+	ERRNO_FILTER(second, 13);
+	ERRNO_FILTER(third,  12);
+	long ret;
+	pid_t parent = getppid();
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_first);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_second);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_third);
+	ASSERT_EQ(0, ret);
+
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	EXPECT_EQ(-1, read(0, NULL, 0));
+	EXPECT_EQ(12, errno);
+}
+
 FIXTURE_DATA(TRAP) {
 	struct sock_fprog prog;
 };
@@ -676,7 +892,7 @@
 	syscall(__NR_getpid);
 }
 
-static struct siginfo TRAP_info;
+static siginfo_t TRAP_info;
 static volatile int TRAP_nr;
 static void TRAP_action(int nr, siginfo_t *info, void *void_context)
 {
@@ -735,6 +951,7 @@
 
 FIXTURE_DATA(precedence) {
 	struct sock_fprog allow;
+	struct sock_fprog log;
 	struct sock_fprog trace;
 	struct sock_fprog error;
 	struct sock_fprog trap;
@@ -746,6 +963,13 @@
 	struct sock_filter allow_insns[] = {
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 	};
+	struct sock_filter log_insns[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+	};
 	struct sock_filter trace_insns[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
 			offsetof(struct seccomp_data, nr)),
@@ -782,6 +1006,7 @@
 	memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \
 	self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns)
 	FILTER_ALLOC(allow);
+	FILTER_ALLOC(log);
 	FILTER_ALLOC(trace);
 	FILTER_ALLOC(error);
 	FILTER_ALLOC(trap);
@@ -792,6 +1017,7 @@
 {
 #define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter)
 	FILTER_FREE(allow);
+	FILTER_FREE(log);
 	FILTER_FREE(trace);
 	FILTER_FREE(error);
 	FILTER_FREE(trap);
@@ -809,6 +1035,8 @@
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -833,6 +1061,8 @@
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -864,6 +1094,8 @@
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
@@ -885,6 +1117,8 @@
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -910,6 +1144,8 @@
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -931,6 +1167,8 @@
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -949,6 +1187,8 @@
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
@@ -971,6 +1211,8 @@
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	/* Should work just fine. */
@@ -992,12 +1234,54 @@
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	/* Should work just fine. */
 	EXPECT_EQ(parent, syscall(__NR_getppid));
 	/* No ptracer */
 	EXPECT_EQ(-1, syscall(__NR_getpid));
 }
 
+TEST_F(precedence, log_is_fifth)
+{
+	pid_t mypid, parent;
+	long ret;
+
+	mypid = getpid();
+	parent = getppid();
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
+	/* Should work just fine. */
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	/* Should also work just fine */
+	EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
+TEST_F(precedence, log_is_fifth_in_any_order)
+{
+	pid_t mypid, parent;
+	long ret;
+
+	mypid = getpid();
+	parent = getppid();
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+	ASSERT_EQ(0, ret);
+	/* Should work just fine. */
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	/* Should also work just fine */
+	EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
 #ifndef PTRACE_O_TRACESECCOMP
 #define PTRACE_O_TRACESECCOMP	0x00000080
 #endif
@@ -1262,6 +1546,13 @@
 # error "Do not know how to find your architecture's registers and syscalls"
 #endif
 
+/* When the syscall return can't be changed, stub out the tests for it. */
+#ifdef SYSCALL_NUM_RET_SHARE_REG
+# define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(-1, action)
+#else
+# define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(val, action)
+#endif
+
 /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
  * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux).
  */
@@ -1357,7 +1648,7 @@
 #ifdef SYSCALL_NUM_RET_SHARE_REG
 		TH_LOG("Can't modify syscall return on this architecture");
 #else
-		regs.SYSCALL_RET = 1;
+		regs.SYSCALL_RET = EPERM;
 #endif
 
 #ifdef HAVE_GETREGS
@@ -1426,6 +1717,8 @@
 
 	if (nr == __NR_getpid)
 		change_syscall(_metadata, tracee, __NR_getppid);
+	if (nr == __NR_open)
+		change_syscall(_metadata, tracee, -1);
 }
 
 FIXTURE_DATA(TRACE_syscall) {
@@ -1480,6 +1773,28 @@
 		free(self->prog.filter);
 }
 
+TEST_F(TRACE_syscall, ptrace_syscall_redirected)
+{
+	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+	teardown_trace_fixture(_metadata, self->tracer);
+	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+					   true);
+
+	/* Tracer will redirect getpid to getppid. */
+	EXPECT_NE(self->mypid, syscall(__NR_getpid));
+}
+
+TEST_F(TRACE_syscall, ptrace_syscall_dropped)
+{
+	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+	teardown_trace_fixture(_metadata, self->tracer);
+	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+					   true);
+
+	/* Tracer should skip the open syscall, resulting in EPERM. */
+	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_open));
+}
+
 TEST_F(TRACE_syscall, syscall_allowed)
 {
 	long ret;
@@ -1520,13 +1835,8 @@
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
 	ASSERT_EQ(0, ret);
 
-#ifdef SYSCALL_NUM_RET_SHARE_REG
-	/* gettid has been skipped */
-	EXPECT_EQ(-1, syscall(__NR_gettid));
-#else
 	/* gettid has been skipped and an altered return value stored. */
-	EXPECT_EQ(1, syscall(__NR_gettid));
-#endif
+	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid));
 	EXPECT_NE(self->mytid, syscall(__NR_gettid));
 }
 
@@ -1557,6 +1867,7 @@
 	ASSERT_EQ(0, ret);
 
 	/* Tracer will redirect getpid to getppid, and we should see EPERM. */
+	errno = 0;
 	EXPECT_EQ(-1, syscall(__NR_getpid));
 	EXPECT_EQ(EPERM, errno);
 }
@@ -1654,47 +1965,6 @@
 	EXPECT_NE(self->mypid, syscall(__NR_getpid));
 }
 
-#ifndef __NR_seccomp
-# if defined(__i386__)
-#  define __NR_seccomp 354
-# elif defined(__x86_64__)
-#  define __NR_seccomp 317
-# elif defined(__arm__)
-#  define __NR_seccomp 383
-# elif defined(__aarch64__)
-#  define __NR_seccomp 277
-# elif defined(__hppa__)
-#  define __NR_seccomp 338
-# elif defined(__powerpc__)
-#  define __NR_seccomp 358
-# elif defined(__s390__)
-#  define __NR_seccomp 348
-# else
-#  warning "seccomp syscall number unknown for this architecture"
-#  define __NR_seccomp 0xffff
-# endif
-#endif
-
-#ifndef SECCOMP_SET_MODE_STRICT
-#define SECCOMP_SET_MODE_STRICT 0
-#endif
-
-#ifndef SECCOMP_SET_MODE_FILTER
-#define SECCOMP_SET_MODE_FILTER 1
-#endif
-
-#ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
-#endif
-
-#ifndef seccomp
-int seccomp(unsigned int op, unsigned int flags, void *args)
-{
-	errno = 0;
-	return syscall(__NR_seccomp, op, flags, args);
-}
-#endif
-
 TEST(seccomp_syscall)
 {
 	struct sock_filter filter[] = {
@@ -1783,6 +2053,67 @@
 	}
 }
 
+/*
+ * Test detection of known and unknown filter flags. Userspace needs to be able
+ * to check if a filter flag is supported by the current kernel and a good way
+ * of doing that is by attempting to enter filter mode, with the flag bit in
+ * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates
+ * that the flag is valid and EINVAL indicates that the flag is invalid.
+ */
+TEST(detect_seccomp_filter_flags)
+{
+	unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
+				 SECCOMP_FILTER_FLAG_LOG };
+	unsigned int flag, all_flags;
+	int i;
+	long ret;
+
+	/* Test detection of known-good filter flags */
+	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+		flag = flags[i];
+		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+		ASSERT_NE(ENOSYS, errno) {
+			TH_LOG("Kernel does not support seccomp syscall!");
+		}
+		EXPECT_EQ(-1, ret);
+		EXPECT_EQ(EFAULT, errno) {
+			TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!",
+			       flag);
+		}
+
+		all_flags |= flag;
+	}
+
+	/* Test detection of all known-good filter flags */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EFAULT, errno) {
+		TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+		       all_flags);
+	}
+
+	/* Test detection of an unknown filter flag */
+	flag = -1;
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!",
+		       flag);
+	}
+
+	/*
+	 * Test detection of an unknown filter flag that may simply need to be
+	 * added to this test
+	 */
+	flag = flags[ARRAY_SIZE(flags) - 1] << 1;
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?",
+		       flag);
+	}
+}
+
 TEST(TSYNC_first)
 {
 	struct sock_filter filter[] = {
@@ -2421,6 +2752,99 @@
 		_metadata->passed = 0;
 }
 
+TEST_SIGNAL(filter_flag_log, SIGSYS)
+{
+	struct sock_filter allow_filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_filter kill_filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog allow_prog = {
+		.len = (unsigned short)ARRAY_SIZE(allow_filter),
+		.filter = allow_filter,
+	};
+	struct sock_fprog kill_prog = {
+		.len = (unsigned short)ARRAY_SIZE(kill_filter),
+		.filter = kill_filter,
+	};
+	long ret;
+	pid_t parent = getppid();
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	/* Verify that the FILTER_FLAG_LOG flag isn't accepted in strict mode */
+	ret = seccomp(SECCOMP_SET_MODE_STRICT, SECCOMP_FILTER_FLAG_LOG,
+		      &allow_prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
+	EXPECT_NE(0, ret) {
+		TH_LOG("Kernel accepted FILTER_FLAG_LOG flag in strict mode!");
+	}
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Kernel returned unexpected errno for FILTER_FLAG_LOG flag in strict mode!");
+	}
+
+	/* Verify that a simple, permissive filter can be added with no flags */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog);
+	EXPECT_EQ(0, ret);
+
+	/* See if the same filter can be added with the FILTER_FLAG_LOG flag */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+		      &allow_prog);
+	ASSERT_NE(EINVAL, errno) {
+		TH_LOG("Kernel does not support the FILTER_FLAG_LOG flag!");
+	}
+	EXPECT_EQ(0, ret);
+
+	/* Ensure that the kill filter works with the FILTER_FLAG_LOG flag */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+		      &kill_prog);
+	EXPECT_EQ(0, ret);
+
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	/* getpid() should never return. */
+	EXPECT_EQ(0, syscall(__NR_getpid));
+}
+
+TEST(get_action_avail)
+{
+	__u32 actions[] = { SECCOMP_RET_KILL_THREAD, SECCOMP_RET_TRAP,
+			    SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE,
+			    SECCOMP_RET_LOG,   SECCOMP_RET_ALLOW };
+	__u32 unknown_action = 0x10000000U;
+	int i;
+	long ret;
+
+	ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[0]);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
+	ASSERT_NE(EINVAL, errno) {
+		TH_LOG("Kernel does not support SECCOMP_GET_ACTION_AVAIL operation!");
+	}
+	EXPECT_EQ(ret, 0);
+
+	for (i = 0; i < ARRAY_SIZE(actions); i++) {
+		ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[i]);
+		EXPECT_EQ(ret, 0) {
+			TH_LOG("Expected action (0x%X) not available!",
+			       actions[i]);
+		}
+	}
+
+	/* Check that an unknown action is handled properly (EOPNOTSUPP) */
+	ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &unknown_action);
+	EXPECT_EQ(ret, -1);
+	EXPECT_EQ(errno, EOPNOTSUPP);
+}
+
 /*
  * TODO:
  * - add microbenchmarks
@@ -2429,6 +2853,8 @@
  * - endianness checking when appropriate
  * - 64-bit arg prodding
  * - arch value testing (x86 modes especially)
+ * - verify that FILTER_FLAG_LOG filters generate log messages
+ * - verify that RET_LOG generates log messages
  * - ...
  */
 
diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c
index 7d406c3..97bb150 100644
--- a/tools/testing/selftests/sigaltstack/sas.c
+++ b/tools/testing/selftests/sigaltstack/sas.c
@@ -39,7 +39,11 @@
 	stack_t stk;
 	struct stk_data *p;
 
+#if __s390x__
+	register unsigned long sp asm("%15");
+#else
 	register unsigned long sp asm("sp");
+#endif
 
 	if (sp < (unsigned long)sstack ||
 			sp >= (unsigned long)sstack + SIGSTKSZ) {
diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile
index 4981c6b..8e04d0a 100644
--- a/tools/testing/selftests/sync/Makefile
+++ b/tools/testing/selftests/sync/Makefile
@@ -2,12 +2,16 @@
 CFLAGS += -I../../../../usr/include/
 LDFLAGS += -pthread
 
-TEST_PROGS = sync_test
-
-all: $(TEST_PROGS)
+.PHONY: all clean
 
 include ../lib.mk
 
+# lib.mk TEST_CUSTOM_PROGS var is for custom tests that need special
+# build rules. lib.mk will run and install them.
+
+TEST_CUSTOM_PROGS := $(OUTPUT)/sync_test
+all: $(TEST_CUSTOM_PROGS)
+
 OBJS = sync_test.o sync.o
 
 TESTS += sync_alloc.o
@@ -18,6 +22,16 @@
 TESTS += sync_stress_consumer.o
 TESTS += sync_stress_merge.o
 
-sync_test: $(OBJS) $(TESTS)
+OBJS := $(patsubst %,$(OUTPUT)/%,$(OBJS))
+TESTS := $(patsubst %,$(OUTPUT)/%,$(TESTS))
 
-EXTRA_CLEAN := sync_test $(OBJS) $(TESTS)
+$(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS)
+	$(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS)
+
+$(OBJS): $(OUTPUT)/%.o: %.c
+	$(CC) -c $^ -o $@
+
+$(TESTS): $(OUTPUT)/%.o: %.c
+	$(CC) -c $^ -o $@
+
+EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS)
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index c727b96..5fa02d8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -17,5 +17,26 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "d052",
+        "name": "Add 1M filters with the same action",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress",
+            "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000"
+        ],
+        "cmdUnderTest": "$TC -b $BATCH_FILE",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000 bind 1000000",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress",
+            "/bin/rm $BATCH_FILE"
+        ]
     }
-]
\ No newline at end of file
+]
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index cd61b78..a8981c5 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -88,7 +88,7 @@
             exit(1)
 
 
-def test_runner(filtered_tests):
+def test_runner(filtered_tests, args):
     """
     Driver function for the unit tests.
 
@@ -105,6 +105,8 @@
     for tidx in testlist:
         result = True
         tresult = ""
+        if "flower" in tidx["category"] and args.device == None:
+            continue
         print("Test " + tidx["id"] + ": " + tidx["name"])
         prepare_env(tidx["setup"])
         (p, procout) = exec_cmd(tidx["cmdUnderTest"])
@@ -150,7 +152,11 @@
         exec_cmd(cmd, False)
         cmd = 'ip link set $DEV0 up'
         exec_cmd(cmd, False)
-        cmd = 'ip -s $NS link set $DEV1 up'
+        cmd = 'ip -n $NS link set $DEV1 up'
+        exec_cmd(cmd, False)
+        cmd = 'ip link set $DEV2 netns $NS'
+        exec_cmd(cmd, False)
+        cmd = 'ip -n $NS link set $DEV2 up'
         exec_cmd(cmd, False)
 
 
@@ -211,7 +217,8 @@
                         help='Execute the single test case with specified ID')
     parser.add_argument('-i', '--id', action='store_true', dest='gen_id',
                         help='Generate ID numbers for new test cases')
-    return parser
+    parser.add_argument('-d', '--device',
+                        help='Execute the test case in flower category')
     return parser
 
 
@@ -225,6 +232,8 @@
 
     if args.path != None:
          NAMES['TC'] = args.path
+    if args.device != None:
+         NAMES['DEV2'] = args.device
     if not os.path.isfile(NAMES['TC']):
         print("The specified tc path " + NAMES['TC'] + " does not exist.")
         exit(1)
@@ -381,14 +390,17 @@
             if (len(alltests) == 0):
                 print("Cannot find a test case with ID matching " + target_id)
                 exit(1)
-        catresults = test_runner(alltests)
+        catresults = test_runner(alltests, args)
         print("All test results: " + "\n\n" + catresults)
     elif (len(target_category) > 0):
+        if (target_category == "flower") and args.device == None:
+            print("Please specify a NIC device (-d) to run category flower")
+            exit(1)
         if (target_category not in ucat):
             print("Specified category is not present in this file.")
             exit(1)
         else:
-            catresults = test_runner(testcases[target_category])
+            catresults = test_runner(testcases[target_category], args)
             print("Category " + target_category + "\n\n" + catresults)
 
     ns_destroy()
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
new file mode 100755
index 0000000..707c6bf
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -0,0 +1,62 @@
+#!/usr/bin/python3
+
+"""
+tdc_batch.py - a script to generate TC batch file
+
+Copyright (C) 2017 Chris Mi <chrism@mellanox.com>
+"""
+
+import argparse
+
+parser = argparse.ArgumentParser(description='TC batch file generator')
+parser.add_argument("device", help="device name")
+parser.add_argument("file", help="batch file name")
+parser.add_argument("-n", "--number", type=int,
+                    help="how many lines in batch file")
+parser.add_argument("-o", "--skip_sw",
+                    help="skip_sw (offload), by default skip_hw",
+                    action="store_true")
+parser.add_argument("-s", "--share_action",
+                    help="all filters share the same action",
+                    action="store_true")
+parser.add_argument("-p", "--prio",
+                    help="all filters have different prio",
+                    action="store_true")
+args = parser.parse_args()
+
+device = args.device
+file = open(args.file, 'w')
+
+number = 1
+if args.number:
+    number = args.number
+
+skip = "skip_hw"
+if args.skip_sw:
+    skip = "skip_sw"
+
+share_action = ""
+if args.share_action:
+    share_action = "index 1"
+
+prio = "prio 1"
+if args.prio:
+    prio = ""
+    if number > 0x4000:
+        number = 0x4000
+
+index = 0
+for i in range(0x100):
+    for j in range(0x100):
+        for k in range(0x100):
+            mac = ("%02x:%02x:%02x" % (i, j, k))
+            src_mac = "e4:11:00:" + mac
+            dst_mac = "e4:12:00:" + mac
+            cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s "
+                   "src_mac %s dst_mac %s action drop %s" %
+                   (device, prio, skip, src_mac, dst_mac, share_action))
+            file.write("%s\n" % cmd)
+            index += 1
+            if index >= number:
+                file.close()
+                exit(0)
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index 0108737..b635251 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -12,6 +12,8 @@
           # Name of veth devices to be created for the namespace
           'DEV0': 'v0p0',
           'DEV1': 'v0p1',
+          'DEV2': '',
+          'BATCH_FILE': './batch.txt',
           # Name of the namespace to use
           'NS': 'tcut'
         }
diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c
index 9c92b7b..50da454 100644
--- a/tools/testing/selftests/timers/set-timer-lat.c
+++ b/tools/testing/selftests/timers/set-timer-lat.c
@@ -143,7 +143,8 @@
 			printf("%-22s %s missing CAP_WAKE_ALARM?    : [UNSUPPORTED]\n",
 					clockstring(clock_id),
 					flags ? "ABSTIME":"RELTIME");
-			return 0;
+			/* Indicate timer isn't set, so caller doesn't wait */
+			return 1;
 		}
 		printf("%s - timer_create() failed\n", clockstring(clock_id));
 		return -1;
@@ -213,8 +214,9 @@
 	int err;
 
 	err = setup_timer(clock_id, flags, interval, &tm1);
+	/* Unsupported case - return 0 to not fail the test */
 	if (err)
-		return err;
+		return err == 1 ? 0 : err;
 
 	while (alarmcount < 5)
 		sleep(1);
@@ -228,18 +230,17 @@
 	timer_t tm1;
 	const int interval = 0;
 	struct timeval timeout;
-	fd_set fds;
 	int err;
 
 	err = setup_timer(clock_id, flags, interval, &tm1);
+	/* Unsupported case - return 0 to not fail the test */
 	if (err)
-		return err;
+		return err == 1 ? 0 : err;
 
 	memset(&timeout, 0, sizeof(timeout));
 	timeout.tv_sec = 5;
-	FD_ZERO(&fds);
 	do {
-		err = select(FD_SETSIZE, &fds, NULL, NULL, &timeout);
+		err = select(0, NULL, NULL, NULL, &timeout);
 	} while (err == -1 && errno == EINTR);
 
 	timer_delete(tm1);
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index a2c53a3..de2f9ec 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -397,7 +397,7 @@
 	}
 }
 
-static int copy_page(int ufd, unsigned long offset)
+static int __copy_page(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_copy uffdio_copy;
 
@@ -418,7 +418,7 @@
 		fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n",
 			uffdio_copy.copy), exit(1);
 	} else {
-		if (test_uffdio_copy_eexist) {
+		if (test_uffdio_copy_eexist && retry) {
 			test_uffdio_copy_eexist = false;
 			retry_copy_page(ufd, &uffdio_copy, offset);
 		}
@@ -427,6 +427,16 @@
 	return 0;
 }
 
+static int copy_page_retry(int ufd, unsigned long offset)
+{
+	return __copy_page(ufd, offset, true);
+}
+
+static int copy_page(int ufd, unsigned long offset)
+{
+	return __copy_page(ufd, offset, false);
+}
+
 static void *uffd_poll_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
@@ -544,7 +554,7 @@
 	for (page_nr = cpu * nr_pages_per_cpu;
 	     page_nr < (cpu+1) * nr_pages_per_cpu;
 	     page_nr++)
-		copy_page(uffd, page_nr * page_size);
+		copy_page_retry(uffd, page_nr * page_size);
 
 	return NULL;
 }
@@ -779,7 +789,7 @@
 	}
 }
 
-static int uffdio_zeropage(int ufd, unsigned long offset)
+static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_zeropage uffdio_zeropage;
 	int ret;
@@ -814,7 +824,7 @@
 			fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
 				uffdio_zeropage.zeropage), exit(1);
 		} else {
-			if (test_uffdio_zeropage_eexist) {
+			if (test_uffdio_zeropage_eexist && retry) {
 				test_uffdio_zeropage_eexist = false;
 				retry_uffdio_zeropage(ufd, &uffdio_zeropage,
 						      offset);
@@ -830,6 +840,11 @@
 	return 0;
 }
 
+static int uffdio_zeropage(int ufd, unsigned long offset)
+{
+	return __uffdio_zeropage(ufd, offset, false);
+}
+
 /* exercise UFFDIO_ZEROPAGE */
 static int userfaultfd_zeropage_test(void)
 {
diff --git a/tools/testing/selftests/watchdog/Makefile b/tools/testing/selftests/watchdog/Makefile
index f863c66..ee06851 100644
--- a/tools/testing/selftests/watchdog/Makefile
+++ b/tools/testing/selftests/watchdog/Makefile
@@ -1,8 +1,3 @@
-TEST_PROGS := watchdog-test
-
-all: $(TEST_PROGS)
+TEST_GEN_PROGS := watchdog-test
 
 include ../lib.mk
-
-clean:
-	rm -fr $(TEST_PROGS)
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 97f187e..0a74a20 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -20,7 +20,7 @@
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
-CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
+CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
 
 UNAME_M := $(shell uname -m)
 CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index c608ab4..f2ac53a 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -565,8 +565,6 @@
 {
 	if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE))
 		return -EINVAL;
-	if (args->gsi >= KVM_MAX_IRQ_ROUTES)
-		return -EINVAL;
 
 	if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
 		return kvm_irqfd_deassign(kvm, args);