Merge tag 'kvm-arm-for-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/ARM updates for 4.6 - VHE support so that we can run the kernel at EL2 on ARMv8.1 systems - PMU support for guests - 32bit world switch rewritten in C - Various optimizations to the vgic save/restore code Conflicts: include/uapi/linux/kvm.h
author: Paolo Bonzini <pbonzini@redhat.com> 2016-03-09 11:50:42 +0100
committer: Paolo Bonzini <pbonzini@redhat.com> 2016-03-09 11:50:42 +0100
commit: ab92f30875a7ec3e84644a5494febd8901e66742 (patch)
tree: 5254eb36b20b0d1c584c15d0bf3d6a5a9c1bb451
parent: bb9eadf0c35f2e7eb5ca6468f46ebb7473b85537 (diff)
parent: b40c4892d175874d118860c8282a85ee7b64bcbb (diff)
download: linux-ab92f30875a7ec3e84644a5494febd8901e66742.tar.bz2
863 files changed, 14117 insertions, 7886 deletions
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index e8d25e784214..ff49cf901148 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -7,7 +7,7 @@ This is the authoritative documentation on the design, interface and
 conventions of cgroup v2.  It describes all userland-visible aspects
 of cgroup including core and specific controller behaviors.  All
 future changes must be reflected in this document.  Documentation for
-v1 is available under Documentation/cgroup-legacy/.
+v1 is available under Documentation/cgroup-v1/.
 
 CONTENTS
 
diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
index ace05992a262..20df350b9ef3 100644
--- a/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
@@ -30,7 +30,7 @@ that they are defined using standard clock bindings with following
 clock-output-names:
  - "xin24m" - crystal input - required,
  - "ext_i2s" - external I2S clock - optional,
- - "ext_gmac" - external GMAC clock - optional
+ - "rmii_clkin" - external EMAC clock - optional
 
 Example: Clock controller node:
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
index 7803e77d85cb..007a5b46256a 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
@@ -24,9 +24,8 @@ Main node required properties:
 		1 = edge triggered
 		4 = level triggered
 
-  Cells 4 and beyond are reserved for future use. When the 1st cell
-  has a value of 0 or 1, cells 4 and beyond act as padding, and may be
-  ignored. It is recommended that padding cells have a value of 0.
+  Cells 4 and beyond are reserved for future use and must have a value
+  of 0 if present.
 
 - reg : Specifies base physical address(s) and size of the GIC
   registers, in the following order:
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index 81a9f9e6b45f..c8ac222eac67 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -82,8 +82,8 @@ Example:
 				  "ch16", "ch17", "ch18", "ch19",
 				  "ch20", "ch21", "ch22", "ch23",
 				  "ch24";
-		clocks = <&mstp8_clks R8A7795_CLK_ETHERAVB>;
-		power-domains = <&cpg_clocks>;
+		clocks = <&cpg CPG_MOD 812>;
+		power-domains = <&cpg>;
 		phy-mode = "rgmii-id";
 		phy-handle = <&phy0>;
 
diff --git a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
index 4e8b90e43dd8..07a75094c5a8 100644
--- a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
+++ b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
@@ -8,6 +8,7 @@ OHCI and EHCI controllers.
 Required properties:
 - compatible: "renesas,pci-r8a7790" for the R8A7790 SoC;
 	      "renesas,pci-r8a7791" for the R8A7791 SoC;
+	      "renesas,pci-r8a7793" for the R8A7793 SoC;
 	      "renesas,pci-r8a7794" for the R8A7794 SoC;
 	      "renesas,pci-rcar-gen2" for a generic R-Car Gen2 compatible device
 
diff --git a/Documentation/devicetree/bindings/pci/rcar-pci.txt b/Documentation/devicetree/bindings/pci/rcar-pci.txt
index 558fe528ae19..6cf99690eef9 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci.txt
+++ b/Documentation/devicetree/bindings/pci/rcar-pci.txt
@@ -4,6 +4,7 @@ Required properties:
 compatible: "renesas,pcie-r8a7779" for the R8A7779 SoC;
 	    "renesas,pcie-r8a7790" for the R8A7790 SoC;
 	    "renesas,pcie-r8a7791" for the R8A7791 SoC;
+	    "renesas,pcie-r8a7793" for the R8A7793 SoC;
 	    "renesas,pcie-r8a7795" for the R8A7795 SoC;
 	    "renesas,pcie-rcar-gen2" for a generic R-Car Gen2 compatible device.
 
diff --git a/Documentation/devicetree/bindings/regulator/tps65217.txt b/Documentation/devicetree/bindings/regulator/tps65217.txt
index d18109657da6..4f05d208c95c 100644
--- a/Documentation/devicetree/bindings/regulator/tps65217.txt
+++ b/Documentation/devicetree/bindings/regulator/tps65217.txt
@@ -26,11 +26,7 @@ Example:
 		ti,pmic-shutdown-controller;
 
 		regulators {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
 			dcdc1_reg: dcdc1 {
-				reg = <0>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <1800000>;
 				regulator-boot-on;
@@ -38,7 +34,6 @@ Example:
 			};
 
 			dcdc2_reg: dcdc2 {
-				reg = <1>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -46,7 +41,6 @@ Example:
 			};
 
 			dcdc3_reg: dcc3 {
-				reg = <2>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <1500000>;
 				regulator-boot-on;
@@ -54,7 +48,6 @@ Example:
 			};
 
 			ldo1_reg: ldo1 {
-				reg = <3>;
 				regulator-min-microvolt = <1000000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -62,7 +55,6 @@ Example:
 			};
 
 			ldo2_reg: ldo2 {
-				reg = <4>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -70,7 +62,6 @@ Example:
 			};
 
 			ldo3_reg: ldo3 {
-				reg = <5>;
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -78,7 +69,6 @@ Example:
 			};
 
 			ldo4_reg: ldo4 {
-				reg = <6>;
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
index ac2fcd6ff4b8..1068ffce9f91 100644
--- a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
@@ -14,6 +14,10 @@ Required properties:
   interrupt number is the rtc alarm interrupt and second interrupt number
   is the rtc tick interrupt. The number of cells representing a interrupt
   depends on the parent interrupt controller.
+- clocks: Must contain a list of phandle and clock specifier for the rtc
+          and source clocks.
+- clock-names: Must contain "rtc" and "rtc_src" entries sorted in the
+               same order as the clocks property.
 
 Example:
 
@@ -21,4 +25,6 @@ Example:
 		compatible = "samsung,s3c6410-rtc";
 		reg = <0x10070000 0x100>;
 		interrupts = <44 0 45 0>;
+		clocks = <&clock CLK_RTC>, <&s2mps11_osc S2MPS11_CLK_AP>;
+		clock-names = "rtc", "rtc_src";
 	};
diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
index 35ae1fb3537f..ed94c217c98d 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
@@ -9,7 +9,7 @@ Optional properties:
 - fsl,uart-has-rtscts : Indicate the uart has rts and cts
 - fsl,irda-mode : Indicate the uart supports irda mode
 - fsl,dte-mode : Indicate the uart works in DTE mode. The uart works
-                  is DCE mode by default.
+                  in DCE mode by default.
 
 Note: Each uart controller should have an alias correctly numbered
 in "aliases" node.
diff --git a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
index ce55c0a6f757..4da41bf1888e 100644
--- a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
@@ -30,6 +30,8 @@ The compatible list for this generic sound card currently:
  "fsl,imx-audio-sgtl5000"
  (compatible with Documentation/devicetree/bindings/sound/imx-audio-sgtl5000.txt)
 
+ "fsl,imx-audio-wm8960"
+
 Required properties:
 
   - compatible		: Contains one of entries in the compatible list.
diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
index 332e625f6ed0..e5ee3f159893 100644
--- a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
@@ -1,8 +1,9 @@
 * Renesas R-Car Thermal
 
 Required properties:
-- compatible		: "renesas,thermal-<soctype>", "renesas,rcar-thermal"
-			  as fallback.
+- compatible		: "renesas,thermal-<soctype>",
+			   "renesas,rcar-gen2-thermal" (with thermal-zone) or
+			   "renesas,rcar-thermal" (without thermal-zone) as fallback.
 			  Examples with soctypes are:
 			    - "renesas,thermal-r8a73a4" (R-Mobile APE6)
 			    - "renesas,thermal-r8a7779" (R-Car H1)
@@ -36,3 +37,35 @@ thermal@e61f0000 {
 		0xe61f0300 0x38>;
 	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
 };
+
+Example (with thermal-zone):
+
+thermal-zones {
+	cpu_thermal: cpu-thermal {
+		polling-delay-passive	= <1000>;
+		polling-delay		= <5000>;
+
+		thermal-sensors = <&thermal>;
+
+		trips {
+			cpu-crit {
+				temperature	= <115000>;
+				hysteresis	= <0>;
+				type		= "critical";
+			};
+		};
+		cooling-maps {
+		};
+	};
+};
+
+thermal: thermal@e61f0000 {
+	compatible =	"renesas,thermal-r8a7790",
+			"renesas,rcar-gen2-thermal",
+			"renesas,rcar-thermal";
+	reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
+	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
+	power-domains = <&cpg_clocks>;
+	#thermal-sensor-cells = <0>;
+};
diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt
index c477af086e65..686a64bba775 100644
--- a/Documentation/filesystems/efivarfs.txt
+++ b/Documentation/filesystems/efivarfs.txt
@@ -14,3 +14,10 @@ filesystem.
 efivarfs is typically mounted like this,
 
 	mount -t efivarfs none /sys/firmware/efi/efivars
+
+Due to the presence of numerous firmware bugs where removing non-standard
+UEFI variables causes the system firmware to fail to POST, efivarfs
+files that are not well-known standardized variables are created
+as immutable files.  This doesn't prevent removal - "chattr -i" will work -
+but it does prevent this kind of failure from being accomplished
+accidentally.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 551ecf09c8dd..9a53c929f017 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -4235,6 +4235,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default value of this parameter is determined by
 			the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
 
+	workqueue.debug_force_rr_cpu
+			Workqueue used to implicitly guarantee that work
+			items queued without explicit CPU specified are put
+			on the local CPU.  This guarantee is no longer true
+			and while local CPU is still preferred work items
+			may be put on foreign CPUs.  This debug option
+			forces round-robin CPU selection to flush out
+			usages which depend on the now broken guarantee.
+			When enabled, memory and cache locality will be
+			impacted.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index 767392ffd31e..a484d2c109d7 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -1,9 +1,7 @@
 		High Precision Event Timer Driver for Linux
 
 The High Precision Event Timer (HPET) hardware follows a specification
-by Intel and Microsoft which can be found at
-
-	http://www.intel.com/hardwaredesign/hpetspec_1.pdf
+by Intel and Microsoft, revision 1.
 
 Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
 and up to 32 comparators.  Normally three or more comparators are provided,
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 335fe889efd9..4d0542c5206b 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2507,8 +2507,9 @@ struct kvm_create_device {
 
 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
-Type: device ioctl, vm ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+Type: device ioctl, vm ioctl, vcpu ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
@@ -2533,8 +2534,9 @@ struct kvm_device_attr {
 
 4.81 KVM_HAS_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
-Type: device ioctl, vm ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+Type: device ioctl, vm ioctl, vcpu ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
@@ -2577,6 +2579,8 @@ Possible features:
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
 	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
 	  Depends on KVM_CAP_ARM_PSCI_0_2.
+	- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
+	  Depends on KVM_CAP_ARM_PMU_V3.
 
 
 4.83 KVM_ARM_PREFERRED_TARGET
diff --git a/Documentation/virtual/kvm/devices/vcpu.txt b/Documentation/virtual/kvm/devices/vcpu.txt
new file mode 100644
index 000000000000..c04165868faf
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/vcpu.txt
@@ -0,0 +1,33 @@
+Generic vcpu interface
+====================================
+
+The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct
+kvm_device_attr as other devices, but targets VCPU-wide settings and controls.
+
+The groups and attributes per virtual cpu, if any, are architecture specific.
+
+1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL
+Architectures: ARM64
+
+1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ
+Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a
+            pointer to an int
+Returns: -EBUSY: The PMU overflow interrupt is already set
+         -ENXIO: The overflow interrupt not set when attempting to get it
+         -ENODEV: PMUv3 not supported
+         -EINVAL: Invalid PMU overflow interrupt number supplied
+
+A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt
+number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt
+type must be same for each vcpu. As a PPI, the interrupt number is the same for
+all vcpus, while as an SPI it must be a separate number per vcpu.
+
+1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT
+Parameters: no additional parameter in kvm_device_attr.addr
+Returns: -ENODEV: PMUv3 not supported
+         -ENXIO: PMUv3 not properly configured as required prior to calling this
+                 attribute
+         -EBUSY: PMUv3 already initialized
+
+Request the initialization of the PMUv3.
diff --git a/MAINTAINERS b/MAINTAINERS
index 7f1fa4ff300a..da3e4d8016d0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -920,17 +920,24 @@ M:	Emilio López <emilio@elopez.com.ar>
 S:	Maintained
 F:	drivers/clk/sunxi/
 
-ARM/Amlogic MesonX SoC support
+ARM/Amlogic Meson SoC support
 M:	Carlo Caione <carlo@caione.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-meson@googlegroups.com
+W:	http://linux-meson.com/
 S:	Maintained
-F:	drivers/media/rc/meson-ir.c
-N:	meson[x68]
+F:	arch/arm/mach-meson/
+F:	arch/arm/boot/dts/meson*
+N:	meson
 
 ARM/Annapurna Labs ALPINE ARCHITECTURE
 M:	Tsahee Zidenberg <tsahee@annapurnalabs.com>
+M:	Antoine Tenart <antoine.tenart@free-electrons.com>
 S:	Maintained
 F:	arch/arm/mach-alpine/
+F:	arch/arm/boot/dts/alpine*
+F:	arch/arm64/boot/dts/al/
+F:	drivers/*/*alpine*
 
 ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT
 M:	Nicolas Ferre <nicolas.ferre@atmel.com>
@@ -1442,8 +1449,8 @@ S:	Maintained
 ARM/RENESAS ARM64 ARCHITECTURE
 M:	Simon Horman <horms@verge.net.au>
 M:	Magnus Damm <magnus.damm@gmail.com>
-L:	linux-sh@vger.kernel.org
-Q:	http://patchwork.kernel.org/project/linux-sh/list/
+L:	linux-renesas-soc@vger.kernel.org
+Q:	http://patchwork.kernel.org/project/linux-renesas-soc/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next
 S:	Supported
 F:	arch/arm64/boot/dts/renesas/
@@ -2362,14 +2369,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rpi/linux-rpi.git
 S:	Maintained
 N:	bcm2835
 
-BROADCOM BCM33XX MIPS ARCHITECTURE
-M:	Kevin Cernekee <cernekee@gmail.com>
-L:	linux-mips@linux-mips.org
-S:	Maintained
-F:	arch/mips/bcm3384/*
-F:	arch/mips/include/asm/mach-bcm3384/*
-F:	arch/mips/kernel/*bmips*
-
 BROADCOM BCM47XX MIPS ARCHITECTURE
 M:	Hauke Mehrtens <hauke@hauke-m.de>
 M:	Rafał Miłecki <zajec5@gmail.com>
@@ -3452,7 +3451,6 @@ F:	drivers/usb/dwc2/
 DESIGNWARE USB3 DRD IP DRIVER
 M:	Felipe Balbi <balbi@kernel.org>
 L:	linux-usb@vger.kernel.org
-L:	linux-omap@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
 S:	Maintained
 F:	drivers/usb/dwc3/
@@ -6136,7 +6134,7 @@ F:	include/uapi/linux/sunrpc/
 
 KERNEL SELFTEST FRAMEWORK
 M:	Shuah Khan <shuahkh@osg.samsung.com>
-L:	linux-api@vger.kernel.org
+L:	linux-kselftest@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/shuah/linux-kselftest
 S:	Maintained
 F:	tools/testing/selftests
@@ -7362,7 +7360,7 @@ F:	drivers/tty/isicom.c
 F:	include/linux/isicom.h
 
 MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER
-M:	Felipe Balbi <balbi@kernel.org>
+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
@@ -7694,13 +7692,13 @@ S:	Maintained
 F:	arch/nios2/
 
 NOKIA N900 POWER SUPPLY DRIVERS
-M:	Pali Rohár <pali.rohar@gmail.com>
-S:	Maintained
+R:	Pali Rohár <pali.rohar@gmail.com>
 F:	include/linux/power/bq2415x_charger.h
 F:	include/linux/power/bq27xxx_battery.h
 F:	include/linux/power/isp1704_charger.h
 F:	drivers/power/bq2415x_charger.c
 F:	drivers/power/bq27xxx_battery.c
+F:	drivers/power/bq27xxx_battery_i2c.c
 F:	drivers/power/isp1704_charger.c
 F:	drivers/power/rx51_battery.c
 
@@ -7931,11 +7929,9 @@ F:	drivers/media/platform/omap3isp/
 F:	drivers/staging/media/omap4iss/
 
 OMAP USB SUPPORT
-M:	Felipe Balbi <balbi@kernel.org>
 L:	linux-usb@vger.kernel.org
 L:	linux-omap@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/*/*omap*
 F:	arch/arm/*omap*/usb*
 
@@ -9566,6 +9562,12 @@ M:	Andreas Noever <andreas.noever@gmail.com>
 S:	Maintained
 F:	drivers/thunderbolt/
 
+TI BQ27XXX POWER SUPPLY DRIVER
+R:	Andrew F. Davis <afd@ti.com>
+F:	include/linux/power/bq27xxx_battery.h
+F:	drivers/power/bq27xxx_battery.c
+F:	drivers/power/bq27xxx_battery_i2c.c
+
 TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER
 M:	John Stultz <john.stultz@linaro.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
@@ -9787,10 +9789,11 @@ S:	Supported
 F:	drivers/scsi/be2iscsi/
 
 Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER
-M:	Sathya Perla <sathya.perla@avagotech.com>
-M:	Ajit Khaparde <ajit.khaparde@avagotech.com>
-M:	Padmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
-M:	Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
+M:	Sathya Perla <sathya.perla@broadcom.com>
+M:	Ajit Khaparde <ajit.khaparde@broadcom.com>
+M:	Padmanabh Ratnakar <padmanabh.ratnakar@broadcom.com>
+M:	Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
+M:	Somnath Kotur <somnath.kotur@broadcom.com>
 L:	netdev@vger.kernel.org
 W:	http://www.emulex.com
 S:	Supported
@@ -12020,7 +12023,6 @@ F:	arch/arm64/xen/
 F:	arch/arm64/include/asm/xen/
 
 XEN NETWORK BACKEND DRIVER
-M:	Ian Campbell <ian.campbell@citrix.com>
 M:	Wei Liu <wei.liu2@citrix.com>
 L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index 682840850f58..af6e5f893d56 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 5
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc6
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 76dde9db7934..8a188bc1786a 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -12,8 +12,6 @@ config ARC
 	select BUILDTIME_EXTABLE_SORT
 	select COMMON_CLK
 	select CLONE_BACKWARDS
-	# ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev
-	select DEVTMPFS if !INITRAMFS_SOURCE=""
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_FIND_FIRST_BIT
@@ -275,14 +273,6 @@ config ARC_DCCM_BASE
 	default "0xA0000000"
 	depends on ARC_HAS_DCCM
 
-config ARC_HAS_HW_MPY
-	bool "Use Hardware Multiplier (Normal or Faster XMAC)"
-	default y
-	help
-	  Influences how gcc generates code for MPY operations.
-	  If enabled, MPYxx insns are generated, provided by Standard/XMAC
-	  Multipler. Otherwise software multipy lib is used
-
 choice
 	prompt "MMU Version"
 	default ARC_MMU_V3 if ARC_CPU_770
@@ -338,6 +328,19 @@ config ARC_PAGE_SIZE_4K
 
 endchoice
 
+choice
+	prompt "MMU Super Page Size"
+	depends on ISA_ARCV2 && TRANSPARENT_HUGEPAGE
+	default ARC_HUGEPAGE_2M
+
+config ARC_HUGEPAGE_2M
+	bool "2MB"
+
+config ARC_HUGEPAGE_16M
+	bool "16MB"
+
+endchoice
+
 if ISA_ARCOMPACT
 
 config ARC_COMPACT_IRQ_LEVELS
@@ -410,7 +413,7 @@ config ARC_HAS_RTC
 	default n
 	depends on !SMP
 
-config ARC_HAS_GRTC
+config ARC_HAS_GFRC
 	bool "SMP synchronized 64-bit cycle counter"
 	default y
 	depends on SMP
@@ -529,14 +532,6 @@ config ARC_DBG_TLB_MISS_COUNT
 	  Counts number of I and D TLB Misses and exports them via Debugfs
 	  The counters can be cleared via Debugfs as well
 
-if SMP
-
-config ARC_IPI_DBG
-	bool "Debug Inter Core interrupts"
-	default n
-
-endif
-
 endif
 
 config ARC_UBOOT_SUPPORT
@@ -566,6 +561,12 @@ endmenu
 endmenu	 # "ARC Architecture Configuration"
 
 source "mm/Kconfig"
+
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	default "12" if ARC_HUGEPAGE_16M
+	default "11"
+
 source "net/Kconfig"
 source "drivers/Kconfig"
 source "fs/Kconfig"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index aeb19021099e..c8230f3395f2 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -74,10 +74,6 @@ ldflags-$(CONFIG_CPU_BIG_ENDIAN)	+= -EB
 # --build-id w/o "-marclinux". Default arc-elf32-ld is OK
 ldflags-$(upto_gcc44)			+= -marclinux
 
-ifndef CONFIG_ARC_HAS_HW_MPY
-	cflags-y	+= -mno-mpy
-endif
-
 LIBGCC	:= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
 
 # Modules with short calls might break for calls into builtin-kernel
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index f1ac9818b751..5d4e2a07ad3e 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -39,6 +39,7 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -73,7 +74,6 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
@@ -91,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 323486d6ee83..87ee46b237ef 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -39,14 +39,10 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_AXS=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
@@ -78,14 +74,12 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
@@ -97,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 66191cd0447e..d80daf4f7e73 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -40,14 +40,10 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_AXS=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
@@ -79,14 +75,12 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
@@ -98,12 +92,10 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 138f9d887957..f41095340b6a 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -4,6 +4,7 @@ CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -26,7 +27,6 @@ CONFIG_ARC_PLAT_SIM=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -34,6 +34,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -51,7 +52,6 @@ CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
@@ -63,4 +63,3 @@ CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 # CONFIG_DEBUG_PREEMPT is not set
-CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index f68838e8068a..cfaa33cb5921 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -35,6 +35,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -49,7 +50,6 @@ CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
@@ -61,4 +61,3 @@ CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 # CONFIG_DEBUG_PREEMPT is not set
-CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 96bd1c20fb0b..bb2a8dc778b5 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -21,13 +22,11 @@ CONFIG_MODULES=y
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARC_PLAT_SIM=y
-CONFIG_ARC_BOARD_ML509=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -35,6 +34,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -49,7 +49,6 @@ CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
@@ -60,4 +59,3 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 31e1d95764ff..646182e93753 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -33,6 +33,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -58,7 +59,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index fcae66683ca0..ceca2541950d 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -34,12 +34,12 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_OSCI_LAN=y
 CONFIG_INPUT_EVDEV=y
 # CONFIG_MOUSE_PS2_ALPS is not set
 # CONFIG_MOUSE_PS2_LOGIPS2PP is not set
@@ -58,7 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index b01b659168ea..4b6da90f6f26 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
@@ -18,15 +19,11 @@ CONFIG_MODULES=y
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARC_PLAT_SIM=y
-CONFIG_ARC_BOARD_ML509=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
-CONFIG_ARC_HAS_LL64=y
-# CONFIG_ARC_HAS_RTSC is not set
 CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=y
@@ -40,6 +37,7 @@ CONFIG_INET=y
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -56,14 +54,11 @@ CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-CONFIG_NET_OSCI_LAN=y
 # CONFIG_WLAN is not set
 CONFIG_INPUT_EVDEV=y
 CONFIG_MOUSE_PS2_TOUCHKIT=y
 # CONFIG_SERIO_SERPORT is not set
-CONFIG_SERIO_LIBPS2=y
 CONFIG_SERIO_ARC_PS2=y
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
@@ -75,9 +70,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-CONFIG_ARCPGU_RGB888=y
-CONFIG_ARCPGU_DISPTYPE=0
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 3b4dc9cebcf1..9b342eaf95ae 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -3,6 +3,7 @@ CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="tb10x"
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
@@ -26,12 +27,10 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLOCK is not set
 CONFIG_ARC_PLAT_TB10X=y
 CONFIG_ARC_CACHE_LINE_SHIFT=5
-CONFIG_ARC_STACK_NONEXEC=y
 CONFIG_HZ=250
 CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk"
 CONFIG_PREEMPT_VOLUNTARY=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -44,8 +43,8 @@ CONFIG_IP_MULTICAST=y
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
-CONFIG_PROC_DEVICETREE=y
 CONFIG_NETDEVICES=y
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -55,9 +54,6 @@ CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 CONFIG_STMMAC_ETH=y
-CONFIG_STMMAC_DEBUG_FS=y
-CONFIG_STMMAC_DA=y
-CONFIG_STMMAC_CHAINED=y
 # CONFIG_NET_VENDOR_WIZNET is not set
 # CONFIG_WLAN is not set
 # CONFIG_INPUT is not set
@@ -91,7 +87,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_LEDS_TRIGGER_TRANSIENT=y
 CONFIG_DMADEVICES=y
 CONFIG_DW_DMAC=y
-CONFIG_NET_DMA=y
 CONFIG_ASYNC_TX_DMA=y
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
@@ -100,17 +95,16 @@ CONFIG_TMPFS=y
 CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_DEBUG_INFO=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
-CONFIG_MAGIC_SYSRQ=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_HEADERS_CHECK=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index f36c047b33ca..735985974a31 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -16,7 +16,7 @@ CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
-# CONFIG_ARC_HAS_GRTC is not set
+# CONFIG_ARC_HAS_GFRC is not set
 CONFIG_ARC_UBOOT_SUPPORT=y
 CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp"
 CONFIG_PREEMPT=y
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 7fac7d85ed6a..f9f4c6f59fdb 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -10,7 +10,8 @@
 #define _ASM_ARC_ARCREGS_H
 
 /* Build Configuration Registers */
-#define ARC_REG_DCCMBASE_BCR	0x61	/* DCCM Base Addr */
+#define ARC_REG_AUX_DCCM	0x18	/* DCCM Base Addr ARCv2 */
+#define ARC_REG_DCCM_BASE_BUILD	0x61	/* DCCM Base Addr ARCompact */
 #define ARC_REG_CRC_BCR		0x62
 #define ARC_REG_VECBASE_BCR	0x68
 #define ARC_REG_PERIBASE_BCR	0x69
@@ -18,10 +19,10 @@
 #define ARC_REG_DPFP_BCR	0x6C	/* ARCompact: Dbl Precision FPU */
 #define ARC_REG_FP_V2_BCR	0xc8	/* ARCv2 FPU */
 #define ARC_REG_SLC_BCR		0xce
-#define ARC_REG_DCCM_BCR	0x74	/* DCCM Present + SZ */
+#define ARC_REG_DCCM_BUILD	0x74	/* DCCM size (common) */
 #define ARC_REG_TIMERS_BCR	0x75
 #define ARC_REG_AP_BCR		0x76
-#define ARC_REG_ICCM_BCR	0x78
+#define ARC_REG_ICCM_BUILD	0x78	/* ICCM size (common) */
 #define ARC_REG_XY_MEM_BCR	0x79
 #define ARC_REG_MAC_BCR		0x7a
 #define ARC_REG_MUL_BCR		0x7b
@@ -36,6 +37,7 @@
 #define ARC_REG_IRQ_BCR		0xF3
 #define ARC_REG_SMART_BCR	0xFF
 #define ARC_REG_CLUSTER_BCR	0xcf
+#define ARC_REG_AUX_ICCM	0x208	/* ICCM Base Addr (ARCv2) */
 
 /* status32 Bits Positions */
 #define STATUS_AE_BIT		5	/* Exception active */
@@ -246,7 +248,7 @@ struct bcr_perip {
 #endif
 };
 
-struct bcr_iccm {
+struct bcr_iccm_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int base:16, pad:5, sz:3, ver:8;
 #else
@@ -254,17 +256,15 @@ struct bcr_iccm {
 #endif
 };
 
-/* DCCM Base Address Register: ARC_REG_DCCMBASE_BCR */
-struct bcr_dccm_base {
+struct bcr_iccm_arcv2 {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int addr:24, ver:8;
+	unsigned int pad:8, sz11:4, sz01:4, sz10:4, sz00:4, ver:8;
 #else
-	unsigned int ver:8, addr:24;
+	unsigned int ver:8, sz00:4, sz10:4, sz01:4, sz11:4, pad:8;
 #endif
 };
 
-/* DCCM RAM Configuration Register: ARC_REG_DCCM_BCR */
-struct bcr_dccm {
+struct bcr_dccm_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int res:21, sz:3, ver:8;
 #else
@@ -272,6 +272,14 @@ struct bcr_dccm {
 #endif
 };
 
+struct bcr_dccm_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:12, cyc:3, pad1:1, sz1:4, sz0:4, ver:8;
+#else
+	unsigned int ver:8, sz0:4, sz1:4, pad1:1, cyc:3, pad2:12;
+#endif
+};
+
 /* ARCompact: Both SP and DP FPU BCRs have same format */
 struct bcr_fp_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
@@ -315,9 +323,9 @@ struct bcr_bpu_arcv2 {
 
 struct bcr_generic {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int pad:24, ver:8;
+	unsigned int info:24, ver:8;
 #else
-	unsigned int ver:8, pad:24;
+	unsigned int ver:8, info:24;
 #endif
 };
 
@@ -349,14 +357,13 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
-	struct bcr_timer timers;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
 			     fpu_sp:1, fpu_dp:1, pad2:6,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
-			     pad4:8;
+			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
 	struct bcr_mpy extn_mpy;
 	struct bcr_extn_xymem extn_xymem;
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
index 4fd7d62a6e30..49014f0ef36d 100644
--- a/arch/arc/include/asm/irq.h
+++ b/arch/arc/include/asm/irq.h
@@ -16,11 +16,9 @@
 #ifdef CONFIG_ISA_ARCOMPACT
 #define TIMER0_IRQ      3
 #define TIMER1_IRQ      4
-#define IPI_IRQ		(NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */
 #else
 #define TIMER0_IRQ      16
 #define TIMER1_IRQ      17
-#define IPI_IRQ         19
 #endif
 
 #include <linux/interrupt.h>
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index 258b0e5ad332..37c2f751eebf 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -22,6 +22,7 @@
 #define AUX_IRQ_CTRL		0x00E
 #define AUX_IRQ_ACT		0x043	/* Active Intr across all levels */
 #define AUX_IRQ_LVL_PEND	0x200	/* Pending Intr across all levels */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
 #define AUX_IRQ_PRIORITY	0x206
 #define ICAUSE			0x40a
 #define AUX_IRQ_SELECT		0x40b
@@ -30,8 +31,11 @@
 /* Was Intr taken in User Mode */
 #define AUX_IRQ_ACT_BIT_U	31
 
-/* 0 is highest level, but taken by FIRQs, if present in design */
-#define ARCV2_IRQ_DEF_PRIO		0
+/*
+ * User space should be interruptable even by lowest prio interrupt
+ * Safe even if actual interrupt priorities is fewer or even one
+ */
+#define ARCV2_IRQ_DEF_PRIO	15
 
 /* seed value for status register */
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
@@ -112,6 +116,16 @@ static inline int arch_irqs_disabled(void)
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
+static inline void arc_softirq_trigger(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, irq);
+}
+
+static inline void arc_softirq_clear(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, 0);
+}
+
 #else
 
 .macro IRQ_DISABLE  scratch
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
index 46f4e5351b2a..847e3bbe387f 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -39,8 +39,8 @@ struct mcip_cmd {
 #define CMD_DEBUG_SET_MASK		0x34
 #define CMD_DEBUG_SET_SELECT		0x36
 
-#define CMD_GRTC_READ_LO		0x42
-#define CMD_GRTC_READ_HI		0x43
+#define CMD_GFRC_READ_LO		0x42
+#define CMD_GFRC_READ_HI		0x43
 
 #define CMD_IDU_ENABLE			0x71
 #define CMD_IDU_DISABLE			0x72
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 57af2f05ae84..d426d4215513 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -179,37 +179,44 @@
 #define __S111  PAGE_U_X_W_R
 
 /****************************************************************
- * Page Table Lookup split
+ * 2 tier (PGD:PTE) software page walker
  *
- * We implement 2 tier paging and since this is all software, we are free
- * to customize the span of a PGD / PTE entry to suit us
- *
- *			32 bit virtual address
+ * [31]		    32 bit virtual address              [0]
  * -------------------------------------------------------
- * | BITS_FOR_PGD    |  BITS_FOR_PTE    |  BITS_IN_PAGE  |
+ * |               | <------------ PGDIR_SHIFT ----------> |
+ * |		   |					 |
+ * | BITS_FOR_PGD  |  BITS_FOR_PTE  | <-- PAGE_SHIFT --> |
  * -------------------------------------------------------
  *       |                  |                |
  *       |                  |                --> off in page frame
- *       |		    |
  *       |                  ---> index into Page Table
- *       |
  *       ----> index into Page Directory
+ *
+ * In a single page size configuration, only PAGE_SHIFT is fixed
+ * So both PGD and PTE sizing can be tweaked
+ *  e.g. 8K page (PAGE_SHIFT 13) can have
+ *  - PGDIR_SHIFT 21  -> 11:8:13 address split
+ *  - PGDIR_SHIFT 24  -> 8:11:13 address split
+ *
+ * If Super Page is configured, PGDIR_SHIFT becomes fixed too,
+ * so the sizing flexibility is gone.
  */
 
-#define BITS_IN_PAGE	PAGE_SHIFT
-
-/* Optimal Sizing of Pg Tbl - based on MMU page size */
-#if defined(CONFIG_ARC_PAGE_SIZE_8K)
-#define BITS_FOR_PTE	8		/* 11:8:13 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_16K)
-#define BITS_FOR_PTE	8		/* 10:8:14 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_4K)
-#define BITS_FOR_PTE	9		/* 11:9:12 */
+#if defined(CONFIG_ARC_HUGEPAGE_16M)
+#define PGDIR_SHIFT	24
+#elif defined(CONFIG_ARC_HUGEPAGE_2M)
+#define PGDIR_SHIFT	21
+#else
+/*
+ * Only Normal page support so "hackable" (see comment above)
+ * Default value provides 11:8:13 (8K), 11:9:12 (4K)
+ */
+#define PGDIR_SHIFT	21
 #endif
 
-#define BITS_FOR_PGD	(32 - BITS_FOR_PTE - BITS_IN_PAGE)
+#define BITS_FOR_PTE	(PGDIR_SHIFT - PAGE_SHIFT)
+#define BITS_FOR_PGD	(32 - PGDIR_SHIFT)
 
-#define PGDIR_SHIFT	(32 - BITS_FOR_PGD)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)	/* vaddr span, not PDG sz */
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index cbfec79137bf..c1264607bbff 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -45,11 +45,12 @@ VECTOR	reserved		; Reserved slots
 VECTOR	handle_interrupt	; (16) Timer0
 VECTOR	handle_interrupt	; unused (Timer1)
 VECTOR	handle_interrupt	; unused (WDT)
-VECTOR	handle_interrupt	; (19) ICI (inter core interrupt)
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt	; (23) End of fixed IRQs
+VECTOR	handle_interrupt	; (19) Inter core Interrupt (IPI)
+VECTOR	handle_interrupt	; (20) perf Interrupt
+VECTOR	handle_interrupt	; (21) Software Triggered Intr (Self IPI)
+VECTOR	handle_interrupt	; unused
+VECTOR	handle_interrupt	; (23) unused
+# End of fixed IRQs
 
 .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8
 	VECTOR	handle_interrupt
@@ -211,7 +212,11 @@ debug_marker_syscall:
 ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig
 ; entry was via Exception in DS which got preempted in kernel).
 ;
-; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling
+; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround
+;
+; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline
+; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly
+
 .Lintr_ret_to_delay_slot:
 debug_marker_ds:
 
@@ -222,18 +227,23 @@ debug_marker_ds:
 	ld	r2, [sp, PT_ret]
 	ld	r3, [sp, PT_status32]
 
+	; STAT32 for Int return created from scratch
+	; (No delay dlot, disable Further intr in trampoline)
+
 	bic  	r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK
 	st	r0, [sp, PT_status32]
 
 	mov	r1, .Lintr_ret_to_delay_slot_2
 	st	r1, [sp, PT_ret]
 
+	; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots
 	st	r2, [sp, 0]
 	st	r3, [sp, 4]
 
 	b	.Lisr_ret_fast_path
 
 .Lintr_ret_to_delay_slot_2:
+	; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP
 	sub	sp, sp, SZ_PT_REGS
 	st	r9, [sp, -4]
 
@@ -243,11 +253,19 @@ debug_marker_ds:
 	ld	r9, [sp, 4]
 	sr	r9, [erstatus]
 
+	; restore AUX_USER_SP if returning to U mode
+	bbit0	r9, STATUS_U_BIT, 1f
+	ld	r9, [sp, PT_sp]
+	sr	r9, [AUX_USER_SP]
+
+1:
 	ld	r9, [sp, 8]
 	sr	r9, [erbta]
 
 	ld	r9, [sp, -4]
 	add	sp, sp, SZ_PT_REGS
+
+	; return from pure kernel mode to delay slot
 	rtie
 
 END(ret_from_exception)
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 0394f9f61b46..942526322ae7 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -14,6 +14,8 @@
 #include <linux/irqchip.h>
 #include <asm/irq.h>
 
+static int irq_prio;
+
 /*
  * Early Hardware specific Interrupt setup
  * -Called very early (start_kernel -> setup_arch -> setup_processor)
@@ -24,6 +26,14 @@ void arc_init_IRQ(void)
 {
 	unsigned int tmp;
 
+	struct irq_build {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:3, firq:1, prio:4, exts:8, irqs:8, ver:8;
+#else
+		unsigned int ver:8, irqs:8, exts:8, prio:4, firq:1, pad:3;
+#endif
+	} irq_bcr;
+
 	struct aux_irq_ctrl {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int res3:18, save_idx_regs:1, res2:1,
@@ -46,28 +56,25 @@ void arc_init_IRQ(void)
 
 	WRITE_AUX(AUX_IRQ_CTRL, ictrl);
 
-	/* setup status32, don't enable intr yet as kernel doesn't want */
-	tmp = read_aux_reg(0xa);
-	tmp |= ISA_INIT_STATUS_BITS;
-	tmp &= ~STATUS_IE_MASK;
-	asm volatile("flag %0	\n"::"r"(tmp));
-
 	/*
 	 * ARCv2 core intc provides multiple interrupt priorities (upto 16).
 	 * Typical builds though have only two levels (0-high, 1-low)
 	 * Linux by default uses lower prio 1 for most irqs, reserving 0 for
 	 * NMI style interrupts in future (say perf)
-	 *
-	 * Read the intc BCR to confirm that Linux default priority is avail
-	 * in h/w
-	 *
-	 * Note:
-	 *  IRQ_BCR[27..24] contains N-1 (for N priority levels) and prio level
-	 *  is 0 based.
 	 */
-	tmp = (read_aux_reg(ARC_REG_IRQ_BCR) >> 24 ) & 0xF;
-	if (ARCV2_IRQ_DEF_PRIO > tmp)
-		panic("Linux default irq prio incorrect\n");
+
+	READ_BCR(ARC_REG_IRQ_BCR, irq_bcr);
+
+	irq_prio = irq_bcr.prio;	/* Encoded as N-1 for N levels */
+	pr_info("archs-intc\t: %d priority levels (default %d)%s\n",
+		irq_prio + 1, irq_prio,
+		irq_bcr.firq ? " FIRQ (not used)":"");
+
+	/* setup status32, don't enable intr yet as kernel doesn't want */
+	tmp = read_aux_reg(0xa);
+	tmp |= STATUS_AD_MASK | (irq_prio << 1);
+	tmp &= ~STATUS_IE_MASK;
+	asm volatile("flag %0	\n"::"r"(tmp));
 }
 
 static void arcv2_irq_mask(struct irq_data *data)
@@ -86,7 +93,7 @@ void arcv2_irq_enable(struct irq_data *data)
 {
 	/* set default priority */
 	write_aux_reg(AUX_IRQ_SELECT, data->irq);
-	write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+	write_aux_reg(AUX_IRQ_PRIORITY, irq_prio);
 
 	/*
 	 * hw auto enables (linux unmask) all by default
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index 06bcedf19b62..224d1c3aa9c4 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -81,9 +81,6 @@ static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq,
 {
 	switch (irq) {
 	case TIMER0_IRQ:
-#ifdef CONFIG_SMP
-	case IPI_IRQ:
-#endif
 		irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq);
 		break;
 	default:
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index bd237acdf4f2..c41c364b926c 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -11,9 +11,13 @@
 #include <linux/smp.h>
 #include <linux/irq.h>
 #include <linux/spinlock.h>
+#include <asm/irqflags-arcv2.h>
 #include <asm/mcip.h>
 #include <asm/setup.h>
 
+#define IPI_IRQ		19
+#define SOFTIRQ_IRQ	21
+
 static char smp_cpuinfo_buf[128];
 static int idu_detected;
 
@@ -22,6 +26,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock);
 static void mcip_setup_per_cpu(int cpu)
 {
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
+	smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ);
 }
 
 static void mcip_ipi_send(int cpu)
@@ -29,46 +34,44 @@ static void mcip_ipi_send(int cpu)
 	unsigned long flags;
 	int ipi_was_pending;
 
+	/* ARConnect can only send IPI to others */
+	if (unlikely(cpu == raw_smp_processor_id())) {
+		arc_softirq_trigger(SOFTIRQ_IRQ);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
 	/*
-	 * NOTE: We must spin here if the other cpu hasn't yet
-	 * serviced a previous message. This can burn lots
-	 * of time, but we MUST follows this protocol or
-	 * ipi messages can be lost!!!
-	 * Also, we must release the lock in this loop because
-	 * the other side may get to this same loop and not
-	 * be able to ack -- thus causing deadlock.
+	 * If receiver already has a pending interrupt, elide sending this one.
+	 * Linux cross core calling works well with concurrent IPIs
+	 * coalesced into one
+	 * see arch/arc/kernel/smp.c: ipi_send_msg_one()
 	 */
+	__mcip_cmd(CMD_INTRPT_READ_STATUS, cpu);
+	ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK);
+	if (!ipi_was_pending)
+		__mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu);
 
-	do {
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		__mcip_cmd(CMD_INTRPT_READ_STATUS, cpu);
-		ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK);
-		if (ipi_was_pending == 0)
-			break; /* break out but keep lock */
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	} while (1);
-
-	__mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu);
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
-
-#ifdef CONFIG_ARC_IPI_DBG
-	if (ipi_was_pending)
-		pr_info("IPI ACK delayed from cpu %d\n", cpu);
-#endif
 }
 
 static void mcip_ipi_clear(int irq)
 {
 	unsigned int cpu, c;
 	unsigned long flags;
-	unsigned int __maybe_unused copy;
+
+	if (unlikely(irq == SOFTIRQ_IRQ)) {
+		arc_softirq_clear(irq);
+		return;
+	}
 
 	raw_spin_lock_irqsave(&mcip_lock, flags);
 
 	/* Who sent the IPI */
 	__mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0);
 
-	copy = cpu = read_aux_reg(ARC_REG_MCIP_READBACK);	/* 1,2,4,8... */
+	cpu = read_aux_reg(ARC_REG_MCIP_READBACK);	/* 1,2,4,8... */
 
 	/*
 	 * In rare case, multiple concurrent IPIs sent to same target can
@@ -82,12 +85,6 @@ static void mcip_ipi_clear(int irq)
 	} while (cpu);
 
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
-
-#ifdef CONFIG_ARC_IPI_DBG
-	if (c != __ffs(copy))
-		pr_info("IPIs from %x coalesced to %x\n",
-			copy, raw_smp_processor_id());
-#endif
 }
 
 static void mcip_probe_n_setup(void)
@@ -96,13 +93,13 @@ static void mcip_probe_n_setup(void)
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int pad3:8,
 			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  grtc:1, dbg:1, pad2:1,
+			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
 			     msg:1, sem:1, ipi:1, pad:1,
 			     ver:8;
 #else
 		unsigned int ver:8,
 			     pad:1, ipi:1, sem:1, msg:1,
-			     pad2:1, dbg:1, grtc:1, iocoh:1,
+			     pad2:1, dbg:1, gfrc:1, iocoh:1,
 			     num_cores:6, llm:1, idu:1,
 			     pad3:8;
 #endif
@@ -111,12 +108,13 @@ static void mcip_probe_n_setup(void)
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
 	sprintf(smp_cpuinfo_buf,
-		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
+		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n",
 		mp.ver, mp.num_cores,
 		IS_AVAIL1(mp.ipi, "IPI "),
 		IS_AVAIL1(mp.idu, "IDU "),
+		IS_AVAIL1(mp.llm, "LLM "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
-		IS_AVAIL1(mp.grtc, "GRTC"));
+		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	idu_detected = mp.idu;
 
@@ -125,8 +123,8 @@ static void mcip_probe_n_setup(void)
 		__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf);
 	}
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_GRTC) && !mp.grtc)
-		panic("kernel trying to use non-existent GRTC\n");
+	if (IS_ENABLED(CONFIG_ARC_HAS_GFRC) && !mp.gfrc)
+		panic("kernel trying to use non-existent GFRC\n");
 }
 
 struct plat_smp_ops plat_smp_ops = {
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index e1b87444ea9a..cdc821df1809 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -42,9 +42,57 @@ struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 
+static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
+{
+	if (is_isa_arcompact()) {
+		struct bcr_iccm_arcompact iccm;
+		struct bcr_dccm_arcompact dccm;
+
+		READ_BCR(ARC_REG_ICCM_BUILD, iccm);
+		if (iccm.ver) {
+			cpu->iccm.sz = 4096 << iccm.sz;	/* 8K to 512K */
+			cpu->iccm.base_addr = iccm.base << 16;
+		}
+
+		READ_BCR(ARC_REG_DCCM_BUILD, dccm);
+		if (dccm.ver) {
+			unsigned long base;
+			cpu->dccm.sz = 2048 << dccm.sz;	/* 2K to 256K */
+
+			base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD);
+			cpu->dccm.base_addr = base & ~0xF;
+		}
+	} else {
+		struct bcr_iccm_arcv2 iccm;
+		struct bcr_dccm_arcv2 dccm;
+		unsigned long region;
+
+		READ_BCR(ARC_REG_ICCM_BUILD, iccm);
+		if (iccm.ver) {
+			cpu->iccm.sz = 256 << iccm.sz00;	/* 512B to 16M */
+			if (iccm.sz00 == 0xF && iccm.sz01 > 0)
+				cpu->iccm.sz <<= iccm.sz01;
+
+			region = read_aux_reg(ARC_REG_AUX_ICCM);
+			cpu->iccm.base_addr = region & 0xF0000000;
+		}
+
+		READ_BCR(ARC_REG_DCCM_BUILD, dccm);
+		if (dccm.ver) {
+			cpu->dccm.sz = 256 << dccm.sz0;
+			if (dccm.sz0 == 0xF && dccm.sz1 > 0)
+				cpu->dccm.sz <<= dccm.sz1;
+
+			region = read_aux_reg(ARC_REG_AUX_DCCM);
+			cpu->dccm.base_addr = region & 0xF0000000;
+		}
+	}
+}
+
 static void read_arc_build_cfg_regs(void)
 {
 	struct bcr_perip uncached_space;
+	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	unsigned long perip_space;
@@ -53,7 +101,11 @@ static void read_arc_build_cfg_regs(void)
 	READ_BCR(AUX_IDENTITY, cpu->core);
 	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
-	READ_BCR(ARC_REG_TIMERS_BCR, cpu->timers);
+	READ_BCR(ARC_REG_TIMERS_BCR, timer);
+	cpu->extn.timer0 = timer.t0;
+	cpu->extn.timer1 = timer.t1;
+	cpu->extn.rtc = timer.rtc;
+
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
@@ -71,36 +123,11 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0;        /* 1,3 */
 	cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
 	cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
-
-	/* Note that we read the CCM BCRs independent of kernel config
-	 * This is to catch the cases where user doesn't know that
-	 * CCMs are present in hardware build
-	 */
-	{
-		struct bcr_iccm iccm;
-		struct bcr_dccm dccm;
-		struct bcr_dccm_base dccm_base;
-		unsigned int bcr_32bit_val;
-
-		bcr_32bit_val = read_aux_reg(ARC_REG_ICCM_BCR);
-		if (bcr_32bit_val) {
-			iccm = *((struct bcr_iccm *)&bcr_32bit_val);
-			cpu->iccm.base_addr = iccm.base << 16;
-			cpu->iccm.sz = 0x2000 << (iccm.sz - 1);
-		}
-
-		bcr_32bit_val = read_aux_reg(ARC_REG_DCCM_BCR);
-		if (bcr_32bit_val) {
-			dccm = *((struct bcr_dccm *)&bcr_32bit_val);
-			cpu->dccm.sz = 0x800 << (dccm.sz);
-
-			READ_BCR(ARC_REG_DCCMBASE_BCR, dccm_base);
-			cpu->dccm.base_addr = dccm_base.addr << 8;
-		}
-	}
-
 	READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
 
+	/* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
+	read_decode_ccm_bcr(cpu);
+
 	read_decode_mmu_bcr();
 	read_decode_cache_bcr();
 
@@ -208,9 +235,9 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       (unsigned int)(arc_get_core_freq() / 10000) % 100);
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
-		       IS_AVAIL1(cpu->timers.t0, "Timer0 "),
-		       IS_AVAIL1(cpu->timers.t1, "Timer1 "),
-		       IS_AVAIL2(cpu->timers.rtc, "64-bit RTC ",
+		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
+		       IS_AVAIL1(cpu->extn.timer1, "Timer1 "),
+		       IS_AVAIL2(cpu->extn.rtc, "Local-64-bit-Ctr ",
 				 CONFIG_ARC_HAS_RTC));
 
 	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
@@ -232,8 +259,6 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 
 			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
 		}
-		n += scnprintf(buf + n, len - n, "%s",
-			       IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY));
 	}
 
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
@@ -293,13 +318,13 @@ static void arc_chk_core_config(void)
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	int fpu_enabled;
 
-	if (!cpu->timers.t0)
+	if (!cpu->extn.timer0)
 		panic("Timer0 is not present!\n");
 
-	if (!cpu->timers.t1)
+	if (!cpu->extn.timer1)
 		panic("Timer1 is not present!\n");
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->timers.rtc)
+	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->extn.rtc)
 		panic("RTC is not present\n");
 
 #ifdef CONFIG_ARC_HAS_DCCM
@@ -334,6 +359,7 @@ static void arc_chk_core_config(void)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
 
 	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    IS_ENABLED(CONFIG_ARC_HAS_LLSC) &&
 	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
 		panic("llock/scond livelock workaround missing\n");
 }
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index ef6e9e15b82a..424e937da5c8 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -336,11 +336,8 @@ irqreturn_t do_IPI(int irq, void *dev_id)
 		int rc;
 
 		rc = __do_IPI(msg);
-#ifdef CONFIG_ARC_IPI_DBG
-		/* IPI received but no valid @msg */
 		if (rc)
 			pr_info("IPI with bogus msg %ld in %ld\n", msg, copy);
-#endif
 		pending &= ~(1U << msg);
 	} while (pending);
 
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index dfad287f1db1..156d9833ff84 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -62,7 +62,7 @@
 
 /********** Clock Source Device *********/
 
-#ifdef CONFIG_ARC_HAS_GRTC
+#ifdef CONFIG_ARC_HAS_GFRC
 
 static int arc_counter_setup(void)
 {
@@ -83,10 +83,10 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 
 	local_irq_save(flags);
 
-	__mcip_cmd(CMD_GRTC_READ_LO, 0);
+	__mcip_cmd(CMD_GFRC_READ_LO, 0);
 	stamp.l = read_aux_reg(ARC_REG_MCIP_READBACK);
 
-	__mcip_cmd(CMD_GRTC_READ_HI, 0);
+	__mcip_cmd(CMD_GFRC_READ_HI, 0);
 	stamp.h = read_aux_reg(ARC_REG_MCIP_READBACK);
 
 	local_irq_restore(flags);
@@ -95,7 +95,7 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 }
 
 static struct clocksource arc_counter = {
-	.name   = "ARConnect GRTC",
+	.name   = "ARConnect GFRC",
 	.rating = 400,
 	.read   = arc_counter_read,
 	.mask   = CLOCKSOURCE_MASK(64),
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index f3db13d2d90e..0cc150b87b86 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -285,8 +285,10 @@
 	};
 };
 
+
+/include/ "tps65217.dtsi"
+
 &tps {
-	compatible = "ti,tps65217";
 	/*
 	 * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only
 	 * mode") at poweroff.  Most BeagleBone versions do not support RTC-only
@@ -307,17 +309,12 @@
 	ti,pmic-shutdown-controller;
 
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			regulator-name = "vdds_dpr";
 			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -327,7 +324,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -337,25 +333,21 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			regulator-name = "vio,vrtc,vdds";
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			regulator-name = "vdd_3v3aux";
 			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			regulator-name = "vdd_1v8";
 			regulator-always-on;
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			regulator-name = "vdd_3v3a";
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am335x-chilisom.dtsi b/arch/arm/boot/dts/am335x-chilisom.dtsi
index fda457b07e15..857d9894103a 100644
--- a/arch/arm/boot/dts/am335x-chilisom.dtsi
+++ b/arch/arm/boot/dts/am335x-chilisom.dtsi
@@ -128,21 +128,16 @@
 
 };
 
-&tps {
-	compatible = "ti,tps65217";
+/include/ "tps65217.dtsi"
 
+&tps {
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			regulator-name = "vdds_dpr";
 			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -152,7 +147,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -162,28 +156,24 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			regulator-name = "vio,vrtc,vdds";
 			regulator-boot-on;
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			regulator-name = "vdd_3v3aux";
 			regulator-boot-on;
 			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			regulator-name = "vdd_1v8";
 			regulator-boot-on;
 			regulator-always-on;
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			regulator-name = "vdd_3v3d";
 			regulator-boot-on;
 			regulator-always-on;
diff --git a/arch/arm/boot/dts/am335x-nano.dts b/arch/arm/boot/dts/am335x-nano.dts
index 77559a1ded60..f313999c503e 100644
--- a/arch/arm/boot/dts/am335x-nano.dts
+++ b/arch/arm/boot/dts/am335x-nano.dts
@@ -375,15 +375,11 @@
 	wp-gpios = <&gpio3 18 0>;
 };
 
-&tps {
-	compatible = "ti,tps65217";
+#include "tps65217.dtsi"
 
+&tps {
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			/* +1.5V voltage with ±4% tolerance */
 			regulator-min-microvolt = <1450000>;
 			regulator-max-microvolt = <1550000>;
@@ -392,7 +388,6 @@
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.1V with ±4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <915000>;
@@ -402,7 +397,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with ±4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <915000>;
@@ -412,7 +406,6 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			/* +1.8V voltage with ±4% tolerance */
 			regulator-min-microvolt = <1750000>;
 			regulator-max-microvolt = <1870000>;
@@ -421,7 +414,6 @@
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			/* +3.3V voltage with ±4% tolerance */
 			regulator-min-microvolt = <3175000>;
 			regulator-max-microvolt = <3430000>;
@@ -430,7 +422,6 @@
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			/* +1.8V voltage with ±4% tolerance */
 			regulator-min-microvolt = <1750000>;
 			regulator-max-microvolt = <1870000>;
@@ -439,7 +430,6 @@
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			/* +3.3V voltage with ±4% tolerance */
 			regulator-min-microvolt = <3175000>;
 			regulator-max-microvolt = <3430000>;
diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts
index 471a3a70ea1f..8867aaaec54d 100644
--- a/arch/arm/boot/dts/am335x-pepper.dts
+++ b/arch/arm/boot/dts/am335x-pepper.dts
@@ -420,9 +420,9 @@
 	vin-supply = <&vbat>;
 };
 
-&tps {
-	compatible = "ti,tps65217";
+/include/ "tps65217.dtsi"
 
+&tps {
 	backlight {
 		isel = <1>; /* ISET1 */
 		fdim = <200>; /* TPS65217_BL_FDIM_200HZ */
@@ -430,17 +430,12 @@
 	};
 
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			/* VDD_1V8 system supply */
 			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_CORE voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -450,7 +445,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_MPU voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -460,21 +454,18 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			/* VRTC 1.8V always-on supply */
 			regulator-name = "vrtc,vdds";
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			/* 3.3V rail */
 			regulator-name = "vdd_3v3aux";
 			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			/* VDD_3V3A 3.3V rail */
 			regulator-name = "vdd_3v3a";
 			regulator-min-microvolt = <3300000>;
@@ -482,7 +473,6 @@
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			/* VDD_3V3B 3.3V rail */
 			regulator-name = "vdd_3v3b";
 			regulator-always-on;
diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts
index 1b5b044fcd91..865de8500f1c 100644
--- a/arch/arm/boot/dts/am335x-shc.dts
+++ b/arch/arm/boot/dts/am335x-shc.dts
@@ -46,7 +46,7 @@
 			gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>;
 			linux,code = <KEY_BACK>;
 			debounce-interval = <1000>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		front_button {
@@ -54,7 +54,7 @@
 			gpios = <&gpio1 25 GPIO_ACTIVE_HIGH>;
 			linux,code = <KEY_FRONT>;
 			debounce-interval = <1000>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/am335x-sl50.dts b/arch/arm/boot/dts/am335x-sl50.dts
index d38edfa53bb9..3303c281697b 100644
--- a/arch/arm/boot/dts/am335x-sl50.dts
+++ b/arch/arm/boot/dts/am335x-sl50.dts
@@ -375,19 +375,16 @@
 	pinctrl-0 = <&uart4_pins>;
 };
 
+#include "tps65217.dtsi"
+
 &tps {
-	compatible = "ti,tps65217";
 	ti,pmic-shutdown-controller;
 
 	interrupt-parent = <&intc>;
 	interrupts = <7>;	/* NNMI */
 
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			/* VDDS_DDR */
 			regulator-min-microvolt = <1500000>;
 			regulator-max-microvolt = <1500000>;
@@ -395,7 +392,6 @@
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -405,7 +401,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -415,7 +410,6 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			/* VRTC / VIO / VDDS*/
 			regulator-always-on;
 			regulator-min-microvolt = <1800000>;
@@ -423,7 +417,6 @@
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			/* VDD_3V3AUX */
 			regulator-always-on;
 			regulator-min-microvolt = <3300000>;
@@ -431,7 +424,6 @@
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			/* VDD_1V8 */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
@@ -439,7 +431,6 @@
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			/* VDD_3V3A */
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 36c0fa6c362a..a0986c65be0c 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -173,6 +173,8 @@
 
 		sound0_master: simple-audio-card,codec {
 			sound-dai = <&tlv320aic3104>;
+			assigned-clocks = <&clkoutmux2_clk_mux>;
+			assigned-clock-parents = <&sys_clk2_dclk_div>;
 			clocks = <&clkout2_clk>;
 		};
 	};
@@ -796,6 +798,8 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&mcasp3_pins_default>;
 	pinctrl-1 = <&mcasp3_pins_sleep>;
+	assigned-clocks = <&mcasp3_ahclkx_mux>;
+	assigned-clock-parents = <&sys_clkin2>;
 	status = "okay";
 
 	op-mode = <0>;	/* MCASP_IIS_MODE */
diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
index 8d93882dc8d5..1c06cb76da07 100644
--- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
+++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
@@ -545,7 +545,7 @@
 		ti,debounce-tol = /bits/ 16 <10>;
 		ti,debounce-rep = /bits/ 16 <1>;
 
-		linux,wakeup;
+		wakeup-source;
 	};
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 4f6ae921656f..f74d3db4846d 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -896,7 +896,6 @@
 				#size-cells = <1>;
 				reg = <0x2100000 0x10000>;
 				ranges = <0 0x2100000 0x10000>;
-				interrupt-parent = <&intc>;
 				clocks = <&clks IMX6QDL_CLK_CAAM_MEM>,
 					 <&clks IMX6QDL_CLK_CAAM_ACLK>,
 					 <&clks IMX6QDL_CLK_CAAM_IPG>,
diff --git a/arch/arm/boot/dts/kirkwood-ds112.dts b/arch/arm/boot/dts/kirkwood-ds112.dts
index bf4143c6cb8f..b84af3da8c84 100644
--- a/arch/arm/boot/dts/kirkwood-ds112.dts
+++ b/arch/arm/boot/dts/kirkwood-ds112.dts
@@ -14,7 +14,7 @@
 #include "kirkwood-synology.dtsi"
 
 / {
-	model = "Synology DS111";
+	model = "Synology DS112";
 	compatible = "synology,ds111", "marvell,kirkwood";
 
 	memory {
diff --git a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
index 420788229e6f..aae8a7aceab7 100644
--- a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
+++ b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
@@ -228,6 +228,37 @@
 	};
 };
 
+&devbus_bootcs {
+	status = "okay";
+	devbus,keep-config;
+
+	flash@0 {
+		compatible = "jedec-flash";
+		reg = <0 0x40000>;
+		bank-width = <1>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			header@0 {
+				reg = <0 0x30000>;
+				read-only;
+			};
+
+			uboot@30000 {
+				reg = <0x30000 0xF000>;
+				read-only;
+			};
+
+			uboot_env@3F000 {
+				reg = <0x3F000 0x1000>;
+			};
+		};
+	};
+};
+
 &mdio {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h
index 1afe24629d1f..b0c912feaa2f 100644
--- a/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/arch/arm/boot/dts/sama5d2-pinfunc.h
@@ -90,7 +90,7 @@
 #define PIN_PA14__I2SC1_MCK		PINMUX_PIN(PIN_PA14, 4, 2)
 #define PIN_PA14__FLEXCOM3_IO2		PINMUX_PIN(PIN_PA14, 5, 1)
 #define PIN_PA14__D9			PINMUX_PIN(PIN_PA14, 6, 2)
-#define PIN_PA15			14
+#define PIN_PA15			15
 #define PIN_PA15__GPIO			PINMUX_PIN(PIN_PA15, 0, 0)
 #define PIN_PA15__SPI0_MOSI		PINMUX_PIN(PIN_PA15, 1, 1)
 #define PIN_PA15__TF1			PINMUX_PIN(PIN_PA15, 2, 1)
diff --git a/arch/arm/boot/dts/tps65217.dtsi b/arch/arm/boot/dts/tps65217.dtsi
new file mode 100644
index 000000000000..a63272422d76
--- /dev/null
+++ b/arch/arm/boot/dts/tps65217.dtsi
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.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 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Integrated Power Management Chip
+ * http://www.ti.com/lit/ds/symlink/tps65217.pdf
+ */
+
+&tps {
+	compatible = "ti,tps65217";
+
+	regulators {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		dcdc1_reg: regulator@0 {
+			reg = <0>;
+			regulator-compatible = "dcdc1";
+		};
+
+		dcdc2_reg: regulator@1 {
+			reg = <1>;
+			regulator-compatible = "dcdc2";
+		};
+
+		dcdc3_reg: regulator@2 {
+			reg = <2>;
+			regulator-compatible = "dcdc3";
+		};
+
+		ldo1_reg: regulator@3 {
+			reg = <3>;
+			regulator-compatible = "ldo1";
+		};
+
+		ldo2_reg: regulator@4 {
+			reg = <4>;
+			regulator-compatible = "ldo2";
+		};
+
+		ldo3_reg: regulator@5 {
+			reg = <5>;
+			regulator-compatible = "ldo3";
+		};
+
+		ldo4_reg: regulator@6 {
+			reg = <6>;
+			regulator-compatible = "ldo4";
+		};
+	};
+};
diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c
index 2dc6da70ae59..d7ed252708c5 100644
--- a/arch/arm/common/icst.c
+++ b/arch/arm/common/icst.c
@@ -16,7 +16,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
-
+#include <asm/div64.h>
 #include <asm/hardware/icst.h>
 
 /*
@@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div);
 
 unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco)
 {
-	return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]);
+	u64 dividend = p->ref * 2 * (u64)(vco.v + 8);
+	u32 divisor = (vco.r + 2) * p->s2div[vco.s];
+
+	do_div(dividend, divisor);
+	return (unsigned long)dividend;
 }
 
 EXPORT_SYMBOL(icst_hz);
@@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq)
 
 		if (f > p->vco_min && f <= p->vco_max)
 			break;
+		i++;
 	} while (i < 8);
 
 	if (i >= 8)
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index a7151744b85c..d18d6b42fcf5 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -292,24 +292,23 @@ CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
-CONFIG_OMAP2_DSS=m
-CONFIG_OMAP5_DSS_HDMI=y
-CONFIG_OMAP2_DSS_SDI=y
-CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP5_DSS_HDMI=y
+CONFIG_FB_OMAP2_DSS_SDI=y
+CONFIG_FB_OMAP2_DSS_DSI=y
 CONFIG_FB_OMAP2=m
-CONFIG_DISPLAY_ENCODER_TFP410=m
-CONFIG_DISPLAY_ENCODER_TPD12S015=m
-CONFIG_DISPLAY_CONNECTOR_DVI=m
-CONFIG_DISPLAY_CONNECTOR_HDMI=m
-CONFIG_DISPLAY_CONNECTOR_ANALOG_TV=m
-CONFIG_DISPLAY_PANEL_DPI=m
-CONFIG_DISPLAY_PANEL_DSI_CM=m
-CONFIG_DISPLAY_PANEL_SONY_ACX565AKM=m
-CONFIG_DISPLAY_PANEL_LGPHILIPS_LB035Q02=m
-CONFIG_DISPLAY_PANEL_SHARP_LS037V7DW01=m
-CONFIG_DISPLAY_PANEL_TPO_TD028TTEC1=m
-CONFIG_DISPLAY_PANEL_TPO_TD043MTEA1=m
-CONFIG_DISPLAY_PANEL_NEC_NL8048HL11=m
+CONFIG_FB_OMAP2_ENCODER_TFP410=m
+CONFIG_FB_OMAP2_ENCODER_TPD12S015=m
+CONFIG_FB_OMAP2_CONNECTOR_DVI=m
+CONFIG_FB_OMAP2_CONNECTOR_HDMI=m
+CONFIG_FB_OMAP2_CONNECTOR_ANALOG_TV=m
+CONFIG_FB_OMAP2_PANEL_DPI=m
+CONFIG_FB_OMAP2_PANEL_DSI_CM=m
+CONFIG_FB_OMAP2_PANEL_SONY_ACX565AKM=m
+CONFIG_FB_OMAP2_PANEL_LGPHILIPS_LB035Q02=m
+CONFIG_FB_OMAP2_PANEL_SHARP_LS037V7DW01=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD028TTEC1=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD043MTEA1=m
+CONFIG_FB_OMAP2_PANEL_NEC_NL8048HL11=m
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=y
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index b445a5d56f43..89a3a3e592d6 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -364,7 +364,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_blkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= ce_aes_setkey,
 		.encrypt	= ecb_encrypt,
 		.decrypt	= ecb_decrypt,
@@ -441,7 +441,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_ablkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= ablk_set_key,
 		.encrypt	= ablk_encrypt,
 		.decrypt	= ablk_decrypt,
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 7da5503c0591..e08d15184056 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void)
 	u32 irqstat;
 
 	asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 194c91b610ff..15d58b42d5a1 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -19,38 +19,7 @@
 #ifndef __ARM_KVM_ASM_H__
 #define __ARM_KVM_ASM_H__
 
-/* 0 is reserved as an invalid value. */
-#define c0_MPIDR	1	/* MultiProcessor ID Register */
-#define c0_CSSELR	2	/* Cache Size Selection Register */
-#define c1_SCTLR	3	/* System Control Register */
-#define c1_ACTLR	4	/* Auxiliary Control Register */
-#define c1_CPACR	5	/* Coprocessor Access Control */
-#define c2_TTBR0	6	/* Translation Table Base Register 0 */
-#define c2_TTBR0_high	7	/* TTBR0 top 32 bits */
-#define c2_TTBR1	8	/* Translation Table Base Register 1 */
-#define c2_TTBR1_high	9	/* TTBR1 top 32 bits */
-#define c2_TTBCR	10	/* Translation Table Base Control R. */
-#define c3_DACR		11	/* Domain Access Control Register */
-#define c5_DFSR		12	/* Data Fault Status Register */
-#define c5_IFSR		13	/* Instruction Fault Status Register */
-#define c5_ADFSR	14	/* Auxilary Data Fault Status R */
-#define c5_AIFSR	15	/* Auxilary Instrunction Fault Status R */
-#define c6_DFAR		16	/* Data Fault Address Register */
-#define c6_IFAR		17	/* Instruction Fault Address Register */
-#define c7_PAR		18	/* Physical Address Register */
-#define c7_PAR_high	19	/* PAR top 32 bits */
-#define c9_L2CTLR	20	/* Cortex A15/A7 L2 Control Register */
-#define c10_PRRR	21	/* Primary Region Remap Register */
-#define c10_NMRR	22	/* Normal Memory Remap Register */
-#define c12_VBAR	23	/* Vector Base Address Register */
-#define c13_CID		24	/* Context ID Register */
-#define c13_TID_URW	25	/* Thread ID, User R/W */
-#define c13_TID_URO	26	/* Thread ID, User R/O */
-#define c13_TID_PRIV	27	/* Thread ID, Privileged */
-#define c14_CNTKCTL	28	/* Timer Control Register (PL1) */
-#define c10_AMAIR0	29	/* Auxilary Memory Attribute Indirection Reg0 */
-#define c10_AMAIR1	30	/* Auxilary Memory Attribute Indirection Reg1 */
-#define NR_CP15_REGS	31	/* Number of regs (incl. invalid) */
+#include <asm/virt.h>
 
 #define ARM_EXCEPTION_RESET	  0
 #define ARM_EXCEPTION_UNDEFINED   1
@@ -86,19 +55,15 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_exit[];
-extern char __kvm_hyp_exit_end[];
-
 extern char __kvm_hyp_vector[];
 
-extern char __kvm_hyp_code_start[];
-extern char __kvm_hyp_code_end[];
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+extern void __init_stage2_translation(void);
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 3095df091ff8..ee5328fc4b06 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -68,12 +68,12 @@ static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 
 static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu)
 {
-	return &vcpu->arch.regs.usr_regs.ARM_pc;
+	return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_pc;
 }
 
 static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu)
 {
-	return &vcpu->arch.regs.usr_regs.ARM_cpsr;
+	return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr;
 }
 
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
@@ -83,13 +83,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 
 static inline bool mode_has_spsr(struct kvm_vcpu *vcpu)
 {
-	unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK;
+	unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK;
 	return (cpsr_mode > USR_MODE && cpsr_mode < SYSTEM_MODE);
 }
 
 static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu)
 {
-	unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK;
+	unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK;
 	return cpsr_mode > USR_MODE;;
 }
 
@@ -108,11 +108,6 @@ static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu)
 	return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8;
 }
 
-static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.fault.hyp_pc;
-}
-
 static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
@@ -143,6 +138,11 @@ static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW;
 }
 
+static inline bool kvm_vcpu_dabt_is_cm(struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & HSR_DABT_CM);
+}
+
 /* Get Access Size from a data abort */
 static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
 {
@@ -192,7 +192,7 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.cp15[c0_MPIDR] & MPIDR_HWID_BITMASK;
+	return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index f9f27792d8ed..385070180c25 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -85,20 +85,61 @@ struct kvm_vcpu_fault_info {
 	u32 hsr;		/* Hyp Syndrome Register */
 	u32 hxfar;		/* Hyp Data/Inst. Fault Address Register */
 	u32 hpfar;		/* Hyp IPA Fault Address Register */
-	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
 };
 
-typedef struct vfp_hard_struct kvm_cpu_context_t;
+/*
+ * 0 is reserved as an invalid value.
+ * Order should be kept in sync with the save/restore code.
+ */
+enum vcpu_sysreg {
+	__INVALID_SYSREG__,
+	c0_MPIDR,		/* MultiProcessor ID Register */
+	c0_CSSELR,		/* Cache Size Selection Register */
+	c1_SCTLR,		/* System Control Register */
+	c1_ACTLR,		/* Auxiliary Control Register */
+	c1_CPACR,		/* Coprocessor Access Control */
+	c2_TTBR0,		/* Translation Table Base Register 0 */
+	c2_TTBR0_high,		/* TTBR0 top 32 bits */
+	c2_TTBR1,		/* Translation Table Base Register 1 */
+	c2_TTBR1_high,		/* TTBR1 top 32 bits */
+	c2_TTBCR,		/* Translation Table Base Control R. */
+	c3_DACR,		/* Domain Access Control Register */
+	c5_DFSR,		/* Data Fault Status Register */
+	c5_IFSR,		/* Instruction Fault Status Register */
+	c5_ADFSR,		/* Auxilary Data Fault Status R */
+	c5_AIFSR,		/* Auxilary Instrunction Fault Status R */
+	c6_DFAR,		/* Data Fault Address Register */
+	c6_IFAR,		/* Instruction Fault Address Register */
+	c7_PAR,			/* Physical Address Register */
+	c7_PAR_high,		/* PAR top 32 bits */
+	c9_L2CTLR,		/* Cortex A15/A7 L2 Control Register */
+	c10_PRRR,		/* Primary Region Remap Register */
+	c10_NMRR,		/* Normal Memory Remap Register */
+	c12_VBAR,		/* Vector Base Address Register */
+	c13_CID,		/* Context ID Register */
+	c13_TID_URW,		/* Thread ID, User R/W */
+	c13_TID_URO,		/* Thread ID, User R/O */
+	c13_TID_PRIV,		/* Thread ID, Privileged */
+	c14_CNTKCTL,		/* Timer Control Register (PL1) */
+	c10_AMAIR0,		/* Auxilary Memory Attribute Indirection Reg0 */
+	c10_AMAIR1,		/* Auxilary Memory Attribute Indirection Reg1 */
+	NR_CP15_REGS		/* Number of regs (incl. invalid) */
+};
+
+struct kvm_cpu_context {
+	struct kvm_regs	gp_regs;
+	struct vfp_hard_struct vfp;
+	u32 cp15[NR_CP15_REGS];
+};
+
+typedef struct kvm_cpu_context kvm_cpu_context_t;
 
 struct kvm_vcpu_arch {
-	struct kvm_regs regs;
+	struct kvm_cpu_context ctxt;
 
 	int target; /* Processor target */
 	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
-	/* System control coprocessor (cp15) */
-	u32 cp15[NR_CP15_REGS];
-
 	/* The CPU type we expose to the VM */
 	u32 midr;
 
@@ -111,9 +152,6 @@ struct kvm_vcpu_arch {
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
-	/* Floating point registers (VFP and Advanced SIMD/NEON) */
-	struct vfp_hard_struct vfp_guest;
-
 	/* Host FP context */
 	kvm_cpu_context_t *host_cpu_context;
 
@@ -158,12 +196,14 @@ struct kvm_vcpu_stat {
 	u64 exits;
 };
 
+#define vcpu_cp15(v,r)	(v)->arch.ctxt.cp15[r]
+
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
-u64 kvm_call_hyp(void *hypfn, ...);
+unsigned long kvm_call_hyp(void *hypfn, ...);
 void force_vm_exit(const cpumask_t *mask);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
@@ -220,6 +260,11 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
 
+static inline void __cpu_init_stage2(void)
+{
+	kvm_call_hyp(__init_stage2_translation);
+}
+
 static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 {
 	return 0;
@@ -242,5 +287,20 @@ static inline void kvm_arm_init_debug(void) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+static inline int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+					     struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+					     struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+					     struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
 
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
new file mode 100644
index 000000000000..f0e860761380
--- /dev/null
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -0,0 +1,139 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_HYP_H__
+#define __ARM_KVM_HYP_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_mmu.h>
+#include <asm/vfp.h>
+
+#define __hyp_text __section(.hyp.text) notrace
+
+#define kern_hyp_va(v) (v)
+#define hyp_kern_va(v) (v)
+
+#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
+	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
+#define __ACCESS_CP15_64(Op1, CRm)		\
+	"mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64
+#define __ACCESS_VFP(CRn)			\
+	"mrc", "mcr", __stringify(p10, 7, %0, CRn, cr0, 0), u32
+
+#define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
+#define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
+
+#define __read_sysreg(r, w, c, t) ({				\
+	t __val;						\
+	asm volatile(r " " c : "=r" (__val));			\
+	__val;							\
+})
+#define read_sysreg(...)		__read_sysreg(__VA_ARGS__)
+
+#define write_special(v, r)					\
+	asm volatile("msr " __stringify(r) ", %0" : : "r" (v))
+#define read_special(r) ({					\
+	u32 __val;						\
+	asm volatile("mrs %0, " __stringify(r) : "=r" (__val));	\
+	__val;							\
+})
+
+#define TTBR0		__ACCESS_CP15_64(0, c2)
+#define TTBR1		__ACCESS_CP15_64(1, c2)
+#define VTTBR		__ACCESS_CP15_64(6, c2)
+#define PAR		__ACCESS_CP15_64(0, c7)
+#define CNTV_CVAL	__ACCESS_CP15_64(3, c14)
+#define CNTVOFF		__ACCESS_CP15_64(4, c14)
+
+#define MIDR		__ACCESS_CP15(c0, 0, c0, 0)
+#define CSSELR		__ACCESS_CP15(c0, 2, c0, 0)
+#define VPIDR		__ACCESS_CP15(c0, 4, c0, 0)
+#define VMPIDR		__ACCESS_CP15(c0, 4, c0, 5)
+#define SCTLR		__ACCESS_CP15(c1, 0, c0, 0)
+#define CPACR		__ACCESS_CP15(c1, 0, c0, 2)
+#define HCR		__ACCESS_CP15(c1, 4, c1, 0)
+#define HDCR		__ACCESS_CP15(c1, 4, c1, 1)
+#define HCPTR		__ACCESS_CP15(c1, 4, c1, 2)
+#define HSTR		__ACCESS_CP15(c1, 4, c1, 3)
+#define TTBCR		__ACCESS_CP15(c2, 0, c0, 2)
+#define HTCR		__ACCESS_CP15(c2, 4, c0, 2)
+#define VTCR		__ACCESS_CP15(c2, 4, c1, 2)
+#define DACR		__ACCESS_CP15(c3, 0, c0, 0)
+#define DFSR		__ACCESS_CP15(c5, 0, c0, 0)
+#define IFSR		__ACCESS_CP15(c5, 0, c0, 1)
+#define ADFSR		__ACCESS_CP15(c5, 0, c1, 0)
+#define AIFSR		__ACCESS_CP15(c5, 0, c1, 1)
+#define HSR		__ACCESS_CP15(c5, 4, c2, 0)
+#define DFAR		__ACCESS_CP15(c6, 0, c0, 0)
+#define IFAR		__ACCESS_CP15(c6, 0, c0, 2)
+#define HDFAR		__ACCESS_CP15(c6, 4, c0, 0)
+#define HIFAR		__ACCESS_CP15(c6, 4, c0, 2)
+#define HPFAR		__ACCESS_CP15(c6, 4, c0, 4)
+#define ICIALLUIS	__ACCESS_CP15(c7, 0, c1, 0)
+#define ATS1CPR		__ACCESS_CP15(c7, 0, c8, 0)
+#define TLBIALLIS	__ACCESS_CP15(c8, 0, c3, 0)
+#define TLBIALLNSNHIS	__ACCESS_CP15(c8, 4, c3, 4)
+#define PRRR		__ACCESS_CP15(c10, 0, c2, 0)
+#define NMRR		__ACCESS_CP15(c10, 0, c2, 1)
+#define AMAIR0		__ACCESS_CP15(c10, 0, c3, 0)
+#define AMAIR1		__ACCESS_CP15(c10, 0, c3, 1)
+#define VBAR		__ACCESS_CP15(c12, 0, c0, 0)
+#define CID		__ACCESS_CP15(c13, 0, c0, 1)
+#define TID_URW		__ACCESS_CP15(c13, 0, c0, 2)
+#define TID_URO		__ACCESS_CP15(c13, 0, c0, 3)
+#define TID_PRIV	__ACCESS_CP15(c13, 0, c0, 4)
+#define HTPIDR		__ACCESS_CP15(c13, 4, c0, 2)
+#define CNTKCTL		__ACCESS_CP15(c14, 0, c1, 0)
+#define CNTV_CTL	__ACCESS_CP15(c14, 0, c3, 1)
+#define CNTHCTL		__ACCESS_CP15(c14, 4, c1, 0)
+
+#define VFP_FPEXC	__ACCESS_VFP(FPEXC)
+
+/* AArch64 compatibility macros, only for the timer so far */
+#define read_sysreg_el0(r)		read_sysreg(r##_el0)
+#define write_sysreg_el0(v, r)		write_sysreg(v, r##_el0)
+
+#define cntv_ctl_el0			CNTV_CTL
+#define cntv_cval_el0			CNTV_CVAL
+#define cntvoff_el2			CNTVOFF
+#define cnthctl_el2			CNTHCTL
+
+void __timer_save_state(struct kvm_vcpu *vcpu);
+void __timer_restore_state(struct kvm_vcpu *vcpu);
+
+void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
+
+void __sysreg_save_state(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
+
+void asmlinkage __vfp_save_state(struct vfp_hard_struct *vfp);
+void asmlinkage __vfp_restore_state(struct vfp_hard_struct *vfp);
+static inline bool __vfp_enabled(void)
+{
+	return !(read_sysreg(HCPTR) & (HCPTR_TCP(11) | HCPTR_TCP(10)));
+}
+
+void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt);
+void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt);
+
+int asmlinkage __guest_enter(struct kvm_vcpu *vcpu,
+			     struct kvm_cpu_context *host);
+int asmlinkage __hyp_do_panic(const char *, int, u32);
+
+#endif /* __ARM_KVM_HYP_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index a520b7987a29..da44be9db4fa 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -179,7 +179,7 @@ struct kvm;
 
 static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
-	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
+	return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101;
 }
 
 static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
index 4371f45c5784..d4ceaf5f299b 100644
--- a/arch/arm/include/asm/virt.h
+++ b/arch/arm/include/asm/virt.h
@@ -74,6 +74,15 @@ static inline bool is_hyp_mode_mismatched(void)
 {
 	return !!(__boot_cpu_mode & BOOT_CPU_MODE_MISMATCH);
 }
+
+static inline bool is_kernel_in_hyp_mode(void)
+{
+	return false;
+}
+
+/* The section containing the hypervisor text */
+extern char __hyp_text_start[];
+extern char __hyp_text_end[];
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index 0375c8caa061..9408a994cc91 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page);
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
 	/*
-	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * multiple Xen page, it's not possible to have a mix of local and
-	 * foreign Xen page. So if the first xen_pfn == mfn the page is local
-	 * otherwise it's a foreign page grant-mapped in dom0. If the page is
-	 * local we can safely call the native dma_ops function, otherwise we
-	 * call the xen specific function.
+	 * Dom0 is mapped 1:1, while the Linux page can span across
+	 * multiple Xen pages, it's not possible for it to contain a
+	 * mix of local and foreign Xen pages. So if the first xen_pfn
+	 * == mfn the page is local otherwise it's a foreign page
+	 * grant-mapped in dom0. If the page is local we can safely
+	 * call the native dma_ops function, otherwise we call the xen
+	 * specific function.
 	 */
 	if (local)
 		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 871b8267d211..27d05813ff09 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -170,41 +170,11 @@ int main(void)
   DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
   BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
-  DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
-  DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
-  DEFINE(VCPU_CP15,		offsetof(struct kvm_vcpu, arch.cp15));
-  DEFINE(VCPU_VFP_GUEST,	offsetof(struct kvm_vcpu, arch.vfp_guest));
-  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.host_cpu_context));
-  DEFINE(VCPU_REGS,		offsetof(struct kvm_vcpu, arch.regs));
-  DEFINE(VCPU_USR_REGS,		offsetof(struct kvm_vcpu, arch.regs.usr_regs));
-  DEFINE(VCPU_SVC_REGS,		offsetof(struct kvm_vcpu, arch.regs.svc_regs));
-  DEFINE(VCPU_ABT_REGS,		offsetof(struct kvm_vcpu, arch.regs.abt_regs));
-  DEFINE(VCPU_UND_REGS,		offsetof(struct kvm_vcpu, arch.regs.und_regs));
-  DEFINE(VCPU_IRQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.irq_regs));
-  DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
-  DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
-  DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
-  DEFINE(VCPU_HCR,		offsetof(struct kvm_vcpu, arch.hcr));
-  DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
-  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
-  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
-  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.fault.hpfar));
-  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
-  DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
-  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
-  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
-  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
-  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
-  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
-  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
-  DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
-  DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
-  DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
-  DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
-  DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
-  DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
-  DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
+  DEFINE(VCPU_GUEST_CTXT,	offsetof(struct kvm_vcpu, arch.ctxt));
+  DEFINE(VCPU_HOST_CTXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
+  DEFINE(CPU_CTXT_VFP,		offsetof(struct kvm_cpu_context, vfp));
+  DEFINE(CPU_CTXT_GP_REGS,	offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(GP_REGS_USR,		offsetof(struct kvm_regs, usr_regs));
 #endif
   BLANK();
 #ifdef CONFIG_VDSO
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 8b60fde5ce48..b4139cbbbdd9 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -18,6 +18,11 @@
 	*(.proc.info.init)						\
 	VMLINUX_SYMBOL(__proc_info_end) = .;
 
+#define HYPERVISOR_TEXT							\
+	VMLINUX_SYMBOL(__hyp_text_start) = .;				\
+	*(.hyp.text)							\
+	VMLINUX_SYMBOL(__hyp_text_end) = .;
+
 #define IDMAP_TEXT							\
 	ALIGN_FUNCTION();						\
 	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
@@ -108,6 +113,7 @@ SECTIONS
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT
+			HYPERVISOR_TEXT
 			KPROBES_TEXT
 			*(.gnu.warning)
 			*(.glue_7)
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index c5eef02c52ba..eb1bf4309c13 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -17,6 +17,7 @@ AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 KVM := ../../../virt/kvm
 kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 
+obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index dda1959f0dde..9ca653e34d8c 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/kvm.h>
 #include <trace/events/kvm.h>
+#include <kvm/arm_pmu.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -265,6 +266,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
+	kvm_pmu_vcpu_destroy(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
@@ -320,6 +322,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;
 
 	kvm_arm_set_running_vcpu(NULL);
+	kvm_timer_vcpu_put(vcpu);
 }
 
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
@@ -577,6 +580,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_pmu_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
@@ -593,6 +597,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
 			vcpu->arch.power_off || vcpu->arch.pause) {
 			local_irq_enable();
+			kvm_pmu_sync_hwstate(vcpu);
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			preempt_enable();
@@ -642,10 +647,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 
 		/*
-		 * We must sync the timer state before the vgic state so that
-		 * the vgic can properly sample the updated state of the
+		 * We must sync the PMU and timer state before the vgic state so
+		 * that the vgic can properly sample the updated state of the
 		 * interrupt line.
 		 */
+		kvm_pmu_sync_hwstate(vcpu);
 		kvm_timer_sync_hwstate(vcpu);
 
 		kvm_vgic_sync_hwstate(vcpu);
@@ -823,11 +829,54 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
+	struct kvm_device_attr attr;
 
 	switch (ioctl) {
 	case KVM_ARM_VCPU_INIT: {
@@ -870,6 +919,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			return -E2BIG;
 		return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
 	}
+	case KVM_SET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_set_attr(vcpu, &attr);
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_get_attr(vcpu, &attr);
+	}
+	case KVM_HAS_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_has_attr(vcpu, &attr);
+	}
 	default:
 		return -EINVAL;
 	}
@@ -967,6 +1031,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 }
 
+static void cpu_init_stage2(void *dummy)
+{
+	__cpu_init_stage2();
+}
+
 static void cpu_init_hyp_mode(void *dummy)
 {
 	phys_addr_t boot_pgd_ptr;
@@ -985,6 +1054,7 @@ static void cpu_init_hyp_mode(void *dummy)
 	vector_ptr = (unsigned long)__kvm_hyp_vector;
 
 	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+	__cpu_init_stage2();
 
 	kvm_arm_init_debug();
 }
@@ -1035,6 +1105,82 @@ static inline void hyp_cpu_pm_init(void)
 }
 #endif
 
+static void teardown_common_resources(void)
+{
+	free_percpu(kvm_host_cpu_state);
+}
+
+static int init_common_resources(void)
+{
+	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
+	if (!kvm_host_cpu_state) {
+		kvm_err("Cannot allocate host CPU state\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int init_subsystems(void)
+{
+	int err;
+
+	/*
+	 * Init HYP view of VGIC
+	 */
+	err = kvm_vgic_hyp_init();
+	switch (err) {
+	case 0:
+		vgic_present = true;
+		break;
+	case -ENODEV:
+	case -ENXIO:
+		vgic_present = false;
+		break;
+	default:
+		return err;
+	}
+
+	/*
+	 * Init HYP architected timer support
+	 */
+	err = kvm_timer_hyp_init();
+	if (err)
+		return err;
+
+	kvm_perf_init();
+	kvm_coproc_table_init();
+
+	return 0;
+}
+
+static void teardown_hyp_mode(void)
+{
+	int cpu;
+
+	if (is_kernel_in_hyp_mode())
+		return;
+
+	free_hyp_pgds();
+	for_each_possible_cpu(cpu)
+		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+}
+
+static int init_vhe_mode(void)
+{
+	/*
+	 * Execute the init code on each CPU.
+	 */
+	on_each_cpu(cpu_init_stage2, NULL, 1);
+
+	/* set size of VMID supported by CPU */
+	kvm_vmid_bits = kvm_get_vmid_bits();
+	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
+	kvm_info("VHE mode initialized successfully\n");
+	return 0;
+}
+
 /**
  * Inits Hyp-mode on all online CPUs
  */
@@ -1065,7 +1211,7 @@ static int init_hyp_mode(void)
 		stack_page = __get_free_page(GFP_KERNEL);
 		if (!stack_page) {
 			err = -ENOMEM;
-			goto out_free_stack_pages;
+			goto out_err;
 		}
 
 		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
@@ -1074,16 +1220,16 @@ static int init_hyp_mode(void)
 	/*
 	 * Map the Hyp-code called directly from the host
 	 */
-	err = create_hyp_mappings(__kvm_hyp_code_start, __kvm_hyp_code_end);
+	err = create_hyp_mappings(__hyp_text_start, __hyp_text_end);
 	if (err) {
 		kvm_err("Cannot map world-switch code\n");
-		goto out_free_mappings;
+		goto out_err;
 	}
 
 	err = create_hyp_mappings(__start_rodata, __end_rodata);
 	if (err) {
 		kvm_err("Cannot map rodata section\n");
-		goto out_free_mappings;
+		goto out_err;
 	}
 
 	/*
@@ -1095,20 +1241,10 @@ static int init_hyp_mode(void)
 
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
-			goto out_free_mappings;
+			goto out_err;
 		}
 	}
 
-	/*
-	 * Map the host CPU structures
-	 */
-	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
-	if (!kvm_host_cpu_state) {
-		err = -ENOMEM;
-		kvm_err("Cannot allocate host CPU state\n");
-		goto out_free_mappings;
-	}
-
 	for_each_possible_cpu(cpu) {
 		kvm_cpu_context_t *cpu_ctxt;
 
@@ -1117,7 +1253,7 @@ static int init_hyp_mode(void)
 
 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
-			goto out_free_context;
+			goto out_err;
 		}
 	}
 
@@ -1126,34 +1262,22 @@ static int init_hyp_mode(void)
 	 */
 	on_each_cpu(cpu_init_hyp_mode, NULL, 1);
 
-	/*
-	 * Init HYP view of VGIC
-	 */
-	err = kvm_vgic_hyp_init();
-	switch (err) {
-	case 0:
-		vgic_present = true;
-		break;
-	case -ENODEV:
-	case -ENXIO:
-		vgic_present = false;
-		break;
-	default:
-		goto out_free_context;
-	}
-
-	/*
-	 * Init HYP architected timer support
-	 */
-	err = kvm_timer_hyp_init();
-	if (err)
-		goto out_free_context;
-
 #ifndef CONFIG_HOTPLUG_CPU
 	free_boot_hyp_pgd();
 #endif
 
-	kvm_perf_init();
+	cpu_notifier_register_begin();
+
+	err = __register_cpu_notifier(&hyp_init_cpu_nb);
+
+	cpu_notifier_register_done();
+
+	if (err) {
+		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+		goto out_err;
+	}
+
+	hyp_cpu_pm_init();
 
 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
@@ -1162,14 +1286,9 @@ static int init_hyp_mode(void)
 	kvm_info("Hyp mode initialized successfully\n");
 
 	return 0;
-out_free_context:
-	free_percpu(kvm_host_cpu_state);
-out_free_mappings:
-	free_hyp_pgds();
-out_free_stack_pages:
-	for_each_possible_cpu(cpu)
-		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+
 out_err:
+	teardown_hyp_mode();
 	kvm_err("error initializing Hyp mode: %d\n", err);
 	return err;
 }
@@ -1213,26 +1332,27 @@ int kvm_arch_init(void *opaque)
 		}
 	}
 
-	cpu_notifier_register_begin();
-
-	err = init_hyp_mode();
+	err = init_common_resources();
 	if (err)
-		goto out_err;
+		return err;
 
-	err = __register_cpu_notifier(&hyp_init_cpu_nb);
-	if (err) {
-		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+	if (is_kernel_in_hyp_mode())
+		err = init_vhe_mode();
+	else
+		err = init_hyp_mode();
+	if (err)
 		goto out_err;
-	}
-
-	cpu_notifier_register_done();
 
-	hyp_cpu_pm_init();
+	err = init_subsystems();
+	if (err)
+		goto out_hyp;
 
-	kvm_coproc_table_init();
 	return 0;
+
+out_hyp:
+	teardown_hyp_mode();
 out_err:
-	cpu_notifier_register_done();
+	teardown_common_resources();
 	return err;
 }
 
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index f3d88dc388bc..1bb2b79c01ff 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -16,6 +16,8 @@
  * along with this program; if not, write to the Free Software
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
+
+#include <linux/bsearch.h>
 #include <linux/mm.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
@@ -54,8 +56,8 @@ static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu,
 				       const struct coproc_reg *r,
 				       u64 val)
 {
-	vcpu->arch.cp15[r->reg] = val & 0xffffffff;
-	vcpu->arch.cp15[r->reg + 1] = val >> 32;
+	vcpu_cp15(vcpu, r->reg) = val & 0xffffffff;
+	vcpu_cp15(vcpu, r->reg + 1) = val >> 32;
 }
 
 static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu,
@@ -63,9 +65,9 @@ static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu,
 {
 	u64 val;
 
-	val = vcpu->arch.cp15[r->reg + 1];
+	val = vcpu_cp15(vcpu, r->reg + 1);
 	val = val << 32;
-	val = val | vcpu->arch.cp15[r->reg];
+	val = val | vcpu_cp15(vcpu, r->reg);
 	return val;
 }
 
@@ -104,7 +106,7 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 	 * vcpu_id, but we read the 'U' bit from the underlying
 	 * hardware directly.
 	 */
-	vcpu->arch.cp15[c0_MPIDR] = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) |
+	vcpu_cp15(vcpu, c0_MPIDR) = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) |
 				     ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) |
 				     (vcpu->vcpu_id & 3));
 }
@@ -117,7 +119,7 @@ static bool access_actlr(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR];
+	*vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c1_ACTLR);
 	return true;
 }
 
@@ -139,7 +141,7 @@ static bool access_l2ctlr(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR];
+	*vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c9_L2CTLR);
 	return true;
 }
 
@@ -156,7 +158,7 @@ static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 	ncores = min(ncores, 3U);
 	l2ctlr |= (ncores & 3) << 24;
 
-	vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
+	vcpu_cp15(vcpu, c9_L2CTLR) = l2ctlr;
 }
 
 static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
@@ -171,7 +173,7 @@ static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 	else
 		actlr &= ~(1U << 6);
 
-	vcpu->arch.cp15[c1_ACTLR] = actlr;
+	vcpu_cp15(vcpu, c1_ACTLR) = actlr;
 }
 
 /*
@@ -218,9 +220,9 @@ bool access_vm_reg(struct kvm_vcpu *vcpu,
 
 	BUG_ON(!p->is_write);
 
-	vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
+	vcpu_cp15(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt1);
 	if (p->is_64bit)
-		vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
+		vcpu_cp15(vcpu, r->reg + 1) = *vcpu_reg(vcpu, p->Rt2);
 
 	kvm_toggle_cache(vcpu, was_enabled);
 	return true;
@@ -381,17 +383,26 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
 };
 
+static int check_reg_table(const struct coproc_reg *table, unsigned int n)
+{
+	unsigned int i;
+
+	for (i = 1; i < n; i++) {
+		if (cmp_reg(&table[i-1], &table[i]) >= 0) {
+			kvm_err("reg table %p out of order (%d)\n", table, i - 1);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 /* Target specific emulation tables */
 static struct kvm_coproc_target_table *target_tables[KVM_ARM_NUM_TARGETS];
 
 void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table)
 {
-	unsigned int i;
-
-	for (i = 1; i < table->num; i++)
-		BUG_ON(cmp_reg(&table->table[i-1],
-			       &table->table[i]) >= 0);
-
+	BUG_ON(check_reg_table(table->table, table->num));
 	target_tables[table->target] = table;
 }
 
@@ -405,29 +416,32 @@ static const struct coproc_reg *get_target_table(unsigned target, size_t *num)
 	return table->table;
 }
 
+#define reg_to_match_value(x)						\
+	({								\
+		unsigned long val;					\
+		val  = (x)->CRn << 11;					\
+		val |= (x)->CRm << 7;					\
+		val |= (x)->Op1 << 4;					\
+		val |= (x)->Op2 << 1;					\
+		val |= !(x)->is_64bit;					\
+		val;							\
+	 })
+
+static int match_reg(const void *key, const void *elt)
+{
+	const unsigned long pval = (unsigned long)key;
+	const struct coproc_reg *r = elt;
+
+	return pval - reg_to_match_value(r);
+}
+
 static const struct coproc_reg *find_reg(const struct coproc_params *params,
 					 const struct coproc_reg table[],
 					 unsigned int num)
 {
-	unsigned int i;
-
-	for (i = 0; i < num; i++) {
-		const struct coproc_reg *r = &table[i];
-
-		if (params->is_64bit != r->is_64)
-			continue;
-		if (params->CRn != r->CRn)
-			continue;
-		if (params->CRm != r->CRm)
-			continue;
-		if (params->Op1 != r->Op1)
-			continue;
-		if (params->Op2 != r->Op2)
-			continue;
+	unsigned long pval = reg_to_match_value(params);
 
-		return r;
-	}
-	return NULL;
+	return bsearch((void *)pval, table, num, sizeof(table[0]), match_reg);
 }
 
 static int emulate_cp15(struct kvm_vcpu *vcpu,
@@ -645,6 +659,9 @@ static struct coproc_reg invariant_cp15[] = {
 	{ CRn( 0), CRm( 0), Op1( 0), Op2( 3), is32, NULL, get_TLBTR },
 	{ CRn( 0), CRm( 0), Op1( 0), Op2( 6), is32, NULL, get_REVIDR },
 
+	{ CRn( 0), CRm( 0), Op1( 1), Op2( 1), is32, NULL, get_CLIDR },
+	{ CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR },
+
 	{ CRn( 0), CRm( 1), Op1( 0), Op2( 0), is32, NULL, get_ID_PFR0 },
 	{ CRn( 0), CRm( 1), Op1( 0), Op2( 1), is32, NULL, get_ID_PFR1 },
 	{ CRn( 0), CRm( 1), Op1( 0), Op2( 2), is32, NULL, get_ID_DFR0 },
@@ -660,9 +677,6 @@ static struct coproc_reg invariant_cp15[] = {
 	{ CRn( 0), CRm( 2), Op1( 0), Op2( 3), is32, NULL, get_ID_ISAR3 },
 	{ CRn( 0), CRm( 2), Op1( 0), Op2( 4), is32, NULL, get_ID_ISAR4 },
 	{ CRn( 0), CRm( 2), Op1( 0), Op2( 5), is32, NULL, get_ID_ISAR5 },
-
-	{ CRn( 0), CRm( 0), Op1( 1), Op2( 1), is32, NULL, get_CLIDR },
-	{ CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR },
 };
 
 /*
@@ -901,7 +915,7 @@ static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr)
 	if (vfpid < num_fp_regs()) {
 		if (KVM_REG_SIZE(id) != 8)
 			return -ENOENT;
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpregs[vfpid],
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpregs[vfpid],
 				   id);
 	}
 
@@ -911,13 +925,13 @@ static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr)
 
 	switch (vfpid) {
 	case KVM_REG_ARM_VFP_FPEXC:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpexc, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpexc, id);
 	case KVM_REG_ARM_VFP_FPSCR:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpscr, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpscr, id);
 	case KVM_REG_ARM_VFP_FPINST:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpinst, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst, id);
 	case KVM_REG_ARM_VFP_FPINST2:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpinst2, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst2, id);
 	case KVM_REG_ARM_VFP_MVFR0:
 		val = fmrx(MVFR0);
 		return reg_to_user(uaddr, &val, id);
@@ -945,7 +959,7 @@ static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr)
 	if (vfpid < num_fp_regs()) {
 		if (KVM_REG_SIZE(id) != 8)
 			return -ENOENT;
-		return reg_from_user(&vcpu->arch.vfp_guest.fpregs[vfpid],
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpregs[vfpid],
 				     uaddr, id);
 	}
 
@@ -955,13 +969,13 @@ static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr)
 
 	switch (vfpid) {
 	case KVM_REG_ARM_VFP_FPEXC:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpexc, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpexc, uaddr, id);
 	case KVM_REG_ARM_VFP_FPSCR:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpscr, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpscr, uaddr, id);
 	case KVM_REG_ARM_VFP_FPINST:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpinst, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst, uaddr, id);
 	case KVM_REG_ARM_VFP_FPINST2:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpinst2, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst2, uaddr, id);
 	/* These are invariant. */
 	case KVM_REG_ARM_VFP_MVFR0:
 		if (reg_from_user(&val, uaddr, id))
@@ -1030,7 +1044,7 @@ int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		val = vcpu_cp15_reg64_get(vcpu, r);
 		ret = reg_to_user(uaddr, &val, reg->id);
 	} else if (KVM_REG_SIZE(reg->id) == 4) {
-		ret = reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+		ret = reg_to_user(uaddr, &vcpu_cp15(vcpu, r->reg), reg->id);
 	}
 
 	return ret;
@@ -1060,7 +1074,7 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		if (!ret)
 			vcpu_cp15_reg64_set(vcpu, r, val);
 	} else if (KVM_REG_SIZE(reg->id) == 4) {
-		ret = reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+		ret = reg_from_user(&vcpu_cp15(vcpu, r->reg), uaddr, reg->id);
 	}
 
 	return ret;
@@ -1096,7 +1110,7 @@ static int write_demux_regids(u64 __user *uindices)
 static u64 cp15_to_index(const struct coproc_reg *reg)
 {
 	u64 val = KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT);
-	if (reg->is_64) {
+	if (reg->is_64bit) {
 		val |= KVM_REG_SIZE_U64;
 		val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
 		/*
@@ -1210,8 +1224,8 @@ void kvm_coproc_table_init(void)
 	unsigned int i;
 
 	/* Make sure tables are unique and in order. */
-	for (i = 1; i < ARRAY_SIZE(cp15_regs); i++)
-		BUG_ON(cmp_reg(&cp15_regs[i-1], &cp15_regs[i]) >= 0);
+	BUG_ON(check_reg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
+	BUG_ON(check_reg_table(invariant_cp15, ARRAY_SIZE(invariant_cp15)));
 
 	/* We abuse the reset function to overwrite the table itself. */
 	for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++)
@@ -1248,7 +1262,7 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu)
 	const struct coproc_reg *table;
 
 	/* Catch someone adding a register without putting in reset entry. */
-	memset(vcpu->arch.cp15, 0x42, sizeof(vcpu->arch.cp15));
+	memset(vcpu->arch.ctxt.cp15, 0x42, sizeof(vcpu->arch.ctxt.cp15));
 
 	/* Generic chip reset first (so target could override). */
 	reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs));
@@ -1257,6 +1271,6 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu)
 	reset_coproc_regs(vcpu, table, num);
 
 	for (num = 1; num < NR_CP15_REGS; num++)
-		if (vcpu->arch.cp15[num] == 0x42424242)
-			panic("Didn't reset vcpu->arch.cp15[%zi]", num);
+		if (vcpu_cp15(vcpu, num) == 0x42424242)
+			panic("Didn't reset vcpu_cp15(vcpu, %zi)", num);
 }
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index 88d24a3a9778..eef1759c2b65 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -37,7 +37,7 @@ struct coproc_reg {
 	unsigned long Op1;
 	unsigned long Op2;
 
-	bool is_64;
+	bool is_64bit;
 
 	/* Trapped access from guest, if non-NULL. */
 	bool (*access)(struct kvm_vcpu *,
@@ -47,7 +47,7 @@ struct coproc_reg {
 	/* Initialization for vcpu. */
 	void (*reset)(struct kvm_vcpu *, const struct coproc_reg *);
 
-	/* Index into vcpu->arch.cp15[], or 0 if we don't need to save it. */
+	/* Index into vcpu_cp15(vcpu, ...), or 0 if we don't need to save it. */
 	unsigned long reg;
 
 	/* Value (usually reset value) */
@@ -104,25 +104,25 @@ static inline void reset_unknown(struct kvm_vcpu *vcpu,
 				 const struct coproc_reg *r)
 {
 	BUG_ON(!r->reg);
-	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15));
-	vcpu->arch.cp15[r->reg] = 0xdecafbad;
+	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15));
+	vcpu_cp15(vcpu, r->reg) = 0xdecafbad;
 }
 
 static inline void reset_val(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 {
 	BUG_ON(!r->reg);
-	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15));
-	vcpu->arch.cp15[r->reg] = r->val;
+	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15));
+	vcpu_cp15(vcpu, r->reg) = r->val;
 }
 
 static inline void reset_unknown64(struct kvm_vcpu *vcpu,
 				   const struct coproc_reg *r)
 {
 	BUG_ON(!r->reg);
-	BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.cp15));
+	BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.ctxt.cp15));
 
-	vcpu->arch.cp15[r->reg] = 0xdecafbad;
-	vcpu->arch.cp15[r->reg+1] = 0xd0c0ffee;
+	vcpu_cp15(vcpu, r->reg) = 0xdecafbad;
+	vcpu_cp15(vcpu, r->reg+1) = 0xd0c0ffee;
 }
 
 static inline int cmp_reg(const struct coproc_reg *i1,
@@ -141,7 +141,7 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 		return i1->Op1 - i2->Op1;
 	if (i1->Op2 != i2->Op2)
 		return i1->Op2 - i2->Op2;
-	return i2->is_64 - i1->is_64;
+	return i2->is_64bit - i1->is_64bit;
 }
 
 
@@ -150,8 +150,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 #define CRm64(_x)       .CRn = _x, .CRm = 0
 #define Op1(_x) 	.Op1 = _x
 #define Op2(_x) 	.Op2 = _x
-#define is64		.is_64 = true
-#define is32		.is_64 = false
+#define is64		.is_64bit = true
+#define is32		.is_64bit = false
 
 bool access_vm_reg(struct kvm_vcpu *vcpu,
 		   const struct coproc_params *p,
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index dc99159857b4..a494def3f195 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -112,7 +112,7 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = {
  */
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	unsigned long *reg_array = (unsigned long *)&vcpu->arch.regs;
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs;
 	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
 
 	switch (mode) {
@@ -147,15 +147,15 @@ unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu)
 	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
 	switch (mode) {
 	case SVC_MODE:
-		return &vcpu->arch.regs.KVM_ARM_SVC_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_SVC_spsr;
 	case ABT_MODE:
-		return &vcpu->arch.regs.KVM_ARM_ABT_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_ABT_spsr;
 	case UND_MODE:
-		return &vcpu->arch.regs.KVM_ARM_UND_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_UND_spsr;
 	case IRQ_MODE:
-		return &vcpu->arch.regs.KVM_ARM_IRQ_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_IRQ_spsr;
 	case FIQ_MODE:
-		return &vcpu->arch.regs.KVM_ARM_FIQ_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_FIQ_spsr;
 	default:
 		BUG();
 	}
@@ -266,8 +266,8 @@ void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
 
 static u32 exc_vector_base(struct kvm_vcpu *vcpu)
 {
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
-	u32 vbar = vcpu->arch.cp15[c12_VBAR];
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
+	u32 vbar = vcpu_cp15(vcpu, c12_VBAR);
 
 	if (sctlr & SCTLR_V)
 		return 0xffff0000;
@@ -282,7 +282,7 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu)
 static void kvm_update_psr(struct kvm_vcpu *vcpu, unsigned long mode)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
 	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | mode;
 
@@ -357,22 +357,22 @@ static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 
 	if (is_pabt) {
 		/* Set IFAR and IFSR */
-		vcpu->arch.cp15[c6_IFAR] = addr;
-		is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
+		vcpu_cp15(vcpu, c6_IFAR) = addr;
+		is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
 		/* Always give debug fault for now - should give guest a clue */
 		if (is_lpae)
-			vcpu->arch.cp15[c5_IFSR] = 1 << 9 | 0x22;
+			vcpu_cp15(vcpu, c5_IFSR) = 1 << 9 | 0x22;
 		else
-			vcpu->arch.cp15[c5_IFSR] = 2;
+			vcpu_cp15(vcpu, c5_IFSR) = 2;
 	} else { /* !iabt */
 		/* Set DFAR and DFSR */
-		vcpu->arch.cp15[c6_DFAR] = addr;
-		is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
+		vcpu_cp15(vcpu, c6_DFAR) = addr;
+		is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
 		/* Always give debug fault for now - should give guest a clue */
 		if (is_lpae)
-			vcpu->arch.cp15[c5_DFSR] = 1 << 9 | 0x22;
+			vcpu_cp15(vcpu, c5_DFSR) = 1 << 9 | 0x22;
 		else
-			vcpu->arch.cp15[c5_DFSR] = 2;
+			vcpu_cp15(vcpu, c5_DFSR) = 2;
 	}
 
 }
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 5fa69d7bae58..12cbb6824443 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -25,7 +25,6 @@
 #include <asm/cputype.h>
 #include <asm/uaccess.h>
 #include <asm/kvm.h>
-#include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 
@@ -55,7 +54,7 @@ static u64 core_reg_offset_from_id(u64 id)
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u32 __user *uaddr = (u32 __user *)(long)reg->addr;
-	struct kvm_regs *regs = &vcpu->arch.regs;
+	struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs;
 	u64 off;
 
 	if (KVM_REG_SIZE(reg->id) != 4)
@@ -72,7 +71,7 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u32 __user *uaddr = (u32 __user *)(long)reg->addr;
-	struct kvm_regs *regs = &vcpu->arch.regs;
+	struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs;
 	u64 off, val;
 
 	if (KVM_REG_SIZE(reg->id) != 4)
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 3ede90d8b20b..3f1ef0dbc899 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -147,13 +147,6 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	switch (exception_index) {
 	case ARM_EXCEPTION_IRQ:
 		return 1;
-	case ARM_EXCEPTION_UNDEFINED:
-		kvm_err("Undefined exception in Hyp mode at: %#08lx\n",
-			kvm_vcpu_get_hyp_pc(vcpu));
-		BUG();
-		panic("KVM: Hypervisor undefined exception!\n");
-	case ARM_EXCEPTION_DATA_ABORT:
-	case ARM_EXCEPTION_PREF_ABORT:
 	case ARM_EXCEPTION_HVC:
 		/*
 		 * See ARM ARM B1.14.1: "Hyp traps on instructions
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
new file mode 100644
index 000000000000..8dfa5f7f9290
--- /dev/null
+++ b/arch/arm/kvm/hyp/Makefile
@@ -0,0 +1,17 @@
+#
+# Makefile for Kernel-based Virtual Machine module, HYP part
+#
+
+KVM=../../../../virt/kvm
+
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+
+obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
+obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += vfp.o
+obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += entry.o
+obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
+obj-$(CONFIG_KVM_ARM_HOST) += switch.o
+obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c
new file mode 100644
index 000000000000..111bda8cdebd
--- /dev/null
+++ b/arch/arm/kvm/hyp/banked-sr.c
@@ -0,0 +1,77 @@
+/*
+ * Original code:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_hyp.h>
+
+__asm__(".arch_extension     virt");
+
+void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->gp_regs.usr_regs.ARM_sp	= read_special(SP_usr);
+	ctxt->gp_regs.usr_regs.ARM_pc	= read_special(ELR_hyp);
+	ctxt->gp_regs.usr_regs.ARM_cpsr	= read_special(SPSR);
+	ctxt->gp_regs.KVM_ARM_SVC_sp	= read_special(SP_svc);
+	ctxt->gp_regs.KVM_ARM_SVC_lr	= read_special(LR_svc);
+	ctxt->gp_regs.KVM_ARM_SVC_spsr	= read_special(SPSR_svc);
+	ctxt->gp_regs.KVM_ARM_ABT_sp	= read_special(SP_abt);
+	ctxt->gp_regs.KVM_ARM_ABT_lr	= read_special(LR_abt);
+	ctxt->gp_regs.KVM_ARM_ABT_spsr	= read_special(SPSR_abt);
+	ctxt->gp_regs.KVM_ARM_UND_sp	= read_special(SP_und);
+	ctxt->gp_regs.KVM_ARM_UND_lr	= read_special(LR_und);
+	ctxt->gp_regs.KVM_ARM_UND_spsr	= read_special(SPSR_und);
+	ctxt->gp_regs.KVM_ARM_IRQ_sp	= read_special(SP_irq);
+	ctxt->gp_regs.KVM_ARM_IRQ_lr	= read_special(LR_irq);
+	ctxt->gp_regs.KVM_ARM_IRQ_spsr	= read_special(SPSR_irq);
+	ctxt->gp_regs.KVM_ARM_FIQ_r8	= read_special(R8_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_r9	= read_special(R9_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_r10	= read_special(R10_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_fp	= read_special(R11_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_ip	= read_special(R12_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_sp	= read_special(SP_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_lr	= read_special(LR_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_spsr	= read_special(SPSR_fiq);
+}
+
+void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt)
+{
+	write_special(ctxt->gp_regs.usr_regs.ARM_sp,	SP_usr);
+	write_special(ctxt->gp_regs.usr_regs.ARM_pc,	ELR_hyp);
+	write_special(ctxt->gp_regs.usr_regs.ARM_cpsr,	SPSR_cxsf);
+	write_special(ctxt->gp_regs.KVM_ARM_SVC_sp,	SP_svc);
+	write_special(ctxt->gp_regs.KVM_ARM_SVC_lr,	LR_svc);
+	write_special(ctxt->gp_regs.KVM_ARM_SVC_spsr,	SPSR_svc);
+	write_special(ctxt->gp_regs.KVM_ARM_ABT_sp,	SP_abt);
+	write_special(ctxt->gp_regs.KVM_ARM_ABT_lr,	LR_abt);
+	write_special(ctxt->gp_regs.KVM_ARM_ABT_spsr,	SPSR_abt);
+	write_special(ctxt->gp_regs.KVM_ARM_UND_sp,	SP_und);
+	write_special(ctxt->gp_regs.KVM_ARM_UND_lr,	LR_und);
+	write_special(ctxt->gp_regs.KVM_ARM_UND_spsr,	SPSR_und);
+	write_special(ctxt->gp_regs.KVM_ARM_IRQ_sp,	SP_irq);
+	write_special(ctxt->gp_regs.KVM_ARM_IRQ_lr,	LR_irq);
+	write_special(ctxt->gp_regs.KVM_ARM_IRQ_spsr,	SPSR_irq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_r8,	R8_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_r9,	R9_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_r10,	R10_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_fp,	R11_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_ip,	R12_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_sp,	SP_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_lr,	LR_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_spsr,	SPSR_fiq);
+}
diff --git a/arch/arm/kvm/hyp/cp15-sr.c b/arch/arm/kvm/hyp/cp15-sr.c
new file mode 100644
index 000000000000..c4782812714c
--- /dev/null
+++ b/arch/arm/kvm/hyp/cp15-sr.c
@@ -0,0 +1,84 @@
+/*
+ * Original code:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_hyp.h>
+
+static u64 *cp15_64(struct kvm_cpu_context *ctxt, int idx)
+{
+	return (u64 *)(ctxt->cp15 + idx);
+}
+
+void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->cp15[c0_MPIDR]		= read_sysreg(VMPIDR);
+	ctxt->cp15[c0_CSSELR]		= read_sysreg(CSSELR);
+	ctxt->cp15[c1_SCTLR]		= read_sysreg(SCTLR);
+	ctxt->cp15[c1_CPACR]		= read_sysreg(CPACR);
+	*cp15_64(ctxt, c2_TTBR0)	= read_sysreg(TTBR0);
+	*cp15_64(ctxt, c2_TTBR1)	= read_sysreg(TTBR1);
+	ctxt->cp15[c2_TTBCR]		= read_sysreg(TTBCR);
+	ctxt->cp15[c3_DACR]		= read_sysreg(DACR);
+	ctxt->cp15[c5_DFSR]		= read_sysreg(DFSR);
+	ctxt->cp15[c5_IFSR]		= read_sysreg(IFSR);
+	ctxt->cp15[c5_ADFSR]		= read_sysreg(ADFSR);
+	ctxt->cp15[c5_AIFSR]		= read_sysreg(AIFSR);
+	ctxt->cp15[c6_DFAR]		= read_sysreg(DFAR);
+	ctxt->cp15[c6_IFAR]		= read_sysreg(IFAR);
+	*cp15_64(ctxt, c7_PAR)		= read_sysreg(PAR);
+	ctxt->cp15[c10_PRRR]		= read_sysreg(PRRR);
+	ctxt->cp15[c10_NMRR]		= read_sysreg(NMRR);
+	ctxt->cp15[c10_AMAIR0]		= read_sysreg(AMAIR0);
+	ctxt->cp15[c10_AMAIR1]		= read_sysreg(AMAIR1);
+	ctxt->cp15[c12_VBAR]		= read_sysreg(VBAR);
+	ctxt->cp15[c13_CID]		= read_sysreg(CID);
+	ctxt->cp15[c13_TID_URW]		= read_sysreg(TID_URW);
+	ctxt->cp15[c13_TID_URO]		= read_sysreg(TID_URO);
+	ctxt->cp15[c13_TID_PRIV]	= read_sysreg(TID_PRIV);
+	ctxt->cp15[c14_CNTKCTL]		= read_sysreg(CNTKCTL);
+}
+
+void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->cp15[c0_MPIDR],	VMPIDR);
+	write_sysreg(ctxt->cp15[c0_CSSELR],	CSSELR);
+	write_sysreg(ctxt->cp15[c1_SCTLR],	SCTLR);
+	write_sysreg(ctxt->cp15[c1_CPACR],	CPACR);
+	write_sysreg(*cp15_64(ctxt, c2_TTBR0),	TTBR0);
+	write_sysreg(*cp15_64(ctxt, c2_TTBR1),	TTBR1);
+	write_sysreg(ctxt->cp15[c2_TTBCR],	TTBCR);
+	write_sysreg(ctxt->cp15[c3_DACR],	DACR);
+	write_sysreg(ctxt->cp15[c5_DFSR],	DFSR);
+	write_sysreg(ctxt->cp15[c5_IFSR],	IFSR);
+	write_sysreg(ctxt->cp15[c5_ADFSR],	ADFSR);
+	write_sysreg(ctxt->cp15[c5_AIFSR],	AIFSR);
+	write_sysreg(ctxt->cp15[c6_DFAR],	DFAR);
+	write_sysreg(ctxt->cp15[c6_IFAR],	IFAR);
+	write_sysreg(*cp15_64(ctxt, c7_PAR),	PAR);
+	write_sysreg(ctxt->cp15[c10_PRRR],	PRRR);
+	write_sysreg(ctxt->cp15[c10_NMRR],	NMRR);
+	write_sysreg(ctxt->cp15[c10_AMAIR0],	AMAIR0);
+	write_sysreg(ctxt->cp15[c10_AMAIR1],	AMAIR1);
+	write_sysreg(ctxt->cp15[c12_VBAR],	VBAR);
+	write_sysreg(ctxt->cp15[c13_CID],	CID);
+	write_sysreg(ctxt->cp15[c13_TID_URW],	TID_URW);
+	write_sysreg(ctxt->cp15[c13_TID_URO],	TID_URO);
+	write_sysreg(ctxt->cp15[c13_TID_PRIV],	TID_PRIV);
+	write_sysreg(ctxt->cp15[c14_CNTKCTL],	CNTKCTL);
+}
diff --git a/arch/arm/kvm/hyp/entry.S b/arch/arm/kvm/hyp/entry.S
new file mode 100644
index 000000000000..21c238871c9e
--- /dev/null
+++ b/arch/arm/kvm/hyp/entry.S
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm_arm.h>
+
+	.arch_extension     virt
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+#define USR_REGS_OFFSET		(CPU_CTXT_GP_REGS + GP_REGS_USR)
+
+/* int __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host) */
+ENTRY(__guest_enter)
+	@ Save host registers
+	add	r1, r1, #(USR_REGS_OFFSET + S_R4)
+	stm	r1!, {r4-r12}
+	str	lr, [r1, #4]	@ Skip SP_usr (already saved)
+
+	@ Restore guest registers
+	add	r0, r0,  #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0)
+	ldr	lr, [r0, #S_LR]
+	ldm	r0, {r0-r12}
+
+	clrex
+	eret
+ENDPROC(__guest_enter)
+
+ENTRY(__guest_exit)
+	/*
+	 * return convention:
+	 * guest r0, r1, r2 saved on the stack
+	 * r0: vcpu pointer
+	 * r1: exception code
+	 */
+
+	add	r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R3)
+	stm	r2!, {r3-r12}
+	str	lr, [r2, #4]
+	add	r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0)
+	pop	{r3, r4, r5}		@ r0, r1, r2
+	stm	r2, {r3-r5}
+
+	ldr	r0, [r0, #VCPU_HOST_CTXT]
+	add	r0, r0, #(USR_REGS_OFFSET + S_R4)
+	ldm	r0!, {r4-r12}
+	ldr	lr, [r0, #4]
+
+	mov	r0, r1
+	bx	lr
+ENDPROC(__guest_exit)
+
+/*
+ * If VFPv3 support is not available, then we will not switch the VFP
+ * registers; however cp10 and cp11 accesses will still trap and fallback
+ * to the regular coprocessor emulation code, which currently will
+ * inject an undefined exception to the guest.
+ */
+#ifdef CONFIG_VFPv3
+ENTRY(__vfp_guest_restore)
+	push	{r3, r4, lr}
+
+	@ NEON/VFP used.  Turn on VFP access.
+	mrc	p15, 4, r1, c1, c1, 2		@ HCPTR
+	bic	r1, r1, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	mcr	p15, 4, r1, c1, c1, 2		@ HCPTR
+	isb
+
+	@ Switch VFP/NEON hardware state to the guest's
+	mov	r4, r0
+	ldr	r0, [r0, #VCPU_HOST_CTXT]
+	add	r0, r0, #CPU_CTXT_VFP
+	bl	__vfp_save_state
+	add	r0, r4, #(VCPU_GUEST_CTXT + CPU_CTXT_VFP)
+	bl	__vfp_restore_state
+
+	pop	{r3, r4, lr}
+	pop	{r0, r1, r2}
+	clrex
+	eret
+ENDPROC(__vfp_guest_restore)
+#endif
+
+	.popsection
+
diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S
new file mode 100644
index 000000000000..78091383a5d9
--- /dev/null
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -0,0 +1,169 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.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, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/linkage.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+
+	.arch_extension     virt
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+.macro load_vcpu	reg
+	mrc	p15, 4, \reg, c13, c0, 2	@ HTPIDR
+.endm
+
+/********************************************************************
+ * Hypervisor exception vector and handlers
+ *
+ *
+ * The KVM/ARM Hypervisor ABI is defined as follows:
+ *
+ * Entry to Hyp mode from the host kernel will happen _only_ when an HVC
+ * instruction is issued since all traps are disabled when running the host
+ * kernel as per the Hyp-mode initialization at boot time.
+ *
+ * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc
+ * below) when the HVC instruction is called from SVC mode (i.e. a guest or the
+ * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC
+ * instructions are called from within Hyp-mode.
+ *
+ * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode):
+ *    Switching to Hyp mode is done through a simple HVC #0 instruction. The
+ *    exception vector code will check that the HVC comes from VMID==0.
+ *    - r0 contains a pointer to a HYP function
+ *    - r1, r2, and r3 contain arguments to the above function.
+ *    - The HYP function will be called with its arguments in r0, r1 and r2.
+ *    On HYP function return, we return directly to SVC.
+ *
+ * Note that the above is used to execute code in Hyp-mode from a host-kernel
+ * point of view, and is a different concept from performing a world-switch and
+ * executing guest code SVC mode (with a VMID != 0).
+ */
+
+	.align 5
+__kvm_hyp_vector:
+	.global __kvm_hyp_vector
+
+	@ Hyp-mode exception vector
+	W(b)	hyp_reset
+	W(b)	hyp_undef
+	W(b)	hyp_svc
+	W(b)	hyp_pabt
+	W(b)	hyp_dabt
+	W(b)	hyp_hvc
+	W(b)	hyp_irq
+	W(b)	hyp_fiq
+
+.macro invalid_vector label, cause
+	.align
+\label:	mov	r0, #\cause
+	b	__hyp_panic
+.endm
+
+	invalid_vector	hyp_reset	ARM_EXCEPTION_RESET
+	invalid_vector	hyp_undef	ARM_EXCEPTION_UNDEFINED
+	invalid_vector	hyp_svc		ARM_EXCEPTION_SOFTWARE
+	invalid_vector	hyp_pabt	ARM_EXCEPTION_PREF_ABORT
+	invalid_vector	hyp_dabt	ARM_EXCEPTION_DATA_ABORT
+	invalid_vector	hyp_fiq		ARM_EXCEPTION_FIQ
+
+ENTRY(__hyp_do_panic)
+	mrs	lr, cpsr
+	bic	lr, lr, #MODE_MASK
+	orr	lr, lr, #SVC_MODE
+THUMB(	orr	lr, lr, #PSR_T_BIT	)
+	msr	spsr_cxsf, lr
+	ldr	lr, =panic
+	msr	ELR_hyp, lr
+	ldr	lr, =kvm_call_hyp
+	clrex
+	eret
+ENDPROC(__hyp_do_panic)
+
+hyp_hvc:
+	/*
+	 * Getting here is either because of a trap from a guest,
+	 * or from executing HVC from the host kernel, which means
+	 * "do something in Hyp mode".
+	 */
+	push	{r0, r1, r2}
+
+	@ Check syndrome register
+	mrc	p15, 4, r1, c5, c2, 0	@ HSR
+	lsr	r0, r1, #HSR_EC_SHIFT
+	cmp	r0, #HSR_EC_HVC
+	bne	guest_trap		@ Not HVC instr.
+
+	/*
+	 * Let's check if the HVC came from VMID 0 and allow simple
+	 * switch to Hyp mode
+	 */
+	mrrc    p15, 6, r0, r2, c2
+	lsr     r2, r2, #16
+	and     r2, r2, #0xff
+	cmp     r2, #0
+	bne	guest_trap		@ Guest called HVC
+
+	/*
+	 * Getting here means host called HVC, we shift parameters and branch
+	 * to Hyp function.
+	 */
+	pop	{r0, r1, r2}
+
+	/* Check for __hyp_get_vectors */
+	cmp	r0, #-1
+	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
+	beq	1f
+
+	push	{lr}
+
+	mov	lr, r0
+	mov	r0, r1
+	mov	r1, r2
+	mov	r2, r3
+
+THUMB(	orr	lr, #1)
+	blx	lr			@ Call the HYP function
+
+	pop	{lr}
+1:	eret
+
+guest_trap:
+	load_vcpu r0			@ Load VCPU pointer to r0
+
+#ifdef CONFIG_VFPv3
+	@ Check for a VFP access
+	lsr	r1, r1, #HSR_EC_SHIFT
+	cmp	r1, #HSR_EC_CP_0_13
+	beq	__vfp_guest_restore
+#endif
+
+	mov	r1, #ARM_EXCEPTION_HVC
+	b	__guest_exit
+
+hyp_irq:
+	push	{r0, r1, r2}
+	mov	r1, #ARM_EXCEPTION_IRQ
+	load_vcpu r0			@ Load VCPU pointer to r0
+	b	__guest_exit
+
+	.ltorg
+
+	.popsection
diff --git a/arch/arm/kvm/hyp/s2-setup.c b/arch/arm/kvm/hyp/s2-setup.c
new file mode 100644
index 000000000000..7be39af2ed6c
--- /dev/null
+++ b/arch/arm/kvm/hyp/s2-setup.c
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/types.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+void __hyp_text __init_stage2_translation(void)
+{
+	u64 val;
+
+	val = read_sysreg(VTCR) & ~VTCR_MASK;
+
+	val |= read_sysreg(HTCR) & VTCR_HTCR_SH;
+	val |= KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S;
+
+	write_sysreg(val, VTCR);
+}
diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c
new file mode 100644
index 000000000000..b13caa90cd44
--- /dev/null
+++ b/arch/arm/kvm/hyp/switch.c
@@ -0,0 +1,232 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+__asm__(".arch_extension     virt");
+
+/*
+ * Activate the traps, saving the host's fpexc register before
+ * overwriting it. We'll restore it on VM exit.
+ */
+static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host)
+{
+	u32 val;
+
+	/*
+	 * We are about to set HCPTR.TCP10/11 to trap all floating point
+	 * register accesses to HYP, however, the ARM ARM clearly states that
+	 * traps are only taken to HYP if the operation would not otherwise
+	 * trap to SVC.  Therefore, always make sure that for 32-bit guests,
+	 * we set FPEXC.EN to prevent traps to SVC, when setting the TCP bits.
+	 */
+	val = read_sysreg(VFP_FPEXC);
+	*fpexc_host = val;
+	if (!(val & FPEXC_EN)) {
+		write_sysreg(val | FPEXC_EN, VFP_FPEXC);
+		isb();
+	}
+
+	write_sysreg(vcpu->arch.hcr | vcpu->arch.irq_lines, HCR);
+	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
+	write_sysreg(HSTR_T(15), HSTR);
+	write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR);
+	val = read_sysreg(HDCR);
+	write_sysreg(val | HDCR_TPM | HDCR_TPMCR, HDCR);
+}
+
+static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	u32 val;
+
+	write_sysreg(0, HCR);
+	write_sysreg(0, HSTR);
+	val = read_sysreg(HDCR);
+	write_sysreg(val & ~(HDCR_TPM | HDCR_TPMCR), HDCR);
+	write_sysreg(0, HCPTR);
+}
+
+static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(vcpu->arch.midr, VPIDR);
+}
+
+static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
+{
+	write_sysreg(0, VTTBR);
+	write_sysreg(read_sysreg(MIDR), VPIDR);
+}
+
+static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
+{
+	__vgic_v2_save_state(vcpu);
+}
+
+static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
+{
+	__vgic_v2_restore_state(vcpu);
+}
+
+static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u32 hsr = read_sysreg(HSR);
+	u8 ec = hsr >> HSR_EC_SHIFT;
+	u32 hpfar, far;
+
+	vcpu->arch.fault.hsr = hsr;
+
+	if (ec == HSR_EC_IABT)
+		far = read_sysreg(HIFAR);
+	else if (ec == HSR_EC_DABT)
+		far = read_sysreg(HDFAR);
+	else
+		return true;
+
+	/*
+	 * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode:
+	 *
+	 * Abort on the stage 2 translation for a memory access from a
+	 * Non-secure PL1 or PL0 mode:
+	 *
+	 * For any Access flag fault or Translation fault, and also for any
+	 * Permission fault on the stage 2 translation of a memory access
+	 * made as part of a translation table walk for a stage 1 translation,
+	 * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR
+	 * is UNKNOWN.
+	 */
+	if (!(hsr & HSR_DABT_S1PTW) && (hsr & HSR_FSC_TYPE) == FSC_PERM) {
+		u64 par, tmp;
+
+		par = read_sysreg(PAR);
+		write_sysreg(far, ATS1CPR);
+		isb();
+
+		tmp = read_sysreg(PAR);
+		write_sysreg(par, PAR);
+
+		if (unlikely(tmp & 1))
+			return false; /* Translation failed, back to guest */
+
+		hpfar = ((tmp >> 12) & ((1UL << 28) - 1)) << 4;
+	} else {
+		hpfar = read_sysreg(HPFAR);
+	}
+
+	vcpu->arch.fault.hxfar = far;
+	vcpu->arch.fault.hpfar = hpfar;
+	return true;
+}
+
+static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool fp_enabled;
+	u64 exit_code;
+	u32 fpexc;
+
+	vcpu = kern_hyp_va(vcpu);
+	write_sysreg(vcpu, HTPIDR);
+
+	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	__sysreg_save_state(host_ctxt);
+	__banked_save_state(host_ctxt);
+
+	__activate_traps(vcpu, &fpexc);
+	__activate_vm(vcpu);
+
+	__vgic_restore_state(vcpu);
+	__timer_restore_state(vcpu);
+
+	__sysreg_restore_state(guest_ctxt);
+	__banked_restore_state(guest_ctxt);
+
+	/* Jump in the fire! */
+again:
+	exit_code = __guest_enter(vcpu, host_ctxt);
+	/* And we're baaack! */
+
+	if (exit_code == ARM_EXCEPTION_HVC && !__populate_fault_info(vcpu))
+		goto again;
+
+	fp_enabled = __vfp_enabled();
+
+	__banked_save_state(guest_ctxt);
+	__sysreg_save_state(guest_ctxt);
+	__timer_save_state(vcpu);
+	__vgic_save_state(vcpu);
+
+	__deactivate_traps(vcpu);
+	__deactivate_vm(vcpu);
+
+	__banked_restore_state(host_ctxt);
+	__sysreg_restore_state(host_ctxt);
+
+	if (fp_enabled) {
+		__vfp_save_state(&guest_ctxt->vfp);
+		__vfp_restore_state(&host_ctxt->vfp);
+	}
+
+	write_sysreg(fpexc, VFP_FPEXC);
+
+	return exit_code;
+}
+
+__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+static const char * const __hyp_panic_string[] = {
+	[ARM_EXCEPTION_RESET]      = "\nHYP panic: RST   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_UNDEFINED]  = "\nHYP panic: UNDEF PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_SOFTWARE]   = "\nHYP panic: SVC   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_PREF_ABORT] = "\nHYP panic: PABRT PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_DATA_ABORT] = "\nHYP panic: DABRT PC:%08x ADDR:%08x",
+	[ARM_EXCEPTION_IRQ]        = "\nHYP panic: IRQ   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_FIQ]        = "\nHYP panic: FIQ   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_HVC]        = "\nHYP panic: HVC   PC:%08x CPSR:%08x",
+};
+
+void __hyp_text __noreturn __hyp_panic(int cause)
+{
+	u32 elr = read_special(ELR_hyp);
+	u32 val;
+
+	if (cause == ARM_EXCEPTION_DATA_ABORT)
+		val = read_sysreg(HDFAR);
+	else
+		val = read_special(SPSR);
+
+	if (read_sysreg(VTTBR)) {
+		struct kvm_vcpu *vcpu;
+		struct kvm_cpu_context *host_ctxt;
+
+		vcpu = (struct kvm_vcpu *)read_sysreg(HTPIDR);
+		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+		__deactivate_traps(vcpu);
+		__deactivate_vm(vcpu);
+		__sysreg_restore_state(host_ctxt);
+	}
+
+	/* Call panic for real */
+	__hyp_do_panic(__hyp_panic_string[cause], elr, val);
+
+	unreachable();
+}
diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c
new file mode 100644
index 000000000000..a2636001e616
--- /dev/null
+++ b/arch/arm/kvm/hyp/tlb.c
@@ -0,0 +1,70 @@
+/*
+ * Original code:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_hyp.h>
+
+/**
+ * Flush per-VMID TLBs
+ *
+ * __kvm_tlb_flush_vmid(struct kvm *kvm);
+ *
+ * We rely on the hardware to broadcast the TLB invalidation to all CPUs
+ * inside the inner-shareable domain (which is the case for all v7
+ * implementations).  If we come across a non-IS SMP implementation, we'll
+ * have to use an IPI based mechanism. Until then, we stick to the simple
+ * hardware assisted version.
+ *
+ * As v7 does not support flushing per IPA, just nuke the whole TLB
+ * instead, ignoring the ipa value.
+ */
+static void __hyp_text __tlb_flush_vmid(struct kvm *kvm)
+{
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	kvm = kern_hyp_va(kvm);
+	write_sysreg(kvm->arch.vttbr, VTTBR);
+	isb();
+
+	write_sysreg(0, TLBIALLIS);
+	dsb(ish);
+	isb();
+
+	write_sysreg(0, VTTBR);
+}
+
+__alias(__tlb_flush_vmid) void __kvm_tlb_flush_vmid(struct kvm *kvm);
+
+static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	__tlb_flush_vmid(kvm);
+}
+
+__alias(__tlb_flush_vmid_ipa) void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm,
+							    phys_addr_t ipa);
+
+static void __hyp_text __tlb_flush_vm_context(void)
+{
+	write_sysreg(0, TLBIALLNSNHIS);
+	write_sysreg(0, ICIALLUIS);
+	dsb(ish);
+}
+
+__alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void);
diff --git a/arch/arm/kvm/hyp/vfp.S b/arch/arm/kvm/hyp/vfp.S
new file mode 100644
index 000000000000..7c297e87eb8b
--- /dev/null
+++ b/arch/arm/kvm/hyp/vfp.S
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/vfpmacros.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/* void __vfp_save_state(struct vfp_hard_struct *vfp); */
+ENTRY(__vfp_save_state)
+	push	{r4, r5}
+	VFPFMRX	r1, FPEXC
+
+	@ Make sure *really* VFP is enabled so we can touch the registers.
+	orr	r5, r1, #FPEXC_EN
+	tst	r5, #FPEXC_EX		@ Check for VFP Subarchitecture
+	bic	r5, r5, #FPEXC_EX	@ FPEXC_EX disable
+	VFPFMXR	FPEXC, r5
+	isb
+
+	VFPFMRX	r2, FPSCR
+	beq	1f
+
+	@ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so
+	@ we only need to save them if FPEXC_EX is set.
+	VFPFMRX r3, FPINST
+	tst	r5, #FPEXC_FP2V
+	VFPFMRX r4, FPINST2, ne		@ vmrsne
+1:
+	VFPFSTMIA r0, r5		@ Save VFP registers
+	stm	r0, {r1-r4}		@ Save FPEXC, FPSCR, FPINST, FPINST2
+	pop	{r4, r5}
+	bx	lr
+ENDPROC(__vfp_save_state)
+
+/* void __vfp_restore_state(struct vfp_hard_struct *vfp);
+ * Assume FPEXC_EN is on and FPEXC_EX is off */
+ENTRY(__vfp_restore_state)
+	VFPFLDMIA r0, r1		@ Load VFP registers
+	ldm	r0, {r0-r3}		@ Load FPEXC, FPSCR, FPINST, FPINST2
+
+	VFPFMXR FPSCR, r1
+	tst	r0, #FPEXC_EX		@ Check for VFP Subarchitecture
+	beq	1f
+	VFPFMXR FPINST, r2
+	tst	r0, #FPEXC_FP2V
+	VFPFMXR FPINST2, r3, ne
+1:
+	VFPFMXR FPEXC, r0		@ FPEXC	(last, in case !EN)
+	bx	lr
+ENDPROC(__vfp_restore_state)
+
+	.popsection
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 3988e72d16ff..1f9ae17476f9 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -84,14 +84,6 @@ __do_hyp_init:
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c2, c0, 2	@ HTCR
 
-	mrc	p15, 4, r1, c2, c1, 2	@ VTCR
-	ldr	r2, =VTCR_MASK
-	bic	r1, r1, r2
-	bic	r0, r0, #(~VTCR_HTCR_SH)	@ clear non-reusable HTCR bits
-	orr	r1, r0, r1
-	orr	r1, r1, #(KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S)
-	mcr	p15, 4, r1, c2, c1, 2	@ VTCR
-
 	@ Use the same memory attributes for hyp. accesses as the kernel
 	@ (copy MAIRx ro HMAIRx).
 	mrc	p15, 0, r0, c10, c2, 0
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 900ef6dd8f72..b1bd316f14c0 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -17,211 +17,14 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/const.h>
-#include <asm/unified.h>
-#include <asm/page.h>
-#include <asm/ptrace.h>
-#include <asm/asm-offsets.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_arm.h>
-#include <asm/vfpmacros.h>
-#include "interrupts_head.S"
 
 	.text
 
-__kvm_hyp_code_start:
-	.globl __kvm_hyp_code_start
-
-/********************************************************************
- * Flush per-VMID TLBs
- *
- * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
- *
- * We rely on the hardware to broadcast the TLB invalidation to all CPUs
- * inside the inner-shareable domain (which is the case for all v7
- * implementations).  If we come across a non-IS SMP implementation, we'll
- * have to use an IPI based mechanism. Until then, we stick to the simple
- * hardware assisted version.
- *
- * As v7 does not support flushing per IPA, just nuke the whole TLB
- * instead, ignoring the ipa value.
- */
-ENTRY(__kvm_tlb_flush_vmid_ipa)
-	push	{r2, r3}
-
-	dsb	ishst
-	add	r0, r0, #KVM_VTTBR
-	ldrd	r2, r3, [r0]
-	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
-	isb
-	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
-	dsb	ish
-	isb
-	mov	r2, #0
-	mov	r3, #0
-	mcrr	p15, 6, r2, r3, c2	@ Back to VMID #0
-	isb				@ Not necessary if followed by eret
-
-	pop	{r2, r3}
-	bx	lr
-ENDPROC(__kvm_tlb_flush_vmid_ipa)
-
-/**
- * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
- *
- * Reuses __kvm_tlb_flush_vmid_ipa() for ARMv7, without passing address
- * parameter
- */
-
-ENTRY(__kvm_tlb_flush_vmid)
-	b	__kvm_tlb_flush_vmid_ipa
-ENDPROC(__kvm_tlb_flush_vmid)
-
-/********************************************************************
- * Flush TLBs and instruction caches of all CPUs inside the inner-shareable
- * domain, for all VMIDs
- *
- * void __kvm_flush_vm_context(void);
- */
-ENTRY(__kvm_flush_vm_context)
-	mov	r0, #0			@ rn parameter for c15 flushes is SBZ
-
-	/* Invalidate NS Non-Hyp TLB Inner Shareable (TLBIALLNSNHIS) */
-	mcr     p15, 4, r0, c8, c3, 4
-	/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
-	mcr     p15, 0, r0, c7, c1, 0
-	dsb	ish
-	isb				@ Not necessary if followed by eret
-
-	bx	lr
-ENDPROC(__kvm_flush_vm_context)
-
-
-/********************************************************************
- *  Hypervisor world-switch code
- *
- *
- * int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
- */
-ENTRY(__kvm_vcpu_run)
-	@ Save the vcpu pointer
-	mcr	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
-
-	save_host_regs
-
-	restore_vgic_state
-	restore_timer_state
-
-	@ Store hardware CP15 state and load guest state
-	read_cp15_state store_to_vcpu = 0
-	write_cp15_state read_from_vcpu = 1
-
-	@ If the host kernel has not been configured with VFPv3 support,
-	@ then it is safer if we deny guests from using it as well.
-#ifdef CONFIG_VFPv3
-	@ Set FPEXC_EN so the guest doesn't trap floating point instructions
-	VFPFMRX r2, FPEXC		@ VMRS
-	push	{r2}
-	orr	r2, r2, #FPEXC_EN
-	VFPFMXR FPEXC, r2		@ VMSR
-#endif
-
-	@ Configure Hyp-role
-	configure_hyp_role vmentry
-
-	@ Trap coprocessor CRx accesses
-	set_hstr vmentry
-	set_hcptr vmentry, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
-	set_hdcr vmentry
-
-	@ Write configured ID register into MIDR alias
-	ldr	r1, [vcpu, #VCPU_MIDR]
-	mcr	p15, 4, r1, c0, c0, 0
-
-	@ Write guest view of MPIDR into VMPIDR
-	ldr	r1, [vcpu, #CP15_OFFSET(c0_MPIDR)]
-	mcr	p15, 4, r1, c0, c0, 5
-
-	@ Set up guest memory translation
-	ldr	r1, [vcpu, #VCPU_KVM]
-	add	r1, r1, #KVM_VTTBR
-	ldrd	r2, r3, [r1]
-	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
-
-	@ We're all done, just restore the GPRs and go to the guest
-	restore_guest_regs
-	clrex				@ Clear exclusive monitor
-	eret
-
-__kvm_vcpu_return:
-	/*
-	 * return convention:
-	 * guest r0, r1, r2 saved on the stack
-	 * r0: vcpu pointer
-	 * r1: exception code
-	 */
-	save_guest_regs
-
-	@ Set VMID == 0
-	mov	r2, #0
-	mov	r3, #0
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
-
-	@ Don't trap coprocessor accesses for host kernel
-	set_hstr vmexit
-	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
-
-#ifdef CONFIG_VFPv3
-	@ Switch VFP/NEON hardware state to the host's
-	add	r7, vcpu, #VCPU_VFP_GUEST
-	store_vfp_state r7
-	add	r7, vcpu, #VCPU_VFP_HOST
-	ldr	r7, [r7]
-	restore_vfp_state r7
-
-after_vfp_restore:
-	@ Restore FPEXC_EN which we clobbered on entry
-	pop	{r2}
-	VFPFMXR FPEXC, r2
-#else
-after_vfp_restore:
-#endif
-
-	@ Reset Hyp-role
-	configure_hyp_role vmexit
-
-	@ Let host read hardware MIDR
-	mrc	p15, 0, r2, c0, c0, 0
-	mcr	p15, 4, r2, c0, c0, 0
-
-	@ Back to hardware MPIDR
-	mrc	p15, 0, r2, c0, c0, 5
-	mcr	p15, 4, r2, c0, c0, 5
-
-	@ Store guest CP15 state and restore host state
-	read_cp15_state store_to_vcpu = 1
-	write_cp15_state read_from_vcpu = 0
-
-	save_timer_state
-	save_vgic_state
-
-	restore_host_regs
-	clrex				@ Clear exclusive monitor
-#ifndef CONFIG_CPU_ENDIAN_BE8
-	mov	r0, r1			@ Return the return code
-	mov	r1, #0			@ Clear upper bits in return value
-#else
-	@ r1 already has return code
-	mov	r0, #0			@ Clear upper bits in return value
-#endif /* CONFIG_CPU_ENDIAN_BE8 */
-	bx	lr			@ return to IOCTL
-
 /********************************************************************
  *  Call function in Hyp mode
  *
  *
- * u64 kvm_call_hyp(void *hypfn, ...);
+ * unsigned long kvm_call_hyp(void *hypfn, ...);
  *
  * This is not really a variadic function in the classic C-way and care must
  * be taken when calling this to ensure parameters are passed in registers
@@ -232,7 +35,7 @@ after_vfp_restore:
  * passed as r0, r1, and r2 (a maximum of 3 arguments in addition to the
  * function pointer can be passed).  The function being called must be mapped
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
- * passed in r0 and r1.
+ * passed in r0 (strictly 32bit).
  *
  * A function pointer with a value of 0xffffffff has a special meaning,
  * and is used to implement __hyp_get_vectors in the same way as in
@@ -246,281 +49,4 @@ after_vfp_restore:
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	bx	lr
-
-/********************************************************************
- * Hypervisor exception vector and handlers
- *
- *
- * The KVM/ARM Hypervisor ABI is defined as follows:
- *
- * Entry to Hyp mode from the host kernel will happen _only_ when an HVC
- * instruction is issued since all traps are disabled when running the host
- * kernel as per the Hyp-mode initialization at boot time.
- *
- * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc
- * below) when the HVC instruction is called from SVC mode (i.e. a guest or the
- * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC
- * instructions are called from within Hyp-mode.
- *
- * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode):
- *    Switching to Hyp mode is done through a simple HVC #0 instruction. The
- *    exception vector code will check that the HVC comes from VMID==0 and if
- *    so will push the necessary state (SPSR, lr_usr) on the Hyp stack.
- *    - r0 contains a pointer to a HYP function
- *    - r1, r2, and r3 contain arguments to the above function.
- *    - The HYP function will be called with its arguments in r0, r1 and r2.
- *    On HYP function return, we return directly to SVC.
- *
- * Note that the above is used to execute code in Hyp-mode from a host-kernel
- * point of view, and is a different concept from performing a world-switch and
- * executing guest code SVC mode (with a VMID != 0).
- */
-
-/* Handle undef, svc, pabt, or dabt by crashing with a user notice */
-.macro bad_exception exception_code, panic_str
-	push	{r0-r2}
-	mrrc	p15, 6, r0, r1, c2	@ Read VTTBR
-	lsr	r1, r1, #16
-	ands	r1, r1, #0xff
-	beq	99f
-
-	load_vcpu			@ Load VCPU pointer
-	.if \exception_code == ARM_EXCEPTION_DATA_ABORT
-	mrc	p15, 4, r2, c5, c2, 0	@ HSR
-	mrc	p15, 4, r1, c6, c0, 0	@ HDFAR
-	str	r2, [vcpu, #VCPU_HSR]
-	str	r1, [vcpu, #VCPU_HxFAR]
-	.endif
-	.if \exception_code == ARM_EXCEPTION_PREF_ABORT
-	mrc	p15, 4, r2, c5, c2, 0	@ HSR
-	mrc	p15, 4, r1, c6, c0, 2	@ HIFAR
-	str	r2, [vcpu, #VCPU_HSR]
-	str	r1, [vcpu, #VCPU_HxFAR]
-	.endif
-	mov	r1, #\exception_code
-	b	__kvm_vcpu_return
-
-	@ We were in the host already. Let's craft a panic-ing return to SVC.
-99:	mrs	r2, cpsr
-	bic	r2, r2, #MODE_MASK
-	orr	r2, r2, #SVC_MODE
-THUMB(	orr	r2, r2, #PSR_T_BIT	)
-	msr	spsr_cxsf, r2
-	mrs	r1, ELR_hyp
-	ldr	r2, =panic
-	msr	ELR_hyp, r2
-	ldr	r0, =\panic_str
-	clrex				@ Clear exclusive monitor
-	eret
-.endm
-
-	.text
-
-	.align 5
-__kvm_hyp_vector:
-	.globl __kvm_hyp_vector
-
-	@ Hyp-mode exception vector
-	W(b)	hyp_reset
-	W(b)	hyp_undef
-	W(b)	hyp_svc
-	W(b)	hyp_pabt
-	W(b)	hyp_dabt
-	W(b)	hyp_hvc
-	W(b)	hyp_irq
-	W(b)	hyp_fiq
-
-	.align
-hyp_reset:
-	b	hyp_reset
-
-	.align
-hyp_undef:
-	bad_exception ARM_EXCEPTION_UNDEFINED, und_die_str
-
-	.align
-hyp_svc:
-	bad_exception ARM_EXCEPTION_HVC, svc_die_str
-
-	.align
-hyp_pabt:
-	bad_exception ARM_EXCEPTION_PREF_ABORT, pabt_die_str
-
-	.align
-hyp_dabt:
-	bad_exception ARM_EXCEPTION_DATA_ABORT, dabt_die_str
-
-	.align
-hyp_hvc:
-	/*
-	 * Getting here is either becuase of a trap from a guest or from calling
-	 * HVC from the host kernel, which means "switch to Hyp mode".
-	 */
-	push	{r0, r1, r2}
-
-	@ Check syndrome register
-	mrc	p15, 4, r1, c5, c2, 0	@ HSR
-	lsr	r0, r1, #HSR_EC_SHIFT
-	cmp	r0, #HSR_EC_HVC
-	bne	guest_trap		@ Not HVC instr.
-
-	/*
-	 * Let's check if the HVC came from VMID 0 and allow simple
-	 * switch to Hyp mode
-	 */
-	mrrc    p15, 6, r0, r2, c2
-	lsr     r2, r2, #16
-	and     r2, r2, #0xff
-	cmp     r2, #0
-	bne	guest_trap		@ Guest called HVC
-
-	/*
-	 * Getting here means host called HVC, we shift parameters and branch
-	 * to Hyp function.
-	 */
-	pop	{r0, r1, r2}
-
-	/* Check for __hyp_get_vectors */
-	cmp	r0, #-1
-	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
-	beq	1f
-
-	push	{lr}
-	mrs	lr, SPSR
-	push	{lr}
-
-	mov	lr, r0
-	mov	r0, r1
-	mov	r1, r2
-	mov	r2, r3
-
-THUMB(	orr	lr, #1)
-	blx	lr			@ Call the HYP function
-
-	pop	{lr}
-	msr	SPSR_csxf, lr
-	pop	{lr}
-1:	eret
-
-guest_trap:
-	load_vcpu			@ Load VCPU pointer to r0
-	str	r1, [vcpu, #VCPU_HSR]
-
-	@ Check if we need the fault information
-	lsr	r1, r1, #HSR_EC_SHIFT
-#ifdef CONFIG_VFPv3
-	cmp	r1, #HSR_EC_CP_0_13
-	beq	switch_to_guest_vfp
-#endif
-	cmp	r1, #HSR_EC_IABT
-	mrceq	p15, 4, r2, c6, c0, 2	@ HIFAR
-	beq	2f
-	cmp	r1, #HSR_EC_DABT
-	bne	1f
-	mrc	p15, 4, r2, c6, c0, 0	@ HDFAR
-
-2:	str	r2, [vcpu, #VCPU_HxFAR]
-
-	/*
-	 * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode:
-	 *
-	 * Abort on the stage 2 translation for a memory access from a
-	 * Non-secure PL1 or PL0 mode:
-	 *
-	 * For any Access flag fault or Translation fault, and also for any
-	 * Permission fault on the stage 2 translation of a memory access
-	 * made as part of a translation table walk for a stage 1 translation,
-	 * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR
-	 * is UNKNOWN.
-	 */
-
-	/* Check for permission fault, and S1PTW */
-	mrc	p15, 4, r1, c5, c2, 0	@ HSR
-	and	r0, r1, #HSR_FSC_TYPE
-	cmp	r0, #FSC_PERM
-	tsteq	r1, #(1 << 7)		@ S1PTW
-	mrcne	p15, 4, r2, c6, c0, 4	@ HPFAR
-	bne	3f
-
-	/* Preserve PAR */
-	mrrc	p15, 0, r0, r1, c7	@ PAR
-	push	{r0, r1}
-
-	/* Resolve IPA using the xFAR */
-	mcr	p15, 0, r2, c7, c8, 0	@ ATS1CPR
-	isb
-	mrrc	p15, 0, r0, r1, c7	@ PAR
-	tst	r0, #1
-	bne	4f			@ Failed translation
-	ubfx	r2, r0, #12, #20
-	lsl	r2, r2, #4
-	orr	r2, r2, r1, lsl #24
-
-	/* Restore PAR */
-	pop	{r0, r1}
-	mcrr	p15, 0, r0, r1, c7	@ PAR
-
-3:	load_vcpu			@ Load VCPU pointer to r0
-	str	r2, [r0, #VCPU_HPFAR]
-
-1:	mov	r1, #ARM_EXCEPTION_HVC
-	b	__kvm_vcpu_return
-
-4:	pop	{r0, r1}		@ Failed translation, return to guest
-	mcrr	p15, 0, r0, r1, c7	@ PAR
-	clrex
-	pop	{r0, r1, r2}
-	eret
-
-/*
- * If VFPv3 support is not available, then we will not switch the VFP
- * registers; however cp10 and cp11 accesses will still trap and fallback
- * to the regular coprocessor emulation code, which currently will
- * inject an undefined exception to the guest.
- */
-#ifdef CONFIG_VFPv3
-switch_to_guest_vfp:
-	push	{r3-r7}
-
-	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
-
-	@ Switch VFP/NEON hardware state to the guest's
-	add	r7, r0, #VCPU_VFP_HOST
-	ldr	r7, [r7]
-	store_vfp_state r7
-	add	r7, r0, #VCPU_VFP_GUEST
-	restore_vfp_state r7
-
-	pop	{r3-r7}
-	pop	{r0-r2}
-	clrex
-	eret
-#endif
-
-	.align
-hyp_irq:
-	push	{r0, r1, r2}
-	mov	r1, #ARM_EXCEPTION_IRQ
-	load_vcpu			@ Load VCPU pointer to r0
-	b	__kvm_vcpu_return
-
-	.align
-hyp_fiq:
-	b	hyp_fiq
-
-	.ltorg
-
-__kvm_hyp_code_end:
-	.globl	__kvm_hyp_code_end
-
-	.section ".rodata"
-
-und_die_str:
-	.ascii	"unexpected undefined exception in Hyp mode at: %#08x\n"
-pabt_die_str:
-	.ascii	"unexpected prefetch abort in Hyp mode at: %#08x\n"
-dabt_die_str:
-	.ascii	"unexpected data abort in Hyp mode at: %#08x\n"
-svc_die_str:
-	.ascii	"unexpected HVC/SVC trap in Hyp mode at: %#08x\n"
+ENDPROC(kvm_call_hyp)
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
deleted file mode 100644
index 51a59504bef4..000000000000
--- a/arch/arm/kvm/interrupts_head.S
+++ /dev/null
@@ -1,648 +0,0 @@
-#include <linux/irqchip/arm-gic.h>
-#include <asm/assembler.h>
-
-#define VCPU_USR_REG(_reg_nr)	(VCPU_USR_REGS + (_reg_nr * 4))
-#define VCPU_USR_SP		(VCPU_USR_REG(13))
-#define VCPU_USR_LR		(VCPU_USR_REG(14))
-#define CP15_OFFSET(_cp15_reg_idx) (VCPU_CP15 + (_cp15_reg_idx * 4))
-
-/*
- * Many of these macros need to access the VCPU structure, which is always
- * held in r0. These macros should never clobber r1, as it is used to hold the
- * exception code on the return path (except of course the macro that switches
- * all the registers before the final jump to the VM).
- */
-vcpu	.req	r0		@ vcpu pointer always in r0
-
-/* Clobbers {r2-r6} */
-.macro store_vfp_state vfp_base
-	@ The VFPFMRX and VFPFMXR macros are the VMRS and VMSR instructions
-	VFPFMRX	r2, FPEXC
-	@ Make sure VFP is enabled so we can touch the registers.
-	orr	r6, r2, #FPEXC_EN
-	VFPFMXR	FPEXC, r6
-
-	VFPFMRX	r3, FPSCR
-	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
-	beq	1f
-	@ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so
-	@ we only need to save them if FPEXC_EX is set.
-	VFPFMRX r4, FPINST
-	tst	r2, #FPEXC_FP2V
-	VFPFMRX r5, FPINST2, ne		@ vmrsne
-	bic	r6, r2, #FPEXC_EX	@ FPEXC_EX disable
-	VFPFMXR	FPEXC, r6
-1:
-	VFPFSTMIA \vfp_base, r6		@ Save VFP registers
-	stm	\vfp_base, {r2-r5}	@ Save FPEXC, FPSCR, FPINST, FPINST2
-.endm
-
-/* Assume FPEXC_EN is on and FPEXC_EX is off, clobbers {r2-r6} */
-.macro restore_vfp_state vfp_base
-	VFPFLDMIA \vfp_base, r6		@ Load VFP registers
-	ldm	\vfp_base, {r2-r5}	@ Load FPEXC, FPSCR, FPINST, FPINST2
-
-	VFPFMXR FPSCR, r3
-	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
-	beq	1f
-	VFPFMXR FPINST, r4
-	tst	r2, #FPEXC_FP2V
-	VFPFMXR FPINST2, r5, ne
-1:
-	VFPFMXR FPEXC, r2	@ FPEXC	(last, in case !EN)
-.endm
-
-/* These are simply for the macros to work - value don't have meaning */
-.equ usr, 0
-.equ svc, 1
-.equ abt, 2
-.equ und, 3
-.equ irq, 4
-.equ fiq, 5
-
-.macro push_host_regs_mode mode
-	mrs	r2, SP_\mode
-	mrs	r3, LR_\mode
-	mrs	r4, SPSR_\mode
-	push	{r2, r3, r4}
-.endm
-
-/*
- * Store all host persistent registers on the stack.
- * Clobbers all registers, in all modes, except r0 and r1.
- */
-.macro save_host_regs
-	/* Hyp regs. Only ELR_hyp (SPSR_hyp already saved) */
-	mrs	r2, ELR_hyp
-	push	{r2}
-
-	/* usr regs */
-	push	{r4-r12}	@ r0-r3 are always clobbered
-	mrs	r2, SP_usr
-	mov	r3, lr
-	push	{r2, r3}
-
-	push_host_regs_mode svc
-	push_host_regs_mode abt
-	push_host_regs_mode und
-	push_host_regs_mode irq
-
-	/* fiq regs */
-	mrs	r2, r8_fiq
-	mrs	r3, r9_fiq
-	mrs	r4, r10_fiq
-	mrs	r5, r11_fiq
-	mrs	r6, r12_fiq
-	mrs	r7, SP_fiq
-	mrs	r8, LR_fiq
-	mrs	r9, SPSR_fiq
-	push	{r2-r9}
-.endm
-
-.macro pop_host_regs_mode mode
-	pop	{r2, r3, r4}
-	msr	SP_\mode, r2
-	msr	LR_\mode, r3
-	msr	SPSR_\mode, r4
-.endm
-
-/*
- * Restore all host registers from the stack.
- * Clobbers all registers, in all modes, except r0 and r1.
- */
-.macro restore_host_regs
-	pop	{r2-r9}
-	msr	r8_fiq, r2
-	msr	r9_fiq, r3
-	msr	r10_fiq, r4
-	msr	r11_fiq, r5
-	msr	r12_fiq, r6
-	msr	SP_fiq, r7
-	msr	LR_fiq, r8
-	msr	SPSR_fiq, r9
-
-	pop_host_regs_mode irq
-	pop_host_regs_mode und
-	pop_host_regs_mode abt
-	pop_host_regs_mode svc
-
-	pop	{r2, r3}
-	msr	SP_usr, r2
-	mov	lr, r3
-	pop	{r4-r12}
-
-	pop	{r2}
-	msr	ELR_hyp, r2
-.endm
-
-/*
- * Restore SP, LR and SPSR for a given mode. offset is the offset of
- * this mode's registers from the VCPU base.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r1, r2, r3, r4.
- */
-.macro restore_guest_regs_mode mode, offset
-	add	r1, vcpu, \offset
-	ldm	r1, {r2, r3, r4}
-	msr	SP_\mode, r2
-	msr	LR_\mode, r3
-	msr	SPSR_\mode, r4
-.endm
-
-/*
- * Restore all guest registers from the vcpu struct.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers *all* registers.
- */
-.macro restore_guest_regs
-	restore_guest_regs_mode svc, #VCPU_SVC_REGS
-	restore_guest_regs_mode abt, #VCPU_ABT_REGS
-	restore_guest_regs_mode und, #VCPU_UND_REGS
-	restore_guest_regs_mode irq, #VCPU_IRQ_REGS
-
-	add	r1, vcpu, #VCPU_FIQ_REGS
-	ldm	r1, {r2-r9}
-	msr	r8_fiq, r2
-	msr	r9_fiq, r3
-	msr	r10_fiq, r4
-	msr	r11_fiq, r5
-	msr	r12_fiq, r6
-	msr	SP_fiq, r7
-	msr	LR_fiq, r8
-	msr	SPSR_fiq, r9
-
-	@ Load return state
-	ldr	r2, [vcpu, #VCPU_PC]
-	ldr	r3, [vcpu, #VCPU_CPSR]
-	msr	ELR_hyp, r2
-	msr	SPSR_cxsf, r3
-
-	@ Load user registers
-	ldr	r2, [vcpu, #VCPU_USR_SP]
-	ldr	r3, [vcpu, #VCPU_USR_LR]
-	msr	SP_usr, r2
-	mov	lr, r3
-	add	vcpu, vcpu, #(VCPU_USR_REGS)
-	ldm	vcpu, {r0-r12}
-.endm
-
-/*
- * Save SP, LR and SPSR for a given mode. offset is the offset of
- * this mode's registers from the VCPU base.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2, r3, r4, r5.
- */
-.macro save_guest_regs_mode mode, offset
-	add	r2, vcpu, \offset
-	mrs	r3, SP_\mode
-	mrs	r4, LR_\mode
-	mrs	r5, SPSR_\mode
-	stm	r2, {r3, r4, r5}
-.endm
-
-/*
- * Save all guest registers to the vcpu struct
- * Expects guest's r0, r1, r2 on the stack.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2, r3, r4, r5.
- */
-.macro save_guest_regs
-	@ Store usr registers
-	add	r2, vcpu, #VCPU_USR_REG(3)
-	stm	r2, {r3-r12}
-	add	r2, vcpu, #VCPU_USR_REG(0)
-	pop	{r3, r4, r5}		@ r0, r1, r2
-	stm	r2, {r3, r4, r5}
-	mrs	r2, SP_usr
-	mov	r3, lr
-	str	r2, [vcpu, #VCPU_USR_SP]
-	str	r3, [vcpu, #VCPU_USR_LR]
-
-	@ Store return state
-	mrs	r2, ELR_hyp
-	mrs	r3, spsr
-	str	r2, [vcpu, #VCPU_PC]
-	str	r3, [vcpu, #VCPU_CPSR]
-
-	@ Store other guest registers
-	save_guest_regs_mode svc, #VCPU_SVC_REGS
-	save_guest_regs_mode abt, #VCPU_ABT_REGS
-	save_guest_regs_mode und, #VCPU_UND_REGS
-	save_guest_regs_mode irq, #VCPU_IRQ_REGS
-.endm
-
-/* Reads cp15 registers from hardware and stores them in memory
- * @store_to_vcpu: If 0, registers are written in-order to the stack,
- * 		   otherwise to the VCPU struct pointed to by vcpup
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2 - r12
- */
-.macro read_cp15_state store_to_vcpu
-	mrc	p15, 0, r2, c1, c0, 0	@ SCTLR
-	mrc	p15, 0, r3, c1, c0, 2	@ CPACR
-	mrc	p15, 0, r4, c2, c0, 2	@ TTBCR
-	mrc	p15, 0, r5, c3, c0, 0	@ DACR
-	mrrc	p15, 0, r6, r7, c2	@ TTBR 0
-	mrrc	p15, 1, r8, r9, c2	@ TTBR 1
-	mrc	p15, 0, r10, c10, c2, 0	@ PRRR
-	mrc	p15, 0, r11, c10, c2, 1	@ NMRR
-	mrc	p15, 2, r12, c0, c0, 0	@ CSSELR
-
-	.if \store_to_vcpu == 0
-	push	{r2-r12}		@ Push CP15 registers
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
-	str	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
-	str	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
-	str	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
-	add	r2, vcpu, #CP15_OFFSET(c2_TTBR0)
-	strd	r6, r7, [r2]
-	add	r2, vcpu, #CP15_OFFSET(c2_TTBR1)
-	strd	r8, r9, [r2]
-	str	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
-	str	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
-	str	r12, [vcpu, #CP15_OFFSET(c0_CSSELR)]
-	.endif
-
-	mrc	p15, 0, r2, c13, c0, 1	@ CID
-	mrc	p15, 0, r3, c13, c0, 2	@ TID_URW
-	mrc	p15, 0, r4, c13, c0, 3	@ TID_URO
-	mrc	p15, 0, r5, c13, c0, 4	@ TID_PRIV
-	mrc	p15, 0, r6, c5, c0, 0	@ DFSR
-	mrc	p15, 0, r7, c5, c0, 1	@ IFSR
-	mrc	p15, 0, r8, c5, c1, 0	@ ADFSR
-	mrc	p15, 0, r9, c5, c1, 1	@ AIFSR
-	mrc	p15, 0, r10, c6, c0, 0	@ DFAR
-	mrc	p15, 0, r11, c6, c0, 2	@ IFAR
-	mrc	p15, 0, r12, c12, c0, 0	@ VBAR
-
-	.if \store_to_vcpu == 0
-	push	{r2-r12}		@ Push CP15 registers
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c13_CID)]
-	str	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
-	str	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
-	str	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
-	str	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
-	str	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
-	str	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
-	str	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
-	str	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
-	str	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
-	str	r12, [vcpu, #CP15_OFFSET(c12_VBAR)]
-	.endif
-
-	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
-	mrrc	p15, 0, r4, r5, c7	@ PAR
-	mrc	p15, 0, r6, c10, c3, 0	@ AMAIR0
-	mrc	p15, 0, r7, c10, c3, 1	@ AMAIR1
-
-	.if \store_to_vcpu == 0
-	push	{r2,r4-r7}
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
-	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
-	strd	r4, r5, [r12]
-	str	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
-	str	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
-	.endif
-.endm
-
-/*
- * Reads cp15 registers from memory and writes them to hardware
- * @read_from_vcpu: If 0, registers are read in-order from the stack,
- *		    otherwise from the VCPU struct pointed to by vcpup
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro write_cp15_state read_from_vcpu
-	.if \read_from_vcpu == 0
-	pop	{r2,r4-r7}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
-	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
-	ldrd	r4, r5, [r12]
-	ldr	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
-	ldr	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
-	.endif
-
-	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
-	mcrr	p15, 0, r4, r5, c7	@ PAR
-	mcr	p15, 0, r6, c10, c3, 0	@ AMAIR0
-	mcr	p15, 0, r7, c10, c3, 1	@ AMAIR1
-
-	.if \read_from_vcpu == 0
-	pop	{r2-r12}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c13_CID)]
-	ldr	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
-	ldr	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
-	ldr	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
-	ldr	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
-	ldr	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
-	ldr	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
-	ldr	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
-	ldr	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
-	ldr	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
-	ldr	r12, [vcpu, #CP15_OFFSET(c12_VBAR)]
-	.endif
-
-	mcr	p15, 0, r2, c13, c0, 1	@ CID
-	mcr	p15, 0, r3, c13, c0, 2	@ TID_URW
-	mcr	p15, 0, r4, c13, c0, 3	@ TID_URO
-	mcr	p15, 0, r5, c13, c0, 4	@ TID_PRIV
-	mcr	p15, 0, r6, c5, c0, 0	@ DFSR
-	mcr	p15, 0, r7, c5, c0, 1	@ IFSR
-	mcr	p15, 0, r8, c5, c1, 0	@ ADFSR
-	mcr	p15, 0, r9, c5, c1, 1	@ AIFSR
-	mcr	p15, 0, r10, c6, c0, 0	@ DFAR
-	mcr	p15, 0, r11, c6, c0, 2	@ IFAR
-	mcr	p15, 0, r12, c12, c0, 0	@ VBAR
-
-	.if \read_from_vcpu == 0
-	pop	{r2-r12}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
-	ldr	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
-	ldr	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
-	ldr	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
-	add	r12, vcpu, #CP15_OFFSET(c2_TTBR0)
-	ldrd	r6, r7, [r12]
-	add	r12, vcpu, #CP15_OFFSET(c2_TTBR1)
-	ldrd	r8, r9, [r12]
-	ldr	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
-	ldr	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
-	ldr	r12, [vcpu, #CP15_OFFSET(c0_CSSELR)]
-	.endif
-
-	mcr	p15, 0, r2, c1, c0, 0	@ SCTLR
-	mcr	p15, 0, r3, c1, c0, 2	@ CPACR
-	mcr	p15, 0, r4, c2, c0, 2	@ TTBCR
-	mcr	p15, 0, r5, c3, c0, 0	@ DACR
-	mcrr	p15, 0, r6, r7, c2	@ TTBR 0
-	mcrr	p15, 1, r8, r9, c2	@ TTBR 1
-	mcr	p15, 0, r10, c10, c2, 0	@ PRRR
-	mcr	p15, 0, r11, c10, c2, 1	@ NMRR
-	mcr	p15, 2, r12, c0, c0, 0	@ CSSELR
-.endm
-
-/*
- * Save the VGIC CPU state into memory
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro save_vgic_state
-	/* Get VGIC VCTRL base into r2 */
-	ldr	r2, [vcpu, #VCPU_KVM]
-	ldr	r2, [r2, #KVM_VGIC_VCTRL]
-	cmp	r2, #0
-	beq	2f
-
-	/* Compute the address of struct vgic_cpu */
-	add	r11, vcpu, #VCPU_VGIC_CPU
-
-	/* Save all interesting registers */
-	ldr	r4, [r2, #GICH_VMCR]
-	ldr	r5, [r2, #GICH_MISR]
-	ldr	r6, [r2, #GICH_EISR0]
-	ldr	r7, [r2, #GICH_EISR1]
-	ldr	r8, [r2, #GICH_ELRSR0]
-	ldr	r9, [r2, #GICH_ELRSR1]
-	ldr	r10, [r2, #GICH_APR]
-ARM_BE8(rev	r4, r4	)
-ARM_BE8(rev	r5, r5	)
-ARM_BE8(rev	r6, r6	)
-ARM_BE8(rev	r7, r7	)
-ARM_BE8(rev	r8, r8	)
-ARM_BE8(rev	r9, r9	)
-ARM_BE8(rev	r10, r10	)
-
-	str	r4, [r11, #VGIC_V2_CPU_VMCR]
-	str	r5, [r11, #VGIC_V2_CPU_MISR]
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	str	r6, [r11, #(VGIC_V2_CPU_EISR + 4)]
-	str	r7, [r11, #VGIC_V2_CPU_EISR]
-	str	r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
-	str	r9, [r11, #VGIC_V2_CPU_ELRSR]
-#else
-	str	r6, [r11, #VGIC_V2_CPU_EISR]
-	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
-	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
-	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
-#endif
-	str	r10, [r11, #VGIC_V2_CPU_APR]
-
-	/* Clear GICH_HCR */
-	mov	r5, #0
-	str	r5, [r2, #GICH_HCR]
-
-	/* Save list registers */
-	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_V2_CPU_LR
-	ldr	r4, [r11, #VGIC_CPU_NR_LR]
-1:	ldr	r6, [r2], #4
-ARM_BE8(rev	r6, r6	)
-	str	r6, [r3], #4
-	subs	r4, r4, #1
-	bne	1b
-2:
-.endm
-
-/*
- * Restore the VGIC CPU state from memory
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro restore_vgic_state
-	/* Get VGIC VCTRL base into r2 */
-	ldr	r2, [vcpu, #VCPU_KVM]
-	ldr	r2, [r2, #KVM_VGIC_VCTRL]
-	cmp	r2, #0
-	beq	2f
-
-	/* Compute the address of struct vgic_cpu */
-	add	r11, vcpu, #VCPU_VGIC_CPU
-
-	/* We only restore a minimal set of registers */
-	ldr	r3, [r11, #VGIC_V2_CPU_HCR]
-	ldr	r4, [r11, #VGIC_V2_CPU_VMCR]
-	ldr	r8, [r11, #VGIC_V2_CPU_APR]
-ARM_BE8(rev	r3, r3	)
-ARM_BE8(rev	r4, r4	)
-ARM_BE8(rev	r8, r8	)
-
-	str	r3, [r2, #GICH_HCR]
-	str	r4, [r2, #GICH_VMCR]
-	str	r8, [r2, #GICH_APR]
-
-	/* Restore list registers */
-	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_V2_CPU_LR
-	ldr	r4, [r11, #VGIC_CPU_NR_LR]
-1:	ldr	r6, [r3], #4
-ARM_BE8(rev	r6, r6  )
-	str	r6, [r2], #4
-	subs	r4, r4, #1
-	bne	1b
-2:
-.endm
-
-#define CNTHCTL_PL1PCTEN	(1 << 0)
-#define CNTHCTL_PL1PCEN		(1 << 1)
-
-/*
- * Save the timer state onto the VCPU and allow physical timer/counter access
- * for the host.
- *
- * Assumes vcpu pointer in vcpu reg
- * Clobbers r2-r5
- */
-.macro save_timer_state
-	ldr	r4, [vcpu, #VCPU_KVM]
-	ldr	r2, [r4, #KVM_TIMER_ENABLED]
-	cmp	r2, #0
-	beq	1f
-
-	mrc	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-	str	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-
-	isb
-
-	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
-	ldr	r4, =VCPU_TIMER_CNTV_CVAL
-	add	r5, vcpu, r4
-	strd	r2, r3, [r5]
-
-	@ Ensure host CNTVCT == CNTPCT
-	mov	r2, #0
-	mcrr	p15, 4, r2, r2, c14	@ CNTVOFF
-
-1:
-	mov	r2, #0			@ Clear ENABLE
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-
-	@ Allow physical timer/counter access for the host
-	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-	orr	r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN)
-	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-.endm
-
-/*
- * Load the timer state from the VCPU and deny physical timer/counter access
- * for the host.
- *
- * Assumes vcpu pointer in vcpu reg
- * Clobbers r2-r5
- */
-.macro restore_timer_state
-	@ Disallow physical timer access for the guest
-	@ Physical counter access is allowed
-	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-	orr	r2, r2, #CNTHCTL_PL1PCTEN
-	bic	r2, r2, #CNTHCTL_PL1PCEN
-	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-
-	ldr	r4, [vcpu, #VCPU_KVM]
-	ldr	r2, [r4, #KVM_TIMER_ENABLED]
-	cmp	r2, #0
-	beq	1f
-
-	ldr	r2, [r4, #KVM_TIMER_CNTVOFF]
-	ldr	r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
-	mcrr	p15, 4, rr_lo_hi(r2, r3), c14	@ CNTVOFF
-
-	ldr	r4, =VCPU_TIMER_CNTV_CVAL
-	add	r5, vcpu, r4
-	ldrd	r2, r3, [r5]
-	mcrr	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
-	isb
-
-	ldr	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-	and	r2, r2, #3
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-1:
-.endm
-
-.equ vmentry,	0
-.equ vmexit,	1
-
-/* Configures the HSTR (Hyp System Trap Register) on entry/return
- * (hardware reset value is 0) */
-.macro set_hstr operation
-	mrc	p15, 4, r2, c1, c1, 3
-	ldr	r3, =HSTR_T(15)
-	.if \operation == vmentry
-	orr	r2, r2, r3		@ Trap CR{15}
-	.else
-	bic	r2, r2, r3		@ Don't trap any CRx accesses
-	.endif
-	mcr	p15, 4, r2, c1, c1, 3
-.endm
-
-/* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2.
- * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
- * VFP wasn't already enabled (always executed on vmtrap).
- * If a label is specified with vmexit, it is branched to if VFP wasn't
- * enabled.
- */
-.macro set_hcptr operation, mask, label = none
-	mrc	p15, 4, r2, c1, c1, 2
-	ldr	r3, =\mask
-	.if \operation == vmentry
-	orr	r3, r2, r3		@ Trap coproc-accesses defined in mask
-	.else
-	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
-	.endif
-	mcr	p15, 4, r3, c1, c1, 2
-	.if \operation != vmentry
-	.if \operation == vmexit
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	beq	1f
-	.endif
-	isb
-	.if \label != none
-	b	\label
-	.endif
-1:
-	.endif
-.endm
-
-/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
- * (hardware reset value is 0) */
-.macro set_hdcr operation
-	mrc	p15, 4, r2, c1, c1, 1
-	ldr	r3, =(HDCR_TPM|HDCR_TPMCR)
-	.if \operation == vmentry
-	orr	r2, r2, r3		@ Trap some perfmon accesses
-	.else
-	bic	r2, r2, r3		@ Don't trap any perfmon accesses
-	.endif
-	mcr	p15, 4, r2, c1, c1, 1
-.endm
-
-/* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
-.macro configure_hyp_role operation
-	.if \operation == vmentry
-	ldr	r2, [vcpu, #VCPU_HCR]
-	ldr	r3, [vcpu, #VCPU_IRQ_LINES]
-	orr	r2, r2, r3
-	.else
-	mov	r2, #0
-	.endif
-	mcr	p15, 4, r2, c1, c1, 0	@ HCR
-.endm
-
-.macro load_vcpu
-	mrc	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
-.endm
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 7f33b2056ae6..0f6600f05137 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -206,7 +206,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	run->mmio.is_write	= is_write;
 	run->mmio.phys_addr	= fault_ipa;
 	run->mmio.len		= len;
-	memcpy(run->mmio.data, data_buf, len);
+	if (is_write)
+		memcpy(run->mmio.data, data_buf, len);
 
 	if (!ret) {
 		/* We handled the access successfully in the kernel. */
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index aba61fd3697a..58dbd5c439df 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -28,6 +28,7 @@
 #include <asm/kvm_mmio.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/virt.h>
 
 #include "trace.h"
 
@@ -598,6 +599,9 @@ int create_hyp_mappings(void *from, void *to)
 	unsigned long start = KERN_TO_HYP((unsigned long)from);
 	unsigned long end = KERN_TO_HYP((unsigned long)to);
 
+	if (is_kernel_in_hyp_mode())
+		return 0;
+
 	start = start & PAGE_MASK;
 	end = PAGE_ALIGN(end);
 
@@ -630,6 +634,9 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 	unsigned long start = KERN_TO_HYP((unsigned long)from);
 	unsigned long end = KERN_TO_HYP((unsigned long)to);
 
+	if (is_kernel_in_hyp_mode())
+		return 0;
+
 	/* Check for a valid kernel IO mapping */
 	if (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))
 		return -EINVAL;
@@ -1431,6 +1438,22 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		}
 
 		/*
+		 * Check for a cache maintenance operation. Since we
+		 * ended-up here, we know it is outside of any memory
+		 * slot. But we can't find out if that is for a device,
+		 * or if the guest is just being stupid. The only thing
+		 * we know for sure is that this range cannot be cached.
+		 *
+		 * So let's assume that the guest is just being
+		 * cautious, and skip the instruction.
+		 */
+		if (kvm_vcpu_dabt_is_cm(vcpu)) {
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
+		/*
 		 * The IPA is reported as [MAX:12], so we need to
 		 * complement it with the bottom 12 bits from the
 		 * faulting VA. This is always 12 bits, irrespective
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index eeb85858d6bb..0048b5a62a50 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -71,7 +71,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	}
 
 	/* Reset core registers */
-	memcpy(&vcpu->arch.regs, reset_regs, sizeof(vcpu->arch.regs));
+	memcpy(&vcpu->arch.ctxt.gp_regs, reset_regs, sizeof(vcpu->arch.ctxt.gp_regs));
 
 	/* Reset CP15 registers */
 	kvm_reset_coprocs(vcpu);
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 809827265fb3..bab814d2f37d 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -18,6 +18,7 @@
 
 #include <asm/setup.h>
 #include <asm/mach/arch.h>
+#include <asm/system_info.h>
 
 #include "common.h"
 
@@ -77,12 +78,31 @@ static const char *const n900_boards_compat[] __initconst = {
 	NULL,
 };
 
+/* Set system_rev from atags */
+static void __init rx51_set_system_rev(const struct tag *tags)
+{
+	const struct tag *tag;
+
+	if (tags->hdr.tag != ATAG_CORE)
+		return;
+
+	for_each_tag(tag, tags) {
+		if (tag->hdr.tag == ATAG_REVISION) {
+			system_rev = tag->u.revision.rev;
+			break;
+		}
+	}
+}
+
 /* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags,
  * save them while the data is still not overwritten
  */
 static void __init rx51_reserve(void)
 {
-	save_atags((const struct tag *)(PAGE_OFFSET + 0x100));
+	const struct tag *tags = (const struct tag *)(PAGE_OFFSET + 0x100);
+
+	save_atags(tags);
+	rx51_set_system_rev(tags);
 	omap_reserve();
 }
 
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 7b76ce01c21d..8633c703546a 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base)
 
 static void set_onenand_cfg(void __iomem *onenand_base)
 {
-	u32 reg;
+	u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT;
 
-	reg = readw(onenand_base + ONENAND_REG_SYS_CFG1);
-	reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9));
 	reg |=	(latency << ONENAND_SYS_CFG1_BRL_SHIFT) |
 		ONENAND_SYS_CFG1_BL_16;
 	if (onenand_flags & ONENAND_FLAG_SYNCREAD)
@@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base)
 		reg |= ONENAND_SYS_CFG1_VHF;
 	else
 		reg &= ~ONENAND_SYS_CFG1_VHF;
+
 	writew(reg, onenand_base + ONENAND_REG_SYS_CFG1);
 }
 
@@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base)
 		}
 	}
 
+	onenand_async.sync_write = true;
 	omap2_onenand_calc_async_timings(&t);
 
 	ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async);
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 0437537751bc..f7ff3b9dad87 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -191,12 +191,22 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct omap_device *od;
+	int err;
 
 	switch (event) {
 	case BUS_NOTIFY_DEL_DEVICE:
 		if (pdev->archdata.od)
 			omap_device_delete(pdev->archdata.od);
 		break;
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		od = to_omap_device(pdev);
+		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED)) {
+			dev_info(dev, "enabled after unload, idling\n");
+			err = omap_device_idle(pdev);
+			if (err)
+				dev_err(dev, "failed to idle\n");
+		}
+		break;
 	case BUS_NOTIFY_ADD_DEVICE:
 		if (pdev->dev.of_node)
 			omap_device_build_from_dt(pdev);
@@ -602,8 +612,10 @@ static int _od_runtime_resume(struct device *dev)
 	int ret;
 
 	ret = omap_device_enable(pdev);
-	if (ret)
+	if (ret) {
+		dev_err(dev, "use pm_runtime_put_sync_suspend() in driver?\n");
 		return ret;
+	}
 
 	return pm_generic_runtime_resume(dev);
 }
diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h
index 9cb11215ceba..b3a4ed5289ec 100644
--- a/arch/arm/mach-shmobile/common.h
+++ b/arch/arm/mach-shmobile/common.h
@@ -4,7 +4,6 @@
 extern void shmobile_init_delay(void);
 extern void shmobile_boot_vector(void);
 extern unsigned long shmobile_boot_fn;
-extern unsigned long shmobile_boot_arg;
 extern unsigned long shmobile_boot_size;
 extern void shmobile_smp_boot(void);
 extern void shmobile_smp_sleep(void);
diff --git a/arch/arm/mach-shmobile/headsmp-scu.S b/arch/arm/mach-shmobile/headsmp-scu.S
index fa5248c52399..5e503d91ad70 100644
--- a/arch/arm/mach-shmobile/headsmp-scu.S
+++ b/arch/arm/mach-shmobile/headsmp-scu.S
@@ -38,9 +38,3 @@ ENTRY(shmobile_boot_scu)
 
 	b	secondary_startup
 ENDPROC(shmobile_boot_scu)
-
-	.text
-	.align	2
-	.globl	shmobile_scu_base
-shmobile_scu_base:
-	.space	4
diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S
index 330c1fc63197..32e0bf6e3ccb 100644
--- a/arch/arm/mach-shmobile/headsmp.S
+++ b/arch/arm/mach-shmobile/headsmp.S
@@ -24,7 +24,6 @@
 	.arm
 	.align  12
 ENTRY(shmobile_boot_vector)
-	ldr     r0, 2f
 	ldr     r1, 1f
 	bx	r1
 
@@ -34,9 +33,6 @@ ENDPROC(shmobile_boot_vector)
 	.globl	shmobile_boot_fn
 shmobile_boot_fn:
 1:	.space	4
-	.globl	shmobile_boot_arg
-shmobile_boot_arg:
-2:	.space	4
 	.globl	shmobile_boot_size
 shmobile_boot_size:
 	.long	. - shmobile_boot_vector
@@ -46,13 +42,15 @@ shmobile_boot_size:
  */
 
 ENTRY(shmobile_smp_boot)
-						@ r0 = MPIDR_HWID_BITMASK
 	mrc	p15, 0, r1, c0, c0, 5		@ r1 = MPIDR
-	and	r0, r1, r0			@ r0 = cpu_logical_map() value
+	and	r0, r1, #0xffffff		@ MPIDR_HWID_BITMASK
+						@ r0 = cpu_logical_map() value
 	mov	r1, #0				@ r1 = CPU index
-	adr	r5, 1f				@ array of per-cpu mpidr values
-	adr	r6, 2f				@ array of per-cpu functions
-	adr	r7, 3f				@ array of per-cpu arguments
+	adr	r2, 1f
+	ldmia	r2, {r5, r6, r7}
+	add	r5, r5, r2			@ array of per-cpu mpidr values
+	add	r6, r6, r2			@ array of per-cpu functions
+	add	r7, r7, r2			@ array of per-cpu arguments
 
 shmobile_smp_boot_find_mpidr:
 	ldr	r8, [r5, r1, lsl #2]
@@ -80,12 +78,18 @@ ENTRY(shmobile_smp_sleep)
 	b	shmobile_smp_boot
 ENDPROC(shmobile_smp_sleep)
 
+	.align	2
+1:	.long	shmobile_smp_mpidr - .
+	.long	shmobile_smp_fn - 1b
+	.long	shmobile_smp_arg - 1b
+
+	.bss
 	.globl	shmobile_smp_mpidr
 shmobile_smp_mpidr:
-1:	.space	NR_CPUS * 4
+	.space	NR_CPUS * 4
 	.globl	shmobile_smp_fn
 shmobile_smp_fn:
-2:	.space	NR_CPUS * 4
+	.space	NR_CPUS * 4
 	.globl	shmobile_smp_arg
 shmobile_smp_arg:
-3:	.space	NR_CPUS * 4
+	.space	NR_CPUS * 4
diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c
index 911884f7e28b..aba75c89f9c1 100644
--- a/arch/arm/mach-shmobile/platsmp-apmu.c
+++ b/arch/arm/mach-shmobile/platsmp-apmu.c
@@ -123,7 +123,6 @@ void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus,
 {
 	/* install boot code shared by all CPUs */
 	shmobile_boot_fn = virt_to_phys(shmobile_smp_boot);
-	shmobile_boot_arg = MPIDR_HWID_BITMASK;
 
 	/* perform per-cpu setup */
 	apmu_parse_cfg(apmu_init_cpu, apmu_config, num);
diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c
index 64663110ab6c..081a097c9219 100644
--- a/arch/arm/mach-shmobile/platsmp-scu.c
+++ b/arch/arm/mach-shmobile/platsmp-scu.c
@@ -17,6 +17,9 @@
 #include <asm/smp_scu.h>
 #include "common.h"
 
+
+void __iomem *shmobile_scu_base;
+
 static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb,
 					  unsigned long action, void *hcpu)
 {
@@ -41,7 +44,6 @@ void __init shmobile_smp_scu_prepare_cpus(unsigned int max_cpus)
 {
 	/* install boot code shared by all CPUs */
 	shmobile_boot_fn = virt_to_phys(shmobile_smp_boot);
-	shmobile_boot_arg = MPIDR_HWID_BITMASK;
 
 	/* enable SCU and cache coherency on booting CPU */
 	scu_enable(shmobile_scu_base);
diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c
index b854fe2095ad..0b024a9dbd43 100644
--- a/arch/arm/mach-shmobile/smp-r8a7779.c
+++ b/arch/arm/mach-shmobile/smp-r8a7779.c
@@ -92,8 +92,6 @@ static void __init r8a7779_smp_prepare_cpus(unsigned int max_cpus)
 {
 	/* Map the reset vector (in headsmp-scu.S, headsmp.S) */
 	__raw_writel(__pa(shmobile_boot_vector), AVECR);
-	shmobile_boot_fn = virt_to_phys(shmobile_boot_scu);
-	shmobile_boot_arg = (unsigned long)shmobile_scu_base;
 
 	/* setup r8a7779 specific SCU bits */
 	shmobile_scu_base = IOMEM(R8A7779_SCU_BASE);
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 4b4058db0781..66353caa35b9 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -173,7 +173,7 @@ unsigned long arch_mmap_rnd(void)
 {
 	unsigned long rnd;
 
-	rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+	rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8cc62289a63e..cf118d93290d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -750,6 +750,19 @@ config ARM64_LSE_ATOMICS
 	  not support these instructions and requires the kernel to be
 	  built with binutils >= 2.25.
 
+config ARM64_VHE
+	bool "Enable support for Virtualization Host Extensions (VHE)"
+	default y
+	help
+	  Virtualization Host Extensions (VHE) allow the kernel to run
+	  directly at EL2 (instead of EL1) on processors that support
+	  it. This leads to better performance for KVM, as they reduce
+	  the cost of the world switch.
+
+	  Selecting this option allows the VHE feature to be detected
+	  at runtime, and does not affect processors that do not
+	  implement this feature.
+
 endmenu
 
 endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 307237cfe728..b5e3f6d42b88 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -88,7 +88,7 @@ Image: vmlinux
 Image.%: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-zinstall install: vmlinux
+zinstall install:
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
 %.dtb: scripts
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index abcbba2f01ba..305c552b5ec1 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -34,10 +34,10 @@ $(obj)/Image.lzma: $(obj)/Image FORCE
 $(obj)/Image.lzo: $(obj)/Image FORCE
 	$(call if_changed,lzo)
 
-install: $(obj)/Image
+install:
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
-zinstall: $(obj)/Image.gz
+zinstall:
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image.gz System.map "$(INSTALL_PATH)"
diff --git a/arch/arm64/boot/install.sh b/arch/arm64/boot/install.sh
index 12ed78aa6f0c..d91e1f022573 100644
--- a/arch/arm64/boot/install.sh
+++ b/arch/arm64/boot/install.sh
@@ -20,6 +20,20 @@
 #   $4 - default install path (blank if root directory)
 #
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
 if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 05d9e16c0dfd..7a3d22a46faf 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -294,7 +294,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_blkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= aes_setkey,
 		.encrypt	= ecb_encrypt,
 		.decrypt	= ecb_decrypt,
@@ -371,7 +371,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_ablkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= ablk_set_key,
 		.encrypt	= ablk_encrypt,
 		.decrypt	= ablk_decrypt,
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25ed2..8ec88e5b290f 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 8f271b83f910..a5c769b1c65b 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -30,8 +30,12 @@
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
 #define ARM64_WORKAROUND_834220			7
+/* #define ARM64_HAS_NO_HW_PREFETCH		8 */
+/* #define ARM64_HAS_UAO			9 */
+/* #define ARM64_ALT_PAN_NOT_UAO		10 */
+#define ARM64_HAS_VIRT_HOST_EXTN		11
 
-#define ARM64_NCAPS				8
+#define ARM64_NCAPS				12
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 9732908bfc8a..115ea2a64520 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -18,6 +18,7 @@
 
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/virt.h>
 
 #ifdef __KERNEL__
 
@@ -35,10 +36,21 @@ struct arch_hw_breakpoint {
 	struct arch_hw_breakpoint_ctrl ctrl;
 };
 
+/* Privilege Levels */
+#define AARCH64_BREAKPOINT_EL1	1
+#define AARCH64_BREAKPOINT_EL0	2
+
+#define DBG_HMC_HYP		(1 << 13)
+
 static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
 {
-	return (ctrl.len << 5) | (ctrl.type << 3) | (ctrl.privilege << 1) |
+	u32 val = (ctrl.len << 5) | (ctrl.type << 3) | (ctrl.privilege << 1) |
 		ctrl.enabled;
+
+	if (is_kernel_in_hyp_mode() && ctrl.privilege == AARCH64_BREAKPOINT_EL1)
+		val |= DBG_HMC_HYP;
+
+	return val;
 }
 
 static inline void decode_ctrl_reg(u32 reg,
@@ -61,10 +73,6 @@ static inline void decode_ctrl_reg(u32 reg,
 #define ARM_BREAKPOINT_STORE	2
 #define AARCH64_ESR_ACCESS_MASK	(1 << 6)
 
-/* Privilege Levels */
-#define AARCH64_BREAKPOINT_EL1	1
-#define AARCH64_BREAKPOINT_EL0	2
-
 /* Lengths */
 #define ARM_BREAKPOINT_LEN_1	0x1
 #define ARM_BREAKPOINT_LEN_2	0x3
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index bef6e9243c63..b56a0a81e4cb 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,7 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
+#define HCR_E2H		(UL(1) << 34)
 #define HCR_ID		(UL(1) << 33)
 #define HCR_CD		(UL(1) << 32)
 #define HCR_RW_SHIFT	31
@@ -81,7 +82,7 @@
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
 #define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
-
+#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* Hyp System Control Register (SCTLR_EL2) bits */
 #define SCTLR_EL2_EE	(1 << 25)
@@ -107,8 +108,6 @@
 #define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
 			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
 
-#define TCR_EL2_FLAGS	(TCR_EL2_RES1 | TCR_EL2_PS_40B)
-
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_RES1		(1 << 31)
 #define VTCR_EL2_PS_MASK	(7 << 16)
@@ -218,4 +217,7 @@
 	ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
 	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
 
+#define CPACR_EL1_FPEN		(3 << 20)
+#define CPACR_EL1_TTA		(1 << 28)
+
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 52b777b7d407..2d02ba67478c 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -35,9 +35,6 @@ extern char __kvm_hyp_init_end[];
 
 extern char __kvm_hyp_vector[];
 
-#define	__kvm_hyp_code_start	__hyp_text_start
-#define	__kvm_hyp_code_end	__hyp_text_end
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
@@ -45,9 +42,12 @@ extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
+extern void __init_stage2_translation(void);
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 779a5872a2c5..40bc1681b6d5 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -29,6 +29,7 @@
 #include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
+#include <asm/virt.h>
 
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu);
@@ -43,6 +44,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+	if (is_kernel_in_hyp_mode())
+		vcpu->arch.hcr_el2 |= HCR_E2H;
 	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
 }
@@ -189,6 +192,11 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
 }
 
+static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
+}
+
 static inline int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
 {
 	return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 689d4c95e12f..71fa6fe9d54a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -25,7 +25,9 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/kvm.h>
+#include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
+#include <asm/kvm_perf_event.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -36,10 +38,11 @@
 
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>
+#include <kvm/arm_pmu.h>
 
 #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
 
-#define KVM_VCPU_MAX_FEATURES 3
+#define KVM_VCPU_MAX_FEATURES 4
 
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -114,6 +117,21 @@ enum vcpu_sysreg {
 	MDSCR_EL1,	/* Monitor Debug System Control Register */
 	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
 
+	/* Performance Monitors Registers */
+	PMCR_EL0,	/* Control Register */
+	PMSELR_EL0,	/* Event Counter Selection Register */
+	PMEVCNTR0_EL0,	/* Event Counter Register (0-30) */
+	PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30,
+	PMCCNTR_EL0,	/* Cycle Counter Register */
+	PMEVTYPER0_EL0,	/* Event Type Register (0-30) */
+	PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30,
+	PMCCFILTR_EL0,	/* Cycle Count Filter Register */
+	PMCNTENSET_EL0,	/* Count Enable Set Register */
+	PMINTENSET_EL1,	/* Interrupt Enable Set Register */
+	PMOVSSET_EL0,	/* Overflow Flag Status Set Register */
+	PMSWINC_EL0,	/* Software Increment Register */
+	PMUSERENR_EL0,	/* User Enable Register */
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -211,6 +229,7 @@ struct kvm_vcpu_arch {
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
 	struct arch_timer_cpu timer_cpu;
+	struct kvm_pmu pmu;
 
 	/*
 	 * Anything that is not used directly from assembly code goes
@@ -342,5 +361,18 @@ void kvm_arm_init_debug(void);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+
+/* #define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__) */
+
+static inline void __cpu_init_stage2(void)
+{
+	kvm_call_hyp(__init_stage2_translation);
+}
 
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
new file mode 100644
index 000000000000..a46b019ebcf5
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -0,0 +1,181 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_HYP_H__
+#define __ARM64_KVM_HYP_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_perf_event.h>
+#include <asm/sysreg.h>
+
+#define __hyp_text __section(.hyp.text) notrace
+
+static inline unsigned long __kern_hyp_va(unsigned long v)
+{
+	asm volatile(ALTERNATIVE("and %0, %0, %1",
+				 "nop",
+				 ARM64_HAS_VIRT_HOST_EXTN)
+		     : "+r" (v) : "i" (HYP_PAGE_OFFSET_MASK));
+	return v;
+}
+
+#define kern_hyp_va(v) (typeof(v))(__kern_hyp_va((unsigned long)(v)))
+
+static inline unsigned long __hyp_kern_va(unsigned long v)
+{
+	u64 offset = PAGE_OFFSET - HYP_PAGE_OFFSET;
+	asm volatile(ALTERNATIVE("add %0, %0, %1",
+				 "nop",
+				 ARM64_HAS_VIRT_HOST_EXTN)
+		     : "+r" (v) : "r" (offset));
+	return v;
+}
+
+#define hyp_kern_va(v) (typeof(v))(__hyp_kern_va((unsigned long)(v)))
+
+#define read_sysreg_elx(r,nvh,vh)					\
+	({								\
+		u64 reg;						\
+		asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
+					 "mrs_s %0, " __stringify(r##vh),\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+			     : "=r" (reg));				\
+		reg;							\
+	})
+
+#define write_sysreg_elx(v,r,nvh,vh)					\
+	do {								\
+		u64 __val = (u64)(v);					\
+		asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
+					 "msr_s " __stringify(r##vh) ", %x0",\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+					 : : "rZ" (__val));		\
+	} while (0)
+
+/*
+ * Unified accessors for registers that have a different encoding
+ * between VHE and non-VHE. They must be specified without their "ELx"
+ * encoding.
+ */
+#define read_sysreg_el2(r)						\
+	({								\
+		u64 reg;						\
+		asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##_EL2),\
+					 "mrs %0, " __stringify(r##_EL1),\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+			     : "=r" (reg));				\
+		reg;							\
+	})
+
+#define write_sysreg_el2(v,r)						\
+	do {								\
+		u64 __val = (u64)(v);					\
+		asm volatile(ALTERNATIVE("msr " __stringify(r##_EL2) ", %x0",\
+					 "msr " __stringify(r##_EL1) ", %x0",\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+					 : : "rZ" (__val));		\
+	} while (0)
+
+#define read_sysreg_el0(r)	read_sysreg_elx(r, _EL0, _EL02)
+#define write_sysreg_el0(v,r)	write_sysreg_elx(v, r, _EL0, _EL02)
+#define read_sysreg_el1(r)	read_sysreg_elx(r, _EL1, _EL12)
+#define write_sysreg_el1(v,r)	write_sysreg_elx(v, r, _EL1, _EL12)
+
+/* The VHE specific system registers and their encoding */
+#define sctlr_EL12              sys_reg(3, 5, 1, 0, 0)
+#define cpacr_EL12              sys_reg(3, 5, 1, 0, 2)
+#define ttbr0_EL12              sys_reg(3, 5, 2, 0, 0)
+#define ttbr1_EL12              sys_reg(3, 5, 2, 0, 1)
+#define tcr_EL12                sys_reg(3, 5, 2, 0, 2)
+#define afsr0_EL12              sys_reg(3, 5, 5, 1, 0)
+#define afsr1_EL12              sys_reg(3, 5, 5, 1, 1)
+#define esr_EL12                sys_reg(3, 5, 5, 2, 0)
+#define far_EL12                sys_reg(3, 5, 6, 0, 0)
+#define mair_EL12               sys_reg(3, 5, 10, 2, 0)
+#define amair_EL12              sys_reg(3, 5, 10, 3, 0)
+#define vbar_EL12               sys_reg(3, 5, 12, 0, 0)
+#define contextidr_EL12         sys_reg(3, 5, 13, 0, 1)
+#define cntkctl_EL12            sys_reg(3, 5, 14, 1, 0)
+#define cntp_tval_EL02          sys_reg(3, 5, 14, 2, 0)
+#define cntp_ctl_EL02           sys_reg(3, 5, 14, 2, 1)
+#define cntp_cval_EL02          sys_reg(3, 5, 14, 2, 2)
+#define cntv_tval_EL02          sys_reg(3, 5, 14, 3, 0)
+#define cntv_ctl_EL02           sys_reg(3, 5, 14, 3, 1)
+#define cntv_cval_EL02          sys_reg(3, 5, 14, 3, 2)
+#define spsr_EL12               sys_reg(3, 5, 4, 0, 0)
+#define elr_EL12                sys_reg(3, 5, 4, 0, 1)
+
+/**
+ * hyp_alternate_select - Generates patchable code sequences that are
+ * used to switch between two implementations of a function, depending
+ * on the availability of a feature.
+ *
+ * @fname: a symbol name that will be defined as a function returning a
+ * function pointer whose type will match @orig and @alt
+ * @orig: A pointer to the default function, as returned by @fname when
+ * @cond doesn't hold
+ * @alt: A pointer to the alternate function, as returned by @fname
+ * when @cond holds
+ * @cond: a CPU feature (as described in asm/cpufeature.h)
+ */
+#define hyp_alternate_select(fname, orig, alt, cond)			\
+typeof(orig) * __hyp_text fname(void)					\
+{									\
+	typeof(alt) *val = orig;					\
+	asm volatile(ALTERNATIVE("nop		\n",			\
+				 "mov	%0, %1	\n",			\
+				 cond)					\
+		     : "+r" (val) : "r" (alt));				\
+	return val;							\
+}
+
+void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
+
+void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
+
+void __timer_save_state(struct kvm_vcpu *vcpu);
+void __timer_restore_state(struct kvm_vcpu *vcpu);
+
+void __sysreg_save_host_state(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_host_state(struct kvm_cpu_context *ctxt);
+void __sysreg_save_guest_state(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt);
+void __sysreg32_save_state(struct kvm_vcpu *vcpu);
+void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
+
+void __debug_save_state(struct kvm_vcpu *vcpu,
+			struct kvm_guest_debug_arch *dbg,
+			struct kvm_cpu_context *ctxt);
+void __debug_restore_state(struct kvm_vcpu *vcpu,
+			   struct kvm_guest_debug_arch *dbg,
+			   struct kvm_cpu_context *ctxt);
+void __debug_cond_save_host_state(struct kvm_vcpu *vcpu);
+void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu);
+
+void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
+void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
+bool __fpsimd_enabled(void);
+
+u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+void __noreturn __hyp_do_panic(unsigned long, ...);
+
+#endif /* __ARM64_KVM_HYP_H__ */
+
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 736433912a1e..9a9318adefa6 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -23,13 +23,16 @@
 #include <asm/cpufeature.h>
 
 /*
- * As we only have the TTBR0_EL2 register, we cannot express
+ * As ARMv8.0 only has the TTBR0_EL2 register, we cannot express
  * "negative" addresses. This makes it impossible to directly share
  * mappings with the kernel.
  *
  * Instead, give the HYP mode its own VA region at a fixed offset from
  * the kernel by just masking the top bits (which are all ones for a
  * kernel address).
+ *
+ * ARMv8.1 (using VHE) does have a TTBR1_EL2, and doesn't use these
+ * macros (the entire kernel runs at EL2).
  */
 #define HYP_PAGE_OFFSET_SHIFT	VA_BITS
 #define HYP_PAGE_OFFSET_MASK	((UL(1) << HYP_PAGE_OFFSET_SHIFT) - 1)
@@ -56,12 +59,19 @@
 
 #ifdef __ASSEMBLY__
 
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+
 /*
  * Convert a kernel VA into a HYP VA.
  * reg: VA to be converted.
  */
 .macro kern_hyp_va	reg
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN	
 	and	\reg, \reg, #HYP_PAGE_OFFSET_MASK
+alternative_else
+	nop
+alternative_endif
 .endm
 
 #else
diff --git a/arch/arm64/include/asm/kvm_perf_event.h b/arch/arm64/include/asm/kvm_perf_event.h
new file mode 100644
index 000000000000..c18fdebb8f66
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_perf_event.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_KVM_PERF_EVENT_H
+#define __ASM_KVM_PERF_EVENT_H
+
+#define	ARMV8_PMU_MAX_COUNTERS	32
+#define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
+
+/*
+ * Per-CPU PMCR: config reg
+ */
+#define ARMV8_PMU_PMCR_E	(1 << 0) /* Enable all counters */
+#define ARMV8_PMU_PMCR_P	(1 << 1) /* Reset all counters */
+#define ARMV8_PMU_PMCR_C	(1 << 2) /* Cycle counter reset */
+#define ARMV8_PMU_PMCR_D	(1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV8_PMU_PMCR_X	(1 << 4) /* Export to ETM */
+#define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
+/* Determines which bit of PMCCNTR_EL0 generates an overflow */
+#define ARMV8_PMU_PMCR_LC	(1 << 6)
+#define	ARMV8_PMU_PMCR_N_SHIFT	11	 /* Number of counters supported */
+#define	ARMV8_PMU_PMCR_N_MASK	0x1f
+#define	ARMV8_PMU_PMCR_MASK	0x7f	 /* Mask for writable bits */
+
+/*
+ * PMOVSR: counters overflow flag status reg
+ */
+#define	ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
+#define	ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+
+/*
+ * PMXEVTYPER: Event selection reg
+ */
+#define	ARMV8_PMU_EVTYPE_MASK	0xc80003ff	/* Mask for writable bits */
+#define	ARMV8_PMU_EVTYPE_EVENT	0x3ff		/* Mask for EVENT bits */
+
+#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR	0	/* Software increment event */
+
+/*
+ * Event filters for PMUv3
+ */
+#define	ARMV8_PMU_EXCLUDE_EL1	(1 << 31)
+#define	ARMV8_PMU_EXCLUDE_EL0	(1 << 30)
+#define	ARMV8_PMU_INCLUDE_EL2	(1 << 27)
+
+/*
+ * PMUSERENR: user enable reg
+ */
+#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
+#define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
+#define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
+#define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+
+#endif
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 7a5df5252dd7..9f22dd607958 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -23,6 +23,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/ptrace.h>
+
 /*
  * __boot_cpu_mode records what mode CPUs were booted in.
  * A correctly-implemented bootloader must start all CPUs in the same mode:
@@ -50,6 +52,14 @@ static inline bool is_hyp_mode_mismatched(void)
 	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
 }
 
+static inline bool is_kernel_in_hyp_mode(void)
+{
+	u64 el;
+
+	asm("mrs %0, CurrentEL" : "=r" (el));
+	return el == CurrentEL_EL2;
+}
+
 /* The section containing the hypervisor text */
 extern char __hyp_text_start[];
 extern char __hyp_text_end[];
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 2d4ca4bb0dd3..f209ea151dca 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -94,6 +94,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
 #define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
+#define KVM_ARM_VCPU_PMU_V3		3 /* Support guest PMUv3 */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -204,6 +205,11 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_CTRL	4
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
 
+/* Device Control API on vcpu fd */
+#define KVM_ARM_VCPU_PMU_V3_CTRL	0
+#define   KVM_ARM_VCPU_PMU_V3_IRQ	0
+#define   KVM_ARM_VCPU_PMU_V3_INIT	1
+
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
 #define KVM_ARM_IRQ_TYPE_MASK		0xff
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index fffa4ac6c25a..b0ab4e93db0d 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -110,9 +110,6 @@ int main(void)
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
   DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
-  DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
-  DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
-  DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
 #endif
 #ifdef CONFIG_CPU_PM
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 5c90aa490a2b..ba745199297e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -26,6 +26,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
+#include <asm/virt.h>
 
 unsigned long elf_hwcap __read_mostly;
 EXPORT_SYMBOL_GPL(elf_hwcap);
@@ -621,6 +622,11 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry)
 	return has_sre;
 }
 
+static bool runs_at_el2(const struct arm64_cpu_capabilities *entry)
+{
+	return is_kernel_in_hyp_mode();
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -651,6 +657,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 2,
 	},
 #endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+	{
+		.desc = "Virtualization Host Extensions",
+		.capability = ARM64_HAS_VIRT_HOST_EXTN,
+		.matches = runs_at_el2,
+	},
 	{},
 };
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 8aee3aeec3e6..c536c9e307b9 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -226,11 +226,28 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 	return retval;
 }
 
+static void send_user_sigtrap(int si_code)
+{
+	struct pt_regs *regs = current_pt_regs();
+	siginfo_t info = {
+		.si_signo	= SIGTRAP,
+		.si_errno	= 0,
+		.si_code	= si_code,
+		.si_addr	= (void __user *)instruction_pointer(regs),
+	};
+
+	if (WARN_ON(!user_mode(regs)))
+		return;
+
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
+	force_sig_info(SIGTRAP, &info, current);
+}
+
 static int single_step_handler(unsigned long addr, unsigned int esr,
 			       struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	/*
 	 * If we are stepping a pending breakpoint, call the hw_breakpoint
 	 * handler first.
@@ -239,11 +256,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 		return 0;
 
 	if (user_mode(regs)) {
-		info.si_signo = SIGTRAP;
-		info.si_errno = 0;
-		info.si_code  = TRAP_HWBKPT;
-		info.si_addr  = (void __user *)instruction_pointer(regs);
-		force_sig_info(SIGTRAP, &info, current);
+		send_user_sigtrap(TRAP_HWBKPT);
 
 		/*
 		 * ptrace will disable single step unless explicitly
@@ -307,17 +320,8 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 static int brk_handler(unsigned long addr, unsigned int esr,
 		       struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	if (user_mode(regs)) {
-		info = (siginfo_t) {
-			.si_signo = SIGTRAP,
-			.si_errno = 0,
-			.si_code  = TRAP_BRKPT,
-			.si_addr  = (void __user *)instruction_pointer(regs),
-		};
-
-		force_sig_info(SIGTRAP, &info, current);
+		send_user_sigtrap(TRAP_BRKPT);
 	} else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
 		pr_warning("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
@@ -328,7 +332,6 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 
 int aarch32_break_handler(struct pt_regs *regs)
 {
-	siginfo_t info;
 	u32 arm_instr;
 	u16 thumb_instr;
 	bool bp = false;
@@ -359,14 +362,7 @@ int aarch32_break_handler(struct pt_regs *regs)
 	if (!bp)
 		return -EFAULT;
 
-	info = (siginfo_t) {
-		.si_signo = SIGTRAP,
-		.si_errno = 0,
-		.si_code  = TRAP_BRKPT,
-		.si_addr  = pc,
-	};
-
-	force_sig_info(SIGTRAP, &info, current);
+	send_user_sigtrap(TRAP_BRKPT);
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 917d98108b3f..6f2f37743d3b 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -30,6 +30,7 @@
 #include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/kernel-pgtable.h>
+#include <asm/kvm_arm.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
@@ -464,9 +465,27 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	isb
 	ret
 
+2:
+#ifdef CONFIG_ARM64_VHE
+	/*
+	 * Check for VHE being present. For the rest of the EL2 setup,
+	 * x2 being non-zero indicates that we do have VHE, and that the
+	 * kernel is intended to run at EL2.
+	 */
+	mrs	x2, id_aa64mmfr1_el1
+	ubfx	x2, x2, #8, #4
+#else
+	mov	x2, xzr
+#endif
+
 	/* Hyp configuration. */
-2:	mov	x0, #(1 << 31)			// 64-bit EL1
+	mov	x0, #HCR_RW			// 64-bit EL1
+	cbz	x2, set_hcr
+	orr	x0, x0, #HCR_TGE		// Enable Host Extensions
+	orr	x0, x0, #HCR_E2H
+set_hcr:
 	msr	hcr_el2, x0
+	isb
 
 	/* Generic timers. */
 	mrs	x0, cnthctl_el2
@@ -526,6 +545,13 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
 
+	cbz	x2, install_el2_stub
+
+	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
+	isb
+	ret
+
+install_el2_stub:
 	/* Hypervisor stub */
 	adrp	x0, __hyp_stub_vectors
 	add	x0, x0, #:lo12:__hyp_stub_vectors
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index 999633bd7294..352f7abd91c9 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -89,6 +89,7 @@ __efistub_memcpy		= KALLSYMS_HIDE(__pi_memcpy);
 __efistub_memmove		= KALLSYMS_HIDE(__pi_memmove);
 __efistub_memset		= KALLSYMS_HIDE(__pi_memset);
 __efistub_strlen		= KALLSYMS_HIDE(__pi_strlen);
+__efistub_strnlen		= KALLSYMS_HIDE(__pi_strnlen);
 __efistub_strcmp		= KALLSYMS_HIDE(__pi_strcmp);
 __efistub_strncmp		= KALLSYMS_HIDE(__pi_strncmp);
 __efistub___flush_dcache_area	= KALLSYMS_HIDE(__pi___flush_dcache_area);
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index f7ab14c4d5df..1b52269ffa87 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -20,6 +20,7 @@
  */
 
 #include <asm/irq_regs.h>
+#include <asm/virt.h>
 
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
@@ -691,9 +692,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 
 	if (attr->exclude_idle)
 		return -EPERM;
+	if (is_kernel_in_hyp_mode() &&
+	    attr->exclude_kernel != attr->exclude_hv)
+		return -EINVAL;
 	if (attr->exclude_user)
 		config_base |= ARMV8_EXCLUDE_EL0;
-	if (attr->exclude_kernel)
+	if (!is_kernel_in_hyp_mode() && attr->exclude_kernel)
 		config_base |= ARMV8_EXCLUDE_EL1;
 	if (!attr->exclude_hv)
 		config_base |= ARMV8_INCLUDE_EL2;
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 4fad9787ab46..d9751a4769e7 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -44,14 +44,13 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	unsigned long irq_stack_ptr;
 
 	/*
-	 * Use raw_smp_processor_id() to avoid false-positives from
-	 * CONFIG_DEBUG_PREEMPT. get_wchan() calls unwind_frame() on sleeping
-	 * task stacks, we can be pre-empted in this case, so
-	 * {raw_,}smp_processor_id() may give us the wrong value. Sleeping
-	 * tasks can't ever be on an interrupt stack, so regardless of cpu,
-	 * the checks will always fail.
+	 * Switching between stacks is valid when tracing current and in
+	 * non-preemptible context.
 	 */
-	irq_stack_ptr = IRQ_STACK_PTR(raw_smp_processor_id());
+	if (tsk == current && !preemptible())
+		irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	else
+		irq_stack_ptr = 0;
 
 	low  = frame->sp;
 	/* irq stacks are not THREAD_SIZE aligned */
@@ -64,8 +63,8 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 		return -EINVAL;
 
 	frame->sp = fp + 0x10;
-	frame->fp = *(unsigned long *)(fp);
-	frame->pc = *(unsigned long *)(fp + 8);
+	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
+	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk && tsk->ret_stack &&
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index cbedd724f48e..c5392081b49b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -146,9 +146,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
-	unsigned long irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	unsigned long irq_stack_ptr;
 	int skip;
 
+	/*
+	 * Switching between stacks is valid when tracing current and in
+	 * non-preemptible context.
+	 */
+	if (tsk == current && !preemptible())
+		irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	else
+		irq_stack_ptr = 0;
+
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
 	if (!tsk)
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index a5272c07d1cb..de7450df7629 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -36,6 +36,7 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	select KVM_ARM_VGIC_V3
+	select KVM_ARM_PMU if HW_PERF_EVENTS
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple
@@ -48,6 +49,12 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.
 
+config KVM_ARM_PMU
+	bool
+	---help---
+	  Adds support for a virtual Performance Monitoring Unit (PMU) in
+	  virtual machines.
+
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index caee9ee8e12a..122cff482ac4 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -26,3 +26,4 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
+kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index fcb778899a38..dbe45c364bbb 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -380,3 +380,54 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	}
 	return 0;
 }
+
+int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_ARM_VCPU_PMU_V3_CTRL:
+		ret = kvm_arm_pmu_v3_set_attr(vcpu, attr);
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_ARM_VCPU_PMU_V3_CTRL:
+		ret = kvm_arm_pmu_v3_get_attr(vcpu, attr);
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_ARM_VCPU_PMU_V3_CTRL:
+		ret = kvm_arm_pmu_v3_has_attr(vcpu, attr);
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 3e568dcd907b..7d8747c6427c 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -64,7 +64,7 @@ __do_hyp_init:
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK
 	and	x4, x4, x5
-	ldr	x5, =TCR_EL2_FLAGS
+	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
 #ifndef CONFIG_ARM64_VA_BITS_48
@@ -85,25 +85,14 @@ __do_hyp_init:
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 #endif
-	msr	tcr_el2, x4
-
-	ldr	x4, =VTCR_EL2_FLAGS
 	/*
 	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
-	 * VTCR_EL2.
+	 * TCR_EL2.
 	 */
 	mrs	x5, ID_AA64MMFR0_EL1
 	bfi	x4, x5, #16, #3
-	/*
-	 * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS bit in
-	 * VTCR_EL2.
-	 */
-	mrs	x5, ID_AA64MMFR1_EL1
-	ubfx	x5, x5, #5, #1
-	lsl	x5, x5, #VTCR_EL2_VS
-	orr	x4, x4, x5
 
-	msr	vtcr_el2, x4
+	msr	tcr_el2, x4
 
 	mrs	x4, mair_el1
 	msr	mair_el2, x4
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 0ccdcbbef3c2..0689a74e6ba0 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -17,7 +17,9 @@
 
 #include <linux/linkage.h>
 
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
 
 /*
  * u64 kvm_call_hyp(void *hypfn, ...);
@@ -38,6 +40,11 @@
  * arch/arm64/kernel/hyp_stub.S.
  */
 ENTRY(kvm_call_hyp)
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN	
 	hvc	#0
 	ret
+alternative_else
+	b	__vhe_hyp_call
+	nop
+alternative_endif
 ENDPROC(kvm_call_hyp)
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 826032bc3945..b6a8fc5ad1af 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -2,9 +2,12 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-sr.o
+KVM=../../../../virt/kvm
+
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+
 obj-$(CONFIG_KVM_ARM_HOST) += vgic-v3-sr.o
-obj-$(CONFIG_KVM_ARM_HOST) += timer-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += entry.o
@@ -12,3 +15,4 @@ obj-$(CONFIG_KVM_ARM_HOST) += switch.o
 obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o
 obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
 obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
+obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index c9c1e97501a9..053cf8b057c1 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -19,9 +19,7 @@
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 #define read_debug(r,n)		read_sysreg(r##n##_el1)
 #define write_debug(v,r,n)	write_sysreg(v, r##n##_el1)
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index fd0fbe9b7e6a..ce9e5e5f28cf 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -130,9 +130,15 @@ ENDPROC(__guest_exit)
 ENTRY(__fpsimd_guest_restore)
 	stp	x4, lr, [sp, #-16]!
 
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	x2, cptr_el2
 	bic	x2, x2, #CPTR_EL2_TFP
 	msr	cptr_el2, x2
+alternative_else
+	mrs	x2, cpacr_el1
+	orr	x2, x2, #CPACR_EL1_FPEN
+	msr	cpacr_el1, x2
+alternative_endif
 	isb
 
 	mrs	x3, tpidr_el2
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 93e8d983c0bd..3488894397ff 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -19,7 +19,6 @@
 
 #include <asm/alternative.h>
 #include <asm/assembler.h>
-#include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
@@ -38,10 +37,42 @@
 	ldp	x0, x1, [sp], #16
 .endm
 
+.macro do_el2_call
+	/*
+	 * Shuffle the parameters before calling the function
+	 * pointed to in x0. Assumes parameters in x[1,2,3].
+	 */
+	sub	sp, sp, #16
+	str	lr, [sp]
+	mov	lr, x0
+	mov	x0, x1
+	mov	x1, x2
+	mov	x2, x3
+	blr	lr
+	ldr	lr, [sp]
+	add	sp, sp, #16
+.endm
+
+ENTRY(__vhe_hyp_call)
+	do_el2_call
+	/*
+	 * We used to rely on having an exception return to get
+	 * an implicit isb. In the E2H case, we don't have it anymore.
+	 * rather than changing all the leaf functions, just do it here
+	 * before returning to the rest of the kernel.
+	 */
+	isb
+	ret
+ENDPROC(__vhe_hyp_call)
+	
 el1_sync:				// Guest trapped into EL2
 	save_x0_to_x3
 
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	x1, esr_el2
+alternative_else
+	mrs	x1, esr_el1
+alternative_endif
 	lsr	x2, x1, #ESR_ELx_EC_SHIFT
 
 	cmp	x2, #ESR_ELx_EC_HVC64
@@ -58,19 +89,13 @@ el1_sync:				// Guest trapped into EL2
 	mrs	x0, vbar_el2
 	b	2f
 
-1:	stp	lr, xzr, [sp, #-16]!
-
+1:
 	/*
-	 * Compute the function address in EL2, and shuffle the parameters.
+	 * Perform the EL2 call
 	 */
 	kern_hyp_va	x0
-	mov	lr, x0
-	mov	x0, x1
-	mov	x1, x2
-	mov	x2, x3
-	blr	lr
+	do_el2_call
 
-	ldp	lr, xzr, [sp], #16
 2:	eret
 
 el1_trap:
@@ -83,72 +108,10 @@ el1_trap:
 	cmp	x2, #ESR_ELx_EC_FP_ASIMD
 	b.eq	__fpsimd_guest_restore
 
-	cmp	x2, #ESR_ELx_EC_DABT_LOW
-	mov	x0, #ESR_ELx_EC_IABT_LOW
-	ccmp	x2, x0, #4, ne
-	b.ne	1f		// Not an abort we care about
-
-	/* This is an abort. Check for permission fault */
-alternative_if_not ARM64_WORKAROUND_834220
-	and	x2, x1, #ESR_ELx_FSC_TYPE
-	cmp	x2, #FSC_PERM
-	b.ne	1f		// Not a permission fault
-alternative_else
-	nop			// Use the permission fault path to
-	nop			// check for a valid S1 translation,
-	nop			// regardless of the ESR value.
-alternative_endif
-
-	/*
-	 * Check for Stage-1 page table walk, which is guaranteed
-	 * to give a valid HPFAR_EL2.
-	 */
-	tbnz	x1, #7, 1f	// S1PTW is set
-
-	/* Preserve PAR_EL1 */
-	mrs	x3, par_el1
-	stp	x3, xzr, [sp, #-16]!
-
-	/*
-	 * Permission fault, HPFAR_EL2 is invalid.
-	 * Resolve the IPA the hard way using the guest VA.
-	 * Stage-1 translation already validated the memory access rights.
-	 * As such, we can use the EL1 translation regime, and don't have
-	 * to distinguish between EL0 and EL1 access.
-	 */
-	mrs	x2, far_el2
-	at	s1e1r, x2
-	isb
-
-	/* Read result */
-	mrs	x3, par_el1
-	ldp	x0, xzr, [sp], #16	// Restore PAR_EL1 from the stack
-	msr	par_el1, x0
-	tbnz	x3, #0, 3f		// Bail out if we failed the translation
-	ubfx	x3, x3, #12, #36	// Extract IPA
-	lsl	x3, x3, #4		// and present it like HPFAR
-	b	2f
-
-1:	mrs	x3, hpfar_el2
-	mrs	x2, far_el2
-
-2:	mrs	x0, tpidr_el2
-	str	w1, [x0, #VCPU_ESR_EL2]
-	str	x2, [x0, #VCPU_FAR_EL2]
-	str	x3, [x0, #VCPU_HPFAR_EL2]
-
+	mrs	x0, tpidr_el2
 	mov	x1, #ARM_EXCEPTION_TRAP
 	b	__guest_exit
 
-	/*
-	 * Translation failed. Just return to the guest and
-	 * let it fault again. Another CPU is probably playing
-	 * behind our back.
-	 */
-3:	restore_x0_to_x3
-
-	eret
-
 el1_irq:
 	save_x0_to_x3
 	mrs	x0, tpidr_el2
diff --git a/arch/arm64/kvm/hyp/hyp.h b/arch/arm64/kvm/hyp/hyp.h
deleted file mode 100644
index fb275178b6af..000000000000
--- a/arch/arm64/kvm/hyp/hyp.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Copyright (C) 2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.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 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_KVM_HYP_H__
-#define __ARM64_KVM_HYP_H__
-
-#include <linux/compiler.h>
-#include <linux/kvm_host.h>
-#include <asm/kvm_mmu.h>
-#include <asm/sysreg.h>
-
-#define __hyp_text __section(.hyp.text) notrace
-
-#define kern_hyp_va(v) (typeof(v))((unsigned long)(v) & HYP_PAGE_OFFSET_MASK)
-#define hyp_kern_va(v) (typeof(v))((unsigned long)(v) - HYP_PAGE_OFFSET \
-						      + PAGE_OFFSET)
-
-/**
- * hyp_alternate_select - Generates patchable code sequences that are
- * used to switch between two implementations of a function, depending
- * on the availability of a feature.
- *
- * @fname: a symbol name that will be defined as a function returning a
- * function pointer whose type will match @orig and @alt
- * @orig: A pointer to the default function, as returned by @fname when
- * @cond doesn't hold
- * @alt: A pointer to the alternate function, as returned by @fname
- * when @cond holds
- * @cond: a CPU feature (as described in asm/cpufeature.h)
- */
-#define hyp_alternate_select(fname, orig, alt, cond)			\
-typeof(orig) * __hyp_text fname(void)					\
-{									\
-	typeof(alt) *val = orig;					\
-	asm volatile(ALTERNATIVE("nop		\n",			\
-				 "mov	%0, %1	\n",			\
-				 cond)					\
-		     : "+r" (val) : "r" (alt));				\
-	return val;							\
-}
-
-void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
-void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
-
-void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
-void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
-
-void __timer_save_state(struct kvm_vcpu *vcpu);
-void __timer_restore_state(struct kvm_vcpu *vcpu);
-
-void __sysreg_save_state(struct kvm_cpu_context *ctxt);
-void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
-void __sysreg32_save_state(struct kvm_vcpu *vcpu);
-void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
-
-void __debug_save_state(struct kvm_vcpu *vcpu,
-			struct kvm_guest_debug_arch *dbg,
-			struct kvm_cpu_context *ctxt);
-void __debug_restore_state(struct kvm_vcpu *vcpu,
-			   struct kvm_guest_debug_arch *dbg,
-			   struct kvm_cpu_context *ctxt);
-void __debug_cond_save_host_state(struct kvm_vcpu *vcpu);
-void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu);
-
-void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
-void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
-static inline bool __fpsimd_enabled(void)
-{
-	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
-}
-
-u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
-void __noreturn __hyp_do_panic(unsigned long, ...);
-
-#endif /* __ARM64_KVM_HYP_H__ */
-
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
new file mode 100644
index 000000000000..bfc54fd82797
--- /dev/null
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/types.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+void __hyp_text __init_stage2_translation(void)
+{
+	u64 val = VTCR_EL2_FLAGS;
+	u64 tmp;
+
+	/*
+	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS
+	 * bits in VTCR_EL2. Amusingly, the PARange is 4 bits, while
+	 * PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
+	 */
+	val |= (read_sysreg(id_aa64mmfr0_el1) & 7) << 16;
+
+	/*
+	 * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS
+	 * bit in VTCR_EL2.
+	 */
+	tmp = (read_sysreg(id_aa64mmfr1_el1) >> 4) & 0xf;
+	val |= (tmp == 2) ? VTCR_EL2_VS : 0;
+
+	write_sysreg(val, vtcr_el2);
+}
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index f0e7bdfae134..437cfad5e3d8 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -15,7 +15,53 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "hyp.h"
+#include <linux/types.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+static bool __hyp_text __fpsimd_enabled_nvhe(void)
+{
+	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
+}
+
+static bool __hyp_text __fpsimd_enabled_vhe(void)
+{
+	return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN);
+}
+
+static hyp_alternate_select(__fpsimd_is_enabled,
+			    __fpsimd_enabled_nvhe, __fpsimd_enabled_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+bool __hyp_text __fpsimd_enabled(void)
+{
+	return __fpsimd_is_enabled()();
+}
+
+static void __hyp_text __activate_traps_vhe(void)
+{
+	u64 val;
+
+	val = read_sysreg(cpacr_el1);
+	val |= CPACR_EL1_TTA;
+	val &= ~CPACR_EL1_FPEN;
+	write_sysreg(val, cpacr_el1);
+
+	write_sysreg(__kvm_hyp_vector, vbar_el1);
+}
+
+static void __hyp_text __activate_traps_nvhe(void)
+{
+	u64 val;
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
+	write_sysreg(val, cptr_el2);
+}
+
+static hyp_alternate_select(__activate_traps_arch,
+			    __activate_traps_nvhe, __activate_traps_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
 
 static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 {
@@ -36,20 +82,37 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(val, hcr_el2);
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
+	/* Make sure we trap PMU access from EL0 to EL2 */
+	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+	__activate_traps_arch()();
+}
 
-	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
-	write_sysreg(val, cptr_el2);
+static void __hyp_text __deactivate_traps_vhe(void)
+{
+	extern char vectors[];	/* kernel exception vectors */
 
-	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+	write_sysreg(CPACR_EL1_FPEN, cpacr_el1);
+	write_sysreg(vectors, vbar_el1);
 }
 
-static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	write_sysreg(HCR_RW, hcr_el2);
+	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
+}
+
+static hyp_alternate_select(__deactivate_traps_arch,
+			    __deactivate_traps_nvhe, __deactivate_traps_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	__deactivate_traps_arch()();
 	write_sysreg(0, hstr_el2);
 	write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2);
-	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
+	write_sysreg(0, pmuserenr_el0);
 }
 
 static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
@@ -89,6 +152,86 @@ static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
 	__vgic_call_restore_state()(vcpu);
 }
 
+static bool __hyp_text __true_value(void)
+{
+	return true;
+}
+
+static bool __hyp_text __false_value(void)
+{
+	return false;
+}
+
+static hyp_alternate_select(__check_arm_834220,
+			    __false_value, __true_value,
+			    ARM64_WORKAROUND_834220);
+
+static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+	u64 par, tmp;
+
+	/*
+	 * Resolve the IPA the hard way using the guest VA.
+	 *
+	 * Stage-1 translation already validated the memory access
+	 * rights. As such, we can use the EL1 translation regime, and
+	 * don't have to distinguish between EL0 and EL1 access.
+	 *
+	 * We do need to save/restore PAR_EL1 though, as we haven't
+	 * saved the guest context yet, and we may return early...
+	 */
+	par = read_sysreg(par_el1);
+	asm volatile("at s1e1r, %0" : : "r" (far));
+	isb();
+
+	tmp = read_sysreg(par_el1);
+	write_sysreg(par, par_el1);
+
+	if (unlikely(tmp & 1))
+		return false; /* Translation failed, back to guest */
+
+	/* Convert PAR to HPFAR format */
+	*hpfar = ((tmp >> 12) & ((1UL << 36) - 1)) << 4;
+	return true;
+}
+
+static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u64 esr = read_sysreg_el2(esr);
+	u8 ec = esr >> ESR_ELx_EC_SHIFT;
+	u64 hpfar, far;
+
+	vcpu->arch.fault.esr_el2 = esr;
+
+	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+		return true;
+
+	far = read_sysreg_el2(far);
+
+	/*
+	 * The HPFAR can be invalid if the stage 2 fault did not
+	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+	 * bit is clear) and one of the two following cases are true:
+	 *   1. The fault was due to a permission fault
+	 *   2. The processor carries errata 834220
+	 *
+	 * Therefore, for all non S1PTW faults where we either have a
+	 * permission fault or the errata workaround is enabled, we
+	 * resolve the IPA using the AT instruction.
+	 */
+	if (!(esr & ESR_ELx_S1PTW) &&
+	    (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+		if (!__translate_far_to_hpfar(far, &hpfar))
+			return false;
+	} else {
+		hpfar = read_sysreg(hpfar_el2);
+	}
+
+	vcpu->arch.fault.far_el2 = far;
+	vcpu->arch.fault.hpfar_el2 = hpfar;
+	return true;
+}
+
 static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
@@ -102,7 +245,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
 	guest_ctxt = &vcpu->arch.ctxt;
 
-	__sysreg_save_state(host_ctxt);
+	__sysreg_save_host_state(host_ctxt);
 	__debug_cond_save_host_state(vcpu);
 
 	__activate_traps(vcpu);
@@ -116,16 +259,20 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 	 * to Cortex-A57 erratum #852523.
 	 */
 	__sysreg32_restore_state(vcpu);
-	__sysreg_restore_state(guest_ctxt);
+	__sysreg_restore_guest_state(guest_ctxt);
 	__debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
 
 	/* Jump in the fire! */
+again:
 	exit_code = __guest_enter(vcpu, host_ctxt);
 	/* And we're baaack! */
 
+	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
+		goto again;
+
 	fp_enabled = __fpsimd_enabled();
 
-	__sysreg_save_state(guest_ctxt);
+	__sysreg_save_guest_state(guest_ctxt);
 	__sysreg32_save_state(vcpu);
 	__timer_save_state(vcpu);
 	__vgic_save_state(vcpu);
@@ -133,7 +280,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 	__deactivate_traps(vcpu);
 	__deactivate_vm(vcpu);
 
-	__sysreg_restore_state(host_ctxt);
+	__sysreg_restore_host_state(host_ctxt);
 
 	if (fp_enabled) {
 		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
@@ -150,11 +297,34 @@ __alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
 
-void __hyp_text __noreturn __hyp_panic(void)
+static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
 {
 	unsigned long str_va = (unsigned long)__hyp_panic_string;
-	u64 spsr = read_sysreg(spsr_el2);
-	u64 elr = read_sysreg(elr_el2);
+
+	__hyp_do_panic(hyp_kern_va(str_va),
+		       spsr,  elr,
+		       read_sysreg(esr_el2),   read_sysreg_el2(far),
+		       read_sysreg(hpfar_el2), par,
+		       (void *)read_sysreg(tpidr_el2));
+}
+
+static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par)
+{
+	panic(__hyp_panic_string,
+	      spsr,  elr,
+	      read_sysreg_el2(esr),   read_sysreg_el2(far),
+	      read_sysreg(hpfar_el2), par,
+	      (void *)read_sysreg(tpidr_el2));
+}
+
+static hyp_alternate_select(__hyp_call_panic,
+			    __hyp_call_panic_nvhe, __hyp_call_panic_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+void __hyp_text __noreturn __hyp_panic(void)
+{
+	u64 spsr = read_sysreg_el2(spsr);
+	u64 elr = read_sysreg_el2(elr);
 	u64 par = read_sysreg(par_el1);
 
 	if (read_sysreg(vttbr_el2)) {
@@ -165,15 +335,11 @@ void __hyp_text __noreturn __hyp_panic(void)
 		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
 		__deactivate_traps(vcpu);
 		__deactivate_vm(vcpu);
-		__sysreg_restore_state(host_ctxt);
+		__sysreg_restore_host_state(host_ctxt);
 	}
 
 	/* Call panic for real */
-	__hyp_do_panic(hyp_kern_va(str_va),
-		       spsr,  elr,
-		       read_sysreg(esr_el2),   read_sysreg(far_el2),
-		       read_sysreg(hpfar_el2), par,
-		       (void *)read_sysreg(tpidr_el2));
+	__hyp_call_panic()(spsr, elr, par);
 
 	unreachable();
 }
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 425630980229..0f7c40eb3f53 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -19,75 +19,122 @@
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmu.h>
+#include <asm/kvm_hyp.h>
 
-#include "hyp.h"
+/* Yes, this does nothing, on purpose */
+static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
 
-/* ctxt is already in the HYP VA space */
-void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+/*
+ * Non-VHE: Both host and guest must save everything.
+ *
+ * VHE: Host must save tpidr*_el[01], actlr_el1, sp0, pc, pstate, and
+ * guest must save everything.
+ */
+
+static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
-	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
-	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg(sctlr_el1);
 	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
-	ctxt->sys_regs[CPACR_EL1]	= read_sysreg(cpacr_el1);
-	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg(ttbr0_el1);
-	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg(ttbr1_el1);
-	ctxt->sys_regs[TCR_EL1]		= read_sysreg(tcr_el1);
-	ctxt->sys_regs[ESR_EL1]		= read_sysreg(esr_el1);
-	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg(afsr0_el1);
-	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg(afsr1_el1);
-	ctxt->sys_regs[FAR_EL1]		= read_sysreg(far_el1);
-	ctxt->sys_regs[MAIR_EL1]	= read_sysreg(mair_el1);
-	ctxt->sys_regs[VBAR_EL1]	= read_sysreg(vbar_el1);
-	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg(contextidr_el1);
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
-	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg(amair_el1);
-	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg(cntkctl_el1);
+	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
+	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
+	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
+}
+
+static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
+	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
+	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(sctlr);
+	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(cpacr);
+	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(ttbr0);
+	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(ttbr1);
+	ctxt->sys_regs[TCR_EL1]		= read_sysreg_el1(tcr);
+	ctxt->sys_regs[ESR_EL1]		= read_sysreg_el1(esr);
+	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg_el1(afsr0);
+	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg_el1(afsr1);
+	ctxt->sys_regs[FAR_EL1]		= read_sysreg_el1(far);
+	ctxt->sys_regs[MAIR_EL1]	= read_sysreg_el1(mair);
+	ctxt->sys_regs[VBAR_EL1]	= read_sysreg_el1(vbar);
+	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg_el1(contextidr);
+	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(amair);
+	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(cntkctl);
 	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 
-	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
-	ctxt->gp_regs.regs.pc		= read_sysreg(elr_el2);
-	ctxt->gp_regs.regs.pstate	= read_sysreg(spsr_el2);
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
-	ctxt->gp_regs.elr_el1		= read_sysreg(elr_el1);
-	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg(spsr_el1);
+	ctxt->gp_regs.elr_el1		= read_sysreg_el1(elr);
+	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr);
+}
+
+static hyp_alternate_select(__sysreg_call_save_host_state,
+			    __sysreg_save_state, __sysreg_do_nothing,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+void __hyp_text __sysreg_save_host_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_call_save_host_state()(ctxt);
+	__sysreg_save_common_state(ctxt);
+}
+
+void __hyp_text __sysreg_save_guest_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_state(ctxt);
+	__sysreg_save_common_state(ctxt);
 }
 
-void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[MPIDR_EL1],	  vmpidr_el2);
-	write_sysreg(ctxt->sys_regs[CSSELR_EL1],  csselr_el1);
-	write_sysreg(ctxt->sys_regs[SCTLR_EL1],	  sctlr_el1);
 	write_sysreg(ctxt->sys_regs[ACTLR_EL1],	  actlr_el1);
-	write_sysreg(ctxt->sys_regs[CPACR_EL1],	  cpacr_el1);
-	write_sysreg(ctxt->sys_regs[TTBR0_EL1],	  ttbr0_el1);
-	write_sysreg(ctxt->sys_regs[TTBR1_EL1],	  ttbr1_el1);
-	write_sysreg(ctxt->sys_regs[TCR_EL1],	  tcr_el1);
-	write_sysreg(ctxt->sys_regs[ESR_EL1],	  esr_el1);
-	write_sysreg(ctxt->sys_regs[AFSR0_EL1],	  afsr0_el1);
-	write_sysreg(ctxt->sys_regs[AFSR1_EL1],	  afsr1_el1);
-	write_sysreg(ctxt->sys_regs[FAR_EL1],	  far_el1);
-	write_sysreg(ctxt->sys_regs[MAIR_EL1],	  mair_el1);
-	write_sysreg(ctxt->sys_regs[VBAR_EL1],	  vbar_el1);
-	write_sysreg(ctxt->sys_regs[CONTEXTIDR_EL1], contextidr_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],	  tpidr_el1);
-	write_sysreg(ctxt->sys_regs[AMAIR_EL1],	  amair_el1);
-	write_sysreg(ctxt->sys_regs[CNTKCTL_EL1], cntkctl_el1);
-	write_sysreg(ctxt->sys_regs[PAR_EL1],	  par_el1);
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
-
-	write_sysreg(ctxt->gp_regs.regs.sp,	sp_el0);
-	write_sysreg(ctxt->gp_regs.regs.pc,	elr_el2);
-	write_sysreg(ctxt->gp_regs.regs.pstate,	spsr_el2);
-	write_sysreg(ctxt->gp_regs.sp_el1,	sp_el1);
-	write_sysreg(ctxt->gp_regs.elr_el1,	elr_el1);
-	write_sysreg(ctxt->gp_regs.spsr[KVM_SPSR_EL1], spsr_el1);
+	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
+	write_sysreg_el2(ctxt->gp_regs.regs.pc,	  elr);
+	write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
+}
+
+static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
+	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
+	write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	sctlr);
+	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	cpacr);
+	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	ttbr0);
+	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	ttbr1);
+	write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	tcr);
+	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	esr);
+	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	afsr0);
+	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	afsr1);
+	write_sysreg_el1(ctxt->sys_regs[FAR_EL1],	far);
+	write_sysreg_el1(ctxt->sys_regs[MAIR_EL1],	mair);
+	write_sysreg_el1(ctxt->sys_regs[VBAR_EL1],	vbar);
+	write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],contextidr);
+	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	amair);
+	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], 	cntkctl);
+	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
+	write_sysreg(ctxt->sys_regs[MDSCR_EL1],		mdscr_el1);
+
+	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
+	write_sysreg_el1(ctxt->gp_regs.elr_el1,		elr);
+	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr);
+}
+
+static hyp_alternate_select(__sysreg_call_restore_host_state,
+			    __sysreg_restore_state, __sysreg_do_nothing,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+void __hyp_text __sysreg_restore_host_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_call_restore_host_state()(ctxt);
+	__sysreg_restore_common_state(ctxt);
+}
+
+void __hyp_text __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_state(ctxt);
+	__sysreg_restore_common_state(ctxt);
 }
 
 void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 2a7e0d838698..be8177cdd3bf 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -15,7 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
diff --git a/arch/arm64/kvm/hyp/vgic-v2-sr.c b/arch/arm64/kvm/hyp/vgic-v2-sr.c
deleted file mode 100644
index e71761238cfc..000000000000
--- a/arch/arm64/kvm/hyp/vgic-v2-sr.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * Copyright (C) 2012-2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.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 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/compiler.h>
-#include <linux/irqchip/arm-gic.h>
-#include <linux/kvm_host.h>
-
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
-
-/* vcpu is already in the HYP VA space */
-void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
-{
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	struct vgic_dist *vgic = &kvm->arch.vgic;
-	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
-	u32 eisr0, eisr1, elrsr0, elrsr1;
-	int i, nr_lr;
-
-	if (!base)
-		return;
-
-	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
-	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
-	cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
-	eisr0  = readl_relaxed(base + GICH_EISR0);
-	elrsr0 = readl_relaxed(base + GICH_ELRSR0);
-	if (unlikely(nr_lr > 32)) {
-		eisr1  = readl_relaxed(base + GICH_EISR1);
-		elrsr1 = readl_relaxed(base + GICH_ELRSR1);
-	} else {
-		eisr1 = elrsr1 = 0;
-	}
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	cpu_if->vgic_eisr  = ((u64)eisr0 << 32) | eisr1;
-	cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1;
-#else
-	cpu_if->vgic_eisr  = ((u64)eisr1 << 32) | eisr0;
-	cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0;
-#endif
-	cpu_if->vgic_apr    = readl_relaxed(base + GICH_APR);
-
-	writel_relaxed(0, base + GICH_HCR);
-
-	for (i = 0; i < nr_lr; i++)
-		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
-}
-
-/* vcpu is already in the HYP VA space */
-void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
-{
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	struct vgic_dist *vgic = &kvm->arch.vgic;
-	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
-	int i, nr_lr;
-
-	if (!base)
-		return;
-
-	writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
-	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
-	writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
-
-	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
-	for (i = 0; i < nr_lr; i++)
-		writel_relaxed(cpu_if->vgic_lr[i], base + GICH_LR0 + (i * 4));
-}
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 9142e082f5f3..fff7cd42b3a3 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -19,9 +19,7 @@
 #include <linux/irqchip/arm-gic-v3.h>
 #include <linux/kvm_host.h>
 
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 #define vtr_to_max_lr_idx(v)		((v) & 0xf)
 #define vtr_to_nr_pri_bits(v)		(((u32)(v) >> 29) + 1)
@@ -39,12 +37,133 @@
 		asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\
 	} while (0)
 
-/* vcpu is already in the HYP VA space */
+static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
+{
+	switch (lr & 0xf) {
+	case 0:
+		return read_gicreg(ICH_LR0_EL2);
+	case 1:
+		return read_gicreg(ICH_LR1_EL2);
+	case 2:
+		return read_gicreg(ICH_LR2_EL2);
+	case 3:
+		return read_gicreg(ICH_LR3_EL2);
+	case 4:
+		return read_gicreg(ICH_LR4_EL2);
+	case 5:
+		return read_gicreg(ICH_LR5_EL2);
+	case 6:
+		return read_gicreg(ICH_LR6_EL2);
+	case 7:
+		return read_gicreg(ICH_LR7_EL2);
+	case 8:
+		return read_gicreg(ICH_LR8_EL2);
+	case 9:
+		return read_gicreg(ICH_LR9_EL2);
+	case 10:
+		return read_gicreg(ICH_LR10_EL2);
+	case 11:
+		return read_gicreg(ICH_LR11_EL2);
+	case 12:
+		return read_gicreg(ICH_LR12_EL2);
+	case 13:
+		return read_gicreg(ICH_LR13_EL2);
+	case 14:
+		return read_gicreg(ICH_LR14_EL2);
+	case 15:
+		return read_gicreg(ICH_LR15_EL2);
+	}
+
+	unreachable();
+}
+
+static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
+{
+	switch (lr & 0xf) {
+	case 0:
+		write_gicreg(val, ICH_LR0_EL2);
+		break;
+	case 1:
+		write_gicreg(val, ICH_LR1_EL2);
+		break;
+	case 2:
+		write_gicreg(val, ICH_LR2_EL2);
+		break;
+	case 3:
+		write_gicreg(val, ICH_LR3_EL2);
+		break;
+	case 4:
+		write_gicreg(val, ICH_LR4_EL2);
+		break;
+	case 5:
+		write_gicreg(val, ICH_LR5_EL2);
+		break;
+	case 6:
+		write_gicreg(val, ICH_LR6_EL2);
+		break;
+	case 7:
+		write_gicreg(val, ICH_LR7_EL2);
+		break;
+	case 8:
+		write_gicreg(val, ICH_LR8_EL2);
+		break;
+	case 9:
+		write_gicreg(val, ICH_LR9_EL2);
+		break;
+	case 10:
+		write_gicreg(val, ICH_LR10_EL2);
+		break;
+	case 11:
+		write_gicreg(val, ICH_LR11_EL2);
+		break;
+	case 12:
+		write_gicreg(val, ICH_LR12_EL2);
+		break;
+	case 13:
+		write_gicreg(val, ICH_LR13_EL2);
+		break;
+	case 14:
+		write_gicreg(val, ICH_LR14_EL2);
+		break;
+	case 15:
+		write_gicreg(val, ICH_LR15_EL2);
+		break;
+	}
+}
+
+static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu, int nr_lr)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	int i;
+	bool expect_mi;
+
+	expect_mi = !!(cpu_if->vgic_hcr & ICH_HCR_UIE);
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+		expect_mi |= (!(cpu_if->vgic_lr[i] & ICH_LR_HW) &&
+			      (cpu_if->vgic_lr[i] & ICH_LR_EOI));
+	}
+
+	if (expect_mi) {
+		cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
+
+		if (cpu_if->vgic_misr & ICH_MISR_EOI)
+			cpu_if->vgic_eisr = read_gicreg(ICH_EISR_EL2);
+		else
+			cpu_if->vgic_eisr = 0;
+	} else {
+		cpu_if->vgic_misr = 0;
+		cpu_if->vgic_eisr = 0;
+	}
+}
+
 void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u64 val;
-	u32 max_lr_idx, nr_pri_bits;
 
 	/*
 	 * Make sure stores to the GIC via the memory mapped interface
@@ -53,68 +172,66 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 	dsb(st);
 
 	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
-	cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
-	cpu_if->vgic_eisr  = read_gicreg(ICH_EISR_EL2);
-	cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
-	write_gicreg(0, ICH_HCR_EL2);
-	val = read_gicreg(ICH_VTR_EL2);
-	max_lr_idx = vtr_to_max_lr_idx(val);
-	nr_pri_bits = vtr_to_nr_pri_bits(val);
+	if (vcpu->arch.vgic_cpu.live_lrs) {
+		int i;
+		u32 max_lr_idx, nr_pri_bits;
 
-	switch (max_lr_idx) {
-	case 15:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)] = read_gicreg(ICH_LR15_EL2);
-	case 14:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)] = read_gicreg(ICH_LR14_EL2);
-	case 13:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)] = read_gicreg(ICH_LR13_EL2);
-	case 12:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)] = read_gicreg(ICH_LR12_EL2);
-	case 11:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)] = read_gicreg(ICH_LR11_EL2);
-	case 10:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)] = read_gicreg(ICH_LR10_EL2);
-	case 9:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)] = read_gicreg(ICH_LR9_EL2);
-	case 8:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)] = read_gicreg(ICH_LR8_EL2);
-	case 7:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)] = read_gicreg(ICH_LR7_EL2);
-	case 6:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)] = read_gicreg(ICH_LR6_EL2);
-	case 5:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)] = read_gicreg(ICH_LR5_EL2);
-	case 4:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)] = read_gicreg(ICH_LR4_EL2);
-	case 3:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)] = read_gicreg(ICH_LR3_EL2);
-	case 2:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)] = read_gicreg(ICH_LR2_EL2);
-	case 1:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)] = read_gicreg(ICH_LR1_EL2);
-	case 0:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)] = read_gicreg(ICH_LR0_EL2);
-	}
+		cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
-	switch (nr_pri_bits) {
-	case 7:
-		cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
-		cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
-	case 6:
-		cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
-	default:
-		cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
-	}
+		write_gicreg(0, ICH_HCR_EL2);
+		val = read_gicreg(ICH_VTR_EL2);
+		max_lr_idx = vtr_to_max_lr_idx(val);
+		nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	switch (nr_pri_bits) {
-	case 7:
-		cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
-		cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
-	case 6:
-		cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
-	default:
-		cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+		save_maint_int_state(vcpu, max_lr_idx + 1);
+
+		for (i = 0; i <= max_lr_idx; i++) {
+			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+			if (cpu_if->vgic_elrsr & (1 << i)) {
+				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
+				continue;
+			}
+
+			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
+			__gic_v3_set_lr(0, i);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
+			cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
+		case 6:
+			cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
+		default:
+			cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
+			cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
+		case 6:
+			cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
+		default:
+			cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+		}
+
+		vcpu->arch.vgic_cpu.live_lrs = 0;
+	} else {
+		cpu_if->vgic_misr  = 0;
+		cpu_if->vgic_eisr  = 0;
+		cpu_if->vgic_elrsr = 0xffff;
+		cpu_if->vgic_ap0r[0] = 0;
+		cpu_if->vgic_ap0r[1] = 0;
+		cpu_if->vgic_ap0r[2] = 0;
+		cpu_if->vgic_ap0r[3] = 0;
+		cpu_if->vgic_ap1r[0] = 0;
+		cpu_if->vgic_ap1r[1] = 0;
+		cpu_if->vgic_ap1r[2] = 0;
+		cpu_if->vgic_ap1r[3] = 0;
 	}
 
 	val = read_gicreg(ICC_SRE_EL2);
@@ -128,6 +245,8 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u64 val;
 	u32 max_lr_idx, nr_pri_bits;
+	u16 live_lrs = 0;
+	int i;
 
 	/*
 	 * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
@@ -140,66 +259,46 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
 	isb();
 
-	write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
-	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
-
 	val = read_gicreg(ICH_VTR_EL2);
 	max_lr_idx = vtr_to_max_lr_idx(val);
 	nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	switch (nr_pri_bits) {
-	case 7:
-		 write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
-		 write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
-	case 6:
-		 write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
-	default:
-		 write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
-	}	 	                           
-		 	                           
-	switch (nr_pri_bits) {
-	case 7:
-		 write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
-		 write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
-	case 6:
-		 write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
-	default:
-		 write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+	for (i = 0; i <= max_lr_idx; i++) {
+		if (cpu_if->vgic_lr[i] & ICH_LR_STATE)
+			live_lrs |= (1 << i);
 	}
 
-	switch (max_lr_idx) {
-	case 15:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2);
-	case 14:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)], ICH_LR14_EL2);
-	case 13:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)], ICH_LR13_EL2);
-	case 12:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)], ICH_LR12_EL2);
-	case 11:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)], ICH_LR11_EL2);
-	case 10:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)], ICH_LR10_EL2);
-	case 9:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)], ICH_LR9_EL2);
-	case 8:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)], ICH_LR8_EL2);
-	case 7:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)], ICH_LR7_EL2);
-	case 6:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)], ICH_LR6_EL2);
-	case 5:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)], ICH_LR5_EL2);
-	case 4:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)], ICH_LR4_EL2);
-	case 3:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)], ICH_LR3_EL2);
-	case 2:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)], ICH_LR2_EL2);
-	case 1:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)], ICH_LR1_EL2);
-	case 0:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)], ICH_LR0_EL2);
+	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
+
+	if (live_lrs) {
+		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
+
+		switch (nr_pri_bits) {
+		case 7:
+			write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
+			write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
+		case 6:
+			write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
+		default:
+			write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
+			write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
+		case 6:
+			write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
+		default:
+			write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
+		}
+
+		for (i = 0; i <= max_lr_idx; i++) {
+			if (!(live_lrs & (1 << i)))
+				continue;
+
+			__gic_v3_set_lr(cpu_if->vgic_lr[i], i);
+		}
 	}
 
 	/*
@@ -209,6 +308,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 */
 	isb();
 	dsb(sy);
+	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
@@ -220,6 +320,15 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	}
 }
 
+void __hyp_text __vgic_v3_init_lrs(void)
+{
+	int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
+	int i;
+
+	for (i = 0; i <= max_lr_idx; i++)
+		__gic_v3_set_lr(0, i);
+}
+
 static u64 __hyp_text __vgic_v3_read_ich_vtr_el2(void)
 {
 	return read_gicreg(ICH_VTR_EL2);
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f34745cb3d23..9677bf069bcc 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -77,7 +77,11 @@ int kvm_arch_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_GUEST_DEBUG_HW_WPS:
 		r = get_num_wrps();
 		break;
+	case KVM_CAP_ARM_PMU_V3:
+		r = kvm_arm_support_pmu_v3();
+		break;
 	case KVM_CAP_SET_GUEST_DEBUG:
+	case KVM_CAP_VCPU_ATTRIBUTES:
 		r = 1;
 		break;
 	default:
@@ -120,6 +124,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);
 
+	/* Reset PMU */
+	kvm_pmu_vcpu_reset(vcpu);
+
 	/* Reset timer */
 	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 2e90371cfb37..61ba59104845 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -20,6 +20,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bsearch.h>
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
@@ -34,6 +35,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
 #include <asm/kvm_mmu.h>
+#include <asm/perf_event.h>
 
 #include <trace/events/kvm.h>
 
@@ -439,6 +441,344 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
 }
 
+static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	u64 pmcr, val;
+
+	asm volatile("mrs %0, pmcr_el0\n" : "=r" (pmcr));
+	/* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) is reset to UNKNOWN
+	 * except PMCR.E resetting to zero.
+	 */
+	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
+	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
+	vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+}
+
+static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & ARMV8_PMU_USERENR_EN) || vcpu_mode_priv(vcpu));
+}
+
+static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & (ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN))
+		 || vcpu_mode_priv(vcpu));
+}
+
+static bool pmu_access_cycle_counter_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & (ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN))
+		 || vcpu_mode_priv(vcpu));
+}
+
+static bool pmu_access_event_counter_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & (ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN))
+		 || vcpu_mode_priv(vcpu));
+}
+
+static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	u64 val;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write) {
+		/* Only update writeable bits of PMCR */
+		val = vcpu_sys_reg(vcpu, PMCR_EL0);
+		val &= ~ARMV8_PMU_PMCR_MASK;
+		val |= p->regval & ARMV8_PMU_PMCR_MASK;
+		vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+		kvm_pmu_handle_pmcr(vcpu, val);
+	} else {
+		/* PMCR.P & PMCR.C are RAZ */
+		val = vcpu_sys_reg(vcpu, PMCR_EL0)
+		      & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
+		p->regval = val;
+	}
+
+	return true;
+}
+
+static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_event_counter_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write)
+		vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
+	else
+		/* return PMSELR.SEL field */
+		p->regval = vcpu_sys_reg(vcpu, PMSELR_EL0)
+			    & ARMV8_PMU_COUNTER_MASK;
+
+	return true;
+}
+
+static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	u64 pmceid;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	BUG_ON(p->is_write);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (!(p->Op2 & 1))
+		asm volatile("mrs %0, pmceid0_el0\n" : "=r" (pmceid));
+	else
+		asm volatile("mrs %0, pmceid1_el0\n" : "=r" (pmceid));
+
+	p->regval = pmceid;
+
+	return true;
+}
+
+static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
+{
+	u64 pmcr, val;
+
+	pmcr = vcpu_sys_reg(vcpu, PMCR_EL0);
+	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX)
+		return false;
+
+	return true;
+}
+
+static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
+			      struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	u64 idx;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (r->CRn == 9 && r->CRm == 13) {
+		if (r->Op2 == 2) {
+			/* PMXEVCNTR_EL0 */
+			if (pmu_access_event_counter_el0_disabled(vcpu))
+				return false;
+
+			idx = vcpu_sys_reg(vcpu, PMSELR_EL0)
+			      & ARMV8_PMU_COUNTER_MASK;
+		} else if (r->Op2 == 0) {
+			/* PMCCNTR_EL0 */
+			if (pmu_access_cycle_counter_el0_disabled(vcpu))
+				return false;
+
+			idx = ARMV8_PMU_CYCLE_IDX;
+		} else {
+			BUG();
+		}
+	} else if (r->CRn == 14 && (r->CRm & 12) == 8) {
+		/* PMEVCNTRn_EL0 */
+		if (pmu_access_event_counter_el0_disabled(vcpu))
+			return false;
+
+		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
+	} else {
+		BUG();
+	}
+
+	if (!pmu_counter_idx_valid(vcpu, idx))
+		return false;
+
+	if (p->is_write) {
+		if (pmu_access_el0_disabled(vcpu))
+			return false;
+
+		kvm_pmu_set_counter_value(vcpu, idx, p->regval);
+	} else {
+		p->regval = kvm_pmu_get_counter_value(vcpu, idx);
+	}
+
+	return true;
+}
+
+static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			       const struct sys_reg_desc *r)
+{
+	u64 idx, reg;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) {
+		/* PMXEVTYPER_EL0 */
+		idx = vcpu_sys_reg(vcpu, PMSELR_EL0) & ARMV8_PMU_COUNTER_MASK;
+		reg = PMEVTYPER0_EL0 + idx;
+	} else if (r->CRn == 14 && (r->CRm & 12) == 12) {
+		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
+		if (idx == ARMV8_PMU_CYCLE_IDX)
+			reg = PMCCFILTR_EL0;
+		else
+			/* PMEVTYPERn_EL0 */
+			reg = PMEVTYPER0_EL0 + idx;
+	} else {
+		BUG();
+	}
+
+	if (!pmu_counter_idx_valid(vcpu, idx))
+		return false;
+
+	if (p->is_write) {
+		kvm_pmu_set_counter_event_type(vcpu, p->regval, idx);
+		vcpu_sys_reg(vcpu, reg) = p->regval & ARMV8_PMU_EVTYPE_MASK;
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK;
+	}
+
+	return true;
+}
+
+static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 val, mask;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	mask = kvm_pmu_valid_counter_mask(vcpu);
+	if (p->is_write) {
+		val = p->regval & mask;
+		if (r->Op2 & 0x1) {
+			/* accessing PMCNTENSET_EL0 */
+			vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
+			kvm_pmu_enable_counter(vcpu, val);
+		} else {
+			/* accessing PMCNTENCLR_EL0 */
+			vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
+			kvm_pmu_disable_counter(vcpu, val);
+		}
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
+	}
+
+	return true;
+}
+
+static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (!vcpu_mode_priv(vcpu))
+		return false;
+
+	if (p->is_write) {
+		u64 val = p->regval & mask;
+
+		if (r->Op2 & 0x1)
+			/* accessing PMINTENSET_EL1 */
+			vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
+		else
+			/* accessing PMINTENCLR_EL1 */
+			vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMINTENSET_EL1) & mask;
+	}
+
+	return true;
+}
+
+static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write) {
+		if (r->CRm & 0x2)
+			/* accessing PMOVSSET_EL0 */
+			kvm_pmu_overflow_set(vcpu, p->regval & mask);
+		else
+			/* accessing PMOVSCLR_EL0 */
+			vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMOVSSET_EL0) & mask;
+	}
+
+	return true;
+}
+
+static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 mask;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_write_swinc_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write) {
+		mask = kvm_pmu_valid_counter_mask(vcpu);
+		kvm_pmu_software_increment(vcpu, p->regval & mask);
+		return true;
+	}
+
+	return false;
+}
+
+static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (p->is_write) {
+		if (!vcpu_mode_priv(vcpu))
+			return false;
+
+		vcpu_sys_reg(vcpu, PMUSERENR_EL0) = p->regval
+						    & ARMV8_PMU_USERENR_MASK;
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMUSERENR_EL0)
+			    & ARMV8_PMU_USERENR_MASK;
+	}
+
+	return true;
+}
+
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	/* DBGBVRn_EL1 */						\
@@ -454,6 +794,20 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111),	\
 	  trap_wcr, reset_wcr, n, 0,  get_wcr, set_wcr }
 
+/* Macro to expand the PMEVCNTRn_EL0 register */
+#define PMU_PMEVCNTR_EL0(n)						\
+	/* PMEVCNTRn_EL0 */						\
+	{ Op0(0b11), Op1(0b011), CRn(0b1110),				\
+	  CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), }
+
+/* Macro to expand the PMEVTYPERn_EL0 register */
+#define PMU_PMEVTYPER_EL0(n)						\
+	/* PMEVTYPERn_EL0 */						\
+	{ Op0(0b11), Op1(0b011), CRn(0b1110),				\
+	  CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -583,10 +937,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* PMINTENSET_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
-	  trap_raz_wi },
+	  access_pminten, reset_unknown, PMINTENSET_EL1 },
 	/* PMINTENCLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
-	  trap_raz_wi },
+	  access_pminten, NULL, PMINTENSET_EL1 },
 
 	/* MAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
@@ -623,43 +977,46 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* PMCR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
-	  trap_raz_wi },
+	  access_pmcr, reset_pmcr, },
 	/* PMCNTENSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
-	  trap_raz_wi },
+	  access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
 	/* PMCNTENCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
-	  trap_raz_wi },
+	  access_pmcnten, NULL, PMCNTENSET_EL0 },
 	/* PMOVSCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
-	  trap_raz_wi },
+	  access_pmovs, NULL, PMOVSSET_EL0 },
 	/* PMSWINC_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
-	  trap_raz_wi },
+	  access_pmswinc, reset_unknown, PMSWINC_EL0 },
 	/* PMSELR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
-	  trap_raz_wi },
+	  access_pmselr, reset_unknown, PMSELR_EL0 },
 	/* PMCEID0_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
-	  trap_raz_wi },
+	  access_pmceid },
 	/* PMCEID1_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
-	  trap_raz_wi },
+	  access_pmceid },
 	/* PMCCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
-	  trap_raz_wi },
+	  access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
 	/* PMXEVTYPER_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
-	  trap_raz_wi },
+	  access_pmu_evtyper },
 	/* PMXEVCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
-	  trap_raz_wi },
-	/* PMUSERENR_EL0 */
+	  access_pmu_evcntr },
+	/* PMUSERENR_EL0
+	 * This register resets as unknown in 64bit mode while it resets as zero
+	 * in 32bit mode. Here we choose to reset it as zero for consistency.
+	 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
-	  trap_raz_wi },
+	  access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
 	/* PMOVSSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
-	  trap_raz_wi },
+	  access_pmovs, reset_unknown, PMOVSSET_EL0 },
 
 	/* TPIDR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
@@ -668,6 +1025,77 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011),
 	  NULL, reset_unknown, TPIDRRO_EL0 },
 
+	/* PMEVCNTRn_EL0 */
+	PMU_PMEVCNTR_EL0(0),
+	PMU_PMEVCNTR_EL0(1),
+	PMU_PMEVCNTR_EL0(2),
+	PMU_PMEVCNTR_EL0(3),
+	PMU_PMEVCNTR_EL0(4),
+	PMU_PMEVCNTR_EL0(5),
+	PMU_PMEVCNTR_EL0(6),
+	PMU_PMEVCNTR_EL0(7),
+	PMU_PMEVCNTR_EL0(8),
+	PMU_PMEVCNTR_EL0(9),
+	PMU_PMEVCNTR_EL0(10),
+	PMU_PMEVCNTR_EL0(11),
+	PMU_PMEVCNTR_EL0(12),
+	PMU_PMEVCNTR_EL0(13),
+	PMU_PMEVCNTR_EL0(14),
+	PMU_PMEVCNTR_EL0(15),
+	PMU_PMEVCNTR_EL0(16),
+	PMU_PMEVCNTR_EL0(17),
+	PMU_PMEVCNTR_EL0(18),
+	PMU_PMEVCNTR_EL0(19),
+	PMU_PMEVCNTR_EL0(20),
+	PMU_PMEVCNTR_EL0(21),
+	PMU_PMEVCNTR_EL0(22),
+	PMU_PMEVCNTR_EL0(23),
+	PMU_PMEVCNTR_EL0(24),
+	PMU_PMEVCNTR_EL0(25),
+	PMU_PMEVCNTR_EL0(26),
+	PMU_PMEVCNTR_EL0(27),
+	PMU_PMEVCNTR_EL0(28),
+	PMU_PMEVCNTR_EL0(29),
+	PMU_PMEVCNTR_EL0(30),
+	/* PMEVTYPERn_EL0 */
+	PMU_PMEVTYPER_EL0(0),
+	PMU_PMEVTYPER_EL0(1),
+	PMU_PMEVTYPER_EL0(2),
+	PMU_PMEVTYPER_EL0(3),
+	PMU_PMEVTYPER_EL0(4),
+	PMU_PMEVTYPER_EL0(5),
+	PMU_PMEVTYPER_EL0(6),
+	PMU_PMEVTYPER_EL0(7),
+	PMU_PMEVTYPER_EL0(8),
+	PMU_PMEVTYPER_EL0(9),
+	PMU_PMEVTYPER_EL0(10),
+	PMU_PMEVTYPER_EL0(11),
+	PMU_PMEVTYPER_EL0(12),
+	PMU_PMEVTYPER_EL0(13),
+	PMU_PMEVTYPER_EL0(14),
+	PMU_PMEVTYPER_EL0(15),
+	PMU_PMEVTYPER_EL0(16),
+	PMU_PMEVTYPER_EL0(17),
+	PMU_PMEVTYPER_EL0(18),
+	PMU_PMEVTYPER_EL0(19),
+	PMU_PMEVTYPER_EL0(20),
+	PMU_PMEVTYPER_EL0(21),
+	PMU_PMEVTYPER_EL0(22),
+	PMU_PMEVTYPER_EL0(23),
+	PMU_PMEVTYPER_EL0(24),
+	PMU_PMEVTYPER_EL0(25),
+	PMU_PMEVTYPER_EL0(26),
+	PMU_PMEVTYPER_EL0(27),
+	PMU_PMEVTYPER_EL0(28),
+	PMU_PMEVTYPER_EL0(29),
+	PMU_PMEVTYPER_EL0(30),
+	/* PMCCFILTR_EL0
+	 * This register resets as unknown in 64bit mode while it resets as zero
+	 * in 32bit mode. Here we choose to reset it as zero for consistency.
+	 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b1111), Op2(0b111),
+	  access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
+
 	/* DACR32_EL2 */
 	{ Op0(0b11), Op1(0b100), CRn(0b0011), CRm(0b0000), Op2(0b000),
 	  NULL, reset_unknown, DACR32_EL2 },
@@ -857,6 +1285,20 @@ static const struct sys_reg_desc cp14_64_regs[] = {
 	{ Op1( 0), CRm( 2), .access = trap_raz_wi },
 };
 
+/* Macro to expand the PMEVCNTRn register */
+#define PMU_PMEVCNTR(n)							\
+	/* PMEVCNTRn */							\
+	{ Op1(0), CRn(0b1110),						\
+	  CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evcntr }
+
+/* Macro to expand the PMEVTYPERn register */
+#define PMU_PMEVTYPER(n)						\
+	/* PMEVTYPERn */						\
+	{ Op1(0), CRn(0b1110),						\
+	  CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evtyper }
+
 /*
  * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
  * depending on the way they are accessed (as a 32bit or a 64bit
@@ -885,19 +1327,21 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
 
 	/* PMU */
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), access_pmcr },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), access_pmcnten },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), access_pmcnten },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), access_pmovs },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 4), access_pmswinc },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), access_pmselr },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), access_pmu_evcntr },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), access_pmu_evtyper },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), access_pmu_evcntr },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), access_pmuserenr },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), access_pminten },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs },
 
 	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
 	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
@@ -908,10 +1352,78 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },
 
 	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+
+	/* PMEVCNTRn */
+	PMU_PMEVCNTR(0),
+	PMU_PMEVCNTR(1),
+	PMU_PMEVCNTR(2),
+	PMU_PMEVCNTR(3),
+	PMU_PMEVCNTR(4),
+	PMU_PMEVCNTR(5),
+	PMU_PMEVCNTR(6),
+	PMU_PMEVCNTR(7),
+	PMU_PMEVCNTR(8),
+	PMU_PMEVCNTR(9),
+	PMU_PMEVCNTR(10),
+	PMU_PMEVCNTR(11),
+	PMU_PMEVCNTR(12),
+	PMU_PMEVCNTR(13),
+	PMU_PMEVCNTR(14),
+	PMU_PMEVCNTR(15),
+	PMU_PMEVCNTR(16),
+	PMU_PMEVCNTR(17),
+	PMU_PMEVCNTR(18),
+	PMU_PMEVCNTR(19),
+	PMU_PMEVCNTR(20),
+	PMU_PMEVCNTR(21),
+	PMU_PMEVCNTR(22),
+	PMU_PMEVCNTR(23),
+	PMU_PMEVCNTR(24),
+	PMU_PMEVCNTR(25),
+	PMU_PMEVCNTR(26),
+	PMU_PMEVCNTR(27),
+	PMU_PMEVCNTR(28),
+	PMU_PMEVCNTR(29),
+	PMU_PMEVCNTR(30),
+	/* PMEVTYPERn */
+	PMU_PMEVTYPER(0),
+	PMU_PMEVTYPER(1),
+	PMU_PMEVTYPER(2),
+	PMU_PMEVTYPER(3),
+	PMU_PMEVTYPER(4),
+	PMU_PMEVTYPER(5),
+	PMU_PMEVTYPER(6),
+	PMU_PMEVTYPER(7),
+	PMU_PMEVTYPER(8),
+	PMU_PMEVTYPER(9),
+	PMU_PMEVTYPER(10),
+	PMU_PMEVTYPER(11),
+	PMU_PMEVTYPER(12),
+	PMU_PMEVTYPER(13),
+	PMU_PMEVTYPER(14),
+	PMU_PMEVTYPER(15),
+	PMU_PMEVTYPER(16),
+	PMU_PMEVTYPER(17),
+	PMU_PMEVTYPER(18),
+	PMU_PMEVTYPER(19),
+	PMU_PMEVTYPER(20),
+	PMU_PMEVTYPER(21),
+	PMU_PMEVTYPER(22),
+	PMU_PMEVTYPER(23),
+	PMU_PMEVTYPER(24),
+	PMU_PMEVTYPER(25),
+	PMU_PMEVTYPER(26),
+	PMU_PMEVTYPER(27),
+	PMU_PMEVTYPER(28),
+	PMU_PMEVTYPER(29),
+	PMU_PMEVTYPER(30),
+	/* PMCCFILTR */
+	{ Op1(0), CRn(14), CRm(15), Op2(7), access_pmu_evtyper },
 };
 
 static const struct sys_reg_desc cp15_64_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 0), CRm( 9), Op2( 0), access_pmu_evcntr },
 	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
@@ -942,29 +1454,32 @@ static const struct sys_reg_desc *get_target_table(unsigned target,
 	}
 }
 
+#define reg_to_match_value(x)						\
+	({								\
+		unsigned long val;					\
+		val  = (x)->Op0 << 14;					\
+		val |= (x)->Op1 << 11;					\
+		val |= (x)->CRn << 7;					\
+		val |= (x)->CRm << 3;					\
+		val |= (x)->Op2;					\
+		val;							\
+	 })
+
+static int match_sys_reg(const void *key, const void *elt)
+{
+	const unsigned long pval = (unsigned long)key;
+	const struct sys_reg_desc *r = elt;
+
+	return pval - reg_to_match_value(r);
+}
+
 static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
 					 const struct sys_reg_desc table[],
 					 unsigned int num)
 {
-	unsigned int i;
-
-	for (i = 0; i < num; i++) {
-		const struct sys_reg_desc *r = &table[i];
-
-		if (params->Op0 != r->Op0)
-			continue;
-		if (params->Op1 != r->Op1)
-			continue;
-		if (params->CRn != r->CRn)
-			continue;
-		if (params->CRm != r->CRm)
-			continue;
-		if (params->Op2 != r->Op2)
-			continue;
+	unsigned long pval = reg_to_match_value(params);
 
-		return r;
-	}
-	return NULL;
+	return bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg);
 }
 
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S
index 2ca665711bf2..eae38da6e0bb 100644
--- a/arch/arm64/lib/strnlen.S
+++ b/arch/arm64/lib/strnlen.S
@@ -168,4 +168,4 @@ CPU_LE( lsr	tmp2, tmp2, tmp4 )	/* Shift (tmp1 & 63).  */
 .Lhit_limit:
 	mov	len, limit
 	ret
-ENDPROC(strnlen)
+ENDPIPROC(strnlen)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 331c4ca6205c..a6e757cbab77 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void)
 		ret = register_iommu_dma_ops_notifier(&platform_bus_type);
 	if (!ret)
 		ret = register_iommu_dma_ops_notifier(&amba_bustype);
+
+	/* handle devices queued before this arch_initcall */
+	if (!ret)
+		__iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
 	return ret;
 }
 arch_initcall(__iommu_dma_init);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 92ddac1e8ca2..abe2a9542b3a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -371,6 +371,13 @@ static int __kprobes do_translation_fault(unsigned long addr,
 	return 0;
 }
 
+static int do_alignment_fault(unsigned long addr, unsigned int esr,
+			      struct pt_regs *regs)
+{
+	do_bad_area(addr, esr, regs);
+	return 0;
+}
+
 /*
  * This abort handler always returns "fault".
  */
@@ -418,7 +425,7 @@ static struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
-	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
+	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 4c893b5189dd..232f787a088a 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -53,10 +53,10 @@ unsigned long arch_mmap_rnd(void)
 
 #ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT))
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
 	else
 #endif
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 	return rnd << PAGE_SHIFT;
 }
 
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index fc96e814188e..d1fc4796025e 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -108,6 +108,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -266,6 +268,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -366,6 +374,7 @@ CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_HYDRA=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 05c904f08d9d..9bfe8be3658c 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -106,6 +106,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -264,6 +266,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -344,6 +352,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index d572b731c510..ebdcfae55580 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -106,6 +106,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -264,6 +266,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -353,6 +361,7 @@ CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 11a30c65ad44..8acc65e54995 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -104,6 +104,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -262,6 +264,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -343,6 +351,7 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 6630a5154b9d..0c6a3d52b26e 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -106,6 +106,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -264,6 +266,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -345,6 +353,7 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 1d90b71d0903..12a8a6cb32f4 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -105,6 +105,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -266,6 +268,12 @@ CONFIG_DEV_APPLETALK=m
 CONFIG_IPDDP=m
 CONFIG_IPDDP_ENCAP=y
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -362,6 +370,7 @@ CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_MACSONIC=y
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 1fd21c1ca87f..64ff2dcb34c8 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -115,6 +115,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -276,6 +278,12 @@ CONFIG_DEV_APPLETALK=m
 CONFIG_IPDDP=m
 CONFIG_IPDDP_ENCAP=y
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -404,6 +412,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_MACSONIC=y
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_HYDRA=y
 CONFIG_MAC8390=y
 CONFIG_NE2000=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 74e10f79d7b1..07fc6abcfe0c 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -103,6 +103,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -261,6 +263,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -343,6 +351,7 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 7034e716f166..69903ded88f7 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -104,6 +104,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -262,6 +264,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -343,6 +351,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index f7deb5f702a6..bd8401686dde 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -104,6 +104,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -262,6 +264,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -352,6 +360,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 0ce79eb0d805..5f9fb3ab9636 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -101,6 +101,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -259,6 +261,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -340,6 +348,7 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 4cb787e4991f..5d1c674530e2 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -101,6 +101,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -259,6 +261,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -341,6 +349,7 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index f9d96bf86910..bafaff6dcd7b 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		376
+#define NR_syscalls		377
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 36cf129de663..0ca729665f29 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -381,5 +381,6 @@
 #define __NR_userfaultfd	373
 #define __NR_membarrier		374
 #define __NR_mlock2		375
+#define __NR_copy_file_range	376
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 282cd903f4c4..8bb94261ff97 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -396,3 +396,4 @@ ENTRY(sys_call_table)
 	.long sys_userfaultfd
 	.long sys_membarrier
 	.long sys_mlock2		/* 375 */
+	.long sys_copy_file_range
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 57a945e832f4..74a3db92da1b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2085,7 +2085,7 @@ config PAGE_SIZE_32KB
 
 config PAGE_SIZE_64KB
 	bool "64kB"
-	depends on !CPU_R3000 && !CPU_TX39XX
+	depends on !CPU_R3000 && !CPU_TX39XX && !CPU_R6000
 	help
 	  Using 64kB page size will result in higher performance kernel at
 	  the price of higher memory consumption.  This option is available on
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index cefb7a596878..e090fc388e02 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -227,7 +227,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
@@ -258,7 +258,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS64)			\
 		__res = 0;						\
@@ -285,6 +285,11 @@ struct mips_elf_abiflags_v0 {
 
 #endif /* !defined(ELF_ARCH) */
 
+#define mips_elf_check_machine(x) ((x)->e_machine == EM_MIPS)
+
+#define vmcore_elf32_check_arch mips_elf_check_machine
+#define vmcore_elf64_check_arch mips_elf_check_machine
+
 struct mips_abi;
 
 extern struct mips_abi mips_abi;
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 9cbf383b8834..f06f97bd62df 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -179,6 +179,10 @@ static inline void lose_fpu_inatomic(int save, struct task_struct *tsk)
 		if (save)
 			_save_fp(tsk);
 		__disable_fpu();
+	} else {
+		/* FPU should not have been left enabled with no owner */
+		WARN(read_c0_status() & ST0_CU1,
+		     "Orphaned FPU left enabled");
 	}
 	KSTK_STATUS(tsk) &= ~ST0_CU1;
 	clear_tsk_thread_flag(tsk, TIF_USEDFPU);
diff --git a/arch/mips/include/asm/octeon/octeon-feature.h b/arch/mips/include/asm/octeon/octeon-feature.h
index 8ebd3f579b84..3ed10a8d7865 100644
--- a/arch/mips/include/asm/octeon/octeon-feature.h
+++ b/arch/mips/include/asm/octeon/octeon-feature.h
@@ -128,7 +128,8 @@ static inline int octeon_has_feature(enum octeon_feature feature)
 	case OCTEON_FEATURE_PCIE:
 		return OCTEON_IS_MODEL(OCTEON_CN56XX)
 			|| OCTEON_IS_MODEL(OCTEON_CN52XX)
-			|| OCTEON_IS_MODEL(OCTEON_CN6XXX);
+			|| OCTEON_IS_MODEL(OCTEON_CN6XXX)
+			|| OCTEON_IS_MODEL(OCTEON_CN7XXX);
 
 	case OCTEON_FEATURE_SRIO:
 		return OCTEON_IS_MODEL(OCTEON_CN63XX)
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 3f832c3dd8f5..041153f5cf93 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count;
  * User space process size: 2GB. This is hardcoded into a few places,
  * so don't change it unless you know what you are doing.
  */
-#define TASK_SIZE	0x7fff8000UL
+#define TASK_SIZE	0x80000000UL
 #endif
 
 #define STACK_TOP_MAX	TASK_SIZE
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index a71da576883c..eebf39549606 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -289,7 +289,7 @@
 		.set	reorder
 		.set	noat
 		mfc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_IM
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
@@ -330,7 +330,7 @@
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_FR | ST0_IM
 		and	a0, v1
 		LONG_L	v0, PT_STATUS(sp)
 		nor	v1, $0, v1
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6499d93ae68d..47bc45a67e9b 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
 	if ((config_enabled(CONFIG_32BIT) ||
 	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
-	    (regs->regs[2] == __NR_syscall)) {
+	    (regs->regs[2] == __NR_syscall))
 		i++;
-		n++;
-	}
 
 	while (n--)
 		ret |= mips_get_syscall_arg(args++, task, regs, i++);
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 90f03a7da665..3129795de940 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -380,16 +380,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 357)
 #define __NR_membarrier			(__NR_Linux + 358)
 #define __NR_mlock2			(__NR_Linux + 359)
+#define __NR_copy_file_range		(__NR_Linux + 360)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		359
+#define __NR_Linux_syscalls		360
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		359
+#define __NR_O32_Linux_syscalls		360
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -717,16 +718,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 317)
 #define __NR_membarrier			(__NR_Linux + 318)
 #define __NR_mlock2			(__NR_Linux + 319)
+#define __NR_copy_file_range		(__NR_Linux + 320)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		319
+#define __NR_Linux_syscalls		320
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		319
+#define __NR_64_Linux_syscalls		320
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1058,15 +1060,16 @@
 #define __NR_userfaultfd		(__NR_Linux + 321)
 #define __NR_membarrier			(__NR_Linux + 322)
 #define __NR_mlock2			(__NR_Linux + 323)
+#define __NR_copy_file_range		(__NR_Linux + 324)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		323
+#define __NR_Linux_syscalls		324
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		323
+#define __NR_N32_Linux_syscalls		324
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 1188e00bb120..1b992c6e3d8e 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -35,7 +35,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 928767858b86..abd3affe5fb3 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -47,7 +47,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index f2975d4d1e44..eddd5fd6fdfa 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -65,12 +65,10 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
 	status |= KU_USER;
 	regs->cp0_status = status;
+	lose_fpu(0);
+	clear_thread_flag(TIF_MSA_CTX_LIVE);
 	clear_used_math();
-	clear_fpu_owner();
 	init_dsp();
-	clear_thread_flag(TIF_USEDMSA);
-	clear_thread_flag(TIF_MSA_CTX_LIVE);
-	disable_msa();
 	regs->cp0_epc = pc;
 	regs->regs[29] = sp;
 }
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 2d23c834ba96..a56317444bda 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -595,3 +595,4 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index deac63315d0e..2b2dc14610d0 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -433,4 +433,5 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 5320 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 5a69eb48d0a8..2bf5c8593d91 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -423,4 +423,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index e4b6d7c97822..c5b759e584c7 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -578,4 +578,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 569a7d5242dd..5fdaf8bdcd2e 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -782,6 +782,7 @@ static inline void prefill_possible_map(void) {}
 void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
+	mips_cm_probe();
 	prom_init();
 
 	setup_early_fdc_console();
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index bafcb7ad5c85..ae790c575d4f 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -663,7 +663,7 @@ static int simulate_rdhwr_normal(struct pt_regs *regs, unsigned int opcode)
 	return -1;
 }
 
-static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned short opcode)
+static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned int opcode)
 {
 	if ((opcode & MM_POOL32A_FUNC) == MM_RDHWR) {
 		int rd = (opcode & MM_RS) >> 16;
@@ -1119,11 +1119,12 @@ no_r2_instr:
 	if (get_isa16_mode(regs->cp0_epc)) {
 		unsigned short mmop[2] = { 0 };
 
-		if (unlikely(get_user(mmop[0], epc) < 0))
+		if (unlikely(get_user(mmop[0], (u16 __user *)epc + 0) < 0))
 			status = SIGSEGV;
-		if (unlikely(get_user(mmop[1], epc) < 0))
+		if (unlikely(get_user(mmop[1], (u16 __user *)epc + 1) < 0))
 			status = SIGSEGV;
-		opcode = (mmop[0] << 16) | mmop[1];
+		opcode = mmop[0];
+		opcode = (opcode << 16) | mmop[1];
 
 		if (status < 0)
 			status = simulate_rdhwr_mm(regs, opcode);
@@ -1369,26 +1370,12 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 		if (unlikely(compute_return_epc(regs) < 0))
 			break;
 
-		if (get_isa16_mode(regs->cp0_epc)) {
-			unsigned short mmop[2] = { 0 };
-
-			if (unlikely(get_user(mmop[0], epc) < 0))
-				status = SIGSEGV;
-			if (unlikely(get_user(mmop[1], epc) < 0))
-				status = SIGSEGV;
-			opcode = (mmop[0] << 16) | mmop[1];
-
-			if (status < 0)
-				status = simulate_rdhwr_mm(regs, opcode);
-		} else {
+		if (!get_isa16_mode(regs->cp0_epc)) {
 			if (unlikely(get_user(opcode, epc) < 0))
 				status = SIGSEGV;
 
 			if (!cpu_has_llsc && status < 0)
 				status = simulate_llsc(regs, opcode);
-
-			if (status < 0)
-				status = simulate_rdhwr_normal(regs, opcode);
 		}
 
 		if (status < 0)
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 5c81fdd032c3..353037699512 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -146,7 +146,7 @@ unsigned long arch_mmap_rnd(void)
 {
 	unsigned long rnd;
 
-	rnd = (unsigned long)get_random_int();
+	rnd = get_random_long();
 	rnd <<= PAGE_SHIFT;
 	if (TASK_IS_32BIT_ADDR)
 		rnd &= 0xfffffful;
@@ -174,7 +174,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 
 static inline unsigned long brk_rnd(void)
 {
-	unsigned long rnd = get_random_int();
+	unsigned long rnd = get_random_long();
 
 	rnd = rnd << PAGE_SHIFT;
 	/* 8MB for 32bit, 256MB for 64bit */
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 3bd0597d9c3d..249647578e58 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -181,10 +181,6 @@ static int __init mips_sc_probe_cm3(void)
 	return 1;
 }
 
-void __weak platform_early_l2_init(void)
-{
-}
-
 static inline int __init mips_sc_probe(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
@@ -194,12 +190,6 @@ static inline int __init mips_sc_probe(void)
 	/* Mark as not present until probe completed */
 	c->scache.flags |= MIPS_CACHE_NOT_PRESENT;
 
-	/*
-	 * Do we need some platform specific probing before
-	 * we configure L2?
-	 */
-	platform_early_l2_init();
-
 	if (mips_cm_revision() >= CM_REV_CM3)
 		return mips_sc_probe_cm3();
 
diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c
index 571148c5fd0b..dc2c5214809d 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -293,7 +293,6 @@ mips_pci_controller:
 	console_config();
 #endif
 	/* Early detection of CMP support */
-	mips_cm_probe();
 	mips_cpc_probe();
 
 	if (!register_cps_smp_ops())
@@ -304,10 +303,3 @@ mips_pci_controller:
 		return;
 	register_up_smp_ops();
 }
-
-void platform_early_l2_init(void)
-{
-	/* L2 configuration lives in the CM3 */
-	if (mips_cm_revision() >= CM_REV_CM3)
-		mips_cm_probe();
-}
diff --git a/arch/mips/pci/pci-mt7620.c b/arch/mips/pci/pci-mt7620.c
index a009ee458934..1ae932c2d78b 100644
--- a/arch/mips/pci/pci-mt7620.c
+++ b/arch/mips/pci/pci-mt7620.c
@@ -297,12 +297,12 @@ static int mt7620_pci_probe(struct platform_device *pdev)
 		return PTR_ERR(rstpcie0);
 
 	bridge_base = devm_ioremap_resource(&pdev->dev, bridge_res);
-	if (!bridge_base)
-		return -ENOMEM;
+	if (IS_ERR(bridge_base))
+		return PTR_ERR(bridge_base);
 
 	pcie_base = devm_ioremap_resource(&pdev->dev, pcie_res);
-	if (!pcie_base)
-		return -ENOMEM;
+	if (IS_ERR(pcie_base))
+		return PTR_ERR(pcie_base);
 
 	iomem_resource.start = 0;
 	iomem_resource.end = ~0;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e4824fd04bb7..9faa18c4f3f7 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -557,7 +557,7 @@ choice
 
 config PPC_4K_PAGES
 	bool "4k page size"
-	select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
+	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
 
 config PPC_16K_PAGES
 	bool "16k page size"
@@ -566,7 +566,7 @@ config PPC_16K_PAGES
 config PPC_64K_PAGES
 	bool "64k page size"
 	depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64)
-	select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
+	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
 
 config PPC_256K_PAGES
 	bool "256k page size"
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8d1c41d28318..ac07a30a7934 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -281,6 +281,10 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 
+#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+extern void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+				    unsigned long address, pmd_t *pmdp);
+
 #define pmd_move_must_withdraw pmd_move_must_withdraw
 struct spinlock;
 static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index c5eb86f3d452..867c39b45df6 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -81,6 +81,7 @@ struct pci_dn;
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 #define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
 #define EEH_PE_REMOVED		(1 << 10)	/* Removed permanently	*/
+#define EEH_PE_PRI_BUS		(1 << 11)	/* Cached primary bus   */
 
 struct eeh_pe {
 	int type;			/* PE type: PHB/Bus/Device	*/
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index 8e86b48d0369..32e36b16773f 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -57,12 +57,14 @@ DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_exit,
 extern void hcall_tracepoint_regfunc(void);
 extern void hcall_tracepoint_unregfunc(void);
 
-TRACE_EVENT_FN(hcall_entry,
+TRACE_EVENT_FN_COND(hcall_entry,
 
 	TP_PROTO(unsigned long opcode, unsigned long *args),
 
 	TP_ARGS(opcode, args),
 
+	TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(unsigned long, opcode)
 	),
@@ -76,13 +78,15 @@ TRACE_EVENT_FN(hcall_entry,
 	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
 );
 
-TRACE_EVENT_FN(hcall_exit,
+TRACE_EVENT_FN_COND(hcall_exit,
 
 	TP_PROTO(unsigned long opcode, unsigned long retval,
 		unsigned long *retbuf),
 
 	TP_ARGS(opcode, retval, retbuf),
 
+	TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(unsigned long, opcode)
 		__field(unsigned long, retval)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 938742135ee0..650cfb31ea3d 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 		eeh_pcid_put(dev);
 		if (driver->err_handler &&
 		    driver->err_handler->error_detected &&
-		    driver->err_handler->slot_reset &&
-		    driver->err_handler->resume)
+		    driver->err_handler->slot_reset)
 			return NULL;
 	}
 
@@ -564,6 +563,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
 	if (bus) {
+		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(bus);
 		pci_unlock_rescan_remove();
@@ -803,6 +803,7 @@ perm_error:
 	 * the their PCI config any more.
 	 */
 	if (frozen_bus) {
+		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
 		pci_lock_rescan_remove();
@@ -886,6 +887,7 @@ static void eeh_handle_special_event(void)
 					continue;
 
 				/* Notify all devices to be down */
+				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 				bus = eeh_pe_bus_get(phb_pe);
 				eeh_pe_dev_traverse(pe,
 					eeh_report_failure, NULL);
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index ca9e5371930e..98f81800e00c 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -928,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 		bus = pe->phb->bus;
 	} else if (pe->type & EEH_PE_BUS ||
 		   pe->type & EEH_PE_DEVICE) {
-		if (pe->bus) {
+		if (pe->state & EEH_PE_PRI_BUS) {
 			bus = pe->bus;
 			goto out;
 		}
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index ac64ffdb52c8..08b7a40de5f8 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -340,7 +340,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 			if (name[0] == '.') {
 				if (strcmp(name+1, "TOC.") == 0)
 					syms[i].st_shndx = SHN_ABS;
-				memmove(name, name+1, strlen(name));
+				syms[i].st_name++;
 			}
 		}
 	}
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index dccc87e8fee5..3c5736e52a14 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1768,9 +1768,9 @@ static inline unsigned long brk_rnd(void)
 
 	/* 8MB for 32bit, 1GB for 64bit */
 	if (is_32bit_task())
-		rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
+		rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT)));
 	else
-		rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
+		rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT)));
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 0762c1e08c88..edb09912f0c9 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -111,7 +111,13 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 */
 	if (!(old_pte & _PAGE_COMBO)) {
 		flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags);
-		old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND;
+		/*
+		 * clear the old slot details from the old and new pte.
+		 * On hash insert failure we use old pte value and we don't
+		 * want slot information there if we have a insert failure.
+		 */
+		old_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
+		new_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
 		goto htab_insert_hpte;
 	}
 	/*
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 49b152b0f926..eb2accdd76fd 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -78,9 +78,19 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		 * base page size. This is because demote_segment won't flush
 		 * hash page table entries.
 		 */
-		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) {
 			flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
 					    ssize, flags);
+			/*
+			 * With THP, we also clear the slot information with
+			 * respect to all the 64K hash pte mapping the 16MB
+			 * page. They are all invalid now. This make sure we
+			 * don't find the slot valid when we fault with 4k
+			 * base page size.
+			 *
+			 */
+			memset(hpte_slot_array, 0, PTE_FRAG_SIZE);
+		}
 	}
 
 	valid = hpte_valid(hpte_slot_array, index);
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 0f0502e12f6c..4087705ba90f 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -59,9 +59,9 @@ unsigned long arch_mmap_rnd(void)
 
 	/* 8MB for 32bit, 1GB for 64bit */
 	if (is_32bit_task())
-		rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT));
+		rnd = get_random_long() % (1<<(23-PAGE_SHIFT));
 	else
-		rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT));
+		rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT));
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 3124a20d0fab..cdf2123d46db 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -646,6 +646,28 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	return pgtable;
 }
 
+void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+			     unsigned long address, pmd_t *pmdp)
+{
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
+
+	/*
+	 * We can't mark the pmd none here, because that will cause a race
+	 * against exit_mmap. We need to continue mark pmd TRANS HUGE, while
+	 * we spilt, but at the same time we wan't rest of the ppc64 code
+	 * not to insert hash pte on this, because we will be modifying
+	 * the deposited pgtable in the caller of this function. Hence
+	 * clear the _PAGE_USER so that we move the fault handling to
+	 * higher level function and that will serialize against ptl.
+	 * We need to flush existing hash pte entries here even though,
+	 * the translation is still valid, because we will withdraw
+	 * pgtable_t after this.
+	 */
+	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_USER, 0);
+}
+
+
 /*
  * set a new huge pmd. We should not be called for updating
  * an existing pmd entry. That should go via pmd_hugepage_update.
@@ -663,10 +685,20 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
 }
 
+/*
+ * We use this to invalidate a pmdp entry before switching from a
+ * hugepte to regular pmd entry.
+ */
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
 	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+
+	/*
+	 * This ensures that generic code that rely on IRQ disabling
+	 * to prevent a parallel THP split work as expected.
+	 */
+	kick_all_cpus_sync();
 }
 
 /*
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 5f152b95ca0c..87f47e55aab6 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	 * PCI devices of the PE are expected to be removed prior
 	 * to PE reset.
 	 */
-	if (!edev->pe->bus)
+	if (!(edev->pe->state & EEH_PE_PRI_BUS)) {
 		edev->pe->bus = pci_find_bus(hose->global_number,
 					     pdn->busno);
+		if (edev->pe->bus)
+			edev->pe->state |= EEH_PE_PRI_BUS;
+	}
 
 	/*
 	 * Enable EEH explicitly so that we will do EEH check
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 573ae1994097..f90dc04395bf 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3180,6 +3180,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
        .dma_dev_setup = pnv_pci_dma_dev_setup,
+       .dma_bus_setup = pnv_pci_dma_bus_setup,
 #ifdef CONFIG_PCI_MSI
        .setup_msi_irqs = pnv_setup_msi_irqs,
        .teardown_msi_irqs = pnv_teardown_msi_irqs,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 2f55c86df703..b1ef84a6c9d1 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -599,6 +599,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
 	u64 rpn = __pa(uaddr) >> tbl->it_page_shift;
 	long i;
 
+	if (proto_tce & TCE_PCI_WRITE)
+		proto_tce |= TCE_PCI_READ;
+
 	for (i = 0; i < npages; i++) {
 		unsigned long newtce = proto_tce |
 			((rpn + i) << tbl->it_page_shift);
@@ -620,6 +623,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index,
 
 	BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl));
 
+	if (newtce & TCE_PCI_WRITE)
+		newtce |= TCE_PCI_READ;
+
 	oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce));
 	*hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
 	*direction = iommu_tce_direction(oldtce);
@@ -760,6 +766,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		phb->dma_dev_setup(phb, pdev);
 }
 
+void pnv_pci_dma_bus_setup(struct pci_bus *bus)
+{
+	struct pci_controller *hose = bus->sysdata;
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+
+	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+		if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)))
+			continue;
+
+		if (!pe->pbus)
+			continue;
+
+		if (bus->number == ((pe->rid >> 8) & 0xFF)) {
+			pe->pbus = bus;
+			break;
+		}
+	}
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 7f56313e8d72..00691a9b99af 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -242,6 +242,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
 extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
+extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
 extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
 extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
 
diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h
index ea91ddfe54eb..629c90865a07 100644
--- a/arch/s390/include/asm/fpu/internal.h
+++ b/arch/s390/include/asm/fpu/internal.h
@@ -40,6 +40,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs)
 static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
 	fpregs->pad = 0;
+	fpregs->fpc = fpu->fpc;
 	if (MACHINE_HAS_VX)
 		convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
 	else
@@ -49,6 +50,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 
 static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
+	fpu->fpc = fpregs->fpc;
 	if (MACHINE_HAS_VX)
 		convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
 	else
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
index 7aa799134a11..a52b6cca873d 100644
--- a/arch/s390/include/asm/livepatch.h
+++ b/arch/s390/include/asm/livepatch.h
@@ -37,7 +37,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->psw.addr = ip;
 }
 #else
-#error Live patching support is disabled; check CONFIG_LIVEPATCH
+#error Include linux/livepatch.h, not asm/livepatch.h
 #endif
 
 #endif
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 66c94417c0ba..4af60374eba0 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs,
 
 	/* Restore high gprs from signal stack */
 	if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high,
-			     sizeof(&sregs_ext->gprs_high)))
+			     sizeof(sregs_ext->gprs_high)))
 		return -EFAULT;
 	for (i = 0; i < NUM_GPRS; i++)
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index cfcba2dd9bb5..0943b11a2f6e 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -260,12 +260,13 @@ static unsigned long __store_trace(struct perf_callchain_entry *entry,
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			   struct pt_regs *regs)
 {
-	unsigned long head;
+	unsigned long head, frame_size;
 	struct stack_frame *head_sf;
 
 	if (user_mode(regs))
 		return;
 
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
 	head = regs->gprs[15];
 	head_sf = (struct stack_frame *) head;
 
@@ -273,8 +274,9 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 		return;
 
 	head = head_sf->back_chain;
-	head = __store_trace(entry, head, S390_lowcore.async_stack - ASYNC_SIZE,
-			     S390_lowcore.async_stack);
+	head = __store_trace(entry, head,
+			     S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
+			     S390_lowcore.async_stack + frame_size);
 
 	__store_trace(entry, head, S390_lowcore.thread_info,
 		      S390_lowcore.thread_info + THREAD_SIZE);
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 5acba3cb7220..8f64ebd63767 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -59,26 +59,32 @@ static unsigned long save_context_stack(struct stack_trace *trace,
 	}
 }
 
-void save_stack_trace(struct stack_trace *trace)
+static void __save_stack_trace(struct stack_trace *trace, unsigned long sp)
 {
-	register unsigned long sp asm ("15");
-	unsigned long orig_sp, new_sp;
+	unsigned long new_sp, frame_size;
 
-	orig_sp = sp;
-	new_sp = save_context_stack(trace, orig_sp,
-				    S390_lowcore.panic_stack - PAGE_SIZE,
-				    S390_lowcore.panic_stack, 1);
-	if (new_sp != orig_sp)
-		return;
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+	new_sp = save_context_stack(trace, sp,
+			S390_lowcore.panic_stack + frame_size - PAGE_SIZE,
+			S390_lowcore.panic_stack + frame_size, 1);
 	new_sp = save_context_stack(trace, new_sp,
-				    S390_lowcore.async_stack - ASYNC_SIZE,
-				    S390_lowcore.async_stack, 1);
-	if (new_sp != orig_sp)
-		return;
+			S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
+			S390_lowcore.async_stack + frame_size, 1);
 	save_context_stack(trace, new_sp,
 			   S390_lowcore.thread_info,
 			   S390_lowcore.thread_info + THREAD_SIZE, 1);
 }
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	register unsigned long r15 asm ("15");
+	unsigned long sp;
+
+	sp = r15;
+	__save_stack_trace(trace, sp);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
@@ -86,6 +92,10 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	unsigned long sp, low, high;
 
 	sp = tsk->thread.ksp;
+	if (tsk == current) {
+		/* Get current stack pointer. */
+		asm volatile("la %0,0(15)" : "=a" (sp));
+	}
 	low = (unsigned long) task_stack_page(tsk);
 	high = (unsigned long) task_pt_regs(tsk);
 	save_context_stack(trace, sp, low, high, 0);
@@ -93,3 +103,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+	unsigned long sp;
+
+	sp = kernel_stack_pointer(regs);
+	__save_stack_trace(trace, sp);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_regs);
diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c
index 21a5df99552b..dde7654f5c68 100644
--- a/arch/s390/kernel/trace.c
+++ b/arch/s390/kernel/trace.c
@@ -18,6 +18,9 @@ void trace_s390_diagnose_norecursion(int diag_nr)
 	unsigned long flags;
 	unsigned int *depth;
 
+	/* Avoid lockdep recursion. */
+	if (IS_ENABLED(CONFIG_LOCKDEP))
+		return;
 	local_irq_save(flags);
 	depth = this_cpu_ptr(&diagnose_trace_depth);
 	if (*depth == 0) {
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index fec59c067d0d..792f9c63fbca 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -93,15 +93,19 @@ static int __memcpy_real(void *dest, void *src, size_t count)
  */
 int memcpy_real(void *dest, void *src, size_t count)
 {
+	int irqs_disabled, rc;
 	unsigned long flags;
-	int rc;
 
 	if (!count)
 		return 0;
-	local_irq_save(flags);
-	__arch_local_irq_stnsm(0xfbUL);
+	flags = __arch_local_irq_stnsm(0xf8UL);
+	irqs_disabled = arch_irqs_disabled_flags(flags);
+	if (!irqs_disabled)
+		trace_hardirqs_off();
 	rc = __memcpy_real(dest, src, count);
-	local_irq_restore(flags);
+	if (!irqs_disabled)
+		trace_hardirqs_on();
+	__arch_local_irq_ssm(flags);
 	return rc;
 }
 
diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c
index fe0bfe370c45..1884e1759529 100644
--- a/arch/s390/oprofile/backtrace.c
+++ b/arch/s390/oprofile/backtrace.c
@@ -54,12 +54,13 @@ __show_trace(unsigned int *depth, unsigned long sp,
 
 void s390_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
-	unsigned long head;
+	unsigned long head, frame_size;
 	struct stack_frame* head_sf;
 
 	if (user_mode(regs))
 		return;
 
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
 	head = regs->gprs[15];
 	head_sf = (struct stack_frame*)head;
 
@@ -68,8 +69,9 @@ void s390_backtrace(struct pt_regs * const regs, unsigned int depth)
 
 	head = head_sf->back_chain;
 
-	head = __show_trace(&depth, head, S390_lowcore.async_stack - ASYNC_SIZE,
-			    S390_lowcore.async_stack);
+	head = __show_trace(&depth, head,
+			    S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
+			    S390_lowcore.async_stack + frame_size);
 
 	__show_trace(&depth, head, S390_lowcore.thread_info,
 		     S390_lowcore.thread_info + THREAD_SIZE);
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c690c8e16a96..b489e9759518 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -264,7 +264,7 @@ static unsigned long mmap_rnd(void)
 	unsigned long rnd = 0UL;
 
 	if (current->flags & PF_RANDOMIZE) {
-		unsigned long val = get_random_int();
+		unsigned long val = get_random_long();
 		if (test_thread_flag(TIF_32BIT))
 			rnd = (val % (1UL << (23UL-PAGE_SHIFT)));
 		else
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9af2e6338400..c46662f64c39 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -475,6 +475,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
+	depends on EFI
 	depends on X86_X2APIC
 	depends on PCI
 	---help---
@@ -777,8 +778,8 @@ config HPET_TIMER
 	  HPET is the next generation timer replacing legacy 8254s.
 	  The HPET provides a stable time base on SMP
 	  systems, unlike the TSC, but it is more expensive to access,
-	  as it is off-chip.  You can find the HPET spec at
-	  <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>.
+	  as it is off-chip.  The interface used is documented
+	  in the HPET spec, revision 1.
 
 	  You can safely choose Y here.  However, HPET will only be
 	  activated if the platform and the BIOS support this feature.
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 77d8c5112900..bb3e376d0f33 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -294,6 +294,7 @@ sysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
 	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
 	pushfl				/* pt_regs->flags (except IF = 0) */
+	ASM_CLAC			/* Clear AC after saving FLAGS */
 	orl	$X86_EFLAGS_IF, (%esp)	/* Fix IF */
 	pushl	$__USER_CS		/* pt_regs->cs */
 	pushl	$0			/* pt_regs->ip = 0 (placeholder) */
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index ff1c6d61f332..3c990eeee40b 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -261,6 +261,7 @@ ENTRY(entry_INT80_compat)
 	 * Interrupts are off on entry.
 	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	ASM_CLAC			/* Do this early to minimize exposure */
 	SWAPGS
 
 	/*
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 19c099afa861..e795f5274217 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -41,7 +41,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 #else
-#error Live patching support is disabled; check CONFIG_LIVEPATCH
+#error Include linux/livepatch.h, not asm/livepatch.h
 #endif
 
 #endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 46873fbd44e1..d08eacd298c2 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2d5a50cb61a2..20c11d1aa4cc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -766,7 +766,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
  * Return saved PC of a blocked thread.
  * What is this good for? it will be always the scheduler or ret_from_fork.
  */
-#define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
+#define thread_saved_pc(t)	READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index f5dcb5204dcd..3fe0eac59462 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__put_user_size(*(u8 *)from, (u8 __user *)to,
 					1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__put_user_size(*(u16 *)from, (u16 __user *)to,
 					2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__put_user_size(*(u32 *)from, (u32 __user *)to,
 					4, ret, 4);
+			__uaccess_end();
 			return ret;
 		case 8:
+			__uaccess_begin();
 			__put_user_size(*(u64 *)from, (u64 __user *)to,
 					8, ret, 8);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to,
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index 968d57dd54c9..f320ee32d5a1 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -57,7 +57,7 @@ static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
 {
 	if (xen_pci_frontend && xen_pci_frontend->enable_msi)
 		return xen_pci_frontend->enable_msi(dev, vectors);
-	return -ENODEV;
+	return -ENOSYS;
 }
 static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
 {
@@ -69,7 +69,7 @@ static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
 {
 	if (xen_pci_frontend && xen_pci_frontend->enable_msix)
 		return xen_pci_frontend->enable_msix(dev, vectors, nvec);
-	return -ENODEV;
+	return -ENOSYS;
 }
 static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev)
 {
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 49742746a6c9..8836fc9fa84b 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -323,6 +323,8 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 	return 0;
 
 fail:
+	if (amd_uncore_nb)
+		*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
 	kfree(uncore_nb);
 	return -ENOMEM;
 }
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1505587d06e9..b9b09fec173b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 	u16 sel;
 
 	la = seg_base(ctxt, addr.seg) + addr.ea;
-	*linear = la;
 	*max_size = 0;
 	switch (mode) {
 	case X86EMUL_MODE_PROT64:
+		*linear = la;
 		if (is_noncanonical_address(la))
 			goto bad;
 
@@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 			goto bad;
 		break;
 	default:
+		*linear = la = (u32)la;
 		usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL,
 						addr.seg);
 		if (!usable)
@@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 			if (size > *max_size)
 				goto bad;
 		}
-		la &= (u32)-1;
 		break;
 	}
 	if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6013f3685ef4..e159a8185ad9 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -252,7 +252,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 			return ret;
 
 		kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
-		walker->ptes[level] = pte;
+		walker->ptes[level - 1] = pte;
 	}
 	return 0;
 }
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 982ce34f4a9b..27f89c79a44b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
+ * This will force destination out of cache for more performance.
+ *
+ * Note: Cached memory copy is used when destination or size is not
+ * naturally aligned. That is:
+ *  - Require 8-byte alignment when size is 8 bytes or larger.
+ *  - Require 4-byte alignment when size is 4 bytes.
  */
 ENTRY(__copy_user_nocache)
 	ASM_STAC
+
+	/* If size is less than 8 bytes, go to 4-byte copy */
 	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	jb .L_4b_nocache_copy_entry
+
+	/* If destination is not 8-byte aligned, "cache" copy to align it */
 	ALIGN_DESTINATION
+
+	/* Set 4x8-byte copy count and remainder */
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_8b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4x8-byte nocache loop-copy */
+.L_4x8b_nocache_copy_loop:
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
 	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
+	jnz .L_4x8b_nocache_copy_loop
+
+	/* Set 8-byte copy count and remainder */
+.L_8b_nocache_copy_entry:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
+	jz .L_4b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 8-byte nocache loop-copy */
+.L_8b_nocache_copy_loop:
+20:	movq (%rsi),%r8
+21:	movnti %r8,(%rdi)
 	leaq 8(%rsi),%rsi
 	leaq 8(%rdi),%rdi
 	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
+	jnz .L_8b_nocache_copy_loop
+
+	/* If no byte left, we're done */
+.L_4b_nocache_copy_entry:
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* If destination is not 4-byte aligned, go to byte copy: */
+	movl %edi,%ecx
+	andl $3,%ecx
+	jnz .L_1b_cache_copy_entry
+
+	/* Set 4-byte copy count (1 or 0) and remainder */
 	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
+	andl $3,%edx
+	shrl $2,%ecx
+	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4-byte nocache copy: */
+30:	movl (%rsi),%r8d
+31:	movnti %r8d,(%rdi)
+	leaq 4(%rsi),%rsi
+	leaq 4(%rdi),%rdi
+
+	/* If no bytes left, we're done: */
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* Perform byte "cache" loop-copy for the remainder */
+.L_1b_cache_copy_entry:
+	movl %edx,%ecx
+.L_1b_cache_copy_loop:
+40:	movb (%rsi),%al
+41:	movb %al,(%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
+	jnz .L_1b_cache_copy_loop
+
+	/* Finished copying; fence the prior stores */
+.L_finish_copy:
+	xorl %eax,%eax
 	ASM_CLAC
 	sfence
 	ret
 
 	.section .fixup,"ax"
-30:	shll $6,%ecx
+.L_fixup_4x8b_copy:
+	shll $6,%ecx
 	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
+	jmp .L_fixup_handle_tail
+.L_fixup_8b_copy:
+	lea (%rdx,%rcx,8),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_4b_copy:
+	lea (%rdx,%rcx,4),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_1b_copy:
+	movl %ecx,%edx
+.L_fixup_handle_tail:
+	sfence
 	jmp copy_user_handle_tail
 	.previous
 
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
+	_ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(20b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(21b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(30b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(31b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(40b,.L_fixup_1b_copy)
+	_ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index eef44d9a3f77..e830c71a1323 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
+	if (pmd_huge(*pmd_k))
+		return 0;
+
 	pte_k = pte_offset_kernel(pmd_k, address);
 	if (!pte_present(*pte_k))
 		return -1;
@@ -360,8 +363,6 @@ void vmalloc_sync_all(void)
  * 64-bit:
  *
  *   Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
  */
 static noinline int vmalloc_fault(unsigned long address)
 {
@@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud_ref))
 		return -1;
 
-	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
+	if (pud_huge(*pud))
+		return 0;
+
 	pmd = pmd_offset(pud, address);
 	pmd_ref = pmd_offset(pud_ref, address);
 	if (pmd_none(*pmd_ref))
 		return -1;
 
-	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
+	if (pmd_huge(*pmd))
+		return 0;
+
 	pte_ref = pte_offset_kernel(pmd_ref, address);
 	if (!pte_present(*pte_ref))
 		return -1;
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 6d5eb5900372..d8a798d8bf50 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -102,7 +102,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 
-		page = pte_page(pte);
 		if (pte_devmap(pte)) {
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
@@ -115,6 +114,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
 		get_page(page);
 		put_dev_pagemap(pgmap);
 		SetPageReferenced(page);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 96bd1e2bffaf..72bb52f93c3d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -71,12 +71,12 @@ unsigned long arch_mmap_rnd(void)
 
 	if (mmap_is_ia32())
 #ifdef CONFIG_COMPAT
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
 #else
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 #endif
 	else
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b2fd67da1701..ef05755a1900 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
 		break;
 	}
 
-	if (regno > nr_registers) {
+	if (regno >= nr_registers) {
 		WARN_ONCE(1, "decoded an instruction with an invalid register");
 		return -EINVAL;
 	}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f653ed0c..d04f8094bc23 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -469,7 +469,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
 	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
+	phys_addr_t start, end;
 	struct memblock_region *r;
 
 	/*
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 2440814b0069..9cf96d82147a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -419,24 +419,30 @@ pmd_t *lookup_pmd_address(unsigned long address)
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
 	unsigned long virt_addr = (unsigned long)__virt_addr;
-	unsigned long phys_addr, offset;
+	phys_addr_t phys_addr;
+	unsigned long offset;
 	enum pg_level level;
 	pte_t *pte;
 
 	pte = lookup_address(virt_addr, &level);
 	BUG_ON(!pte);
 
+	/*
+	 * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t
+	 * before being left-shifted PAGE_SHIFT bits -- this trick is to
+	 * make 32-PAE kernel work correctly.
+	 */
 	switch (level) {
 	case PG_LEVEL_1G:
-		phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
+		phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
 		offset = virt_addr & ~PUD_PAGE_MASK;
 		break;
 	case PG_LEVEL_2M:
-		phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
+		phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
 		offset = virt_addr & ~PMD_PAGE_MASK;
 		break;
 	default:
-		phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+		phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
 		offset = virt_addr & ~PAGE_MASK;
 	}
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 2879efc73a96..d34b5118b4e8 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -711,28 +711,22 @@ int pcibios_add_device(struct pci_dev *dev)
 	return 0;
 }
 
-int pcibios_alloc_irq(struct pci_dev *dev)
+int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
-	/*
-	 * If the PCI device was already claimed by core code and has
-	 * MSI enabled, probing of the pcibios IRQ will overwrite
-	 * dev->irq.  So bail out if MSI is already enabled.
-	 */
-	if (pci_dev_msi_enabled(dev))
-		return -EBUSY;
+	int err;
 
-	return pcibios_enable_irq(dev);
-}
+	if ((err = pci_enable_resources(dev, mask)) < 0)
+		return err;
 
-void pcibios_free_irq(struct pci_dev *dev)
-{
-	if (pcibios_disable_irq)
-		pcibios_disable_irq(dev);
+	if (!pci_dev_msi_enabled(dev))
+		return pcibios_enable_irq(dev);
+	return 0;
 }
 
-int pcibios_enable_device(struct pci_dev *dev, int mask)
+void pcibios_disable_device (struct pci_dev *dev)
 {
-	return pci_enable_resources(dev, mask);
+	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+		pcibios_disable_irq(dev);
 }
 
 int pci_ext_cfg_avail(void)
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 0d24e7c10145..8b93e634af84 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	int polarity;
 	int ret;
 
-	if (pci_has_managed_irq(dev))
+	if (dev->irq_managed && dev->irq > 0)
 		return 0;
 
 	switch (intel_mid_identify_cpu()) {
@@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (pci_has_managed_irq(dev)) {
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
 		dev->irq_managed = 0;
-		/*
-		 * Don't reset dev->irq here, otherwise
-		 * intel_mid_pci_irq_enable() will fail on next call.
-		 */
 	}
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 32e70343e6fd..9bd115484745 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			struct pci_dev *temp_dev;
 			int irq;
 
-			if (pci_has_managed_irq(dev))
+			if (dev->irq_managed && dev->irq > 0)
 				return 0;
 
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
@@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
-				pci_set_managed_irq(dev, irq);
+				dev->irq_managed = 1;
+				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
 				return 0;
@@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	return 0;
 }
 
+bool mp_should_keep_irq(struct device *dev)
+{
+	if (dev->power.is_prepared)
+		return true;
+#ifdef CONFIG_PM
+	if (dev->power.runtime_status == RPM_SUSPENDING)
+		return true;
+#endif
+
+	return false;
+}
+
 static void pirq_disable_irq(struct pci_dev *dev)
 {
-	if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) {
+	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
-		pci_reset_managed_irq(dev);
+		dev->irq = 0;
+		dev->irq_managed = 0;
 	}
 }
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index ff31ab464213..beac4dfdade6 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -196,7 +196,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	return 0;
 
 error:
-	dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
+	if (ret == -ENOSYS)
+		dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
+	else if (ret)
+		dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret);
 free:
 	kfree(v);
 	return ret;
diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c
index c61b6c332e97..bfadcd0f4944 100644
--- a/arch/x86/platform/intel-quark/imr.c
+++ b/arch/x86/platform/intel-quark/imr.c
@@ -592,14 +592,14 @@ static void __init imr_fixup_memmap(struct imr_device *idev)
 	end = (unsigned long)__end_rodata - 1;
 
 	/*
-	 * Setup a locked IMR around the physical extent of the kernel
+	 * Setup an unlocked IMR around the physical extent of the kernel
 	 * from the beginning of the .text secton to the end of the
 	 * .rodata section as one physically contiguous block.
 	 *
 	 * We don't round up @size since it is already PAGE_SIZE aligned.
 	 * See vmlinux.lds.S for details.
 	 */
-	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true);
+	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false);
 	if (ret < 0) {
 		pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n",
 			size / 1024, start, end);
diff --git a/block/Kconfig b/block/Kconfig
index 161491d0a879..0363cd731320 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_DAX
+	bool "Block device DAX support"
+	depends on FS_DAX
+	depends on BROKEN
+	help
+	  When DAX support is available (CONFIG_FS_DAX) raw block
+	  devices can also support direct userspace access to the
+	  storage capacity via MMAP(2) similar to a file on a
+	  DAX-enabled filesystem.  However, the DAX I/O-path disables
+	  some standard I/O-statistics, and the MMAP(2) path has some
+	  operational differences due to bypassing the page
+	  cache.  If in doubt, say N.
+
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
diff --git a/block/bio.c b/block/bio.c
index dbabd48b1934..cf7591551b17 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -874,7 +874,7 @@ int submit_bio_wait(int rw, struct bio *bio)
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
 	submit_bio(rw, bio);
-	wait_for_completion(&ret.event);
+	wait_for_completion_io(&ret.event);
 
 	return ret.error;
 }
@@ -1090,9 +1090,12 @@ int bio_uncopy_user(struct bio *bio)
 	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
-		 * don't copy into a random user address space, just free.
+		 * don't copy into a random user address space, just free
+		 * and return -EINTR so user space doesn't expect any data.
 		 */
-		if (current->mm && bio_data_dir(bio) == READ)
+		if (!current->mm)
+			ret = -EINTR;
+		else if (bio_data_dir(bio) == READ)
 			ret = bio_copy_to_iter(bio, bmd->iter);
 		if (bmd->is_our_pages)
 			bio_free_pages(bio);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5a37188b559f..66e6f1aae02e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 {
 	struct gendisk *disk;
 	struct blkcg_gq *blkg;
+	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		return -ENODEV;
 	}
 
@@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		ret = PTR_ERR(blkg);
 		rcu_read_unlock();
 		spin_unlock_irq(disk->queue->queue_lock);
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		/*
 		 * If queue was bypassing, we should retry.  Do so after a
 		 * short msleep().  It isn't strictly necessary but queue
@@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
+	struct module *owner;
+
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
+	owner = ctx->disk->fops->owner;
 	put_disk(ctx->disk);
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index ab51685988c2..b83d29755b5a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2455,14 +2455,16 @@ struct request *blk_peek_request(struct request_queue *q)
 
 			rq = NULL;
 			break;
-		} else if (ret == BLKPREP_KILL) {
+		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
+			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
+
 			rq->cmd_flags |= REQ_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
 			 */
 			blk_start_request(rq);
-			__blk_end_request_all(rq, -EIO);
+			__blk_end_request_all(rq, err);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
 			break;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4c0622fae413..56c0a726b619 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -599,8 +599,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		 * If a request wasn't started before the queue was
 		 * marked dying, kill it here or it'll go unnoticed.
 		 */
-		if (unlikely(blk_queue_dying(rq->q)))
-			blk_mq_complete_request(rq, -EIO);
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+		}
 		return;
 	}
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index dd4973583978..c7bb666aafd1 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,8 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors =
-		BLK_SAFE_MAX_SECTORS;
+	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_dev_sectors = 0;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e140cc487ce1..dd93763057ce 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -147,10 +147,9 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
 {
-	unsigned long long val;
 
-	val = q->limits.max_hw_discard_sectors << 9;
-	return sprintf(page, "%llu\n", val);
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index a753df2b3fc2..d0dd7882d8c7 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -39,7 +39,6 @@ struct deadline_data {
 	 */
 	struct request *next_rq[2];
 	unsigned int batching;		/* number of sequential requests made */
-	sector_t last_sector;		/* head position */
 	unsigned int starved;		/* times reads have starved writes */
 
 	/*
@@ -210,8 +209,6 @@ deadline_move_request(struct deadline_data *dd, struct request *rq)
 	dd->next_rq[WRITE] = NULL;
 	dd->next_rq[data_dir] = deadline_latter_request(rq);
 
-	dd->last_sector = rq_end_sector(rq);
-
 	/*
 	 * take it off the sort and fifo list, move
 	 * to dispatch queue
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 38c1aa89d3a0..28556fce4267 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -65,18 +65,10 @@ struct skcipher_async_req {
 	struct skcipher_async_rsgl first_sgl;
 	struct list_head list;
 	struct scatterlist *tsg;
-	char iv[];
+	atomic_t *inflight;
+	struct skcipher_request req;
 };
 
-#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)))
-
-#define GET_REQ_SIZE(ctx) \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))
-
-#define GET_IV_SIZE(ctx) \
-	crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req))
-
 #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
 		      sizeof(struct scatterlist) - 1)
 
@@ -102,15 +94,12 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq)
 
 static void skcipher_async_cb(struct crypto_async_request *req, int err)
 {
-	struct sock *sk = req->data;
-	struct alg_sock *ask = alg_sk(sk);
-	struct skcipher_ctx *ctx = ask->private;
-	struct skcipher_async_req *sreq = GET_SREQ(req, ctx);
+	struct skcipher_async_req *sreq = req->data;
 	struct kiocb *iocb = sreq->iocb;
 
-	atomic_dec(&ctx->inflight);
+	atomic_dec(sreq->inflight);
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
+	kzfree(sreq);
 	iocb->ki_complete(iocb, err, err);
 }
 
@@ -306,8 +295,11 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req);
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	unsigned ivsize = crypto_skcipher_ivsize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct af_alg_control con = {};
@@ -509,37 +501,43 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	struct skcipher_async_req *sreq;
 	struct skcipher_request *req;
 	struct skcipher_async_rsgl *last_rsgl = NULL;
-	unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx);
-	unsigned int reqlen = sizeof(struct skcipher_async_req) +
-				GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx);
+	unsigned int txbufs = 0, len = 0, tx_nents;
+	unsigned int reqsize = crypto_skcipher_reqsize(tfm);
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 	int err = -ENOMEM;
 	bool mark = false;
+	char *iv;
 
-	lock_sock(sk);
-	req = kmalloc(reqlen, GFP_KERNEL);
-	if (unlikely(!req))
-		goto unlock;
+	sreq = kzalloc(sizeof(*sreq) + reqsize + ivsize, GFP_KERNEL);
+	if (unlikely(!sreq))
+		goto out;
 
-	sreq = GET_SREQ(req, ctx);
+	req = &sreq->req;
+	iv = (char *)(req + 1) + reqsize;
 	sreq->iocb = msg->msg_iocb;
-	memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl));
 	INIT_LIST_HEAD(&sreq->list);
+	sreq->inflight = &ctx->inflight;
+
+	lock_sock(sk);
+	tx_nents = skcipher_all_sg_nents(ctx);
 	sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL);
-	if (unlikely(!sreq->tsg)) {
-		kfree(req);
+	if (unlikely(!sreq->tsg))
 		goto unlock;
-	}
 	sg_init_table(sreq->tsg, tx_nents);
-	memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx));
-	skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req));
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-				      skcipher_async_cb, sk);
+	memcpy(iv, ctx->iv, ivsize);
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      skcipher_async_cb, sreq);
 
 	while (iov_iter_count(&msg->msg_iter)) {
 		struct skcipher_async_rsgl *rsgl;
@@ -615,20 +613,22 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg,
 		sg_mark_end(sreq->tsg + txbufs - 1);
 
 	skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg,
-				   len, sreq->iv);
+				   len, iv);
 	err = ctx->enc ? crypto_skcipher_encrypt(req) :
 			 crypto_skcipher_decrypt(req);
 	if (err == -EINPROGRESS) {
 		atomic_inc(&ctx->inflight);
 		err = -EIOCBQUEUED;
+		sreq = NULL;
 		goto unlock;
 	}
 free:
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
 unlock:
 	skcipher_wmem_wakeup(sk);
 	release_sock(sk);
+	kzfree(sreq);
+out:
 	return err;
 }
 
@@ -637,9 +637,12 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm(
-		&ctx->req));
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
+	unsigned bs = crypto_skcipher_blocksize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	int err = -EAGAIN;
@@ -947,7 +950,8 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 	ask->private = ctx;
 
 	skcipher_request_set_tfm(&ctx->req, skcipher);
-	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_SLEEP |
+						 CRYPTO_TFM_REQ_MAY_BACKLOG,
 				      af_alg_complete, &ctx->completion);
 
 	sk->sk_destruct = skcipher_sock_destruct;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 237f3795cfaa..43fe85f20d57 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -499,6 +499,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (link->dump == NULL)
 			return -EINVAL;
 
+		down_read(&crypto_alg_sem);
 		list_for_each_entry(alg, &crypto_alg_list, cra_list)
 			dump_alloc += CRYPTO_REPORT_MAXSIZE;
 
@@ -508,8 +509,11 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				.done = link->done,
 				.min_dump_alloc = dump_alloc,
 			};
-			return netlink_dump_start(crypto_nlsk, skb, nlh, &c);
+			err = netlink_dump_start(crypto_nlsk, skb, nlh, &c);
 		}
+		up_read(&crypto_alg_sem);
+
+		return err;
 	}
 
 	err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX,
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index ad6d8c6b777e..fb53db187854 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -469,37 +469,16 @@ static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc,
 	nfit_mem->bdw = NULL;
 }
 
-static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
+static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa)
 {
 	u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
 	struct nfit_memdev *nfit_memdev;
 	struct nfit_flush *nfit_flush;
-	struct nfit_dcr *nfit_dcr;
 	struct nfit_bdw *nfit_bdw;
 	struct nfit_idt *nfit_idt;
 	u16 idt_idx, range_index;
 
-	list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) {
-		if (nfit_dcr->dcr->region_index != dcr)
-			continue;
-		nfit_mem->dcr = nfit_dcr->dcr;
-		break;
-	}
-
-	if (!nfit_mem->dcr) {
-		dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n",
-				spa->range_index, __to_nfit_memdev(nfit_mem)
-				? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR");
-		return -ENODEV;
-	}
-
-	/*
-	 * We've found enough to create an nvdimm, optionally
-	 * find an associated BDW
-	 */
-	list_add(&nfit_mem->list, &acpi_desc->dimms);
-
 	list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) {
 		if (nfit_bdw->bdw->region_index != dcr)
 			continue;
@@ -508,12 +487,12 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	if (!nfit_mem->bdw)
-		return 0;
+		return;
 
 	nfit_mem_find_spa_bdw(acpi_desc, nfit_mem);
 
 	if (!nfit_mem->spa_bdw)
-		return 0;
+		return;
 
 	range_index = nfit_mem->spa_bdw->range_index;
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
@@ -538,8 +517,6 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
 		}
 		break;
 	}
-
-	return 0;
 }
 
 static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
@@ -548,7 +525,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 	struct nfit_mem *nfit_mem, *found;
 	struct nfit_memdev *nfit_memdev;
 	int type = nfit_spa_type(spa);
-	u16 dcr;
 
 	switch (type) {
 	case NFIT_SPA_DCR:
@@ -559,14 +535,18 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
-		int rc;
+		struct nfit_dcr *nfit_dcr;
+		u32 device_handle;
+		u16 dcr;
 
 		if (nfit_memdev->memdev->range_index != spa->range_index)
 			continue;
 		found = NULL;
 		dcr = nfit_memdev->memdev->region_index;
+		device_handle = nfit_memdev->memdev->device_handle;
 		list_for_each_entry(nfit_mem, &acpi_desc->dimms, list)
-			if (__to_nfit_memdev(nfit_mem)->region_index == dcr) {
+			if (__to_nfit_memdev(nfit_mem)->device_handle
+					== device_handle) {
 				found = nfit_mem;
 				break;
 			}
@@ -579,6 +559,31 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 			if (!nfit_mem)
 				return -ENOMEM;
 			INIT_LIST_HEAD(&nfit_mem->list);
+			list_add(&nfit_mem->list, &acpi_desc->dimms);
+		}
+
+		list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) {
+			if (nfit_dcr->dcr->region_index != dcr)
+				continue;
+			/*
+			 * Record the control region for the dimm.  For
+			 * the ACPI 6.1 case, where there are separate
+			 * control regions for the pmem vs blk
+			 * interfaces, be sure to record the extended
+			 * blk details.
+			 */
+			if (!nfit_mem->dcr)
+				nfit_mem->dcr = nfit_dcr->dcr;
+			else if (nfit_mem->dcr->windows == 0
+					&& nfit_dcr->dcr->windows)
+				nfit_mem->dcr = nfit_dcr->dcr;
+			break;
+		}
+
+		if (dcr && !nfit_mem->dcr) {
+			dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n",
+					spa->range_index, dcr);
+			return -ENODEV;
 		}
 
 		if (type == NFIT_SPA_DCR) {
@@ -595,6 +600,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 				nfit_mem->idt_dcr = nfit_idt->idt;
 				break;
 			}
+			nfit_mem_init_bdw(acpi_desc, nfit_mem, spa);
 		} else {
 			/*
 			 * A single dimm may belong to multiple SPA-PM
@@ -603,13 +609,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 			 */
 			nfit_mem->memdev_pmem = nfit_memdev->memdev;
 		}
-
-		if (found)
-			continue;
-
-		rc = nfit_mem_add(acpi_desc, nfit_mem, spa);
-		if (rc)
-			return rc;
 	}
 
 	return 0;
@@ -1504,9 +1503,7 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc,
 		case 1:
 			/* ARS unsupported, but we should never get here */
 			return 0;
-		case 2:
-			return -EINVAL;
-		case 3:
+		case 6:
 			/* ARS is in progress */
 			msleep(1000);
 			break;
@@ -1517,13 +1514,13 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc,
 }
 
 static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc,
-		struct nd_cmd_ars_status *cmd)
+		struct nd_cmd_ars_status *cmd, u32 size)
 {
 	int rc;
 
 	while (1) {
 		rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd,
-			sizeof(*cmd));
+			size);
 		if (rc || cmd->status & 0xffff)
 			return -ENXIO;
 
@@ -1538,6 +1535,8 @@ static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc,
 		case 2:
 			/* No ARS performed for the current boot */
 			return 0;
+		case 3:
+			/* TODO: error list overflow support */
 		default:
 			return -ENXIO;
 		}
@@ -1581,6 +1580,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc,
 	struct nd_cmd_ars_start *ars_start = NULL;
 	struct nd_cmd_ars_cap *ars_cap = NULL;
 	u64 start, len, cur, remaining;
+	u32 ars_status_size;
 	int rc;
 
 	ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL);
@@ -1610,14 +1610,14 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc,
 	 * Check if a full-range ARS has been run. If so, use those results
 	 * without having to start a new ARS.
 	 */
-	ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status),
-			GFP_KERNEL);
+	ars_status_size = ars_cap->max_ars_out;
+	ars_status = kzalloc(ars_status_size, GFP_KERNEL);
 	if (!ars_status) {
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	rc = ars_get_status(nd_desc, ars_status);
+	rc = ars_get_status(nd_desc, ars_status, ars_status_size);
 	if (rc)
 		goto out;
 
@@ -1647,7 +1647,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc,
 		if (rc)
 			goto out;
 
-		rc = ars_get_status(nd_desc, ars_status);
+		rc = ars_get_status(nd_desc, ars_status, ars_status_size);
 		if (rc)
 			goto out;
 
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index d30184c7f3bc..c8e169e46673 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -406,7 +406,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return 0;
 	}
 
-	if (pci_has_managed_irq(dev))
+	if (dev->irq_managed && dev->irq > 0)
 		return 0;
 
 	entry = acpi_pci_irq_lookup(dev, pin);
@@ -451,7 +451,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		kfree(entry);
 		return rc;
 	}
-	pci_set_managed_irq(dev, rc);
+	dev->irq = rc;
+	dev->irq_managed = 1;
 
 	if (link)
 		snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link);
@@ -474,9 +475,17 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	u8 pin;
 
 	pin = dev->pin;
-	if (!pin || !pci_has_managed_irq(dev))
+	if (!pin || !dev->irq_managed || dev->irq <= 0)
 		return;
 
+	/* Keep IOAPIC pin configuration when suspending */
+	if (dev->dev.power.is_prepared)
+		return;
+#ifdef	CONFIG_PM
+	if (dev->dev.power.runtime_status == RPM_SUSPENDING)
+		return;
+#endif
+
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry)
 		return;
@@ -496,6 +505,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin));
 	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
-		pci_reset_managed_irq(dev);
+		dev->irq_managed = 0;
 	}
 }
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index fa2863567eed..ededa909df2f 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -4,7 +4,6 @@
  *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
  *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
  *  Copyright (C) 2002       Dominik Brodowski <devel@brodo.de>
- *  Copyright (c) 2015, The Linux Foundation. All rights reserved.
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
@@ -438,6 +437,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq)
  * enabled system.
  */
 
+#define ACPI_MAX_IRQS		256
 #define ACPI_MAX_ISA_IRQ	16
 
 #define PIRQ_PENALTY_PCI_AVAILABLE	(0)
@@ -447,7 +447,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq)
 #define PIRQ_PENALTY_ISA_USED		(16*16*16*16*16)
 #define PIRQ_PENALTY_ISA_ALWAYS		(16*16*16*16*16*16)
 
-static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = {
+static int acpi_irq_penalty[ACPI_MAX_IRQS] = {
 	PIRQ_PENALTY_ISA_ALWAYS,	/* IRQ0 timer */
 	PIRQ_PENALTY_ISA_ALWAYS,	/* IRQ1 keyboard */
 	PIRQ_PENALTY_ISA_ALWAYS,	/* IRQ2 cascade */
@@ -464,68 +464,9 @@ static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = {
 	PIRQ_PENALTY_ISA_USED,		/* IRQ13 fpe, sometimes */
 	PIRQ_PENALTY_ISA_USED,		/* IRQ14 ide0 */
 	PIRQ_PENALTY_ISA_USED,		/* IRQ15 ide1 */
+	/* >IRQ15 */
 };
 
-struct irq_penalty_info {
-	int irq;
-	int penalty;
-	struct list_head node;
-};
-
-static LIST_HEAD(acpi_irq_penalty_list);
-
-static int acpi_irq_get_penalty(int irq)
-{
-	struct irq_penalty_info *irq_info;
-
-	if (irq < ACPI_MAX_ISA_IRQ)
-		return acpi_irq_isa_penalty[irq];
-
-	list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) {
-		if (irq_info->irq == irq)
-			return irq_info->penalty;
-	}
-
-	return 0;
-}
-
-static int acpi_irq_set_penalty(int irq, int new_penalty)
-{
-	struct irq_penalty_info *irq_info;
-
-	/* see if this is a ISA IRQ */
-	if (irq < ACPI_MAX_ISA_IRQ) {
-		acpi_irq_isa_penalty[irq] = new_penalty;
-		return 0;
-	}
-
-	/* next, try to locate from the dynamic list */
-	list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) {
-		if (irq_info->irq == irq) {
-			irq_info->penalty  = new_penalty;
-			return 0;
-		}
-	}
-
-	/* nope, let's allocate a slot for this IRQ */
-	irq_info = kzalloc(sizeof(*irq_info), GFP_KERNEL);
-	if (!irq_info)
-		return -ENOMEM;
-
-	irq_info->irq = irq;
-	irq_info->penalty = new_penalty;
-	list_add_tail(&irq_info->node, &acpi_irq_penalty_list);
-
-	return 0;
-}
-
-static void acpi_irq_add_penalty(int irq, int penalty)
-{
-	int curpen = acpi_irq_get_penalty(irq);
-
-	acpi_irq_set_penalty(irq, curpen + penalty);
-}
-
 int __init acpi_irq_penalty_init(void)
 {
 	struct acpi_pci_link *link;
@@ -546,16 +487,15 @@ int __init acpi_irq_penalty_init(void)
 			    link->irq.possible_count;
 
 			for (i = 0; i < link->irq.possible_count; i++) {
-				if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) {
-					int irqpos = link->irq.possible[i];
-
-					acpi_irq_add_penalty(irqpos, penalty);
-				}
+				if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ)
+					acpi_irq_penalty[link->irq.
+							 possible[i]] +=
+					    penalty;
 			}
 
 		} else if (link->irq.active) {
-			acpi_irq_add_penalty(link->irq.active,
-					     PIRQ_PENALTY_PCI_POSSIBLE);
+			acpi_irq_penalty[link->irq.active] +=
+			    PIRQ_PENALTY_PCI_POSSIBLE;
 		}
 	}
 
@@ -607,12 +547,12 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
 		 * the use of IRQs 9, 10, 11, and >15.
 		 */
 		for (i = (link->irq.possible_count - 1); i >= 0; i--) {
-			if (acpi_irq_get_penalty(irq) >
-			    acpi_irq_get_penalty(link->irq.possible[i]))
+			if (acpi_irq_penalty[irq] >
+			    acpi_irq_penalty[link->irq.possible[i]])
 				irq = link->irq.possible[i];
 		}
 	}
-	if (acpi_irq_get_penalty(irq) >= PIRQ_PENALTY_ISA_ALWAYS) {
+	if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) {
 		printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. "
 			    "Try pci=noacpi or acpi=off\n",
 			    acpi_device_name(link->device),
@@ -628,8 +568,7 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
 			    acpi_device_bid(link->device));
 		return -ENODEV;
 	} else {
-		acpi_irq_add_penalty(link->irq.active, PIRQ_PENALTY_PCI_USING);
-
+		acpi_irq_penalty[link->irq.active] += PIRQ_PENALTY_PCI_USING;
 		printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n",
 		       acpi_device_name(link->device),
 		       acpi_device_bid(link->device), link->irq.active);
@@ -839,7 +778,7 @@ static void acpi_pci_link_remove(struct acpi_device *device)
 }
 
 /*
- * modify penalty from cmdline
+ * modify acpi_irq_penalty[] from cmdline
  */
 static int __init acpi_irq_penalty_update(char *str, int used)
 {
@@ -857,10 +796,13 @@ static int __init acpi_irq_penalty_update(char *str, int used)
 		if (irq < 0)
 			continue;
 
+		if (irq >= ARRAY_SIZE(acpi_irq_penalty))
+			continue;
+
 		if (used)
-			acpi_irq_add_penalty(irq, PIRQ_PENALTY_ISA_USED);
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED;
 		else
-			acpi_irq_set_penalty(irq, PIRQ_PENALTY_PCI_AVAILABLE);
+			acpi_irq_penalty[irq] = PIRQ_PENALTY_PCI_AVAILABLE;
 
 		if (retval != 2)	/* no next number */
 			break;
@@ -877,15 +819,18 @@ static int __init acpi_irq_penalty_update(char *str, int used)
  */
 void acpi_penalize_isa_irq(int irq, int active)
 {
-	if (irq >= 0)
-		acpi_irq_add_penalty(irq, active ?
-			PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING);
+	if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) {
+		if (active)
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED;
+		else
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING;
+	}
 }
 
 bool acpi_isa_irq_available(int irq)
 {
-	return irq >= 0 &&
-		(acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS);
+	return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) ||
+			    acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS);
 }
 
 /*
@@ -895,18 +840,13 @@ bool acpi_isa_irq_available(int irq)
  */
 void acpi_penalize_sci_irq(int irq, int trigger, int polarity)
 {
-	int penalty;
-
-	if (irq < 0)
-		return;
-
-	if (trigger != ACPI_MADT_TRIGGER_LEVEL ||
-	    polarity != ACPI_MADT_POLARITY_ACTIVE_LOW)
-		penalty = PIRQ_PENALTY_ISA_ALWAYS;
-	else
-		penalty = PIRQ_PENALTY_PCI_USING;
-
-	acpi_irq_add_penalty(irq, penalty);
+	if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) {
+		if (trigger != ACPI_MADT_TRIGGER_LEVEL ||
+		    polarity != ACPI_MADT_POLARITY_ACTIVE_LOW)
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_ALWAYS;
+		else
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING;
+	}
 }
 
 /*
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index a39e85f9efa9..7d00b7a015ea 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2074,7 +2074,7 @@ static int binder_thread_write(struct binder_proc *proc,
 			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
 				return -EFAULT;
 
-			ptr += sizeof(void *);
+			ptr += sizeof(cookie);
 			list_for_each_entry(w, &proc->delivered_death, entry) {
 				struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work);
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 594fcabd22cd..546a3692774f 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -264,6 +264,26 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index a4faa438889c..a44c75d4c284 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -250,6 +250,7 @@ enum {
 	AHCI_HFLAG_MULTI_MSI		= 0,
 	AHCI_HFLAG_MULTI_MSIX		= 0,
 #endif
+	AHCI_HFLAG_WAKE_BEFORE_STOP	= (1 << 22), /* wake before DMA stop */
 
 	/* ap->flags bits */
 
diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c
index b36cae2fd04b..e87bcec0fd7c 100644
--- a/drivers/ata/ahci_brcmstb.c
+++ b/drivers/ata/ahci_brcmstb.c
@@ -317,6 +317,7 @@ static int brcm_ahci_probe(struct platform_device *pdev)
 	if (IS_ERR(hpriv))
 		return PTR_ERR(hpriv);
 	hpriv->plat_data = priv;
+	hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP;
 
 	brcm_sata_alpm_init(hpriv);
 
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index d61740e78d6d..402967902cbe 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -496,8 +496,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 		}
 	}
 
-	/* fabricate port_map from cap.nr_ports */
-	if (!port_map) {
+	/* fabricate port_map from cap.nr_ports for < AHCI 1.3 */
+	if (!port_map && vers < 0x10300) {
 		port_map = (1 << ahci_nr_ports(cap)) - 1;
 		dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map);
 
@@ -593,8 +593,22 @@ EXPORT_SYMBOL_GPL(ahci_start_engine);
 int ahci_stop_engine(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	u32 tmp;
 
+	/*
+	 * On some controllers, stopping a port's DMA engine while the port
+	 * is in ALPM state (partial or slumber) results in failures on
+	 * subsequent DMA engine starts.  For those controllers, put the
+	 * port back in active state before stopping its DMA engine.
+	 */
+	if ((hpriv->flags & AHCI_HFLAG_WAKE_BEFORE_STOP) &&
+	    (ap->link.lpm_policy > ATA_LPM_MAX_POWER) &&
+	    ahci_set_lpm(&ap->link, ATA_LPM_MAX_POWER, ATA_LPM_WAKE_ONLY)) {
+		dev_err(ap->host->dev, "Failed to wake up port before engine stop\n");
+		return -EIO;
+	}
+
 	tmp = readl(port_mmio + PORT_CMD);
 
 	/* check if the HBA is idle */
@@ -689,6 +703,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 	void __iomem *port_mmio = ahci_port_base(ap);
 
 	if (policy != ATA_LPM_MAX_POWER) {
+		/* wakeup flag only applies to the max power policy */
+		hints &= ~ATA_LPM_WAKE_ONLY;
+
 		/*
 		 * Disable interrupts on Phy Ready. This keeps us from
 		 * getting woken up due to spurious phy ready
@@ -704,7 +721,8 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 		u32 cmd = readl(port_mmio + PORT_CMD);
 
 		if (policy == ATA_LPM_MAX_POWER || !(hints & ATA_LPM_HIPM)) {
-			cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
+			if (!(hints & ATA_LPM_WAKE_ONLY))
+				cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
 			cmd |= PORT_CMD_ICC_ACTIVE;
 
 			writel(cmd, port_mmio + PORT_CMD);
@@ -712,6 +730,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 
 			/* wait 10ms to be sure we've come out of LPM state */
 			ata_msleep(ap, 10);
+
+			if (hints & ATA_LPM_WAKE_ONLY)
+				return 0;
 		} else {
 			cmd |= PORT_CMD_ALPE;
 			if (policy == ATA_LPM_MIN_POWER)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index cbb74719d2c1..55e257c268dd 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4125,6 +4125,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "SAMSUNG CD-ROM SN-124", "N001",	ATA_HORKAGE_NODMA },
 	{ "Seagate STT20000A", NULL,		ATA_HORKAGE_NODMA },
 	{ " 2GB ATA Flash Disk", "ADMA428M",	ATA_HORKAGE_NODMA },
+	{ "VRFDFC22048UCHC-TE*", NULL,		ATA_HORKAGE_NODMA },
 	/* Odd clown on sil3726/4726 PMPs */
 	{ "Config  Disk",	NULL,		ATA_HORKAGE_DISABLE },
 
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index cdf6215a9a22..051b6158d1b7 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -997,12 +997,9 @@ static inline int ata_hsm_ok_in_wq(struct ata_port *ap,
 static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 {
 	struct ata_port *ap = qc->ap;
-	unsigned long flags;
 
 	if (ap->ops->error_handler) {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
-
 			/* EH might have kicked in while host lock is
 			 * released.
 			 */
@@ -1014,8 +1011,6 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 				} else
 					ata_port_freeze(ap);
 			}
-
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else {
 			if (likely(!(qc->err_mask & AC_ERR_HSM)))
 				ata_qc_complete(qc);
@@ -1024,10 +1019,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 		}
 	} else {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
 			ata_sff_irq_on(ap);
 			ata_qc_complete(qc);
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else
 			ata_qc_complete(qc);
 	}
@@ -1048,9 +1041,10 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
 {
 	struct ata_link *link = qc->dev->link;
 	struct ata_eh_info *ehi = &link->eh_info;
-	unsigned long flags = 0;
 	int poll_next;
 
+	lockdep_assert_held(ap->lock);
+
 	WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0);
 
 	/* Make sure ata_sff_qc_issue() does not throw things
@@ -1112,14 +1106,6 @@ fsm_start:
 			}
 		}
 
-		/* Send the CDB (atapi) or the first data block (ata pio out).
-		 * During the state transition, interrupt handler shouldn't
-		 * be invoked before the data transfer is complete and
-		 * hsm_task_state is changed. Hence, the following locking.
-		 */
-		if (in_wq)
-			spin_lock_irqsave(ap->lock, flags);
-
 		if (qc->tf.protocol == ATA_PROT_PIO) {
 			/* PIO data out protocol.
 			 * send first data block.
@@ -1135,9 +1121,6 @@ fsm_start:
 			/* send CDB */
 			atapi_send_cdb(ap, qc);
 
-		if (in_wq)
-			spin_unlock_irqrestore(ap->lock, flags);
-
 		/* if polling, ata_sff_pio_task() handles the rest.
 		 * otherwise, interrupt handler takes over from here.
 		 */
@@ -1296,7 +1279,8 @@ fsm_start:
 		break;
 	default:
 		poll_next = 0;
-		BUG();
+		WARN(true, "ata%d: SFF host state machine in invalid state %d",
+		     ap->print_id, ap->hsm_task_state);
 	}
 
 	return poll_next;
@@ -1361,12 +1345,14 @@ static void ata_sff_pio_task(struct work_struct *work)
 	u8 status;
 	int poll_next;
 
+	spin_lock_irq(ap->lock);
+
 	BUG_ON(ap->sff_pio_task_link == NULL);
 	/* qc can be NULL if timeout occurred */
 	qc = ata_qc_from_tag(ap, link->active_tag);
 	if (!qc) {
 		ap->sff_pio_task_link = NULL;
-		return;
+		goto out_unlock;
 	}
 
 fsm_start:
@@ -1381,11 +1367,14 @@ fsm_start:
 	 */
 	status = ata_sff_busy_wait(ap, ATA_BUSY, 5);
 	if (status & ATA_BUSY) {
+		spin_unlock_irq(ap->lock);
 		ata_msleep(ap, 2);
+		spin_lock_irq(ap->lock);
+
 		status = ata_sff_busy_wait(ap, ATA_BUSY, 10);
 		if (status & ATA_BUSY) {
 			ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE);
-			return;
+			goto out_unlock;
 		}
 	}
 
@@ -1402,6 +1391,8 @@ fsm_start:
 	 */
 	if (poll_next)
 		goto fsm_start;
+out_unlock:
+	spin_unlock_irq(ap->lock);
 }
 
 /**
diff --git a/drivers/base/component.c b/drivers/base/component.c
index 89f5cf68d80a..04a1582e80bb 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -206,6 +206,8 @@ static void component_match_release(struct device *master,
 		if (mc->release)
 			mc->release(master, mc->data);
 	}
+
+	kfree(match->compare);
 }
 
 static void devm_component_match_release(struct device *dev, void *res)
@@ -221,14 +223,14 @@ static int component_match_realloc(struct device *dev,
 	if (match->alloc == num)
 		return 0;
 
-	new = devm_kmalloc_array(dev, num, sizeof(*new), GFP_KERNEL);
+	new = kmalloc_array(num, sizeof(*new), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
 	if (match->compare) {
 		memcpy(new, match->compare, sizeof(*new) *
 					    min(match->num, num));
-		devm_kfree(dev, match->compare);
+		kfree(match->compare);
 	}
 	match->compare = new;
 	match->alloc = num;
@@ -283,6 +285,24 @@ void component_match_add_release(struct device *master,
 }
 EXPORT_SYMBOL(component_match_add_release);
 
+static void free_master(struct master *master)
+{
+	struct component_match *match = master->match;
+	int i;
+
+	list_del(&master->node);
+
+	if (match) {
+		for (i = 0; i < match->num; i++) {
+			struct component *c = match->compare[i].component;
+			if (c)
+				c->master = NULL;
+		}
+	}
+
+	kfree(master);
+}
+
 int component_master_add_with_match(struct device *dev,
 	const struct component_master_ops *ops,
 	struct component_match *match)
@@ -309,11 +329,9 @@ int component_master_add_with_match(struct device *dev,
 
 	ret = try_to_bring_up_master(master, NULL);
 
-	if (ret < 0) {
-		/* Delete off the list if we weren't successful */
-		list_del(&master->node);
-		kfree(master);
-	}
+	if (ret < 0)
+		free_master(master);
+
 	mutex_unlock(&component_mutex);
 
 	return ret < 0 ? ret : 0;
@@ -324,25 +342,12 @@ void component_master_del(struct device *dev,
 	const struct component_master_ops *ops)
 {
 	struct master *master;
-	int i;
 
 	mutex_lock(&component_mutex);
 	master = __master_find(dev, ops);
 	if (master) {
-		struct component_match *match = master->match;
-
 		take_down_master(master);
-
-		list_del(&master->node);
-
-		if (match) {
-			for (i = 0; i < match->num; i++) {
-				struct component *c = match->compare[i].component;
-				if (c)
-					c->master = NULL;
-			}
-		}
-		kfree(master);
+		free_master(master);
 	}
 	mutex_unlock(&component_mutex);
 }
@@ -486,6 +491,8 @@ int component_add(struct device *dev, const struct component_ops *ops)
 
 	ret = try_to_bring_up_masters(component);
 	if (ret < 0) {
+		if (component->master)
+			remove_component(component->master, component);
 		list_del(&component->node);
 
 		kfree(component);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 9e251201dd48..84708a5f8c52 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -866,7 +866,7 @@ static void set_fdc(int drive)
 }
 
 /* locks the driver */
-static int lock_fdc(int drive, bool interruptible)
+static int lock_fdc(int drive)
 {
 	if (WARN(atomic_read(&usage_count) == 0,
 		 "Trying to lock fdc while usage count=0\n"))
@@ -2173,7 +2173,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req)
 {
 	int ret;
 
-	if (lock_fdc(drive, true))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	set_floppy(drive);
@@ -2960,7 +2960,7 @@ static int user_reset_fdc(int drive, int arg, bool interruptible)
 {
 	int ret;
 
-	if (lock_fdc(drive, interruptible))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	if (arg == FD_RESET_ALWAYS)
@@ -3243,7 +3243,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		mutex_lock(&open_lock);
-		if (lock_fdc(drive, true)) {
+		if (lock_fdc(drive)) {
 			mutex_unlock(&open_lock);
 			return -EINTR;
 		}
@@ -3263,7 +3263,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 	} else {
 		int oldStretch;
 
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (cmd != FDDEFPRM) {
 			/* notice a disk change immediately, else
@@ -3349,7 +3349,7 @@ static int get_floppy_geometry(int drive, int type, struct floppy_struct **g)
 	if (type)
 		*g = &floppy_type[type];
 	else {
-		if (lock_fdc(drive, false))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(false, 0) == -EINTR)
 			return -EINTR;
@@ -3433,7 +3433,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		if (UDRS->fd_ref != 1)
 			/* somebody else has this drive open */
 			return -EBUSY;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 
 		/* do the actual eject. Fails on
@@ -3445,7 +3445,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return ret;
 	case FDCLRPRM:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		current_type[drive] = NULL;
 		floppy_sizes[drive] = MAX_DISK_SIZE << 1;
@@ -3467,7 +3467,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		UDP->flags &= ~FTD_MSG;
 		return 0;
 	case FDFMTBEG:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3484,7 +3484,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		return do_format(drive, &inparam.f);
 	case FDFMTEND:
 	case FDFLUSH:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		return invalidate_drive(bdev);
 	case FDSETEMSGTRESH:
@@ -3507,7 +3507,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		outparam = UDP;
 		break;
 	case FDPOLLDRVSTAT:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3530,7 +3530,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 	case FDRAWCMD:
 		if (type)
 			return -EINVAL;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		set_floppy(drive);
 		i = raw_cmd_ioctl(cmd, (void __user *)param);
@@ -3539,7 +3539,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return i;
 	case FDTWADDLE:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		twaddle();
 		process_fd_request();
@@ -3663,6 +3663,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 
 	opened_bdev[drive] = bdev;
 
+	if (!(mode & (FMODE_READ|FMODE_WRITE))) {
+		res = -EINVAL;
+		goto out;
+	}
+
 	res = -ENXIO;
 
 	if (!floppy_track_buffer) {
@@ -3706,21 +3711,20 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	if (UFDCS->rawcmd == 1)
 		UFDCS->rawcmd = 2;
 
-	if (!(mode & FMODE_NDELAY)) {
-		if (mode & (FMODE_READ|FMODE_WRITE)) {
-			UDRS->last_checked = 0;
-			clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
-			check_disk_change(bdev);
-			if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
-				goto out;
-			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
-				goto out;
-		}
-		res = -EROFS;
-		if ((mode & FMODE_WRITE) &&
-		    !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
-			goto out;
-	}
+	UDRS->last_checked = 0;
+	clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+	check_disk_change(bdev);
+	if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+		goto out;
+	if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+		goto out;
+
+	res = -EROFS;
+
+	if ((mode & FMODE_WRITE) &&
+			!test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
+		goto out;
+
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 	return 0;
@@ -3748,7 +3752,8 @@ static unsigned int floppy_check_events(struct gendisk *disk,
 		return DISK_EVENT_MEDIA_CHANGE;
 
 	if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) {
-		lock_fdc(drive, false);
+		if (lock_fdc(drive))
+			return -EINTR;
 		poll_drive(false, 0);
 		process_fd_request();
 	}
@@ -3847,7 +3852,9 @@ static int floppy_revalidate(struct gendisk *disk)
 			 "VFS: revalidate called on non-open device.\n"))
 			return -EFAULT;
 
-		lock_fdc(drive, false);
+		res = lock_fdc(drive);
+		if (res)
+			return res;
 		cf = (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
 		      test_bit(FD_VERIFY_BIT, &UDRS->flags));
 		if (!(cf || test_bit(drive, &fake_change) || drive_no_geom(drive))) {
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 8ba1e97d573c..64a7b5971b57 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -478,7 +478,7 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
 	id->ver_id = 0x1;
 	id->vmnt = 0;
 	id->cgrps = 1;
-	id->cap = 0x3;
+	id->cap = 0x2;
 	id->dom = 0x1;
 
 	id->ppaf.blk_offset = 0;
@@ -707,9 +707,7 @@ static int null_add_dev(void)
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
-
 	mutex_lock(&lock);
-	list_add_tail(&nullb->list, &nullb_list);
 	nullb->index = nullb_indexes++;
 	mutex_unlock(&lock);
 
@@ -743,6 +741,10 @@ static int null_add_dev(void)
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
 
 	add_disk(disk);
+
+	mutex_lock(&lock);
+	list_add_tail(&nullb->list, &nullb_list);
+	mutex_unlock(&lock);
 done:
 	return 0;
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8a8dc91c39f7..83eb9e6bf8b0 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1873,6 +1873,43 @@ again:
 	return err;
 }
 
+static int negotiate_mq(struct blkfront_info *info)
+{
+	unsigned int backend_max_queues = 0;
+	int err;
+	unsigned int i;
+
+	BUG_ON(info->nr_rings);
+
+	/* Check if backend supports multiple queues. */
+	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+			   "multi-queue-max-queues", "%u", &backend_max_queues);
+	if (err < 0)
+		backend_max_queues = 1;
+
+	info->nr_rings = min(backend_max_queues, xen_blkif_max_queues);
+	/* We need at least one ring. */
+	if (!info->nr_rings)
+		info->nr_rings = 1;
+
+	info->rinfo = kzalloc(sizeof(struct blkfront_ring_info) * info->nr_rings, GFP_KERNEL);
+	if (!info->rinfo) {
+		xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < info->nr_rings; i++) {
+		struct blkfront_ring_info *rinfo;
+
+		rinfo = &info->rinfo[i];
+		INIT_LIST_HEAD(&rinfo->indirect_pages);
+		INIT_LIST_HEAD(&rinfo->grants);
+		rinfo->dev_info = info;
+		INIT_WORK(&rinfo->work, blkif_restart_queue);
+		spin_lock_init(&rinfo->ring_lock);
+	}
+	return 0;
+}
 /**
  * Entry point to this code when a new device is created.  Allocate the basic
  * structures and the ring buffer for communication with the backend, and
@@ -1883,9 +1920,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 			  const struct xenbus_device_id *id)
 {
 	int err, vdevice;
-	unsigned int r_index;
 	struct blkfront_info *info;
-	unsigned int backend_max_queues = 0;
 
 	/* FIXME: Use dynamic device id if this is not set. */
 	err = xenbus_scanf(XBT_NIL, dev->nodename,
@@ -1936,33 +1971,10 @@ static int blkfront_probe(struct xenbus_device *dev,
 	}
 
 	info->xbdev = dev;
-	/* Check if backend supports multiple queues. */
-	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
-			   "multi-queue-max-queues", "%u", &backend_max_queues);
-	if (err < 0)
-		backend_max_queues = 1;
-
-	info->nr_rings = min(backend_max_queues, xen_blkif_max_queues);
-	/* We need at least one ring. */
-	if (!info->nr_rings)
-		info->nr_rings = 1;
-
-	info->rinfo = kzalloc(sizeof(struct blkfront_ring_info) * info->nr_rings, GFP_KERNEL);
-	if (!info->rinfo) {
-		xenbus_dev_fatal(dev, -ENOMEM, "allocating ring_info structure");
+	err = negotiate_mq(info);
+	if (err) {
 		kfree(info);
-		return -ENOMEM;
-	}
-
-	for (r_index = 0; r_index < info->nr_rings; r_index++) {
-		struct blkfront_ring_info *rinfo;
-
-		rinfo = &info->rinfo[r_index];
-		INIT_LIST_HEAD(&rinfo->indirect_pages);
-		INIT_LIST_HEAD(&rinfo->grants);
-		rinfo->dev_info = info;
-		INIT_WORK(&rinfo->work, blkif_restart_queue);
-		spin_lock_init(&rinfo->ring_lock);
+		return err;
 	}
 
 	mutex_init(&info->mutex);
@@ -2123,12 +2135,16 @@ static int blkif_recover(struct blkfront_info *info)
 static int blkfront_resume(struct xenbus_device *dev)
 {
 	struct blkfront_info *info = dev_get_drvdata(&dev->dev);
-	int err;
+	int err = 0;
 
 	dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);
 
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
+	err = negotiate_mq(info);
+	if (err)
+		return err;
+
 	err = talk_to_blkback(dev, info);
 
 	/*
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 240b6cf1d97c..be54e5331a45 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -42,7 +42,7 @@
 /*
  * The High Precision Event Timer driver.
  * This driver is closely modelled after the rtc.c driver.
- * http://www.intel.com/hardwaredesign/hpetspec_1.pdf
+ * See HPET spec revision 1.
  */
 #define	HPET_USER_FREQ	(64)
 #define	HPET_DRIFT	(500)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d0da5d852d41..b583e5336630 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1819,6 +1819,28 @@ unsigned int get_random_int(void)
 EXPORT_SYMBOL(get_random_int);
 
 /*
+ * Same as get_random_int(), but returns unsigned long.
+ */
+unsigned long get_random_long(void)
+{
+	__u32 *hash;
+	unsigned long ret;
+
+	if (arch_get_random_long(&ret))
+		return ret;
+
+	hash = get_cpu_var(get_random_int_hash);
+
+	hash[0] += current->pid + jiffies + random_get_entropy();
+	md5_transform(hash, random_int_secret);
+	ret = *(unsigned long *)hash;
+	put_cpu_var(get_random_int_hash);
+
+	return ret;
+}
+EXPORT_SYMBOL(get_random_long);
+
+/*
  * randomize_range() returns a start address such that
  *
  *    [...... <range> .....]
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index b038e3666058..bae4be6501df 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -43,7 +43,7 @@ obj-$(CONFIG_COMMON_CLK_SI514)		+= clk-si514.o
 obj-$(CONFIG_COMMON_CLK_SI570)		+= clk-si570.o
 obj-$(CONFIG_COMMON_CLK_CDCE925)	+= clk-cdce925.o
 obj-$(CONFIG_ARCH_STM32)		+= clk-stm32f4.o
-obj-$(CONFIG_ARCH_TANGOX)		+= clk-tango4.o
+obj-$(CONFIG_ARCH_TANGO)		+= clk-tango4.o
 obj-$(CONFIG_CLK_TWL6040)		+= clk-twl6040.o
 obj-$(CONFIG_ARCH_U300)			+= clk-u300.o
 obj-$(CONFIG_ARCH_VT8500)		+= clk-vt8500.o
diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c
index 19fed65587e8..7b09a265d79f 100644
--- a/drivers/clk/clk-gpio.c
+++ b/drivers/clk/clk-gpio.c
@@ -289,7 +289,7 @@ static void __init of_gpio_clk_setup(struct device_node *node,
 
 	num_parents = of_clk_get_parent_count(node);
 	if (num_parents < 0)
-		return;
+		num_parents = 0;
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c
index cd0f2726f5e0..89e9ca78bb94 100644
--- a/drivers/clk/clk-scpi.c
+++ b/drivers/clk/clk-scpi.c
@@ -299,7 +299,7 @@ static int scpi_clocks_probe(struct platform_device *pdev)
 	/* Add the virtual cpufreq device */
 	cpufreq_dev = platform_device_register_simple("scpi-cpufreq",
 						      -1, NULL, 0);
-	if (!cpufreq_dev)
+	if (IS_ERR(cpufreq_dev))
 		pr_warn("unable to register cpufreq device");
 
 	return 0;
diff --git a/drivers/clk/mvebu/dove-divider.c b/drivers/clk/mvebu/dove-divider.c
index d5c5bfa35a5a..3e0b52daa35f 100644
--- a/drivers/clk/mvebu/dove-divider.c
+++ b/drivers/clk/mvebu/dove-divider.c
@@ -247,7 +247,7 @@ static struct clk_onecell_data dove_divider_data = {
 
 void __init dove_divider_clk_init(struct device_node *np)
 {
-	void *base;
+	void __iomem *base;
 
 	base = of_iomap(np, 0);
 	if (WARN_ON(!base))
diff --git a/drivers/clk/qcom/gcc-apq8084.c b/drivers/clk/qcom/gcc-apq8084.c
index cf73e539e9f6..070037a29ea5 100644
--- a/drivers/clk/qcom/gcc-apq8084.c
+++ b/drivers/clk/qcom/gcc-apq8084.c
@@ -3587,7 +3587,6 @@ static const struct regmap_config gcc_apq8084_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x1fc0,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_apq8084_desc = {
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index b692ae881d6a..dd5402bac620 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -3005,7 +3005,6 @@ static const struct regmap_config gcc_ipq806x_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x3e40,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_ipq806x_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c
index f6a2b14dfec4..ad413036f7c7 100644
--- a/drivers/clk/qcom/gcc-msm8660.c
+++ b/drivers/clk/qcom/gcc-msm8660.c
@@ -2702,7 +2702,6 @@ static const struct regmap_config gcc_msm8660_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x363c,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8660_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index e3bf09d7d0ef..8cc9b2868b41 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -3336,7 +3336,6 @@ static const struct regmap_config gcc_msm8916_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x80000,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8916_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index f31111e32d44..983dd7dc89a7 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -3468,7 +3468,6 @@ static const struct regmap_config gcc_msm8960_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x3660,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct regmap_config gcc_apq8064_regmap_config = {
@@ -3477,7 +3476,6 @@ static const struct regmap_config gcc_apq8064_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x3880,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8960_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8974.c b/drivers/clk/qcom/gcc-msm8974.c
index df164d618e34..335952db309b 100644
--- a/drivers/clk/qcom/gcc-msm8974.c
+++ b/drivers/clk/qcom/gcc-msm8974.c
@@ -2680,7 +2680,6 @@ static const struct regmap_config gcc_msm8974_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x1fc0,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8974_desc = {
diff --git a/drivers/clk/qcom/lcc-ipq806x.c b/drivers/clk/qcom/lcc-ipq806x.c
index 62e79fadd5f7..db3998e5e2d8 100644
--- a/drivers/clk/qcom/lcc-ipq806x.c
+++ b/drivers/clk/qcom/lcc-ipq806x.c
@@ -419,7 +419,6 @@ static const struct regmap_config lcc_ipq806x_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0xfc,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc lcc_ipq806x_desc = {
diff --git a/drivers/clk/qcom/lcc-msm8960.c b/drivers/clk/qcom/lcc-msm8960.c
index bf95bb0ea1b8..4fcf9d1d233c 100644
--- a/drivers/clk/qcom/lcc-msm8960.c
+++ b/drivers/clk/qcom/lcc-msm8960.c
@@ -524,7 +524,6 @@ static const struct regmap_config lcc_msm8960_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0xfc,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc lcc_msm8960_desc = {
diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c
index 1e703fda8a0f..30777f9f1a43 100644
--- a/drivers/clk/qcom/mmcc-apq8084.c
+++ b/drivers/clk/qcom/mmcc-apq8084.c
@@ -3368,7 +3368,6 @@ static const struct regmap_config mmcc_apq8084_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x5104,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc mmcc_apq8084_desc = {
diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c
index d73a048d3b9d..00e36192a1de 100644
--- a/drivers/clk/qcom/mmcc-msm8960.c
+++ b/drivers/clk/qcom/mmcc-msm8960.c
@@ -3029,7 +3029,6 @@ static const struct regmap_config mmcc_msm8960_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x334,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct regmap_config mmcc_apq8064_regmap_config = {
@@ -3038,7 +3037,6 @@ static const struct regmap_config mmcc_apq8064_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x350,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc mmcc_msm8960_desc = {
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index bbe28ed93669..9d790bcadf25 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -2594,7 +2594,6 @@ static const struct regmap_config mmcc_msm8974_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x5104,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc mmcc_msm8974_desc = {
diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index ebce98033fbb..bc7fbac83ab7 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -133,7 +133,7 @@ PNAME(mux_spdif_p)	= { "spdif_src", "spdif_frac", "xin12m" };
 PNAME(mux_uart0_p)	= { "uart0_src", "uart0_frac", "xin24m" };
 PNAME(mux_uart1_p)	= { "uart1_src", "uart1_frac", "xin24m" };
 PNAME(mux_uart2_p)	= { "uart2_src", "uart2_frac", "xin24m" };
-PNAME(mux_mac_p)	= { "mac_pll_src", "ext_gmac" };
+PNAME(mux_mac_p)	= { "mac_pll_src", "rmii_clkin" };
 PNAME(mux_dclk_p)	= { "dclk_lcdc", "dclk_cru" };
 
 static struct rockchip_pll_clock rk3036_pll_clks[] __initdata = {
@@ -224,16 +224,16 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(2), 2, GFLAGS),
 
 	COMPOSITE_NODIV(SCLK_TIMER0, "sclk_timer0", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 4, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 4, 1, MFLAGS,
 			RK2928_CLKGATE_CON(1), 0, GFLAGS),
 	COMPOSITE_NODIV(SCLK_TIMER1, "sclk_timer1", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 5, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 5, 1, MFLAGS,
 			RK2928_CLKGATE_CON(1), 1, GFLAGS),
 	COMPOSITE_NODIV(SCLK_TIMER2, "sclk_timer2", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 6, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 6, 1, MFLAGS,
 			RK2928_CLKGATE_CON(2), 4, GFLAGS),
 	COMPOSITE_NODIV(SCLK_TIMER3, "sclk_timer3", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 7, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 7, 1, MFLAGS,
 			RK2928_CLKGATE_CON(2), 5, GFLAGS),
 
 	MUX(0, "uart_pll_clk", mux_pll_src_apll_dpll_gpll_usb480m_p, 0,
@@ -242,11 +242,11 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(1), 8, GFLAGS),
 	COMPOSITE_NOMUX(0, "uart1_src", "uart_pll_clk", 0,
-			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
-			RK2928_CLKGATE_CON(1), 8, GFLAGS),
+			RK2928_CLKSEL_CON(14), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 10, GFLAGS),
 	COMPOSITE_NOMUX(0, "uart2_src", "uart_pll_clk", 0,
-			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
-			RK2928_CLKGATE_CON(1), 8, GFLAGS),
+			RK2928_CLKSEL_CON(15), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 12, GFLAGS),
 	COMPOSITE_FRACMUX(0, "uart0_frac", "uart0_src", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(17), 0,
 			RK2928_CLKGATE_CON(1), 9, GFLAGS,
@@ -279,13 +279,13 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(3), 2, GFLAGS),
 
 	COMPOSITE_NODIV(0, "sclk_sdmmc_src", mux_mmc_src_p, 0,
-			RK2928_CLKSEL_CON(12), 8, 2, DFLAGS,
+			RK2928_CLKSEL_CON(12), 8, 2, MFLAGS,
 			RK2928_CLKGATE_CON(2), 11, GFLAGS),
 	DIV(SCLK_SDMMC, "sclk_sdmmc", "sclk_sdmmc_src", 0,
 			RK2928_CLKSEL_CON(11), 0, 7, DFLAGS),
 
 	COMPOSITE_NODIV(0, "sclk_sdio_src", mux_mmc_src_p, 0,
-			RK2928_CLKSEL_CON(12), 10, 2, DFLAGS,
+			RK2928_CLKSEL_CON(12), 10, 2, MFLAGS,
 			RK2928_CLKGATE_CON(2), 13, GFLAGS),
 	DIV(SCLK_SDIO, "sclk_sdio", "sclk_sdio_src", 0,
 			RK2928_CLKSEL_CON(11), 8, 7, DFLAGS),
@@ -344,12 +344,12 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(10), 5, GFLAGS),
 
 	COMPOSITE_NOGATE(0, "mac_pll_src", mux_pll_src_3plls_p, 0,
-			RK2928_CLKSEL_CON(21), 0, 2, MFLAGS, 4, 5, DFLAGS),
+			RK2928_CLKSEL_CON(21), 0, 2, MFLAGS, 9, 5, DFLAGS),
 	MUX(SCLK_MACREF, "mac_clk_ref", mux_mac_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(21), 3, 1, MFLAGS),
 
 	COMPOSITE_NOMUX(SCLK_MAC, "mac_clk", "mac_clk_ref", 0,
-			RK2928_CLKSEL_CON(21), 9, 5, DFLAGS,
+			RK2928_CLKSEL_CON(21), 4, 5, DFLAGS,
 			RK2928_CLKGATE_CON(2), 6, GFLAGS),
 
 	MUX(SCLK_HDMI, "dclk_hdmi", mux_dclk_p, 0,
diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c
index be0ede522269..21f3ea909fab 100644
--- a/drivers/clk/rockchip/clk-rk3368.c
+++ b/drivers/clk/rockchip/clk-rk3368.c
@@ -780,13 +780,13 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
 	GATE(PCLK_TSADC, "pclk_tsadc", "pclk_peri", 0, RK3368_CLKGATE_CON(20), 0, GFLAGS),
 
 	/* pclk_pd_alive gates */
-	GATE(PCLK_TIMER1, "pclk_timer1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 8, GFLAGS),
-	GATE(PCLK_TIMER0, "pclk_timer0", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 7, GFLAGS),
-	GATE(0, "pclk_alive_niu", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 12, GFLAGS),
-	GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 11, GFLAGS),
-	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 3, GFLAGS),
-	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 2, GFLAGS),
-	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 1, GFLAGS),
+	GATE(PCLK_TIMER1, "pclk_timer1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 13, GFLAGS),
+	GATE(PCLK_TIMER0, "pclk_timer0", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 12, GFLAGS),
+	GATE(0, "pclk_alive_niu", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(22), 9, GFLAGS),
+	GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(22), 8, GFLAGS),
+	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 3, GFLAGS),
+	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 2, GFLAGS),
+	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 1, GFLAGS),
 
 	/*
 	 * pclk_vio gates
@@ -796,12 +796,12 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
 	GATE(0, "pclk_dphytx", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 8, GFLAGS),
 
 	/* pclk_pd_pmu gates */
-	GATE(PCLK_PMUGRF, "pclk_pmugrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 0, GFLAGS),
-	GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3368_CLKGATE_CON(17), 4, GFLAGS),
-	GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 3, GFLAGS),
-	GATE(0, "pclk_pmu_noc", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS),
-	GATE(0, "pclk_intmem1", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 1, GFLAGS),
-	GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS),
+	GATE(PCLK_PMUGRF, "pclk_pmugrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 5, GFLAGS),
+	GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3368_CLKGATE_CON(23), 4, GFLAGS),
+	GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 3, GFLAGS),
+	GATE(0, "pclk_pmu_noc", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 2, GFLAGS),
+	GATE(0, "pclk_intmem1", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 1, GFLAGS),
+	GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 0, GFLAGS),
 
 	/* timer gates */
 	GATE(0, "sclk_timer15", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 11, GFLAGS),
diff --git a/drivers/clk/tegra/clk-emc.c b/drivers/clk/tegra/clk-emc.c
index e1fe8f35d45c..74e7544f861b 100644
--- a/drivers/clk/tegra/clk-emc.c
+++ b/drivers/clk/tegra/clk-emc.c
@@ -450,8 +450,10 @@ static int load_timings_from_dt(struct tegra_clk_emc *tegra,
 		struct emc_timing *timing = tegra->timings + (i++);
 
 		err = load_one_timing_from_dt(tegra, timing, child);
-		if (err)
+		if (err) {
+			of_node_put(child);
 			return err;
+		}
 
 		timing->ram_code = ram_code;
 	}
@@ -499,9 +501,9 @@ struct clk *tegra_clk_register_emc(void __iomem *base, struct device_node *np,
 		 * fuses until the apbmisc driver is loaded.
 		 */
 		err = load_timings_from_dt(tegra, node, node_ram_code);
+		of_node_put(node);
 		if (err)
 			return ERR_PTR(err);
-		of_node_put(node);
 		break;
 	}
 
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index 19ce0738ee76..62ea38187b71 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -11,6 +11,7 @@ enum clk_id {
 	tegra_clk_afi,
 	tegra_clk_amx,
 	tegra_clk_amx1,
+	tegra_clk_apb2ape,
 	tegra_clk_apbdma,
 	tegra_clk_apbif,
 	tegra_clk_ape,
diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index a534bfab30b3..6ac3f843e7ca 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -86,15 +86,21 @@
 #define PLLE_SS_DISABLE (PLLE_SS_CNTL_BYPASS_SS | PLLE_SS_CNTL_INTERP_RESET |\
 				PLLE_SS_CNTL_SSC_BYP)
 #define PLLE_SS_MAX_MASK 0x1ff
-#define PLLE_SS_MAX_VAL 0x25
+#define PLLE_SS_MAX_VAL_TEGRA114 0x25
+#define PLLE_SS_MAX_VAL_TEGRA210 0x21
 #define PLLE_SS_INC_MASK (0xff << 16)
 #define PLLE_SS_INC_VAL (0x1 << 16)
 #define PLLE_SS_INCINTRV_MASK (0x3f << 24)
-#define PLLE_SS_INCINTRV_VAL (0x20 << 24)
+#define PLLE_SS_INCINTRV_VAL_TEGRA114 (0x20 << 24)
+#define PLLE_SS_INCINTRV_VAL_TEGRA210 (0x23 << 24)
 #define PLLE_SS_COEFFICIENTS_MASK \
 	(PLLE_SS_MAX_MASK | PLLE_SS_INC_MASK | PLLE_SS_INCINTRV_MASK)
-#define PLLE_SS_COEFFICIENTS_VAL \
-	(PLLE_SS_MAX_VAL | PLLE_SS_INC_VAL | PLLE_SS_INCINTRV_VAL)
+#define PLLE_SS_COEFFICIENTS_VAL_TEGRA114 \
+	(PLLE_SS_MAX_VAL_TEGRA114 | PLLE_SS_INC_VAL |\
+	 PLLE_SS_INCINTRV_VAL_TEGRA114)
+#define PLLE_SS_COEFFICIENTS_VAL_TEGRA210 \
+	(PLLE_SS_MAX_VAL_TEGRA210 | PLLE_SS_INC_VAL |\
+	 PLLE_SS_INCINTRV_VAL_TEGRA210)
 
 #define PLLE_AUX_PLLP_SEL	BIT(2)
 #define PLLE_AUX_USE_LOCKDET	BIT(3)
@@ -880,7 +886,7 @@ static int clk_plle_training(struct tegra_clk_pll *pll)
 static int clk_plle_enable(struct clk_hw *hw)
 {
 	struct tegra_clk_pll *pll = to_clk_pll(hw);
-	unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk));
+	unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 	struct tegra_clk_pll_freq_table sel;
 	u32 val;
 	int err;
@@ -1378,7 +1384,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	u32 val;
 	int ret;
 	unsigned long flags = 0;
-	unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk));
+	unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 
 	if (_get_table_rate(hw, &sel, pll->params->fixed_rate, input_rate))
 		return -EINVAL;
@@ -1401,7 +1407,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	val |= PLLE_MISC_IDDQ_SW_CTRL;
 	val &= ~PLLE_MISC_IDDQ_SW_VALUE;
 	val |= PLLE_MISC_PLLE_PTS;
-	val |= PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK;
+	val &= ~(PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK);
 	pll_writel_misc(val, pll);
 	udelay(5);
 
@@ -1428,7 +1434,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	val = pll_readl(PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_CENTER | PLLE_SS_CNTL_INVERT);
 	val &= ~PLLE_SS_COEFFICIENTS_MASK;
-	val |= PLLE_SS_COEFFICIENTS_VAL;
+	val |= PLLE_SS_COEFFICIENTS_VAL_TEGRA114;
 	pll_writel(val, PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_SSC_BYP | PLLE_SS_CNTL_BYPASS_SS);
 	pll_writel(val, PLLE_SS_CTRL, pll);
@@ -2012,9 +2018,9 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw)
 	struct tegra_clk_pll *pll = to_clk_pll(hw);
 	struct tegra_clk_pll_freq_table sel;
 	u32 val;
-	int ret;
+	int ret = 0;
 	unsigned long flags = 0;
-	unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk));
+	unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 
 	if (_get_table_rate(hw, &sel, pll->params->fixed_rate, input_rate))
 		return -EINVAL;
@@ -2022,22 +2028,20 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw)
 	if (pll->lock)
 		spin_lock_irqsave(pll->lock, flags);
 
+	val = pll_readl(pll->params->aux_reg, pll);
+	if (val & PLLE_AUX_SEQ_ENABLE)
+		goto out;
+
 	val = pll_readl_base(pll);
 	val &= ~BIT(30); /* Disable lock override */
 	pll_writel_base(val, pll);
 
-	val = pll_readl(pll->params->aux_reg, pll);
-	val |= PLLE_AUX_ENABLE_SWCTL;
-	val &= ~PLLE_AUX_SEQ_ENABLE;
-	pll_writel(val, pll->params->aux_reg, pll);
-	udelay(1);
-
 	val = pll_readl_misc(pll);
 	val |= PLLE_MISC_LOCK_ENABLE;
 	val |= PLLE_MISC_IDDQ_SW_CTRL;
 	val &= ~PLLE_MISC_IDDQ_SW_VALUE;
 	val |= PLLE_MISC_PLLE_PTS;
-	val |= PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK;
+	val &= ~(PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK);
 	pll_writel_misc(val, pll);
 	udelay(5);
 
@@ -2067,7 +2071,7 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw)
 	val = pll_readl(PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_CENTER | PLLE_SS_CNTL_INVERT);
 	val &= ~PLLE_SS_COEFFICIENTS_MASK;
-	val |= PLLE_SS_COEFFICIENTS_VAL;
+	val |= PLLE_SS_COEFFICIENTS_VAL_TEGRA210;
 	pll_writel(val, PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_SSC_BYP | PLLE_SS_CNTL_BYPASS_SS);
 	pll_writel(val, PLLE_SS_CTRL, pll);
@@ -2104,15 +2108,25 @@ static void clk_plle_tegra210_disable(struct clk_hw *hw)
 	if (pll->lock)
 		spin_lock_irqsave(pll->lock, flags);
 
+	/* If PLLE HW sequencer is enabled, SW should not disable PLLE */
+	val = pll_readl(pll->params->aux_reg, pll);
+	if (val & PLLE_AUX_SEQ_ENABLE)
+		goto out;
+
 	val = pll_readl_base(pll);
 	val &= ~PLLE_BASE_ENABLE;
 	pll_writel_base(val, pll);
 
+	val = pll_readl(pll->params->aux_reg, pll);
+	val |= PLLE_AUX_ENABLE_SWCTL | PLLE_AUX_SS_SWCTL;
+	pll_writel(val, pll->params->aux_reg, pll);
+
 	val = pll_readl_misc(pll);
 	val |= PLLE_MISC_IDDQ_SW_CTRL | PLLE_MISC_IDDQ_SW_VALUE;
 	pll_writel_misc(val, pll);
 	udelay(1);
 
+out:
 	if (pll->lock)
 		spin_unlock_irqrestore(pll->lock, flags);
 }
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 6ad381a888a6..ea2b9cbf9e70 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -773,7 +773,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	XUSB("xusb_dev_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_DEV_SRC, 95, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_dev_src),
 	XUSB("xusb_dev_src", mux_clkm_pllp_pllre, CLK_SOURCE_XUSB_DEV_SRC, 95, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_dev_src_8),
 	MUX8("dbgapb", mux_pllp_clkm_2, CLK_SOURCE_DBGAPB, 185, TEGRA_PERIPH_NO_RESET, tegra_clk_dbgapb),
-	MUX8("msenc", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVENC, 219, 0, tegra_clk_nvenc),
+	MUX8("nvenc", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVENC, 219, 0, tegra_clk_nvenc),
 	MUX8("nvdec", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVDEC, 194, 0, tegra_clk_nvdec),
 	MUX8("nvjpg", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVJPG, 195, 0, tegra_clk_nvjpg),
 	MUX8("ape", mux_plla_pllc4_out0_pllc_pllc4_out1_pllp_pllc4_out2_clkm, CLK_SOURCE_APE, 198, TEGRA_PERIPH_ON_APB, tegra_clk_ape),
@@ -782,7 +782,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	NODIV("sor1", mux_clkm_sor1_brick_sor1_src, CLK_SOURCE_SOR1, 15, MASK(1), 183, 0, tegra_clk_sor1, &sor1_lock),
 	MUX8("sdmmc_legacy", mux_pllp_out3_clkm_pllp_pllc4, CLK_SOURCE_SDMMC_LEGACY, 193, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_sdmmc_legacy),
 	MUX8("qspi", mux_pllp_pllc_pllc_out1_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_QSPI, 211, TEGRA_PERIPH_ON_APB, tegra_clk_qspi),
-	MUX("vii2c", mux_pllp_pllc_clkm, CLK_SOURCE_VI_I2C, 208, TEGRA_PERIPH_ON_APB, tegra_clk_vi_i2c),
+	I2C("vii2c", mux_pllp_pllc_clkm, CLK_SOURCE_VI_I2C, 208, tegra_clk_vi_i2c),
 	MUX("mipibif", mux_pllp_clkm, CLK_SOURCE_MIPIBIF, 173, TEGRA_PERIPH_ON_APB, tegra_clk_mipibif),
 	MUX("uartape", mux_pllp_pllc_clkm, CLK_SOURCE_UARTAPE, 212, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_uartape),
 	MUX8("tsecb", mux_pllp_pllc2_c_c3_clkm, CLK_SOURCE_TSECB, 206, 0, tegra_clk_tsecb),
@@ -829,6 +829,7 @@ static struct tegra_periph_init_data gate_clks[] = {
 	GATE("xusb_gate", "osc", 143, 0, tegra_clk_xusb_gate, 0),
 	GATE("pll_p_out_cpu", "pll_p", 223, 0, tegra_clk_pll_p_out_cpu, 0),
 	GATE("pll_p_out_adsp", "pll_p", 187, 0, tegra_clk_pll_p_out_adsp, 0),
+	GATE("apb2ape", "clk_m", 107, 0, tegra_clk_apb2ape, 0),
 };
 
 static struct tegra_periph_init_data div_clks[] = {
diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c
index 4559a20e3af6..474de0f0c26d 100644
--- a/drivers/clk/tegra/clk-tegra-super-gen4.c
+++ b/drivers/clk/tegra/clk-tegra-super-gen4.c
@@ -67,7 +67,7 @@ static const char *cclk_lp_parents[] = { "clk_m", "pll_c", "clk_32k", "pll_m",
 					 "pll_p", "pll_p_out4", "unused",
 					 "unused", "pll_x", "pll_x_out0" };
 
-const struct tegra_super_gen_info tegra_super_gen_info_gen4 = {
+static const struct tegra_super_gen_info tegra_super_gen_info_gen4 = {
 	.gen = gen4,
 	.sclk_parents = sclk_parents,
 	.cclk_g_parents = cclk_g_parents,
@@ -93,7 +93,7 @@ static const char *cclk_lp_parents_gen5[] = { "clk_m", "unused", "clk_32k", "unu
 					"unused", "unused", "unused", "unused",
 					"dfllCPU_out" };
 
-const struct tegra_super_gen_info tegra_super_gen_info_gen5 = {
+static const struct tegra_super_gen_info tegra_super_gen_info_gen5 = {
 	.gen = gen5,
 	.sclk_parents = sclk_parents_gen5,
 	.cclk_g_parents = cclk_g_parents_gen5,
@@ -171,7 +171,7 @@ static void __init tegra_sclk_init(void __iomem *clk_base,
 	*dt_clk = clk;
 }
 
-void __init tegra_super_clk_init(void __iomem *clk_base,
+static void __init tegra_super_clk_init(void __iomem *clk_base,
 				void __iomem *pmc_base,
 				struct tegra_clk *tegra_clks,
 				struct tegra_clk_pll_params *params,
diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c
index 58514c44ea83..637041fd53ad 100644
--- a/drivers/clk/tegra/clk-tegra210.c
+++ b/drivers/clk/tegra/clk-tegra210.c
@@ -59,8 +59,8 @@
 #define PLLC3_MISC3 0x50c
 
 #define PLLM_BASE 0x90
-#define PLLM_MISC0 0x9c
 #define PLLM_MISC1 0x98
+#define PLLM_MISC2 0x9c
 #define PLLP_BASE 0xa0
 #define PLLP_MISC0 0xac
 #define PLLP_MISC1 0x680
@@ -99,7 +99,7 @@
 #define PLLC4_MISC0 0x5a8
 #define PLLC4_OUT 0x5e4
 #define PLLMB_BASE 0x5e8
-#define PLLMB_MISC0 0x5ec
+#define PLLMB_MISC1 0x5ec
 #define PLLA1_BASE 0x6a4
 #define PLLA1_MISC0 0x6a8
 #define PLLA1_MISC1 0x6ac
@@ -243,7 +243,8 @@ static unsigned long tegra210_input_freq[] = {
 };
 
 static const char *mux_pllmcp_clkm[] = {
-	"pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud", "pll_c2", "pll_c3",
+	"pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud", "pll_mb", "pll_mb",
+	"pll_p",
 };
 #define mux_pllmcp_clkm_idx NULL
 
@@ -367,12 +368,12 @@ static const char *mux_pllmcp_clkm[] = {
 /* PLLMB */
 #define PLLMB_BASE_LOCK			(1 << 27)
 
-#define PLLMB_MISC0_LOCK_OVERRIDE	(1 << 18)
-#define PLLMB_MISC0_IDDQ		(1 << 17)
-#define PLLMB_MISC0_LOCK_ENABLE		(1 << 16)
+#define PLLMB_MISC1_LOCK_OVERRIDE	(1 << 18)
+#define PLLMB_MISC1_IDDQ		(1 << 17)
+#define PLLMB_MISC1_LOCK_ENABLE		(1 << 16)
 
-#define PLLMB_MISC0_DEFAULT_VALUE	0x00030000
-#define PLLMB_MISC0_WRITE_MASK		0x0007ffff
+#define PLLMB_MISC1_DEFAULT_VALUE	0x00030000
+#define PLLMB_MISC1_WRITE_MASK		0x0007ffff
 
 /* PLLP */
 #define PLLP_BASE_OVERRIDE		(1 << 28)
@@ -457,7 +458,8 @@ static void pllcx_check_defaults(struct tegra_clk_pll_params *params)
 			PLLCX_MISC3_WRITE_MASK);
 }
 
-void tegra210_pllcx_set_defaults(const char *name, struct tegra_clk_pll *pllcx)
+static void tegra210_pllcx_set_defaults(const char *name,
+					struct tegra_clk_pll *pllcx)
 {
 	pllcx->params->defaults_set = true;
 
@@ -482,22 +484,22 @@ void tegra210_pllcx_set_defaults(const char *name, struct tegra_clk_pll *pllcx)
 	udelay(1);
 }
 
-void _pllc_set_defaults(struct tegra_clk_pll *pllcx)
+static void _pllc_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_C", pllcx);
 }
 
-void _pllc2_set_defaults(struct tegra_clk_pll *pllcx)
+static void _pllc2_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_C2", pllcx);
 }
 
-void _pllc3_set_defaults(struct tegra_clk_pll *pllcx)
+static void _pllc3_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_C3", pllcx);
 }
 
-void _plla1_set_defaults(struct tegra_clk_pll *pllcx)
+static void _plla1_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_A1", pllcx);
 }
@@ -507,7 +509,7 @@ void _plla1_set_defaults(struct tegra_clk_pll *pllcx)
  * PLL with dynamic ramp and fractional SDM. Dynamic ramp is not used.
  * Fractional SDM is allowed to provide exact audio rates.
  */
-void tegra210_plla_set_defaults(struct tegra_clk_pll *plla)
+static void tegra210_plla_set_defaults(struct tegra_clk_pll *plla)
 {
 	u32 mask;
 	u32 val = readl_relaxed(clk_base + plla->params->base_reg);
@@ -559,7 +561,7 @@ void tegra210_plla_set_defaults(struct tegra_clk_pll *plla)
  * PLLD
  * PLL with fractional SDM.
  */
-void tegra210_plld_set_defaults(struct tegra_clk_pll *plld)
+static void tegra210_plld_set_defaults(struct tegra_clk_pll *plld)
 {
 	u32 val;
 	u32 mask = 0xffff;
@@ -698,7 +700,7 @@ static void plldss_defaults(const char *pll_name, struct tegra_clk_pll *plldss,
 	udelay(1);
 }
 
-void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2)
+static void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2)
 {
 	plldss_defaults("PLL_D2", plld2, PLLD2_MISC0_DEFAULT_VALUE,
 			PLLD2_MISC1_CFG_DEFAULT_VALUE,
@@ -706,7 +708,7 @@ void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2)
 			PLLD2_MISC3_CTRL2_DEFAULT_VALUE);
 }
 
-void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp)
+static void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp)
 {
 	plldss_defaults("PLL_DP", plldp, PLLDP_MISC0_DEFAULT_VALUE,
 			PLLDP_MISC1_CFG_DEFAULT_VALUE,
@@ -719,7 +721,7 @@ void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp)
  * Base and misc0 layout is the same as PLLD2/PLLDP, but no SDM/SSC support.
  * VCO is exposed to the clock tree via fixed 1/3 and 1/5 dividers.
  */
-void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4)
+static void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4)
 {
 	plldss_defaults("PLL_C4", pllc4, PLLC4_MISC0_DEFAULT_VALUE, 0, 0, 0);
 }
@@ -728,7 +730,7 @@ void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4)
  * PLLRE
  * VCO is exposed to the clock tree directly along with post-divider output
  */
-void tegra210_pllre_set_defaults(struct tegra_clk_pll *pllre)
+static void tegra210_pllre_set_defaults(struct tegra_clk_pll *pllre)
 {
 	u32 mask;
 	u32 val = readl_relaxed(clk_base + pllre->params->base_reg);
@@ -780,13 +782,13 @@ static void pllx_get_dyn_steps(struct clk_hw *hw, u32 *step_a, u32 *step_b)
 {
 	unsigned long input_rate;
 
-	if (!IS_ERR_OR_NULL(hw->clk)) {
+	/* cf rate */
+	if (!IS_ERR_OR_NULL(hw->clk))
 		input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
-		/* cf rate */
-		input_rate /= tegra_pll_get_fixed_mdiv(hw, input_rate);
-	} else {
+	else
 		input_rate = 38400000;
-	}
+
+	input_rate /= tegra_pll_get_fixed_mdiv(hw, input_rate);
 
 	switch (input_rate) {
 	case 12000000:
@@ -841,7 +843,7 @@ static void pllx_check_defaults(struct tegra_clk_pll *pll)
 			PLLX_MISC5_WRITE_MASK);
 }
 
-void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx)
+static void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx)
 {
 	u32 val;
 	u32 step_a, step_b;
@@ -901,7 +903,7 @@ void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx)
 }
 
 /* PLLMB */
-void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
+static void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
 {
 	u32 mask, val = readl_relaxed(clk_base + pllmb->params->base_reg);
 
@@ -914,15 +916,15 @@ void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
 		 * PLL is ON: check if defaults already set, then set those
 		 * that can be updated in flight.
 		 */
-		val = PLLMB_MISC0_DEFAULT_VALUE & (~PLLMB_MISC0_IDDQ);
-		mask = PLLMB_MISC0_LOCK_ENABLE | PLLMB_MISC0_LOCK_OVERRIDE;
+		val = PLLMB_MISC1_DEFAULT_VALUE & (~PLLMB_MISC1_IDDQ);
+		mask = PLLMB_MISC1_LOCK_ENABLE | PLLMB_MISC1_LOCK_OVERRIDE;
 		_pll_misc_chk_default(clk_base, pllmb->params, 0, val,
-				~mask & PLLMB_MISC0_WRITE_MASK);
+				~mask & PLLMB_MISC1_WRITE_MASK);
 
 		/* Enable lock detect */
 		val = readl_relaxed(clk_base + pllmb->params->ext_misc_reg[0]);
 		val &= ~mask;
-		val |= PLLMB_MISC0_DEFAULT_VALUE & mask;
+		val |= PLLMB_MISC1_DEFAULT_VALUE & mask;
 		writel_relaxed(val, clk_base + pllmb->params->ext_misc_reg[0]);
 		udelay(1);
 
@@ -930,7 +932,7 @@ void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
 	}
 
 	/* set IDDQ, enable lock detect */
-	writel_relaxed(PLLMB_MISC0_DEFAULT_VALUE,
+	writel_relaxed(PLLMB_MISC1_DEFAULT_VALUE,
 			clk_base + pllmb->params->ext_misc_reg[0]);
 	udelay(1);
 }
@@ -960,7 +962,7 @@ static void pllp_check_defaults(struct tegra_clk_pll *pll, bool enabled)
 			~mask & PLLP_MISC1_WRITE_MASK);
 }
 
-void tegra210_pllp_set_defaults(struct tegra_clk_pll *pllp)
+static void tegra210_pllp_set_defaults(struct tegra_clk_pll *pllp)
 {
 	u32 mask;
 	u32 val = readl_relaxed(clk_base + pllp->params->base_reg);
@@ -1022,7 +1024,7 @@ static void pllu_check_defaults(struct tegra_clk_pll *pll, bool hw_control)
 			~mask & PLLU_MISC1_WRITE_MASK);
 }
 
-void tegra210_pllu_set_defaults(struct tegra_clk_pll *pllu)
+static void tegra210_pllu_set_defaults(struct tegra_clk_pll *pllu)
 {
 	u32 val = readl_relaxed(clk_base + pllu->params->base_reg);
 
@@ -1212,8 +1214,9 @@ static void tegra210_clk_pll_set_gain(struct tegra_clk_pll_freq_table *cfg)
 	cfg->m *= PLL_SDM_COEFF;
 }
 
-unsigned long tegra210_clk_adjust_vco_min(struct tegra_clk_pll_params *params,
-					  unsigned long parent_rate)
+static unsigned long
+tegra210_clk_adjust_vco_min(struct tegra_clk_pll_params *params,
+			    unsigned long parent_rate)
 {
 	unsigned long vco_min = params->vco_min;
 
@@ -1386,7 +1389,7 @@ static struct tegra_clk_pll_params pll_c_params = {
 	.mdiv_default = 3,
 	.div_nmp = &pllc_nmp,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _pllc_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1425,7 +1428,7 @@ static struct tegra_clk_pll_params pll_c2_params = {
 	.ext_misc_reg[2] = PLLC2_MISC2,
 	.ext_misc_reg[3] = PLLC2_MISC3,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _pllc2_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1455,7 +1458,7 @@ static struct tegra_clk_pll_params pll_c3_params = {
 	.ext_misc_reg[2] = PLLC3_MISC2,
 	.ext_misc_reg[3] = PLLC3_MISC3,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _pllc3_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1505,7 +1508,6 @@ static struct tegra_clk_pll_params pll_c4_vco_params = {
 	.base_reg = PLLC4_BASE,
 	.misc_reg = PLLC4_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.max_p = PLL_QLIN_PDIV_MAX,
 	.ext_misc_reg[0] = PLLC4_MISC0,
@@ -1517,8 +1519,7 @@ static struct tegra_clk_pll_params pll_c4_vco_params = {
 	.div_nmp = &pllss_nmp,
 	.freq_table = pll_c4_vco_freq_table,
 	.set_defaults = tegra210_pllc4_set_defaults,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE |
-		 TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
 
@@ -1559,15 +1560,15 @@ static struct tegra_clk_pll_params pll_m_params = {
 	.vco_min = 800000000,
 	.vco_max = 1866000000,
 	.base_reg = PLLM_BASE,
-	.misc_reg = PLLM_MISC1,
+	.misc_reg = PLLM_MISC2,
 	.lock_mask = PLL_BASE_LOCK,
 	.lock_enable_bit_idx = PLLM_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
-	.iddq_reg = PLLM_MISC0,
+	.iddq_reg = PLLM_MISC2,
 	.iddq_bit_idx = PLLM_IDDQ_BIT,
 	.max_p = PLL_QLIN_PDIV_MAX,
-	.ext_misc_reg[0] = PLLM_MISC0,
-	.ext_misc_reg[0] = PLLM_MISC1,
+	.ext_misc_reg[0] = PLLM_MISC2,
+	.ext_misc_reg[1] = PLLM_MISC1,
 	.round_p_to_pdiv = pll_qlin_p_to_pdiv,
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllm_nmp,
@@ -1586,19 +1587,18 @@ static struct tegra_clk_pll_params pll_mb_params = {
 	.vco_min = 800000000,
 	.vco_max = 1866000000,
 	.base_reg = PLLMB_BASE,
-	.misc_reg = PLLMB_MISC0,
+	.misc_reg = PLLMB_MISC1,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLMB_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
-	.iddq_reg = PLLMB_MISC0,
+	.iddq_reg = PLLMB_MISC1,
 	.iddq_bit_idx = PLLMB_IDDQ_BIT,
 	.max_p = PLL_QLIN_PDIV_MAX,
-	.ext_misc_reg[0] = PLLMB_MISC0,
+	.ext_misc_reg[0] = PLLMB_MISC1,
 	.round_p_to_pdiv = pll_qlin_p_to_pdiv,
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllm_nmp,
 	.freq_table = pll_m_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = tegra210_pllmb_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1671,7 +1671,6 @@ static struct tegra_clk_pll_params pll_re_vco_params = {
 	.base_reg = PLLRE_BASE,
 	.misc_reg = PLLRE_MISC0,
 	.lock_mask = PLLRE_MISC_LOCK,
-	.lock_enable_bit_idx = PLLRE_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.max_p = PLL_QLIN_PDIV_MAX,
 	.ext_misc_reg[0] = PLLRE_MISC0,
@@ -1681,8 +1680,7 @@ static struct tegra_clk_pll_params pll_re_vco_params = {
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllre_nmp,
 	.freq_table = pll_re_vco_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_LOCK_MISC |
-		 TEGRA_PLL_HAS_LOCK_ENABLE | TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_LOCK_MISC | TEGRA_PLL_VCO_OUT,
 	.set_defaults = tegra210_pllre_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1712,7 +1710,6 @@ static struct tegra_clk_pll_params pll_p_params = {
 	.base_reg = PLLP_BASE,
 	.misc_reg = PLLP_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLP_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.iddq_reg = PLLP_MISC0,
 	.iddq_bit_idx = PLLXP_IDDQ_BIT,
@@ -1721,8 +1718,7 @@ static struct tegra_clk_pll_params pll_p_params = {
 	.div_nmp = &pllp_nmp,
 	.freq_table = pll_p_freq_table,
 	.fixed_rate = 408000000,
-	.flags = TEGRA_PLL_FIXED | TEGRA_PLL_USE_LOCK |
-		 TEGRA_PLL_HAS_LOCK_ENABLE | TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLL_FIXED | TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT,
 	.set_defaults = tegra210_pllp_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1750,7 +1746,7 @@ static struct tegra_clk_pll_params pll_a1_params = {
 	.ext_misc_reg[2] = PLLA1_MISC2,
 	.ext_misc_reg[3] = PLLA1_MISC3,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _plla1_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1787,7 +1783,6 @@ static struct tegra_clk_pll_params pll_a_params = {
 	.base_reg = PLLA_BASE,
 	.misc_reg = PLLA_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLA_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.round_p_to_pdiv = pll_qlin_p_to_pdiv,
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
@@ -1802,8 +1797,7 @@ static struct tegra_clk_pll_params pll_a_params = {
 	.ext_misc_reg[1] = PLLA_MISC1,
 	.ext_misc_reg[2] = PLLA_MISC2,
 	.freq_table = pll_a_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_MDIV_NEW |
-		 TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK | TEGRA_MDIV_NEW,
 	.set_defaults = tegra210_plla_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 	.set_gain = tegra210_clk_pll_set_gain,
@@ -1836,7 +1830,6 @@ static struct tegra_clk_pll_params pll_d_params = {
 	.base_reg = PLLD_BASE,
 	.misc_reg = PLLD_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLD_MISC_LOCK_ENABLE,
 	.lock_delay = 1000,
 	.iddq_reg = PLLD_MISC0,
 	.iddq_bit_idx = PLLD_IDDQ_BIT,
@@ -1850,7 +1843,7 @@ static struct tegra_clk_pll_params pll_d_params = {
 	.ext_misc_reg[0] = PLLD_MISC0,
 	.ext_misc_reg[1] = PLLD_MISC1,
 	.freq_table = pll_d_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.mdiv_default = 1,
 	.set_defaults = tegra210_plld_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
@@ -1876,7 +1869,6 @@ static struct tegra_clk_pll_params pll_d2_params = {
 	.base_reg = PLLD2_BASE,
 	.misc_reg = PLLD2_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.iddq_reg = PLLD2_BASE,
 	.iddq_bit_idx = PLLSS_IDDQ_BIT,
@@ -1897,7 +1889,7 @@ static struct tegra_clk_pll_params pll_d2_params = {
 	.mdiv_default = 1,
 	.freq_table = tegra210_pll_d2_freq_table,
 	.set_defaults = tegra210_plld2_set_defaults,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 	.set_gain = tegra210_clk_pll_set_gain,
 	.adjust_vco = tegra210_clk_adjust_vco_min,
@@ -1920,7 +1912,6 @@ static struct tegra_clk_pll_params pll_dp_params = {
 	.base_reg = PLLDP_BASE,
 	.misc_reg = PLLDP_MISC,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.iddq_reg = PLLDP_BASE,
 	.iddq_bit_idx = PLLSS_IDDQ_BIT,
@@ -1941,7 +1932,7 @@ static struct tegra_clk_pll_params pll_dp_params = {
 	.mdiv_default = 1,
 	.freq_table = pll_dp_freq_table,
 	.set_defaults = tegra210_plldp_set_defaults,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 	.set_gain = tegra210_clk_pll_set_gain,
 	.adjust_vco = tegra210_clk_adjust_vco_min,
@@ -1973,7 +1964,6 @@ static struct tegra_clk_pll_params pll_u_vco_params = {
 	.base_reg = PLLU_BASE,
 	.misc_reg = PLLU_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLU_MISC_LOCK_ENABLE,
 	.lock_delay = 1000,
 	.iddq_reg = PLLU_MISC0,
 	.iddq_bit_idx = PLLU_IDDQ_BIT,
@@ -1983,8 +1973,7 @@ static struct tegra_clk_pll_params pll_u_vco_params = {
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllu_nmp,
 	.freq_table = pll_u_freq_table,
-	.flags = TEGRA_PLLU | TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE |
-		 TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLLU | TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT,
 	.set_defaults = tegra210_pllu_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -2218,6 +2207,7 @@ static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_pll_c4_out1] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT1, .present = true },
 	[tegra_clk_pll_c4_out2] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT2, .present = true },
 	[tegra_clk_pll_c4_out3] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT3, .present = true },
+	[tegra_clk_apb2ape] = { .dt_id = TEGRA210_CLK_APB2APE, .present = true },
 };
 
 static struct tegra_devclk devclks[] __initdata = {
@@ -2519,7 +2509,7 @@ static void __init tegra210_pll_init(void __iomem *clk_base,
 
 	/* PLLU_VCO */
 	val = readl(clk_base + pll_u_vco_params.base_reg);
-	val &= ~BIT(24); /* disable PLLU_OVERRIDE */
+	val &= ~PLLU_BASE_OVERRIDE; /* disable PLLU_OVERRIDE */
 	writel(val, clk_base + pll_u_vco_params.base_reg);
 
 	clk = tegra_clk_register_pllre("pll_u_vco", "pll_ref", clk_base, pmc,
@@ -2738,8 +2728,6 @@ static struct tegra_clk_init_table init_table[] __initdata = {
 	{ TEGRA210_CLK_DFLL_REF, TEGRA210_CLK_PLL_P, 51000000, 1 },
 	{ TEGRA210_CLK_SBC4, TEGRA210_CLK_PLL_P, 12000000, 1 },
 	{ TEGRA210_CLK_PLL_RE_VCO, TEGRA210_CLK_CLK_MAX, 672000000, 1 },
-	{ TEGRA210_CLK_PLL_U_OUT1, TEGRA210_CLK_CLK_MAX, 48000000, 1 },
-	{ TEGRA210_CLK_PLL_U_OUT2, TEGRA210_CLK_CLK_MAX, 60000000, 1 },
 	{ TEGRA210_CLK_XUSB_GATE, TEGRA210_CLK_CLK_MAX, 0, 1 },
 	{ TEGRA210_CLK_XUSB_SS_SRC, TEGRA210_CLK_PLL_U_480M, 120000000, 0 },
 	{ TEGRA210_CLK_XUSB_FS_SRC, TEGRA210_CLK_PLL_U_48M, 48000000, 0 },
diff --git a/drivers/clk/ti/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c
index 1c300388782b..cc739291a3ce 100644
--- a/drivers/clk/ti/dpll3xxx.c
+++ b/drivers/clk/ti/dpll3xxx.c
@@ -460,7 +460,8 @@ int omap3_noncore_dpll_enable(struct clk_hw *hw)
 
 	parent = clk_hw_get_parent(hw);
 
-	if (clk_hw_get_rate(hw) == clk_get_rate(dd->clk_bypass)) {
+	if (clk_hw_get_rate(hw) ==
+	    clk_hw_get_rate(__clk_get_hw(dd->clk_bypass))) {
 		WARN_ON(parent != __clk_get_hw(dd->clk_bypass));
 		r = _omap3_noncore_dpll_bypass(clk);
 	} else {
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index e62f8cb2c9b5..3bca438ecd19 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -78,6 +78,9 @@ static int vco_set(struct clk_icst *icst, struct icst_vco vco)
 	ret = regmap_read(icst->map, icst->vcoreg_off, &val);
 	if (ret)
 		return ret;
+
+	/* Mask the 18 bits used by the VCO */
+	val &= ~0x7ffff;
 	val |= vco.v | (vco.r << 9) | (vco.s << 16);
 
 	/* This magic unlocks the VCO so it can be controlled */
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index c64d543d64bf..ffe9d1c6b588 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -67,7 +67,7 @@ static int arch_timer_ppi[MAX_TIMER_PPI];
 
 static struct clock_event_device __percpu *arch_timer_evt;
 
-static bool arch_timer_use_virtual = true;
+static enum ppi_nr arch_timer_uses_ppi = VIRT_PPI;
 static bool arch_timer_c3stop;
 static bool arch_timer_mem_use_virtual;
 
@@ -263,14 +263,20 @@ static void __arch_timer_setup(unsigned type,
 		clk->name = "arch_sys_timer";
 		clk->rating = 450;
 		clk->cpumask = cpumask_of(smp_processor_id());
-		if (arch_timer_use_virtual) {
-			clk->irq = arch_timer_ppi[VIRT_PPI];
+		clk->irq = arch_timer_ppi[arch_timer_uses_ppi];
+		switch (arch_timer_uses_ppi) {
+		case VIRT_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
 			clk->set_next_event = arch_timer_set_next_event_virt;
-		} else {
-			clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+			break;
+		case PHYS_SECURE_PPI:
+		case PHYS_NONSECURE_PPI:
+		case HYP_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
 			clk->set_next_event = arch_timer_set_next_event_phys;
+			break;
+		default:
+			BUG();
 		}
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
@@ -338,17 +344,20 @@ static void arch_counter_set_user_access(void)
 	arch_timer_set_cntkctl(cntkctl);
 }
 
+static bool arch_timer_has_nonsecure_ppi(void)
+{
+	return (arch_timer_uses_ppi == PHYS_SECURE_PPI &&
+		arch_timer_ppi[PHYS_NONSECURE_PPI]);
+}
+
 static int arch_timer_setup(struct clock_event_device *clk)
 {
 	__arch_timer_setup(ARCH_CP15_TIMER, clk);
 
-	if (arch_timer_use_virtual)
-		enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
-	else {
-		enable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI], 0);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
-	}
+	enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0);
+
+	if (arch_timer_has_nonsecure_ppi())
+		enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
 
 	arch_counter_set_user_access();
 	if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM))
@@ -390,7 +399,7 @@ static void arch_timer_banner(unsigned type)
 		     (unsigned long)arch_timer_rate / 1000000,
 		     (unsigned long)(arch_timer_rate / 10000) % 100,
 		     type & ARCH_CP15_TIMER ?
-			arch_timer_use_virtual ? "virt" : "phys" :
+		     (arch_timer_uses_ppi == VIRT_PPI) ? "virt" : "phys" :
 			"",
 		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  "/" : "",
 		     type & ARCH_MEM_TIMER ?
@@ -460,7 +469,7 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_CP15_TIMER) {
-		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_use_virtual)
+		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_uses_ppi == VIRT_PPI)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
@@ -490,13 +499,9 @@ static void arch_timer_stop(struct clock_event_device *clk)
 	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
 		 clk->irq, smp_processor_id());
 
-	if (arch_timer_use_virtual)
-		disable_percpu_irq(arch_timer_ppi[VIRT_PPI]);
-	else {
-		disable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI]);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
-	}
+	disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]);
+	if (arch_timer_has_nonsecure_ppi())
+		disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
 
 	clk->set_state_shutdown(clk);
 }
@@ -562,12 +567,14 @@ static int __init arch_timer_register(void)
 		goto out;
 	}
 
-	if (arch_timer_use_virtual) {
-		ppi = arch_timer_ppi[VIRT_PPI];
+	ppi = arch_timer_ppi[arch_timer_uses_ppi];
+	switch (arch_timer_uses_ppi) {
+	case VIRT_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_virt,
 					 "arch_timer", arch_timer_evt);
-	} else {
-		ppi = arch_timer_ppi[PHYS_SECURE_PPI];
+		break;
+	case PHYS_SECURE_PPI:
+	case PHYS_NONSECURE_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_phys,
 					 "arch_timer", arch_timer_evt);
 		if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
@@ -578,6 +585,13 @@ static int __init arch_timer_register(void)
 				free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
 						arch_timer_evt);
 		}
+		break;
+	case HYP_PPI:
+		err = request_percpu_irq(ppi, arch_timer_handler_phys,
+					 "arch_timer", arch_timer_evt);
+		break;
+	default:
+		BUG();
 	}
 
 	if (err) {
@@ -602,15 +616,10 @@ static int __init arch_timer_register(void)
 out_unreg_notify:
 	unregister_cpu_notifier(&arch_timer_cpu_nb);
 out_free_irq:
-	if (arch_timer_use_virtual)
-		free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
-	else {
-		free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+	free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt);
+	if (arch_timer_has_nonsecure_ppi())
+		free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
 				arch_timer_evt);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
-					arch_timer_evt);
-	}
 
 out_free:
 	free_percpu(arch_timer_evt);
@@ -697,12 +706,25 @@ static void __init arch_timer_init(void)
 	 *
 	 * If no interrupt provided for virtual timer, we'll have to
 	 * stick to the physical timer. It'd better be accessible...
+	 *
+	 * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
+	 * accesses to CNTP_*_EL1 registers are silently redirected to
+	 * their CNTHP_*_EL2 counterparts, and use a different PPI
+	 * number.
 	 */
 	if (is_hyp_mode_available() || !arch_timer_ppi[VIRT_PPI]) {
-		arch_timer_use_virtual = false;
+		bool has_ppi;
+
+		if (is_kernel_in_hyp_mode()) {
+			arch_timer_uses_ppi = HYP_PPI;
+			has_ppi = !!arch_timer_ppi[HYP_PPI];
+		} else {
+			arch_timer_uses_ppi = PHYS_SECURE_PPI;
+			has_ppi = (!!arch_timer_ppi[PHYS_SECURE_PPI] ||
+				   !!arch_timer_ppi[PHYS_NONSECURE_PPI]);
+		}
 
-		if (!arch_timer_ppi[PHYS_SECURE_PPI] ||
-		    !arch_timer_ppi[PHYS_NONSECURE_PPI]) {
+		if (!has_ppi) {
 			pr_warn("arch_timer: No interrupt available, giving up\n");
 			return;
 		}
@@ -735,7 +757,7 @@ static void __init arch_timer_of_init(struct device_node *np)
 	 */
 	if (IS_ENABLED(CONFIG_ARM) &&
 	    of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
-			arch_timer_use_virtual = false;
+		arch_timer_uses_ppi = PHYS_SECURE_PPI;
 
 	arch_timer_init();
 }
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 20de861aa0ea..8bf9914d4d15 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -782,7 +782,7 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err)
 	dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU |
 			SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 
 	if (req->base.complete)
 		req->base.complete(&req->base, err);
@@ -795,7 +795,7 @@ static int atmel_sha_hw_init(struct atmel_sha_dev *dd)
 {
 	int err;
 
-	err = clk_prepare_enable(dd->iclk);
+	err = clk_enable(dd->iclk);
 	if (err)
 		return err;
 
@@ -822,7 +822,7 @@ static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd)
 	dev_info(dd->dev,
 			"version: 0x%x\n", dd->hw_version);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 }
 
 static int atmel_sha_handle_queue(struct atmel_sha_dev *dd,
@@ -1410,6 +1410,10 @@ static int atmel_sha_probe(struct platform_device *pdev)
 		goto res_err;
 	}
 
+	err = clk_prepare(sha_dd->iclk);
+	if (err)
+		goto res_err;
+
 	atmel_sha_hw_version_init(sha_dd);
 
 	atmel_sha_get_cap(sha_dd);
@@ -1421,12 +1425,12 @@ static int atmel_sha_probe(struct platform_device *pdev)
 			if (IS_ERR(pdata)) {
 				dev_err(&pdev->dev, "platform data not available\n");
 				err = PTR_ERR(pdata);
-				goto res_err;
+				goto iclk_unprepare;
 			}
 		}
 		if (!pdata->dma_slave) {
 			err = -ENXIO;
-			goto res_err;
+			goto iclk_unprepare;
 		}
 		err = atmel_sha_dma_init(sha_dd, pdata);
 		if (err)
@@ -1457,6 +1461,8 @@ err_algs:
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 err_sha_dma:
+iclk_unprepare:
+	clk_unprepare(sha_dd->iclk);
 res_err:
 	tasklet_kill(&sha_dd->done_task);
 sha_dd_err:
@@ -1483,12 +1489,7 @@ static int atmel_sha_remove(struct platform_device *pdev)
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 
-	iounmap(sha_dd->io_base);
-
-	clk_put(sha_dd->iclk);
-
-	if (sha_dd->irq >= 0)
-		free_irq(sha_dd->irq, sha_dd);
+	clk_unprepare(sha_dd->iclk);
 
 	return 0;
 }
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index 0643e3366e33..c0656e7f37b5 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -306,7 +306,7 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa)
 		return -ENOMEM;
 
 	dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0);
-	if (!dma->cache_pool)
+	if (!dma->padding_pool)
 		return -ENOMEM;
 
 	cesa->dma = dma;
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index 848b93ee930f..fe9dce0245bf 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -500,6 +500,8 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	clk_set_min_rate(tegra->emc_clock, rate);
 	clk_set_rate(tegra->emc_clock, 0);
 
+	*freq = rate;
+
 	return 0;
 }
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index e893318560db..5ad0ec1f0e29 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -156,7 +156,6 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
-	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
 
 	dwc->initialized = true;
@@ -588,6 +587,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 
 		spin_unlock_irqrestore(&dwc->lock, flags);
 	}
+
+	/* Re-enable interrupts */
+	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 }
 
 /* ------------------------------------------------------------------------- */
@@ -618,11 +620,8 @@ static void dw_dma_tasklet(unsigned long data)
 			dwc_scan_descriptors(dw, dwc);
 	}
 
-	/*
-	 * Re-enable interrupts.
-	 */
+	/* Re-enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
 }
 
@@ -1261,6 +1260,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 int dw_dma_cyclic_start(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
 	unsigned long		flags;
 
 	if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) {
@@ -1269,7 +1269,12 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 	}
 
 	spin_lock_irqsave(&dwc->lock, flags);
+
+	/* Enable interrupts to perform cyclic transfer */
+	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
+
 	dwc_dostart(dwc, dwc->cdesc->desc[0]);
+
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 4c30fdd092b3..358f9689a3f5 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -108,6 +108,10 @@ static const struct pci_device_id dw_pci_id_table[] = {
 
 	/* Haswell */
 	{ PCI_VDEVICE(INTEL, 0x9c60) },
+
+	/* Broadwell */
+	{ PCI_VDEVICE(INTEL, 0x9ce0) },
+
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, dw_pci_id_table);
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index d92d65549406..e3d7fcb69b4c 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -113,6 +113,9 @@
 #define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
 #define CHMAP_EXIST		BIT(24)
 
+/* CCSTAT register */
+#define EDMA_CCSTAT_ACTV	BIT(4)
+
 /*
  * Max of 20 segments per channel to conserve PaRAM slots
  * Also note that MAX_NR_SG should be atleast the no.of periods
@@ -1680,9 +1683,20 @@ static void edma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 }
 
+/*
+ * This limit exists to avoid a possible infinite loop when waiting for proof
+ * that a particular transfer is completed. This limit can be hit if there
+ * are large bursts to/from slow devices or the CPU is never able to catch
+ * the DMA hardware idle. On an AM335x transfering 48 bytes from the UART
+ * RX-FIFO, as many as 55 loops have been seen.
+ */
+#define EDMA_MAX_TR_WAIT_LOOPS 1000
+
 static u32 edma_residue(struct edma_desc *edesc)
 {
 	bool dst = edesc->direction == DMA_DEV_TO_MEM;
+	int loop_count = EDMA_MAX_TR_WAIT_LOOPS;
+	struct edma_chan *echan = edesc->echan;
 	struct edma_pset *pset = edesc->pset;
 	dma_addr_t done, pos;
 	int i;
@@ -1691,7 +1705,32 @@ static u32 edma_residue(struct edma_desc *edesc)
 	 * We always read the dst/src position from the first RamPar
 	 * pset. That's the one which is active now.
 	 */
-	pos = edma_get_position(edesc->echan->ecc, edesc->echan->slot[0], dst);
+	pos = edma_get_position(echan->ecc, echan->slot[0], dst);
+
+	/*
+	 * "pos" may represent a transfer request that is still being
+	 * processed by the EDMACC or EDMATC. We will busy wait until
+	 * any one of the situations occurs:
+	 *   1. the DMA hardware is idle
+	 *   2. a new transfer request is setup
+	 *   3. we hit the loop limit
+	 */
+	while (edma_read(echan->ecc, EDMA_CCSTAT) & EDMA_CCSTAT_ACTV) {
+		/* check if a new transfer request is setup */
+		if (edma_get_position(echan->ecc,
+				      echan->slot[0], dst) != pos) {
+			break;
+		}
+
+		if (!--loop_count) {
+			dev_dbg_ratelimited(echan->vchan.chan.device->dev,
+				"%s: timeout waiting for PaRAM update\n",
+				__func__);
+			break;
+		}
+
+		cpu_relax();
+	}
 
 	/*
 	 * Cyclic is simple. Just subtract pset[0].addr from pos.
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1d5df2ef148b..21539d5c54c3 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -861,32 +861,42 @@ void ioat_timer_event(unsigned long data)
 			return;
 	}
 
+	spin_lock_bh(&ioat_chan->cleanup_lock);
+
+	/* handle the no-actives case */
+	if (!ioat_ring_active(ioat_chan)) {
+		spin_lock_bh(&ioat_chan->prep_lock);
+		check_active(ioat_chan);
+		spin_unlock_bh(&ioat_chan->prep_lock);
+		spin_unlock_bh(&ioat_chan->cleanup_lock);
+		return;
+	}
+
 	/* if we haven't made progress and we have already
 	 * acknowledged a pending completion once, then be more
 	 * forceful with a restart
 	 */
-	spin_lock_bh(&ioat_chan->cleanup_lock);
 	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
 		__cleanup(ioat_chan, phys_complete);
 	else if (test_bit(IOAT_COMPLETION_ACK, &ioat_chan->state)) {
+		u32 chanerr;
+
+		chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+		dev_warn(to_dev(ioat_chan), "Restarting channel...\n");
+		dev_warn(to_dev(ioat_chan), "CHANSTS: %#Lx CHANERR: %#x\n",
+			 status, chanerr);
+		dev_warn(to_dev(ioat_chan), "Active descriptors: %d\n",
+			 ioat_ring_active(ioat_chan));
+
 		spin_lock_bh(&ioat_chan->prep_lock);
 		ioat_restart_channel(ioat_chan);
 		spin_unlock_bh(&ioat_chan->prep_lock);
 		spin_unlock_bh(&ioat_chan->cleanup_lock);
 		return;
-	} else {
+	} else
 		set_bit(IOAT_COMPLETION_ACK, &ioat_chan->state);
-		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
-	}
-
 
-	if (ioat_ring_active(ioat_chan))
-		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
-	else {
-		spin_lock_bh(&ioat_chan->prep_lock);
-		check_active(ioat_chan);
-		spin_unlock_bh(&ioat_chan->prep_lock);
-	}
+	mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
 	spin_unlock_bh(&ioat_chan->cleanup_lock);
 }
 
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 756eca8c4cf8..10e6774ab2a2 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -221,7 +221,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(vendor, name, data, size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
@@ -447,7 +447,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(new_var->VendorGuid, name, data,
+			    size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
@@ -540,38 +541,30 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
 static int
 efivar_create_sysfs_entry(struct efivar_entry *new_var)
 {
-	int i, short_name_size;
+	int short_name_size;
 	char *short_name;
-	unsigned long variable_name_size;
-	efi_char16_t *variable_name;
+	unsigned long utf8_name_size;
+	efi_char16_t *variable_name = new_var->var.VariableName;
 	int ret;
 
-	variable_name = new_var->var.VariableName;
-	variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t);
-
 	/*
-	 * Length of the variable bytes in ASCII, plus the '-' separator,
+	 * Length of the variable bytes in UTF8, plus the '-' separator,
 	 * plus the GUID, plus trailing NUL
 	 */
-	short_name_size = variable_name_size / sizeof(efi_char16_t)
-				+ 1 + EFI_VARIABLE_GUID_LEN + 1;
-
-	short_name = kzalloc(short_name_size, GFP_KERNEL);
+	utf8_name_size = ucs2_utf8size(variable_name);
+	short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1;
 
+	short_name = kmalloc(short_name_size, GFP_KERNEL);
 	if (!short_name)
 		return -ENOMEM;
 
-	/* Convert Unicode to normal chars (assume top bits are 0),
-	   ala UTF-8 */
-	for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++) {
-		short_name[i] = variable_name[i] & 0xFF;
-	}
+	ucs2_as_utf8(short_name, variable_name, short_name_size);
+
 	/* This is ugly, but necessary to separate one vendor's
 	   private variables from another's.         */
-
-	*(short_name + strlen(short_name)) = '-';
+	short_name[utf8_name_size] = '-';
 	efi_guid_to_str(&new_var->var.VendorGuid,
-			 short_name + strlen(short_name));
+			 short_name + utf8_name_size + 1);
 
 	new_var->kobj.kset = efivars_kset;
 
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 70a0fb10517f..7f2ea21c730d 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -165,67 +165,133 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer,
 }
 
 struct variable_validate {
+	efi_guid_t vendor;
 	char *name;
 	bool (*validate)(efi_char16_t *var_name, int match, u8 *data,
 			 unsigned long len);
 };
 
+/*
+ * This is the list of variables we need to validate, as well as the
+ * whitelist for what we think is safe not to default to immutable.
+ *
+ * If it has a validate() method that's not NULL, it'll go into the
+ * validation routine.  If not, it is assumed valid, but still used for
+ * whitelisting.
+ *
+ * Note that it's sorted by {vendor,name}, but globbed names must come after
+ * any other name with the same prefix.
+ */
 static const struct variable_validate variable_validate[] = {
-	{ "BootNext", validate_uint16 },
-	{ "BootOrder", validate_boot_order },
-	{ "DriverOrder", validate_boot_order },
-	{ "Boot*", validate_load_option },
-	{ "Driver*", validate_load_option },
-	{ "ConIn", validate_device_path },
-	{ "ConInDev", validate_device_path },
-	{ "ConOut", validate_device_path },
-	{ "ConOutDev", validate_device_path },
-	{ "ErrOut", validate_device_path },
-	{ "ErrOutDev", validate_device_path },
-	{ "Timeout", validate_uint16 },
-	{ "Lang", validate_ascii_string },
-	{ "PlatformLang", validate_ascii_string },
-	{ "", NULL },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL },
+	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
+	{ LINUX_EFI_CRASH_GUID, "*", NULL },
+	{ NULL_GUID, "", NULL },
 };
 
+static bool
+variable_matches(const char *var_name, size_t len, const char *match_name,
+		 int *match)
+{
+	for (*match = 0; ; (*match)++) {
+		char c = match_name[*match];
+		char u = var_name[*match];
+
+		/* Wildcard in the matching name means we've matched */
+		if (c == '*')
+			return true;
+
+		/* Case sensitive match */
+		if (!c && *match == len)
+			return true;
+
+		if (c != u)
+			return false;
+
+		if (!c)
+			return true;
+	}
+	return true;
+}
+
 bool
-efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
+efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		unsigned long data_size)
 {
 	int i;
-	u16 *unicode_name = var_name;
+	unsigned long utf8_size;
+	u8 *utf8_name;
 
-	for (i = 0; variable_validate[i].validate != NULL; i++) {
-		const char *name = variable_validate[i].name;
-		int match;
+	utf8_size = ucs2_utf8size(var_name);
+	utf8_name = kmalloc(utf8_size + 1, GFP_KERNEL);
+	if (!utf8_name)
+		return false;
 
-		for (match = 0; ; match++) {
-			char c = name[match];
-			u16 u = unicode_name[match];
+	ucs2_as_utf8(utf8_name, var_name, utf8_size);
+	utf8_name[utf8_size] = '\0';
 
-			/* All special variables are plain ascii */
-			if (u > 127)
-				return true;
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
+		const char *name = variable_validate[i].name;
+		int match = 0;
 
-			/* Wildcard in the matching name means we've matched */
-			if (c == '*')
-				return variable_validate[i].validate(var_name,
-							     match, data, len);
+		if (efi_guidcmp(vendor, variable_validate[i].vendor))
+			continue;
 
-			/* Case sensitive match */
-			if (c != u)
+		if (variable_matches(utf8_name, utf8_size+1, name, &match)) {
+			if (variable_validate[i].validate == NULL)
 				break;
-
-			/* Reached the end of the string while matching */
-			if (!c)
-				return variable_validate[i].validate(var_name,
-							     match, data, len);
+			kfree(utf8_name);
+			return variable_validate[i].validate(var_name, match,
+							     data, data_size);
 		}
 	}
-
+	kfree(utf8_name);
 	return true;
 }
 EXPORT_SYMBOL_GPL(efivar_validate);
 
+bool
+efivar_variable_is_removable(efi_guid_t vendor, const char *var_name,
+			     size_t len)
+{
+	int i;
+	bool found = false;
+	int match = 0;
+
+	/*
+	 * Check if our variable is in the validated variables list
+	 */
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
+		if (efi_guidcmp(variable_validate[i].vendor, vendor))
+			continue;
+
+		if (variable_matches(var_name, len,
+				     variable_validate[i].name, &match)) {
+			found = true;
+			break;
+		}
+	}
+
+	/*
+	 * If it's in our list, it is removable.
+	 */
+	return found;
+}
+EXPORT_SYMBOL_GPL(efivar_variable_is_removable);
+
 static efi_status_t
 check_var_size(u32 attributes, unsigned long size)
 {
@@ -852,7 +918,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes,
 
 	*set = false;
 
-	if (efivar_validate(name, data, *size) == false)
+	if (efivar_validate(*vendor, name, data, *size) == false)
 		return -EINVAL;
 
 	/*
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 2aeaebd1c6e7..3f87a03abc22 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -312,8 +312,8 @@ static int altera_gpio_probe(struct platform_device *pdev)
 		handle_simple_irq, IRQ_TYPE_NONE);
 
 	if (ret) {
-		dev_info(&pdev->dev, "could not add irqchip\n");
-		return ret;
+		dev_err(&pdev->dev, "could not add irqchip\n");
+		goto teardown;
 	}
 
 	gpiochip_set_chained_irqchip(&altera_gc->mmchip.gc,
@@ -326,6 +326,7 @@ static int altera_gpio_probe(struct platform_device *pdev)
 skip_irq:
 	return 0;
 teardown:
+	of_mm_gpiochip_remove(&altera_gc->mmchip);
 	pr_err("%s: registration failed with status %d\n",
 		node->full_name, ret);
 
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index ec58f4288649..cd007a67b302 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -195,7 +195,7 @@ static int davinci_gpio_of_xlate(struct gpio_chip *gc,
 static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	int i, base;
-	unsigned ngpio;
+	unsigned ngpio, nbank;
 	struct davinci_gpio_controller *chips;
 	struct davinci_gpio_platform_data *pdata;
 	struct davinci_gpio_regs __iomem *regs;
@@ -224,8 +224,9 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (WARN_ON(ARCH_NR_GPIOS < ngpio))
 		ngpio = ARCH_NR_GPIOS;
 
+	nbank = DIV_ROUND_UP(ngpio, 32);
 	chips = devm_kzalloc(dev,
-			     ngpio * sizeof(struct davinci_gpio_controller),
+			     nbank * sizeof(struct davinci_gpio_controller),
 			     GFP_KERNEL);
 	if (!chips)
 		return -ENOMEM;
@@ -511,7 +512,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 			return irq;
 		}
 
-		irq_domain = irq_domain_add_legacy(NULL, ngpio, irq, 0,
+		irq_domain = irq_domain_add_legacy(dev->of_node, ngpio, irq, 0,
 							&davinci_gpio_irq_ops,
 							chips);
 		if (!irq_domain) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 82edf95b7740..5e7770f9a415 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -87,6 +87,8 @@ extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
 extern int amdgpu_enable_semaphores;
 extern int amdgpu_powerplay;
+extern unsigned amdgpu_pcie_gen_cap;
+extern unsigned amdgpu_pcie_lane_cap;
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -132,47 +134,6 @@ extern int amdgpu_powerplay;
 #define AMDGPU_RESET_VCE			(1 << 13)
 #define AMDGPU_RESET_VCE1			(1 << 14)
 
-/* CG block flags */
-#define AMDGPU_CG_BLOCK_GFX			(1 << 0)
-#define AMDGPU_CG_BLOCK_MC			(1 << 1)
-#define AMDGPU_CG_BLOCK_SDMA			(1 << 2)
-#define AMDGPU_CG_BLOCK_UVD			(1 << 3)
-#define AMDGPU_CG_BLOCK_VCE			(1 << 4)
-#define AMDGPU_CG_BLOCK_HDP			(1 << 5)
-#define AMDGPU_CG_BLOCK_BIF			(1 << 6)
-
-/* CG flags */
-#define AMDGPU_CG_SUPPORT_GFX_MGCG		(1 << 0)
-#define AMDGPU_CG_SUPPORT_GFX_MGLS		(1 << 1)
-#define AMDGPU_CG_SUPPORT_GFX_CGCG		(1 << 2)
-#define AMDGPU_CG_SUPPORT_GFX_CGLS		(1 << 3)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS		(1 << 4)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
-#define AMDGPU_CG_SUPPORT_GFX_CP_LS		(1 << 6)
-#define AMDGPU_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
-#define AMDGPU_CG_SUPPORT_MC_LS			(1 << 8)
-#define AMDGPU_CG_SUPPORT_MC_MGCG		(1 << 9)
-#define AMDGPU_CG_SUPPORT_SDMA_LS		(1 << 10)
-#define AMDGPU_CG_SUPPORT_SDMA_MGCG		(1 << 11)
-#define AMDGPU_CG_SUPPORT_BIF_LS		(1 << 12)
-#define AMDGPU_CG_SUPPORT_UVD_MGCG		(1 << 13)
-#define AMDGPU_CG_SUPPORT_VCE_MGCG		(1 << 14)
-#define AMDGPU_CG_SUPPORT_HDP_LS		(1 << 15)
-#define AMDGPU_CG_SUPPORT_HDP_MGCG		(1 << 16)
-
-/* PG flags */
-#define AMDGPU_PG_SUPPORT_GFX_PG		(1 << 0)
-#define AMDGPU_PG_SUPPORT_GFX_SMG		(1 << 1)
-#define AMDGPU_PG_SUPPORT_GFX_DMG		(1 << 2)
-#define AMDGPU_PG_SUPPORT_UVD			(1 << 3)
-#define AMDGPU_PG_SUPPORT_VCE			(1 << 4)
-#define AMDGPU_PG_SUPPORT_CP			(1 << 5)
-#define AMDGPU_PG_SUPPORT_GDS			(1 << 6)
-#define AMDGPU_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
-#define AMDGPU_PG_SUPPORT_SDMA			(1 << 8)
-#define AMDGPU_PG_SUPPORT_ACP			(1 << 9)
-#define AMDGPU_PG_SUPPORT_SAMU			(1 << 10)
-
 /* GFX current status */
 #define AMDGPU_GFX_NORMAL_MODE			0x00000000L
 #define AMDGPU_GFX_SAFE_MODE			0x00000001L
@@ -606,8 +567,6 @@ struct amdgpu_sa_manager {
 	uint32_t		align;
 };
 
-struct amdgpu_sa_bo;
-
 /* sub-allocation buffer */
 struct amdgpu_sa_bo {
 	struct list_head		olist;
@@ -2360,6 +2319,8 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 				     uint32_t flags);
 bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end);
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm);
 uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 				 struct ttm_mem_reg *mem);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index a081dda9fa2f..7a4b101e10c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -795,6 +795,12 @@ static int amdgpu_cgs_query_system_info(void *cgs_device,
 	case CGS_SYSTEM_INFO_PCIE_MLW:
 		sys_info->value = adev->pm.pcie_mlw_mask;
 		break;
+	case CGS_SYSTEM_INFO_CG_FLAGS:
+		sys_info->value = adev->cg_flags;
+		break;
+	case CGS_SYSTEM_INFO_PG_FLAGS:
+		sys_info->value = adev->pg_flags;
+		break;
 	default:
 		return -ENODEV;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 65531463f88e..51bfc114584e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1795,15 +1795,20 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	/* post card */
-	amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	if (!amdgpu_card_posted(adev))
+		amdgpu_atom_asic_init(adev->mode_info.atom_context);
 
 	r = amdgpu_resume(adev);
+	if (r)
+		DRM_ERROR("amdgpu_resume failed (%d).\n", r);
 
 	amdgpu_fence_driver_resume(adev);
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
+	if (resume) {
+		r = amdgpu_ib_ring_tests(adev);
+		if (r)
+			DRM_ERROR("ib ring test failed (%d).\n", r);
+	}
 
 	r = amdgpu_late_init(adev);
 	if (r)
@@ -1933,80 +1938,97 @@ retry:
 	return r;
 }
 
+#define AMDGPU_DEFAULT_PCIE_GEN_MASK 0x30007  /* gen: chipset 1/2, asic 1/2/3 */
+#define AMDGPU_DEFAULT_PCIE_MLW_MASK 0x2f0000 /* 1/2/4/8/16 lanes */
+
 void amdgpu_get_pcie_info(struct amdgpu_device *adev)
 {
 	u32 mask;
 	int ret;
 
-	if (pci_is_root_bus(adev->pdev->bus))
-		return;
+	if (amdgpu_pcie_gen_cap)
+		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
 
-	if (amdgpu_pcie_gen2 == 0)
-		return;
+	if (amdgpu_pcie_lane_cap)
+		adev->pm.pcie_mlw_mask = amdgpu_pcie_lane_cap;
 
-	if (adev->flags & AMD_IS_APU)
+	/* covers APUs as well */
+	if (pci_is_root_bus(adev->pdev->bus)) {
+		if (adev->pm.pcie_gen_mask == 0)
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		if (adev->pm.pcie_mlw_mask == 0)
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		return;
+	}
 
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (!ret) {
-		adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
-
-		if (mask & DRM_PCIE_SPEED_25)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
-		if (mask & DRM_PCIE_SPEED_50)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
-		if (mask & DRM_PCIE_SPEED_80)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
-	}
-	ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
-	if (!ret) {
-		switch (mask) {
-		case 32:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 16:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 12:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 8:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 4:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 2:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 1:
-			adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
-			break;
-		default:
-			break;
+	if (adev->pm.pcie_gen_mask == 0) {
+		ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
+		if (!ret) {
+			adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
+
+			if (mask & DRM_PCIE_SPEED_25)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
+			if (mask & DRM_PCIE_SPEED_50)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
+			if (mask & DRM_PCIE_SPEED_80)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
+		} else {
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		}
+	}
+	if (adev->pm.pcie_mlw_mask == 0) {
+		ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
+		if (!ret) {
+			switch (mask) {
+			case 32:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 16:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 12:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 8:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 4:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 2:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 1:
+				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
+				break;
+			default:
+				break;
+			}
+		} else {
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index acd066d0a805..8297bc319369 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 
 	struct drm_crtc *crtc = &amdgpuCrtc->base;
 	unsigned long flags;
-	unsigned i;
-	int vpos, hpos, stat, min_udelay;
+	unsigned i, repcnt = 4;
+	int vpos, hpos, stat, min_udelay = 0;
 	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
 	amdgpu_flip_wait_fence(adev, &work->excl);
@@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 	 * In practice this won't execute very often unless on very fast
 	 * machines because the time window for this to happen is very small.
 	 */
-	for (;;) {
+	while (amdgpuCrtc->enabled && repcnt--) {
 		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
 		 * start in hpos, and to the "fudged earlier" vblank start in
 		 * vpos.
@@ -114,10 +114,22 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 		/* Sleep at least until estimated real start of hw vblank */
 		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		if (min_udelay > vblank->framedur_ns / 2000) {
+			/* Don't wait ridiculously long - something is wrong */
+			repcnt = 0;
+			break;
+		}
 		usleep_range(min_udelay, 2 * min_udelay);
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 	};
 
+	if (!repcnt)
+		DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, "
+				 "framedur %d, linedur %d, stat %d, vpos %d, "
+				 "hpos %d\n", work->crtc_id, min_udelay,
+				 vblank->framedur_ns / 1000,
+				 vblank->linedur_ns / 1000, stat, vpos, hpos);
+
 	/* do the flip (mmio) */
 	adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base);
 	/* set the flip status */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 9c1af8976bef..9ef1db87cf26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -83,6 +83,8 @@ int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
 int amdgpu_enable_semaphores = 0;
 int amdgpu_powerplay = -1;
+unsigned amdgpu_pcie_gen_cap = 0;
+unsigned amdgpu_pcie_lane_cap = 0;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -170,6 +172,12 @@ MODULE_PARM_DESC(powerplay, "Powerplay component (1 = enable, 0 = disable, -1 =
 module_param_named(powerplay, amdgpu_powerplay, int, 0444);
 #endif
 
+MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
+module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
+
+MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
+module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
+
 static struct pci_device_id pciidlist[] = {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 7380f782cd14..d20c2a8929cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -596,7 +596,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	ttm_eu_backoff_reservation(&ticket, &list);
-	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
+	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) &&
+	    !amdgpu_vm_debug)
 		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
 
 	drm_gem_object_unreference_unlocked(gobj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index b1969f2b2038..d4e2780c0796 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -142,7 +142,8 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
 
 		list_for_each_entry(bo, &node->bos, mn_list) {
 
-			if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+			if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start,
+							  end))
 				continue;
 
 			r = amdgpu_bo_reserve(bo, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 7d8d84eaea4a..66855b62a603 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -113,6 +113,10 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return snprintf(buf, PAGE_SIZE, "off\n");
+
 	if (adev->pp_enabled) {
 		enum amd_dpm_forced_level level;
 
@@ -140,6 +144,11 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	enum amdgpu_dpm_forced_level level;
 	int ret = 0;
 
+	/* Can't force performance level when the card is off */
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	if (strncmp("low", buf, strlen("low")) == 0) {
 		level = AMDGPU_DPM_FORCED_LEVEL_LOW;
 	} else if (strncmp("high", buf, strlen("high")) == 0) {
@@ -157,6 +166,7 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 		mutex_lock(&adev->pm.mutex);
 		if (adev->pm.dpm.thermal_active) {
 			count = -EINVAL;
+			mutex_unlock(&adev->pm.mutex);
 			goto fail;
 		}
 		ret = amdgpu_dpm_force_performance_level(adev, level);
@@ -167,8 +177,6 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 		mutex_unlock(&adev->pm.mutex);
 	}
 fail:
-	mutex_unlock(&adev->pm.mutex);
-
 	return count;
 }
 
@@ -182,8 +190,14 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	struct drm_device *ddev = adev->ddev;
 	int temp;
 
+	/* Can't get temperature when the card is off */
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	if (!adev->pp_enabled && !adev->pm.funcs->get_temperature)
 		temp = 0;
 	else
@@ -634,8 +648,6 @@ force:
 
 	/* update display watermarks based on new power state */
 	amdgpu_display_bandwidth_update(adev);
-	/* update displays */
-	amdgpu_dpm_display_configuration_changed(adev);
 
 	adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs;
 	adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count;
@@ -655,6 +667,9 @@ force:
 
 	amdgpu_dpm_post_set_power_state(adev);
 
+	/* update displays */
+	amdgpu_dpm_display_configuration_changed(adev);
+
 	if (adev->pm.funcs->force_performance_level) {
 		if (adev->pm.dpm.thermal_active) {
 			enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level;
@@ -847,12 +862,16 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	struct drm_device *ddev = adev->ddev;
 
 	if (!adev->pm.dpm_enabled) {
 		seq_printf(m, "dpm not enabled\n");
 		return 0;
 	}
-	if (adev->pp_enabled) {
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
+		seq_printf(m, "PX asic powered off\n");
+	} else if (adev->pp_enabled) {
 		amdgpu_dpm_debugfs_print_current_performance_level(adev, m);
 	} else {
 		mutex_lock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 8b88edb0434b..ca72a2e487b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -354,12 +354,15 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 
 		for (i = 0, count = 0; i < AMDGPU_MAX_RINGS; ++i)
 			if (fences[i])
-				fences[count++] = fences[i];
+				fences[count++] = fence_get(fences[i]);
 
 		if (count) {
 			spin_unlock(&sa_manager->wq.lock);
 			t = fence_wait_any_timeout(fences, count, false,
 						   MAX_SCHEDULE_TIMEOUT);
+			for (i = 0; i < count; ++i)
+				fence_put(fences[i]);
+
 			r = (t > 0) ? 0 : t;
 			spin_lock(&sa_manager->wq.lock);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 55cf05e1c81c..1cbb16e15307 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -712,7 +712,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm)
 						       0, PAGE_SIZE,
 						       PCI_DMA_BIDIRECTIONAL);
 		if (pci_dma_mapping_error(adev->pdev, gtt->ttm.dma_address[i])) {
-			while (--i) {
+			while (i--) {
 				pci_unmap_page(adev->pdev, gtt->ttm.dma_address[i],
 					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 				gtt->ttm.dma_address[i] = 0;
@@ -783,6 +783,25 @@ bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm)
 	return !!gtt->userptr;
 }
 
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end)
+{
+	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	unsigned long size;
+
+	if (gtt == NULL)
+		return false;
+
+	if (gtt->ttm.ttm.state != tt_bound || !gtt->userptr)
+		return false;
+
+	size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE;
+	if (gtt->userptr > end || gtt->userptr + size <= start)
+		return false;
+
+	return true;
+}
+
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 8b4731d4e10e..474ca02b0949 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -31,6 +31,7 @@
 #include "ci_dpm.h"
 #include "gfx_v7_0.h"
 #include "atom.h"
+#include "amd_pcie.h"
 #include <linux/seq_file.h>
 
 #include "smu/smu_7_0_1_d.h"
@@ -5835,18 +5836,16 @@ static int ci_dpm_init(struct amdgpu_device *adev)
 	u8 frev, crev;
 	struct ci_power_info *pi;
 	int ret;
-	u32 mask;
 
 	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
 	if (pi == NULL)
 		return -ENOMEM;
 	adev->pm.dpm.priv = pi;
 
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (ret)
-		pi->sys_pcie_mask = 0;
-	else
-		pi->sys_pcie_mask = mask;
+	pi->sys_pcie_mask =
+		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
+		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+
 	pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 
 	pi->pcie_gen_performance.max = AMDGPU_PCIE_GEN1;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index fd9c9588ef46..155965ed14a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1762,6 +1762,9 @@ static void cik_program_aspm(struct amdgpu_device *adev)
 	if (amdgpu_aspm == 0)
 		return;
 
+	if (pci_is_root_bus(adev->pdev->bus))
+		return;
+
 	/* XXX double check APUs */
 	if (adev->flags & AMD_IS_APU)
 		return;
@@ -2332,72 +2335,72 @@ static int cik_common_early_init(void *handle)
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x14;
 		break;
 	case CHIP_HAWAII:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = 0x28;
 		break;
 	case CHIP_KAVERI:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG |
-			  AMDGPU_PG_SUPPORT_GFX_DMG |*/
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_ACP |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG |
+			  AMD_PG_SUPPORT_GFX_DMG |*/
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_ACP |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->pdev->device == 0x1312 ||
 			adev->pdev->device == 0x1316 ||
@@ -2409,29 +2412,29 @@ static int cik_common_early_init(void *handle)
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG | */
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG | */
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->asic_type == CHIP_KABINI) {
 			if (adev->rev_id == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 5f712ceddf08..c55ecf0ea845 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -885,7 +885,7 @@ static void cik_enable_sdma_mgcg(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG)) {
 		WREG32(mmSDMA0_CLK_CTRL + SDMA0_REGISTER_OFFSET, 0x00000100);
 		WREG32(mmSDMA0_CLK_CTRL + SDMA1_REGISTER_OFFSET, 0x00000100);
 	} else {
@@ -906,7 +906,7 @@ static void cik_enable_sdma_mgls(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS)) {
 		orig = data = RREG32(mmSDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET);
 		data |= 0x100;
 		if (orig != data)
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index 4dd17f2dd905..9056355309d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -445,13 +445,13 @@ static int cz_dpm_init(struct amdgpu_device *adev)
 	pi->gfx_pg_threshold = 500;
 	pi->caps_fps = true;
 	/* uvd */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
 	/* vce */
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
 	pi->caps_vce_dpm = true;
 	/* acp */
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_acp_dpm = true;
 
 	pi->caps_stable_power_state = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 6c76139de1c9..7732059ae30f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4109,7 +4109,7 @@ static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)
 
 	orig = data = RREG32(mmRLC_CGCG_CGLS_CTRL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) {
 		gfx_v7_0_enable_gui_idle_interrupt(adev, true);
 
 		tmp = gfx_v7_0_halt_rlc(adev);
@@ -4147,9 +4147,9 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 {
 	u32 data, orig, tmp = 0;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGCG)) {
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) {
-			if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CP_LS) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) {
+			if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CP_LS) {
 				orig = data = RREG32(mmCP_MEM_SLP_CNTL);
 				data |= CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
 				if (orig != data)
@@ -4176,14 +4176,14 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 
 		gfx_v7_0_update_rlc(adev, tmp);
 
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS) {
 			orig = data = RREG32(mmCGTS_SM_CTRL_REG);
 			data &= ~CGTS_SM_CTRL_REG__SM_MODE_MASK;
 			data |= (0x2 << CGTS_SM_CTRL_REG__SM_MODE__SHIFT);
 			data |= CGTS_SM_CTRL_REG__SM_MODE_ENABLE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__OVERRIDE_MASK;
-			if ((adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) &&
-			    (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS_LS))
+			if ((adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) &&
+			    (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS_LS))
 				data &= ~CGTS_SM_CTRL_REG__LS_OVERRIDE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__ON_MONITOR_ADD_MASK;
 			data |= CGTS_SM_CTRL_REG__ON_MONITOR_ADD_EN_MASK;
@@ -4249,7 +4249,7 @@ static void gfx_v7_0_enable_sclk_slowdown_on_pu(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
@@ -4263,7 +4263,7 @@ static void gfx_v7_0_enable_sclk_slowdown_on_pd(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
@@ -4276,7 +4276,7 @@ static void gfx_v7_0_enable_cp_pg(struct amdgpu_device *adev, bool enable)
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_CP))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_CP))
 		data &= ~0x8000;
 	else
 		data |= 0x8000;
@@ -4289,7 +4289,7 @@ static void gfx_v7_0_enable_gds_pg(struct amdgpu_device *adev, bool enable)
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GDS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GDS))
 		data &= ~0x2000;
 	else
 		data |= 0x2000;
@@ -4370,7 +4370,7 @@ static void gfx_v7_0_enable_gfx_cgpg(struct amdgpu_device *adev,
 {
 	u32 data, orig;
 
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG)) {
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
 		orig = data = RREG32(mmRLC_PG_CNTL);
 		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
 		if (orig != data)
@@ -4442,7 +4442,7 @@ static void gfx_v7_0_enable_gfx_static_mgpg(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_SMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG))
 		data |= RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
@@ -4456,7 +4456,7 @@ static void gfx_v7_0_enable_gfx_dynamic_mgpg(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_DMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG))
 		data |= RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
@@ -4623,15 +4623,15 @@ static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev,
 
 static void gfx_v7_0_init_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_enable_sclk_slowdown_on_pu(adev, true);
 		gfx_v7_0_enable_sclk_slowdown_on_pd(adev, true);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_init_gfx_cgpg(adev);
 			gfx_v7_0_enable_cp_pg(adev, true);
 			gfx_v7_0_enable_gds_pg(adev, true);
@@ -4643,14 +4643,14 @@ static void gfx_v7_0_init_pg(struct amdgpu_device *adev)
 
 static void gfx_v7_0_fini_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, false);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, false);
 			gfx_v7_0_enable_gds_pg(adev, false);
 		}
@@ -5527,14 +5527,14 @@ static int gfx_v7_0_set_powergating_state(void *handle,
 	if (state == AMD_PG_STATE_GATE)
 		gate = true;
 
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, gate);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, gate);
 			gfx_v7_0_enable_gds_pg(adev, gate);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 8f8ec37ecd88..1c40bd90afbb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4995,7 +4995,7 @@ static int gfx_v8_0_set_priv_reg_fault_state(struct amdgpu_device *adev,
 	case AMDGPU_IRQ_STATE_ENABLE:
 		cp_int_cntl = RREG32(mmCP_INT_CNTL_RING0);
 		cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
-					    PRIV_REG_INT_ENABLE, 0);
+					    PRIV_REG_INT_ENABLE, 1);
 		WREG32(mmCP_INT_CNTL_RING0, cp_int_cntl);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 8aa2991ab379..b8060795b27b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -792,7 +792,7 @@ static void gmc_v7_0_enable_mc_ls(struct amdgpu_device *adev,
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_LS))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
 			data |= mc_cg_ls_en[i];
 		else
 			data &= ~mc_cg_ls_en[i];
@@ -809,7 +809,7 @@ static void gmc_v7_0_enable_mc_mgcg(struct amdgpu_device *adev,
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_MGCG))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
 			data |= mc_cg_en[i];
 		else
 			data &= ~mc_cg_en[i];
@@ -825,7 +825,7 @@ static void gmc_v7_0_enable_bif_mgls(struct amdgpu_device *adev,
 
 	orig = data = RREG32_PCIE(ixPCIE_CNTL2);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_BIF_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) {
 		data = REG_SET_FIELD(data, PCIE_CNTL2, SLV_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, MST_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, REPLAY_MEM_LS_EN, 1);
@@ -848,7 +848,7 @@ static void gmc_v7_0_enable_hdp_mgcg(struct amdgpu_device *adev,
 
 	orig = data = RREG32(mmHDP_HOST_PATH_CNTL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_MGCG))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG))
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 0);
 	else
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 1);
@@ -864,7 +864,7 @@ static void gmc_v7_0_enable_hdp_ls(struct amdgpu_device *adev,
 
 	orig = data = RREG32(mmHDP_MEM_POWER_LS);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_LS))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 1);
 	else
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 7e9154c7f1db..654d76723bc3 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -2859,11 +2859,11 @@ static int kv_dpm_init(struct amdgpu_device *adev)
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
-	pi->caps_samu_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_SAMU) ? true : false;
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_samu_pg = (adev->pg_flags & AMD_PG_SUPPORT_SAMU) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_stable_p_state = false;
 
 	ret = kv_parse_sys_info_table(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 5e9f73af83a8..fbd3767671bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -611,7 +611,7 @@ static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) {
 		data = RREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL);
 		data = 0xfff;
 		WREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL, data);
@@ -830,6 +830,9 @@ static int uvd_v4_2_set_clockgating_state(void *handle,
 	bool gate = false;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	if (state == AMD_CG_STATE_GATE)
 		gate = true;
 
@@ -848,7 +851,10 @@ static int uvd_v4_2_set_powergating_state(void *handle,
 	 * revisit this when there is a cleaner line between
 	 * the smc and the hw blocks
 	 */
-	 struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
 
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v4_2_stop(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 38864f562981..57f1c5bf3bf1 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -774,6 +774,11 @@ static int uvd_v5_0_process_interrupt(struct amdgpu_device *adev,
 static int uvd_v5_0_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	return 0;
 }
 
@@ -789,6 +794,9 @@ static int uvd_v5_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v5_0_stop(adev);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 3d5913926436..0b365b7651ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -532,7 +532,7 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	uvd_v6_0_mc_resume(adev);
 
 	/* Set dynamic clock gating in S/W control mode */
-	if (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG) {
+	if (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG) {
 		if (adev->flags & AMD_IS_APU)
 			cz_set_uvd_clock_gating_branches(adev, false);
 		else
@@ -1000,7 +1000,7 @@ static int uvd_v6_0_set_clockgating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
 		return 0;
 
 	if (enable) {
@@ -1030,6 +1030,9 @@ static int uvd_v6_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v6_0_stop(adev);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 52ac7a8f1e58..a822edacfa95 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -373,7 +373,7 @@ static void vce_v2_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 {
 	bool sw_cg = false;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) {
 		if (sw_cg)
 			vce_v2_0_set_sw_cg(adev, true);
 		else
@@ -608,6 +608,9 @@ static int vce_v2_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v2_0_stop()? */
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index e99af81e4aec..d662fa9f9091 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -277,7 +277,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 		WREG32_P(mmVCE_STATUS, 0, ~1);
 
 		/* Set Clock-Gating off */
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)
+		if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)
 			vce_v3_0_set_vce_sw_clock_gating(adev, false);
 
 		if (r) {
@@ -676,7 +676,7 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 	int i;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG))
 		return 0;
 
 	mutex_lock(&adev->grbm_idx_mutex);
@@ -728,6 +728,9 @@ static int vce_v3_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v3_0_stop()? */
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 89f5a1ff6f43..0d14d108a6c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1457,8 +1457,7 @@ static int vi_common_early_init(void *handle)
 	case CHIP_STONEY:
 		adev->has_uvd = true;
 		adev->cg_flags = 0;
-		/* Disable UVD pg */
-		adev->pg_flags = /* AMDGPU_PG_SUPPORT_UVD | */AMDGPU_PG_SUPPORT_VCE;
+		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 1195d06f55bc..dbf7e6413cab 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -85,6 +85,38 @@ enum amd_powergating_state {
 	AMD_PG_STATE_UNGATE,
 };
 
+/* CG flags */
+#define AMD_CG_SUPPORT_GFX_MGCG			(1 << 0)
+#define AMD_CG_SUPPORT_GFX_MGLS			(1 << 1)
+#define AMD_CG_SUPPORT_GFX_CGCG			(1 << 2)
+#define AMD_CG_SUPPORT_GFX_CGLS			(1 << 3)
+#define AMD_CG_SUPPORT_GFX_CGTS			(1 << 4)
+#define AMD_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
+#define AMD_CG_SUPPORT_GFX_CP_LS		(1 << 6)
+#define AMD_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
+#define AMD_CG_SUPPORT_MC_LS			(1 << 8)
+#define AMD_CG_SUPPORT_MC_MGCG			(1 << 9)
+#define AMD_CG_SUPPORT_SDMA_LS			(1 << 10)
+#define AMD_CG_SUPPORT_SDMA_MGCG		(1 << 11)
+#define AMD_CG_SUPPORT_BIF_LS			(1 << 12)
+#define AMD_CG_SUPPORT_UVD_MGCG			(1 << 13)
+#define AMD_CG_SUPPORT_VCE_MGCG			(1 << 14)
+#define AMD_CG_SUPPORT_HDP_LS			(1 << 15)
+#define AMD_CG_SUPPORT_HDP_MGCG			(1 << 16)
+
+/* PG flags */
+#define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
+#define AMD_PG_SUPPORT_GFX_SMG			(1 << 1)
+#define AMD_PG_SUPPORT_GFX_DMG			(1 << 2)
+#define AMD_PG_SUPPORT_UVD			(1 << 3)
+#define AMD_PG_SUPPORT_VCE			(1 << 4)
+#define AMD_PG_SUPPORT_CP			(1 << 5)
+#define AMD_PG_SUPPORT_GDS			(1 << 6)
+#define AMD_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
+#define AMD_PG_SUPPORT_SDMA			(1 << 8)
+#define AMD_PG_SUPPORT_ACP			(1 << 9)
+#define AMD_PG_SUPPORT_SAMU			(1 << 10)
+
 enum amd_pm_state_type {
 	/* not used for dpm */
 	POWER_STATE_TYPE_DEFAULT,
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index 713aec954692..aec38fc3834f 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -109,6 +109,8 @@ enum cgs_system_info_id {
 	CGS_SYSTEM_INFO_ADAPTER_BDF_ID = 1,
 	CGS_SYSTEM_INFO_PCIE_GEN_INFO,
 	CGS_SYSTEM_INFO_PCIE_MLW,
+	CGS_SYSTEM_INFO_CG_FLAGS,
+	CGS_SYSTEM_INFO_PG_FLAGS,
 	CGS_SYSTEM_INFO_ID_MAXIMUM,
 };
 
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
index 52a3efc97f05..46410e3c7349 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
@@ -31,7 +31,7 @@
 static int pem_init(struct pp_eventmgr *eventmgr)
 {
 	int result = 0;
-	struct pem_event_data event_data;
+	struct pem_event_data event_data = { {0} };
 
 	/* Initialize PowerPlay feature info */
 	pem_init_feature_info(eventmgr);
@@ -52,7 +52,7 @@ static int pem_init(struct pp_eventmgr *eventmgr)
 
 static void pem_fini(struct pp_eventmgr *eventmgr)
 {
-	struct pem_event_data event_data;
+	struct pem_event_data event_data = { {0} };
 
 	pem_uninit_featureInfo(eventmgr);
 	pem_unregister_interrupts(eventmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 0874ab42ee95..cf01177ca3b5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -174,6 +174,8 @@ static int cz_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 {
 	struct cz_hwmgr *cz_hwmgr = (struct cz_hwmgr *)(hwmgr->backend);
 	uint32_t i;
+	struct cgs_system_info sys_info = {0};
+	int result;
 
 	cz_hwmgr->gfx_ramp_step = 256*25/100;
 
@@ -247,6 +249,22 @@ static int cz_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 				   PHM_PlatformCaps_DisableVoltageIsland);
 
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 44a925006479..980d3bf8ea76 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -4451,6 +4451,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	pp_atomctrl_gpio_pin_assignment gpio_pin_assignment;
 	struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable);
 	phw_tonga_ulv_parm *ulv;
+	struct cgs_system_info sys_info = {0};
 
 	PP_ASSERT_WITH_CODE((NULL != hwmgr),
 		"Invalid Parameter!", return -1;);
@@ -4615,9 +4616,23 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 
 	data->vddc_phase_shed_control = 0;
 
-	if (0 == result) {
-		struct cgs_system_info sys_info = {0};
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
 
+	if (0 == result) {
 		data->is_tlu_enabled = 0;
 		hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
 			TONGA_MAX_HARDWARE_POWERLEVELS;
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 3f74193885f1..9a7b44616b55 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -65,8 +65,6 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state)
 	 */
 	state->allow_modeset = true;
 
-	state->num_connector = ACCESS_ONCE(dev->mode_config.num_connector);
-
 	state->crtcs = kcalloc(dev->mode_config.num_crtc,
 			       sizeof(*state->crtcs), GFP_KERNEL);
 	if (!state->crtcs)
@@ -83,16 +81,6 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state)
 				      sizeof(*state->plane_states), GFP_KERNEL);
 	if (!state->plane_states)
 		goto fail;
-	state->connectors = kcalloc(state->num_connector,
-				    sizeof(*state->connectors),
-				    GFP_KERNEL);
-	if (!state->connectors)
-		goto fail;
-	state->connector_states = kcalloc(state->num_connector,
-					  sizeof(*state->connector_states),
-					  GFP_KERNEL);
-	if (!state->connector_states)
-		goto fail;
 
 	state->dev = dev;
 
@@ -823,19 +811,27 @@ drm_atomic_get_connector_state(struct drm_atomic_state *state,
 
 	index = drm_connector_index(connector);
 
-	/*
-	 * Construction of atomic state updates can race with a connector
-	 * hot-add which might overflow. In this case flip the table and just
-	 * restart the entire ioctl - no one is fast enough to livelock a cpu
-	 * with physical hotplug events anyway.
-	 *
-	 * Note that we only grab the indexes once we have the right lock to
-	 * prevent hotplug/unplugging of connectors. So removal is no problem,
-	 * at most the array is a bit too large.
-	 */
 	if (index >= state->num_connector) {
-		DRM_DEBUG_ATOMIC("Hot-added connector would overflow state array, restarting\n");
-		return ERR_PTR(-EAGAIN);
+		struct drm_connector **c;
+		struct drm_connector_state **cs;
+		int alloc = max(index + 1, config->num_connector);
+
+		c = krealloc(state->connectors, alloc * sizeof(*state->connectors), GFP_KERNEL);
+		if (!c)
+			return ERR_PTR(-ENOMEM);
+
+		state->connectors = c;
+		memset(&state->connectors[state->num_connector], 0,
+		       sizeof(*state->connectors) * (alloc - state->num_connector));
+
+		cs = krealloc(state->connector_states, alloc * sizeof(*state->connector_states), GFP_KERNEL);
+		if (!cs)
+			return ERR_PTR(-ENOMEM);
+
+		state->connector_states = cs;
+		memset(&state->connector_states[state->num_connector], 0,
+		       sizeof(*state->connector_states) * (alloc - state->num_connector));
+		state->num_connector = alloc;
 	}
 
 	if (state->connector_states[index])
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 7c523060a076..4f2d3e161593 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1493,7 +1493,7 @@ void drm_atomic_helper_swap_state(struct drm_device *dev,
 {
 	int i;
 
-	for (i = 0; i < dev->mode_config.num_connector; i++) {
+	for (i = 0; i < state->num_connector; i++) {
 		struct drm_connector *connector = state->connectors[i];
 
 		if (!connector)
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index d40bab29747e..f6191215b2cb 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -918,12 +918,19 @@ int drm_connector_init(struct drm_device *dev,
 	connector->base.properties = &connector->properties;
 	connector->dev = dev;
 	connector->funcs = funcs;
+
+	connector->connector_id = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL);
+	if (connector->connector_id < 0) {
+		ret = connector->connector_id;
+		goto out_put;
+	}
+
 	connector->connector_type = connector_type;
 	connector->connector_type_id =
 		ida_simple_get(connector_ida, 1, 0, GFP_KERNEL);
 	if (connector->connector_type_id < 0) {
 		ret = connector->connector_type_id;
-		goto out_put;
+		goto out_put_id;
 	}
 	connector->name =
 		kasprintf(GFP_KERNEL, "%s-%d",
@@ -931,7 +938,7 @@ int drm_connector_init(struct drm_device *dev,
 			  connector->connector_type_id);
 	if (!connector->name) {
 		ret = -ENOMEM;
-		goto out_put;
+		goto out_put_type_id;
 	}
 
 	INIT_LIST_HEAD(&connector->probed_modes);
@@ -959,7 +966,12 @@ int drm_connector_init(struct drm_device *dev,
 	}
 
 	connector->debugfs_entry = NULL;
-
+out_put_type_id:
+	if (ret)
+		ida_remove(connector_ida, connector->connector_type_id);
+out_put_id:
+	if (ret)
+		ida_remove(&config->connector_ida, connector->connector_id);
 out_put:
 	if (ret)
 		drm_mode_object_put(dev, &connector->base);
@@ -996,6 +1008,9 @@ void drm_connector_cleanup(struct drm_connector *connector)
 	ida_remove(&drm_connector_enum_list[connector->connector_type].ida,
 		   connector->connector_type_id);
 
+	ida_remove(&dev->mode_config.connector_ida,
+		   connector->connector_id);
+
 	kfree(connector->display_info.bus_formats);
 	drm_mode_object_put(dev, &connector->base);
 	kfree(connector->name);
@@ -1013,32 +1028,6 @@ void drm_connector_cleanup(struct drm_connector *connector)
 EXPORT_SYMBOL(drm_connector_cleanup);
 
 /**
- * drm_connector_index - find the index of a registered connector
- * @connector: connector to find index for
- *
- * Given a registered connector, return the index of that connector within a DRM
- * device's list of connectors.
- */
-unsigned int drm_connector_index(struct drm_connector *connector)
-{
-	unsigned int index = 0;
-	struct drm_connector *tmp;
-	struct drm_mode_config *config = &connector->dev->mode_config;
-
-	WARN_ON(!drm_modeset_is_locked(&config->connection_mutex));
-
-	drm_for_each_connector(tmp, connector->dev) {
-		if (tmp == connector)
-			return index;
-
-		index++;
-	}
-
-	BUG();
-}
-EXPORT_SYMBOL(drm_connector_index);
-
-/**
  * drm_connector_register - register a connector
  * @connector: the connector to register
  *
@@ -5789,6 +5778,7 @@ void drm_mode_config_init(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev->mode_config.plane_list);
 	idr_init(&dev->mode_config.crtc_idr);
 	idr_init(&dev->mode_config.tile_idr);
+	ida_init(&dev->mode_config.connector_ida);
 
 	drm_modeset_lock_all(dev);
 	drm_mode_create_standard_properties(dev);
@@ -5869,6 +5859,7 @@ void drm_mode_config_cleanup(struct drm_device *dev)
 		crtc->funcs->destroy(crtc);
 	}
 
+	ida_destroy(&dev->mode_config.connector_ida);
 	idr_destroy(&dev->mode_config.tile_idr);
 	idr_destroy(&dev->mode_config.crtc_idr);
 	drm_modeset_lock_fini(&dev->mode_config.connection_mutex);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 8ae13de272c4..27fbd79d0daf 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1159,11 +1159,13 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 			drm_dp_put_port(port);
 			goto out;
 		}
-
-		drm_mode_connector_set_tile_property(port->connector);
-
+		if (port->port_num >= DP_MST_LOGICAL_PORT_0) {
+			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
+			drm_mode_connector_set_tile_property(port->connector);
+		}
 		(*mstb->mgr->cbs->register_connector)(port->connector);
 	}
+
 out:
 	/* put reference to this port */
 	drm_dp_put_port(port);
@@ -1188,8 +1190,8 @@ static void drm_dp_update_port(struct drm_dp_mst_branch *mstb,
 	port->ddps = conn_stat->displayport_device_plug_status;
 
 	if (old_ddps != port->ddps) {
-		dowork = true;
 		if (port->ddps) {
+			dowork = true;
 		} else {
 			port->available_pbn = 0;
 		}
@@ -1294,13 +1296,8 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m
 		if (port->input)
 			continue;
 
-		if (!port->ddps) {
-			if (port->cached_edid) {
-				kfree(port->cached_edid);
-				port->cached_edid = NULL;
-			}
+		if (!port->ddps)
 			continue;
-		}
 
 		if (!port->available_pbn)
 			drm_dp_send_enum_path_resources(mgr, mstb, port);
@@ -1311,12 +1308,6 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m
 				drm_dp_check_and_send_link_address(mgr, mstb_child);
 				drm_dp_put_mst_branch_device(mstb_child);
 			}
-		} else if (port->pdt == DP_PEER_DEVICE_SST_SINK ||
-			port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV) {
-			if (!port->cached_edid) {
-				port->cached_edid =
-					drm_get_edid(port->connector, &port->aux.ddc);
-			}
 		}
 	}
 }
@@ -1336,8 +1327,6 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work)
 		drm_dp_check_and_send_link_address(mgr, mstb);
 		drm_dp_put_mst_branch_device(mstb);
 	}
-
-	(*mgr->cbs->hotplug)(mgr);
 }
 
 static bool drm_dp_validate_guid(struct drm_dp_mst_topology_mgr *mgr,
@@ -1597,6 +1586,7 @@ static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
 			for (i = 0; i < txmsg->reply.u.link_addr.nports; i++) {
 				drm_dp_add_port(mstb, mgr->dev, &txmsg->reply.u.link_addr.ports[i]);
 			}
+			(*mgr->cbs->hotplug)(mgr);
 		}
 	} else {
 		mstb->link_address_sent = false;
@@ -2293,6 +2283,8 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 			drm_dp_update_port(mstb, &msg.u.conn_stat);
 
 			DRM_DEBUG_KMS("Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", msg.u.conn_stat.port_number, msg.u.conn_stat.legacy_device_plug_status, msg.u.conn_stat.displayport_device_plug_status, msg.u.conn_stat.message_capability_status, msg.u.conn_stat.input_port, msg.u.conn_stat.peer_device_type);
+			(*mgr->cbs->hotplug)(mgr);
+
 		} else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY) {
 			drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false);
 			if (!mstb)
@@ -2379,6 +2371,10 @@ enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector
 
 	case DP_PEER_DEVICE_SST_SINK:
 		status = connector_status_connected;
+		/* for logical ports - cache the EDID */
+		if (port->port_num >= 8 && !port->cached_edid) {
+			port->cached_edid = drm_get_edid(connector, &port->aux.ddc);
+		}
 		break;
 	case DP_PEER_DEVICE_DP_LEGACY_CONV:
 		if (port->ldps)
@@ -2433,7 +2429,10 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_
 
 	if (port->cached_edid)
 		edid = drm_edid_duplicate(port->cached_edid);
-
+	else {
+		edid = drm_get_edid(connector, &port->aux.ddc);
+		drm_mode_connector_set_tile_property(connector);
+	}
 	port->has_audio = drm_detect_monitor_audio(edid);
 	drm_dp_put_port(port);
 	return edid;
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index d12a4efa651b..1fe14579e8c9 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -224,6 +224,64 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
 		diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0;
 	}
 
+	/*
+	 * Within a drm_vblank_pre_modeset - drm_vblank_post_modeset
+	 * interval? If so then vblank irqs keep running and it will likely
+	 * happen that the hardware vblank counter is not trustworthy as it
+	 * might reset at some point in that interval and vblank timestamps
+	 * are not trustworthy either in that interval. Iow. this can result
+	 * in a bogus diff >> 1 which must be avoided as it would cause
+	 * random large forward jumps of the software vblank counter.
+	 */
+	if (diff > 1 && (vblank->inmodeset & 0x2)) {
+		DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u"
+			      " due to pre-modeset.\n", pipe, diff);
+		diff = 1;
+	}
+
+	/*
+	 * FIMXE: Need to replace this hack with proper seqlocks.
+	 *
+	 * Restrict the bump of the software vblank counter to a safe maximum
+	 * value of +1 whenever there is the possibility that concurrent readers
+	 * of vblank timestamps could be active at the moment, as the current
+	 * implementation of the timestamp caching and updating is not safe
+	 * against concurrent readers for calls to store_vblank() with a bump
+	 * of anything but +1. A bump != 1 would very likely return corrupted
+	 * timestamps to userspace, because the same slot in the cache could
+	 * be concurrently written by store_vblank() and read by one of those
+	 * readers without the read-retry logic detecting the collision.
+	 *
+	 * Concurrent readers can exist when we are called from the
+	 * drm_vblank_off() or drm_vblank_on() functions and other non-vblank-
+	 * irq callers. However, all those calls to us are happening with the
+	 * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount
+	 * can't increase while we are executing. Therefore a zero refcount at
+	 * this point is safe for arbitrary counter bumps if we are called
+	 * outside vblank irq, a non-zero count is not 100% safe. Unfortunately
+	 * we must also accept a refcount of 1, as whenever we are called from
+	 * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and
+	 * we must let that one pass through in order to not lose vblank counts
+	 * during vblank irq off - which would completely defeat the whole
+	 * point of this routine.
+	 *
+	 * Whenever we are called from vblank irq, we have to assume concurrent
+	 * readers exist or can show up any time during our execution, even if
+	 * the refcount is currently zero, as vblank irqs are usually only
+	 * enabled due to the presence of readers, and because when we are called
+	 * from vblank irq we can't hold the vbl_lock to protect us from sudden
+	 * bumps in vblank refcount. Therefore also restrict bumps to +1 when
+	 * called from vblank irq.
+	 */
+	if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 ||
+	    (flags & DRM_CALLED_FROM_VBLIRQ))) {
+		DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u "
+			      "refcount %u, vblirq %u\n", pipe, diff,
+			      atomic_read(&vblank->refcount),
+			      (flags & DRM_CALLED_FROM_VBLIRQ) != 0);
+		diff = 1;
+	}
+
 	DRM_DEBUG_VBL("updating vblank count on crtc %u:"
 		      " current=%u, diff=%u, hw=%u hw_last=%u\n",
 		      pipe, vblank->count, diff, cur_vblank, vblank->last);
@@ -1316,7 +1374,13 @@ void drm_vblank_off(struct drm_device *dev, unsigned int pipe)
 	spin_lock_irqsave(&dev->event_lock, irqflags);
 
 	spin_lock(&dev->vbl_lock);
-	vblank_disable_and_save(dev, pipe);
+	DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n",
+		      pipe, vblank->enabled, vblank->inmodeset);
+
+	/* Avoid redundant vblank disables without previous drm_vblank_on(). */
+	if (drm_core_check_feature(dev, DRIVER_ATOMIC) || !vblank->inmodeset)
+		vblank_disable_and_save(dev, pipe);
+
 	wake_up(&vblank->queue);
 
 	/*
@@ -1418,6 +1482,9 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe)
 		return;
 
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n",
+		      pipe, vblank->enabled, vblank->inmodeset);
+
 	/* Drop our private "prevent drm_vblank_get" refcount */
 	if (vblank->inmodeset) {
 		atomic_dec(&vblank->refcount);
@@ -1430,8 +1497,7 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe)
 	 * re-enable interrupts if there are users left, or the
 	 * user wishes vblank interrupts to be enabled all the time.
 	 */
-	if (atomic_read(&vblank->refcount) != 0 ||
-	    (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0))
+	if (atomic_read(&vblank->refcount) != 0 || drm_vblank_offdelay == 0)
 		WARN_ON(drm_vblank_enable(dev, pipe));
 	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 }
@@ -1526,6 +1592,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe)
 	if (vblank->inmodeset) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		dev->vblank_disable_allowed = true;
+		drm_reset_vblank_timestamp(dev, pipe);
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 
 		if (vblank->inmodeset & 0x2)
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 83efca941388..f17d39279596 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -1,6 +1,6 @@
 config DRM_EXYNOS
 	tristate "DRM Support for Samsung SoC EXYNOS Series"
-	depends on OF && DRM && (PLAT_SAMSUNG || ARCH_MULTIPLATFORM)
+	depends on OF && DRM && (ARCH_S3C64XX || ARCH_EXYNOS || ARCH_MULTIPLATFORM)
 	select DRM_KMS_HELPER
 	select DRM_KMS_FB_HELPER
 	select FB_CFB_FILLRECT
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 1bf6a21130c7..162ab93e99cb 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -93,7 +93,7 @@ static int decon_enable_vblank(struct exynos_drm_crtc *crtc)
 	if (test_bit(BIT_SUSPENDED, &ctx->flags))
 		return -EPERM;
 
-	if (test_and_set_bit(BIT_IRQS_ENABLED, &ctx->flags)) {
+	if (!test_and_set_bit(BIT_IRQS_ENABLED, &ctx->flags)) {
 		val = VIDINTCON0_INTEN;
 		if (ctx->out_type == IFTYPE_I80)
 			val |= VIDINTCON0_FRAMEDONE;
@@ -402,8 +402,6 @@ static void decon_enable(struct exynos_drm_crtc *crtc)
 		decon_enable_vblank(ctx->crtc);
 
 	decon_commit(ctx->crtc);
-
-	set_bit(BIT_SUSPENDED, &ctx->flags);
 }
 
 static void decon_disable(struct exynos_drm_crtc *crtc)
@@ -582,9 +580,9 @@ out:
 static int exynos5433_decon_suspend(struct device *dev)
 {
 	struct decon_context *ctx = dev_get_drvdata(dev);
-	int i;
+	int i = ARRAY_SIZE(decon_clks_name);
 
-	for (i = 0; i < ARRAY_SIZE(decon_clks_name); i++)
+	while (--i >= 0)
 		clk_disable_unprepare(ctx->clks[i]);
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index e977a81af2e6..26e81d191f56 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1782,6 +1782,7 @@ static int exynos_dsi_bind(struct device *dev, struct device *master,
 
 	bridge = of_drm_find_bridge(dsi->bridge_node);
 	if (bridge) {
+		encoder->bridge = bridge;
 		drm_bridge_attach(drm_dev, bridge);
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index f6118baa8e3e..8baabd813ff5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -50,7 +50,7 @@ static int exynos_drm_fb_mmap(struct fb_info *info,
 	if (vm_size > exynos_gem->size)
 		return -EINVAL;
 
-	ret = dma_mmap_attrs(helper->dev->dev, vma, exynos_gem->pages,
+	ret = dma_mmap_attrs(helper->dev->dev, vma, exynos_gem->cookie,
 			     exynos_gem->dma_addr, exynos_gem->size,
 			     &exynos_gem->dma_attrs);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index c747824f3c98..8a4f4a0211d0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1723,7 +1723,7 @@ static int fimc_probe(struct platform_device *pdev)
 		goto err_put_clk;
 	}
 
-	DRM_DEBUG_KMS("id[%d]ippdrv[0x%x]\n", ctx->id, (int)ippdrv);
+	DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
 
 	spin_lock_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index c17efdb238a6..8dfe6e113a88 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -1166,7 +1166,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 		goto err_free_event;
 	}
 
-	cmd = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd;
+	cmd = (struct drm_exynos_g2d_cmd *)(unsigned long)req->cmd;
 
 	if (copy_from_user(cmdlist->data + cmdlist->last,
 				(void __user *)cmd,
@@ -1184,7 +1184,8 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	if (req->cmd_buf_nr) {
 		struct drm_exynos_g2d_cmd *cmd_buf;
 
-		cmd_buf = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd_buf;
+		cmd_buf = (struct drm_exynos_g2d_cmd *)
+				(unsigned long)req->cmd_buf;
 
 		if (copy_from_user(cmdlist->data + cmdlist->last,
 					(void __user *)cmd_buf,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 32358c5e3db4..26b5e4bd55b6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -218,7 +218,7 @@ static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
 		return ERR_PTR(ret);
 	}
 
-	DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp);
+	DRM_DEBUG_KMS("created file object = %p\n", obj->filp);
 
 	return exynos_gem;
 }
@@ -335,7 +335,7 @@ static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem,
 	if (vm_size > exynos_gem->size)
 		return -EINVAL;
 
-	ret = dma_mmap_attrs(drm_dev->dev, vma, exynos_gem->pages,
+	ret = dma_mmap_attrs(drm_dev->dev, vma, exynos_gem->cookie,
 			     exynos_gem->dma_addr, exynos_gem->size,
 			     &exynos_gem->dma_attrs);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 7aecd23cfa11..5d20da8f957e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1723,7 +1723,7 @@ static int gsc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	DRM_DEBUG_KMS("id[%d]ippdrv[0x%x]\n", ctx->id, (int)ippdrv);
+	DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
 
 	mutex_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 67d24236e745..95eeb9116f10 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -208,7 +208,7 @@ static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id)
 	 * e.g PAUSE state, queue buf, command control.
 	 */
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
-		DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n", count++, (int)ippdrv);
+		DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n", count++, ippdrv);
 
 		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
@@ -388,8 +388,8 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 	}
 	property->prop_id = ret;
 
-	DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[0x%x]\n",
-		property->prop_id, property->cmd, (int)ippdrv);
+	DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[%p]\n",
+		property->prop_id, property->cmd, ippdrv);
 
 	/* stored property information and ippdrv in private data */
 	c_node->property = *property;
@@ -518,7 +518,7 @@ static int ipp_put_mem_node(struct drm_device *drm_dev,
 {
 	int i;
 
-	DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node);
+	DRM_DEBUG_KMS("node[%p]\n", m_node);
 
 	if (!m_node) {
 		DRM_ERROR("invalid dequeue node.\n");
@@ -562,7 +562,7 @@ static struct drm_exynos_ipp_mem_node
 	m_node->buf_id = qbuf->buf_id;
 	INIT_LIST_HEAD(&m_node->list);
 
-	DRM_DEBUG_KMS("m_node[0x%x]ops_id[%d]\n", (int)m_node, qbuf->ops_id);
+	DRM_DEBUG_KMS("m_node[%p]ops_id[%d]\n", m_node, qbuf->ops_id);
 	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]\n", qbuf->prop_id, m_node->buf_id);
 
 	for_each_ipp_planar(i) {
@@ -582,8 +582,8 @@ static struct drm_exynos_ipp_mem_node
 
 			buf_info->handles[i] = qbuf->handle[i];
 			buf_info->base[i] = *addr;
-			DRM_DEBUG_KMS("i[%d]base[0x%x]hd[0x%lx]\n", i,
-				      buf_info->base[i], buf_info->handles[i]);
+			DRM_DEBUG_KMS("i[%d]base[%pad]hd[0x%lx]\n", i,
+				      &buf_info->base[i], buf_info->handles[i]);
 		}
 	}
 
@@ -664,7 +664,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node,
 
 	mutex_lock(&c_node->event_lock);
 	list_for_each_entry_safe(e, te, &c_node->event_list, base.link) {
-		DRM_DEBUG_KMS("count[%d]e[0x%x]\n", count++, (int)e);
+		DRM_DEBUG_KMS("count[%d]e[%p]\n", count++, e);
 
 		/*
 		 * qbuf == NULL condition means all event deletion.
@@ -755,7 +755,7 @@ static struct drm_exynos_ipp_mem_node
 
 	/* find memory node from memory list */
 	list_for_each_entry(m_node, head, list) {
-		DRM_DEBUG_KMS("count[%d]m_node[0x%x]\n", count++, (int)m_node);
+		DRM_DEBUG_KMS("count[%d]m_node[%p]\n", count++, m_node);
 
 		/* compare buffer id */
 		if (m_node->buf_id == qbuf->buf_id)
@@ -772,7 +772,7 @@ static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
 	struct exynos_drm_ipp_ops *ops = NULL;
 	int ret = 0;
 
-	DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node);
+	DRM_DEBUG_KMS("node[%p]\n", m_node);
 
 	if (!m_node) {
 		DRM_ERROR("invalid queue node.\n");
@@ -1237,7 +1237,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 			m_node = list_first_entry(head,
 				struct drm_exynos_ipp_mem_node, list);
 
-			DRM_DEBUG_KMS("m_node[0x%x]\n", (int)m_node);
+			DRM_DEBUG_KMS("m_node[%p]\n", m_node);
 
 			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
 			if (ret) {
@@ -1610,8 +1610,8 @@ static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 		}
 		ippdrv->prop_list.ipp_id = ret;
 
-		DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]ipp_id[%d]\n",
-			count++, (int)ippdrv, ret);
+		DRM_DEBUG_KMS("count[%d]ippdrv[%p]ipp_id[%d]\n",
+			count++, ippdrv, ret);
 
 		/* store parent device for node */
 		ippdrv->parent_dev = dev;
@@ -1668,7 +1668,7 @@ static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev,
 
 	file_priv->ipp_dev = dev;
 
-	DRM_DEBUG_KMS("done priv[0x%x]\n", (int)dev);
+	DRM_DEBUG_KMS("done priv[%p]\n", dev);
 
 	return 0;
 }
@@ -1685,8 +1685,8 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
 		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry_safe(c_node, tc_node,
 			&ippdrv->cmd_list, list) {
-			DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n",
-				count++, (int)ippdrv);
+			DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n",
+				count++, ippdrv);
 
 			if (c_node->filp == file) {
 				/*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 4eaef36aec5a..9869d70e9e54 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/of_graph.h>
 #include <linux/clk.h>
+#include <linux/component.h>
 #include <drm/drmP.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
@@ -306,9 +307,9 @@ exit:
 	return ret;
 }
 
-void mic_disable(struct drm_bridge *bridge) { }
+static void mic_disable(struct drm_bridge *bridge) { }
 
-void mic_post_disable(struct drm_bridge *bridge)
+static void mic_post_disable(struct drm_bridge *bridge)
 {
 	struct exynos_mic *mic = bridge->driver_private;
 	int i;
@@ -328,7 +329,7 @@ already_disabled:
 	mutex_unlock(&mic_mutex);
 }
 
-void mic_pre_enable(struct drm_bridge *bridge)
+static void mic_pre_enable(struct drm_bridge *bridge)
 {
 	struct exynos_mic *mic = bridge->driver_private;
 	int ret, i;
@@ -371,11 +372,35 @@ already_enabled:
 	mutex_unlock(&mic_mutex);
 }
 
-void mic_enable(struct drm_bridge *bridge) { }
+static void mic_enable(struct drm_bridge *bridge) { }
 
-void mic_destroy(struct drm_bridge *bridge)
+static const struct drm_bridge_funcs mic_bridge_funcs = {
+	.disable = mic_disable,
+	.post_disable = mic_post_disable,
+	.pre_enable = mic_pre_enable,
+	.enable = mic_enable,
+};
+
+static int exynos_mic_bind(struct device *dev, struct device *master,
+			   void *data)
 {
-	struct exynos_mic *mic = bridge->driver_private;
+	struct exynos_mic *mic = dev_get_drvdata(dev);
+	int ret;
+
+	mic->bridge.funcs = &mic_bridge_funcs;
+	mic->bridge.of_node = dev->of_node;
+	mic->bridge.driver_private = mic;
+	ret = drm_bridge_add(&mic->bridge);
+	if (ret)
+		DRM_ERROR("mic: Failed to add MIC to the global bridge list\n");
+
+	return ret;
+}
+
+static void exynos_mic_unbind(struct device *dev, struct device *master,
+			      void *data)
+{
+	struct exynos_mic *mic = dev_get_drvdata(dev);
 	int i;
 
 	mutex_lock(&mic_mutex);
@@ -387,16 +412,16 @@ void mic_destroy(struct drm_bridge *bridge)
 
 already_disabled:
 	mutex_unlock(&mic_mutex);
+
+	drm_bridge_remove(&mic->bridge);
 }
 
-static const struct drm_bridge_funcs mic_bridge_funcs = {
-	.disable = mic_disable,
-	.post_disable = mic_post_disable,
-	.pre_enable = mic_pre_enable,
-	.enable = mic_enable,
+static const struct component_ops exynos_mic_component_ops = {
+	.bind	= exynos_mic_bind,
+	.unbind	= exynos_mic_unbind,
 };
 
-int exynos_mic_probe(struct platform_device *pdev)
+static int exynos_mic_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct exynos_mic *mic;
@@ -435,17 +460,8 @@ int exynos_mic_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	mic->bridge.funcs = &mic_bridge_funcs;
-	mic->bridge.of_node = dev->of_node;
-	mic->bridge.driver_private = mic;
-	ret = drm_bridge_add(&mic->bridge);
-	if (ret) {
-		DRM_ERROR("mic: Failed to add MIC to the global bridge list\n");
-		goto err;
-	}
-
 	for (i = 0; i < NUM_CLKS; i++) {
-		mic->clks[i] = of_clk_get_by_name(dev->of_node, clk_names[i]);
+		mic->clks[i] = devm_clk_get(dev, clk_names[i]);
 		if (IS_ERR(mic->clks[i])) {
 			DRM_ERROR("mic: Failed to get clock (%s)\n",
 								clk_names[i]);
@@ -454,7 +470,10 @@ int exynos_mic_probe(struct platform_device *pdev)
 		}
 	}
 
+	platform_set_drvdata(pdev, mic);
+
 	DRM_DEBUG_KMS("MIC has been probed\n");
+	return component_add(dev, &exynos_mic_component_ops);
 
 err:
 	return ret;
@@ -462,14 +481,7 @@ err:
 
 static int exynos_mic_remove(struct platform_device *pdev)
 {
-	struct exynos_mic *mic = platform_get_drvdata(pdev);
-	int i;
-
-	drm_bridge_remove(&mic->bridge);
-
-	for (i = NUM_CLKS - 1; i > -1; i--)
-		clk_put(mic->clks[i]);
-
+	component_del(&pdev->dev, &exynos_mic_component_ops);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index bea0f7826d30..ce59f4443394 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -754,7 +754,7 @@ static int rotator_probe(struct platform_device *pdev)
 		goto err_ippdrv_register;
 	}
 
-	DRM_DEBUG_KMS("ippdrv[0x%x]\n", (int)ippdrv);
+	DRM_DEBUG_KMS("ippdrv[%p]\n", ippdrv);
 
 	platform_set_drvdata(pdev, rot);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 62ac4e5fa51d..b605bd7395ec 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -223,7 +223,7 @@ static void vidi_fake_vblank_handler(struct work_struct *work)
 	}
 }
 
-static int vidi_show_connection(struct device *dev,
+static ssize_t vidi_show_connection(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct vidi_context *ctx = dev_get_drvdata(dev);
@@ -238,7 +238,7 @@ static int vidi_show_connection(struct device *dev,
 	return rc;
 }
 
-static int vidi_store_connection(struct device *dev,
+static ssize_t vidi_store_connection(struct device *dev,
 				struct device_attribute *attr,
 				const char *buf, size_t len)
 {
@@ -294,7 +294,9 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data,
 	}
 
 	if (vidi->connection) {
-		struct edid *raw_edid  = (struct edid *)(uint32_t)vidi->edid;
+		struct edid *raw_edid;
+
+		raw_edid = (struct edid *)(unsigned long)vidi->edid;
 		if (!drm_edid_is_valid(raw_edid)) {
 			DRM_DEBUG_KMS("edid data is invalid.\n");
 			return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 0fc38bb7276c..cf39ed3133d6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -825,8 +825,11 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 		}
 
 		for_each_pipe(dev_priv, pipe) {
-			if (!intel_display_power_is_enabled(dev_priv,
-						POWER_DOMAIN_PIPE(pipe))) {
+			enum intel_display_power_domain power_domain;
+
+			power_domain = POWER_DOMAIN_PIPE(pipe);
+			if (!intel_display_power_get_if_enabled(dev_priv,
+								power_domain)) {
 				seq_printf(m, "Pipe %c power disabled\n",
 					   pipe_name(pipe));
 				continue;
@@ -840,6 +843,8 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			seq_printf(m, "Pipe %c IER:\t%08x\n",
 				   pipe_name(pipe),
 				   I915_READ(GEN8_DE_PIPE_IER(pipe)));
+
+			intel_display_power_put(dev_priv, power_domain);
 		}
 
 		seq_printf(m, "Display Engine port interrupt mask:\t%08x\n",
@@ -3985,6 +3990,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 	struct intel_crtc *crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev,
 									pipe));
+	enum intel_display_power_domain power_domain;
 	u32 val = 0; /* shut up gcc */
 	int ret;
 
@@ -3995,7 +4001,8 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 	if (pipe_crc->source && source)
 		return -EINVAL;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) {
+	power_domain = POWER_DOMAIN_PIPE(pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) {
 		DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n");
 		return -EIO;
 	}
@@ -4012,7 +4019,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 		ret = ivb_pipe_crc_ctl_reg(dev, pipe, &source, &val);
 
 	if (ret != 0)
-		return ret;
+		goto out;
 
 	/* none -> real source transition */
 	if (source) {
@@ -4024,8 +4031,10 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 		entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR,
 				  sizeof(pipe_crc->entries[0]),
 				  GFP_KERNEL);
-		if (!entries)
-			return -ENOMEM;
+		if (!entries) {
+			ret = -ENOMEM;
+			goto out;
+		}
 
 		/*
 		 * When IPS gets enabled, the pipe CRC changes. Since IPS gets
@@ -4081,7 +4090,12 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 		hsw_enable_ips(crtc);
 	}
 
-	return 0;
+	ret = 0;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f0f75d7c0d94..b0847b915545 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -751,6 +751,7 @@ struct intel_csr {
 	uint32_t mmio_count;
 	i915_reg_t mmioaddr[8];
 	uint32_t mmiodata[8];
+	uint32_t dc_state;
 };
 
 #define DEV_INFO_FOR_EACH_FLAG(func, sep) \
@@ -1988,6 +1989,9 @@ enum hdmi_force_audio {
 #define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
+	unsigned int flags;
+#define I915_GEM_OBJECT_HAS_STRUCT_PAGE 0x1
+
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
 	 * of pages before to binding them into the GTT, and put_pages() is
@@ -2003,6 +2007,7 @@ struct drm_i915_gem_object_ops {
 	 */
 	int (*get_pages)(struct drm_i915_gem_object *);
 	void (*put_pages)(struct drm_i915_gem_object *);
+
 	int (*dmabuf_export)(struct drm_i915_gem_object *);
 	void (*release)(struct drm_i915_gem_object *);
 };
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ddc21d4b388d..bb44bad15403 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4425,6 +4425,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
+	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = i915_gem_object_get_pages_gtt,
 	.put_pages = i915_gem_object_put_pages_gtt,
 };
@@ -5261,7 +5262,7 @@ i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, int n)
 	struct page *page;
 
 	/* Only default objects have per-page dirty tracking */
-	if (WARN_ON(obj->ops != &i915_gem_object_ops))
+	if (WARN_ON((obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE) == 0))
 		return NULL;
 
 	page = i915_gem_object_get_page(obj, n);
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 19fb0bddc1cd..59e45b3a6937 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -789,9 +789,10 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
-	.dmabuf_export = i915_gem_userptr_dmabuf_export,
+	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
+	.dmabuf_export = i915_gem_userptr_dmabuf_export,
 	.release = i915_gem_userptr_release,
 };
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 007ae83a4086..4897728713f6 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3287,19 +3287,20 @@ enum skl_disp_power_wells {
 
 #define PORT_HOTPLUG_STAT	_MMIO(dev_priv->info.display_mmio_offset + 0x61114)
 /*
- * HDMI/DP bits are gen4+
+ * HDMI/DP bits are g4x+
  *
  * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused.
  * Please check the detailed lore in the commit message for for experimental
  * evidence.
  */
-#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
+/* Bspec says GM45 should match G4X/VLV/CHV, but reality disagrees */
+#define   PORTD_HOTPLUG_LIVE_STATUS_GM45	(1 << 29)
+#define   PORTC_HOTPLUG_LIVE_STATUS_GM45	(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_GM45	(1 << 27)
+/* G4X/VLV/CHV DP/HDMI bits again match Bspec */
+#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
 #define   PORTC_HOTPLUG_LIVE_STATUS_G4X		(1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
-/* VLV DP/HDMI bits again match Bspec */
-#define   PORTD_HOTPLUG_LIVE_STATUS_VLV		(1 << 27)
-#define   PORTC_HOTPLUG_LIVE_STATUS_VLV		(1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS_VLV		(1 << 29)
+#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTD_HOTPLUG_INT_LONG_PULSE		(2 << 21)
 #define   PORTD_HOTPLUG_INT_SHORT_PULSE		(1 << 21)
@@ -7514,7 +7515,7 @@ enum skl_disp_power_wells {
 #define  DPLL_CFGCR2_PDIV_7 (4<<2)
 #define  DPLL_CFGCR2_CENTRAL_FREQ_MASK	(3)
 
-#define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR2)
+#define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR1)
 #define DPLL_CFGCR2(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR2, _DPLL2_CFGCR2)
 
 /* BXT display engine PLL */
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index a2aa09ce3202..a8af594fbd00 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -49,7 +49,7 @@ static void i915_save_display(struct drm_device *dev)
 		dev_priv->regfile.savePP_ON_DELAYS = I915_READ(PCH_PP_ON_DELAYS);
 		dev_priv->regfile.savePP_OFF_DELAYS = I915_READ(PCH_PP_OFF_DELAYS);
 		dev_priv->regfile.savePP_DIVISOR = I915_READ(PCH_PP_DIVISOR);
-	} else if (!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) {
+	} else if (INTEL_INFO(dev)->gen <= 4) {
 		dev_priv->regfile.savePP_CONTROL = I915_READ(PP_CONTROL);
 		dev_priv->regfile.savePP_ON_DELAYS = I915_READ(PP_ON_DELAYS);
 		dev_priv->regfile.savePP_OFF_DELAYS = I915_READ(PP_OFF_DELAYS);
@@ -84,7 +84,7 @@ static void i915_restore_display(struct drm_device *dev)
 		I915_WRITE(PCH_PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
 		I915_WRITE(PCH_PP_DIVISOR, dev_priv->regfile.savePP_DIVISOR);
 		I915_WRITE(PCH_PP_CONTROL, dev_priv->regfile.savePP_CONTROL);
-	} else if (!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) {
+	} else if (INTEL_INFO(dev)->gen <= 4) {
 		I915_WRITE(PP_ON_DELAYS, dev_priv->regfile.savePP_ON_DELAYS);
 		I915_WRITE(PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
 		I915_WRITE(PP_DIVISOR, dev_priv->regfile.savePP_DIVISOR);
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 9c89df1af036..a7b4a524fadd 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -71,22 +71,29 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(crt->adpa_reg);
 
 	if (!(tmp & ADPA_DAC_ENABLE))
-		return false;
+		goto out;
 
 	if (HAS_PCH_CPT(dev))
 		*pipe = PORT_TO_PIPE_CPT(tmp);
 	else
 		*pipe = PORT_TO_PIPE(tmp);
 
-	return true;
+	ret = true;
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static unsigned int intel_crt_get_flags(struct intel_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 9bb63a85997a..647d85e77c2f 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -240,6 +240,8 @@ void intel_csr_load_program(struct drm_i915_private *dev_priv)
 		I915_WRITE(dev_priv->csr.mmioaddr[i],
 			   dev_priv->csr.mmiodata[i]);
 	}
+
+	dev_priv->csr.dc_state = 0;
 }
 
 static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e6408e5583d7..0f3df2c39f7c 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1589,7 +1589,8 @@ skl_ddi_pll_select(struct intel_crtc *intel_crtc,
 			 DPLL_CFGCR2_KDIV(wrpll_params.kdiv) |
 			 DPLL_CFGCR2_PDIV(wrpll_params.pdiv) |
 			 wrpll_params.central_freq;
-	} else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) {
+	} else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+		   intel_encoder->type == INTEL_OUTPUT_DP_MST) {
 		switch (crtc_state->port_clock / 2) {
 		case 81000:
 			ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_810, 0);
@@ -1968,13 +1969,16 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 	enum transcoder cpu_transcoder;
 	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(intel_encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	if (!intel_encoder->get_hw_state(intel_encoder, &pipe))
-		return false;
+	if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) {
+		ret = false;
+		goto out;
+	}
 
 	if (port == PORT_A)
 		cpu_transcoder = TRANSCODER_EDP;
@@ -1986,23 +1990,33 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 	switch (tmp & TRANS_DDI_MODE_SELECT_MASK) {
 	case TRANS_DDI_MODE_SELECT_HDMI:
 	case TRANS_DDI_MODE_SELECT_DVI:
-		return (type == DRM_MODE_CONNECTOR_HDMIA);
+		ret = type == DRM_MODE_CONNECTOR_HDMIA;
+		break;
 
 	case TRANS_DDI_MODE_SELECT_DP_SST:
-		if (type == DRM_MODE_CONNECTOR_eDP)
-			return true;
-		return (type == DRM_MODE_CONNECTOR_DisplayPort);
+		ret = type == DRM_MODE_CONNECTOR_eDP ||
+		      type == DRM_MODE_CONNECTOR_DisplayPort;
+		break;
+
 	case TRANS_DDI_MODE_SELECT_DP_MST:
 		/* if the transcoder is in MST state then
 		 * connector isn't connected */
-		return false;
+		ret = false;
+		break;
 
 	case TRANS_DDI_MODE_SELECT_FDI:
-		return (type == DRM_MODE_CONNECTOR_VGA);
+		ret = type == DRM_MODE_CONNECTOR_VGA;
+		break;
 
 	default:
-		return false;
+		ret = false;
+		break;
 	}
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
@@ -2014,15 +2028,18 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
 	int i;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(DDI_BUF_CTL(port));
 
 	if (!(tmp & DDI_BUF_CTL_ENABLE))
-		return false;
+		goto out;
 
 	if (port == PORT_A) {
 		tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP));
@@ -2040,25 +2057,32 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 			break;
 		}
 
-		return true;
-	} else {
-		for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) {
-			tmp = I915_READ(TRANS_DDI_FUNC_CTL(i));
+		ret = true;
 
-			if ((tmp & TRANS_DDI_PORT_MASK)
-			    == TRANS_DDI_SELECT_PORT(port)) {
-				if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == TRANS_DDI_MODE_SELECT_DP_MST)
-					return false;
+		goto out;
+	}
 
-				*pipe = i;
-				return true;
-			}
+	for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) {
+		tmp = I915_READ(TRANS_DDI_FUNC_CTL(i));
+
+		if ((tmp & TRANS_DDI_PORT_MASK) == TRANS_DDI_SELECT_PORT(port)) {
+			if ((tmp & TRANS_DDI_MODE_SELECT_MASK) ==
+			    TRANS_DDI_MODE_SELECT_DP_MST)
+				goto out;
+
+			*pipe = i;
+			ret = true;
+
+			goto out;
 		}
 	}
 
 	DRM_DEBUG_KMS("No pipe for ddi port %c found\n", port_name(port));
 
-	return false;
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc)
@@ -2507,12 +2531,14 @@ static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
 	val = I915_READ(WRPLL_CTL(pll->id));
 	hw_state->wrpll = val;
 
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
 	return val & WRPLL_PLL_ENABLE;
 }
 
@@ -2522,12 +2548,14 @@ static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
 	val = I915_READ(SPLL_CTL);
 	hw_state->spll = val;
 
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
 	return val & SPLL_PLL_ENABLE;
 }
 
@@ -2644,16 +2672,19 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	uint32_t val;
 	unsigned int dpll;
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
+	ret = false;
+
 	/* DPLL0 is not part of the shared DPLLs, so pll->id is 0 for DPLL1 */
 	dpll = pll->id + 1;
 
 	val = I915_READ(regs[pll->id].ctl);
 	if (!(val & LCPLL_PLL_ENABLE))
-		return false;
+		goto out;
 
 	val = I915_READ(DPLL_CTRL1);
 	hw_state->ctrl1 = (val >> (dpll * 6)) & 0x3f;
@@ -2663,8 +2694,12 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 		hw_state->cfgcr1 = I915_READ(regs[pll->id].cfgcr1);
 		hw_state->cfgcr2 = I915_READ(regs[pll->id].cfgcr2);
 	}
+	ret = true;
 
-	return true;
+out:
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
+	return ret;
 }
 
 static void skl_shared_dplls_init(struct drm_i915_private *dev_priv)
@@ -2931,13 +2966,16 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	enum port port = (enum port)pll->id;	/* 1:1 port->PLL mapping */
 	uint32_t val;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
+	ret = false;
+
 	val = I915_READ(BXT_PORT_PLL_ENABLE(port));
 	if (!(val & PORT_PLL_ENABLE))
-		return false;
+		goto out;
 
 	hw_state->ebb0 = I915_READ(BXT_PORT_PLL_EBB_0(port));
 	hw_state->ebb0 &= PORT_PLL_P1_MASK | PORT_PLL_P2_MASK;
@@ -2984,7 +3022,12 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 				 I915_READ(BXT_PORT_PCS_DW12_LN23(port)));
 	hw_state->pcsdw12 &= LANE_STAGGER_MASK | LANESTAGGER_STRAP_OVRD;
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
+	return ret;
 }
 
 static void bxt_shared_dplls_init(struct drm_i915_private *dev_priv)
@@ -3119,11 +3162,15 @@ bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
 {
 	u32 temp;
 
-	if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
+	if (intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
 		temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
+
+		intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
+
 		if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe))
 			return true;
 	}
+
 	return false;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5feb65725c04..46947fffd599 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1351,18 +1351,21 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 	bool cur_state;
 	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
 								      pipe);
+	enum intel_display_power_domain power_domain;
 
 	/* if we need the pipe quirk it must be always on */
 	if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
 	    (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
 		state = true;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-				POWER_DOMAIN_TRANSCODER(cpu_transcoder))) {
-		cur_state = false;
-	} else {
+	power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder);
+	if (intel_display_power_get_if_enabled(dev_priv, power_domain)) {
 		u32 val = I915_READ(PIPECONF(cpu_transcoder));
 		cur_state = !!(val & PIPECONF_ENABLE);
+
+		intel_display_power_put(dev_priv, power_domain);
+	} else {
+		cur_state = false;
 	}
 
 	I915_STATE_WARN(cur_state != state,
@@ -8171,18 +8174,22 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-					    POWER_DOMAIN_PIPE(crtc->pipe)))
+	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
+	ret = false;
+
 	tmp = I915_READ(PIPECONF(crtc->pipe));
 	if (!(tmp & PIPECONF_ENABLE))
-		return false;
+		goto out;
 
 	if (IS_G4X(dev) || IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
 		switch (tmp & PIPECONF_BPC_MASK) {
@@ -8262,7 +8269,12 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	pipe_config->base.adjusted_mode.crtc_clock =
 		pipe_config->port_clock / pipe_config->pixel_multiplier;
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void ironlake_init_pch_refclk(struct drm_device *dev)
@@ -9366,18 +9378,21 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-					    POWER_DOMAIN_PIPE(crtc->pipe)))
+	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
+	ret = false;
 	tmp = I915_READ(PIPECONF(crtc->pipe));
 	if (!(tmp & PIPECONF_ENABLE))
-		return false;
+		goto out;
 
 	switch (tmp & PIPECONF_BPC_MASK) {
 	case PIPECONF_6BPC:
@@ -9440,7 +9455,12 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 
 	ironlake_get_pfit_config(crtc, pipe_config);
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
@@ -9950,12 +9970,17 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum intel_display_power_domain pfit_domain;
+	enum intel_display_power_domain power_domain;
+	unsigned long power_domain_mask;
 	uint32_t tmp;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-					 POWER_DOMAIN_PIPE(crtc->pipe)))
+	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
+	power_domain_mask = BIT(power_domain);
+
+	ret = false;
 
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
@@ -9982,13 +10007,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 			pipe_config->cpu_transcoder = TRANSCODER_EDP;
 	}
 
-	if (!intel_display_power_is_enabled(dev_priv,
-			POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder)))
-		return false;
+	power_domain = POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+		goto out;
+	power_domain_mask |= BIT(power_domain);
 
 	tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder));
 	if (!(tmp & PIPECONF_ENABLE))
-		return false;
+		goto out;
 
 	haswell_get_ddi_port_state(crtc, pipe_config);
 
@@ -9998,14 +10024,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		skl_init_scalers(dev, crtc, pipe_config);
 	}
 
-	pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
-
 	if (INTEL_INFO(dev)->gen >= 9) {
 		pipe_config->scaler_state.scaler_id = -1;
 		pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX);
 	}
 
-	if (intel_display_power_is_enabled(dev_priv, pfit_domain)) {
+	power_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
+	if (intel_display_power_get_if_enabled(dev_priv, power_domain)) {
+		power_domain_mask |= BIT(power_domain);
 		if (INTEL_INFO(dev)->gen >= 9)
 			skylake_get_pfit_config(crtc, pipe_config);
 		else
@@ -10023,7 +10049,13 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->pixel_multiplier = 1;
 	}
 
-	return true;
+	ret = true;
+
+out:
+	for_each_power_domain(power_domain, power_domain_mask)
+		intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
@@ -13630,7 +13662,7 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
 	val = I915_READ(PCH_DPLL(pll->id));
@@ -13638,6 +13670,8 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 	hw_state->fp0 = I915_READ(PCH_FP0(pll->id));
 	hw_state->fp1 = I915_READ(PCH_FP1(pll->id));
 
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
 	return val & DPLL_VCO_ENABLE;
 }
 
@@ -15568,10 +15602,12 @@ void i915_redisable_vga(struct drm_device *dev)
 	 * level, just check if the power well is enabled instead of trying to
 	 * follow the "don't touch the power well if we don't need it" policy
 	 * the rest of the driver uses. */
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_VGA))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_VGA))
 		return;
 
 	i915_redisable_vga_power_on(dev);
+
+	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
 }
 
 static bool primary_get_hw_state(struct intel_plane *plane)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 796e3d313cb9..1d8de43bed56 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2362,15 +2362,18 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(intel_dp->output_reg);
 
 	if (!(tmp & DP_PORT_EN))
-		return false;
+		goto out;
 
 	if (IS_GEN7(dev) && port == PORT_A) {
 		*pipe = PORT_TO_PIPE_CPT(tmp);
@@ -2381,7 +2384,9 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 			u32 trans_dp = I915_READ(TRANS_DP_CTL(p));
 			if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) {
 				*pipe = p;
-				return true;
+				ret = true;
+
+				goto out;
 			}
 		}
 
@@ -2393,7 +2398,12 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 		*pipe = PORT_TO_PIPE(tmp);
 	}
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void intel_dp_get_config(struct intel_encoder *encoder,
@@ -4493,20 +4503,20 @@ static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv,
 	return I915_READ(PORT_HOTPLUG_STAT) & bit;
 }
 
-static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool gm45_digital_port_connected(struct drm_i915_private *dev_priv,
+					struct intel_digital_port *port)
 {
 	u32 bit;
 
 	switch (port->port) {
 	case PORT_B:
-		bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTB_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_C:
-		bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTC_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_D:
-		bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTD_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	default:
 		MISSING_CASE(port->port);
@@ -4558,8 +4568,8 @@ bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
 		return cpt_digital_port_connected(dev_priv, port);
 	else if (IS_BROXTON(dev_priv))
 		return bxt_digital_port_connected(dev_priv, port);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_digital_port_connected(dev_priv, port);
+	else if (IS_GM45(dev_priv))
+		return gm45_digital_port_connected(dev_priv, port);
 	else
 		return g4x_digital_port_connected(dev_priv, port);
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 88887938e0bf..0b8eefc2acc5 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -215,27 +215,46 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 	}
 }
 
-static void
-intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
+/*
+ * Pick training pattern for channel equalization. Training Pattern 3 for HBR2
+ * or 1.2 devices that support it, Training Pattern 2 otherwise.
+ */
+static u32 intel_dp_training_pattern(struct intel_dp *intel_dp)
 {
-	bool channel_eq = false;
-	int tries, cr_tries;
-	uint32_t training_pattern = DP_TRAINING_PATTERN_2;
+	u32 training_pattern = DP_TRAINING_PATTERN_2;
+	bool source_tps3, sink_tps3;
 
 	/*
-	 * Training Pattern 3 for HBR2 or 1.2 devices that support it.
-	 *
 	 * Intel platforms that support HBR2 also support TPS3. TPS3 support is
-	 * also mandatory for downstream devices that support HBR2.
+	 * also mandatory for downstream devices that support HBR2. However, not
+	 * all sinks follow the spec.
 	 *
 	 * Due to WaDisableHBR2 SKL < B0 is the only exception where TPS3 is
-	 * supported but still not enabled.
+	 * supported in source but still not enabled.
 	 */
-	if (intel_dp_source_supports_hbr2(intel_dp) &&
-	    drm_dp_tps3_supported(intel_dp->dpcd))
+	source_tps3 = intel_dp_source_supports_hbr2(intel_dp);
+	sink_tps3 = drm_dp_tps3_supported(intel_dp->dpcd);
+
+	if (source_tps3 && sink_tps3) {
 		training_pattern = DP_TRAINING_PATTERN_3;
-	else if (intel_dp->link_rate == 540000)
-		DRM_ERROR("5.4 Gbps link rate without HBR2/TPS3 support\n");
+	} else if (intel_dp->link_rate == 540000) {
+		if (!source_tps3)
+			DRM_DEBUG_KMS("5.4 Gbps link rate without source HBR2/TPS3 support\n");
+		if (!sink_tps3)
+			DRM_DEBUG_KMS("5.4 Gbps link rate without sink TPS3 support\n");
+	}
+
+	return training_pattern;
+}
+
+static void
+intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
+{
+	bool channel_eq = false;
+	int tries, cr_tries;
+	u32 training_pattern;
+
+	training_pattern = intel_dp_training_pattern(intel_dp);
 
 	/* channel equalization */
 	if (!intel_dp_set_link_train(intel_dp,
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index ea5415851c6e..df7f3cb66056 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1428,6 +1428,8 @@ bool __intel_display_power_is_enabled(struct drm_i915_private *dev_priv,
 				      enum intel_display_power_domain domain);
 void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
+bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
+					enum intel_display_power_domain domain);
 void intel_display_power_put(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
 
@@ -1514,6 +1516,7 @@ enable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
 	enable_rpm_wakeref_asserts(dev_priv)
 
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 44742fa2f616..0193c62a53ef 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -664,13 +664,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	enum intel_display_power_domain power_domain;
 	enum port port;
+	bool ret;
 
 	DRM_DEBUG_KMS("\n");
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	/* XXX: this only works for one DSI output */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		i915_reg_t ctrl_reg = IS_BROXTON(dev) ?
@@ -691,12 +694,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 		if (dpi_enabled || (func & CMD_MODE_DATA_WIDTH_MASK)) {
 			if (I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY) {
 				*pipe = port == PORT_A ? PIPE_A : PIPE_B;
-				return true;
+				ret = true;
+
+				goto out;
 			}
 		}
 	}
+out:
+	intel_display_power_put(dev_priv, power_domain);
 
-	return false;
+	return ret;
 }
 
 static void intel_dsi_get_config(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index a5e99ac305da..e8113ad65477 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -204,10 +204,28 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	struct drm_device *dev = intel_dsi->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	if (dev_priv->vbt.dsi.seq_version >= 3)
+		data++;
+
 	gpio = *data++;
 
 	/* pull up/down */
-	action = *data++;
+	action = *data++ & 1;
+
+	if (gpio >= ARRAY_SIZE(gtable)) {
+		DRM_DEBUG_KMS("unknown gpio %u\n", gpio);
+		goto out;
+	}
+
+	if (!IS_VALLEYVIEW(dev_priv)) {
+		DRM_DEBUG_KMS("GPIO element not supported on this platform\n");
+		goto out;
+	}
+
+	if (dev_priv->vbt.dsi.seq_version >= 3) {
+		DRM_DEBUG_KMS("GPIO element v3 not supported\n");
+		goto out;
+	}
 
 	function = gtable[gpio].function_reg;
 	pad = gtable[gpio].pad_reg;
@@ -226,6 +244,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	vlv_gpio_nc_write(dev_priv, pad, val);
 	mutex_unlock(&dev_priv->sb_lock);
 
+out:
 	return data;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 4a77639a489d..cb5d1b15755c 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -880,15 +880,18 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(intel_hdmi->hdmi_reg);
 
 	if (!(tmp & SDVO_ENABLE))
-		return false;
+		goto out;
 
 	if (HAS_PCH_CPT(dev))
 		*pipe = PORT_TO_PIPE_CPT(tmp);
@@ -897,7 +900,12 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 	else
 		*pipe = PORT_TO_PIPE(tmp);
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void intel_hdmi_get_config(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 25254b5c1ac5..deb8282c26d8 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -683,7 +683,7 @@ int intel_setup_gmbus(struct drm_device *dev)
 	return 0;
 
 err:
-	while (--pin) {
+	while (pin--) {
 		if (!intel_gmbus_is_valid_pin(dev_priv, pin))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 0da0240caf81..bc04d8d29acb 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -75,22 +75,30 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(lvds_encoder->reg);
 
 	if (!(tmp & LVDS_PORT_EN))
-		return false;
+		goto out;
 
 	if (HAS_PCH_CPT(dev))
 		*pipe = PORT_TO_PIPE_CPT(tmp);
 	else
 		*pipe = PORT_TO_PIPE(tmp);
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void intel_lvds_get_config(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index eb5fa05cf476..b28c29f20e75 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1783,16 +1783,20 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate,
 				   const struct intel_plane_state *pstate,
 				   uint32_t mem_value)
 {
-	int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0;
+	/*
+	 * We treat the cursor plane as always-on for the purposes of watermark
+	 * calculation.  Until we have two-stage watermark programming merged,
+	 * this is necessary to avoid flickering.
+	 */
+	int cpp = 4;
+	int width = pstate->visible ? pstate->base.crtc_w : 64;
 
-	if (!cstate->base.active || !pstate->visible)
+	if (!cstate->base.active)
 		return 0;
 
 	return ilk_wm_method2(ilk_pipe_pixel_rate(cstate),
 			      cstate->base.adjusted_mode.crtc_htotal,
-			      drm_rect_width(&pstate->dst),
-			      bpp,
-			      mem_value);
+			      width, cpp, mem_value);
 }
 
 /* Only for WM_LP. */
@@ -2825,7 +2829,10 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 	memset(ddb, 0, sizeof(*ddb));
 
 	for_each_pipe(dev_priv, pipe) {
-		if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe)))
+		enum intel_display_power_domain power_domain;
+
+		power_domain = POWER_DOMAIN_PIPE(pipe);
+		if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 			continue;
 
 		for_each_plane(dev_priv, pipe, plane) {
@@ -2837,6 +2844,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 		val = I915_READ(CUR_BUF_CFG(pipe));
 		skl_ddb_entry_init_from_hw(&ddb->plane[pipe][PLANE_CURSOR],
 					   val);
+
+		intel_display_power_put(dev_priv, power_domain);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index ddbdbffe829a..678ed3475d7e 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -470,6 +470,43 @@ static void gen9_set_dc_state_debugmask_memory_up(
 	}
 }
 
+static void gen9_write_dc_state(struct drm_i915_private *dev_priv,
+				u32 state)
+{
+	int rewrites = 0;
+	int rereads = 0;
+	u32 v;
+
+	I915_WRITE(DC_STATE_EN, state);
+
+	/* It has been observed that disabling the dc6 state sometimes
+	 * doesn't stick and dmc keeps returning old value. Make sure
+	 * the write really sticks enough times and also force rewrite until
+	 * we are confident that state is exactly what we want.
+	 */
+	do  {
+		v = I915_READ(DC_STATE_EN);
+
+		if (v != state) {
+			I915_WRITE(DC_STATE_EN, state);
+			rewrites++;
+			rereads = 0;
+		} else if (rereads++ > 5) {
+			break;
+		}
+
+	} while (rewrites < 100);
+
+	if (v != state)
+		DRM_ERROR("Writing dc state to 0x%x failed, now 0x%x\n",
+			  state, v);
+
+	/* Most of the times we need one retry, avoid spam */
+	if (rewrites > 1)
+		DRM_DEBUG_KMS("Rewrote dc state to 0x%x %d times\n",
+			      state, rewrites);
+}
+
 static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state)
 {
 	uint32_t val;
@@ -494,10 +531,18 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state)
 	val = I915_READ(DC_STATE_EN);
 	DRM_DEBUG_KMS("Setting DC state from %02x to %02x\n",
 		      val & mask, state);
+
+	/* Check if DMC is ignoring our DC state requests */
+	if ((val & mask) != dev_priv->csr.dc_state)
+		DRM_ERROR("DC state mismatch (0x%x -> 0x%x)\n",
+			  dev_priv->csr.dc_state, val & mask);
+
 	val &= ~mask;
 	val |= state;
-	I915_WRITE(DC_STATE_EN, val);
-	POSTING_READ(DC_STATE_EN);
+
+	gen9_write_dc_state(dev_priv, val);
+
+	dev_priv->csr.dc_state = val & mask;
 }
 
 void bxt_enable_dc9(struct drm_i915_private *dev_priv)
@@ -1442,6 +1487,22 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
 	chv_set_pipe_power_well(dev_priv, power_well, false);
 }
 
+static void
+__intel_display_power_get_domain(struct drm_i915_private *dev_priv,
+				 enum intel_display_power_domain domain)
+{
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *power_well;
+	int i;
+
+	for_each_power_well(i, power_well, BIT(domain), power_domains) {
+		if (!power_well->count++)
+			intel_power_well_enable(dev_priv, power_well);
+	}
+
+	power_domains->domain_use_count[domain]++;
+}
+
 /**
  * intel_display_power_get - grab a power domain reference
  * @dev_priv: i915 device instance
@@ -1457,24 +1518,53 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
 void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain)
 {
-	struct i915_power_domains *power_domains;
-	struct i915_power_well *power_well;
-	int i;
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 
 	intel_runtime_pm_get(dev_priv);
 
-	power_domains = &dev_priv->power_domains;
+	mutex_lock(&power_domains->lock);
+
+	__intel_display_power_get_domain(dev_priv, domain);
+
+	mutex_unlock(&power_domains->lock);
+}
+
+/**
+ * intel_display_power_get_if_enabled - grab a reference for an enabled display power domain
+ * @dev_priv: i915 device instance
+ * @domain: power domain to reference
+ *
+ * This function grabs a power domain reference for @domain and ensures that the
+ * power domain and all its parents are powered up. Therefore users should only
+ * grab a reference to the innermost power domain they need.
+ *
+ * Any power domain reference obtained by this function must have a symmetric
+ * call to intel_display_power_put() to release the reference again.
+ */
+bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
+					enum intel_display_power_domain domain)
+{
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	bool is_enabled;
+
+	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+		return false;
 
 	mutex_lock(&power_domains->lock);
 
-	for_each_power_well(i, power_well, BIT(domain), power_domains) {
-		if (!power_well->count++)
-			intel_power_well_enable(dev_priv, power_well);
+	if (__intel_display_power_is_enabled(dev_priv, domain)) {
+		__intel_display_power_get_domain(dev_priv, domain);
+		is_enabled = true;
+	} else {
+		is_enabled = false;
 	}
 
-	power_domains->domain_use_count[domain]++;
-
 	mutex_unlock(&power_domains->lock);
+
+	if (!is_enabled)
+		intel_runtime_pm_put(dev_priv);
+
+	return is_enabled;
 }
 
 /**
@@ -2246,6 +2336,43 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
 }
 
 /**
+ * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use
+ * @dev_priv: i915 device instance
+ *
+ * This function grabs a device-level runtime pm reference if the device is
+ * already in use and ensures that it is powered up.
+ *
+ * Any runtime pm reference obtained by this function must have a symmetric
+ * call to intel_runtime_pm_put() to release the reference again.
+ */
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_PM))
+		return true;
+
+	ret = pm_runtime_get_if_in_use(device);
+
+	/*
+	 * In cases runtime PM is disabled by the RPM core and we get an
+	 * -EINVAL return value we are not supposed to call this function,
+	 * since the power state is undefined. This applies atm to the
+	 * late/early system suspend/resume handlers.
+	 */
+	WARN_ON_ONCE(ret < 0);
+	if (ret <= 0)
+		return false;
+
+	atomic_inc(&dev_priv->pm.wakeref_count);
+	assert_rpm_wakelock_held(dev_priv);
+
+	return true;
+}
+
+/**
  * intel_runtime_pm_get_noresume - grab a runtime pm reference
  * @dev_priv: i915 device instance
  *
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 78f520d05de9..e3acc35e3805 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1520,7 +1520,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm)
 				    DMA_BIDIRECTIONAL);
 
 		if (dma_mapping_error(pdev, addr)) {
-			while (--i) {
+			while (i--) {
 				dma_unmap_page(pdev, ttm_dma->dma_address[i],
 					       PAGE_SIZE, DMA_BIDIRECTIONAL);
 				ttm_dma->dma_address[i] = 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 24be27d3cd18..20935eb2a09e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -635,10 +635,6 @@ nouveau_display_resume(struct drm_device *dev, bool runtime)
 		nv_crtc->lut.depth = 0;
 	}
 
-	/* Make sure that drm and hw vblank irqs get resumed if needed. */
-	for (head = 0; head < dev->mode_config.num_crtc; head++)
-		drm_vblank_on(dev, head);
-
 	/* This should ensure we don't hit a locking problem when someone
 	 * wakes us up via a connector.  We should never go into suspend
 	 * while the display is on anyways.
@@ -648,6 +644,10 @@ nouveau_display_resume(struct drm_device *dev, bool runtime)
 
 	drm_helper_resume_force_mode(dev);
 
+	/* Make sure that drm and hw vblank irqs get resumed if needed. */
+	for (head = 0; head < dev->mode_config.num_crtc; head++)
+		drm_vblank_on(dev, head);
+
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 8a70cec59bcd..2dfe58af12e4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -24,7 +24,7 @@
 static int nouveau_platform_probe(struct platform_device *pdev)
 {
 	const struct nvkm_device_tegra_func *func;
-	struct nvkm_device *device;
+	struct nvkm_device *device = NULL;
 	struct drm_device *drm;
 	int ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 7f8a42721eb2..e7e581d6a8ff 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -252,32 +252,40 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 
 	if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL)))
 		return -ENOMEM;
-	*pdevice = &tdev->device;
+
 	tdev->func = func;
 	tdev->pdev = pdev;
 	tdev->irq = -1;
 
 	tdev->vdd = devm_regulator_get(&pdev->dev, "vdd");
-	if (IS_ERR(tdev->vdd))
-		return PTR_ERR(tdev->vdd);
+	if (IS_ERR(tdev->vdd)) {
+		ret = PTR_ERR(tdev->vdd);
+		goto free;
+	}
 
 	tdev->rst = devm_reset_control_get(&pdev->dev, "gpu");
-	if (IS_ERR(tdev->rst))
-		return PTR_ERR(tdev->rst);
+	if (IS_ERR(tdev->rst)) {
+		ret = PTR_ERR(tdev->rst);
+		goto free;
+	}
 
 	tdev->clk = devm_clk_get(&pdev->dev, "gpu");
-	if (IS_ERR(tdev->clk))
-		return PTR_ERR(tdev->clk);
+	if (IS_ERR(tdev->clk)) {
+		ret = PTR_ERR(tdev->clk);
+		goto free;
+	}
 
 	tdev->clk_pwr = devm_clk_get(&pdev->dev, "pwr");
-	if (IS_ERR(tdev->clk_pwr))
-		return PTR_ERR(tdev->clk_pwr);
+	if (IS_ERR(tdev->clk_pwr)) {
+		ret = PTR_ERR(tdev->clk_pwr);
+		goto free;
+	}
 
 	nvkm_device_tegra_probe_iommu(tdev);
 
 	ret = nvkm_device_tegra_power_up(tdev);
 	if (ret)
-		return ret;
+		goto remove;
 
 	tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value;
 	ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev,
@@ -285,9 +293,19 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 			       cfg, dbg, detect, mmio, subdev_mask,
 			       &tdev->device);
 	if (ret)
-		return ret;
+		goto powerdown;
+
+	*pdevice = &tdev->device;
 
 	return 0;
+
+powerdown:
+	nvkm_device_tegra_power_down(tdev);
+remove:
+	nvkm_device_tegra_remove_iommu(tdev);
+free:
+	kfree(tdev);
+	return ret;
 }
 #else
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c
index 74e2f7c6c07e..9688970eca47 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c
@@ -328,6 +328,7 @@ nvkm_dp_train(struct work_struct *w)
 		.outp = outp,
 	}, *dp = &_dp;
 	u32 datarate = 0;
+	u8  pwr;
 	int ret;
 
 	if (!outp->base.info.location && disp->func->sor.magic)
@@ -355,6 +356,15 @@ nvkm_dp_train(struct work_struct *w)
 	/* disable link interrupt handling during link training */
 	nvkm_notify_put(&outp->irq);
 
+	/* ensure sink is not in a low-power state */
+	if (!nvkm_rdaux(outp->aux, DPCD_SC00, &pwr, 1)) {
+		if ((pwr & DPCD_SC00_SET_POWER) != DPCD_SC00_SET_POWER_D0) {
+			pwr &= ~DPCD_SC00_SET_POWER;
+			pwr |=  DPCD_SC00_SET_POWER_D0;
+			nvkm_wraux(outp->aux, DPCD_SC00, &pwr, 1);
+		}
+	}
+
 	/* enable down-spreading and execute pre-train script from vbios */
 	dp_link_train_init(dp, outp->dpcd[3] & 0x01);
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h
index 9596290329c7..6e10c5e0ef11 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h
@@ -71,5 +71,11 @@
 #define DPCD_LS0C_LANE1_POST_CURSOR2                                       0x0c
 #define DPCD_LS0C_LANE0_POST_CURSOR2                                       0x03
 
+/* DPCD Sink Control */
+#define DPCD_SC00                                                       0x00600
+#define DPCD_SC00_SET_POWER                                                0x03
+#define DPCD_SC00_SET_POWER_D0                                             0x01
+#define DPCD_SC00_SET_POWER_D3                                             0x03
+
 void nvkm_dp_train(struct work_struct *);
 #endif
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 2ae8577497ca..7c2e78201ead 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -168,7 +168,8 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 		       cmd->command_size))
 		return -EFAULT;
 
-	reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL);
+	reloc_info = kmalloc_array(cmd->relocs_num,
+				   sizeof(struct qxl_reloc_info), GFP_KERNEL);
 	if (!reloc_info)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
index 3d031b50a8fd..9f029dda1f07 100644
--- a/drivers/gpu/drm/qxl/qxl_prime.c
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -68,5 +68,5 @@ int qxl_gem_prime_mmap(struct drm_gem_object *obj,
 		       struct vm_area_struct *area)
 {
 	WARN_ONCE(1, "not implemented");
-	return ENOSYS;
+	return -ENOSYS;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 298ea1c453c3..2b9ba03a7c1a 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -403,7 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	struct drm_crtc *crtc = &radeon_crtc->base;
 	unsigned long flags;
 	int r;
-	int vpos, hpos, stat, min_udelay;
+	int vpos, hpos, stat, min_udelay = 0;
+	unsigned repcnt = 4;
 	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         down_read(&rdev->exclusive_lock);
@@ -454,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	 * In practice this won't execute very often unless on very fast
 	 * machines because the time window for this to happen is very small.
 	 */
-	for (;;) {
+	while (radeon_crtc->enabled && repcnt--) {
 		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
 		 * start in hpos, and to the "fudged earlier" vblank start in
 		 * vpos.
@@ -472,10 +473,22 @@ static void radeon_flip_work_func(struct work_struct *__work)
 		/* Sleep at least until estimated real start of hw vblank */
 		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		if (min_udelay > vblank->framedur_ns / 2000) {
+			/* Don't wait ridiculously long - something is wrong */
+			repcnt = 0;
+			break;
+		}
 		usleep_range(min_udelay, 2 * min_udelay);
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 	};
 
+	if (!repcnt)
+		DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, "
+				 "framedur %d, linedur %d, stat %d, vpos %d, "
+				 "hpos %d\n", work->crtc_id, min_udelay,
+				 vblank->framedur_ns / 1000,
+				 vblank->linedur_ns / 1000, stat, vpos, hpos);
+
 	/* do the flip (mmio) */
 	radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base);
 
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 460c8f2989da..ca3be90a3bb4 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -276,8 +276,12 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev)
 	if (rdev->irq.installed) {
 		for (i = 0; i < rdev->num_crtc; i++) {
 			if (rdev->pm.active_crtcs & (1 << i)) {
-				rdev->pm.req_vblank |= (1 << i);
-				drm_vblank_get(rdev->ddev, i);
+				/* This can fail if a modeset is in progress */
+				if (drm_vblank_get(rdev->ddev, i) == 0)
+					rdev->pm.req_vblank |= (1 << i);
+				else
+					DRM_DEBUG_DRIVER("crtc %d no vblank, can glitch\n",
+							 i);
 			}
 		}
 	}
@@ -1075,8 +1079,6 @@ force:
 
 	/* update display watermarks based on new power state */
 	radeon_bandwidth_update(rdev);
-	/* update displays */
-	radeon_dpm_display_configuration_changed(rdev);
 
 	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
 	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
@@ -1097,6 +1099,9 @@ force:
 
 	radeon_dpm_post_set_power_state(rdev);
 
+	/* update displays */
+	radeon_dpm_display_configuration_changed(rdev);
+
 	if (rdev->asic->dpm.force_performance_level) {
 		if (rdev->pm.dpm.thermal_active) {
 			enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index c507896aca45..197b157b73d0 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -349,8 +349,13 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 			/* see if we can skip over some allocations */
 		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
 
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_ref(fences[i]);
+
 		spin_unlock(&sa_manager->wq.lock);
 		r = radeon_fence_wait_any(rdev, fences, false);
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_unref(&fences[i]);
 		spin_lock(&sa_manager->wq.lock);
 		/* if we have nothing to wait for block */
 		if (r == -ENOENT) {
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index e34307459e50..e06ac546a90f 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -758,7 +758,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 						       0, PAGE_SIZE,
 						       PCI_DMA_BIDIRECTIONAL);
 		if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) {
-			while (--i) {
+			while (i--) {
 				pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i],
 					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 				gtt->ttm.dma_address[i] = 0;
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 18dfe3ec9a62..22278bcfc60e 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -215,7 +215,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 	struct drm_gem_cma_object *cma_obj;
 
 	if (size == 0)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	/* First, try to get a vc4_bo from the kernel BO cache. */
 	if (from_cache) {
@@ -237,7 +237,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 		if (IS_ERR(cma_obj)) {
 			DRM_ERROR("Failed to allocate from CMA:\n");
 			vc4_bo_stats_dump(vc4);
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
@@ -259,8 +259,8 @@ int vc4_dumb_create(struct drm_file *file_priv,
 		args->size = args->pitch * args->height;
 
 	bo = vc4_bo_create(dev, args->size, false);
-	if (!bo)
-		return -ENOMEM;
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
 
 	ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle);
 	drm_gem_object_unreference_unlocked(&bo->base.base);
@@ -443,8 +443,8 @@ int vc4_create_bo_ioctl(struct drm_device *dev, void *data,
 	 * get zeroed, and that might leak data between users.
 	 */
 	bo = vc4_bo_create(dev, args->size, false);
-	if (!bo)
-		return -ENOMEM;
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
 
 	ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle);
 	drm_gem_object_unreference_unlocked(&bo->base.base);
@@ -496,8 +496,8 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data,
 	}
 
 	bo = vc4_bo_create(dev, args->size, true);
-	if (!bo)
-		return -ENOMEM;
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
 
 	ret = copy_from_user(bo->base.vaddr,
 			     (void __user *)(uintptr_t)args->data,
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 080865ec2bae..51a63330d4f8 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -91,8 +91,12 @@ struct vc4_dev {
 	struct vc4_bo *overflow_mem;
 	struct work_struct overflow_mem_work;
 
+	int power_refcount;
+
+	/* Mutex controlling the power refcount. */
+	struct mutex power_lock;
+
 	struct {
-		uint32_t last_ct0ca, last_ct1ca;
 		struct timer_list timer;
 		struct work_struct reset_work;
 	} hangcheck;
@@ -142,6 +146,7 @@ struct vc4_seqno_cb {
 };
 
 struct vc4_v3d {
+	struct vc4_dev *vc4;
 	struct platform_device *pdev;
 	void __iomem *regs;
 };
@@ -192,6 +197,11 @@ struct vc4_exec_info {
 	/* Sequence number for this bin/render job. */
 	uint64_t seqno;
 
+	/* Last current addresses the hardware was processing when the
+	 * hangcheck timer checked on us.
+	 */
+	uint32_t last_ct0ca, last_ct1ca;
+
 	/* Kernel-space copy of the ioctl arguments */
 	struct drm_vc4_submit_cl *args;
 
@@ -434,7 +444,6 @@ void vc4_plane_async_set_fb(struct drm_plane *plane,
 extern struct platform_driver vc4_v3d_driver;
 int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused);
 int vc4_v3d_debugfs_regs(struct seq_file *m, void *unused);
-int vc4_v3d_set_power(struct vc4_dev *vc4, bool on);
 
 /* vc4_validate.c */
 int
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 48ce30a6f4b5..202aa1544acc 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -23,6 +23,7 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/device.h>
 #include <linux/io.h>
 
@@ -228,8 +229,16 @@ vc4_reset(struct drm_device *dev)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
 	DRM_INFO("Resetting GPU.\n");
-	vc4_v3d_set_power(vc4, false);
-	vc4_v3d_set_power(vc4, true);
+
+	mutex_lock(&vc4->power_lock);
+	if (vc4->power_refcount) {
+		/* Power the device off and back on the by dropping the
+		 * reference on runtime PM.
+		 */
+		pm_runtime_put_sync_suspend(&vc4->v3d->pdev->dev);
+		pm_runtime_get_sync(&vc4->v3d->pdev->dev);
+	}
+	mutex_unlock(&vc4->power_lock);
 
 	vc4_irq_reset(dev);
 
@@ -257,10 +266,17 @@ vc4_hangcheck_elapsed(unsigned long data)
 	struct drm_device *dev = (struct drm_device *)data;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	uint32_t ct0ca, ct1ca;
+	unsigned long irqflags;
+	struct vc4_exec_info *exec;
+
+	spin_lock_irqsave(&vc4->job_lock, irqflags);
+	exec = vc4_first_job(vc4);
 
 	/* If idle, we can stop watching for hangs. */
-	if (list_empty(&vc4->job_list))
+	if (!exec) {
+		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		return;
+	}
 
 	ct0ca = V3D_READ(V3D_CTNCA(0));
 	ct1ca = V3D_READ(V3D_CTNCA(1));
@@ -268,14 +284,16 @@ vc4_hangcheck_elapsed(unsigned long data)
 	/* If we've made any progress in execution, rearm the timer
 	 * and wait.
 	 */
-	if (ct0ca != vc4->hangcheck.last_ct0ca ||
-	    ct1ca != vc4->hangcheck.last_ct1ca) {
-		vc4->hangcheck.last_ct0ca = ct0ca;
-		vc4->hangcheck.last_ct1ca = ct1ca;
+	if (ct0ca != exec->last_ct0ca || ct1ca != exec->last_ct1ca) {
+		exec->last_ct0ca = ct0ca;
+		exec->last_ct1ca = ct1ca;
+		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		vc4_queue_hangcheck(dev);
 		return;
 	}
 
+	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
+
 	/* We've gone too long with no progress, reset.  This has to
 	 * be done from a work struct, since resetting can sleep and
 	 * this timer hook isn't allowed to.
@@ -340,12 +358,7 @@ vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno, uint64_t timeout_ns,
 	finish_wait(&vc4->job_wait_queue, &wait);
 	trace_vc4_wait_for_seqno_end(dev, seqno);
 
-	if (ret && ret != -ERESTARTSYS) {
-		DRM_ERROR("timeout waiting for render thread idle\n");
-		return ret;
-	}
-
-	return 0;
+	return ret;
 }
 
 static void
@@ -578,9 +591,9 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 	}
 
 	bo = vc4_bo_create(dev, exec_size, true);
-	if (!bo) {
+	if (IS_ERR(bo)) {
 		DRM_ERROR("Couldn't allocate BO for binning\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(bo);
 		goto fail;
 	}
 	exec->exec_bo = &bo->base;
@@ -617,6 +630,7 @@ fail:
 static void
 vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	unsigned i;
 
 	/* Need the struct lock for drm_gem_object_unreference(). */
@@ -635,6 +649,11 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	}
 	mutex_unlock(&dev->struct_mutex);
 
+	mutex_lock(&vc4->power_lock);
+	if (--vc4->power_refcount == 0)
+		pm_runtime_put(&vc4->v3d->pdev->dev);
+	mutex_unlock(&vc4->power_lock);
+
 	kfree(exec);
 }
 
@@ -746,6 +765,9 @@ vc4_wait_bo_ioctl(struct drm_device *dev, void *data,
 	struct drm_gem_object *gem_obj;
 	struct vc4_bo *bo;
 
+	if (args->pad != 0)
+		return -EINVAL;
+
 	gem_obj = drm_gem_object_lookup(dev, file_priv, args->handle);
 	if (!gem_obj) {
 		DRM_ERROR("Failed to look up GEM BO %d\n", args->handle);
@@ -772,7 +794,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_submit_cl *args = data;
 	struct vc4_exec_info *exec;
-	int ret;
+	int ret = 0;
 
 	if ((args->flags & ~VC4_SUBMIT_CL_USE_CLEAR_COLOR) != 0) {
 		DRM_ERROR("Unknown flags: 0x%02x\n", args->flags);
@@ -785,6 +807,15 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		return -ENOMEM;
 	}
 
+	mutex_lock(&vc4->power_lock);
+	if (vc4->power_refcount++ == 0)
+		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
+	mutex_unlock(&vc4->power_lock);
+	if (ret < 0) {
+		kfree(exec);
+		return ret;
+	}
+
 	exec->args = args;
 	INIT_LIST_HEAD(&exec->unref_list);
 
@@ -839,6 +870,8 @@ vc4_gem_init(struct drm_device *dev)
 		    (unsigned long)dev);
 
 	INIT_WORK(&vc4->job_done_work, vc4_job_done_work);
+
+	mutex_init(&vc4->power_lock);
 }
 
 void
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index b68060e758db..78a21357fb2d 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -57,7 +57,7 @@ vc4_overflow_mem_work(struct work_struct *work)
 	struct vc4_bo *bo;
 
 	bo = vc4_bo_create(dev, 256 * 1024, true);
-	if (!bo) {
+	if (IS_ERR(bo)) {
 		DRM_ERROR("Couldn't allocate binner overflow mem\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c
index 8a2a312e2c1b..0f12418725e5 100644
--- a/drivers/gpu/drm/vc4/vc4_render_cl.c
+++ b/drivers/gpu/drm/vc4/vc4_render_cl.c
@@ -316,20 +316,11 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec,
 	size += xtiles * ytiles * loop_body_size;
 
 	setup->rcl = &vc4_bo_create(dev, size, true)->base;
-	if (!setup->rcl)
-		return -ENOMEM;
+	if (IS_ERR(setup->rcl))
+		return PTR_ERR(setup->rcl);
 	list_add_tail(&to_vc4_bo(&setup->rcl->base)->unref_head,
 		      &exec->unref_list);
 
-	rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG);
-	rcl_u32(setup,
-		(setup->color_write ? (setup->color_write->paddr +
-				       args->color_write.offset) :
-		 0));
-	rcl_u16(setup, args->width);
-	rcl_u16(setup, args->height);
-	rcl_u16(setup, args->color_write.bits);
-
 	/* The tile buffer gets cleared when the previous tile is stored.  If
 	 * the clear values changed between frames, then the tile buffer has
 	 * stale clear values in it, so we have to do a store in None mode (no
@@ -349,6 +340,15 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec,
 		rcl_u32(setup, 0); /* no address, since we're in None mode */
 	}
 
+	rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG);
+	rcl_u32(setup,
+		(setup->color_write ? (setup->color_write->paddr +
+				       args->color_write.offset) :
+		 0));
+	rcl_u16(setup, args->width);
+	rcl_u16(setup, args->height);
+	rcl_u16(setup, args->color_write.bits);
+
 	for (y = min_y_tile; y <= max_y_tile; y++) {
 		for (x = min_x_tile; x <= max_x_tile; x++) {
 			bool first = (x == min_x_tile && y == min_y_tile);
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index 314ff71db978..31de5d17bc85 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -17,6 +17,7 @@
  */
 
 #include "linux/component.h"
+#include "linux/pm_runtime.h"
 #include "vc4_drv.h"
 #include "vc4_regs.h"
 
@@ -144,18 +145,6 @@ int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused)
 }
 #endif /* CONFIG_DEBUG_FS */
 
-int
-vc4_v3d_set_power(struct vc4_dev *vc4, bool on)
-{
-	/* XXX: This interface is needed for GPU reset, and the way to
-	 * do it is to turn our power domain off and back on.  We
-	 * can't just reset from within the driver, because the reset
-	 * bits are in the power domain's register area, and get set
-	 * during the poweron process.
-	 */
-	return 0;
-}
-
 static void vc4_v3d_init_hw(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
@@ -167,6 +156,29 @@ static void vc4_v3d_init_hw(struct drm_device *dev)
 	V3D_WRITE(V3D_VPMBASE, 0);
 }
 
+#ifdef CONFIG_PM
+static int vc4_v3d_runtime_suspend(struct device *dev)
+{
+	struct vc4_v3d *v3d = dev_get_drvdata(dev);
+	struct vc4_dev *vc4 = v3d->vc4;
+
+	vc4_irq_uninstall(vc4->dev);
+
+	return 0;
+}
+
+static int vc4_v3d_runtime_resume(struct device *dev)
+{
+	struct vc4_v3d *v3d = dev_get_drvdata(dev);
+	struct vc4_dev *vc4 = v3d->vc4;
+
+	vc4_v3d_init_hw(vc4->dev);
+	vc4_irq_postinstall(vc4->dev);
+
+	return 0;
+}
+#endif
+
 static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -179,6 +191,8 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 	if (!v3d)
 		return -ENOMEM;
 
+	dev_set_drvdata(dev, v3d);
+
 	v3d->pdev = pdev;
 
 	v3d->regs = vc4_ioremap_regs(pdev, 0);
@@ -186,6 +200,7 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 		return PTR_ERR(v3d->regs);
 
 	vc4->v3d = v3d;
+	v3d->vc4 = vc4;
 
 	if (V3D_READ(V3D_IDENT0) != V3D_EXPECTED_IDENT0) {
 		DRM_ERROR("V3D_IDENT0 read 0x%08x instead of 0x%08x\n",
@@ -207,6 +222,8 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
+	pm_runtime_enable(dev);
+
 	return 0;
 }
 
@@ -216,6 +233,8 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master,
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 
+	pm_runtime_disable(dev);
+
 	drm_irq_uninstall(drm);
 
 	/* Disable the binner's overflow memory address, so the next
@@ -228,6 +247,10 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master,
 	vc4->v3d = NULL;
 }
 
+static const struct dev_pm_ops vc4_v3d_pm_ops = {
+	SET_RUNTIME_PM_OPS(vc4_v3d_runtime_suspend, vc4_v3d_runtime_resume, NULL)
+};
+
 static const struct component_ops vc4_v3d_ops = {
 	.bind   = vc4_v3d_bind,
 	.unbind = vc4_v3d_unbind,
@@ -255,5 +278,6 @@ struct platform_driver vc4_v3d_driver = {
 	.driver = {
 		.name = "vc4_v3d",
 		.of_match_table = vc4_v3d_dt_match,
+		.pm = &vc4_v3d_pm_ops,
 	},
 };
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index e26d9f6face3..24c2c746e8f3 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -401,8 +401,8 @@ validate_tile_binning_config(VALIDATE_ARGS)
 	tile_bo = vc4_bo_create(dev, exec->tile_alloc_offset + tile_alloc_size,
 				true);
 	exec->tile_bo = &tile_bo->base;
-	if (!exec->tile_bo)
-		return -ENOMEM;
+	if (IS_ERR(exec->tile_bo))
+		return PTR_ERR(exec->tile_bo);
 	list_add_tail(&tile_bo->unref_head, &exec->unref_list);
 
 	/* tile alloc address. */
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index f155b8380481..2b3105c8aed3 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -126,7 +126,7 @@ static int ads1015_reg_to_mv(struct i2c_client *client, unsigned int channel,
 	struct ads1015_data *data = i2c_get_clientdata(client);
 	unsigned int pga = data->channel_data[channel].pga;
 	int fullscale = fullscale_table[pga];
-	const unsigned mask = data->id == ads1115 ? 0x7fff : 0x7ff0;
+	const int mask = data->id == ads1115 ? 0x7fff : 0x7ff0;
 
 	return DIV_ROUND_CLOSEST(reg * fullscale, mask);
 }
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 82de3deeb18a..685568b1236d 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -406,16 +406,11 @@ static int gpio_fan_get_cur_state(struct thermal_cooling_device *cdev,
 				  unsigned long *state)
 {
 	struct gpio_fan_data *fan_data = cdev->devdata;
-	int r;
 
 	if (!fan_data)
 		return -EINVAL;
 
-	r = get_fan_speed_index(fan_data);
-	if (r < 0)
-		return r;
-
-	*state = r;
+	*state = fan_data->speed_index;
 	return 0;
 }
 
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index f62d69799a9c..27fa0cb09538 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1271,6 +1271,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	switch (dev->device) {
 	case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS:
 	case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS:
+	case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS:
+	case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS:
 	case PCI_DEVICE_ID_INTEL_DNV_SMBUS:
 		priv->features |= FEATURE_I2C_BLOCK_READ;
 		priv->features |= FEATURE_IRQ;
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 08d26ba61ed3..13c45296ce5b 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1450,7 +1450,8 @@ omap_i2c_probe(struct platform_device *pdev)
 
 err_unuse_clocks:
 	omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0);
-	pm_runtime_put(omap->dev);
+	pm_runtime_dont_use_autosuspend(omap->dev);
+	pm_runtime_put_sync(omap->dev);
 	pm_runtime_disable(&pdev->dev);
 err_free_mem:
 
@@ -1468,6 +1469,7 @@ static int omap_i2c_remove(struct platform_device *pdev)
 		return ret;
 
 	omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	return 0;
diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c
index f3e5ff8522f0..213ba55e17c3 100644
--- a/drivers/i2c/busses/i2c-uniphier-f.c
+++ b/drivers/i2c/busses/i2c-uniphier-f.c
@@ -467,7 +467,7 @@ static int uniphier_fi2c_clk_init(struct device *dev,
 		bus_speed = UNIPHIER_FI2C_DEFAULT_SPEED;
 
 	if (!bus_speed) {
-		dev_err(dev, "clock-freqyency should not be zero\n");
+		dev_err(dev, "clock-frequency should not be zero\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/i2c/busses/i2c-uniphier.c b/drivers/i2c/busses/i2c-uniphier.c
index 1f4f3f53819c..89eaa8a7e1e0 100644
--- a/drivers/i2c/busses/i2c-uniphier.c
+++ b/drivers/i2c/busses/i2c-uniphier.c
@@ -328,7 +328,7 @@ static int uniphier_i2c_clk_init(struct device *dev,
 		bus_speed = UNIPHIER_I2C_DEFAULT_SPEED;
 
 	if (!bus_speed) {
-		dev_err(dev, "clock-freqyency should not be zero\n");
+		dev_err(dev, "clock-frequency should not be zero\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 3de93517efe4..14606afbfaa8 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -336,7 +336,6 @@ static ssize_t _show_port_gid_attr(struct ib_port *p,
 	union ib_gid gid;
 	struct ib_gid_attr gid_attr = {};
 	ssize_t ret;
-	va_list args;
 
 	ret = ib_query_gid(p->ibdev, p->port_num, tab_attr->index, &gid,
 			   &gid_attr);
@@ -348,7 +347,6 @@ static ssize_t _show_port_gid_attr(struct ib_port *p,
 err:
 	if (gid_attr.ndev)
 		dev_put(gid_attr.ndev);
-	va_end(args);
 	return ret;
 }
 
@@ -722,12 +720,11 @@ static struct attribute_group *get_counter_table(struct ib_device *dev,
 
 	if (get_perf_mad(dev, port_num, IB_PMA_CLASS_PORT_INFO,
 				&cpi, 40, sizeof(cpi)) >= 0) {
-
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH)
 			/* We have extended counters */
 			return &pma_group_ext;
 
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
 			/* But not the IETF ones */
 			return &pma_group_noietf;
 	}
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 26833bfa639b..d68f506c1922 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -817,17 +817,48 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
 }
 
-static void edit_counter(struct mlx4_counter *cnt,
-					struct ib_pma_portcounters *pma_cnt)
+static void edit_counter(struct mlx4_counter *cnt, void *counters,
+			 __be16 attr_id)
 {
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
-			     (be64_to_cpu(cnt->tx_bytes) >> 2));
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
-			     (be64_to_cpu(cnt->rx_bytes) >> 2));
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
-			     be64_to_cpu(cnt->tx_frames));
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
-			     be64_to_cpu(cnt->rx_frames));
+	switch (attr_id) {
+	case IB_PMA_PORT_COUNTERS:
+	{
+		struct ib_pma_portcounters *pma_cnt =
+			(struct ib_pma_portcounters *)counters;
+
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
+				     (be64_to_cpu(cnt->tx_bytes) >> 2));
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
+				     (be64_to_cpu(cnt->rx_bytes) >> 2));
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
+				     be64_to_cpu(cnt->tx_frames));
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
+				     be64_to_cpu(cnt->rx_frames));
+		break;
+	}
+	case IB_PMA_PORT_COUNTERS_EXT:
+	{
+		struct ib_pma_portcounters_ext *pma_cnt_ext =
+			(struct ib_pma_portcounters_ext *)counters;
+
+		pma_cnt_ext->port_xmit_data =
+			cpu_to_be64(be64_to_cpu(cnt->tx_bytes) >> 2);
+		pma_cnt_ext->port_rcv_data =
+			cpu_to_be64(be64_to_cpu(cnt->rx_bytes) >> 2);
+		pma_cnt_ext->port_xmit_packets = cnt->tx_frames;
+		pma_cnt_ext->port_rcv_packets = cnt->rx_frames;
+		break;
+	}
+	}
+}
+
+static int iboe_process_mad_port_info(void *out_mad)
+{
+	struct ib_class_port_info cpi = {};
+
+	cpi.capability_mask = IB_PMA_CLASS_CAP_EXT_WIDTH;
+	memcpy(out_mad, &cpi, sizeof(cpi));
+	return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
 }
 
 static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
@@ -842,6 +873,9 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT)
 		return -EINVAL;
 
+	if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)
+		return iboe_process_mad_port_info((void *)(out_mad->data + 40));
+
 	memset(&counter_stats, 0, sizeof(counter_stats));
 	mutex_lock(&dev->counters_table[port_num - 1].mutex);
 	list_for_each_entry(tmp_counter,
@@ -863,7 +897,8 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		switch (counter_stats.counter_mode & 0xf) {
 		case 0:
 			edit_counter(&counter_stats,
-				     (void *)(out_mad->data + 40));
+				     (void *)(out_mad->data + 40),
+				     in_mad->mad_hdr.attr_id);
 			err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
 			break;
 		default:
@@ -894,8 +929,10 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	 */
 	if (link == IB_LINK_LAYER_INFINIBAND) {
 		if (mlx4_is_slave(dev->dev) &&
-		    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
-		    in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS)
+		    (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
+		     (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS ||
+		      in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT ||
+		      in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)))
 			return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
 						in_grh, in_mad, out_mad);
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index bc5536f00b6c..fd97534762b8 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1681,9 +1681,12 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (qp->ibqp.uobject)
-		context->usr_page = cpu_to_be32(to_mucontext(ibqp->uobject->context)->uar.index);
+		context->usr_page = cpu_to_be32(
+			mlx4_to_hw_uar_index(dev->dev,
+					     to_mucontext(ibqp->uobject->context)->uar.index));
 	else
-		context->usr_page = cpu_to_be32(dev->priv_uar.index);
+		context->usr_page = cpu_to_be32(
+			mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index));
 
 	if (attr_mask & IB_QP_DEST_QPN)
 		context->remote_qpn = cpu_to_be32(attr->dest_qp_num);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 9116bc3988a6..34cb8e87c7b8 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -270,8 +270,10 @@ static int sq_overhead(enum ib_qp_type qp_type)
 		/* fall through */
 	case IB_QPT_RC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
-			sizeof(struct mlx5_wqe_atomic_seg) +
-			sizeof(struct mlx5_wqe_raddr_seg);
+			max(sizeof(struct mlx5_wqe_atomic_seg) +
+			    sizeof(struct mlx5_wqe_raddr_seg),
+			    sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+			    sizeof(struct mlx5_mkey_seg));
 		break;
 
 	case IB_QPT_XRC_TGT:
@@ -279,9 +281,9 @@ static int sq_overhead(enum ib_qp_type qp_type)
 
 	case IB_QPT_UC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
-			sizeof(struct mlx5_wqe_raddr_seg) +
-			sizeof(struct mlx5_wqe_umr_ctrl_seg) +
-			sizeof(struct mlx5_mkey_seg);
+			max(sizeof(struct mlx5_wqe_raddr_seg),
+			    sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+			    sizeof(struct mlx5_mkey_seg));
 		break;
 
 	case IB_QPT_UD:
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index 040bb8b5cb15..12503f15fbd6 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -323,9 +323,6 @@ struct ocrdma_cq {
 			 */
 	u32 max_hw_cqe;
 	bool phase_change;
-	bool deferred_arm, deferred_sol;
-	bool first_arm;
-
 	spinlock_t cq_lock ____cacheline_aligned; /* provide synchronization
 						   * to cq polling
 						   */
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 573849354cb9..f38743018cb4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -228,6 +228,11 @@ static int ocrdma_alloc_resources(struct ocrdma_dev *dev)
 
 	ocrdma_alloc_pd_pool(dev);
 
+	if (!ocrdma_alloc_stats_resources(dev)) {
+		pr_err("%s: stats resource allocation failed\n", __func__);
+		goto alloc_err;
+	}
+
 	spin_lock_init(&dev->av_tbl.lock);
 	spin_lock_init(&dev->flush_q_lock);
 	return 0;
@@ -238,6 +243,7 @@ alloc_err:
 
 static void ocrdma_free_resources(struct ocrdma_dev *dev)
 {
+	ocrdma_release_stats_resources(dev);
 	kfree(dev->stag_arr);
 	kfree(dev->qp_tbl);
 	kfree(dev->cq_tbl);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 86c303a620c1..255f774080a4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -64,10 +64,11 @@ static int ocrdma_add_stat(char *start, char *pcur,
 	return cpy_len;
 }
 
-static bool ocrdma_alloc_stats_mem(struct ocrdma_dev *dev)
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev)
 {
 	struct stats_mem *mem = &dev->stats_mem;
 
+	mutex_init(&dev->stats_lock);
 	/* Alloc mbox command mem*/
 	mem->size = max_t(u32, sizeof(struct ocrdma_rdma_stats_req),
 			sizeof(struct ocrdma_rdma_stats_resp));
@@ -91,13 +92,14 @@ static bool ocrdma_alloc_stats_mem(struct ocrdma_dev *dev)
 	return true;
 }
 
-static void ocrdma_release_stats_mem(struct ocrdma_dev *dev)
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev)
 {
 	struct stats_mem *mem = &dev->stats_mem;
 
 	if (mem->va)
 		dma_free_coherent(&dev->nic_info.pdev->dev, mem->size,
 				  mem->va, mem->pa);
+	mem->va = NULL;
 	kfree(mem->debugfs_mem);
 }
 
@@ -838,15 +840,9 @@ void ocrdma_add_port_stats(struct ocrdma_dev *dev)
 				&dev->reset_stats, &ocrdma_dbg_ops))
 		goto err;
 
-	/* Now create dma_mem for stats mbx command */
-	if (!ocrdma_alloc_stats_mem(dev))
-		goto err;
-
-	mutex_init(&dev->stats_lock);
 
 	return;
 err:
-	ocrdma_release_stats_mem(dev);
 	debugfs_remove_recursive(dev->dir);
 	dev->dir = NULL;
 }
@@ -855,9 +851,7 @@ void ocrdma_rem_port_stats(struct ocrdma_dev *dev)
 {
 	if (!dev->dir)
 		return;
-	debugfs_remove(dev->dir);
-	mutex_destroy(&dev->stats_lock);
-	ocrdma_release_stats_mem(dev);
+	debugfs_remove_recursive(dev->dir);
 }
 
 void ocrdma_init_debugfs(void)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
index c9e58d04c7b8..bba1fec4f11f 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
@@ -65,6 +65,8 @@ enum OCRDMA_STATS_TYPE {
 
 void ocrdma_rem_debugfs(void);
 void ocrdma_init_debugfs(void);
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev);
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev);
 void ocrdma_rem_port_stats(struct ocrdma_dev *dev);
 void ocrdma_add_port_stats(struct ocrdma_dev *dev);
 int ocrdma_pma_counters(struct ocrdma_dev *dev,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index d4c687b548d8..12420e4ecf3d 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -125,8 +125,8 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 					IB_DEVICE_SYS_IMAGE_GUID |
 					IB_DEVICE_LOCAL_DMA_LKEY |
 					IB_DEVICE_MEM_MGT_EXTENSIONS;
-	attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_srq_sge);
-	attr->max_sge_rd = 0;
+	attr->max_sge = dev->attr.max_send_sge;
+	attr->max_sge_rd = attr->max_sge;
 	attr->max_cq = dev->attr.max_cq;
 	attr->max_cqe = dev->attr.max_cqe;
 	attr->max_mr = dev->attr.max_mr;
@@ -1094,7 +1094,6 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
 	spin_lock_init(&cq->comp_handler_lock);
 	INIT_LIST_HEAD(&cq->sq_head);
 	INIT_LIST_HEAD(&cq->rq_head);
-	cq->first_arm = true;
 
 	if (ib_ctx) {
 		uctx = get_ocrdma_ucontext(ib_ctx);
@@ -2726,8 +2725,7 @@ static int ocrdma_update_ud_rcqe(struct ib_wc *ibwc, struct ocrdma_cqe *cqe)
 		OCRDMA_CQE_UD_STATUS_MASK) >> OCRDMA_CQE_UD_STATUS_SHIFT;
 	ibwc->src_qp = le32_to_cpu(cqe->flags_status_srcqpn) &
 						OCRDMA_CQE_SRCQP_MASK;
-	ibwc->pkey_index = le32_to_cpu(cqe->ud.rxlen_pkey) &
-						OCRDMA_CQE_PKEY_MASK;
+	ibwc->pkey_index = 0;
 	ibwc->wc_flags = IB_WC_GRH;
 	ibwc->byte_len = (le32_to_cpu(cqe->ud.rxlen_pkey) >>
 					OCRDMA_CQE_UD_XFER_LEN_SHIFT);
@@ -2911,12 +2909,9 @@ expand_cqe:
 	}
 stop_cqe:
 	cq->getp = cur_getp;
-	if (cq->deferred_arm || polled_hw_cqes) {
-		ocrdma_ring_cq_db(dev, cq->id, cq->deferred_arm,
-				  cq->deferred_sol, polled_hw_cqes);
-		cq->deferred_arm = false;
-		cq->deferred_sol = false;
-	}
+
+	if (polled_hw_cqes)
+		ocrdma_ring_cq_db(dev, cq->id, false, false, polled_hw_cqes);
 
 	return i;
 }
@@ -3000,13 +2995,7 @@ int ocrdma_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags cq_flags)
 	if (cq_flags & IB_CQ_SOLICITED)
 		sol_needed = true;
 
-	if (cq->first_arm) {
-		ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0);
-		cq->first_arm = false;
-	}
-
-	cq->deferred_arm = true;
-	cq->deferred_sol = sol_needed;
+	ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0);
 	spin_unlock_irqrestore(&cq->cq_lock, flags);
 
 	return 0;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 5ea0c14070d1..fa9c42ff1fb0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -245,8 +245,6 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_reset_mac_header(skb);
 	skb_pull(skb, IPOIB_ENCAP_LEN);
 
-	skb->truesize = SKB_TRUESIZE(skb->len);
-
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 050dfa175d16..25889311b1e9 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -456,7 +456,10 @@ out_locked:
 	return status;
 }
 
-static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
+/*
+ * Caller must hold 'priv->lock'
+ */
+static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_sa_multicast *multicast;
@@ -466,6 +469,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 	ib_sa_comp_mask comp_mask;
 	int ret = 0;
 
+	if (!priv->broadcast ||
+	    !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
+		return -EINVAL;
+
 	ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw);
 
 	rec.mgid     = mcast->mcmember.mgid;
@@ -525,20 +532,23 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 			rec.join_state = 4;
 #endif
 	}
+	spin_unlock_irq(&priv->lock);
 
 	multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
 					 &rec, comp_mask, GFP_KERNEL,
 					 ipoib_mcast_join_complete, mcast);
+	spin_lock_irq(&priv->lock);
 	if (IS_ERR(multicast)) {
 		ret = PTR_ERR(multicast);
 		ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
-		spin_lock_irq(&priv->lock);
 		/* Requeue this join task with a backoff delay */
 		__ipoib_mcast_schedule_join_thread(priv, mcast, 1);
 		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
 		spin_unlock_irq(&priv->lock);
 		complete(&mcast->done);
+		spin_lock_irq(&priv->lock);
 	}
+	return 0;
 }
 
 void ipoib_mcast_join_task(struct work_struct *work)
@@ -620,9 +630,10 @@ void ipoib_mcast_join_task(struct work_struct *work)
 				/* Found the next unjoined group */
 				init_completion(&mcast->done);
 				set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-				spin_unlock_irq(&priv->lock);
-				ipoib_mcast_join(dev, mcast);
-				spin_lock_irq(&priv->lock);
+				if (ipoib_mcast_join(dev, mcast)) {
+					spin_unlock_irq(&priv->lock);
+					return;
+				}
 			} else if (!delay_until ||
 				 time_before(mcast->delay_until, delay_until))
 				delay_until = mcast->delay_until;
@@ -641,10 +652,9 @@ out:
 	if (mcast) {
 		init_completion(&mcast->done);
 		set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+		ipoib_mcast_join(dev, mcast);
 	}
 	spin_unlock_irq(&priv->lock);
-	if (mcast)
-		ipoib_mcast_join(dev, mcast);
 }
 
 int ipoib_mcast_start_thread(struct net_device *dev)
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 6727954ab74b..e8a84d12b7ff 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1207,7 +1207,6 @@ static void xpad_led_disconnect(struct usb_xpad *xpad)
 #else
 static int xpad_led_probe(struct usb_xpad *xpad) { return 0; }
 static void xpad_led_disconnect(struct usb_xpad *xpad) { }
-static void xpad_identify_controller(struct usb_xpad *xpad) { }
 #endif
 
 static int xpad_start_input(struct usb_xpad *xpad)
diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c
index 4d446d5085aa..c01a1d648f9f 100644
--- a/drivers/input/keyboard/adp5589-keys.c
+++ b/drivers/input/keyboard/adp5589-keys.c
@@ -235,7 +235,7 @@ struct adp5589_kpad {
 	unsigned short gpimapsize;
 	unsigned extend_cfg;
 	bool is_adp5585;
-	bool adp5585_support_row5;
+	bool support_row5;
 #ifdef CONFIG_GPIOLIB
 	unsigned char gpiomap[ADP5589_MAXGPIO];
 	bool export_gpio;
@@ -485,7 +485,7 @@ static int adp5589_build_gpiomap(struct adp5589_kpad *kpad,
 	if (kpad->extend_cfg & C4_EXTEND_CFG)
 		pin_used[kpad->var->c4_extend_cfg] = true;
 
-	if (!kpad->adp5585_support_row5)
+	if (!kpad->support_row5)
 		pin_used[5] = true;
 
 	for (i = 0; i < kpad->var->maxgpio; i++)
@@ -884,12 +884,13 @@ static int adp5589_probe(struct i2c_client *client,
 
 	switch (id->driver_data) {
 	case ADP5585_02:
-		kpad->adp5585_support_row5 = true;
+		kpad->support_row5 = true;
 	case ADP5585_01:
 		kpad->is_adp5585 = true;
 		kpad->var = &const_adp5585;
 		break;
 	case ADP5589:
+		kpad->support_row5 = true;
 		kpad->var = &const_adp5589;
 		break;
 	}
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 378db10001df..4401be225d64 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -304,8 +304,10 @@ static int cap11xx_init_leds(struct device *dev,
 		led->cdev.brightness = LED_OFF;
 
 		error = of_property_read_u32(child, "reg", &reg);
-		if (error != 0 || reg >= num_leds)
+		if (error != 0 || reg >= num_leds) {
+			of_node_put(child);
 			return -EINVAL;
+		}
 
 		led->reg = reg;
 		led->priv = priv;
@@ -313,8 +315,10 @@ static int cap11xx_init_leds(struct device *dev,
 		INIT_WORK(&led->work, cap11xx_led_work);
 
 		error = devm_led_classdev_register(dev, &led->cdev);
-		if (error)
+		if (error) {
+			of_node_put(child);
 			return error;
+		}
 
 		priv->num_leds++;
 		led++;
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index d6d16fa78281..1f2337abcf2f 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -733,7 +733,7 @@ config INPUT_XEN_KBDDEV_FRONTEND
 	  module will be called xen-kbdfront.
 
 config INPUT_SIRFSOC_ONKEY
-	bool "CSR SiRFSoC power on/off/suspend key support"
+	tristate "CSR SiRFSoC power on/off/suspend key support"
 	depends on ARCH_SIRF && OF
 	default y
 	help
diff --git a/drivers/input/misc/sirfsoc-onkey.c b/drivers/input/misc/sirfsoc-onkey.c
index 9d5b89befe6f..ed7237f19539 100644
--- a/drivers/input/misc/sirfsoc-onkey.c
+++ b/drivers/input/misc/sirfsoc-onkey.c
@@ -101,7 +101,7 @@ static void sirfsoc_pwrc_close(struct input_dev *input)
 static const struct of_device_id sirfsoc_pwrc_of_match[] = {
 	{ .compatible = "sirf,prima2-pwrc" },
 	{},
-}
+};
 MODULE_DEVICE_TABLE(of, sirfsoc_pwrc_of_match);
 
 static int sirfsoc_pwrc_probe(struct platform_device *pdev)
diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index e272f06258ce..a3f0f5a47490 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -458,8 +458,6 @@ int vmmouse_init(struct psmouse *psmouse)
 	priv->abs_dev = abs_dev;
 	psmouse->private = priv;
 
-	input_set_capability(rel_dev, EV_REL, REL_WHEEL);
-
 	/* Set up and register absolute device */
 	snprintf(priv->phys, sizeof(priv->phys), "%s/input1",
 		 psmouse->ps2dev.serio->phys);
@@ -475,10 +473,6 @@ int vmmouse_init(struct psmouse *psmouse)
 	abs_dev->id.version = psmouse->model;
 	abs_dev->dev.parent = &psmouse->ps2dev.serio->dev;
 
-	error = input_register_device(priv->abs_dev);
-	if (error)
-		goto init_fail;
-
 	/* Set absolute device capabilities */
 	input_set_capability(abs_dev, EV_KEY, BTN_LEFT);
 	input_set_capability(abs_dev, EV_KEY, BTN_RIGHT);
@@ -488,6 +482,13 @@ int vmmouse_init(struct psmouse *psmouse)
 	input_set_abs_params(abs_dev, ABS_X, 0, VMMOUSE_MAX_X, 0, 0);
 	input_set_abs_params(abs_dev, ABS_Y, 0, VMMOUSE_MAX_Y, 0, 0);
 
+	error = input_register_device(priv->abs_dev);
+	if (error)
+		goto init_fail;
+
+	/* Add wheel capability to the relative device */
+	input_set_capability(rel_dev, EV_REL, REL_WHEEL);
+
 	psmouse->protocol_handler = vmmouse_process_byte;
 	psmouse->disconnect = vmmouse_disconnect;
 	psmouse->reconnect = vmmouse_reconnect;
diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index 8f828975ab10..1ca7f551e2da 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -134,7 +134,7 @@ static void serio_find_driver(struct serio *serio)
 	int error;
 
 	error = device_attach(&serio->dev);
-	if (error < 0)
+	if (error < 0 && error != -EPROBE_DEFER)
 		dev_warn(&serio->dev,
 			 "device_attach() failed for %s (%s), error: %d\n",
 			 serio->phys, serio->name, error);
diff --git a/drivers/input/touchscreen/colibri-vf50-ts.c b/drivers/input/touchscreen/colibri-vf50-ts.c
index 5d4903a402cc..69828d015d45 100644
--- a/drivers/input/touchscreen/colibri-vf50-ts.c
+++ b/drivers/input/touchscreen/colibri-vf50-ts.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 0b0f8c17f3f7..23fbe382da8b 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -822,16 +822,22 @@ static void edt_ft5x06_ts_get_defaults(struct device *dev,
 	int error;
 
 	error = device_property_read_u32(dev, "threshold", &val);
-	if (!error)
-		reg_addr->reg_threshold = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_threshold, val);
+		tsdata->threshold = val;
+	}
 
 	error = device_property_read_u32(dev, "gain", &val);
-	if (!error)
-		reg_addr->reg_gain = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_gain, val);
+		tsdata->gain = val;
+	}
 
 	error = device_property_read_u32(dev, "offset", &val);
-	if (!error)
-		reg_addr->reg_offset = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_offset, val);
+		tsdata->offset = val;
+	}
 }
 
 static void
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 62a400c5ba06..fb092f3f11cb 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1353,7 +1353,7 @@ void dmar_disable_qi(struct intel_iommu *iommu)
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts =  dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts =  readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_QIES))
 		goto end;
 
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 50464833d0b8..d9939fa9b588 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -249,12 +249,30 @@ static void intel_flush_pasid_dev(struct intel_svm *svm, struct intel_svm_dev *s
 static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
+	struct intel_svm_dev *sdev;
 
+	/* This might end up being called from exit_mmap(), *before* the page
+	 * tables are cleared. And __mmu_notifier_release() will delete us from
+	 * the list of notifiers so that our invalidate_range() callback doesn't
+	 * get called when the page tables are cleared. So we need to protect
+	 * against hardware accessing those page tables.
+	 *
+	 * We do it by clearing the entry in the PASID table and then flushing
+	 * the IOTLB and the PASID table caches. This might upset hardware;
+	 * perhaps we'll want to point the PASID to a dummy PGD (like the zero
+	 * page) so that we end up taking a fault that the hardware really
+	 * *has* to handle gracefully without affecting other processes.
+	 */
 	svm->iommu->pasid_table[svm->pasid].val = 0;
+	wmb();
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdev, &svm->devs, list) {
+		intel_flush_pasid_dev(svm, sdev, svm->pasid);
+		intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+	}
+	rcu_read_unlock();
 
-	/* There's no need to do any flush because we can't get here if there
-	 * are any devices left anyway. */
-	WARN_ON(!list_empty(&svm->devs));
 }
 
 static const struct mmu_notifier_ops intel_mmuops = {
@@ -379,7 +397,6 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 				goto out;
 			}
 			iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1;
-			mm = NULL;
 		} else
 			iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11);
 		wmb();
@@ -442,11 +459,11 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 				kfree_rcu(sdev, rcu);
 
 				if (list_empty(&svm->devs)) {
-					mmu_notifier_unregister(&svm->notifier, svm->mm);
 
 					idr_remove(&svm->iommu->pasid_idr, svm->pasid);
 					if (svm->mm)
-						mmput(svm->mm);
+						mmu_notifier_unregister(&svm->notifier, svm->mm);
+
 					/* We mandate that no page faults may be outstanding
 					 * for the PASID when intel_svm_unbind_mm() is called.
 					 * If that is not obeyed, subtle errors will happen.
@@ -507,6 +524,10 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 	struct intel_svm *svm = NULL;
 	int head, tail, handled = 0;
 
+	/* Clear PPR bit before reading head/tail registers, to
+	 * ensure that we get a new interrupt if needed. */
+	writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG);
+
 	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
 	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
 	while (head != tail) {
@@ -551,6 +572,9 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		 * any faults on kernel addresses. */
 		if (!svm->mm)
 			goto bad_req;
+		/* If the mm is already defunct, don't handle faults. */
+		if (!atomic_inc_not_zero(&svm->mm->mm_users))
+			goto bad_req;
 		down_read(&svm->mm->mmap_sem);
 		vma = find_extend_vma(svm->mm, address);
 		if (!vma || address < vma->vm_start)
@@ -567,6 +591,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		result = QI_RESP_SUCCESS;
 	invalid:
 		up_read(&svm->mm->mmap_sem);
+		mmput(svm->mm);
 	bad_req:
 		/* Accounting for major/minor faults? */
 		rcu_read_lock();
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index c12ba4516df2..ac596928f6b4 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -629,7 +629,7 @@ static void iommu_disable_irq_remapping(struct intel_iommu *iommu)
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts = readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_IRES))
 		goto end;
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 3447549fcc93..43dfd15c1dd2 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -66,7 +66,10 @@ struct its_node {
 	unsigned long		phys_base;
 	struct its_cmd_block	*cmd_base;
 	struct its_cmd_block	*cmd_write;
-	void			*tables[GITS_BASER_NR_REGS];
+	struct {
+		void		*base;
+		u32		order;
+	} tables[GITS_BASER_NR_REGS];
 	struct its_collection	*collections;
 	struct list_head	its_device_list;
 	u64			flags;
@@ -75,6 +78,9 @@ struct its_node {
 
 #define ITS_ITT_ALIGN		SZ_256
 
+/* Convert page order to size in bytes */
+#define PAGE_ORDER_TO_SIZE(o)	(PAGE_SIZE << (o))
+
 struct event_lpi_map {
 	unsigned long		*lpi_map;
 	u16			*col_map;
@@ -597,11 +603,6 @@ static void its_unmask_irq(struct irq_data *d)
 	lpi_set_config(d, true);
 }
 
-static void its_eoi_irq(struct irq_data *d)
-{
-	gic_write_eoir(d->hwirq);
-}
-
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
@@ -638,7 +639,7 @@ static struct irq_chip its_irq_chip = {
 	.name			= "ITS",
 	.irq_mask		= its_mask_irq,
 	.irq_unmask		= its_unmask_irq,
-	.irq_eoi		= its_eoi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
 	.irq_set_affinity	= its_set_affinity,
 	.irq_compose_msi_msg	= its_irq_compose_msi_msg,
 };
@@ -807,9 +808,10 @@ static void its_free_tables(struct its_node *its)
 	int i;
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		if (its->tables[i]) {
-			free_page((unsigned long)its->tables[i]);
-			its->tables[i] = NULL;
+		if (its->tables[i].base) {
+			free_pages((unsigned long)its->tables[i].base,
+				   its->tables[i].order);
+			its->tables[i].base = NULL;
 		}
 	}
 }
@@ -842,7 +844,6 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
 		u64 type = GITS_BASER_TYPE(val);
 		u64 entry_size = GITS_BASER_ENTRY_SIZE(val);
 		int order = get_order(psz);
-		int alloc_size;
 		int alloc_pages;
 		u64 tmp;
 		void *base;
@@ -874,9 +875,8 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
 			}
 		}
 
-		alloc_size = (1 << order) * PAGE_SIZE;
 retry_alloc_baser:
-		alloc_pages = (alloc_size / psz);
+		alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
 		if (alloc_pages > GITS_BASER_PAGES_MAX) {
 			alloc_pages = GITS_BASER_PAGES_MAX;
 			order = get_order(GITS_BASER_PAGES_MAX * psz);
@@ -890,7 +890,8 @@ retry_alloc_baser:
 			goto out_free;
 		}
 
-		its->tables[i] = base;
+		its->tables[i].base = base;
+		its->tables[i].order = order;
 
 retry_baser:
 		val = (virt_to_phys(base) 				 |
@@ -928,7 +929,7 @@ retry_baser:
 			shr = tmp & GITS_BASER_SHAREABILITY_MASK;
 			if (!shr) {
 				cache = GITS_BASER_nC;
-				__flush_dcache_area(base, alloc_size);
+				__flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order));
 			}
 			goto retry_baser;
 		}
@@ -940,7 +941,7 @@ retry_baser:
 			 * something is horribly wrong...
 			 */
 			free_pages((unsigned long)base, order);
-			its->tables[i] = NULL;
+			its->tables[i].base = NULL;
 
 			switch (psz) {
 			case SZ_16K:
@@ -961,7 +962,7 @@ retry_baser:
 		}
 
 		pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n",
-			(int)(alloc_size / entry_size),
+			(int)(PAGE_ORDER_TO_SIZE(order) / entry_size),
 			its_base_type_string[type],
 			(unsigned long)virt_to_phys(base),
 			psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 911758c056c1..8f9ebf714e2b 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -384,9 +384,6 @@ static struct irq_chip gic_chip = {
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoi_irq,
 	.irq_set_type		= gic_set_type,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= gic_set_affinity,
-#endif
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
@@ -400,9 +397,6 @@ static struct irq_chip gic_eoimode1_chip = {
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoimode1_eoi_irq,
 	.irq_set_type		= gic_set_type,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= gic_set_affinity,
-#endif
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.irq_set_vcpu_affinity	= gic_irq_set_vcpu_affinity,
@@ -443,7 +437,7 @@ static void gic_cpu_if_up(struct gic_chip_data *gic)
 	u32 bypass = 0;
 	u32 mode = 0;
 
-	if (static_key_true(&supports_deactivate))
+	if (gic == &gic_data[0] && static_key_true(&supports_deactivate))
 		mode = GIC_CPU_CTRL_EOImodeNS;
 
 	/*
@@ -1039,6 +1033,11 @@ static void __init __gic_init_bases(unsigned int gic_nr, int irq_start,
 		gic->chip.name = kasprintf(GFP_KERNEL, "GIC-%d", gic_nr);
 	}
 
+#ifdef CONFIG_SMP
+	if (gic_nr == 0)
+		gic->chip.irq_set_affinity = gic_set_affinity;
+#endif
+
 #ifdef CONFIG_GIC_NON_BANKED
 	if (percpu_offset) { /* Frankein-GIC without banked registers... */
 		unsigned int cpu;
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index 0704362f4c82..376b28074e0d 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -22,7 +22,6 @@
 #include <linux/of_irq.h>
 
 #include <asm/exception.h>
-#include <asm/mach/irq.h>
 
 #define SUN4I_IRQ_VECTOR_REG		0x00
 #define SUN4I_IRQ_PROTECTION_REG	0x08
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 2a506fe0c8a4..d1f8ab915b15 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -373,13 +373,7 @@ static void gigaset_freecshw(struct cardstate *cs)
 
 static void gigaset_device_release(struct device *dev)
 {
-	struct cardstate *cs = dev_get_drvdata(dev);
-
-	if (!cs)
-		return;
-	dev_set_drvdata(dev, NULL);
-	kfree(cs->hw.ser);
-	cs->hw.ser = NULL;
+	kfree(container_of(dev, struct ser_cardstate, dev.dev));
 }
 
 /*
@@ -408,7 +402,6 @@ static int gigaset_initcshw(struct cardstate *cs)
 		cs->hw.ser = NULL;
 		return rc;
 	}
-	dev_set_drvdata(&cs->hw.ser->dev.dev, cs);
 
 	tasklet_init(&cs->write_tasklet,
 		     gigaset_modem_fill, (unsigned long) cs);
diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index 8e2944784e00..afde4edef9ae 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -392,7 +392,7 @@ read_dma(struct tiger_ch *bc, u32 idx, int cnt)
 	}
 	stat = bchannel_get_rxbuf(&bc->bch, cnt);
 	/* only transparent use the count here, HDLC overun is detected later */
-	if (stat == ENOMEM) {
+	if (stat == -ENOMEM) {
 		pr_warning("%s.B%d: No memory for %d bytes\n",
 			   card->name, bc->bch.nr, cnt);
 		return;
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 33224cb91c5b..9f6acd5d1d2e 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -572,11 +572,13 @@ int nvm_register(struct request_queue *q, char *disk_name,
 		}
 	}
 
-	ret = nvm_get_sysblock(dev, &dev->sb);
-	if (!ret)
-		pr_err("nvm: device not initialized.\n");
-	else if (ret < 0)
-		pr_err("nvm: err (%d) on device initialization\n", ret);
+	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) {
+		ret = nvm_get_sysblock(dev, &dev->sb);
+		if (!ret)
+			pr_err("nvm: device not initialized.\n");
+		else if (ret < 0)
+			pr_err("nvm: err (%d) on device initialization\n", ret);
+	}
 
 	/* register device with a supported media manager */
 	down_write(&nvm_lock);
@@ -1055,9 +1057,11 @@ static long __nvm_ioctl_dev_init(struct nvm_ioctl_dev_init *init)
 	strncpy(info.mmtype, init->mmtype, NVM_MMTYPE_LEN);
 	info.fs_ppa.ppa = -1;
 
-	ret = nvm_init_sysblock(dev, &info);
-	if (ret)
-		return ret;
+	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) {
+		ret = nvm_init_sysblock(dev, &info);
+		if (ret)
+			return ret;
+	}
 
 	memcpy(&dev->sb, &info, sizeof(struct nvm_sb_info));
 
@@ -1117,7 +1121,10 @@ static long nvm_ioctl_dev_factory(struct file *file, void __user *arg)
 		dev->mt = NULL;
 	}
 
-	return nvm_dev_factory(dev, fact.flags);
+	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT)
+		return nvm_dev_factory(dev, fact.flags);
+
+	return 0;
 }
 
 static long nvm_ctl_ioctl(struct file *file, uint cmd, unsigned long arg)
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index d8c75958ced3..307db1ea22de 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -300,8 +300,10 @@ static int rrpc_move_valid_pages(struct rrpc *rrpc, struct rrpc_block *rblk)
 	}
 
 	page = mempool_alloc(rrpc->page_pool, GFP_NOIO);
-	if (!page)
+	if (!page) {
+		bio_put(bio);
 		return -ENOMEM;
+	}
 
 	while ((slot = find_first_zero_bit(rblk->invalid_pages,
 					    nr_pgs_per_blk)) < nr_pgs_per_blk) {
diff --git a/drivers/lightnvm/rrpc.h b/drivers/lightnvm/rrpc.h
index ef13ac7700c8..f7b37336353f 100644
--- a/drivers/lightnvm/rrpc.h
+++ b/drivers/lightnvm/rrpc.h
@@ -174,8 +174,7 @@ static inline sector_t rrpc_get_sector(sector_t laddr)
 static inline int request_intersects(struct rrpc_inflight_rq *r,
 				sector_t laddr_start, sector_t laddr_end)
 {
-	return (laddr_end >= r->l_start && laddr_end <= r->l_end) &&
-		(laddr_start >= r->l_start && laddr_start <= r->l_end);
+	return (laddr_end >= r->l_start) && (laddr_start <= r->l_end);
 }
 
 static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr,
@@ -184,6 +183,8 @@ static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr,
 	sector_t laddr_end = laddr + pages - 1;
 	struct rrpc_inflight_rq *rtmp;
 
+	WARN_ON(irqs_disabled());
+
 	spin_lock_irq(&rrpc->inflights.lock);
 	list_for_each_entry(rtmp, &rrpc->inflights.reqs, list) {
 		if (unlikely(request_intersects(rtmp, laddr, laddr_end))) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5df40480228b..dd834927bc66 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1191,6 +1191,8 @@ static void dm_unprep_request(struct request *rq)
 
 	if (clone)
 		free_rq_clone(clone);
+	else if (!tio->md->queue->mq_ops)
+		free_rq_tio(tio);
 }
 
 /*
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index e6e4bacb09ee..12099b09a9a7 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2048,6 +2048,7 @@ int db8500_prcmu_config_hotmon(u8 low, u8 high)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_config_hotmon);
 
 static int config_hot_period(u16 val)
 {
@@ -2074,11 +2075,13 @@ int db8500_prcmu_start_temp_sense(u16 cycles32k)
 
 	return config_hot_period(cycles32k);
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_start_temp_sense);
 
 int db8500_prcmu_stop_temp_sense(void)
 {
 	return config_hot_period(0xFFFF);
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_stop_temp_sense);
 
 static int prcmu_a9wdog(u8 cmd, u8 d0, u8 d1, u8 d2, u8 d3)
 {
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 677d0362f334..80f9afcb1382 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -458,7 +458,11 @@ static int mei_ioctl_client_notify_request(struct file *file, u32 request)
 {
 	struct mei_cl *cl = file->private_data;
 
-	return mei_cl_notify_request(cl, file, request);
+	if (request != MEI_HBM_NOTIFICATION_START &&
+	    request != MEI_HBM_NOTIFICATION_STOP)
+		return -EINVAL;
+
+	return mei_cl_notify_request(cl, file, (u8)request);
 }
 
 /**
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 5914263090fc..fe207e542032 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -47,13 +47,10 @@
 #include "queue.h"
 
 MODULE_ALIAS("mmc:block");
-
-#ifdef KERNEL
 #ifdef MODULE_PARAM_PREFIX
 #undef MODULE_PARAM_PREFIX
 #endif
 #define MODULE_PARAM_PREFIX "mmcblk."
-#endif
 
 #define INAND_CMD38_ARG_EXT_CSD  113
 #define INAND_CMD38_ARG_ERASE    0x00
@@ -655,8 +652,10 @@ static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev,
 	}
 
 	md = mmc_blk_get(bdev->bd_disk);
-	if (!md)
+	if (!md) {
+		err = -EINVAL;
 		goto cmd_err;
+	}
 
 	card = md->queue.card;
 	if (IS_ERR(card)) {
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 1c1b45ef3faf..3446097a43c0 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -925,6 +925,10 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 
 			dma_addr = dma_map_page(dma_dev, sg_page(sg), 0,
 						PAGE_SIZE, dir);
+			if (dma_mapping_error(dma_dev, dma_addr)) {
+				data->error = -EFAULT;
+				break;
+			}
 			if (direction == DMA_TO_DEVICE)
 				t->tx_dma = dma_addr + sg->offset;
 			else
@@ -1393,10 +1397,12 @@ static int mmc_spi_probe(struct spi_device *spi)
 		host->dma_dev = dev;
 		host->ones_dma = dma_map_single(dev, ones,
 				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, host->ones_dma))
+			goto fail_ones_dma;
 		host->data_dma = dma_map_single(dev, host->data,
 				sizeof(*host->data), DMA_BIDIRECTIONAL);
-
-		/* REVISIT in theory those map operations can fail... */
+		if (dma_mapping_error(dev, host->data_dma))
+			goto fail_data_dma;
 
 		dma_sync_single_for_cpu(host->dma_dev,
 				host->data_dma, sizeof(*host->data),
@@ -1462,6 +1468,11 @@ fail_glue_init:
 	if (host->dma_dev)
 		dma_unmap_single(host->dma_dev, host->data_dma,
 				sizeof(*host->data), DMA_BIDIRECTIONAL);
+fail_data_dma:
+	if (host->dma_dev)
+		dma_unmap_single(host->dma_dev, host->ones_dma,
+				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
+fail_ones_dma:
 	kfree(host->data);
 
 fail_nobuf1:
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index b6639ea0bf18..f6e4d9718035 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -2232,6 +2232,7 @@ err_irq:
 		dma_release_channel(host->tx_chan);
 	if (host->rx_chan)
 		dma_release_channel(host->rx_chan);
+	pm_runtime_dont_use_autosuspend(host->dev);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	if (host->dbclk)
@@ -2253,6 +2254,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev)
 	dma_release_channel(host->tx_chan);
 	dma_release_channel(host->rx_chan);
 
+	pm_runtime_dont_use_autosuspend(host->dev);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	device_init_wakeup(&pdev->dev, false);
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index ce08896b9d69..da824772bbb4 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -86,7 +86,7 @@ struct pxamci_host {
 static inline void pxamci_init_ocr(struct pxamci_host *host)
 {
 #ifdef CONFIG_REGULATOR
-	host->vcc = regulator_get_optional(mmc_dev(host->mmc), "vmmc");
+	host->vcc = devm_regulator_get_optional(mmc_dev(host->mmc), "vmmc");
 
 	if (IS_ERR(host->vcc))
 		host->vcc = NULL;
@@ -654,12 +654,8 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
-	if (!r || irq < 0)
-		return -ENXIO;
-
-	r = request_mem_region(r->start, SZ_4K, DRIVER_NAME);
-	if (!r)
-		return -EBUSY;
+	if (irq < 0)
+		return irq;
 
 	mmc = mmc_alloc_host(sizeof(struct pxamci_host), &pdev->dev);
 	if (!mmc) {
@@ -695,7 +691,7 @@ static int pxamci_probe(struct platform_device *pdev)
 	host->pdata = pdev->dev.platform_data;
 	host->clkrt = CLKRT_OFF;
 
-	host->clk = clk_get(&pdev->dev, NULL);
+	host->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
 		host->clk = NULL;
@@ -727,9 +723,9 @@ static int pxamci_probe(struct platform_device *pdev)
 	host->irq = irq;
 	host->imask = MMC_I_MASK_ALL;
 
-	host->base = ioremap(r->start, SZ_4K);
-	if (!host->base) {
-		ret = -ENOMEM;
+	host->base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(host->base)) {
+		ret = PTR_ERR(host->base);
 		goto out;
 	}
 
@@ -742,7 +738,8 @@ static int pxamci_probe(struct platform_device *pdev)
 	writel(64, host->base + MMC_RESTO);
 	writel(host->imask, host->base + MMC_I_MASK);
 
-	ret = request_irq(host->irq, pxamci_irq, 0, DRIVER_NAME, host);
+	ret = devm_request_irq(&pdev->dev, host->irq, pxamci_irq, 0,
+			       DRIVER_NAME, host);
 	if (ret)
 		goto out;
 
@@ -804,7 +801,7 @@ static int pxamci_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
 		goto out;
 	} else {
-		mmc->caps |= host->pdata->gpio_card_ro_invert ?
+		mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
 			0 : MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
@@ -833,14 +830,9 @@ out:
 			dma_release_channel(host->dma_chan_rx);
 		if (host->dma_chan_tx)
 			dma_release_channel(host->dma_chan_tx);
-		if (host->base)
-			iounmap(host->base);
-		if (host->clk)
-			clk_put(host->clk);
 	}
 	if (mmc)
 		mmc_free_host(mmc);
-	release_resource(r);
 	return ret;
 }
 
@@ -859,9 +851,6 @@ static int pxamci_remove(struct platform_device *pdev)
 			gpio_ro = host->pdata->gpio_card_ro;
 			gpio_power = host->pdata->gpio_power;
 		}
-		if (host->vcc)
-			regulator_put(host->vcc);
-
 		if (host->pdata && host->pdata->exit)
 			host->pdata->exit(&pdev->dev, mmc);
 
@@ -870,16 +859,10 @@ static int pxamci_remove(struct platform_device *pdev)
 		       END_CMD_RES|PRG_DONE|DATA_TRAN_DONE,
 		       host->base + MMC_I_MASK);
 
-		free_irq(host->irq, host);
 		dmaengine_terminate_all(host->dma_chan_rx);
 		dmaengine_terminate_all(host->dma_chan_tx);
 		dma_release_channel(host->dma_chan_rx);
 		dma_release_channel(host->dma_chan_tx);
-		iounmap(host->base);
-
-		clk_put(host->clk);
-
-		release_resource(host->res);
 
 		mmc_free_host(mmc);
 	}
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index f6047fc94062..a5cda926d38e 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -146,6 +146,33 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
 	.ops = &sdhci_acpi_ops_int,
 };
 
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+	int gpio_cd = mmc_gpio_get_cd(mmc);
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int ret = 0;
+
+	if (!gpio_cd)
+		return 0;
+
+	pm_runtime_get_sync(mmc->parent);
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->flags & SDHCI_DEVICE_DEAD)
+		goto out;
+
+	ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT);
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc->parent);
+	pm_runtime_put_autosuspend(mmc->parent);
+
+	return ret;
+}
+
 static int sdhci_acpi_emmc_probe_slot(struct platform_device *pdev,
 				      const char *hid, const char *uid)
 {
@@ -196,6 +223,9 @@ static int sdhci_acpi_sd_probe_slot(struct platform_device *pdev,
 
 	/* Platform specific code during sd probe slot goes here */
 
+	if (hid && !strcmp(hid, "80865ACA"))
+		host->mmc_host_ops.get_cd = bxt_get_cd;
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 7e7d8f0c9438..9cb86fb25976 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -217,6 +217,7 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 pm_runtime_disable:
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
 clocks_disable_unprepare:
 	clk_disable_unprepare(priv->gck);
 	clk_disable_unprepare(priv->mainck);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index cc851b065d0a..df3b8eced8c4 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -330,6 +330,33 @@ static void spt_read_drive_strength(struct sdhci_host *host)
 	sdhci_pci_spt_drive_strength = 0x10 | ((val >> 12) & 0xf);
 }
 
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+	int gpio_cd = mmc_gpio_get_cd(mmc);
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int ret = 0;
+
+	if (!gpio_cd)
+		return 0;
+
+	pm_runtime_get_sync(mmc->parent);
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->flags & SDHCI_DEVICE_DEAD)
+		goto out;
+
+	ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT);
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc->parent);
+	pm_runtime_put_autosuspend(mmc->parent);
+
+	return ret;
+}
+
 static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
@@ -362,6 +389,10 @@ static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
 	slot->cd_con_id = NULL;
 	slot->cd_idx = 0;
 	slot->cd_override_level = true;
+	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXT_SD ||
+	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD)
+		slot->host->mmc_host_ops.get_cd = bxt_get_cd;
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index d622435d1bcc..add9fdfd1d8f 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1360,7 +1360,7 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	sdhci_runtime_pm_get(host);
 
 	/* Firstly check card presence */
-	present = sdhci_do_get_cd(host);
+	present = mmc->ops->get_cd(mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 
@@ -2849,6 +2849,8 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev,
 
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
+	host->mmc_host_ops = sdhci_ops;
+	mmc->ops = &host->mmc_host_ops;
 
 	return host;
 }
@@ -3037,7 +3039,6 @@ int sdhci_add_host(struct sdhci_host *host)
 	/*
 	 * Set host parameters.
 	 */
-	mmc->ops = &sdhci_ops;
 	max_clk = host->max_clk;
 
 	if (host->ops->get_min_clock)
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 7654ae5d2b4e..0115e9907bf8 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -430,6 +430,7 @@ struct sdhci_host {
 
 	/* Internal data */
 	struct mmc_host *mmc;	/* MMC structure */
+	struct mmc_host_ops mmc_host_ops;	/* MMC host ops */
 	u64 dma_mask;		/* custom DMA mask */
 
 #if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 1ca8a1359cbc..6234eab38ff3 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -445,7 +445,7 @@ static void sh_mmcif_request_dma(struct sh_mmcif_host *host)
 							pdata->slave_id_rx);
 	} else {
 		host->chan_tx = dma_request_slave_channel(dev, "tx");
-		host->chan_tx = dma_request_slave_channel(dev, "rx");
+		host->chan_rx = dma_request_slave_channel(dev, "rx");
 	}
 	dev_dbg(dev, "%s: got channel TX %p RX %p\n", __func__, host->chan_tx,
 		host->chan_rx);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 56b560558884..b7f1a9919033 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev);
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats);
 static void bond_slave_arr_handler(struct work_struct *work);
+static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
+				  int mod);
 
 /*---------------------------- General routines -----------------------------*/
 
@@ -2127,6 +2129,7 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
+			bond_update_speed_duplex(slave);
 			bond_set_slave_link_state(slave, BOND_LINK_UP,
 						  BOND_SLAVE_NOTIFY_NOW);
 			slave->last_link_up = jiffies;
@@ -2459,7 +2462,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		 struct slave *slave)
 {
 	struct arphdr *arp = (struct arphdr *)skb->data;
-	struct slave *curr_active_slave;
+	struct slave *curr_active_slave, *curr_arp_slave;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
 	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
@@ -2506,26 +2509,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		     &sip, &tip);
 
 	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
 
-	/* Backup slaves won't see the ARP reply, but do come through
-	 * here for each ARP probe (so we swap the sip/tip to validate
-	 * the probe).  In a "redundant switch, common router" type of
-	 * configuration, the ARP probe will (hopefully) travel from
-	 * the active, through one switch, the router, then the other
-	 * switch before reaching the backup.
+	/* We 'trust' the received ARP enough to validate it if:
+	 *
+	 * (a) the slave receiving the ARP is active (which includes the
+	 * current ARP slave, if any), or
+	 *
+	 * (b) the receiving slave isn't active, but there is a currently
+	 * active slave and it received valid arp reply(s) after it became
+	 * the currently active slave, or
+	 *
+	 * (c) there is an ARP slave that sent an ARP during the prior ARP
+	 * interval, and we receive an ARP reply on any slave.  We accept
+	 * these because switch FDB update delays may deliver the ARP
+	 * reply to a slave other than the sender of the ARP request.
 	 *
-	 * We 'trust' the arp requests if there is an active slave and
-	 * it received valid arp reply(s) after it became active. This
-	 * is done to avoid endless looping when we can't reach the
+	 * Note: for (b), backup slaves are receiving the broadcast ARP
+	 * request, not a reply.  This request passes from the sending
+	 * slave through the L2 switch(es) to the receiving slave.  Since
+	 * this is checking the request, sip/tip are swapped for
+	 * validation.
+	 *
+	 * This is done to avoid endless looping when we can't reach the
 	 * arp_ip_target and fool ourselves with our own arp requests.
 	 */
-
 	if (bond_is_active_slave(slave))
 		bond_validate_arp(bond, slave, sip, tip);
 	else if (curr_active_slave &&
 		 time_after(slave_last_rx(bond, curr_active_slave),
 			    curr_active_slave->last_link_up))
 		bond_validate_arp(bond, slave, tip, sip);
+	else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
+		 bond_time_in_interval(bond,
+				       dev_trans_start(curr_arp_slave->dev), 1))
+		bond_validate_arp(bond, slave, sip, tip);
 
 out_unlock:
 	if (arp != (struct arphdr *)skb->data)
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index fc5b75675cd8..eb7192fab593 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -117,6 +117,9 @@ MODULE_LICENSE("GPL v2");
  */
 #define EMS_USB_ARM7_CLOCK 8000000
 
+#define CPC_TX_QUEUE_TRIGGER_LOW	25
+#define CPC_TX_QUEUE_TRIGGER_HIGH	35
+
 /*
  * CAN-Message representation in a CPC_MSG. Message object type is
  * CPC_MSG_TYPE_CAN_FRAME or CPC_MSG_TYPE_RTR_FRAME or
@@ -278,6 +281,11 @@ static void ems_usb_read_interrupt_callback(struct urb *urb)
 	switch (urb->status) {
 	case 0:
 		dev->free_slots = dev->intr_in_buffer[1];
+		if(dev->free_slots > CPC_TX_QUEUE_TRIGGER_HIGH){
+			if (netif_queue_stopped(netdev)){
+				netif_wake_queue(netdev);
+			}
+		}
 		break;
 
 	case -ECONNRESET: /* unlink */
@@ -526,8 +534,6 @@ static void ems_usb_write_bulk_callback(struct urb *urb)
 	/* Release context */
 	context->echo_index = MAX_TX_URBS;
 
-	if (netif_queue_stopped(netdev))
-		netif_wake_queue(netdev);
 }
 
 /*
@@ -587,7 +593,7 @@ static int ems_usb_start(struct ems_usb *dev)
 	int err, i;
 
 	dev->intr_in_buffer[0] = 0;
-	dev->free_slots = 15; /* initial size */
+	dev->free_slots = 50; /* initial size */
 
 	for (i = 0; i < MAX_RX_URBS; i++) {
 		struct urb *urb = NULL;
@@ -835,7 +841,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne
 
 		/* Slow down tx path */
 		if (atomic_read(&dev->active_tx_urbs) >= MAX_TX_URBS ||
-		    dev->free_slots < 5) {
+		    dev->free_slots < CPC_TX_QUEUE_TRIGGER_LOW) {
 			netif_stop_queue(netdev);
 		}
 	}
diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c
index cc6c54553418..a47f52f44b0d 100644
--- a/drivers/net/dsa/mv88e6352.c
+++ b/drivers/net/dsa/mv88e6352.c
@@ -25,6 +25,7 @@
 static const struct mv88e6xxx_switch_id mv88e6352_table[] = {
 	{ PORT_SWITCH_ID_6172, "Marvell 88E6172" },
 	{ PORT_SWITCH_ID_6176, "Marvell 88E6176" },
+	{ PORT_SWITCH_ID_6240, "Marvell 88E6240" },
 	{ PORT_SWITCH_ID_6320, "Marvell 88E6320" },
 	{ PORT_SWITCH_ID_6320_A1, "Marvell 88E6320 (A1)" },
 	{ PORT_SWITCH_ID_6320_A2, "Marvell 88e6320 (A2)" },
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index cf34681af4f6..512c8c0be1b4 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -1555,7 +1555,7 @@ static int _mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 
 	if (vlan.vid != vid || !vlan.valid ||
 	    vlan.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
-		return -ENOENT;
+		return -EOPNOTSUPP;
 
 	vlan.data[port] = GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER;
 
@@ -1582,6 +1582,7 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
 			    const struct switchdev_obj_port_vlan *vlan)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	const u16 defpvid = 4000 + ds->index * DSA_MAX_PORTS + port;
 	u16 pvid, vid;
 	int err = 0;
 
@@ -1597,7 +1598,8 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
 			goto unlock;
 
 		if (vid == pvid) {
-			err = _mv88e6xxx_port_pvid_set(ds, port, 0);
+			/* restore reserved VLAN ID */
+			err = _mv88e6xxx_port_pvid_set(ds, port, defpvid);
 			if (err)
 				goto unlock;
 		}
@@ -1889,26 +1891,20 @@ unlock:
 
 int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, u32 members)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	const u16 pvid = 4000 + ds->index * DSA_MAX_PORTS + port;
-	int err;
-
-	/* The port joined a bridge, so leave its reserved VLAN */
-	mutex_lock(&ps->smi_mutex);
-	err = _mv88e6xxx_port_vlan_del(ds, port, pvid);
-	if (!err)
-		err = _mv88e6xxx_port_pvid_set(ds, port, 0);
-	mutex_unlock(&ps->smi_mutex);
-	return err;
+	return 0;
 }
 
 int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, u32 members)
 {
+	return 0;
+}
+
+static int mv88e6xxx_setup_port_default_vlan(struct dsa_switch *ds, int port)
+{
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	const u16 pvid = 4000 + ds->index * DSA_MAX_PORTS + port;
 	int err;
 
-	/* The port left the bridge, so join its reserved VLAN */
 	mutex_lock(&ps->smi_mutex);
 	err = _mv88e6xxx_port_vlan_add(ds, port, pvid, true);
 	if (!err)
@@ -2192,8 +2188,7 @@ int mv88e6xxx_setup_ports(struct dsa_switch *ds)
 		if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i))
 			continue;
 
-		/* setup the unbridged state */
-		ret = mv88e6xxx_port_bridge_leave(ds, i, 0);
+		ret = mv88e6xxx_setup_port_default_vlan(ds, i);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 2777289a26c0..2f79d29f17f2 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -1501,6 +1501,7 @@ static const struct pcmcia_device_id pcnet_ids[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x026f, 0x030a),
 	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1103),
 	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1121),
+	PCMCIA_DEVICE_MANF_CARD(0xc001, 0x0009),
 	PCMCIA_DEVICE_PROD_ID12("2408LAN", "Ethernet", 0x352fff7f, 0x00b2e941),
 	PCMCIA_DEVICE_PROD_ID1234("Socket", "CF 10/100 Ethernet Card", "Revision B", "05/11/06", 0xb38bcc2e, 0x4de88352, 0xeaca6c8d, 0x7e57c22e),
 	PCMCIA_DEVICE_PROD_ID123("Cardwell", "PCMCIA", "ETHERNET", 0x9533672e, 0x281f1c5d, 0x3ff7175b),
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 3f3bcbea15bd..0907ab6ff309 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -2380,7 +2380,7 @@ static int et131x_tx_dma_memory_alloc(struct et131x_adapter *adapter)
 						    sizeof(u32),
 						    &tx_ring->tx_status_pa,
 						    GFP_KERNEL);
-	if (!tx_ring->tx_status_pa) {
+	if (!tx_ring->tx_status) {
 		dev_err(&adapter->pdev->dev,
 			"Cannot alloc memory for Tx status block\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c
index 87e727b921dc..fcdf5dda448f 100644
--- a/drivers/net/ethernet/amd/am79c961a.c
+++ b/drivers/net/ethernet/amd/am79c961a.c
@@ -50,8 +50,8 @@ static const char version[] =
 static void write_rreg(u_long base, u_int reg, u_int val)
 {
 	asm volatile(
-	"str%?h	%1, [%2]	@ NET_RAP\n\t"
-	"str%?h	%0, [%2, #-4]	@ NET_RDP"
+	"strh	%1, [%2]	@ NET_RAP\n\t"
+	"strh	%0, [%2, #-4]	@ NET_RDP"
 	:
 	: "r" (val), "r" (reg), "r" (ISAIO_BASE + 0x0464));
 }
@@ -60,8 +60,8 @@ static inline unsigned short read_rreg(u_long base_addr, u_int reg)
 {
 	unsigned short v;
 	asm volatile(
-	"str%?h	%1, [%2]	@ NET_RAP\n\t"
-	"ldr%?h	%0, [%2, #-4]	@ NET_RDP"
+	"strh	%1, [%2]	@ NET_RAP\n\t"
+	"ldrh	%0, [%2, #-4]	@ NET_RDP"
 	: "=r" (v)
 	: "r" (reg), "r" (ISAIO_BASE + 0x0464));
 	return v;
@@ -70,8 +70,8 @@ static inline unsigned short read_rreg(u_long base_addr, u_int reg)
 static inline void write_ireg(u_long base, u_int reg, u_int val)
 {
 	asm volatile(
-	"str%?h	%1, [%2]	@ NET_RAP\n\t"
-	"str%?h	%0, [%2, #8]	@ NET_IDP"
+	"strh	%1, [%2]	@ NET_RAP\n\t"
+	"strh	%0, [%2, #8]	@ NET_IDP"
 	:
 	: "r" (val), "r" (reg), "r" (ISAIO_BASE + 0x0464));
 }
@@ -80,8 +80,8 @@ static inline unsigned short read_ireg(u_long base_addr, u_int reg)
 {
 	u_short v;
 	asm volatile(
-	"str%?h	%1, [%2]	@ NAT_RAP\n\t"
-	"ldr%?h	%0, [%2, #8]	@ NET_IDP\n\t"
+	"strh	%1, [%2]	@ NAT_RAP\n\t"
+	"ldrh	%0, [%2, #8]	@ NET_IDP\n\t"
 	: "=r" (v)
 	: "r" (reg), "r" (ISAIO_BASE + 0x0464));
 	return v;
@@ -96,7 +96,7 @@ am_writebuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigne
 	offset = ISAMEM_BASE + (offset << 1);
 	length = (length + 1) & ~1;
 	if ((int)buf & 2) {
-		asm volatile("str%?h	%2, [%0], #4"
+		asm volatile("strh	%2, [%0], #4"
 		 : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8)));
 		buf += 2;
 		length -= 2;
@@ -104,20 +104,20 @@ am_writebuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigne
 	while (length > 8) {
 		register unsigned int tmp asm("r2"), tmp2 asm("r3");
 		asm volatile(
-			"ldm%?ia	%0!, {%1, %2}"
+			"ldmia	%0!, {%1, %2}"
 			: "+r" (buf), "=&r" (tmp), "=&r" (tmp2));
 		length -= 8;
 		asm volatile(
-			"str%?h	%1, [%0], #4\n\t"
-			"mov%?	%1, %1, lsr #16\n\t"
-			"str%?h	%1, [%0], #4\n\t"
-			"str%?h	%2, [%0], #4\n\t"
-			"mov%?	%2, %2, lsr #16\n\t"
-			"str%?h	%2, [%0], #4"
+			"strh	%1, [%0], #4\n\t"
+			"mov	%1, %1, lsr #16\n\t"
+			"strh	%1, [%0], #4\n\t"
+			"strh	%2, [%0], #4\n\t"
+			"mov	%2, %2, lsr #16\n\t"
+			"strh	%2, [%0], #4"
 		: "+r" (offset), "=&r" (tmp), "=&r" (tmp2));
 	}
 	while (length > 0) {
-		asm volatile("str%?h	%2, [%0], #4"
+		asm volatile("strh	%2, [%0], #4"
 		 : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8)));
 		buf += 2;
 		length -= 2;
@@ -132,23 +132,23 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned
 	if ((int)buf & 2) {
 		unsigned int tmp;
 		asm volatile(
-			"ldr%?h	%2, [%0], #4\n\t"
-			"str%?b	%2, [%1], #1\n\t"
-			"mov%?	%2, %2, lsr #8\n\t"
-			"str%?b	%2, [%1], #1"
+			"ldrh	%2, [%0], #4\n\t"
+			"strb	%2, [%1], #1\n\t"
+			"mov	%2, %2, lsr #8\n\t"
+			"strb	%2, [%1], #1"
 		: "=&r" (offset), "=&r" (buf), "=r" (tmp): "0" (offset), "1" (buf));
 		length -= 2;
 	}
 	while (length > 8) {
 		register unsigned int tmp asm("r2"), tmp2 asm("r3"), tmp3;
 		asm volatile(
-			"ldr%?h	%2, [%0], #4\n\t"
-			"ldr%?h	%4, [%0], #4\n\t"
-			"ldr%?h	%3, [%0], #4\n\t"
-			"orr%?	%2, %2, %4, lsl #16\n\t"
-			"ldr%?h	%4, [%0], #4\n\t"
-			"orr%?	%3, %3, %4, lsl #16\n\t"
-			"stm%?ia	%1!, {%2, %3}"
+			"ldrh	%2, [%0], #4\n\t"
+			"ldrh	%4, [%0], #4\n\t"
+			"ldrh	%3, [%0], #4\n\t"
+			"orr	%2, %2, %4, lsl #16\n\t"
+			"ldrh	%4, [%0], #4\n\t"
+			"orr	%3, %3, %4, lsl #16\n\t"
+			"stmia	%1!, {%2, %3}"
 		: "=&r" (offset), "=&r" (buf), "=r" (tmp), "=r" (tmp2), "=r" (tmp3)
 		: "0" (offset), "1" (buf));
 		length -= 8;
@@ -156,10 +156,10 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned
 	while (length > 0) {
 		unsigned int tmp;
 		asm volatile(
-			"ldr%?h	%2, [%0], #4\n\t"
-			"str%?b	%2, [%1], #1\n\t"
-			"mov%?	%2, %2, lsr #8\n\t"
-			"str%?b	%2, [%1], #1"
+			"ldrh	%2, [%0], #4\n\t"
+			"strb	%2, [%1], #1\n\t"
+			"mov	%2, %2, lsr #8\n\t"
+			"strb	%2, [%1], #1"
 		: "=&r" (offset), "=&r" (buf), "=r" (tmp) : "0" (offset), "1" (buf));
 		length -= 2;
 	}
diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c
index 256f590f6bb1..3a7ebfdda57d 100644
--- a/drivers/net/ethernet/amd/lance.c
+++ b/drivers/net/ethernet/amd/lance.c
@@ -547,8 +547,8 @@ static int __init lance_probe1(struct net_device *dev, int ioaddr, int irq, int
 	/* Make certain the data structures used by the LANCE are aligned and DMAble. */
 
 	lp = kzalloc(sizeof(*lp), GFP_DMA | GFP_KERNEL);
-	if(lp==NULL)
-		return -ENODEV;
+	if (!lp)
+		return -ENOMEM;
 	if (lance_debug > 6) printk(" (#0x%05lx)", (unsigned long)lp);
 	dev->ml_priv = lp;
 	lp->name = chipname;
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index abe1eabc0171..6446af1403f7 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -163,7 +163,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 		struct sk_buff *skb = tx_buff->skb;
 		unsigned int info = le32_to_cpu(txbd->info);
 
-		if ((info & FOR_EMAC) || !txbd->data)
+		if ((info & FOR_EMAC) || !txbd->data || !skb)
 			break;
 
 		if (unlikely(info & (DROP | DEFR | LTCL | UFLO))) {
@@ -191,6 +191,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 
 		txbd->data = 0;
 		txbd->info = 0;
+		tx_buff->skb = NULL;
 
 		*txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM;
 	}
@@ -446,6 +447,9 @@ static int arc_emac_open(struct net_device *ndev)
 		*last_rx_bd = (*last_rx_bd + 1) % RX_BD_NUM;
 	}
 
+	priv->txbd_curr = 0;
+	priv->txbd_dirty = 0;
+
 	/* Clean Tx BD's */
 	memset(priv->txbd, 0, TX_RING_SZ);
 
@@ -514,6 +518,64 @@ static void arc_emac_set_rx_mode(struct net_device *ndev)
 }
 
 /**
+ * arc_free_tx_queue - free skb from tx queue
+ * @ndev:	Pointer to the network device.
+ *
+ * This function must be called while EMAC disable
+ */
+static void arc_free_tx_queue(struct net_device *ndev)
+{
+	struct arc_emac_priv *priv = netdev_priv(ndev);
+	unsigned int i;
+
+	for (i = 0; i < TX_BD_NUM; i++) {
+		struct arc_emac_bd *txbd = &priv->txbd[i];
+		struct buffer_state *tx_buff = &priv->tx_buff[i];
+
+		if (tx_buff->skb) {
+			dma_unmap_single(&ndev->dev, dma_unmap_addr(tx_buff, addr),
+					 dma_unmap_len(tx_buff, len), DMA_TO_DEVICE);
+
+			/* return the sk_buff to system */
+			dev_kfree_skb_irq(tx_buff->skb);
+		}
+
+		txbd->info = 0;
+		txbd->data = 0;
+		tx_buff->skb = NULL;
+	}
+}
+
+/**
+ * arc_free_rx_queue - free skb from rx queue
+ * @ndev:	Pointer to the network device.
+ *
+ * This function must be called while EMAC disable
+ */
+static void arc_free_rx_queue(struct net_device *ndev)
+{
+	struct arc_emac_priv *priv = netdev_priv(ndev);
+	unsigned int i;
+
+	for (i = 0; i < RX_BD_NUM; i++) {
+		struct arc_emac_bd *rxbd = &priv->rxbd[i];
+		struct buffer_state *rx_buff = &priv->rx_buff[i];
+
+		if (rx_buff->skb) {
+			dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr),
+					dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE);
+
+			/* return the sk_buff to system */
+			dev_kfree_skb_irq(rx_buff->skb);
+		}
+
+		rxbd->info = 0;
+		rxbd->data = 0;
+		rx_buff->skb = NULL;
+	}
+}
+
+/**
  * arc_emac_stop - Close the network device.
  * @ndev:	Pointer to the network device.
  *
@@ -534,6 +596,10 @@ static int arc_emac_stop(struct net_device *ndev)
 	/* Disable EMAC */
 	arc_reg_clr(priv, R_CTRL, EN_MASK);
 
+	/* Return the sk_buff to system */
+	arc_free_tx_queue(ndev);
+	arc_free_rx_queue(ndev);
+
 	return 0;
 }
 
@@ -610,7 +676,6 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 	dma_unmap_addr_set(&priv->tx_buff[*txbd_curr], addr, addr);
 	dma_unmap_len_set(&priv->tx_buff[*txbd_curr], len, len);
 
-	priv->tx_buff[*txbd_curr].skb = skb;
 	priv->txbd[*txbd_curr].data = cpu_to_le32(addr);
 
 	/* Make sure pointer to data buffer is set */
@@ -620,6 +685,11 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 
 	*info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len);
 
+	/* Make sure info word is set */
+	wmb();
+
+	priv->tx_buff[*txbd_curr].skb = skb;
+
 	/* Increment index to point to the next BD */
 	*txbd_curr = (*txbd_curr + 1) % TX_BD_NUM;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index d946bba43726..1fb80100e5e7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6185,26 +6185,80 @@ static int bnx2x_format_ver(u32 num, u8 *str, u16 *len)
 		shift -= 4;
 		digit = ((num & mask) >> shift);
 		if (digit == 0 && remove_leading_zeros) {
-			mask = mask >> 4;
-			continue;
-		} else if (digit < 0xa)
-			*str_ptr = digit + '0';
-		else
-			*str_ptr = digit - 0xa + 'a';
-		remove_leading_zeros = 0;
-		str_ptr++;
-		(*len)--;
+			*str_ptr = '0';
+		} else {
+			if (digit < 0xa)
+				*str_ptr = digit + '0';
+			else
+				*str_ptr = digit - 0xa + 'a';
+
+			remove_leading_zeros = 0;
+			str_ptr++;
+			(*len)--;
+		}
 		mask = mask >> 4;
 		if (shift == 4*4) {
+			if (remove_leading_zeros) {
+				str_ptr++;
+				(*len)--;
+			}
 			*str_ptr = '.';
 			str_ptr++;
 			(*len)--;
 			remove_leading_zeros = 1;
 		}
 	}
+	if (remove_leading_zeros)
+		(*len)--;
 	return 0;
 }
 
+static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len)
+{
+	u8 *str_ptr = str;
+	u32 mask = 0x00f00000;
+	u8 shift = 8*3;
+	u8 digit;
+	u8 remove_leading_zeros = 1;
+
+	if (*len < 10) {
+		/* Need more than 10chars for this format */
+		*str_ptr = '\0';
+		(*len)--;
+		return -EINVAL;
+	}
+
+	while (shift > 0) {
+		shift -= 4;
+		digit = ((num & mask) >> shift);
+		if (digit == 0 && remove_leading_zeros) {
+			*str_ptr = '0';
+		} else {
+			if (digit < 0xa)
+				*str_ptr = digit + '0';
+			else
+				*str_ptr = digit - 0xa + 'a';
+
+			remove_leading_zeros = 0;
+			str_ptr++;
+			(*len)--;
+		}
+		mask = mask >> 4;
+		if ((shift == 4*4) || (shift == 4*2)) {
+			if (remove_leading_zeros) {
+				str_ptr++;
+				(*len)--;
+			}
+			*str_ptr = '.';
+			str_ptr++;
+			(*len)--;
+			remove_leading_zeros = 1;
+		}
+	}
+	if (remove_leading_zeros)
+		(*len)--;
+	return 0;
+}
 
 static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len)
 {
@@ -9677,8 +9731,9 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy,
 
 	if (bnx2x_is_8483x_8485x(phy)) {
 		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, 0x400f, &fw_ver1);
-		bnx2x_save_spirom_version(bp, port, fw_ver1 & 0xfff,
-				phy->ver_addr);
+		if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858)
+			fw_ver1 &= 0xfff;
+		bnx2x_save_spirom_version(bp, port, fw_ver1, phy->ver_addr);
 	} else {
 		/* For 32-bit registers in 848xx, access via MDIO2ARM i/f. */
 		/* (1) set reg 0xc200_0014(SPI_BRIDGE_CTRL_2) to 0x03000000 */
@@ -9732,16 +9787,32 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy,
 static void bnx2x_848xx_set_led(struct bnx2x *bp,
 				struct bnx2x_phy *phy)
 {
-	u16 val, offset, i;
+	u16 val, led3_blink_rate, offset, i;
 	static struct bnx2x_reg_set reg_set[] = {
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED1_MASK, 0x0080},
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED2_MASK, 0x0018},
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED3_MASK, 0x0006},
-		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED3_BLINK, 0x0000},
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_84823_CTL_SLOW_CLK_CNT_HIGH,
 			MDIO_PMA_REG_84823_BLINK_RATE_VAL_15P9HZ},
 		{MDIO_AN_DEVAD, 0xFFFB, 0xFFFD}
 	};
+
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+		/* Set LED5 source */
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD,
+				 MDIO_PMA_REG_8481_LED5_MASK,
+				 0x90);
+		led3_blink_rate = 0x000f;
+	} else {
+		led3_blink_rate = 0x0000;
+	}
+	/* Set LED3 BLINK */
+	bnx2x_cl45_write(bp, phy,
+			 MDIO_PMA_DEVAD,
+			 MDIO_PMA_REG_8481_LED3_BLINK,
+			 led3_blink_rate);
+
 	/* PHYC_CTL_LED_CTL */
 	bnx2x_cl45_read(bp, phy,
 			MDIO_PMA_DEVAD,
@@ -9749,6 +9820,9 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp,
 	val &= 0xFE00;
 	val |= 0x0092;
 
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858)
+		val |= 2 << 12; /* LED5 ON based on source */
+
 	bnx2x_cl45_write(bp, phy,
 			 MDIO_PMA_DEVAD,
 			 MDIO_PMA_REG_8481_LINK_SIGNAL, val);
@@ -9762,10 +9836,17 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp,
 	else
 		offset = MDIO_PMA_REG_84823_CTL_LED_CTL_1;
 
-	/* stretch_en for LED3*/
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858)
+		val = MDIO_PMA_REG_84858_ALLOW_GPHY_ACT |
+		      MDIO_PMA_REG_84823_LED3_STRETCH_EN;
+	else
+		val = MDIO_PMA_REG_84823_LED3_STRETCH_EN;
+
+	/* stretch_en for LEDs */
 	bnx2x_cl45_read_or_write(bp, phy,
-				 MDIO_PMA_DEVAD, offset,
-				 MDIO_PMA_REG_84823_LED3_STRETCH_EN);
+				 MDIO_PMA_DEVAD,
+				 offset,
+				 val);
 }
 
 static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy,
@@ -9775,7 +9856,7 @@ static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy,
 	struct bnx2x *bp = params->bp;
 	switch (action) {
 	case PHY_INIT:
-		if (!bnx2x_is_8483x_8485x(phy)) {
+		if (bnx2x_is_8483x_8485x(phy)) {
 			/* Save spirom version */
 			bnx2x_save_848xx_spirom_version(phy, bp, params->port);
 		}
@@ -10036,15 +10117,20 @@ static int bnx2x_84858_cmd_hdlr(struct bnx2x_phy *phy,
 
 static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
 				struct link_params *params, u16 fw_cmd,
-				u16 cmd_args[], int argc)
+				u16 cmd_args[], int argc, int process)
 {
 	int idx;
 	u16 val;
 	struct bnx2x *bp = params->bp;
-	/* Write CMD_OPEN_OVERRIDE to STATUS reg */
-	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_848xx_CMD_HDLR_STATUS,
-			PHY84833_STATUS_CMD_OPEN_OVERRIDE);
+	int rc = 0;
+
+	if (process == PHY84833_MB_PROCESS2) {
+		/* Write CMD_OPEN_OVERRIDE to STATUS reg */
+		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+				 MDIO_848xx_CMD_HDLR_STATUS,
+				 PHY84833_STATUS_CMD_OPEN_OVERRIDE);
+	}
+
 	for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) {
 		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
 				MDIO_848xx_CMD_HDLR_STATUS, &val);
@@ -10054,15 +10140,27 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
 	}
 	if (idx >= PHY848xx_CMDHDLR_WAIT) {
 		DP(NETIF_MSG_LINK, "FW cmd: FW not ready.\n");
+		/* if the status is CMD_COMPLETE_PASS or CMD_COMPLETE_ERROR
+		 * clear the status to CMD_CLEAR_COMPLETE
+		 */
+		if (val == PHY84833_STATUS_CMD_COMPLETE_PASS ||
+		    val == PHY84833_STATUS_CMD_COMPLETE_ERROR) {
+			bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+					 MDIO_848xx_CMD_HDLR_STATUS,
+					 PHY84833_STATUS_CMD_CLEAR_COMPLETE);
+		}
 		return -EINVAL;
 	}
-
-	/* Prepare argument(s) and issue command */
-	for (idx = 0; idx < argc; idx++) {
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_848xx_CMD_HDLR_DATA1 + idx,
-				cmd_args[idx]);
+	if (process == PHY84833_MB_PROCESS1 ||
+	    process == PHY84833_MB_PROCESS2) {
+		/* Prepare argument(s) */
+		for (idx = 0; idx < argc; idx++) {
+			bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+					 MDIO_848xx_CMD_HDLR_DATA1 + idx,
+					 cmd_args[idx]);
+		}
 	}
+
 	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
 			MDIO_848xx_CMD_HDLR_COMMAND, fw_cmd);
 	for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) {
@@ -10076,24 +10174,30 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
 	if ((idx >= PHY848xx_CMDHDLR_WAIT) ||
 	    (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) {
 		DP(NETIF_MSG_LINK, "FW cmd failed.\n");
-		return -EINVAL;
+		rc = -EINVAL;
 	}
-	/* Gather returning data */
-	for (idx = 0; idx < argc; idx++) {
-		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_848xx_CMD_HDLR_DATA1 + idx,
-				&cmd_args[idx]);
+	if (process == PHY84833_MB_PROCESS3 && rc == 0) {
+		/* Gather returning data */
+		for (idx = 0; idx < argc; idx++) {
+			bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
+					MDIO_848xx_CMD_HDLR_DATA1 + idx,
+					&cmd_args[idx]);
+		}
 	}
-	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_848xx_CMD_HDLR_STATUS,
-			PHY84833_STATUS_CMD_CLEAR_COMPLETE);
-	return 0;
+	if (val == PHY84833_STATUS_CMD_COMPLETE_ERROR ||
+	    val == PHY84833_STATUS_CMD_COMPLETE_PASS) {
+		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+				 MDIO_848xx_CMD_HDLR_STATUS,
+				 PHY84833_STATUS_CMD_CLEAR_COMPLETE);
+	}
+	return rc;
 }
 
 static int bnx2x_848xx_cmd_hdlr(struct bnx2x_phy *phy,
 				struct link_params *params,
 				u16 fw_cmd,
-				u16 cmd_args[], int argc)
+					   u16 cmd_args[], int argc,
+					   int process)
 {
 	struct bnx2x *bp = params->bp;
 
@@ -10106,7 +10210,7 @@ static int bnx2x_848xx_cmd_hdlr(struct bnx2x_phy *phy,
 					    argc);
 	} else {
 		return bnx2x_84833_cmd_hdlr(phy, params, fw_cmd, cmd_args,
-					    argc);
+					    argc, process);
 	}
 }
 
@@ -10133,7 +10237,7 @@ static int bnx2x_848xx_pair_swap_cfg(struct bnx2x_phy *phy,
 
 	status = bnx2x_848xx_cmd_hdlr(phy, params,
 				      PHY848xx_CMD_SET_PAIR_SWAP, data,
-				      PHY848xx_CMDHDLR_MAX_ARGS);
+				      2, PHY84833_MB_PROCESS2);
 	if (status == 0)
 		DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data[1]);
 
@@ -10222,8 +10326,8 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy,
 	DP(NETIF_MSG_LINK, "Don't Advertise 10GBase-T EEE\n");
 
 	/* Prevent Phy from working in EEE and advertising it */
-	rc = bnx2x_848xx_cmd_hdlr(phy, params,
-				  PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1);
+	rc = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_EEE_MODE,
+				  &cmd_args, 1, PHY84833_MB_PROCESS1);
 	if (rc) {
 		DP(NETIF_MSG_LINK, "EEE disable failed.\n");
 		return rc;
@@ -10240,8 +10344,8 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy,
 	struct bnx2x *bp = params->bp;
 	u16 cmd_args = 1;
 
-	rc = bnx2x_848xx_cmd_hdlr(phy, params,
-				  PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1);
+	rc = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_EEE_MODE,
+				  &cmd_args, 1, PHY84833_MB_PROCESS1);
 	if (rc) {
 		DP(NETIF_MSG_LINK, "EEE enable failed.\n");
 		return rc;
@@ -10362,7 +10466,7 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 		cmd_args[3] = PHY84833_CONSTANT_LATENCY;
 		rc = bnx2x_848xx_cmd_hdlr(phy, params,
 					  PHY848xx_CMD_SET_EEE_MODE, cmd_args,
-					  PHY848xx_CMDHDLR_MAX_ARGS);
+					  4, PHY84833_MB_PROCESS1);
 		if (rc)
 			DP(NETIF_MSG_LINK, "Cfg AutogrEEEn failed.\n");
 	}
@@ -10416,6 +10520,32 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 		vars->eee_status &= ~SHMEM_EEE_SUPPORTED_MASK;
 	}
 
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
+		/* Additional settings for jumbo packets in 1000BASE-T mode */
+		/* Allow rx extended length */
+		bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+				MDIO_AN_REG_8481_AUX_CTRL, &val);
+		val |= 0x4000;
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_AUX_CTRL, val);
+		/* TX FIFO Elasticity LSB */
+		bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+				MDIO_AN_REG_8481_1G_100T_EXT_CTRL, &val);
+		val |= 0x1;
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_1G_100T_EXT_CTRL, val);
+		/* TX FIFO Elasticity MSB */
+		/* Enable expansion register 0x46 (Pattern Generator status) */
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_EXPANSION_REG_ACCESS, 0xf46);
+
+		bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+				MDIO_AN_REG_8481_EXPANSION_REG_RD_RW, &val);
+		val |= 0x4000;
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_EXPANSION_REG_RD_RW, val);
+	}
+
 	if (bnx2x_is_8483x_8485x(phy)) {
 		/* Bring PHY out of super isolate mode as the final step. */
 		bnx2x_cl45_read_and_write(bp, phy,
@@ -10555,6 +10685,17 @@ static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy,
 	return link_up;
 }
 
+static int bnx2x_8485x_format_ver(u32 raw_ver, u8 *str, u16 *len)
+{
+	int status = 0;
+	u32 num;
+
+	num = ((raw_ver & 0xF80) >> 7) << 16 | ((raw_ver & 0x7F) << 8) |
+	      ((raw_ver & 0xF000) >> 12);
+	status = bnx2x_3_seq_format_ver(num, str, len);
+	return status;
+}
+
 static int bnx2x_848xx_format_ver(u32 raw_ver, u8 *str, u16 *len)
 {
 	int status = 0;
@@ -10651,10 +10792,25 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 					0x0);
 
 		} else {
+			/* LED 1 OFF */
 			bnx2x_cl45_write(bp, phy,
 					 MDIO_PMA_DEVAD,
 					 MDIO_PMA_REG_8481_LED1_MASK,
 					 0x0);
+
+			if (phy->type ==
+				PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				/* LED 2 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED2_MASK,
+						 0x0);
+				/* LED 3 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x0);
+			}
 		}
 		break;
 	case LED_MODE_FRONT_PANEL_OFF:
@@ -10713,6 +10869,19 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 						 MDIO_PMA_REG_8481_SIGNAL_MASK,
 						 0x0);
 			}
+			if (phy->type ==
+				PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				/* LED 2 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED2_MASK,
+						 0x0);
+				/* LED 3 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x0);
+			}
 		}
 		break;
 	case LED_MODE_ON:
@@ -10776,6 +10945,25 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 						params->port*4,
 						NIG_MASK_MI_INT);
 				}
+			}
+			if (phy->type ==
+			    PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				/* Tell LED3 to constant on */
+				bnx2x_cl45_read(bp, phy,
+						MDIO_PMA_DEVAD,
+						MDIO_PMA_REG_8481_LINK_SIGNAL,
+						&val);
+				val &= ~(7<<6);
+				val |= (2<<6);  /* A83B[8:6]= 2 */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LINK_SIGNAL,
+						 val);
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x20);
+			} else {
 				bnx2x_cl45_write(bp, phy,
 						 MDIO_PMA_DEVAD,
 						 MDIO_PMA_REG_8481_SIGNAL_MASK,
@@ -10854,6 +11042,17 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 					 MDIO_PMA_REG_8481_LINK_SIGNAL,
 					 val);
 			if (phy->type ==
+			    PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED2_MASK,
+						 0x18);
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x06);
+			}
+			if (phy->type ==
 			    PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834) {
 				/* Restore LED4 source to external link,
 				 * and re-enable interrupts.
@@ -11982,7 +12181,7 @@ static const struct bnx2x_phy phy_84858 = {
 	.read_status	= (read_status_t)bnx2x_848xx_read_status,
 	.link_reset	= (link_reset_t)bnx2x_848x3_link_reset,
 	.config_loopback = (config_loopback_t)NULL,
-	.format_fw_ver	= (format_fw_ver_t)bnx2x_848xx_format_ver,
+	.format_fw_ver	= (format_fw_ver_t)bnx2x_8485x_format_ver,
 	.hw_reset	= (hw_reset_t)bnx2x_84833_hw_reset_phy,
 	.set_link_led	= (set_link_led_t)bnx2x_848xx_set_link_led,
 	.phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func
@@ -13807,8 +14006,10 @@ void bnx2x_period_func(struct link_params *params, struct link_vars *vars)
 	if (CHIP_IS_E3(bp)) {
 		struct bnx2x_phy *phy = &params->phy[INT_PHY];
 		bnx2x_set_aer_mmd(params, phy);
-		if ((phy->supported & SUPPORTED_20000baseKR2_Full) &&
-		    (phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_20G))
+		if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
+		     (phy->speed_cap_mask &
+		      PORT_HW_CFG_SPEED_CAPABILITY_D0_20G)) ||
+		    (phy->req_line_speed == SPEED_20000))
 			bnx2x_check_kr2_wa(params, vars, phy);
 		bnx2x_check_over_curr(params, vars);
 		if (vars->rx_tx_asic_rst)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 4dead49bd5cb..a43dea259b12 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -7296,6 +7296,8 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_PMA_REG_84823_CTL_LED_CTL_1			0xa8e3
 #define MDIO_PMA_REG_84833_CTL_LED_CTL_1			0xa8ec
 #define MDIO_PMA_REG_84823_LED3_STRETCH_EN			0x0080
+/* BCM84858 only */
+#define MDIO_PMA_REG_84858_ALLOW_GPHY_ACT			0x8000
 
 /* BCM84833 only */
 #define MDIO_84833_TOP_CFG_FW_REV			0x400f
@@ -7337,6 +7339,10 @@ Theotherbitsarereservedandshouldbezero*/
 #define PHY84833_STATUS_CMD_NOT_OPEN_FOR_CMDS		0x0040
 #define PHY84833_STATUS_CMD_CLEAR_COMPLETE		0x0080
 #define PHY84833_STATUS_CMD_OPEN_OVERRIDE		0xa5a5
+/* Mailbox Process */
+#define PHY84833_MB_PROCESS1				1
+#define PHY84833_MB_PROCESS2				2
+#define PHY84833_MB_PROCESS3				3
 
 /* Mailbox status set used by 84858 only */
 #define PHY84858_STATUS_CMD_RECEIVED			0x0001
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5dc89e527e7d..8ab000dd52d9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -69,7 +69,7 @@ MODULE_VERSION(DRV_MODULE_VERSION);
 #define BNXT_RX_DMA_OFFSET NET_SKB_PAD
 #define BNXT_RX_COPY_THRESH 256
 
-#define BNXT_TX_PUSH_THRESH 92
+#define BNXT_TX_PUSH_THRESH 164
 
 enum board_idx {
 	BCM57301,
@@ -223,11 +223,12 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh) {
-		struct tx_push_bd *push = txr->tx_push;
-		struct tx_bd *tx_push = &push->txbd1;
-		struct tx_bd_ext *tx_push1 = &push->txbd2;
-		void *pdata = tx_push1 + 1;
-		int j;
+		struct tx_push_buffer *tx_push_buf = txr->tx_push;
+		struct tx_push_bd *tx_push = &tx_push_buf->push_bd;
+		struct tx_bd_ext *tx_push1 = &tx_push->txbd2;
+		void *pdata = tx_push_buf->data;
+		u64 *end;
+		int j, push_len;
 
 		/* Set COAL_NOW to be ready quickly for the next push */
 		tx_push->tx_bd_len_flags_type =
@@ -247,6 +248,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
 		tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action);
 
+		end = PTR_ALIGN(pdata + length + 1, 8) - 1;
+		*end = 0;
+
 		skb_copy_from_linear_data(skb, pdata, len);
 		pdata += len;
 		for (j = 0; j < last_frag; j++) {
@@ -261,22 +265,29 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			pdata += skb_frag_size(frag);
 		}
 
-		memcpy(txbd, tx_push, sizeof(*txbd));
+		txbd->tx_bd_len_flags_type = tx_push->tx_bd_len_flags_type;
+		txbd->tx_bd_haddr = txr->data_mapping;
 		prod = NEXT_TX(prod);
 		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
 		memcpy(txbd, tx_push1, sizeof(*txbd));
 		prod = NEXT_TX(prod);
-		push->doorbell =
+		tx_push->doorbell =
 			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod);
 		txr->tx_prod = prod;
 
 		netdev_tx_sent_queue(txq, skb->len);
 
-		__iowrite64_copy(txr->tx_doorbell, push,
-				 (length + sizeof(*push) + 8) / 8);
+		push_len = (length + sizeof(*tx_push) + 7) / 8;
+		if (push_len > 16) {
+			__iowrite64_copy(txr->tx_doorbell, tx_push_buf, 16);
+			__iowrite64_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
+					 push_len - 16);
+		} else {
+			__iowrite64_copy(txr->tx_doorbell, tx_push_buf,
+					 push_len);
+		}
 
 		tx_buf->is_push = 1;
-
 		goto tx_done;
 	}
 
@@ -1753,7 +1764,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 		push_size  = L1_CACHE_ALIGN(sizeof(struct tx_push_bd) +
 					bp->tx_push_thresh);
 
-		if (push_size > 128) {
+		if (push_size > 256) {
 			push_size = 0;
 			bp->tx_push_thresh = 0;
 		}
@@ -1772,7 +1783,6 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 			return rc;
 
 		if (bp->tx_push_size) {
-			struct tx_bd *txbd;
 			dma_addr_t mapping;
 
 			/* One pre-allocated DMA buffer to backup
@@ -1786,13 +1796,11 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 			if (!txr->tx_push)
 				return -ENOMEM;
 
-			txbd = &txr->tx_push->txbd1;
-
 			mapping = txr->tx_push_mapping +
 				sizeof(struct tx_push_bd);
-			txbd->tx_bd_haddr = cpu_to_le64(mapping);
+			txr->data_mapping = cpu_to_le64(mapping);
 
-			memset(txbd + 1, 0, sizeof(struct tx_bd_ext));
+			memset(txr->tx_push, 0, sizeof(struct tx_push_bd));
 		}
 		ring->queue_id = bp->q_info[j].queue_id;
 		if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1))
@@ -4546,20 +4554,18 @@ static int bnxt_update_phy_setting(struct bnxt *bp)
 	if (!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) &&
 	    link_info->force_pause_setting != link_info->req_flow_ctrl)
 		update_pause = true;
-	if (link_info->req_duplex != link_info->duplex_setting)
-		update_link = true;
 	if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
 		if (BNXT_AUTO_MODE(link_info->auto_mode))
 			update_link = true;
 		if (link_info->req_link_speed != link_info->force_link_speed)
 			update_link = true;
+		if (link_info->req_duplex != link_info->duplex_setting)
+			update_link = true;
 	} else {
 		if (link_info->auto_mode == BNXT_LINK_AUTO_NONE)
 			update_link = true;
 		if (link_info->advertising != link_info->auto_link_speeds)
 			update_link = true;
-		if (link_info->req_link_speed != link_info->auto_link_speed)
-			update_link = true;
 	}
 
 	if (update_link)
@@ -4636,7 +4642,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (link_re_init) {
 		rc = bnxt_update_phy_setting(bp);
 		if (rc)
-			goto open_err;
+			netdev_warn(bp->dev, "failed to update phy settings\n");
 	}
 
 	if (irq_re_init) {
@@ -4654,6 +4660,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* Enable TX queues */
 	bnxt_tx_enable(bp);
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
+	bnxt_update_link(bp, true);
 
 	return 0;
 
@@ -5670,22 +5677,16 @@ static int bnxt_probe_phy(struct bnxt *bp)
 	}
 
 	/*initialize the ethool setting copy with NVM settings */
-	if (BNXT_AUTO_MODE(link_info->auto_mode))
-		link_info->autoneg |= BNXT_AUTONEG_SPEED;
-
-	if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) {
-		if (link_info->auto_pause_setting == BNXT_LINK_PAUSE_BOTH)
-			link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
+	if (BNXT_AUTO_MODE(link_info->auto_mode)) {
+		link_info->autoneg = BNXT_AUTONEG_SPEED |
+				     BNXT_AUTONEG_FLOW_CTRL;
+		link_info->advertising = link_info->auto_link_speeds;
 		link_info->req_flow_ctrl = link_info->auto_pause_setting;
-	} else if (link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) {
+	} else {
+		link_info->req_link_speed = link_info->force_link_speed;
+		link_info->req_duplex = link_info->duplex_setting;
 		link_info->req_flow_ctrl = link_info->force_pause_setting;
 	}
-	link_info->req_duplex = link_info->duplex_setting;
-	if (link_info->autoneg & BNXT_AUTONEG_SPEED)
-		link_info->req_link_speed = link_info->auto_link_speed;
-	else
-		link_info->req_link_speed = link_info->force_link_speed;
-	link_info->advertising = link_info->auto_link_speeds;
 	snprintf(phy_ver, PHY_VER_STR_LEN, " ph %d.%d.%d",
 		 link_info->phy_ver[0],
 		 link_info->phy_ver[1],
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 8af3ca8efcef..2be51b332652 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -411,8 +411,8 @@ struct rx_tpa_end_cmp_ext {
 
 #define BNXT_NUM_TESTS(bp)	0
 
-#define BNXT_DEFAULT_RX_RING_SIZE	1023
-#define BNXT_DEFAULT_TX_RING_SIZE	512
+#define BNXT_DEFAULT_RX_RING_SIZE	511
+#define BNXT_DEFAULT_TX_RING_SIZE	511
 
 #define MAX_TPA		64
 
@@ -523,10 +523,16 @@ struct bnxt_ring_struct {
 
 struct tx_push_bd {
 	__le32			doorbell;
-	struct tx_bd		txbd1;
+	__le32			tx_bd_len_flags_type;
+	u32			tx_bd_opaque;
 	struct tx_bd_ext	txbd2;
 };
 
+struct tx_push_buffer {
+	struct tx_push_bd	push_bd;
+	u32			data[25];
+};
+
 struct bnxt_tx_ring_info {
 	struct bnxt_napi	*bnapi;
 	u16			tx_prod;
@@ -538,8 +544,9 @@ struct bnxt_tx_ring_info {
 
 	dma_addr_t		tx_desc_mapping[MAX_TX_PAGES];
 
-	struct tx_push_bd	*tx_push;
+	struct tx_push_buffer	*tx_push;
 	dma_addr_t		tx_push_mapping;
+	__le64			data_mapping;
 
 #define BNXT_DEV_STATE_CLOSING	0x1
 	u32			dev_state;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 922b898e7a32..3238817dfd5f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -486,15 +486,8 @@ static u32 bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info)
 		speed_mask |= SUPPORTED_2500baseX_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_10GB)
 		speed_mask |= SUPPORTED_10000baseT_Full;
-	/* TODO: support 25GB, 50GB with different cable type */
-	if (fw_speeds & BNXT_LINK_SPEED_MSK_20GB)
-		speed_mask |= SUPPORTED_20000baseMLD2_Full |
-			SUPPORTED_20000baseKR2_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB)
-		speed_mask |= SUPPORTED_40000baseKR4_Full |
-			SUPPORTED_40000baseCR4_Full |
-			SUPPORTED_40000baseSR4_Full |
-			SUPPORTED_40000baseLR4_Full;
+		speed_mask |= SUPPORTED_40000baseCR4_Full;
 
 	return speed_mask;
 }
@@ -514,15 +507,8 @@ static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info)
 		speed_mask |= ADVERTISED_2500baseX_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_10GB)
 		speed_mask |= ADVERTISED_10000baseT_Full;
-	/* TODO: how to advertise 20, 25, 40, 50GB with different cable type ?*/
-	if (fw_speeds & BNXT_LINK_SPEED_MSK_20GB)
-		speed_mask |= ADVERTISED_20000baseMLD2_Full |
-			      ADVERTISED_20000baseKR2_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB)
-		speed_mask |= ADVERTISED_40000baseKR4_Full |
-			      ADVERTISED_40000baseCR4_Full |
-			      ADVERTISED_40000baseSR4_Full |
-			      ADVERTISED_40000baseLR4_Full;
+		speed_mask |= ADVERTISED_40000baseCR4_Full;
 	return speed_mask;
 }
 
@@ -557,11 +543,12 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	u16 ethtool_speed;
 
 	cmd->supported = bnxt_fw_to_ethtool_support_spds(link_info);
+	cmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
 
 	if (link_info->auto_link_speeds)
 		cmd->supported |= SUPPORTED_Autoneg;
 
-	if (BNXT_AUTO_MODE(link_info->auto_mode)) {
+	if (link_info->autoneg) {
 		cmd->advertising =
 			bnxt_fw_to_ethtool_advertised_spds(link_info);
 		cmd->advertising |= ADVERTISED_Autoneg;
@@ -570,28 +557,16 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		cmd->autoneg = AUTONEG_DISABLE;
 		cmd->advertising = 0;
 	}
-	if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) {
+	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) {
 		if ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) ==
 		    BNXT_LINK_PAUSE_BOTH) {
 			cmd->advertising |= ADVERTISED_Pause;
-			cmd->supported |= SUPPORTED_Pause;
 		} else {
 			cmd->advertising |= ADVERTISED_Asym_Pause;
-			cmd->supported |= SUPPORTED_Asym_Pause;
 			if (link_info->auto_pause_setting &
 			    BNXT_LINK_PAUSE_RX)
 				cmd->advertising |= ADVERTISED_Pause;
 		}
-	} else if (link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) {
-		if ((link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) ==
-		    BNXT_LINK_PAUSE_BOTH) {
-			cmd->supported |= SUPPORTED_Pause;
-		} else {
-			cmd->supported |= SUPPORTED_Asym_Pause;
-			if (link_info->force_pause_setting &
-			    BNXT_LINK_PAUSE_RX)
-				cmd->supported |= SUPPORTED_Pause;
-		}
 	}
 
 	cmd->port = PORT_NONE;
@@ -670,6 +645,9 @@ static u16 bnxt_get_fw_auto_link_speeds(u32 advertising)
 	if (advertising & ADVERTISED_10000baseT_Full)
 		fw_speed_mask |= BNXT_LINK_SPEED_MSK_10GB;
 
+	if (advertising & ADVERTISED_40000baseCR4_Full)
+		fw_speed_mask |= BNXT_LINK_SPEED_MSK_40GB;
+
 	return fw_speed_mask;
 }
 
@@ -729,7 +707,7 @@ static int bnxt_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		speed = ethtool_cmd_speed(cmd);
 		link_info->req_link_speed = bnxt_get_fw_speed(dev, speed);
 		link_info->req_duplex = BNXT_LINK_DUPLEX_FULL;
-		link_info->autoneg &= ~BNXT_AUTONEG_SPEED;
+		link_info->autoneg = 0;
 		link_info->advertising = 0;
 	}
 
@@ -748,8 +726,7 @@ static void bnxt_get_pauseparam(struct net_device *dev,
 
 	if (BNXT_VF(bp))
 		return;
-	epause->autoneg = !!(link_info->auto_pause_setting &
-			     BNXT_LINK_PAUSE_BOTH);
+	epause->autoneg = !!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL);
 	epause->rx_pause = ((link_info->pause & BNXT_LINK_PAUSE_RX) != 0);
 	epause->tx_pause = ((link_info->pause & BNXT_LINK_PAUSE_TX) != 0);
 }
@@ -765,6 +742,9 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 		return rc;
 
 	if (epause->autoneg) {
+		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
+			return -EINVAL;
+
 		link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_BOTH;
 	} else {
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index b15a60d787c7..d7e01a74e927 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2445,8 +2445,7 @@ static void bcmgenet_irq_task(struct work_struct *work)
 	}
 
 	/* Link UP/DOWN event */
-	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
-	    (priv->irq0_stat & UMAC_IRQ_LINK_EVENT)) {
+	if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) {
 		phy_mac_interrupt(priv->phydev,
 				  !!(priv->irq0_stat & UMAC_IRQ_LINK_UP));
 		priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 49eea8981332..3010080cfeee 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7831,6 +7831,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	return ret;
 }
 
+static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
+{
+	/* Check if we will never have enough descriptors,
+	 * as gso_segs can be more than current ring size
+	 */
+	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
+}
+
 static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
@@ -7934,14 +7942,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * vlan encapsulated.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q) ||
-		    skb->protocol == htons(ETH_P_8021AD))
-			return tg3_tso_bug(tp, tnapi, txq, skb);
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (tg3_tso_bug_gso_check(tnapi, skb))
+				return tg3_tso_bug(tp, tnapi, txq, skb);
+			goto drop;
+		}
 
 		if (!skb_is_gso_v6(skb)) {
 			if (unlikely((ETH_HLEN + hdr_len) > 80) &&
-			    tg3_flag(tp, TSO_BUG))
-				return tg3_tso_bug(tp, tnapi, txq, skb);
-
+			    tg3_flag(tp, TSO_BUG)) {
+				if (tg3_tso_bug_gso_check(tnapi, skb))
+					return tg3_tso_bug(tp, tnapi, txq, skb);
+				goto drop;
+			}
 			ip_csum = iph->check;
 			ip_tot_len = iph->tot_len;
 			iph->check = 0;
@@ -8073,7 +8086,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (would_hit_hwbug) {
 		tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i);
 
-		if (mss) {
+		if (mss && tg3_tso_bug_gso_check(tnapi, skb)) {
 			/* If it's a TSO packet, do GSO instead of
 			 * allocating and copying to a large linear SKB
 			 */
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 872765527081..34d269cd5579 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1683,7 +1683,7 @@ static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs,
 	dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no);
 	/* droq creation and local register settings. */
 	ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx);
-	if (ret_val == -1)
+	if (ret_val < 0)
 		return ret_val;
 
 	if (ret_val == 1) {
@@ -2524,7 +2524,7 @@ static void handle_timestamp(struct octeon_device *oct,
 
 	octeon_swap_8B_data(&resp->timestamp, 1);
 
-	if (unlikely((skb_shinfo(skb)->tx_flags | SKBTX_IN_PROGRESS) != 0)) {
+	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) != 0)) {
 		struct skb_shared_hwtstamps ts;
 		u64 ns = resp->timestamp;
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 4dba86eaa045..174072b3740b 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -983,5 +983,5 @@ int octeon_create_droq(struct octeon_device *oct,
 
 create_droq_fail:
 	octeon_delete_droq(oct, q_no);
-	return -1;
+	return -ENOMEM;
 }
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index c24cb2a86a42..a009bc30dc4d 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -574,8 +574,7 @@ static inline void nicvf_set_rxhash(struct net_device *netdev,
 
 static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 				  struct napi_struct *napi,
-				  struct cmp_queue *cq,
-				  struct cqe_rx_t *cqe_rx, int cqe_type)
+				  struct cqe_rx_t *cqe_rx)
 {
 	struct sk_buff *skb;
 	struct nicvf *nic = netdev_priv(netdev);
@@ -591,7 +590,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 	}
 
 	/* Check for errors */
-	err = nicvf_check_cqe_rx_errs(nic, cq, cqe_rx);
+	err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
 	if (err && !cqe_rx->rb_cnt)
 		return;
 
@@ -682,8 +681,7 @@ loop:
 			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
-			nicvf_rcv_pkt_handler(netdev, napi, cq,
-					      cq_desc, CQE_TYPE_RX);
+			nicvf_rcv_pkt_handler(netdev, napi, cq_desc);
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
@@ -1125,7 +1123,6 @@ int nicvf_stop(struct net_device *netdev)
 
 	/* Clear multiqset info */
 	nic->pnicvf = nic;
-	nic->sqs_count = 0;
 
 	return 0;
 }
@@ -1354,6 +1351,9 @@ void nicvf_update_stats(struct nicvf *nic)
 	drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok +
 				  stats->tx_bcast_frames_ok +
 				  stats->tx_mcast_frames_ok;
+	drv_stats->rx_frames_ok = stats->rx_ucast_frames +
+				  stats->rx_bcast_frames +
+				  stats->rx_mcast_frames;
 	drv_stats->rx_drops = stats->rx_drop_red +
 			      stats->rx_drop_overrun;
 	drv_stats->tx_drops = stats->tx_drops;
@@ -1538,6 +1538,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	nicvf_send_vf_struct(nic);
 
+	if (!pass1_silicon(nic->pdev))
+		nic->hw_tso = true;
+
 	/* Check if this VF is in QS only mode */
 	if (nic->sqs_mode)
 		return 0;
@@ -1557,9 +1560,6 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 
-	if (!pass1_silicon(nic->pdev))
-		nic->hw_tso = true;
-
 	netdev->netdev_ops = &nicvf_netdev_ops;
 	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d0d1b5490061..767347b1f631 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1329,16 +1329,12 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 }
 
 /* Check for errors in the receive cmp.queue entry */
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx)
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
 	struct nicvf_hw_stats *stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
 
-	if (!cqe_rx->err_level && !cqe_rx->err_opcode) {
-		drv_stats->rx_frames_ok++;
+	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
 		return 0;
-	}
 
 	if (netif_msg_rx_err(nic))
 		netdev_err(nic->netdev,
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index c5030a7f213a..6673e1133523 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -338,8 +338,7 @@ u64  nicvf_queue_reg_read(struct nicvf *nic,
 /* Stats */
 void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx);
 void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx);
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx);
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
 int nicvf_check_cqe_tx_errs(struct nicvf *nic,
 			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx);
 #endif /* NICVF_QUEUES_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
index ee04caa6c4d8..a89721fad633 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
@@ -681,6 +681,24 @@ int t3_seeprom_wp(struct adapter *adapter, int enable)
 	return t3_seeprom_write(adapter, EEPROM_STAT_ADDR, enable ? 0xc : 0);
 }
 
+static int vpdstrtouint(char *s, int len, unsigned int base, unsigned int *val)
+{
+	char tok[len + 1];
+
+	memcpy(tok, s, len);
+	tok[len] = 0;
+	return kstrtouint(strim(tok), base, val);
+}
+
+static int vpdstrtou16(char *s, int len, unsigned int base, u16 *val)
+{
+	char tok[len + 1];
+
+	memcpy(tok, s, len);
+	tok[len] = 0;
+	return kstrtou16(strim(tok), base, val);
+}
+
 /**
  *	get_vpd_params - read VPD parameters from VPD EEPROM
  *	@adapter: adapter to read
@@ -709,19 +727,19 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 			return ret;
 	}
 
-	ret = kstrtouint(vpd.cclk_data, 10, &p->cclk);
+	ret = vpdstrtouint(vpd.cclk_data, vpd.cclk_len, 10, &p->cclk);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.mclk_data, 10, &p->mclk);
+	ret = vpdstrtouint(vpd.mclk_data, vpd.mclk_len, 10, &p->mclk);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.uclk_data, 10, &p->uclk);
+	ret = vpdstrtouint(vpd.uclk_data, vpd.uclk_len, 10, &p->uclk);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.mdc_data, 10, &p->mdc);
+	ret = vpdstrtouint(vpd.mdc_data, vpd.mdc_len, 10, &p->mdc);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.mt_data, 10, &p->mem_timing);
+	ret = vpdstrtouint(vpd.mt_data, vpd.mt_len, 10, &p->mem_timing);
 	if (ret)
 		return ret;
 	memcpy(p->sn, vpd.sn_data, SERNUM_LEN);
@@ -733,10 +751,12 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	} else {
 		p->port_type[0] = hex_to_bin(vpd.port0_data[0]);
 		p->port_type[1] = hex_to_bin(vpd.port1_data[0]);
-		ret = kstrtou16(vpd.xaui0cfg_data, 16, &p->xauicfg[0]);
+		ret = vpdstrtou16(vpd.xaui0cfg_data, vpd.xaui0cfg_len, 16,
+				  &p->xauicfg[0]);
 		if (ret)
 			return ret;
-		ret = kstrtou16(vpd.xaui1cfg_data, 16, &p->xauicfg[1]);
+		ret = vpdstrtou16(vpd.xaui1cfg_data, vpd.xaui1cfg_len, 16,
+				  &p->xauicfg[1]);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index a8dda635456d..06bc2d2e7a73 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -165,6 +165,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x5098),	/* Custom 2x40G QSFP */
 	CH_PCI_ID_TABLE_FENTRY(0x5099),	/* Custom 2x40G QSFP */
 	CH_PCI_ID_TABLE_FENTRY(0x509a),	/* Custom T520-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x509b),	/* Custom T540-CR LOM */
 
 	/* T6 adapters:
 	 */
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 1671fa3332c2..7ba6d530b0c0 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -33,7 +33,7 @@
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
-#define DRV_VERSION		"2.3.0.12"
+#define DRV_VERSION		"2.3.0.20"
 #define DRV_COPYRIGHT		"Copyright 2008-2013 Cisco Systems, Inc"
 
 #define ENIC_BARS_MAX		6
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index 1ffd1050860b..1fdf5fe12a95 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -298,7 +298,8 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd,
 			  int wait)
 {
 	struct devcmd2_controller *dc2c = vdev->devcmd2;
-	struct devcmd2_result *result = dc2c->result + dc2c->next_result;
+	struct devcmd2_result *result;
+	u8 color;
 	unsigned int i;
 	int delay, err;
 	u32 fetch_index, new_posted;
@@ -336,13 +337,17 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd,
 	if (dc2c->cmd_ring[posted].flags & DEVCMD2_FNORESULT)
 		return 0;
 
+	result = dc2c->result + dc2c->next_result;
+	color = dc2c->color;
+
+	dc2c->next_result++;
+	if (dc2c->next_result == dc2c->result_size) {
+		dc2c->next_result = 0;
+		dc2c->color = dc2c->color ? 0 : 1;
+	}
+
 	for (delay = 0; delay < wait; delay++) {
-		if (result->color == dc2c->color) {
-			dc2c->next_result++;
-			if (dc2c->next_result == dc2c->result_size) {
-				dc2c->next_result = 0;
-				dc2c->color = dc2c->color ? 0 : 1;
-			}
+		if (result->color == color) {
 			if (result->error) {
 				err = result->error;
 				if (err != ERR_ECMDUNKNOWN ||
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index cf94b72dbacd..48d91941408d 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -128,7 +128,6 @@ struct board_info {
 	struct resource *data_res;
 	struct resource	*addr_req;   /* resources requested */
 	struct resource *data_req;
-	struct resource *irq_res;
 
 	int		 irq_wake;
 
@@ -1300,22 +1299,16 @@ static int
 dm9000_open(struct net_device *dev)
 {
 	struct board_info *db = netdev_priv(dev);
-	unsigned long irqflags = db->irq_res->flags & IRQF_TRIGGER_MASK;
 
 	if (netif_msg_ifup(db))
 		dev_dbg(db->dev, "enabling %s\n", dev->name);
 
-	/* If there is no IRQ type specified, default to something that
-	 * may work, and tell the user that this is a problem */
-
-	if (irqflags == IRQF_TRIGGER_NONE)
-		irqflags = irq_get_trigger_type(dev->irq);
-
-	if (irqflags == IRQF_TRIGGER_NONE)
+	/* If there is no IRQ type specified, tell the user that this is a
+	 * problem
+	 */
+	if (irq_get_trigger_type(dev->irq) == IRQF_TRIGGER_NONE)
 		dev_warn(db->dev, "WARNING: no IRQ resource flags set.\n");
 
-	irqflags |= IRQF_SHARED;
-
 	/* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
 	iow(db, DM9000_GPR, 0);	/* REG_1F bit0 activate phyxcer */
 	mdelay(1); /* delay needs by DM9000B */
@@ -1323,7 +1316,8 @@ dm9000_open(struct net_device *dev)
 	/* Initialize DM9000 board */
 	dm9000_init_dm9000(dev);
 
-	if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
+	if (request_irq(dev->irq, dm9000_interrupt, IRQF_SHARED,
+			dev->name, dev))
 		return -EAGAIN;
 	/* Now that we have an interrupt handler hooked up we can unmask
 	 * our interrupts
@@ -1500,15 +1494,22 @@ dm9000_probe(struct platform_device *pdev)
 
 	db->addr_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	db->data_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	db->irq_res  = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 
-	if (db->addr_res == NULL || db->data_res == NULL ||
-	    db->irq_res == NULL) {
-		dev_err(db->dev, "insufficient resources\n");
+	if (!db->addr_res || !db->data_res) {
+		dev_err(db->dev, "insufficient resources addr=%p data=%p\n",
+			db->addr_res, db->data_res);
 		ret = -ENOENT;
 		goto out;
 	}
 
+	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq < 0) {
+		dev_err(db->dev, "interrupt resource unavailable: %d\n",
+			ndev->irq);
+		ret = ndev->irq;
+		goto out;
+	}
+
 	db->irq_wake = platform_get_irq(pdev, 1);
 	if (db->irq_wake >= 0) {
 		dev_dbg(db->dev, "wakeup irq %d\n", db->irq_wake);
@@ -1570,7 +1571,6 @@ dm9000_probe(struct platform_device *pdev)
 
 	/* fill in parameters for net-dev structure */
 	ndev->base_addr = (unsigned long)db->io_addr;
-	ndev->irq	= db->irq_res->start;
 
 	/* ensure at least we have a default set of IO routines */
 	dm9000_set_io(db, iosize);
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index a7139f588ad2..678f5018d0be 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -469,8 +469,8 @@ static int fmvj18x_config(struct pcmcia_device *link)
 		    goto failed;
 	    }
 	    /* Read MACID from CIS */
-	    for (i = 5; i < 11; i++)
-		    dev->dev_addr[i] = buf[i];
+	    for (i = 0; i < 6; i++)
+		    dev->dev_addr[i] = buf[i + 5];
 	    kfree(buf);
 	} else {
 	    if (pcmcia_get_mac_from_cis(link, dev))
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 662c2ee268c7..b0ae69f84493 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -370,6 +370,11 @@ struct mvneta_port {
 	struct net_device *dev;
 	struct notifier_block cpu_notifier;
 	int rxq_def;
+	/* Protect the access to the percpu interrupt registers,
+	 * ensuring that the configuration remains coherent.
+	 */
+	spinlock_t lock;
+	bool is_stopped;
 
 	/* Core clock */
 	struct clk *clk;
@@ -1038,6 +1043,43 @@ static void mvneta_set_autoneg(struct mvneta_port *pp, int enable)
 	}
 }
 
+static void mvneta_percpu_unmask_interrupt(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	/* All the queue are unmasked, but actually only the ones
+	 * mapped to this CPU will be unmasked
+	 */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+		    MVNETA_RX_INTR_MASK_ALL |
+		    MVNETA_TX_INTR_MASK_ALL |
+		    MVNETA_MISCINTR_INTR_MASK);
+}
+
+static void mvneta_percpu_mask_interrupt(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	/* All the queue are masked, but actually only the ones
+	 * mapped to this CPU will be masked
+	 */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+}
+
+static void mvneta_percpu_clear_intr_cause(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	/* All the queue are cleared, but actually only the ones
+	 * mapped to this CPU will be cleared
+	 */
+	mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
+	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
+}
+
 /* This method sets defaults to the NETA port:
  *	Clears interrupt Cause and Mask registers.
  *	Clears all MAC tables.
@@ -1055,14 +1097,10 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 	int max_cpu = num_present_cpus();
 
 	/* Clear all Cause registers */
-	mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
+	on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true);
 
 	/* Mask all interrupts */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 	mvreg_write(pp, MVNETA_INTR_ENABLE, 0);
 
 	/* Enable MBUS Retry bit16 */
@@ -2528,34 +2566,9 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
 	return 0;
 }
 
-static void mvneta_percpu_unmask_interrupt(void *arg)
-{
-	struct mvneta_port *pp = arg;
-
-	/* All the queue are unmasked, but actually only the ones
-	 * maped to this CPU will be unmasked
-	 */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-		    MVNETA_RX_INTR_MASK_ALL |
-		    MVNETA_TX_INTR_MASK_ALL |
-		    MVNETA_MISCINTR_INTR_MASK);
-}
-
-static void mvneta_percpu_mask_interrupt(void *arg)
-{
-	struct mvneta_port *pp = arg;
-
-	/* All the queue are masked, but actually only the ones
-	 * maped to this CPU will be masked
-	 */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
-}
-
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
-	unsigned int cpu;
+	int cpu;
 
 	mvneta_max_rx_size_set(pp, pp->pkt_size);
 	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
@@ -2564,16 +2577,15 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 	mvneta_port_enable(pp);
 
 	/* Enable polling on the port */
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_enable(&port->napi);
 	}
 
 	/* Unmask interrupts. It has to be done from each CPU */
-	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt,
-					 pp, true);
+	on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
+
 	mvreg_write(pp, MVNETA_INTR_MISC_MASK,
 		    MVNETA_CAUSE_PHY_STATUS_CHANGE |
 		    MVNETA_CAUSE_LINK_CHANGE |
@@ -2589,7 +2601,7 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 
 	phy_stop(pp->phy_dev);
 
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_disable(&port->napi);
@@ -2604,13 +2616,10 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 	mvneta_port_disable(pp);
 
 	/* Clear all ethernet port interrupts */
-	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
+	on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true);
 
 	/* Mask all ethernet port interrupts */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 
 	mvneta_tx_reset(pp);
 	mvneta_rx_reset(pp);
@@ -2847,11 +2856,20 @@ static void mvneta_percpu_disable(void *arg)
 	disable_percpu_irq(pp->dev->irq);
 }
 
+/* Electing a CPU must be done in an atomic way: it should be done
+ * after or before the removal/insertion of a CPU and this function is
+ * not reentrant.
+ */
 static void mvneta_percpu_elect(struct mvneta_port *pp)
 {
-	int online_cpu_idx, max_cpu, cpu, i = 0;
+	int elected_cpu = 0, max_cpu, cpu, i = 0;
+
+	/* Use the cpu associated to the rxq when it is online, in all
+	 * the other cases, use the cpu 0 which can't be offline.
+	 */
+	if (cpu_online(pp->rxq_def))
+		elected_cpu = pp->rxq_def;
 
-	online_cpu_idx = pp->rxq_def % num_online_cpus();
 	max_cpu = num_present_cpus();
 
 	for_each_online_cpu(cpu) {
@@ -2862,7 +2880,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp)
 			if ((rxq % max_cpu) == cpu)
 				rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
 
-		if (i == online_cpu_idx)
+		if (cpu == elected_cpu)
 			/* Map the default receive queue queue to the
 			 * elected CPU
 			 */
@@ -2873,7 +2891,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp)
 		 * the CPU bound to the default RX queue
 		 */
 		if (txq_number == 1)
-			txq_map = (i == online_cpu_idx) ?
+			txq_map = (cpu == elected_cpu) ?
 				MVNETA_CPU_TXQ_ACCESS(1) : 0;
 		else
 			txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) &
@@ -2902,6 +2920,14 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
+		spin_lock(&pp->lock);
+		/* Configuring the driver for a new CPU while the
+		 * driver is stopping is racy, so just avoid it.
+		 */
+		if (pp->is_stopped) {
+			spin_unlock(&pp->lock);
+			break;
+		}
 		netif_tx_stop_all_queues(pp->dev);
 
 		/* We have to synchronise on tha napi of each CPU
@@ -2917,9 +2943,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 		}
 
 		/* Mask all ethernet port interrupts */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+		on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 		napi_enable(&port->napi);
 
 
@@ -2934,27 +2958,25 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 		 */
 		mvneta_percpu_elect(pp);
 
-		/* Unmask all ethernet port interrupts, as this
-		 * notifier is called for each CPU then the CPU to
-		 * Queue mapping is applied
-		 */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-			MVNETA_RX_INTR_MASK(rxq_number) |
-			MVNETA_TX_INTR_MASK(txq_number) |
-			MVNETA_MISCINTR_INTR_MASK);
+		/* Unmask all ethernet port interrupts */
+		on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
 		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
 			MVNETA_CAUSE_PHY_STATUS_CHANGE |
 			MVNETA_CAUSE_LINK_CHANGE |
 			MVNETA_CAUSE_PSC_SYNC_CHANGE);
 		netif_tx_start_all_queues(pp->dev);
+		spin_unlock(&pp->lock);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		netif_tx_stop_all_queues(pp->dev);
+		/* Thanks to this lock we are sure that any pending
+		 * cpu election is done
+		 */
+		spin_lock(&pp->lock);
 		/* Mask all ethernet port interrupts */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+		on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+		spin_unlock(&pp->lock);
 
 		napi_synchronize(&port->napi);
 		napi_disable(&port->napi);
@@ -2968,12 +2990,11 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		/* Check if a new CPU must be elected now this on is down */
+		spin_lock(&pp->lock);
 		mvneta_percpu_elect(pp);
+		spin_unlock(&pp->lock);
 		/* Unmask all ethernet port interrupts */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-			MVNETA_RX_INTR_MASK(rxq_number) |
-			MVNETA_TX_INTR_MASK(txq_number) |
-			MVNETA_MISCINTR_INTR_MASK);
+		on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
 		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
 			MVNETA_CAUSE_PHY_STATUS_CHANGE |
 			MVNETA_CAUSE_LINK_CHANGE |
@@ -2988,7 +3009,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 static int mvneta_open(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	int ret, cpu;
+	int ret;
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
 	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
@@ -3010,22 +3031,12 @@ static int mvneta_open(struct net_device *dev)
 		goto err_cleanup_txqs;
 	}
 
-	/* Even though the documentation says that request_percpu_irq
-	 * doesn't enable the interrupts automatically, it actually
-	 * does so on the local CPU.
-	 *
-	 * Make sure it's disabled.
-	 */
-	mvneta_percpu_disable(pp);
-
 	/* Enable per-CPU interrupt on all the CPU to handle our RX
 	 * queue interrupts
 	 */
-	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_enable,
-					 pp, true);
-
+	on_each_cpu(mvneta_percpu_enable, pp, true);
 
+	pp->is_stopped = false;
 	/* Register a CPU notifier to handle the case where our CPU
 	 * might be taken offline.
 	 */
@@ -3057,13 +3068,20 @@ err_cleanup_rxqs:
 static int mvneta_stop(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	int cpu;
 
+	/* Inform that we are stopping so we don't want to setup the
+	 * driver for new CPUs in the notifiers
+	 */
+	spin_lock(&pp->lock);
+	pp->is_stopped = true;
 	mvneta_stop_dev(pp);
 	mvneta_mdio_remove(pp);
 	unregister_cpu_notifier(&pp->cpu_notifier);
-	for_each_present_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_disable, pp, true);
+	/* Now that the notifier are unregistered, we can release le
+	 * lock
+	 */
+	spin_unlock(&pp->lock);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(dev->irq, pp->ports);
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);
@@ -3312,9 +3330,7 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 
 	netif_tx_stop_all_queues(pp->dev);
 
-	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_mask_interrupt,
-					 pp, true);
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 
 	/* We have to synchronise on the napi of each CPU */
 	for_each_online_cpu(cpu) {
@@ -3335,7 +3351,9 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 	mvreg_write(pp, MVNETA_PORT_CONFIG, val);
 
 	/* Update the elected CPU matching the new rxq_def */
+	spin_lock(&pp->lock);
 	mvneta_percpu_elect(pp);
+	spin_unlock(&pp->lock);
 
 	/* We have to synchronise on the napi of each CPU */
 	for_each_online_cpu(cpu) {
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index a4beccf1fd46..c797971aefab 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -3061,7 +3061,7 @@ static int mvpp2_prs_mac_da_accept(struct mvpp2 *priv, int port,
 
 		pe = kzalloc(sizeof(*pe), GFP_KERNEL);
 		if (!pe)
-			return -1;
+			return -ENOMEM;
 		mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_MAC);
 		pe->index = tid;
 
@@ -3077,7 +3077,7 @@ static int mvpp2_prs_mac_da_accept(struct mvpp2 *priv, int port,
 	if (pmap == 0) {
 		if (add) {
 			kfree(pe);
-			return -1;
+			return -EINVAL;
 		}
 		mvpp2_prs_hw_inv(priv, pe->index);
 		priv->prs_shadow[pe->index].valid = false;
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 715de8affcc9..c7e939945259 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -182,10 +182,17 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 		err = mlx4_reset_slave(dev);
 	else
 		err = mlx4_reset_master(dev);
-	BUG_ON(err != 0);
 
+	if (!err) {
+		mlx4_err(dev, "device was reset successfully\n");
+	} else {
+		/* EEH could have disabled the PCI channel during reset. That's
+		 * recoverable and the PCI error flow will handle it.
+		 */
+		if (!pci_channel_offline(dev->persist->pdev))
+			BUG_ON(1);
+	}
 	dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR;
-	mlx4_err(dev, "device was reset successfully\n");
 	mutex_unlock(&persist->device_state_mutex);
 
 	/* At that step HW was already reset, now notify clients */
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index d48d5793407d..e94ca1c3fc7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2429,7 +2429,7 @@ err_thread:
 	flush_workqueue(priv->mfunc.master.comm_wq);
 	destroy_workqueue(priv->mfunc.master.comm_wq);
 err_slaves:
-	while (--i) {
+	while (i--) {
 		for (port = 1; port <= MLX4_MAX_PORTS; port++)
 			kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 3348e646db70..a849da92f857 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -318,7 +318,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	if (timestamp_en)
 		cq_context->flags  |= cpu_to_be32(1 << 19);
 
-	cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index);
+	cq_context->logsize_usrpage =
+		cpu_to_be32((ilog2(nent) << 24) |
+			    mlx4_to_hw_uar_index(dev, uar->index));
 	cq_context->comp_eqn	    = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn;
 	cq_context->log_page_size   = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 038f9ce391e6..1494997c4f7e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 	.enable		= mlx4_en_phc_enable,
 };
 
+#define MLX4_EN_WRAP_AROUND_SEC	10ULL
+
+/* This function calculates the max shift that enables the user range
+ * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register.
+ */
+static u32 freq_to_shift(u16 freq)
+{
+	u32 freq_khz = freq * 1000;
+	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
+		max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1;
+	/* calculate max possible multiplier in order to fit in 64bit */
+	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
+
+	/* This comes from the reverse of clocksource_khz2mult */
+	return ilog2(div_u64(max_mul * freq_khz, 1000000));
+}
+
 void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
@@ -254,12 +272,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	memset(&mdev->cycles, 0, sizeof(mdev->cycles));
 	mdev->cycles.read = mlx4_en_read_clock;
 	mdev->cycles.mask = CLOCKSOURCE_MASK(48);
-	/* Using shift to make calculation more accurate. Since current HW
-	 * clock frequency is 427 MHz, and cycles are given using a 48 bits
-	 * register, the biggest shift when calculating using u64, is 14
-	 * (max_cycles * multiplier < 2^64)
-	 */
-	mdev->cycles.shift = 14;
+	mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock);
 	mdev->cycles.mult =
 		clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift);
 	mdev->nominal_c_mult = mdev->cycles.mult;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 0c7e3f69a73b..f191a1612589 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2344,8 +2344,6 @@ out:
 	/* set offloads */
 	priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
 }
 
 static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
@@ -2356,8 +2354,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 	/* unset offloads */
 	priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL);
-	priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    &= ~NETIF_F_GSO_UDP_TUNNEL;
 
 	ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
 				  VXLAN_STEER_BY_OUTER_MAC, 0);
@@ -2980,6 +2976,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		priv->rss_hash_fn = ETH_RSS_HASH_TOP;
 	}
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+		dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+
 	mdev->pndev[port] = dev;
 	mdev->upper[port] = NULL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index ee99e67187f5..3904b5fc0b7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -238,11 +238,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	stats->collisions = 0;
 	stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP);
 	stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength);
-	stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_over_errors = 0;
 	stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC);
 	stats->rx_frame_errors = 0;
 	stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
-	stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_missed_errors = 0;
 	stats->tx_aborted_errors = 0;
 	stats->tx_carrier_errors = 0;
 	stats->tx_fifo_errors = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index 12aab5a659d3..02e925d6f734 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -58,7 +58,8 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	} else {
 		context->sq_size_stride = ilog2(TXBB_SIZE) - 4;
 	}
-	context->usr_page = cpu_to_be32(mdev->priv_uar.index);
+	context->usr_page = cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev,
+					mdev->priv_uar.index));
 	context->local_qpn = cpu_to_be32(qpn);
 	context->pri_path.ackto = 1 & 0x07;
 	context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4421bf5463f6..e0946ab22010 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -213,7 +213,9 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 	mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
 				ring->cqn, user_prio, &ring->context);
 	if (ring->bf_alloced)
-		ring->context.usr_page = cpu_to_be32(ring->bf.uar->index);
+		ring->context.usr_page =
+			cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev,
+							 ring->bf.uar->index));
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 4696053165f8..f613977455e0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -940,9 +940,10 @@ static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 	if (!priv->eq_table.uar_map[index]) {
 		priv->eq_table.uar_map[index] =
-			ioremap(pci_resource_start(dev->persist->pdev, 2) +
-				((eq->eqn / 4) << PAGE_SHIFT),
-				PAGE_SIZE);
+			ioremap(
+				pci_resource_start(dev->persist->pdev, 2) +
+				((eq->eqn / 4) << (dev->uar_page_shift)),
+				(1 << (dev->uar_page_shift)));
 		if (!priv->eq_table.uar_map[index]) {
 			mlx4_err(dev, "Couldn't map EQ doorbell for EQN 0x%06x\n",
 				 eq->eqn);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index f1b6d219e445..2cc3c626c3fe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -168,6 +168,20 @@ struct mlx4_port_config {
 
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
+static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
+					      struct mlx4_dev_cap *dev_cap)
+{
+	/* The reserved_uars is calculated by system page size unit.
+	 * Therefore, adjustment is added when the uar page size is less
+	 * than the system page size
+	 */
+	dev->caps.reserved_uars	=
+		max_t(int,
+		      mlx4_get_num_reserved_uar(dev),
+		      dev_cap->reserved_uars /
+			(1 << (PAGE_SHIFT - dev->uar_page_shift)));
+}
+
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -386,8 +400,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.reserved_mtts      = dev_cap->reserved_mtts;
 	dev->caps.reserved_mrws	     = dev_cap->reserved_mrws;
 
-	/* The first 128 UARs are used for EQ doorbells */
-	dev->caps.reserved_uars	     = max_t(int, 128, dev_cap->reserved_uars);
 	dev->caps.reserved_pds	     = dev_cap->reserved_pds;
 	dev->caps.reserved_xrcds     = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
 					dev_cap->reserved_xrcds : 0;
@@ -405,6 +417,15 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 
+	/* Save uar page shift */
+	if (!mlx4_is_slave(dev)) {
+		/* Virtual PCI function needs to determine UAR page size from
+		 * firmware. Only master PCI function can set the uar page size
+		 */
+		dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT;
+		mlx4_set_num_reserved_uars(dev, dev_cap);
+	}
+
 	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) {
 		struct mlx4_init_hca_param hca_param;
 
@@ -815,16 +836,25 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		return -ENODEV;
 	}
 
-	/* slave gets uar page size from QUERY_HCA fw command */
-	dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12);
+	/* Set uar_page_shift for VF */
+	dev->uar_page_shift = hca_param.uar_page_sz + 12;
 
-	/* TODO: relax this assumption */
-	if (dev->caps.uar_page_size != PAGE_SIZE) {
-		mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n",
-			 dev->caps.uar_page_size, PAGE_SIZE);
-		return -ENODEV;
+	/* Make sure the master uar page size is valid */
+	if (dev->uar_page_shift > PAGE_SHIFT) {
+		mlx4_err(dev,
+			 "Invalid configuration: uar page size is larger than system page size\n");
+		return  -ENODEV;
 	}
 
+	/* Set reserved_uars based on the uar_page_shift */
+	mlx4_set_num_reserved_uars(dev, &dev_cap);
+
+	/* Although uar page size in FW differs from system page size,
+	 * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core)
+	 * still works with assumption that uar page size == system page size
+	 */
+	dev->caps.uar_page_size = PAGE_SIZE;
+
 	memset(&func_cap, 0, sizeof(func_cap));
 	err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap);
 	if (err) {
@@ -2179,8 +2209,12 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
 
-		init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
-		init_hca.uar_page_sz = PAGE_SHIFT - 12;
+		/* Always set UAR page size 4KB, set log_uar_sz accordingly */
+		init_hca.log_uar_sz = ilog2(dev->caps.num_uars) +
+				      PAGE_SHIFT -
+				      DEFAULT_UAR_PAGE_SHIFT;
+		init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12;
+
 		init_hca.mw_enabled = 0;
 		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
 		    dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 609c59dc854e..b3cc3ab63799 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -269,9 +269,15 @@ EXPORT_SYMBOL_GPL(mlx4_bf_free);
 
 int mlx4_init_uar_table(struct mlx4_dev *dev)
 {
-	if (dev->caps.num_uars <= 128) {
-		mlx4_err(dev, "Only %d UAR pages (need more than 128)\n",
-			 dev->caps.num_uars);
+	int num_reserved_uar = mlx4_get_num_reserved_uar(dev);
+
+	mlx4_dbg(dev, "uar_page_shift = %d", dev->uar_page_shift);
+	mlx4_dbg(dev, "Effective reserved_uars=%d", dev->caps.reserved_uars);
+
+	if (dev->caps.num_uars <= num_reserved_uar) {
+		mlx4_err(
+			dev, "Only %d UAR pages (need more than %d)\n",
+			dev->caps.num_uars, num_reserved_uar);
 		mlx4_err(dev, "Increase firmware log2_uar_bar_megabytes?\n");
 		return -ENODEV;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index b46dbe29ef6c..25ce1b030a00 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -915,11 +915,13 @@ static int handle_existing_counter(struct mlx4_dev *dev, u8 slave, int port,
 
 	spin_lock_irq(mlx4_tlock(dev));
 	r = find_res(dev, counter_index, RES_COUNTER);
-	if (!r || r->owner != slave)
+	if (!r || r->owner != slave) {
 		ret = -EINVAL;
-	counter = container_of(r, struct res_counter, com);
-	if (!counter->port)
-		counter->port = port;
+	} else {
+		counter = container_of(r, struct res_counter, com);
+		if (!counter->port)
+			counter->port = port;
+	}
 
 	spin_unlock_irq(mlx4_tlock(dev));
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6a3e430f1062..d4e1c3045200 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2024,18 +2024,37 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 					    vf_stats);
 }
 
-static struct net_device_ops mlx5e_netdev_ops = {
+static const struct net_device_ops mlx5e_netdev_ops_basic = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
 	.ndo_start_xmit          = mlx5e_xmit,
 	.ndo_get_stats64         = mlx5e_get_stats,
 	.ndo_set_rx_mode         = mlx5e_set_rx_mode,
 	.ndo_set_mac_address     = mlx5e_set_mac,
-	.ndo_vlan_rx_add_vid	 = mlx5e_vlan_rx_add_vid,
-	.ndo_vlan_rx_kill_vid	 = mlx5e_vlan_rx_kill_vid,
+	.ndo_vlan_rx_add_vid     = mlx5e_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid    = mlx5e_vlan_rx_kill_vid,
 	.ndo_set_features        = mlx5e_set_features,
-	.ndo_change_mtu		 = mlx5e_change_mtu,
-	.ndo_do_ioctl		 = mlx5e_ioctl,
+	.ndo_change_mtu          = mlx5e_change_mtu,
+	.ndo_do_ioctl            = mlx5e_ioctl,
+};
+
+static const struct net_device_ops mlx5e_netdev_ops_sriov = {
+	.ndo_open                = mlx5e_open,
+	.ndo_stop                = mlx5e_close,
+	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_get_stats64         = mlx5e_get_stats,
+	.ndo_set_rx_mode         = mlx5e_set_rx_mode,
+	.ndo_set_mac_address     = mlx5e_set_mac,
+	.ndo_vlan_rx_add_vid     = mlx5e_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid    = mlx5e_vlan_rx_kill_vid,
+	.ndo_set_features        = mlx5e_set_features,
+	.ndo_change_mtu          = mlx5e_change_mtu,
+	.ndo_do_ioctl            = mlx5e_ioctl,
+	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
+	.ndo_set_vf_vlan         = mlx5e_set_vf_vlan,
+	.ndo_get_vf_config       = mlx5e_get_vf_config,
+	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
+	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -2137,18 +2156,11 @@ static void mlx5e_build_netdev(struct net_device *netdev)
 
 	SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
 
-	if (priv->params.num_tc > 1)
-		mlx5e_netdev_ops.ndo_select_queue = mlx5e_select_queue;
-
-	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
-		mlx5e_netdev_ops.ndo_set_vf_mac = mlx5e_set_vf_mac;
-		mlx5e_netdev_ops.ndo_set_vf_vlan = mlx5e_set_vf_vlan;
-		mlx5e_netdev_ops.ndo_get_vf_config = mlx5e_get_vf_config;
-		mlx5e_netdev_ops.ndo_set_vf_link_state = mlx5e_set_vf_link_state;
-		mlx5e_netdev_ops.ndo_get_vf_stats = mlx5e_get_vf_stats;
-	}
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		netdev->netdev_ops = &mlx5e_netdev_ops_sriov;
+	else
+		netdev->netdev_ops = &mlx5e_netdev_ops_basic;
 
-	netdev->netdev_ops        = &mlx5e_netdev_ops;
 	netdev->watchdog_timeo    = 15 * HZ;
 
 	netdev->ethtool_ops	  = &mlx5e_ethtool_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index 726f5435b32f..ae65b9940aed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -49,7 +49,7 @@
 #define MLXSW_PORT_MID			0xd000
 
 #define MLXSW_PORT_MAX_PHY_PORTS	0x40
-#define MLXSW_PORT_MAX_PORTS		MLXSW_PORT_MAX_PHY_PORTS
+#define MLXSW_PORT_MAX_PORTS		(MLXSW_PORT_MAX_PHY_PORTS + 1)
 
 #define MLXSW_PORT_DEVID_BITS_OFFSET	10
 #define MLXSW_PORT_PHY_BITS_OFFSET	4
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index bb77e2207804..ffe4c0305733 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -873,6 +873,62 @@ static inline void mlxsw_reg_spvm_pack(char *payload, u8 local_port,
 	}
 }
 
+/* SPAFT - Switch Port Acceptable Frame Types
+ * ------------------------------------------
+ * The Switch Port Acceptable Frame Types register configures the frame
+ * admittance of the port.
+ */
+#define MLXSW_REG_SPAFT_ID 0x2010
+#define MLXSW_REG_SPAFT_LEN 0x08
+
+static const struct mlxsw_reg_info mlxsw_reg_spaft = {
+	.id = MLXSW_REG_SPAFT_ID,
+	.len = MLXSW_REG_SPAFT_LEN,
+};
+
+/* reg_spaft_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is not supported (all tag types are allowed).
+ */
+MLXSW_ITEM32(reg, spaft, local_port, 0x00, 16, 8);
+
+/* reg_spaft_sub_port
+ * Virtual port within the physical port.
+ * Should be set to 0 when virtual ports are not enabled on the port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, sub_port, 0x00, 8, 8);
+
+/* reg_spaft_allow_untagged
+ * When set, untagged frames on the ingress are allowed (default).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, allow_untagged, 0x04, 31, 1);
+
+/* reg_spaft_allow_prio_tagged
+ * When set, priority tagged frames on the ingress are allowed (default).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, allow_prio_tagged, 0x04, 30, 1);
+
+/* reg_spaft_allow_tagged
+ * When set, tagged frames on the ingress are allowed (default).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, allow_tagged, 0x04, 29, 1);
+
+static inline void mlxsw_reg_spaft_pack(char *payload, u8 local_port,
+					bool allow_untagged)
+{
+	MLXSW_REG_ZERO(spaft, payload);
+	mlxsw_reg_spaft_local_port_set(payload, local_port);
+	mlxsw_reg_spaft_allow_untagged_set(payload, allow_untagged);
+	mlxsw_reg_spaft_allow_prio_tagged_set(payload, true);
+	mlxsw_reg_spaft_allow_tagged_set(payload, true);
+}
+
 /* SFGC - Switch Flooding Group Configuration
  * ------------------------------------------
  * The following register controls the association of flooding tables and MIDs
@@ -3203,6 +3259,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id)
 		return "SPVID";
 	case MLXSW_REG_SPVM_ID:
 		return "SPVM";
+	case MLXSW_REG_SPAFT_ID:
+		return "SPAFT";
 	case MLXSW_REG_SFGC_ID:
 		return "SFGC";
 	case MLXSW_REG_SFTR_ID:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 217856bdd400..09ce451c283b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2123,6 +2123,8 @@ static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port))
 		netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
 
+	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+
 	mlxsw_sp_port->learning = 0;
 	mlxsw_sp_port->learning_sync = 0;
 	mlxsw_sp_port->uc_flood = 0;
@@ -2746,6 +2748,13 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
 		goto err_vport_flood_set;
 	}
 
+	err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
+					  MLXSW_REG_SPMS_STATE_FORWARDING);
+	if (err) {
+		netdev_err(dev, "Failed to set STP state\n");
+		goto err_port_stp_state_set;
+	}
+
 	if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport))
 		netdev_err(dev, "Failed to flush FDB\n");
 
@@ -2763,6 +2772,7 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
 
 	return 0;
 
+err_port_stp_state_set:
 err_vport_flood_set:
 err_port_vid_learning_set:
 err_port_vid_to_fid_validate:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 7f42eb1c320e..3b89ed2f3c76 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -254,5 +254,6 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev,
 int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
 			     bool set, bool only_uc);
 void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port);
+int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index e492ca2cdecd..7b56098acc58 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -370,7 +370,8 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 	return err;
 }
 
-static int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
+static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u16 vid)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char spvid_pl[MLXSW_REG_SPVID_LEN];
@@ -379,6 +380,53 @@ static int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvid), spvid_pl);
 }
 
+static int mlxsw_sp_port_allow_untagged_set(struct mlxsw_sp_port *mlxsw_sp_port,
+					    bool allow)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char spaft_pl[MLXSW_REG_SPAFT_LEN];
+
+	mlxsw_reg_spaft_pack(spaft_pl, mlxsw_sp_port->local_port, allow);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spaft), spaft_pl);
+}
+
+int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
+{
+	struct net_device *dev = mlxsw_sp_port->dev;
+	int err;
+
+	if (!vid) {
+		err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port, false);
+		if (err) {
+			netdev_err(dev, "Failed to disallow untagged traffic\n");
+			return err;
+		}
+	} else {
+		err = __mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid);
+		if (err) {
+			netdev_err(dev, "Failed to set PVID\n");
+			return err;
+		}
+
+		/* Only allow if not already allowed. */
+		if (!mlxsw_sp_port->pvid) {
+			err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port,
+							       true);
+			if (err) {
+				netdev_err(dev, "Failed to allow untagged traffic\n");
+				goto err_port_allow_untagged_set;
+			}
+		}
+	}
+
+	mlxsw_sp_port->pvid = vid;
+	return 0;
+
+err_port_allow_untagged_set:
+	__mlxsw_sp_port_pvid_set(mlxsw_sp_port, mlxsw_sp_port->pvid);
+	return err;
+}
+
 static int mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid)
 {
 	char sfmr_pl[MLXSW_REG_SFMR_LEN];
@@ -540,7 +588,12 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			netdev_err(dev, "Unable to add PVID %d\n", vid_begin);
 			goto err_port_pvid_set;
 		}
-		mlxsw_sp_port->pvid = vid_begin;
+	} else if (!flag_pvid && old_pvid >= vid_begin && old_pvid <= vid_end) {
+		err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0);
+		if (err) {
+			netdev_err(dev, "Unable to del PVID\n");
+			goto err_port_pvid_set;
+		}
 	}
 
 	/* Changing activity bits only if HW operation succeded */
@@ -892,20 +945,18 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
 		return err;
 	}
 
+	if (init)
+		goto out;
+
 	pvid = mlxsw_sp_port->pvid;
-	if (pvid >= vid_begin && pvid <= vid_end && pvid != 1) {
-		/* Default VLAN is always 1 */
-		err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+	if (pvid >= vid_begin && pvid <= vid_end) {
+		err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0);
 		if (err) {
 			netdev_err(dev, "Unable to del PVID %d\n", pvid);
 			return err;
 		}
-		mlxsw_sp_port->pvid = 1;
 	}
 
-	if (init)
-		goto out;
-
 	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end,
 					false, false);
 	if (err) {
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 17d5571d0432..537974cfd427 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6137,28 +6137,28 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 		sw_cnt_1ms_ini = 16000000/rg_saw_cnt;
 		sw_cnt_1ms_ini &= 0x0fff;
 		data = r8168_mac_ocp_read(tp, 0xd412);
-		data &= 0x0fff;
+		data &= ~0x0fff;
 		data |= sw_cnt_1ms_ini;
 		r8168_mac_ocp_write(tp, 0xd412, data);
 	}
 
 	data = r8168_mac_ocp_read(tp, 0xe056);
-	data &= 0xf0;
-	data |= 0x07;
+	data &= ~0xf0;
+	data |= 0x70;
 	r8168_mac_ocp_write(tp, 0xe056, data);
 
 	data = r8168_mac_ocp_read(tp, 0xe052);
-	data &= 0x8008;
-	data |= 0x6000;
+	data &= ~0x6000;
+	data |= 0x8008;
 	r8168_mac_ocp_write(tp, 0xe052, data);
 
 	data = r8168_mac_ocp_read(tp, 0xe0d6);
-	data &= 0x01ff;
+	data &= ~0x01ff;
 	data |= 0x017f;
 	r8168_mac_ocp_write(tp, 0xe0d6, data);
 
 	data = r8168_mac_ocp_read(tp, 0xd420);
-	data &= 0x0fff;
+	data &= ~0x0fff;
 	data |= 0x047f;
 	r8168_mac_ocp_write(tp, 0xd420, data);
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index ac43ed914fcf..744d7806a9ee 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1139,7 +1139,8 @@ static int ravb_set_ringparam(struct net_device *ndev,
 	if (netif_running(ndev)) {
 		netif_device_detach(ndev);
 		/* Stop PTP Clock driver */
-		ravb_ptp_stop(ndev);
+		if (priv->chip_id == RCAR_GEN2)
+			ravb_ptp_stop(ndev);
 		/* Wait for DMA stopping */
 		error = ravb_stop_dma(ndev);
 		if (error) {
@@ -1170,7 +1171,8 @@ static int ravb_set_ringparam(struct net_device *ndev,
 		ravb_emac_init(ndev);
 
 		/* Initialise PTP Clock driver */
-		ravb_ptp_init(ndev, priv->pdev);
+		if (priv->chip_id == RCAR_GEN2)
+			ravb_ptp_init(ndev, priv->pdev);
 
 		netif_device_attach(ndev);
 	}
@@ -1298,7 +1300,8 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	netif_tx_stop_all_queues(ndev);
 
 	/* Stop PTP Clock driver */
-	ravb_ptp_stop(ndev);
+	if (priv->chip_id == RCAR_GEN2)
+		ravb_ptp_stop(ndev);
 
 	/* Wait for DMA stopping */
 	ravb_stop_dma(ndev);
@@ -1311,7 +1314,8 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	ravb_emac_init(ndev);
 
 	/* Initialise PTP Clock driver */
-	ravb_ptp_init(ndev, priv->pdev);
+	if (priv->chip_id == RCAR_GEN2)
+		ravb_ptp_init(ndev, priv->pdev);
 
 	netif_tx_start_all_queues(ndev);
 }
@@ -1814,10 +1818,6 @@ static int ravb_probe(struct platform_device *pdev)
 			   CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB, CCC);
 	}
 
-	/* Set CSEL value */
-	ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_CSEL) | CCC_CSEL_HPB,
-		   CCC);
-
 	/* Set GTI value */
 	error = ravb_set_gti(ndev);
 	if (error)
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 0e2fc1a844ab..db7db8ac4ca3 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2342,8 +2342,8 @@ static int smc_drv_probe(struct platform_device *pdev)
 	}
 
 	ndev->irq = platform_get_irq(pdev, 0);
-	if (ndev->irq <= 0) {
-		ret = -ENODEV;
+	if (ndev->irq < 0) {
+		ret = ndev->irq;
 		goto out_release_io;
 	}
 	/*
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 70814b7386b3..fc8bbff2d7e3 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -1880,9 +1880,9 @@ static int dwceqos_open(struct net_device *ndev)
 	}
 	netdev_reset_queue(ndev);
 
+	dwceqos_init_hw(lp);
 	napi_enable(&lp->napi);
 	phy_start(lp->phy_dev);
-	dwceqos_init_hw(lp);
 
 	netif_start_queue(ndev);
 	tasklet_enable(&lp->tx_bdreclaim_tasklet);
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index e9cc61e1ec74..c3e85acfdc70 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -63,8 +63,12 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv,
 		mode = AM33XX_GMII_SEL_MODE_RGMII;
 		break;
 
-	case PHY_INTERFACE_MODE_MII:
 	default:
+		dev_warn(priv->dev,
+			 "Unsupported PHY mode: \"%s\". Defaulting to MII.\n",
+			phy_modes(phy_mode));
+		/* fallthrough */
+	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
 	};
@@ -106,8 +110,12 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv,
 		mode = AM33XX_GMII_SEL_MODE_RGMII;
 		break;
 
-	case PHY_INTERFACE_MODE_MII:
 	default:
+		dev_warn(priv->dev,
+			 "Unsupported PHY mode: \"%s\". Defaulting to MII.\n",
+			phy_modes(phy_mode));
+		/* fallthrough */
+	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
 	};
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index c61d66d38634..029841f98c32 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -117,21 +117,17 @@ static void get_pkt_info(dma_addr_t *buff, u32 *buff_len, dma_addr_t *ndesc,
 	*ndesc = le32_to_cpu(desc->next_desc);
 }
 
-static void get_pad_info(u32 *pad0, u32 *pad1, u32 *pad2, struct knav_dma_desc *desc)
+static u32 get_sw_data(int index, struct knav_dma_desc *desc)
 {
-	*pad0 = le32_to_cpu(desc->pad[0]);
-	*pad1 = le32_to_cpu(desc->pad[1]);
-	*pad2 = le32_to_cpu(desc->pad[2]);
+	/* No Endian conversion needed as this data is untouched by hw */
+	return desc->sw_data[index];
 }
 
-static void get_pad_ptr(void **padptr, struct knav_dma_desc *desc)
-{
-	u64 pad64;
-
-	pad64 = le32_to_cpu(desc->pad[0]) +
-		((u64)le32_to_cpu(desc->pad[1]) << 32);
-	*padptr = (void *)(uintptr_t)pad64;
-}
+/* use these macros to get sw data */
+#define GET_SW_DATA0(desc) get_sw_data(0, desc)
+#define GET_SW_DATA1(desc) get_sw_data(1, desc)
+#define GET_SW_DATA2(desc) get_sw_data(2, desc)
+#define GET_SW_DATA3(desc) get_sw_data(3, desc)
 
 static void get_org_pkt_info(dma_addr_t *buff, u32 *buff_len,
 			     struct knav_dma_desc *desc)
@@ -163,13 +159,18 @@ static void set_desc_info(u32 desc_info, u32 pkt_info,
 	desc->packet_info = cpu_to_le32(pkt_info);
 }
 
-static void set_pad_info(u32 pad0, u32 pad1, u32 pad2, struct knav_dma_desc *desc)
+static void set_sw_data(int index, u32 data, struct knav_dma_desc *desc)
 {
-	desc->pad[0] = cpu_to_le32(pad0);
-	desc->pad[1] = cpu_to_le32(pad1);
-	desc->pad[2] = cpu_to_le32(pad1);
+	/* No Endian conversion needed as this data is untouched by hw */
+	desc->sw_data[index] = data;
 }
 
+/* use these macros to set sw data */
+#define SET_SW_DATA0(data, desc) set_sw_data(0, data, desc)
+#define SET_SW_DATA1(data, desc) set_sw_data(1, data, desc)
+#define SET_SW_DATA2(data, desc) set_sw_data(2, data, desc)
+#define SET_SW_DATA3(data, desc) set_sw_data(3, data, desc)
+
 static void set_org_pkt_info(dma_addr_t buff, u32 buff_len,
 			     struct knav_dma_desc *desc)
 {
@@ -581,7 +582,6 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp,
 	dma_addr_t dma_desc, dma_buf;
 	unsigned int buf_len, dma_sz = sizeof(*ndesc);
 	void *buf_ptr;
-	u32 pad[2];
 	u32 tmp;
 
 	get_words(&dma_desc, 1, &desc->next_desc);
@@ -593,14 +593,20 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp,
 			break;
 		}
 		get_pkt_info(&dma_buf, &tmp, &dma_desc, ndesc);
-		get_pad_ptr(&buf_ptr, ndesc);
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		buf_ptr = (void *)GET_SW_DATA0(ndesc);
+		buf_len = (int)GET_SW_DATA1(desc);
 		dma_unmap_page(netcp->dev, dma_buf, PAGE_SIZE, DMA_FROM_DEVICE);
 		__free_page(buf_ptr);
 		knav_pool_desc_put(netcp->rx_pool, desc);
 	}
-
-	get_pad_info(&pad[0], &pad[1], &buf_len, desc);
-	buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32));
+	/* warning!!!! We are retrieving the virtual ptr in the sw_data
+	 * field as a 32bit value. Will not work on 64bit machines
+	 */
+	buf_ptr = (void *)GET_SW_DATA0(desc);
+	buf_len = (int)GET_SW_DATA1(desc);
 
 	if (buf_ptr)
 		netcp_frag_free(buf_len <= PAGE_SIZE, buf_ptr);
@@ -639,7 +645,6 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 	dma_addr_t dma_desc, dma_buff;
 	struct netcp_packet p_info;
 	struct sk_buff *skb;
-	u32 pad[2];
 	void *org_buf_ptr;
 
 	dma_desc = knav_queue_pop(netcp->rx_queue, &dma_sz);
@@ -653,8 +658,11 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 	}
 
 	get_pkt_info(&dma_buff, &buf_len, &dma_desc, desc);
-	get_pad_info(&pad[0], &pad[1], &org_buf_len, desc);
-	org_buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32));
+	/* warning!!!! We are retrieving the virtual ptr in the sw_data
+	 * field as a 32bit value. Will not work on 64bit machines
+	 */
+	org_buf_ptr = (void *)GET_SW_DATA0(desc);
+	org_buf_len = (int)GET_SW_DATA1(desc);
 
 	if (unlikely(!org_buf_ptr)) {
 		dev_err(netcp->ndev_dev, "NULL bufptr in desc\n");
@@ -679,7 +687,6 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 	/* Fill in the page fragment list */
 	while (dma_desc) {
 		struct page *page;
-		void *ptr;
 
 		ndesc = knav_pool_desc_unmap(netcp->rx_pool, dma_desc, dma_sz);
 		if (unlikely(!ndesc)) {
@@ -688,8 +695,10 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 		}
 
 		get_pkt_info(&dma_buff, &buf_len, &dma_desc, ndesc);
-		get_pad_ptr(&ptr, ndesc);
-		page = ptr;
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		page = (struct page *)GET_SW_DATA0(desc);
 
 		if (likely(dma_buff && buf_len && page)) {
 			dma_unmap_page(netcp->dev, dma_buff, PAGE_SIZE,
@@ -777,7 +786,10 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq)
 		}
 
 		get_org_pkt_info(&dma, &buf_len, desc);
-		get_pad_ptr(&buf_ptr, desc);
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		buf_ptr = (void *)GET_SW_DATA0(desc);
 
 		if (unlikely(!dma)) {
 			dev_err(netcp->ndev_dev, "NULL orig_buff in desc\n");
@@ -829,7 +841,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	struct page *page;
 	dma_addr_t dma;
 	void *bufptr;
-	u32 pad[3];
+	u32 sw_data[2];
 
 	/* Allocate descriptor */
 	hwdesc = knav_pool_desc_get(netcp->rx_pool);
@@ -846,7 +858,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 				SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 		bufptr = netdev_alloc_frag(primary_buf_len);
-		pad[2] = primary_buf_len;
+		sw_data[1] = primary_buf_len;
 
 		if (unlikely(!bufptr)) {
 			dev_warn_ratelimited(netcp->ndev_dev,
@@ -858,9 +870,10 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 		if (unlikely(dma_mapping_error(netcp->dev, dma)))
 			goto fail;
 
-		pad[0] = lower_32_bits((uintptr_t)bufptr);
-		pad[1] = upper_32_bits((uintptr_t)bufptr);
-
+		/* warning!!!! We are saving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		sw_data[0] = (u32)bufptr;
 	} else {
 		/* Allocate a secondary receive queue entry */
 		page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD);
@@ -870,9 +883,11 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 		}
 		buf_len = PAGE_SIZE;
 		dma = dma_map_page(netcp->dev, page, 0, buf_len, DMA_TO_DEVICE);
-		pad[0] = lower_32_bits(dma);
-		pad[1] = upper_32_bits(dma);
-		pad[2] = 0;
+		/* warning!!!! We are saving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		sw_data[0] = (u32)page;
+		sw_data[1] = 0;
 	}
 
 	desc_info =  KNAV_DMA_DESC_PS_INFO_IN_DESC;
@@ -882,7 +897,8 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	pkt_info |= (netcp->rx_queue_id & KNAV_DMA_DESC_RETQ_MASK) <<
 		    KNAV_DMA_DESC_RETQ_SHIFT;
 	set_org_pkt_info(dma, buf_len, hwdesc);
-	set_pad_info(pad[0], pad[1], pad[2], hwdesc);
+	SET_SW_DATA0(sw_data[0], hwdesc);
+	SET_SW_DATA1(sw_data[1], hwdesc);
 	set_desc_info(desc_info, pkt_info, hwdesc);
 
 	/* Push to FDQs */
@@ -971,7 +987,6 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp,
 					  unsigned int budget)
 {
 	struct knav_dma_desc *desc;
-	void *ptr;
 	struct sk_buff *skb;
 	unsigned int dma_sz;
 	dma_addr_t dma;
@@ -988,8 +1003,10 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp,
 			continue;
 		}
 
-		get_pad_ptr(&ptr, desc);
-		skb = ptr;
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		skb = (struct sk_buff *)GET_SW_DATA0(desc);
 		netcp_free_tx_desc_chain(netcp, desc, dma_sz);
 		if (!skb) {
 			dev_err(netcp->ndev_dev, "No skb in Tx desc\n");
@@ -1194,10 +1211,10 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp,
 	}
 
 	set_words(&tmp, 1, &desc->packet_info);
-	tmp = lower_32_bits((uintptr_t)&skb);
-	set_words(&tmp, 1, &desc->pad[0]);
-	tmp = upper_32_bits((uintptr_t)&skb);
-	set_words(&tmp, 1, &desc->pad[1]);
+	/* warning!!!! We are saving the virtual ptr in the sw_data
+	 * field as a 32bit value. Will not work on 64bit machines
+	 */
+	SET_SW_DATA0((u32)skb, desc);
 
 	if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) {
 		tmp = tx_pipe->switch_to_port;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 0b14ac3b8d11..0bf7edd99573 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1039,6 +1039,34 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	return geneve_xmit_skb(skb, dev, info);
 }
 
+static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
+{
+	/* The max_mtu calculation does not take account of GENEVE
+	 * options, to avoid excluding potentially valid
+	 * configurations.
+	 */
+	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr)
+		- dev->hard_header_len;
+
+	if (new_mtu < 68)
+		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static int geneve_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __geneve_change_mtu(dev, new_mtu, true);
+}
+
 static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
@@ -1083,7 +1111,7 @@ static const struct net_device_ops geneve_netdev_ops = {
 	.ndo_stop		= geneve_stop,
 	.ndo_start_xmit		= geneve_xmit,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
-	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_change_mtu		= geneve_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_fill_metadata_dst	= geneve_fill_metadata_dst,
@@ -1150,6 +1178,7 @@ static void geneve_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 
 	netif_keep_dst(dev);
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	eth_hw_addr_random(dev);
 }
@@ -1441,12 +1470,23 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 		return dev;
 
 	err = geneve_configure(net, dev, &geneve_remote_unspec,
-			       0, 0, 0, htons(dst_port), true, 0);
-	if (err) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
+			       0, 0, 0, htons(dst_port), true,
+			       GENEVE_F_UDP_ZERO_CSUM6_RX);
+	if (err)
+		goto err;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __geneve_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto err;
+
 	return dev;
+
+ err:
+	free_netdev(dev);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 1d3a66563bac..98e34fee45c7 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1089,6 +1089,9 @@ static int netvsc_probe(struct hv_device *dev,
 	net->ethtool_ops = &ethtool_ops;
 	SET_NETDEV_DEV(net, &dev->device);
 
+	/* We always need headroom for rndis header */
+	net->needed_headroom = RNDIS_AND_PPI_SIZE;
+
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index bf241a3ec5e5..db507e3bcab9 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -250,10 +250,6 @@ static int bcm7xxx_config_init(struct phy_device *phydev)
 	phy_write(phydev, MII_BCM7XXX_AUX_MODE, MII_BCM7XX_64CLK_MDIO);
 	phy_read(phydev, MII_BCM7XXX_AUX_MODE);
 
-	/* Workaround only required for 100Mbits/sec capable PHYs */
-	if (phydev->supported & PHY_GBIT_FEATURES)
-		return 0;
-
 	/* set shadow mode 2 */
 	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
 			MII_BCM7XXX_SHD_MODE_2, MII_BCM7XXX_SHD_MODE_2);
@@ -270,7 +266,7 @@ static int bcm7xxx_config_init(struct phy_device *phydev)
 	phy_write(phydev, MII_BCM7XXX_100TX_FALSE_CAR, 0x7555);
 
 	/* reset shadow mode 2 */
-	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, 0);
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, MII_BCM7XXX_SHD_MODE_2);
 	if (ret < 0)
 		return ret;
 
@@ -307,11 +303,6 @@ static int bcm7xxx_suspend(struct phy_device *phydev)
 	return 0;
 }
 
-static int bcm7xxx_dummy_config_init(struct phy_device *phydev)
-{
-	return 0;
-}
-
 #define BCM7XXX_28NM_GPHY(_oui, _name)					\
 {									\
 	.phy_id		= (_oui),					\
@@ -337,7 +328,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.phy_id         = PHY_ID_BCM7425,
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM7425",
-	.features       = PHY_GBIT_FEATURES |
+	.features       = PHY_BASIC_FEATURES |
 			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
 	.flags          = PHY_IS_INTERNAL,
 	.config_init    = bcm7xxx_config_init,
@@ -349,7 +340,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.phy_id         = PHY_ID_BCM7429,
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM7429",
-	.features       = PHY_GBIT_FEATURES |
+	.features       = PHY_BASIC_FEATURES |
 			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
 	.flags          = PHY_IS_INTERNAL,
 	.config_init    = bcm7xxx_config_init,
@@ -361,7 +352,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.phy_id         = PHY_ID_BCM7435,
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM7435",
-	.features       = PHY_GBIT_FEATURES |
+	.features       = PHY_BASIC_FEATURES |
 			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
 	.flags          = PHY_IS_INTERNAL,
 	.config_init    = bcm7xxx_config_init,
@@ -369,30 +360,6 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.read_status    = genphy_read_status,
 	.suspend        = bcm7xxx_suspend,
 	.resume         = bcm7xxx_config_init,
-}, {
-	.phy_id		= PHY_BCM_OUI_4,
-	.phy_id_mask	= 0xffff0000,
-	.name		= "Broadcom BCM7XXX 40nm",
-	.features	= PHY_GBIT_FEATURES |
-			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
-	.flags		= PHY_IS_INTERNAL,
-	.config_init	= bcm7xxx_config_init,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.suspend	= bcm7xxx_suspend,
-	.resume		= bcm7xxx_config_init,
-}, {
-	.phy_id		= PHY_BCM_OUI_5,
-	.phy_id_mask	= 0xffffff00,
-	.name		= "Broadcom BCM7XXX 65nm",
-	.features	= PHY_BASIC_FEATURES |
-			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
-	.flags		= PHY_IS_INTERNAL,
-	.config_init	= bcm7xxx_dummy_config_init,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.suspend	= bcm7xxx_suspend,
-	.resume		= bcm7xxx_config_init,
 } };
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
@@ -404,8 +371,6 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
 	{ PHY_ID_BCM7439, 0xfffffff0, },
 	{ PHY_ID_BCM7435, 0xfffffff0, },
 	{ PHY_ID_BCM7445, 0xfffffff0, },
-	{ PHY_BCM_OUI_4, 0xffff0000 },
-	{ PHY_BCM_OUI_5, 0xffffff00 },
 	{ }
 };
 
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index e3eb96443c97..ab1d0fcaf1d9 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -446,6 +446,12 @@ static int m88e1510_config_aneg(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
+	return 0;
+}
+
+static int marvell_config_init(struct phy_device *phydev)
+{
+	/* Set registers from marvell,reg-init DT property */
 	return marvell_of_reg_init(phydev);
 }
 
@@ -495,7 +501,7 @@ static int m88e1116r_config_init(struct phy_device *phydev)
 
 	mdelay(500);
 
-	return 0;
+	return marvell_config_init(phydev);
 }
 
 static int m88e3016_config_init(struct phy_device *phydev)
@@ -514,7 +520,7 @@ static int m88e3016_config_init(struct phy_device *phydev)
 	if (reg < 0)
 		return reg;
 
-	return 0;
+	return marvell_config_init(phydev);
 }
 
 static int m88e1111_config_init(struct phy_device *phydev)
@@ -1078,6 +1084,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.probe = marvell_probe,
 		.flags = PHY_HAS_INTERRUPT,
+		.config_init = &marvell_config_init,
 		.config_aneg = &marvell_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1149,6 +1156,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1121_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1167,6 +1175,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1318_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1259,6 +1268,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1277,6 +1287,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index bad3f005faee..e551f3a89cfd 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1410,7 +1410,7 @@ int genphy_config_init(struct phy_device *phydev)
 
 	features = (SUPPORTED_TP | SUPPORTED_MII
 			| SUPPORTED_AUI | SUPPORTED_FIBRE |
-			SUPPORTED_BNC);
+			SUPPORTED_BNC | SUPPORTED_Pause | SUPPORTED_Asym_Pause);
 
 	/* Do we support autonegotiation? */
 	val = phy_read(phydev, MII_BMSR);
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index f3c63022eb3c..4ddae8118c85 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -395,6 +395,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
 
 		if (!__pppoe_xmit(sk_pppox(relay_po), skb))
 			goto abort_put;
+
+		sock_put(sk_pppox(relay_po));
 	} else {
 		if (sock_queue_rcv_skb(sk, skb))
 			goto abort_kfree;
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 7f83504dfa69..cdde59089f72 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -395,6 +395,10 @@ config USB_NET_RNDIS_HOST
 	  The protocol specification is incomplete, and is controlled by
 	  (and for) Microsoft; it isn't an "Open" ecosystem or market.
 
+config USB_NET_CDC_SUBSET_ENABLE
+	tristate
+	depends on USB_NET_CDC_SUBSET
+
 config USB_NET_CDC_SUBSET
 	tristate "Simple USB Network Links (CDC Ethernet subset)"
 	depends on USB_USBNET
@@ -413,6 +417,7 @@ config USB_NET_CDC_SUBSET
 config USB_ALI_M5632
 	bool "ALi M5632 based 'USB 2.0 Data Link' cables"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option if you're using a host-to-host cable
 	  based on this design, which supports USB 2.0 high speed.
@@ -420,6 +425,7 @@ config USB_ALI_M5632
 config USB_AN2720
 	bool "AnchorChips 2720 based cables (Xircom PGUNET, ...)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option if you're using a host-to-host cable
 	  based on this design.  Note that AnchorChips is now a
@@ -428,6 +434,7 @@ config USB_AN2720
 config USB_BELKIN
 	bool "eTEK based host-to-host cables (Advance, Belkin, ...)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	default y
 	help
 	  Choose this option if you're using a host-to-host cable
@@ -437,6 +444,7 @@ config USB_BELKIN
 config USB_ARMLINUX
 	bool "Embedded ARM Linux links (iPaq, ...)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	default y
 	help
 	  Choose this option to support the "usb-eth" networking driver
@@ -454,6 +462,7 @@ config USB_ARMLINUX
 config USB_EPSON2888
 	bool "Epson 2888 based firmware (DEVELOPMENT)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option to support the usb networking links used
 	  by some sample firmware from Epson.
@@ -461,6 +470,7 @@ config USB_EPSON2888
 config USB_KC2190
 	bool "KT Technology KC2190 based cables (InstaNet)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option if you're using a host-to-host cable
 	  with one of these chips.
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index b5f04068dbe4..37fb46aee341 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -23,7 +23,7 @@ obj-$(CONFIG_USB_NET_GL620A)	+= gl620a.o
 obj-$(CONFIG_USB_NET_NET1080)	+= net1080.o
 obj-$(CONFIG_USB_NET_PLUSB)	+= plusb.o
 obj-$(CONFIG_USB_NET_RNDIS_HOST)	+= rndis_host.o
-obj-$(CONFIG_USB_NET_CDC_SUBSET)	+= cdc_subset.o
+obj-$(CONFIG_USB_NET_CDC_SUBSET_ENABLE)	+= cdc_subset.o
 obj-$(CONFIG_USB_NET_ZAURUS)	+= zaurus.o
 obj-$(CONFIG_USB_NET_MCS7830)	+= mcs7830.o
 obj-$(CONFIG_USB_USBNET)	+= usbnet.o
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 23e9880791fc..570deef53f74 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -637,6 +637,7 @@ static const struct usb_device_id products[] = {
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
+	{QMI_FIXED_INTF(0x05c6, 0x6001, 3)},	/* 4G LTE usb-modem U901 */
 	{QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
 	{QMI_FIXED_INTF(0x05c6, 0x7002, 1)},
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 221a53025fd0..72ba8ae7f09a 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -377,7 +377,7 @@ union Vmxnet3_GenericDesc {
 #define VMXNET3_TX_RING_MAX_SIZE   4096
 #define VMXNET3_TC_RING_MAX_SIZE   4096
 #define VMXNET3_RX_RING_MAX_SIZE   4096
-#define VMXNET3_RX_RING2_MAX_SIZE  2048
+#define VMXNET3_RX_RING2_MAX_SIZE  4096
 #define VMXNET3_RC_RING_MAX_SIZE   8192
 
 /* a list of reasons for queue stop */
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index bdb8a6c0f8aa..729c344e6774 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.5.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.6.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040500
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040600
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 65439188c582..e6944b29588e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2171,9 +2171,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 #endif
 	}
 
-	if (vxlan->flags & VXLAN_F_COLLECT_METADATA &&
-	    info && info->mode & IP_TUNNEL_INFO_TX) {
-		vxlan_xmit_one(skb, dev, NULL, false);
+	if (vxlan->flags & VXLAN_F_COLLECT_METADATA) {
+		if (info && info->mode & IP_TUNNEL_INFO_TX)
+			vxlan_xmit_one(skb, dev, NULL, false);
+		else
+			kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -2367,29 +2369,43 @@ static void vxlan_set_multicast_list(struct net_device *dev)
 {
 }
 
-static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+static int __vxlan_change_mtu(struct net_device *dev,
+			      struct net_device *lowerdev,
+			      struct vxlan_rdst *dst, int new_mtu, bool strict)
 {
-	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_rdst *dst = &vxlan->default_dst;
-	struct net_device *lowerdev;
-	int max_mtu;
+	int max_mtu = IP_MAX_MTU;
 
-	lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
-	if (lowerdev == NULL)
-		return eth_change_mtu(dev, new_mtu);
+	if (lowerdev)
+		max_mtu = lowerdev->mtu;
 
 	if (dst->remote_ip.sa.sa_family == AF_INET6)
-		max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
+		max_mtu -= VXLAN6_HEADROOM;
 	else
-		max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
+		max_mtu -= VXLAN_HEADROOM;
 
-	if (new_mtu < 68 || new_mtu > max_mtu)
+	if (new_mtu < 68)
 		return -EINVAL;
 
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
 
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst *dst = &vxlan->default_dst;
+	struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
+							 dst->remote_ifindex);
+	return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
+}
+
 static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
 				struct ip_tunnel_info *info,
 				__be16 sport, __be16 dport)
@@ -2523,6 +2539,7 @@ static void vxlan_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 	netif_keep_dst(dev);
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 
 	INIT_LIST_HEAD(&vxlan->next);
@@ -2765,6 +2782,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	int err;
 	bool use_ipv6 = false;
 	__be16 default_port = vxlan->cfg.dst_port;
+	struct net_device *lowerdev = NULL;
 
 	vxlan->net = src_net;
 
@@ -2785,9 +2803,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	}
 
 	if (conf->remote_ifindex) {
-		struct net_device *lowerdev
-			 = __dev_get_by_index(src_net, conf->remote_ifindex);
-
+		lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
 		dst->remote_ifindex = conf->remote_ifindex;
 
 		if (!lowerdev) {
@@ -2811,6 +2827,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		needed_headroom = lowerdev->hard_header_len;
 	}
 
+	if (conf->mtu) {
+		err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false);
+		if (err)
+			return err;
+	}
+
 	if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
 		needed_headroom += VXLAN6_HEADROOM;
 	else
diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c
index 7a72407208b1..629225980463 100644
--- a/drivers/net/wan/dscc4.c
+++ b/drivers/net/wan/dscc4.c
@@ -1626,7 +1626,7 @@ try:
 		if (state & Xpr) {
 			void __iomem *scc_addr;
 			unsigned long ring;
-			int i;
+			unsigned int i;
 
 			/*
 			 * - the busy condition happens (sometimes);
diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig
index 866067789330..7438fbeef744 100644
--- a/drivers/net/wireless/intel/iwlwifi/Kconfig
+++ b/drivers/net/wireless/intel/iwlwifi/Kconfig
@@ -53,7 +53,6 @@ config IWLWIFI_LEDS
 
 config IWLDVM
 	tristate "Intel Wireless WiFi DVM Firmware support"
-	depends on m
 	help
 	  This is the driver that supports the DVM firmware. The list
 	  of the devices that use this firmware is available here:
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
index c84a0299d43e..bce9b3420a13 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2014 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -70,12 +71,15 @@
 
 /* Highest firmware API version supported */
 #define IWL8000_UCODE_API_MAX	20
+#define IWL8265_UCODE_API_MAX	20
 
 /* Oldest version we won't warn about */
 #define IWL8000_UCODE_API_OK	13
+#define IWL8265_UCODE_API_OK	20
 
 /* Lowest firmware API version supported */
 #define IWL8000_UCODE_API_MIN	13
+#define IWL8265_UCODE_API_MIN	20
 
 /* NVM versions */
 #define IWL8000_NVM_VERSION		0x0a1d
@@ -93,6 +97,10 @@
 #define IWL8000_MODULE_FIRMWARE(api) \
 	IWL8000_FW_PRE "-" __stringify(api) ".ucode"
 
+#define IWL8265_FW_PRE "iwlwifi-8265-"
+#define IWL8265_MODULE_FIRMWARE(api) \
+	IWL8265_FW_PRE __stringify(api) ".ucode"
+
 #define NVM_HW_SECTION_NUM_FAMILY_8000		10
 #define DEFAULT_NVM_FILE_FAMILY_8000B		"nvmData-8000B"
 #define DEFAULT_NVM_FILE_FAMILY_8000C		"nvmData-8000C"
@@ -144,10 +152,7 @@ static const struct iwl_tt_params iwl8000_tt_params = {
 	.support_tx_backoff = true,
 };
 
-#define IWL_DEVICE_8000							\
-	.ucode_api_max = IWL8000_UCODE_API_MAX,				\
-	.ucode_api_ok = IWL8000_UCODE_API_OK,				\
-	.ucode_api_min = IWL8000_UCODE_API_MIN,				\
+#define IWL_DEVICE_8000_COMMON						\
 	.device_family = IWL_DEVICE_FAMILY_8000,			\
 	.max_inst_size = IWL60_RTC_INST_SIZE,				\
 	.max_data_size = IWL60_RTC_DATA_SIZE,				\
@@ -167,10 +172,28 @@ static const struct iwl_tt_params iwl8000_tt_params = {
 	.thermal_params = &iwl8000_tt_params,				\
 	.apmg_not_supported = true
 
+#define IWL_DEVICE_8000							\
+	IWL_DEVICE_8000_COMMON,						\
+	.ucode_api_max = IWL8000_UCODE_API_MAX,				\
+	.ucode_api_ok = IWL8000_UCODE_API_OK,				\
+	.ucode_api_min = IWL8000_UCODE_API_MIN				\
+
+#define IWL_DEVICE_8260							\
+	IWL_DEVICE_8000_COMMON,						\
+	.ucode_api_max = IWL8000_UCODE_API_MAX,				\
+	.ucode_api_ok = IWL8000_UCODE_API_OK,				\
+	.ucode_api_min = IWL8000_UCODE_API_MIN				\
+
+#define IWL_DEVICE_8265							\
+	IWL_DEVICE_8000_COMMON,						\
+	.ucode_api_max = IWL8265_UCODE_API_MAX,				\
+	.ucode_api_ok = IWL8265_UCODE_API_OK,				\
+	.ucode_api_min = IWL8265_UCODE_API_MIN				\
+
 const struct iwl_cfg iwl8260_2n_cfg = {
 	.name = "Intel(R) Dual Band Wireless N 8260",
 	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -179,7 +202,7 @@ const struct iwl_cfg iwl8260_2n_cfg = {
 const struct iwl_cfg iwl8260_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 8260",
 	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -188,8 +211,8 @@ const struct iwl_cfg iwl8260_2ac_cfg = {
 
 const struct iwl_cfg iwl8265_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 8265",
-	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	.fw_name_pre = IWL8265_FW_PRE,
+	IWL_DEVICE_8265,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -209,7 +232,7 @@ const struct iwl_cfg iwl4165_2ac_cfg = {
 const struct iwl_cfg iwl8260_2ac_sdio_cfg = {
 	.name = "Intel(R) Dual Band Wireless-AC 8260",
 	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -236,3 +259,4 @@ const struct iwl_cfg iwl4165_2ac_sdio_cfg = {
 };
 
 MODULE_FIRMWARE(IWL8000_MODULE_FIRMWARE(IWL8000_UCODE_API_OK));
+MODULE_FIRMWARE(IWL8265_MODULE_FIRMWARE(IWL8265_UCODE_API_OK));
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 7acb49075683..ab4c2a0470b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -243,8 +243,10 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first)
 	if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) {
 		char rev_step = 'A' + CSR_HW_REV_STEP(drv->trans->hw_rev);
 
-		snprintf(drv->firmware_name, sizeof(drv->firmware_name),
-			 "%s%c-%s.ucode", name_pre, rev_step, tag);
+		if (rev_step != 'A')
+			snprintf(drv->firmware_name,
+				 sizeof(drv->firmware_name), "%s%c-%s.ucode",
+				 name_pre, rev_step, tag);
 	}
 
 	IWL_DEBUG_INFO(drv, "attempting to load firmware %s'%s'\n",
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 9a15642f80dd..ea1e177c2ea1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1298,6 +1298,10 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
 		return -EBUSY;
 	}
 
+	/* we don't support "match all" in the firmware */
+	if (!req->n_match_sets)
+		return -EOPNOTSUPP;
+
 	ret = iwl_mvm_check_running_scans(mvm, type);
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index cc3888e2700d..73c95594eabe 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -490,6 +490,15 @@ static inline void iwl_enable_interrupts(struct iwl_trans *trans)
 	iwl_write32(trans, CSR_INT_MASK, trans_pcie->inta_mask);
 }
 
+static inline void iwl_enable_fw_load_int(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	IWL_DEBUG_ISR(trans, "Enabling FW load interrupt\n");
+	trans_pcie->inta_mask = CSR_INT_BIT_FH_TX;
+	iwl_write32(trans, CSR_INT_MASK, trans_pcie->inta_mask);
+}
+
 static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index ccafbd8cf4b3..152cf9ad9566 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1438,9 +1438,11 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 			 inta & ~trans_pcie->inta_mask);
 	}
 
-	/* Re-enable all interrupts */
-	/* only Re-enable if disabled by irq */
-	if (test_bit(STATUS_INT_ENABLED, &trans->status))
+	/* we are loading the firmware, enable FH_TX interrupt only */
+	if (handled & CSR_INT_BIT_FH_TX)
+		iwl_enable_fw_load_int(trans);
+	/* only Re-enable all interrupt if disabled by irq */
+	else if (test_bit(STATUS_INT_ENABLED, &trans->status))
 		iwl_enable_interrupts(trans);
 	/* Re-enable RF_KILL if it occurred */
 	else if (handled & CSR_INT_BIT_RF_KILL)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index d60a467a983c..5a854c609477 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1021,82 +1021,6 @@ static int iwl_pcie_load_given_ucode_8000(struct iwl_trans *trans,
 					       &first_ucode_section);
 }
 
-static int iwl_trans_pcie_start_fw(struct iwl_trans *trans,
-				   const struct fw_img *fw, bool run_in_rfkill)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	bool hw_rfkill;
-	int ret;
-
-	mutex_lock(&trans_pcie->mutex);
-
-	/* Someone called stop_device, don't try to start_fw */
-	if (trans_pcie->is_down) {
-		IWL_WARN(trans,
-			 "Can't start_fw since the HW hasn't been started\n");
-		ret = EIO;
-		goto out;
-	}
-
-	/* This may fail if AMT took ownership of the device */
-	if (iwl_pcie_prepare_card_hw(trans)) {
-		IWL_WARN(trans, "Exit HW not ready\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	iwl_enable_rfkill_int(trans);
-
-	/* If platform's RF_KILL switch is NOT set to KILL */
-	hw_rfkill = iwl_is_rfkill_set(trans);
-	if (hw_rfkill)
-		set_bit(STATUS_RFKILL, &trans->status);
-	else
-		clear_bit(STATUS_RFKILL, &trans->status);
-	iwl_trans_pcie_rf_kill(trans, hw_rfkill);
-	if (hw_rfkill && !run_in_rfkill) {
-		ret = -ERFKILL;
-		goto out;
-	}
-
-	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
-
-	ret = iwl_pcie_nic_init(trans);
-	if (ret) {
-		IWL_ERR(trans, "Unable to init nic\n");
-		goto out;
-	}
-
-	/* make sure rfkill handshake bits are cleared */
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR,
-		    CSR_UCODE_DRV_GP1_BIT_CMD_BLOCKED);
-
-	/* clear (again), then enable host interrupts */
-	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
-	iwl_enable_interrupts(trans);
-
-	/* really make sure rfkill handshake bits are cleared */
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
-
-	/* Load the given image to the HW */
-	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
-		ret = iwl_pcie_load_given_ucode_8000(trans, fw);
-	else
-		ret = iwl_pcie_load_given_ucode(trans, fw);
-
-out:
-	mutex_unlock(&trans_pcie->mutex);
-	return ret;
-}
-
-static void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr)
-{
-	iwl_pcie_reset_ict(trans);
-	iwl_pcie_tx_start(trans, scd_addr);
-}
-
 static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -1127,7 +1051,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 	 * already dead.
 	 */
 	if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) {
-		IWL_DEBUG_INFO(trans, "DEVICE_ENABLED bit was set and is now cleared\n");
+		IWL_DEBUG_INFO(trans,
+			       "DEVICE_ENABLED bit was set and is now cleared\n");
 		iwl_pcie_tx_stop(trans);
 		iwl_pcie_rx_stop(trans);
 
@@ -1161,7 +1086,6 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 	iwl_disable_interrupts(trans);
 	spin_unlock(&trans_pcie->irq_lock);
 
-
 	/* clear all status bits */
 	clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
 	clear_bit(STATUS_INT_ENABLED, &trans->status);
@@ -1194,10 +1118,116 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 	if (hw_rfkill != was_hw_rfkill)
 		iwl_trans_pcie_rf_kill(trans, hw_rfkill);
 
-	/* re-take ownership to prevent other users from stealing the deivce */
+	/* re-take ownership to prevent other users from stealing the device */
 	iwl_pcie_prepare_card_hw(trans);
 }
 
+static int iwl_trans_pcie_start_fw(struct iwl_trans *trans,
+				   const struct fw_img *fw, bool run_in_rfkill)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	bool hw_rfkill;
+	int ret;
+
+	/* This may fail if AMT took ownership of the device */
+	if (iwl_pcie_prepare_card_hw(trans)) {
+		IWL_WARN(trans, "Exit HW not ready\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	iwl_enable_rfkill_int(trans);
+
+	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
+
+	/*
+	 * We enabled the RF-Kill interrupt and the handler may very
+	 * well be running. Disable the interrupts to make sure no other
+	 * interrupt can be fired.
+	 */
+	iwl_disable_interrupts(trans);
+
+	/* Make sure it finished running */
+	synchronize_irq(trans_pcie->pci_dev->irq);
+
+	mutex_lock(&trans_pcie->mutex);
+
+	/* If platform's RF_KILL switch is NOT set to KILL */
+	hw_rfkill = iwl_is_rfkill_set(trans);
+	if (hw_rfkill)
+		set_bit(STATUS_RFKILL, &trans->status);
+	else
+		clear_bit(STATUS_RFKILL, &trans->status);
+	iwl_trans_pcie_rf_kill(trans, hw_rfkill);
+	if (hw_rfkill && !run_in_rfkill) {
+		ret = -ERFKILL;
+		goto out;
+	}
+
+	/* Someone called stop_device, don't try to start_fw */
+	if (trans_pcie->is_down) {
+		IWL_WARN(trans,
+			 "Can't start_fw since the HW hasn't been started\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	/* make sure rfkill handshake bits are cleared */
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR,
+		    CSR_UCODE_DRV_GP1_BIT_CMD_BLOCKED);
+
+	/* clear (again), then enable host interrupts */
+	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
+
+	ret = iwl_pcie_nic_init(trans);
+	if (ret) {
+		IWL_ERR(trans, "Unable to init nic\n");
+		goto out;
+	}
+
+	/*
+	 * Now, we load the firmware and don't want to be interrupted, even
+	 * by the RF-Kill interrupt (hence mask all the interrupt besides the
+	 * FH_TX interrupt which is needed to load the firmware). If the
+	 * RF-Kill switch is toggled, we will find out after having loaded
+	 * the firmware and return the proper value to the caller.
+	 */
+	iwl_enable_fw_load_int(trans);
+
+	/* really make sure rfkill handshake bits are cleared */
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
+
+	/* Load the given image to the HW */
+	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
+		ret = iwl_pcie_load_given_ucode_8000(trans, fw);
+	else
+		ret = iwl_pcie_load_given_ucode(trans, fw);
+	iwl_enable_interrupts(trans);
+
+	/* re-check RF-Kill state since we may have missed the interrupt */
+	hw_rfkill = iwl_is_rfkill_set(trans);
+	if (hw_rfkill)
+		set_bit(STATUS_RFKILL, &trans->status);
+	else
+		clear_bit(STATUS_RFKILL, &trans->status);
+
+	iwl_trans_pcie_rf_kill(trans, hw_rfkill);
+	if (hw_rfkill && !run_in_rfkill)
+		ret = -ERFKILL;
+
+out:
+	mutex_unlock(&trans_pcie->mutex);
+	return ret;
+}
+
+static void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr)
+{
+	iwl_pcie_reset_ict(trans);
+	iwl_pcie_tx_start(trans, scd_addr);
+}
+
 static void iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rc.c b/drivers/net/wireless/realtek/rtlwifi/rc.c
index 74c14ce28238..28f7010e7108 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rc.c
@@ -138,6 +138,11 @@ static void _rtl_rc_rate_set_series(struct rtl_priv *rtlpriv,
 		    ((wireless_mode == WIRELESS_MODE_N_5G) ||
 		     (wireless_mode == WIRELESS_MODE_N_24G)))
 			rate->flags |= IEEE80211_TX_RC_MCS;
+		if (sta && sta->vht_cap.vht_supported &&
+		    (wireless_mode == WIRELESS_MODE_AC_5G ||
+		     wireless_mode == WIRELESS_MODE_AC_24G ||
+		     wireless_mode == WIRELESS_MODE_AC_ONLY))
+			rate->flags |= IEEE80211_TX_RC_VHT_MCS;
 	}
 }
 
diff --git a/drivers/net/wireless/ti/wlcore/io.c b/drivers/net/wireless/ti/wlcore/io.c
index 9ac118e727e9..564ca750c5ee 100644
--- a/drivers/net/wireless/ti/wlcore/io.c
+++ b/drivers/net/wireless/ti/wlcore/io.c
@@ -175,14 +175,14 @@ int wlcore_set_partition(struct wl1271 *wl,
 	if (ret < 0)
 		goto out;
 
+	/* We don't need the size of the last partition, as it is
+	 * automatically calculated based on the total memory size and
+	 * the sizes of the previous partitions.
+	 */
 	ret = wlcore_raw_write32(wl, HW_PART3_START_ADDR, p->mem3.start);
 	if (ret < 0)
 		goto out;
 
-	ret = wlcore_raw_write32(wl, HW_PART3_SIZE_ADDR, p->mem3.size);
-	if (ret < 0)
-		goto out;
-
 out:
 	return ret;
 }
diff --git a/drivers/net/wireless/ti/wlcore/io.h b/drivers/net/wireless/ti/wlcore/io.h
index 6c257b54f415..10cf3747694d 100644
--- a/drivers/net/wireless/ti/wlcore/io.h
+++ b/drivers/net/wireless/ti/wlcore/io.h
@@ -36,8 +36,8 @@
 #define HW_PART1_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 12)
 #define HW_PART2_SIZE_ADDR              (HW_PARTITION_REGISTERS_ADDR + 16)
 #define HW_PART2_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 20)
-#define HW_PART3_SIZE_ADDR              (HW_PARTITION_REGISTERS_ADDR + 24)
-#define HW_PART3_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 28)
+#define HW_PART3_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 24)
+
 #define HW_ACCESS_REGISTER_SIZE         4
 
 #define HW_ACCESS_PRAM_MAX_RANGE	0x3c000
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 7e2c43f701bc..5d28e9405f32 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -382,18 +382,18 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = {
 	[ND_CMD_ARS_CAP] = {
 		.in_num = 2,
 		.in_sizes = { 8, 8, },
-		.out_num = 2,
-		.out_sizes = { 4, 4, },
+		.out_num = 4,
+		.out_sizes = { 4, 4, 4, 4, },
 	},
 	[ND_CMD_ARS_START] = {
-		.in_num = 4,
-		.in_sizes = { 8, 8, 2, 6, },
-		.out_num = 1,
-		.out_sizes = { 4, },
+		.in_num = 5,
+		.in_sizes = { 8, 8, 2, 1, 5, },
+		.out_num = 2,
+		.out_sizes = { 4, 4, },
 	},
 	[ND_CMD_ARS_STATUS] = {
-		.out_num = 2,
-		.out_sizes = { 4, UINT_MAX, },
+		.out_num = 3,
+		.out_sizes = { 4, 4, UINT_MAX, },
 	},
 };
 
@@ -442,8 +442,8 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
 		return in_field[1];
 	else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2)
 		return out_field[1];
-	else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1)
-		return ND_CMD_ARS_STATUS_MAX;
+	else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2)
+		return out_field[1] - 8;
 
 	return UINT_MAX;
 }
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 7edf31671dab..8d0b54670184 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -41,7 +41,7 @@ struct pmem_device {
 	phys_addr_t		phys_addr;
 	/* when non-zero this device is hosting a 'pfn' instance */
 	phys_addr_t		data_offset;
-	unsigned long		pfn_flags;
+	u64			pfn_flags;
 	void __pmem		*virt_addr;
 	size_t			size;
 	struct badblocks	bb;
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 5d6237391dcd..b586d84f2518 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -17,5 +17,6 @@ config BLK_DEV_NVME_SCSI
 	  and block devices nodes, as well a a translation for a small
 	  number of selected SCSI commands to NVMe commands to the NVMe
 	  driver.  If you don't know what this means you probably want
-	  to say N here, and if you know what it means you probably
-	  want to say N as well.
+	  to say N here, unless you run a distro that abuses the SCSI
+	  emulation to provide stable device names for mount by id, like
+	  some OpenSuSE and SLES versions.
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c5bf001af559..3cd921e6121e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1121,7 +1121,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	ns->queue = blk_mq_init_queue(ctrl->tagset);
 	if (IS_ERR(ns->queue))
 		goto out_free_ns;
-	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
 	ns->queue->queuedata = ns;
 	ns->ctrl = ctrl;
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 5cd3725e2fa4..6bb15e4926dc 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -146,9 +146,10 @@ struct nvme_nvm_command {
 	};
 };
 
+#define NVME_NVM_LP_MLC_PAIRS 886
 struct nvme_nvm_lp_mlc {
 	__u16			num_pairs;
-	__u8			pairs[886];
+	__u8			pairs[NVME_NVM_LP_MLC_PAIRS];
 };
 
 struct nvme_nvm_lp_tbl {
@@ -282,9 +283,14 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 			memcpy(dst->lptbl.id, src->lptbl.id, 8);
 			dst->lptbl.mlc.num_pairs =
 					le16_to_cpu(src->lptbl.mlc.num_pairs);
-			/* 4 bits per pair */
+
+			if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
+				pr_err("nvm: number of MLC pairs not supported\n");
+				return -EINVAL;
+			}
+
 			memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
-						dst->lptbl.mlc.num_pairs >> 1);
+						dst->lptbl.mlc.num_pairs);
 		}
 	}
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 4fb5bb737868..9664d07d807d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -139,9 +139,9 @@ static inline bool nvme_io_incapable(struct nvme_ctrl *ctrl)
 	u32 val = 0;
 
 	if (ctrl->ops->io_incapable(ctrl))
-		return false;
+		return true;
 	if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &val))
-		return false;
+		return true;
 	return val & NVME_CSTS_CFS;
 }
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 72ef8322d32a..a128672472ec 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -678,6 +678,11 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_mq_start_request(req);
 
 	spin_lock_irq(&nvmeq->q_lock);
+	if (unlikely(nvmeq->cq_vector < 0)) {
+		ret = BLK_MQ_RQ_QUEUE_BUSY;
+		spin_unlock_irq(&nvmeq->q_lock);
+		goto out;
+	}
 	__nvme_submit_cmd(nvmeq, &cmnd);
 	nvme_process_cq(nvmeq);
 	spin_unlock_irq(&nvmeq->q_lock);
@@ -999,7 +1004,7 @@ static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved
 	if (!blk_mq_request_started(req))
 		return;
 
-	dev_warn(nvmeq->q_dmadev,
+	dev_dbg_ratelimited(nvmeq->q_dmadev,
 		 "Cancelling I/O %d QID %d\n", req->tag, nvmeq->qid);
 
 	status = NVME_SC_ABORT_REQ;
@@ -2111,16 +2116,12 @@ static void nvme_remove(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
 
-	spin_lock(&dev_list_lock);
-	list_del_init(&dev->node);
-	spin_unlock(&dev_list_lock);
-
 	pci_set_drvdata(pdev, NULL);
-	flush_work(&dev->reset_work);
 	flush_work(&dev->scan_work);
 	nvme_remove_namespaces(&dev->ctrl);
 	nvme_uninit_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, true);
+	flush_work(&dev->reset_work);
 	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
 	nvme_release_cmb(dev);
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 6fd4e5a5ef4a..9d11d9837312 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -70,6 +70,9 @@ static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj,
 	if (pos >= nvmem->size)
 		return 0;
 
+	if (count < nvmem->word_size)
+		return -EINVAL;
+
 	if (pos + count > nvmem->size)
 		count = nvmem->size - pos;
 
@@ -95,6 +98,9 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj,
 	if (pos >= nvmem->size)
 		return 0;
 
+	if (count < nvmem->word_size)
+		return -EINVAL;
+
 	if (pos + count > nvmem->size)
 		count = nvmem->size - pos;
 
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index afb67e7eeee4..3829e5fbf8c3 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -21,6 +21,7 @@ static struct regmap_config qfprom_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 8,
 	.reg_stride = 1,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static struct nvmem_config econfig = {
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 7ee21ae305ae..e7bfc175b8e1 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -635,6 +635,13 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
 		msi_base = be32_to_cpup(msi_map + 2);
 		rid_len = be32_to_cpup(msi_map + 3);
 
+		if (rid_base & ~map_mask) {
+			dev_err(parent_dev,
+				"Invalid msi-map translation - msi-map-mask (0x%x) ignores rid-base (0x%x)\n",
+				map_mask, rid_base);
+			return rid_out;
+		}
+
 		msi_controller_node = of_find_node_by_phandle(phandle);
 
 		matched = (masked_rid >= rid_base &&
@@ -654,7 +661,7 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
 	if (!matched)
 		return rid_out;
 
-	rid_out = masked_rid + msi_base;
+	rid_out = masked_rid - rid_base + msi_base;
 	dev_dbg(dev,
 		"msi-map at: %s, using mask %08x, rid-base: %08x, msi-base: %08x, length: %08x, rid: %08x -> %08x\n",
 		dev_name(parent_dev), map_mask, rid_base, msi_base,
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 5648317d355f..39c4be41ef83 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -154,6 +154,7 @@ static const struct of_device_id whitelist_phys[] = {
 	{ .compatible = "marvell,88E1111", },
 	{ .compatible = "marvell,88e1116", },
 	{ .compatible = "marvell,88e1118", },
+	{ .compatible = "marvell,88e1145", },
 	{ .compatible = "marvell,88e1149r", },
 	{ .compatible = "marvell,88e1310", },
 	{ .compatible = "marvell,88E1510", },
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 75a605426538..d1cdd9c992ac 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -14,6 +14,7 @@ config PCI_DRA7XX
 config PCI_MVEBU
 	bool "Marvell EBU PCIe controller"
 	depends on ARCH_MVEBU || ARCH_DOVE
+	depends on ARM
 	depends on OF
 
 config PCIE_DW
diff --git a/drivers/pci/host/pcie-iproc.c b/drivers/pci/host/pcie-iproc.c
index 5816bceddb65..a576aeeb22da 100644
--- a/drivers/pci/host/pcie-iproc.c
+++ b/drivers/pci/host/pcie-iproc.c
@@ -64,7 +64,6 @@
 #define OARR_SIZE_CFG                BIT(OARR_SIZE_CFG_SHIFT)
 
 #define MAX_NUM_OB_WINDOWS           2
-#define MAX_NUM_PAXC_PF              4
 
 #define IPROC_PCIE_REG_INVALID 0xffff
 
@@ -170,20 +169,6 @@ static inline void iproc_pcie_ob_write(struct iproc_pcie *pcie,
 	writel(val, pcie->base + offset + (window * 8));
 }
 
-static inline bool iproc_pcie_device_is_valid(struct iproc_pcie *pcie,
-					      unsigned int slot,
-					      unsigned int fn)
-{
-	if (slot > 0)
-		return false;
-
-	/* PAXC can only support limited number of functions */
-	if (pcie->type == IPROC_PCIE_PAXC && fn >= MAX_NUM_PAXC_PF)
-		return false;
-
-	return true;
-}
-
 /**
  * Note access to the configuration registers are protected at the higher layer
  * by 'pci_lock' in drivers/pci/access.c
@@ -199,11 +184,11 @@ static void __iomem *iproc_pcie_map_cfg_bus(struct pci_bus *bus,
 	u32 val;
 	u16 offset;
 
-	if (!iproc_pcie_device_is_valid(pcie, slot, fn))
-		return NULL;
-
 	/* root complex access */
 	if (busno == 0) {
+		if (slot > 0 || fn > 0)
+			return NULL;
+
 		iproc_pcie_write_reg(pcie, IPROC_PCIE_CFG_IND_ADDR,
 				     where & CFG_IND_ADDR_MASK);
 		offset = iproc_pcie_reg_offset(pcie, IPROC_PCIE_CFG_IND_DATA);
@@ -213,6 +198,14 @@ static void __iomem *iproc_pcie_map_cfg_bus(struct pci_bus *bus,
 			return (pcie->base + offset);
 	}
 
+	/*
+	 * PAXC is connected to an internally emulated EP within the SoC.  It
+	 * allows only one device.
+	 */
+	if (pcie->type == IPROC_PCIE_PAXC)
+		if (slot > 0)
+			return NULL;
+
 	/* EP device access */
 	val = (busno << CFG_ADDR_BUS_NUM_SHIFT) |
 		(slot << CFG_ADDR_DEV_NUM_SHIFT) |
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 0bf82a20a0fb..48d21e0edd56 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -262,7 +262,6 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
 	rpc->rpd = dev;
 	INIT_WORK(&rpc->dpc_handler, aer_isr);
 	mutex_init(&rpc->rpc_mutex);
-	init_waitqueue_head(&rpc->wait_release);
 
 	/* Use PCIe bus function to store rpc into PCIe device */
 	set_service_data(dev, rpc);
@@ -285,8 +284,7 @@ static void aer_remove(struct pcie_device *dev)
 		if (rpc->isr)
 			free_irq(dev->irq, dev);
 
-		wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
-
+		flush_work(&rpc->dpc_handler);
 		aer_disable_rootport(rpc);
 		kfree(rpc);
 		set_service_data(dev, NULL);
diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index 84420b7c9456..945c939a86c5 100644
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -72,7 +72,6 @@ struct aer_rpc {
 					 * recovery on the same
 					 * root port hierarchy
 					 */
-	wait_queue_head_t wait_release;
 };
 
 struct aer_broadcast_data {
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 712392504ed9..521e39c1b66d 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -811,8 +811,6 @@ void aer_isr(struct work_struct *work)
 	while (get_e_source(rpc, &e_src))
 		aer_isr_one_error(p_device, &e_src);
 	mutex_unlock(&rpc->rpc_mutex);
-
-	wake_up(&rpc->wait_release);
 }
 
 /**
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index c777b97207d5..5f70fee59a94 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -53,7 +53,7 @@ struct pcifront_device {
 };
 
 struct pcifront_sd {
-	int domain;
+	struct pci_sysdata sd;
 	struct pcifront_device *pdev;
 };
 
@@ -67,7 +67,9 @@ static inline void pcifront_init_sd(struct pcifront_sd *sd,
 				    unsigned int domain, unsigned int bus,
 				    struct pcifront_device *pdev)
 {
-	sd->domain = domain;
+	/* Because we do not expose that information via XenBus. */
+	sd->sd.node = first_online_node;
+	sd->sd.domain = domain;
 	sd->pdev = pdev;
 }
 
@@ -468,8 +470,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev,
 	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
 		 domain, bus);
 
-	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
-	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kzalloc(sizeof(*sd), GFP_KERNEL);
 	if (!bus_entry || !sd) {
 		err = -ENOMEM;
 		goto err_out;
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index e7e117d5dbbe..0124d17bd9fe 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -224,6 +224,7 @@ config PHY_MT65XX_USB3
 
 config PHY_HI6220_USB
 	tristate "hi6220 USB PHY support"
+	depends on (ARCH_HISI && ARM64) || COMPILE_TEST
 	select GENERIC_PHY
 	select MFD_SYSCON
 	help
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 8c7f27db6ad3..e7e574dc667a 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -275,20 +275,21 @@ EXPORT_SYMBOL_GPL(phy_exit);
 
 int phy_power_on(struct phy *phy)
 {
-	int ret;
+	int ret = 0;
 
 	if (!phy)
-		return 0;
+		goto out;
 
 	if (phy->pwr) {
 		ret = regulator_enable(phy->pwr);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
-		return ret;
+		goto err_pm_sync;
+
 	ret = 0; /* Override possible ret == -ENOTSUPP */
 
 	mutex_lock(&phy->mutex);
@@ -296,19 +297,20 @@ int phy_power_on(struct phy *phy)
 		ret = phy->ops->power_on(phy);
 		if (ret < 0) {
 			dev_err(&phy->dev, "phy poweron failed --> %d\n", ret);
-			goto out;
+			goto err_pwr_on;
 		}
 	}
 	++phy->power_count;
 	mutex_unlock(&phy->mutex);
 	return 0;
 
-out:
+err_pwr_on:
 	mutex_unlock(&phy->mutex);
 	phy_pm_runtime_put_sync(phy);
+err_pm_sync:
 	if (phy->pwr)
 		regulator_disable(phy->pwr);
-
+out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(phy_power_on);
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index 4a3fc6e59f8e..840f3eae428b 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -715,6 +715,7 @@ static int twl4030_usb_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, 2000);
 	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
 
 	/* Our job is to use irqs and status from the power module
 	 * to keep the transceiver disabled when nothing's connected.
@@ -750,6 +751,7 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	struct twl4030_usb *twl = platform_get_drvdata(pdev);
 	int val;
 
+	usb_remove_phy(&twl->phy);
 	pm_runtime_get_sync(twl->dev);
 	cancel_delayed_work(&twl->id_workaround_work);
 	device_remove_file(twl->dev, &dev_attr_vbus);
@@ -757,6 +759,13 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	/* set transceiver mode to power on defaults */
 	twl4030_usb_set_mode(twl, -1);
 
+	/* idle ulpi before powering off */
+	if (cable_present(twl->linkstat))
+		pm_runtime_put_noidle(twl->dev);
+	pm_runtime_mark_last_busy(twl->dev);
+	pm_runtime_put_sync_suspend(twl->dev);
+	pm_runtime_disable(twl->dev);
+
 	/* autogate 60MHz ULPI clock,
 	 * clear dpll clock request for i2c access,
 	 * disable 32KHz
@@ -771,11 +780,6 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	/* disable complete OTG block */
 	twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
 
-	if (cable_present(twl->linkstat))
-		pm_runtime_put_noidle(twl->dev);
-	pm_runtime_mark_last_busy(twl->dev);
-	pm_runtime_put(twl->dev);
-
 	return 0;
 }
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 16d48a4ed225..e96e86d2e745 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -347,6 +347,7 @@ static int mtk_pconf_parse_conf(struct pinctrl_dev *pctldev,
 		ret = mtk_pconf_set_pull_select(pctl, pin, true, false, arg);
 		break;
 	case PIN_CONFIG_INPUT_ENABLE:
+		mtk_pmx_gpio_set_direction(pctldev, NULL, pin, true);
 		ret = mtk_pconf_set_ies_smt(pctl, pin, arg, param);
 		break;
 	case PIN_CONFIG_OUTPUT:
@@ -354,6 +355,7 @@ static int mtk_pconf_parse_conf(struct pinctrl_dev *pctldev,
 		ret = mtk_pmx_gpio_set_direction(pctldev, NULL, pin, false);
 		break;
 	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+		mtk_pmx_gpio_set_direction(pctldev, NULL, pin, true);
 		ret = mtk_pconf_set_ies_smt(pctl, pin, arg, param);
 		break;
 	case PIN_CONFIG_DRIVE_STRENGTH:
diff --git a/drivers/pinctrl/mvebu/pinctrl-mvebu.c b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
index e4d473811bb3..3ef798fac81b 100644
--- a/drivers/pinctrl/mvebu/pinctrl-mvebu.c
+++ b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
@@ -666,16 +666,19 @@ int mvebu_pinctrl_probe(struct platform_device *pdev)
 		struct mvebu_mpp_ctrl_setting *set = &mode->settings[0];
 		struct mvebu_pinctrl_group *grp;
 		unsigned num_settings;
+		unsigned supp_settings;
 
-		for (num_settings = 0; ; set++) {
+		for (num_settings = 0, supp_settings = 0; ; set++) {
 			if (!set->name)
 				break;
 
+			num_settings++;
+
 			/* skip unsupported settings for this variant */
 			if (pctl->variant && !(pctl->variant & set->variant))
 				continue;
 
-			num_settings++;
+			supp_settings++;
 
 			/* find gpio/gpo/gpi settings */
 			if (strcmp(set->name, "gpio") == 0)
@@ -688,7 +691,7 @@ int mvebu_pinctrl_probe(struct platform_device *pdev)
 		}
 
 		/* skip modes with no settings for this variant */
-		if (!num_settings)
+		if (!supp_settings)
 			continue;
 
 		grp = mvebu_pinctrl_find_group_by_pid(pctl, mode->pid);
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 085e60106ec2..1f7469c9857d 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -191,6 +191,7 @@ static void abx500_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
 		dev_err(pct->dev, "%s write failed (%d)\n", __func__, ret);
 }
 
+#ifdef CONFIG_DEBUG_FS
 static int abx500_get_pull_updown(struct abx500_pinctrl *pct, int offset,
 				  enum abx500_gpio_pull_updown *pull_updown)
 {
@@ -226,6 +227,7 @@ out:
 
 	return ret;
 }
+#endif
 
 static int abx500_set_pull_updown(struct abx500_pinctrl *pct,
 				  int offset, enum abx500_gpio_pull_updown val)
@@ -468,6 +470,7 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_FS
 static int abx500_get_mode(struct pinctrl_dev *pctldev, struct gpio_chip *chip,
 			  unsigned gpio)
 {
@@ -553,8 +556,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_DEBUG_FS
-
 #include <linux/seq_file.h>
 
 static void abx500_gpio_dbg_show_one(struct seq_file *s,
diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
index d90e205cf809..216f227c6009 100644
--- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
+++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
@@ -426,6 +426,7 @@ int pxa2xx_pinctrl_init(struct platform_device *pdev,
 
 	return 0;
 }
+EXPORT_SYMBOL(pxa2xx_pinctrl_init);
 
 int pxa2xx_pinctrl_exit(struct platform_device *pdev)
 {
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index f67b1e958589..5cc97f85db02 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -514,25 +514,35 @@ static const struct pinconf_ops samsung_pinconf_ops = {
 	.pin_config_group_set	= samsung_pinconf_group_set,
 };
 
-/* gpiolib gpio_set callback function */
-static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
+/*
+ * The samsung_gpio_set_vlaue() should be called with "bank->slock" held
+ * to avoid race condition.
+ */
+static void samsung_gpio_set_value(struct gpio_chip *gc,
+					  unsigned offset, int value)
 {
 	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
 	const struct samsung_pin_bank_type *type = bank->type;
-	unsigned long flags;
 	void __iomem *reg;
 	u32 data;
 
 	reg = bank->drvdata->virt_base + bank->pctl_offset;
 
-	spin_lock_irqsave(&bank->slock, flags);
-
 	data = readl(reg + type->reg_offset[PINCFG_TYPE_DAT]);
 	data &= ~(1 << offset);
 	if (value)
 		data |= 1 << offset;
 	writel(data, reg + type->reg_offset[PINCFG_TYPE_DAT]);
+}
+
+/* gpiolib gpio_set callback function */
+static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
+{
+	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->slock, flags);
+	samsung_gpio_set_value(gc, offset, value);
 	spin_unlock_irqrestore(&bank->slock, flags);
 }
 
@@ -553,6 +563,8 @@ static int samsung_gpio_get(struct gpio_chip *gc, unsigned offset)
 }
 
 /*
+ * The samsung_gpio_set_direction() should be called with "bank->slock" held
+ * to avoid race condition.
  * The calls to gpio_direction_output() and gpio_direction_input()
  * leads to this function call.
  */
@@ -564,7 +576,6 @@ static int samsung_gpio_set_direction(struct gpio_chip *gc,
 	struct samsung_pinctrl_drv_data *drvdata;
 	void __iomem *reg;
 	u32 data, mask, shift;
-	unsigned long flags;
 
 	bank = gpiochip_get_data(gc);
 	type = bank->type;
@@ -581,31 +592,42 @@ static int samsung_gpio_set_direction(struct gpio_chip *gc,
 		reg += 4;
 	}
 
-	spin_lock_irqsave(&bank->slock, flags);
-
 	data = readl(reg);
 	data &= ~(mask << shift);
 	if (!input)
 		data |= FUNC_OUTPUT << shift;
 	writel(data, reg);
 
-	spin_unlock_irqrestore(&bank->slock, flags);
-
 	return 0;
 }
 
 /* gpiolib gpio_direction_input callback function. */
 static int samsung_gpio_direction_input(struct gpio_chip *gc, unsigned offset)
 {
-	return samsung_gpio_set_direction(gc, offset, true);
+	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&bank->slock, flags);
+	ret = samsung_gpio_set_direction(gc, offset, true);
+	spin_unlock_irqrestore(&bank->slock, flags);
+	return ret;
 }
 
 /* gpiolib gpio_direction_output callback function. */
 static int samsung_gpio_direction_output(struct gpio_chip *gc, unsigned offset,
 							int value)
 {
-	samsung_gpio_set(gc, offset, value);
-	return samsung_gpio_set_direction(gc, offset, false);
+	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&bank->slock, flags);
+	samsung_gpio_set_value(gc, offset, value);
+	ret = samsung_gpio_set_direction(gc, offset, false);
+	spin_unlock_irqrestore(&bank->slock, flags);
+
+	return ret;
 }
 
 /*
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
index 77d4cf047cee..11760bbe9d51 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
@@ -492,6 +492,7 @@ static const struct sunxi_pinctrl_desc sun8i_h3_pinctrl_data = {
 	.pins = sun8i_h3_pins,
 	.npins = ARRAY_SIZE(sun8i_h3_pins),
 	.irq_banks = 2,
+	.irq_read_needs_mux = true
 };
 
 static int sun8i_h3_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index 20f0ad9bb9f3..e20f23e04c24 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -41,8 +41,7 @@ static const struct key_entry intel_hid_keymap[] = {
 	{ KE_KEY, 4, { KEY_HOME } },
 	{ KE_KEY, 5, { KEY_END } },
 	{ KE_KEY, 6, { KEY_PAGEUP } },
-	{ KE_KEY, 4, { KEY_PAGEDOWN } },
-	{ KE_KEY, 4, { KEY_HOME } },
+	{ KE_KEY, 7, { KEY_PAGEDOWN } },
 	{ KE_KEY, 8, { KEY_RFKILL } },
 	{ KE_KEY, 9, { KEY_POWER } },
 	{ KE_KEY, 11, { KEY_SLEEP } },
diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c
index 02bc5a6343c3..aa454241489c 100644
--- a/drivers/platform/x86/intel_scu_ipcutil.c
+++ b/drivers/platform/x86/intel_scu_ipcutil.c
@@ -49,7 +49,7 @@ struct scu_ipc_data {
 
 static int scu_reg_access(u32 cmd, struct scu_ipc_data  *data)
 {
-	int count = data->count;
+	unsigned int count = data->count;
 
 	if (count == 0 || count == 3 || count > 4)
 		return -EINVAL;
diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c
index 9429e66be096..8eafc6f0df88 100644
--- a/drivers/power/bq27xxx_battery_i2c.c
+++ b/drivers/power/bq27xxx_battery_i2c.c
@@ -21,6 +21,9 @@
 
 #include <linux/power/bq27xxx_battery.h>
 
+static DEFINE_IDR(battery_id);
+static DEFINE_MUTEX(battery_mutex);
+
 static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data)
 {
 	struct bq27xxx_device_info *di = data;
@@ -70,19 +73,33 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client,
 {
 	struct bq27xxx_device_info *di;
 	int ret;
+	char *name;
+	int num;
+
+	/* Get new ID for the new battery device */
+	mutex_lock(&battery_mutex);
+	num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL);
+	mutex_unlock(&battery_mutex);
+	if (num < 0)
+		return num;
+
+	name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s-%d", id->name, num);
+	if (!name)
+		goto err_mem;
 
 	di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL);
 	if (!di)
-		return -ENOMEM;
+		goto err_mem;
 
+	di->id = num;
 	di->dev = &client->dev;
 	di->chip = id->driver_data;
-	di->name = id->name;
+	di->name = name;
 	di->bus.read = bq27xxx_battery_i2c_read;
 
 	ret = bq27xxx_battery_setup(di);
 	if (ret)
-		return ret;
+		goto err_failed;
 
 	/* Schedule a polling after about 1 min */
 	schedule_delayed_work(&di->work, 60 * HZ);
@@ -103,6 +120,16 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client,
 	}
 
 	return 0;
+
+err_mem:
+	ret = -ENOMEM;
+
+err_failed:
+	mutex_lock(&battery_mutex);
+	idr_remove(&battery_id, num);
+	mutex_unlock(&battery_mutex);
+
+	return ret;
 }
 
 static int bq27xxx_battery_i2c_remove(struct i2c_client *client)
@@ -111,6 +138,10 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client)
 
 	bq27xxx_battery_teardown(di);
 
+	mutex_lock(&battery_mutex);
+	idr_remove(&battery_id, di->id);
+	mutex_unlock(&battery_mutex);
+
 	return 0;
 }
 
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 41605dac8309..c78db05e75b1 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3035,6 +3035,7 @@ static void dasd_setup_queue(struct dasd_block *block)
 		max = block->base->discipline->max_blocks << block->s2b_shift;
 	}
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, block->request_queue);
+	block->request_queue->limits.max_dev_sectors = max;
 	blk_queue_logical_block_size(block->request_queue,
 				     block->bp_block);
 	blk_queue_max_hw_sectors(block->request_queue, max);
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index 184b1dbeb554..286782c60da4 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -264,8 +264,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		spin_unlock_irqrestore(&lcu->lock, flags);
 		cancel_work_sync(&lcu->suc_data.worker);
 		spin_lock_irqsave(&lcu->lock, flags);
-		if (device == lcu->suc_data.device)
+		if (device == lcu->suc_data.device) {
+			dasd_put_device(device);
 			lcu->suc_data.device = NULL;
+		}
 	}
 	was_pending = 0;
 	if (device == lcu->ruac_data.device) {
@@ -273,8 +275,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		was_pending = 1;
 		cancel_delayed_work_sync(&lcu->ruac_data.dwork);
 		spin_lock_irqsave(&lcu->lock, flags);
-		if (device == lcu->ruac_data.device)
+		if (device == lcu->ruac_data.device) {
+			dasd_put_device(device);
 			lcu->ruac_data.device = NULL;
+		}
 	}
 	private->lcu = NULL;
 	spin_unlock_irqrestore(&lcu->lock, flags);
@@ -549,8 +553,10 @@ static void lcu_update_work(struct work_struct *work)
 	if ((rc && (rc != -EOPNOTSUPP)) || (lcu->flags & NEED_UAC_UPDATE)) {
 		DBF_DEV_EVENT(DBF_WARNING, device, "could not update"
 			    " alias data in lcu (rc = %d), retry later", rc);
-		schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ);
+		if (!schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ))
+			dasd_put_device(device);
 	} else {
+		dasd_put_device(device);
 		lcu->ruac_data.device = NULL;
 		lcu->flags &= ~UPDATE_PENDING;
 	}
@@ -593,8 +599,10 @@ static int _schedule_lcu_update(struct alias_lcu *lcu,
 	 */
 	if (!usedev)
 		return -EINVAL;
+	dasd_get_device(usedev);
 	lcu->ruac_data.device = usedev;
-	schedule_delayed_work(&lcu->ruac_data.dwork, 0);
+	if (!schedule_delayed_work(&lcu->ruac_data.dwork, 0))
+		dasd_put_device(usedev);
 	return 0;
 }
 
@@ -723,7 +731,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
 	ASCEBC((char *) &cqr->magic, 4);
 	ccw = cqr->cpaddr;
 	ccw->cmd_code = DASD_ECKD_CCW_RSCK;
-	ccw->flags = 0 ;
+	ccw->flags = CCW_FLAG_SLI;
 	ccw->count = 16;
 	ccw->cda = (__u32)(addr_t) cqr->data;
 	((char *)cqr->data)[0] = reason;
@@ -930,6 +938,7 @@ static void summary_unit_check_handling_work(struct work_struct *work)
 	/* 3. read new alias configuration */
 	_schedule_lcu_update(lcu, device);
 	lcu->suc_data.device = NULL;
+	dasd_put_device(device);
 	spin_unlock_irqrestore(&lcu->lock, flags);
 }
 
@@ -989,6 +998,8 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device,
 	}
 	lcu->suc_data.reason = reason;
 	lcu->suc_data.device = device;
+	dasd_get_device(device);
 	spin_unlock(&lcu->lock);
-	schedule_work(&lcu->suc_data.worker);
+	if (!schedule_work(&lcu->suc_data.worker))
+		dasd_put_device(device);
 };
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 361358134315..93880ed6291c 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -562,7 +562,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev,
 			/*
 			 * Command Lock contention
 			 */
-			err = SCSI_DH_RETRY;
+			err = SCSI_DH_IMM_RETRY;
 		break;
 	default:
 		break;
@@ -612,6 +612,8 @@ retry:
 		err = mode_select_handle_sense(sdev, h->sense);
 		if (err == SCSI_DH_RETRY && retry_cnt--)
 			goto retry;
+		if (err == SCSI_DH_IMM_RETRY)
+			goto retry;
 	}
 	if (err == SCSI_DH_OK) {
 		h->state = RDAC_STATE_ACTIVE;
diff --git a/drivers/scsi/hisi_sas/Kconfig b/drivers/scsi/hisi_sas/Kconfig
index b67661836c9f..d1dd1616f983 100644
--- a/drivers/scsi/hisi_sas/Kconfig
+++ b/drivers/scsi/hisi_sas/Kconfig
@@ -1,6 +1,6 @@
 config SCSI_HISI_SAS
 	tristate "HiSilicon SAS"
-	depends on HAS_DMA
+	depends on HAS_DMA && HAS_IOMEM
 	depends on ARM64 || COMPILE_TEST
 	select SCSI_SAS_LIBSAS
 	select BLK_DEV_INTEGRITY
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 057fdeb720ac..eea24d7531cf 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1289,13 +1289,10 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 		goto out;
 	}
 
-	if (cmplt_hdr_data & CMPLT_HDR_ERR_RCRD_XFRD_MSK) {
-		if (!(cmplt_hdr_data & CMPLT_HDR_CMD_CMPLT_MSK) ||
-		    !(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK))
-			ts->stat = SAS_DATA_OVERRUN;
-		else
-			slot_err_v1_hw(hisi_hba, task, slot);
+	if (cmplt_hdr_data & CMPLT_HDR_ERR_RCRD_XFRD_MSK &&
+		!(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK)) {
 
+		slot_err_v1_hw(hisi_hba, task, slot);
 		goto out;
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 52a87657c7dd..692a7570b5e1 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -2204,7 +2204,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 	/* Clear outstanding commands array. */
 	for (que = 0; que < ha->max_req_queues; que++) {
 		req = ha->req_q_map[que];
-		if (!req)
+		if (!req || !test_bit(que, ha->req_qid_map))
 			continue;
 		req->out_ptr = (void *)(req->ring + req->length);
 		*req->out_ptr = 0;
@@ -2221,7 +2221,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 
 	for (que = 0; que < ha->max_rsp_queues; que++) {
 		rsp = ha->rsp_q_map[que];
-		if (!rsp)
+		if (!rsp || !test_bit(que, ha->rsp_qid_map))
 			continue;
 		rsp->in_ptr = (void *)(rsp->ring + rsp->length);
 		*rsp->in_ptr = 0;
@@ -4981,7 +4981,7 @@ qla25xx_init_queues(struct qla_hw_data *ha)
 
 	for (i = 1; i < ha->max_rsp_queues; i++) {
 		rsp = ha->rsp_q_map[i];
-		if (rsp) {
+		if (rsp && test_bit(i, ha->rsp_qid_map)) {
 			rsp->options &= ~BIT_0;
 			ret = qla25xx_init_rsp_que(base_vha, rsp);
 			if (ret != QLA_SUCCESS)
@@ -4996,8 +4996,8 @@ qla25xx_init_queues(struct qla_hw_data *ha)
 	}
 	for (i = 1; i < ha->max_req_queues; i++) {
 		req = ha->req_q_map[i];
-		if (req) {
-		/* Clear outstanding commands array. */
+		if (req && test_bit(i, ha->req_qid_map)) {
+			/* Clear outstanding commands array. */
 			req->options &= ~BIT_0;
 			ret = qla25xx_init_req_que(base_vha, req);
 			if (ret != QLA_SUCCESS)
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index d4d65eb0e9b4..4af95479a9db 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3063,9 +3063,9 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		    "MSI-X: Failed to enable support "
 		    "-- %d/%d\n Retry with %d vectors.\n",
 		    ha->msix_count, ret, ret);
+		ha->msix_count = ret;
+		ha->max_rsp_queues = ha->msix_count - 1;
 	}
-	ha->msix_count = ret;
-	ha->max_rsp_queues = ha->msix_count - 1;
 	ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) *
 				ha->msix_count, GFP_KERNEL);
 	if (!ha->msix_entries) {
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index c5dd594f6c31..cf7ba52bae66 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -600,7 +600,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	/* Delete request queues */
 	for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
 		req = ha->req_q_map[cnt];
-		if (req) {
+		if (req && test_bit(cnt, ha->req_qid_map)) {
 			ret = qla25xx_delete_req_que(vha, req);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00ea,
@@ -614,7 +614,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	/* Delete response queues */
 	for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
 		rsp = ha->rsp_q_map[cnt];
-		if (rsp) {
+		if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
 			ret = qla25xx_delete_rsp_que(vha, rsp);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00eb,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index f1788db43195..f6c7ce35b542 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -409,6 +409,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	int cnt;
 
 	for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
+		if (!test_bit(cnt, ha->req_qid_map))
+			continue;
+
 		req = ha->req_q_map[cnt];
 		qla2x00_free_req_que(ha, req);
 	}
@@ -416,6 +419,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	ha->req_q_map = NULL;
 
 	for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) {
+		if (!test_bit(cnt, ha->rsp_qid_map))
+			continue;
+
 		rsp = ha->rsp_q_map[cnt];
 		qla2x00_free_rsp_que(ha, rsp);
 	}
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 8075a4cdb45c..ee967becd257 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -105,7 +105,7 @@ static void qlt_response_pkt(struct scsi_qla_host *ha, response_t *pkt);
 static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	int fn, void *iocb, int flags);
 static void qlt_send_term_exchange(struct scsi_qla_host *ha, struct qla_tgt_cmd
-	*cmd, struct atio_from_isp *atio, int ha_locked);
+	*cmd, struct atio_from_isp *atio, int ha_locked, int ul_abort);
 static void qlt_reject_free_srr_imm(struct scsi_qla_host *ha,
 	struct qla_tgt_srr_imm *imm, int ha_lock);
 static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha,
@@ -1756,7 +1756,7 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 		qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy,
 		    0, 0, 0, 0, 0, 0);
 	else {
-		if (mcmd->se_cmd.se_tmr_req->function == TMR_ABORT_TASK)
+		if (mcmd->orig_iocb.atio.u.raw.entry_type == ABTS_RECV_24XX)
 			qlt_24xx_send_abts_resp(vha, &mcmd->orig_iocb.abts,
 			    mcmd->fc_tm_rsp, false);
 		else
@@ -2665,7 +2665,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 			/* no need to terminate. FW already freed exchange. */
 			qlt_abort_cmd_on_host_reset(cmd->vha, cmd);
 		else
-			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		return 0;
 	}
@@ -3173,7 +3173,8 @@ static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 }
 
 static void qlt_send_term_exchange(struct scsi_qla_host *vha,
-	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked)
+	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked,
+	int ul_abort)
 {
 	unsigned long flags = 0;
 	int rc;
@@ -3193,8 +3194,7 @@ static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 		qlt_alloc_qfull_cmd(vha, atio, 0, 0);
 
 done:
-	if (cmd && (!cmd->aborted ||
-	    !cmd->cmd_sent_to_fw)) {
+	if (cmd && !ul_abort && !cmd->aborted) {
 		if (cmd->sg_mapped)
 			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
@@ -3253,21 +3253,38 @@ static void qlt_chk_exch_leak_thresh_hold(struct scsi_qla_host *vha)
 
 }
 
-void qlt_abort_cmd(struct qla_tgt_cmd *cmd)
+int qlt_abort_cmd(struct qla_tgt_cmd *cmd)
 {
 	struct qla_tgt *tgt = cmd->tgt;
 	struct scsi_qla_host *vha = tgt->vha;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
+	unsigned long flags;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
 	    "qla_target(%d): terminating exchange for aborted cmd=%p "
 	    "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd,
 	    se_cmd->tag);
 
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if (cmd->aborted) {
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/*
+		 * It's normal to see 2 calls in this path:
+		 *  1) XFER Rdy completion + CMD_T_ABORT
+		 *  2) TCM TMR - drain_state_list
+		 */
+	        ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			"multiple abort. %p transport_state %x, t_state %x,"
+			" se_cmd_flags %x \n", cmd, cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,cmd->se_cmd.se_cmd_flags);
+		return EIO;
+	}
 	cmd->aborted = 1;
 	cmd->cmd_flags |= BIT_6;
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
 
-	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
+	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0, 1);
+	return 0;
 }
 EXPORT_SYMBOL(qlt_abort_cmd);
 
@@ -3282,6 +3299,9 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 
 	BUG_ON(cmd->cmd_in_wq);
 
+	if (cmd->sg_mapped)
+		qlt_unmap_sg(cmd->vha, cmd);
+
 	if (!cmd->q_full)
 		qlt_decr_num_pend_cmds(cmd->vha);
 
@@ -3399,7 +3419,7 @@ static int qlt_term_ctio_exchange(struct scsi_qla_host *vha, void *ctio,
 		term = 1;
 
 	if (term)
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 
 	return term;
 }
@@ -3580,12 +3600,13 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 		case CTIO_PORT_LOGGED_OUT:
 		case CTIO_PORT_UNAVAILABLE:
 		{
-			int logged_out = (status & 0xFFFF);
+			int logged_out =
+				(status & 0xFFFF) == CTIO_PORT_LOGGED_OUT;
+
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf059,
 			    "qla_target(%d): CTIO with %s status %x "
 			    "received (state %x, se_cmd %p)\n", vha->vp_idx,
-			    (logged_out == CTIO_PORT_LOGGED_OUT) ?
-			    "PORT LOGGED OUT" : "PORT UNAVAILABLE",
+			    logged_out ? "PORT LOGGED OUT" : "PORT UNAVAILABLE",
 			    status, cmd->state, se_cmd);
 
 			if (logged_out && cmd->sess) {
@@ -3754,6 +3775,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 		goto out_term;
 	}
 
+	spin_lock_init(&cmd->cmd_lock);
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -3796,7 +3818,7 @@ out_term:
 	 */
 	cmd->cmd_flags |= BIT_2;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1, 0);
 
 	qlt_decr_num_pend_cmds(vha);
 	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
@@ -3918,7 +3940,7 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 
 out_term:
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &op->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &op->atio, 1, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	kfree(op);
 
@@ -3982,7 +4004,8 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	cmd->cmd_in_wq = 1;
 	cmd->cmd_flags |= BIT_0;
-	cmd->se_cmd.cpuid = -1;
+	cmd->se_cmd.cpuid = ha->msix_count ?
+		ha->tgt.rspq_vector_cpuid : WORK_CPU_UNBOUND;
 
 	spin_lock(&vha->cmd_list_lock);
 	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
@@ -3990,7 +4013,6 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	INIT_WORK(&cmd->work, qlt_do_work);
 	if (ha->msix_count) {
-		cmd->se_cmd.cpuid = ha->tgt.rspq_vector_cpuid;
 		if (cmd->atio.u.isp24.fcp_cmnd.rddata)
 			queue_work_on(smp_processor_id(), qla_tgt_wq,
 			    &cmd->work);
@@ -4771,7 +4793,7 @@ out_reject:
 		dump_stack();
 	} else {
 		cmd->cmd_flags |= BIT_9;
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
@@ -4950,7 +4972,7 @@ static void qlt_prepare_srr_imm(struct scsi_qla_host *vha,
 				    sctio, sctio->srr_id);
 				list_del(&sctio->srr_list_entry);
 				qlt_send_term_exchange(vha, sctio->cmd,
-				    &sctio->cmd->atio, 1);
+				    &sctio->cmd->atio, 1, 0);
 				kfree(sctio);
 			}
 		}
@@ -5123,7 +5145,7 @@ static int __qlt_send_busy(struct scsi_qla_host *vha,
 	    atio->u.isp24.fcp_hdr.s_id);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	if (!sess) {
-		qlt_send_term_exchange(vha, NULL, atio, 1);
+		qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 		return 0;
 	}
 	/* Sending marker isn't necessary, since we called from ISR */
@@ -5406,7 +5428,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, SAM_STAT_BUSY);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 
 				if (!ha_locked)
@@ -5523,7 +5545,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, 0);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 			} else {
 				if (tgt->tgt_stop) {
@@ -5532,7 +5554,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 					    "command to target, sending TERM "
 					    "EXCHANGE for rsp\n");
 					qlt_send_term_exchange(vha, NULL,
-					    atio, 1);
+					    atio, 1, 0);
 				} else {
 					ql_dbg(ql_dbg_tgt, vha, 0xe060,
 					    "qla_target(%d): Unable to send "
@@ -5960,7 +5982,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	return;
 
 out_term:
-	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 0);
+	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
 	if (sess)
 		ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 71b2865ba3c8..22a6a767fe07 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -943,6 +943,36 @@ struct qla_tgt_sess {
 	qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
 };
 
+typedef enum {
+	/*
+	 * BIT_0 - Atio Arrival / schedule to work
+	 * BIT_1 - qlt_do_work
+	 * BIT_2 - qlt_do work failed
+	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
+	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
+	 * BIT_5 - status respond / tcm_qla2xx_queue_status
+	 * BIT_6 - tcm request to abort/Term exchange.
+	 *	pre_xmit_response->qlt_send_term_exchange
+	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
+	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
+	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
+	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
+
+	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
+	 * BIT_13 - Bad completion -
+	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
+	 * BIT_14 - Back end data received/sent.
+	 * BIT_15 - SRR prepare ctio
+	 * BIT_16 - complete free
+	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
+	 * BIT_18 - completion w/abort status
+	 * BIT_19 - completion w/unknown status
+	 * BIT_20 - tcm_qla2xxx_free_cmd
+	 */
+	CMD_FLAG_DATA_WORK = BIT_11,
+	CMD_FLAG_DATA_WORK_FREE = BIT_21,
+} cmd_flags_t;
+
 struct qla_tgt_cmd {
 	struct se_cmd se_cmd;
 	struct qla_tgt_sess *sess;
@@ -952,6 +982,7 @@ struct qla_tgt_cmd {
 	/* Sense buffer that will be mapped into outgoing status */
 	unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER];
 
+	spinlock_t cmd_lock;
 	/* to save extra sess dereferences */
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;
@@ -986,30 +1017,8 @@ struct qla_tgt_cmd {
 
 	uint64_t jiffies_at_alloc;
 	uint64_t jiffies_at_free;
-	/* BIT_0 - Atio Arrival / schedule to work
-	 * BIT_1 - qlt_do_work
-	 * BIT_2 - qlt_do work failed
-	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
-	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
-	 * BIT_5 - status respond / tcm_qla2xx_queue_status
-	 * BIT_6 - tcm request to abort/Term exchange.
-	 *	pre_xmit_response->qlt_send_term_exchange
-	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
-	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
-	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
-	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
-	 * BIT_11 - Data actually going to TCM : tcm_qla2xx_handle_data_work
-	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
-	 * BIT_13 - Bad completion -
-	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
-	 * BIT_14 - Back end data received/sent.
-	 * BIT_15 - SRR prepare ctio
-	 * BIT_16 - complete free
-	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
-	 * BIT_18 - completion w/abort status
-	 * BIT_19 - completion w/unknown status
-	 */
-	uint32_t cmd_flags;
+
+	cmd_flags_t cmd_flags;
 };
 
 struct qla_tgt_sess_work_param {
@@ -1148,7 +1157,7 @@ static inline void sid_to_portid(const uint8_t *s_id, port_id_t *p)
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
-extern void qlt_abort_cmd(struct qla_tgt_cmd *);
+extern int qlt_abort_cmd(struct qla_tgt_cmd *);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index ddbe2e7ac14d..c3e622524604 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -395,6 +395,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha,
 	if (ent->t263.queue_type == T263_QUEUE_TYPE_REQ) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				length = req ?
 				    req->length : REQUEST_ENTRY_CNT_24XX;
@@ -408,6 +412,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha,
 	} else if (ent->t263.queue_type == T263_QUEUE_TYPE_RSP) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				length = rsp ?
 				    rsp->length : RESPONSE_ENTRY_CNT_MQ;
@@ -634,6 +642,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha,
 	if (ent->t274.queue_type == T274_QUEUE_TYPE_REQ_SHAD) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
@@ -645,6 +657,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha,
 	} else if (ent->t274.queue_type == T274_QUEUE_TYPE_RSP_SHAD) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index faf0a126627f..1808a01cfb7e 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -298,6 +298,10 @@ static void tcm_qla2xxx_free_cmd(struct qla_tgt_cmd *cmd)
 {
 	cmd->vha->tgt_counters.core_qla_free_cmd++;
 	cmd->cmd_in_wq = 1;
+
+	BUG_ON(cmd->cmd_flags & BIT_20);
+	cmd->cmd_flags |= BIT_20;
+
 	INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free);
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
 }
@@ -374,6 +378,20 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
+
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("write_pending aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
 	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -405,7 +423,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd)
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-					    3 * HZ);
+						50);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -444,6 +462,9 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 	if (bidi)
 		flags |= TARGET_SCF_BIDI_OP;
 
+	if (se_cmd->cpuid != WORK_CPU_UNBOUND)
+		flags |= TARGET_SCF_USE_CPUID;
+
 	sess = cmd->sess;
 	if (!sess) {
 		pr_err("Unable to locate struct qla_tgt_sess from qla_tgt_cmd\n");
@@ -465,13 +486,25 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+	unsigned long flags;
 
 	/*
 	 * Ensure that the complete FCP WRITE payload has been received.
 	 * Otherwise return an exception via CHECK_CONDITION status.
 	 */
 	cmd->cmd_in_wq = 0;
-	cmd->cmd_flags |= BIT_11;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	cmd->cmd_flags |= CMD_FLAG_DATA_WORK;
+	if (cmd->aborted) {
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
 	cmd->vha->tgt_counters.qla_core_ret_ctio++;
 	if (!cmd->write_data_transferred) {
 		/*
@@ -546,6 +579,20 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
 
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("queue_data_in aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
+
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -637,11 +684,34 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd)
 	qlt_xmit_tm_rsp(mcmd);
 }
 
+
+#define DATA_WORK_NOT_FREE(_flags) \
+	(( _flags & (CMD_FLAG_DATA_WORK|CMD_FLAG_DATA_WORK_FREE)) == \
+	 CMD_FLAG_DATA_WORK)
 static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	qlt_abort_cmd(cmd);
+	unsigned long flags;
+
+	if (qlt_abort_cmd(cmd))
+		return;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if ((cmd->state == QLA_TGT_STATE_NEW)||
+		((cmd->state == QLA_TGT_STATE_DATA_IN) &&
+		 DATA_WORK_NOT_FREE(cmd->cmd_flags)) ) {
+
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/* Cmd have not reached firmware.
+		 * Use this trigger to free it. */
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+	return;
+
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 47b9d13f97b8..bbfbfd9e5aa3 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -205,6 +205,8 @@ static struct {
 	{"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC},
 	{"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN},
+	{"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES},
+	{"Marvell", "91xx Config", "1.01", BLIST_SKIP_VPD_PAGES},
 	{"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 4f18a851e2c7..00bc7218a7f8 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1272,16 +1272,18 @@ static void __scsi_remove_target(struct scsi_target *starget)
 void scsi_remove_target(struct device *dev)
 {
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
-	struct scsi_target *starget;
+	struct scsi_target *starget, *last_target = NULL;
 	unsigned long flags;
 
 restart:
 	spin_lock_irqsave(shost->host_lock, flags);
 	list_for_each_entry(starget, &shost->__targets, siblings) {
-		if (starget->state == STARGET_DEL)
+		if (starget->state == STARGET_DEL ||
+		    starget == last_target)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
 			kref_get(&starget->reap_ref);
+			last_target = starget;
 			spin_unlock_irqrestore(shost->host_lock, flags);
 			__scsi_remove_target(starget);
 			scsi_target_reap(starget);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bb669d32ccd0..d749da765df1 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -761,7 +761,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
 		break;
 
 	default:
-		ret = BLKPREP_KILL;
+		ret = BLKPREP_INVALID;
 		goto out;
 	}
 
@@ -839,7 +839,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	int ret;
 
 	if (sdkp->device->no_write_same)
-		return BLKPREP_KILL;
+		return BLKPREP_INVALID;
 
 	BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 55627d097873..292c04eec9ad 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -42,6 +42,7 @@
 #include <scsi/scsi_devinfo.h>
 #include <scsi/scsi_dbg.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/scsi_transport.h>
 
 /*
  * All wire protocol details (storage protocol between the guest and the host)
@@ -477,19 +478,18 @@ struct hv_host_device {
 struct storvsc_scan_work {
 	struct work_struct work;
 	struct Scsi_Host *host;
-	uint lun;
+	u8 lun;
+	u8 tgt_id;
 };
 
 static void storvsc_device_scan(struct work_struct *work)
 {
 	struct storvsc_scan_work *wrk;
-	uint lun;
 	struct scsi_device *sdev;
 
 	wrk = container_of(work, struct storvsc_scan_work, work);
-	lun = wrk->lun;
 
-	sdev = scsi_device_lookup(wrk->host, 0, 0, lun);
+	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 	if (!sdev)
 		goto done;
 	scsi_rescan_device(&sdev->sdev_gendev);
@@ -540,7 +540,7 @@ static void storvsc_remove_lun(struct work_struct *work)
 	if (!scsi_host_get(wrk->host))
 		goto done;
 
-	sdev = scsi_device_lookup(wrk->host, 0, 0, wrk->lun);
+	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 
 	if (sdev) {
 		scsi_remove_device(sdev);
@@ -940,6 +940,7 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 
 	wrk->host = host;
 	wrk->lun = vm_srb->lun;
+	wrk->tgt_id = vm_srb->target_id;
 	INIT_WORK(&wrk->work, process_err_fn);
 	schedule_work(&wrk->work);
 }
@@ -1770,6 +1771,11 @@ static int __init storvsc_drv_init(void)
 	fc_transport_template = fc_attach_transport(&fc_transport_functions);
 	if (!fc_transport_template)
 		return -ENODEV;
+
+	/*
+	 * Install Hyper-V specific timeout handler.
+	 */
+	fc_transport_template->eh_timed_out = storvsc_eh_timed_out;
 #endif
 
 	ret = vmbus_driver_register(&storvsc_drv);
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index 91a003011acf..a9bac3bf20de 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = {
 
 static int __init sh_pm_runtime_init(void)
 {
-	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) {
+	if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_ARCH_SHMOBILE)) {
 		if (!of_find_compatible_node(NULL, NULL,
 					     "renesas,cpg-mstp-clocks"))
 			return 0;
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index aebad36391c9..8feac599e9ab 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1571,6 +1571,7 @@ static int atmel_spi_probe(struct platform_device *pdev)
 
 	as->use_cs_gpios = true;
 	if (atmel_spi_is_v2(as) &&
+	    pdev->dev.of_node &&
 	    !of_get_property(pdev->dev.of_node, "cs-gpios", NULL)) {
 		as->use_cs_gpios = false;
 		master->num_chipselect = 4;
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 7de6f8472a81..ecc73c0a97cf 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -73,8 +73,8 @@
 
 /* Bitfields in CNTL1 */
 #define BCM2835_AUX_SPI_CNTL1_CSHIGH	0x00000700
-#define BCM2835_AUX_SPI_CNTL1_IDLE	0x00000080
-#define BCM2835_AUX_SPI_CNTL1_TXEMPTY	0x00000040
+#define BCM2835_AUX_SPI_CNTL1_TXEMPTY	0x00000080
+#define BCM2835_AUX_SPI_CNTL1_IDLE	0x00000040
 #define BCM2835_AUX_SPI_CNTL1_MSBF_IN	0x00000002
 #define BCM2835_AUX_SPI_CNTL1_KEEP_IN	0x00000001
 
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 7fd6a4c009d2..7cb0c1921495 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -84,7 +84,7 @@ struct fsl_espi_transfer {
 /* SPCOM register values */
 #define SPCOM_CS(x)		((x) << 30)
 #define SPCOM_TRANLEN(x)	((x) << 0)
-#define	SPCOM_TRANLEN_MAX	0xFFFF	/* Max transaction length */
+#define	SPCOM_TRANLEN_MAX	0x10000	/* Max transaction length */
 
 #define AUTOSUSPEND_TIMEOUT 2000
 
@@ -233,7 +233,7 @@ static int fsl_espi_bufs(struct spi_device *spi, struct spi_transfer *t)
 	reinit_completion(&mpc8xxx_spi->done);
 
 	/* Set SPCOM[CS] and SPCOM[TRANLEN] field */
-	if ((t->len - 1) > SPCOM_TRANLEN_MAX) {
+	if (t->len > SPCOM_TRANLEN_MAX) {
 		dev_err(mpc8xxx_spi->dev, "Transaction length (%d)"
 				" beyond the SPCOM[TRANLEN] field\n", t->len);
 		return -EINVAL;
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index d98c33cb64f9..6a4ff27f4357 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -929,7 +929,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 					tx->sgl, tx->nents, DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (!desc_tx)
-			goto no_dma;
+			goto tx_nodma;
 
 		desc_tx->callback = spi_imx_dma_tx_callback;
 		desc_tx->callback_param = (void *)spi_imx;
@@ -941,7 +941,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 					rx->sgl, rx->nents, DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (!desc_rx)
-			goto no_dma;
+			goto rx_nodma;
 
 		desc_rx->callback = spi_imx_dma_rx_callback;
 		desc_rx->callback_param = (void *)spi_imx;
@@ -1008,7 +1008,9 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 
 	return ret;
 
-no_dma:
+rx_nodma:
+	dmaengine_terminate_all(master->dma_tx);
+tx_nodma:
 	pr_warn_once("%s %s: DMA not available, falling back to PIO\n",
 		     dev_driver_string(&master->dev),
 		     dev_name(&master->dev));
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index 894616f687b0..cf4bb36bee25 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -761,6 +761,7 @@ static int spi_test_run_iter(struct spi_device *spi,
 		test.iterate_transfer_mask = 1;
 
 	/* count number of transfers with tx/rx_buf != NULL */
+	rx_count = tx_count = 0;
 	for (i = 0; i < test.transfer_count; i++) {
 		if (test.transfers[i].tx_buf)
 			tx_count++;
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 7273820275e9..0caa3c8bef46 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -1490,6 +1490,8 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
 	return status;
 
 disable_pm:
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 free_master:
 	spi_master_put(master);
@@ -1501,6 +1503,7 @@ static int omap2_mcspi_remove(struct platform_device *pdev)
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
 
+	pm_runtime_dont_use_autosuspend(mcspi->dev);
 	pm_runtime_put_sync(mcspi->dev);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 3327c49674d3..713c63d9681b 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -898,7 +898,7 @@ static ssize_t unmap_zeroes_data_store(struct config_item *item,
 	da->unmap_zeroes_data = flag;
 	pr_debug("dev[%p]: SE Device Thin Provisioning LBPRZ bit: %d\n",
 		 da->da_dev, flag);
-	return 0;
+	return count;
 }
 
 /*
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index cacd97a8cbd0..da457e25717a 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -828,6 +828,50 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	return dev;
 }
 
+/*
+ * Check if the underlying struct block_device request_queue supports
+ * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
+ * in ATA and we need to set TPE=1
+ */
+bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
+				       struct request_queue *q, int block_size)
+{
+	if (!blk_queue_discard(q))
+		return false;
+
+	attrib->max_unmap_lba_count = (q->limits.max_discard_sectors << 9) /
+								block_size;
+	/*
+	 * Currently hardcoded to 1 in Linux/SCSI code..
+	 */
+	attrib->max_unmap_block_desc_count = 1;
+	attrib->unmap_granularity = q->limits.discard_granularity / block_size;
+	attrib->unmap_granularity_alignment = q->limits.discard_alignment /
+								block_size;
+	attrib->unmap_zeroes_data = q->limits.discard_zeroes_data;
+	return true;
+}
+EXPORT_SYMBOL(target_configure_unmap_from_queue);
+
+/*
+ * Convert from blocksize advertised to the initiator to the 512 byte
+ * units unconditionally used by the Linux block layer.
+ */
+sector_t target_to_linux_sector(struct se_device *dev, sector_t lb)
+{
+	switch (dev->dev_attrib.block_size) {
+	case 4096:
+		return lb << 3;
+	case 2048:
+		return lb << 2;
+	case 1024:
+		return lb << 1;
+	default:
+		return lb;
+	}
+}
+EXPORT_SYMBOL(target_to_linux_sector);
+
 int target_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index e3195700211a..75f0f08b2a34 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -160,25 +160,11 @@ static int fd_configure_device(struct se_device *dev)
 			" block_device blocks: %llu logical_block_size: %d\n",
 			dev_size, div_u64(dev_size, fd_dev->fd_block_size),
 			fd_dev->fd_block_size);
-		/*
-		 * Check if the underlying struct block_device request_queue supports
-		 * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
-		 * in ATA and we need to set TPE=1
-		 */
-		if (blk_queue_discard(q)) {
-			dev->dev_attrib.max_unmap_lba_count =
-				q->limits.max_discard_sectors;
-			/*
-			 * Currently hardcoded to 1 in Linux/SCSI code..
-			 */
-			dev->dev_attrib.max_unmap_block_desc_count = 1;
-			dev->dev_attrib.unmap_granularity =
-				q->limits.discard_granularity >> 9;
-			dev->dev_attrib.unmap_granularity_alignment =
-				q->limits.discard_alignment;
+
+		if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
+						      fd_dev->fd_block_size))
 			pr_debug("IFILE: BLOCK Discard support available,"
-					" disabled by default\n");
-		}
+				 " disabled by default\n");
 		/*
 		 * Enable write same emulation for IBLOCK and use 0xFFFF as
 		 * the smaller WRITE_SAME(10) only has a two-byte block count.
@@ -490,9 +476,12 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 	if (S_ISBLK(inode->i_mode)) {
 		/* The backend is block device, use discard */
 		struct block_device *bdev = inode->i_bdev;
+		struct se_device *dev = cmd->se_dev;
 
-		ret = blkdev_issue_discard(bdev, lba,
-				nolb, GFP_KERNEL, 0);
+		ret = blkdev_issue_discard(bdev,
+					   target_to_linux_sector(dev, lba),
+					   target_to_linux_sector(dev,  nolb),
+					   GFP_KERNEL, 0);
 		if (ret < 0) {
 			pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n",
 				ret);
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 5a2899f9f50b..abe4eb997a84 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -121,29 +121,11 @@ static int iblock_configure_device(struct se_device *dev)
 	dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
 	dev->dev_attrib.hw_queue_depth = q->nr_requests;
 
-	/*
-	 * Check if the underlying struct block_device request_queue supports
-	 * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
-	 * in ATA and we need to set TPE=1
-	 */
-	if (blk_queue_discard(q)) {
-		dev->dev_attrib.max_unmap_lba_count =
-				q->limits.max_discard_sectors;
-
-		/*
-		 * Currently hardcoded to 1 in Linux/SCSI code..
-		 */
-		dev->dev_attrib.max_unmap_block_desc_count = 1;
-		dev->dev_attrib.unmap_granularity =
-				q->limits.discard_granularity >> 9;
-		dev->dev_attrib.unmap_granularity_alignment =
-				q->limits.discard_alignment;
-		dev->dev_attrib.unmap_zeroes_data =
-				q->limits.discard_zeroes_data;
-
+	if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
+					      dev->dev_attrib.hw_block_size))
 		pr_debug("IBLOCK: BLOCK Discard support available,"
-				" disabled by default\n");
-	}
+			 " disabled by default\n");
+
 	/*
 	 * Enable write same emulation for IBLOCK and use 0xFFFF as
 	 * the smaller WRITE_SAME(10) only has a two-byte block count.
@@ -415,9 +397,13 @@ static sense_reason_t
 iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 {
 	struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd;
+	struct se_device *dev = cmd->se_dev;
 	int ret;
 
-	ret = blkdev_issue_discard(bdev, lba, nolb, GFP_KERNEL, 0);
+	ret = blkdev_issue_discard(bdev,
+				   target_to_linux_sector(dev, lba),
+				   target_to_linux_sector(dev,  nolb),
+				   GFP_KERNEL, 0);
 	if (ret < 0) {
 		pr_err("blkdev_issue_discard() failed: %d\n", ret);
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -433,8 +419,10 @@ iblock_execute_write_same(struct se_cmd *cmd)
 	struct scatterlist *sg;
 	struct bio *bio;
 	struct bio_list list;
-	sector_t block_lba = cmd->t_task_lba;
-	sector_t sectors = sbc_get_write_same_sectors(cmd);
+	struct se_device *dev = cmd->se_dev;
+	sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba);
+	sector_t sectors = target_to_linux_sector(dev,
+					sbc_get_write_same_sectors(cmd));
 
 	if (cmd->prot_op) {
 		pr_err("WRITE_SAME: Protection information with IBLOCK"
@@ -648,12 +636,12 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		  enum dma_data_direction data_direction)
 {
 	struct se_device *dev = cmd->se_dev;
+	sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba);
 	struct iblock_req *ibr;
 	struct bio *bio, *bio_start;
 	struct bio_list list;
 	struct scatterlist *sg;
 	u32 sg_num = sgl_nents;
-	sector_t block_lba;
 	unsigned bio_cnt;
 	int rw = 0;
 	int i;
@@ -679,24 +667,6 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		rw = READ;
 	}
 
-	/*
-	 * Convert the blocksize advertised to the initiator to the 512 byte
-	 * units unconditionally used by the Linux block layer.
-	 */
-	if (dev->dev_attrib.block_size == 4096)
-		block_lba = (cmd->t_task_lba << 3);
-	else if (dev->dev_attrib.block_size == 2048)
-		block_lba = (cmd->t_task_lba << 2);
-	else if (dev->dev_attrib.block_size == 1024)
-		block_lba = (cmd->t_task_lba << 1);
-	else if (dev->dev_attrib.block_size == 512)
-		block_lba = cmd->t_task_lba;
-	else {
-		pr_err("Unsupported SCSI -> BLOCK LBA conversion:"
-				" %u\n", dev->dev_attrib.block_size);
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	}
-
 	ibr = kzalloc(sizeof(struct iblock_req), GFP_KERNEL);
 	if (!ibr)
 		goto fail;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index dae0750c2032..db4412fe6b8a 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -141,7 +141,6 @@ void	transport_dump_vpd_proto_id(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_assoc(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident_type(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int);
-bool	target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
 void	transport_clear_lun_ref(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
 sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index fcdcb117c60d..82a663ba9800 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -68,23 +68,25 @@ void core_tmr_release_req(struct se_tmr_req *tmr)
 
 	if (dev) {
 		spin_lock_irqsave(&dev->se_tmr_lock, flags);
-		list_del(&tmr->tmr_list);
+		list_del_init(&tmr->tmr_list);
 		spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
 	}
 
 	kfree(tmr);
 }
 
-static void core_tmr_handle_tas_abort(
-	struct se_node_acl *tmr_nacl,
-	struct se_cmd *cmd,
-	int tas)
+static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
 {
-	bool remove = true;
+	unsigned long flags;
+	bool remove = true, send_tas;
 	/*
 	 * TASK ABORTED status (TAS) bit support
 	 */
-	if ((tmr_nacl && (tmr_nacl != cmd->se_sess->se_node_acl)) && tas) {
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	send_tas = (cmd->transport_state & CMD_T_TAS);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
+	if (send_tas) {
 		remove = false;
 		transport_send_task_abort(cmd);
 	}
@@ -107,6 +109,46 @@ static int target_check_cdb_and_preempt(struct list_head *list,
 	return 1;
 }
 
+static bool __target_check_io_state(struct se_cmd *se_cmd,
+				    struct se_session *tmr_sess, int tas)
+{
+	struct se_session *sess = se_cmd->se_sess;
+
+	assert_spin_locked(&sess->sess_cmd_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+	/*
+	 * If command already reached CMD_T_COMPLETE state within
+	 * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
+	 * this se_cmd has been passed to fabric driver and will
+	 * not be aborted.
+	 *
+	 * Otherwise, obtain a local se_cmd->cmd_kref now for TMR
+	 * ABORT_TASK + LUN_RESET for CMD_T_ABORTED processing as
+	 * long as se_cmd->cmd_kref is still active unless zero.
+	 */
+	spin_lock(&se_cmd->t_state_lock);
+	if (se_cmd->transport_state & (CMD_T_COMPLETE | CMD_T_FABRIC_STOP)) {
+		pr_debug("Attempted to abort io tag: %llu already complete or"
+			" fabric stop, skipping\n", se_cmd->tag);
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	if (sess->sess_tearing_down || se_cmd->cmd_wait_set) {
+		pr_debug("Attempted to abort io tag: %llu already shutdown,"
+			" skipping\n", se_cmd->tag);
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	se_cmd->transport_state |= CMD_T_ABORTED;
+
+	if ((tmr_sess != se_cmd->se_sess) && tas)
+		se_cmd->transport_state |= CMD_T_TAS;
+
+	spin_unlock(&se_cmd->t_state_lock);
+
+	return kref_get_unless_zero(&se_cmd->cmd_kref);
+}
+
 void core_tmr_abort_task(
 	struct se_device *dev,
 	struct se_tmr_req *tmr,
@@ -130,34 +172,22 @@ void core_tmr_abort_task(
 		if (tmr->ref_task_tag != ref_tag)
 			continue;
 
-		if (!kref_get_unless_zero(&se_cmd->cmd_kref))
-			continue;
-
 		printk("ABORT_TASK: Found referenced %s task_tag: %llu\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
-		spin_lock(&se_cmd->t_state_lock);
-		if (se_cmd->transport_state & CMD_T_COMPLETE) {
-			printk("ABORT_TASK: ref_tag: %llu already complete,"
-			       " skipping\n", ref_tag);
-			spin_unlock(&se_cmd->t_state_lock);
+		if (!__target_check_io_state(se_cmd, se_sess, 0)) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-
 			target_put_sess_cmd(se_cmd);
-
 			goto out;
 		}
-		se_cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock(&se_cmd->t_state_lock);
-
 		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		target_put_sess_cmd(se_cmd);
 		transport_cmd_finish_abort(se_cmd, true);
+		target_put_sess_cmd(se_cmd);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
 				" ref_tag: %llu\n", ref_tag);
@@ -178,9 +208,11 @@ static void core_tmr_drain_tmr_list(
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_tmr_list);
+	struct se_session *sess;
 	struct se_tmr_req *tmr_p, *tmr_pp;
 	struct se_cmd *cmd;
 	unsigned long flags;
+	bool rc;
 	/*
 	 * Release all pending and outgoing TMRs aside from the received
 	 * LUN_RESET tmr..
@@ -206,17 +238,39 @@ static void core_tmr_drain_tmr_list(
 		if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd))
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
 		spin_lock(&cmd->t_state_lock);
-		if (!(cmd->transport_state & CMD_T_ACTIVE)) {
+		if (!(cmd->transport_state & CMD_T_ACTIVE) ||
+		     (cmd->transport_state & CMD_T_FABRIC_STOP)) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
 		if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
+		if (sess->sess_tearing_down || cmd->cmd_wait_set) {
+			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
+			continue;
+		}
+		cmd->transport_state |= CMD_T_ABORTED;
 		spin_unlock(&cmd->t_state_lock);
 
+		rc = kref_get_unless_zero(&cmd->cmd_kref);
+		if (!rc) {
+			printk("LUN_RESET TMR: non-zero kref_get_unless_zero\n");
+			spin_unlock(&sess->sess_cmd_lock);
+			continue;
+		}
+		spin_unlock(&sess->sess_cmd_lock);
+
 		list_move_tail(&tmr_p->tmr_list, &drain_tmr_list);
 	}
 	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
@@ -230,20 +284,26 @@ static void core_tmr_drain_tmr_list(
 			(preempt_and_abort_list) ? "Preempt" : "", tmr_p,
 			tmr_p->function, tmr_p->response, cmd->t_state);
 
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
+
 		transport_cmd_finish_abort(cmd, 1);
+		target_put_sess_cmd(cmd);
 	}
 }
 
 static void core_tmr_drain_state_list(
 	struct se_device *dev,
 	struct se_cmd *prout_cmd,
-	struct se_node_acl *tmr_nacl,
+	struct se_session *tmr_sess,
 	int tas,
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_task_list);
+	struct se_session *sess;
 	struct se_cmd *cmd, *next;
 	unsigned long flags;
+	int rc;
 
 	/*
 	 * Complete outstanding commands with TASK_ABORTED SAM status.
@@ -282,6 +342,16 @@ static void core_tmr_drain_state_list(
 		if (prout_cmd == cmd)
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
+		rc = __target_check_io_state(cmd, tmr_sess, tas);
+		spin_unlock(&sess->sess_cmd_lock);
+		if (!rc)
+			continue;
+
 		list_move_tail(&cmd->state_list, &drain_task_list);
 		cmd->state_active = false;
 	}
@@ -289,7 +359,7 @@ static void core_tmr_drain_state_list(
 
 	while (!list_empty(&drain_task_list)) {
 		cmd = list_entry(drain_task_list.next, struct se_cmd, state_list);
-		list_del(&cmd->state_list);
+		list_del_init(&cmd->state_list);
 
 		pr_debug("LUN_RESET: %s cmd: %p"
 			" ITT/CmdSN: 0x%08llx/0x%08x, i_state: %d, t_state: %d"
@@ -313,16 +383,11 @@ static void core_tmr_drain_state_list(
 		 * loop above, but we do it down here given that
 		 * cancel_work_sync may block.
 		 */
-		if (cmd->t_state == TRANSPORT_COMPLETE)
-			cancel_work_sync(&cmd->work);
-
-		spin_lock_irqsave(&cmd->t_state_lock, flags);
-		target_stop_cmd(cmd, &flags);
-
-		cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
 
-		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas);
+		core_tmr_handle_tas_abort(cmd, tas);
+		target_put_sess_cmd(cmd);
 	}
 }
 
@@ -334,6 +399,7 @@ int core_tmr_lun_reset(
 {
 	struct se_node_acl *tmr_nacl = NULL;
 	struct se_portal_group *tmr_tpg = NULL;
+	struct se_session *tmr_sess = NULL;
 	int tas;
         /*
 	 * TASK_ABORTED status bit, this is configurable via ConfigFS
@@ -352,8 +418,9 @@ int core_tmr_lun_reset(
 	 * or struct se_device passthrough..
 	 */
 	if (tmr && tmr->task_cmd && tmr->task_cmd->se_sess) {
-		tmr_nacl = tmr->task_cmd->se_sess->se_node_acl;
-		tmr_tpg = tmr->task_cmd->se_sess->se_tpg;
+		tmr_sess = tmr->task_cmd->se_sess;
+		tmr_nacl = tmr_sess->se_node_acl;
+		tmr_tpg = tmr_sess->se_tpg;
 		if (tmr_nacl && tmr_tpg) {
 			pr_debug("LUN_RESET: TMR caller fabric: %s"
 				" initiator port %s\n",
@@ -366,7 +433,7 @@ int core_tmr_lun_reset(
 		dev->transport->name, tas);
 
 	core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list);
-	core_tmr_drain_state_list(dev, prout_cmd, tmr_nacl, tas,
+	core_tmr_drain_state_list(dev, prout_cmd, tmr_sess, tas,
 				preempt_and_abort_list);
 
 	/*
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9f3608e10f25..867bc6d0a68a 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -534,9 +534,6 @@ void transport_deregister_session(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(transport_deregister_session);
 
-/*
- * Called with cmd->t_state_lock held.
- */
 static void target_remove_from_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -561,10 +558,6 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if (write_pending)
-		cmd->t_state = TRANSPORT_WRITE_PENDING;
-
 	if (remove_from_lists) {
 		target_remove_from_state_list(cmd);
 
@@ -574,6 +567,10 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 		cmd->se_lun = NULL;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (write_pending)
+		cmd->t_state = TRANSPORT_WRITE_PENDING;
+
 	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
@@ -627,6 +624,8 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 {
+	bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF);
+
 	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD)
 		transport_lun_remove_cmd(cmd);
 	/*
@@ -638,7 +637,7 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
 		return;
-	if (remove)
+	if (remove && ack_kref)
 		transport_put_cmd(cmd);
 }
 
@@ -694,19 +693,10 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	}
 
 	/*
-	 * See if we are waiting to complete for an exception condition.
-	 */
-	if (cmd->transport_state & CMD_T_REQUEST_STOP) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->task_stop_comp);
-		return;
-	}
-
-	/*
 	 * Check for case where an explicit ABORT_TASK has been received
 	 * and transport_wait_for_tasks() will be waiting for completion..
 	 */
-	if (cmd->transport_state & CMD_T_ABORTED &&
+	if (cmd->transport_state & CMD_T_ABORTED ||
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		complete_all(&cmd->t_transport_stop_comp);
@@ -721,10 +711,10 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	cmd->transport_state |= (CMD_T_COMPLETE | CMD_T_ACTIVE);
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	if (cmd->cpuid == -1)
-		queue_work(target_completion_wq, &cmd->work);
-	else
+	if (cmd->se_cmd_flags & SCF_USE_CPUID)
 		queue_work_on(cmd->cpuid, target_completion_wq, &cmd->work);
+	else
+		queue_work(target_completion_wq, &cmd->work);
 }
 EXPORT_SYMBOL(target_complete_cmd);
 
@@ -1203,7 +1193,6 @@ void transport_init_se_cmd(
 	INIT_LIST_HEAD(&cmd->state_list);
 	init_completion(&cmd->t_transport_stop_comp);
 	init_completion(&cmd->cmd_wait_comp);
-	init_completion(&cmd->task_stop_comp);
 	spin_lock_init(&cmd->t_state_lock);
 	kref_init(&cmd->cmd_kref);
 	cmd->transport_state = CMD_T_DEV_ACTIVE;
@@ -1437,6 +1426,12 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 	 */
 	transport_init_se_cmd(se_cmd, se_tpg->se_tpg_tfo, se_sess,
 				data_length, data_dir, task_attr, sense);
+
+	if (flags & TARGET_SCF_USE_CPUID)
+		se_cmd->se_cmd_flags |= SCF_USE_CPUID;
+	else
+		se_cmd->cpuid = WORK_CPU_UNBOUND;
+
 	if (flags & TARGET_SCF_UNKNOWN_SIZE)
 		se_cmd->unknown_data_length = 1;
 	/*
@@ -1635,33 +1630,6 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
 EXPORT_SYMBOL(target_submit_tmr);
 
 /*
- * If the cmd is active, request it to be stopped and sleep until it
- * has completed.
- */
-bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags)
-	__releases(&cmd->t_state_lock)
-	__acquires(&cmd->t_state_lock)
-{
-	bool was_active = false;
-
-	if (cmd->transport_state & CMD_T_BUSY) {
-		cmd->transport_state |= CMD_T_REQUEST_STOP;
-		spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
-
-		pr_debug("cmd %p waiting to complete\n", cmd);
-		wait_for_completion(&cmd->task_stop_comp);
-		pr_debug("cmd %p stopped successfully\n", cmd);
-
-		spin_lock_irqsave(&cmd->t_state_lock, *flags);
-		cmd->transport_state &= ~CMD_T_REQUEST_STOP;
-		cmd->transport_state &= ~CMD_T_BUSY;
-		was_active = true;
-	}
-
-	return was_active;
-}
-
-/*
  * Handle SAM-esque emulation for generic transport request failures.
  */
 void transport_generic_request_failure(struct se_cmd *cmd,
@@ -1859,19 +1827,21 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 	return true;
 }
 
+static int __transport_check_aborted_status(struct se_cmd *, int);
+
 void target_execute_cmd(struct se_cmd *cmd)
 {
 	/*
-	 * If the received CDB has aleady been aborted stop processing it here.
-	 */
-	if (transport_check_aborted_status(cmd, 1))
-		return;
-
-	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
+	 *
+	 * If the received CDB has aleady been aborted stop processing it here.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
+	if (__transport_check_aborted_status(cmd, 1)) {
+		spin_unlock_irq(&cmd->t_state_lock);
+		return;
+	}
 	if (cmd->transport_state & CMD_T_STOP) {
 		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n",
 			__func__, __LINE__, cmd->tag);
@@ -2222,20 +2192,14 @@ static inline void transport_free_pages(struct se_cmd *cmd)
 }
 
 /**
- * transport_release_cmd - free a command
- * @cmd:       command to free
+ * transport_put_cmd - release a reference to a command
+ * @cmd:       command to release
  *
- * This routine unconditionally frees a command, and reference counting
- * or list removal must be done in the caller.
+ * This routine releases our reference to the command and frees it if possible.
  */
-static int transport_release_cmd(struct se_cmd *cmd)
+static int transport_put_cmd(struct se_cmd *cmd)
 {
 	BUG_ON(!cmd->se_tfo);
-
-	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
-		core_tmr_release_req(cmd->se_tmr_req);
-	if (cmd->t_task_cdb != cmd->__t_task_cdb)
-		kfree(cmd->t_task_cdb);
 	/*
 	 * If this cmd has been setup with target_get_sess_cmd(), drop
 	 * the kref and call ->release_cmd() in kref callback.
@@ -2243,18 +2207,6 @@ static int transport_release_cmd(struct se_cmd *cmd)
 	return target_put_sess_cmd(cmd);
 }
 
-/**
- * transport_put_cmd - release a reference to a command
- * @cmd:       command to release
- *
- * This routine releases our reference to the command and frees it if possible.
- */
-static int transport_put_cmd(struct se_cmd *cmd)
-{
-	transport_free_pages(cmd);
-	return transport_release_cmd(cmd);
-}
-
 void *transport_kmap_data_sg(struct se_cmd *cmd)
 {
 	struct scatterlist *sg = cmd->t_data_sg;
@@ -2450,34 +2402,58 @@ static void transport_write_pending_qf(struct se_cmd *cmd)
 	}
 }
 
-int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
+static bool
+__transport_wait_for_tasks(struct se_cmd *, bool, bool *, bool *,
+			   unsigned long *flags);
+
+static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas)
 {
 	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	__transport_wait_for_tasks(cmd, true, aborted, tas, &flags);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+}
+
+int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
+{
 	int ret = 0;
+	bool aborted = false, tas = false;
 
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
 		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
-			 transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 
-		ret = transport_release_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
 	} else {
 		if (wait_for_tasks)
-			transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 		/*
 		 * Handle WRITE failure case where transport_generic_new_cmd()
 		 * has already added se_cmd to state_list, but fabric has
 		 * failed command before I/O submission.
 		 */
-		if (cmd->state_active) {
-			spin_lock_irqsave(&cmd->t_state_lock, flags);
+		if (cmd->state_active)
 			target_remove_from_state_list(cmd);
-			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		}
 
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
 
-		ret = transport_put_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
+	}
+	/*
+	 * If the task has been internally aborted due to TMR ABORT_TASK
+	 * or LUN_RESET, target_core_tmr.c is responsible for performing
+	 * the remaining calls to target_put_sess_cmd(), and not the
+	 * callers of this function.
+	 */
+	if (aborted) {
+		pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
+		wait_for_completion(&cmd->cmd_wait_comp);
+		cmd->se_tfo->release_cmd(cmd);
+		ret = 1;
 	}
 	return ret;
 }
@@ -2517,26 +2493,46 @@ out:
 }
 EXPORT_SYMBOL(target_get_sess_cmd);
 
+static void target_free_cmd_mem(struct se_cmd *cmd)
+{
+	transport_free_pages(cmd);
+
+	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
+		core_tmr_release_req(cmd->se_tmr_req);
+	if (cmd->t_task_cdb != cmd->__t_task_cdb)
+		kfree(cmd->t_task_cdb);
+}
+
 static void target_release_cmd_kref(struct kref *kref)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
 	struct se_session *se_sess = se_cmd->se_sess;
 	unsigned long flags;
+	bool fabric_stop;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (list_empty(&se_cmd->se_cmd_list)) {
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return;
 	}
-	if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) {
+
+	spin_lock(&se_cmd->t_state_lock);
+	fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP);
+	spin_unlock(&se_cmd->t_state_lock);
+
+	if (se_cmd->cmd_wait_set || fabric_stop) {
+		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+		target_free_cmd_mem(se_cmd);
 		complete(&se_cmd->cmd_wait_comp);
 		return;
 	}
-	list_del(&se_cmd->se_cmd_list);
+	list_del_init(&se_cmd->se_cmd_list);
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
+	target_free_cmd_mem(se_cmd);
 	se_cmd->se_tfo->release_cmd(se_cmd);
 }
 
@@ -2548,6 +2544,7 @@ int target_put_sess_cmd(struct se_cmd *se_cmd)
 	struct se_session *se_sess = se_cmd->se_sess;
 
 	if (!se_sess) {
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return 1;
 	}
@@ -2564,6 +2561,7 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 {
 	struct se_cmd *se_cmd;
 	unsigned long flags;
+	int rc;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (se_sess->sess_tearing_down) {
@@ -2573,8 +2571,15 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 	se_sess->sess_tearing_down = 1;
 	list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
 
-	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list)
-		se_cmd->cmd_wait_set = 1;
+	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) {
+		rc = kref_get_unless_zero(&se_cmd->cmd_kref);
+		if (rc) {
+			se_cmd->cmd_wait_set = 1;
+			spin_lock(&se_cmd->t_state_lock);
+			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
+			spin_unlock(&se_cmd->t_state_lock);
+		}
+	}
 
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 }
@@ -2587,15 +2592,25 @@ void target_wait_for_sess_cmds(struct se_session *se_sess)
 {
 	struct se_cmd *se_cmd, *tmp_cmd;
 	unsigned long flags;
+	bool tas;
 
 	list_for_each_entry_safe(se_cmd, tmp_cmd,
 				&se_sess->sess_wait_list, se_cmd_list) {
-		list_del(&se_cmd->se_cmd_list);
+		list_del_init(&se_cmd->se_cmd_list);
 
 		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
 			" %d\n", se_cmd, se_cmd->t_state,
 			se_cmd->se_tfo->get_cmd_state(se_cmd));
 
+		spin_lock_irqsave(&se_cmd->t_state_lock, flags);
+		tas = (se_cmd->transport_state & CMD_T_TAS);
+		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
+
+		if (!target_put_sess_cmd(se_cmd)) {
+			if (tas)
+				target_put_sess_cmd(se_cmd);
+		}
+
 		wait_for_completion(&se_cmd->cmd_wait_comp);
 		pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d"
 			" fabric state: %d\n", se_cmd, se_cmd->t_state,
@@ -2617,53 +2632,75 @@ void transport_clear_lun_ref(struct se_lun *lun)
 	wait_for_completion(&lun->lun_ref_comp);
 }
 
-/**
- * transport_wait_for_tasks - wait for completion to occur
- * @cmd:	command to wait
- *
- * Called from frontend fabric context to wait for storage engine
- * to pause and/or release frontend generated struct se_cmd.
- */
-bool transport_wait_for_tasks(struct se_cmd *cmd)
+static bool
+__transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
+			   bool *aborted, bool *tas, unsigned long *flags)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
 {
-	unsigned long flags;
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (fabric_stop)
+		cmd->transport_state |= CMD_T_FABRIC_STOP;
+
+	if (cmd->transport_state & CMD_T_ABORTED)
+		*aborted = true;
+
+	if (cmd->transport_state & CMD_T_TAS)
+		*tas = true;
+
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
 		return false;
-	}
 
 	if (!(cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
 		return false;
-	}
 
-	if (!(cmd->transport_state & CMD_T_ACTIVE)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	if (!(cmd->transport_state & CMD_T_ACTIVE))
+		return false;
+
+	if (fabric_stop && *aborted)
 		return false;
-	}
 
 	cmd->transport_state |= CMD_T_STOP;
 
-	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d, t_state: %d, CMD_T_STOP\n",
-		cmd, cmd->tag, cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
+	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d,"
+		 " t_state: %d, CMD_T_STOP\n", cmd, cmd->tag,
+		 cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
 
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
 
 	wait_for_completion(&cmd->t_transport_stop_comp);
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	spin_lock_irqsave(&cmd->t_state_lock, *flags);
 	cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP);
 
-	pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->t_transport_stop_comp) for ITT: 0x%08llx\n",
-		cmd->tag);
+	pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->"
+		 "t_transport_stop_comp) for ITT: 0x%08llx\n", cmd->tag);
 
+	return true;
+}
+
+/**
+ * transport_wait_for_tasks - wait for completion to occur
+ * @cmd:	command to wait
+ *
+ * Called from frontend fabric context to wait for storage engine
+ * to pause and/or release frontend generated struct se_cmd.
+ */
+bool transport_wait_for_tasks(struct se_cmd *cmd)
+{
+	unsigned long flags;
+	bool ret, aborted = false, tas = false;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	ret = __transport_wait_for_tasks(cmd, false, &aborted, &tas, &flags);
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	return true;
+	return ret;
 }
 EXPORT_SYMBOL(transport_wait_for_tasks);
 
@@ -2845,28 +2882,49 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 }
 EXPORT_SYMBOL(transport_send_check_condition_and_sense);
 
-int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
 {
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
 	if (!(cmd->transport_state & CMD_T_ABORTED))
 		return 0;
-
 	/*
 	 * If cmd has been aborted but either no status is to be sent or it has
 	 * already been sent, just return
 	 */
-	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS))
+	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS)) {
+		if (send_status)
+			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
 		return 1;
+	}
 
-	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB: 0x%02x ITT: 0x%08llx\n",
-		 cmd->t_task_cdb[0], cmd->tag);
+	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB:"
+		" 0x%02x ITT: 0x%08llx\n", cmd->t_task_cdb[0], cmd->tag);
 
 	cmd->se_cmd_flags &= ~SCF_SEND_DELAYED_TAS;
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 	trace_target_cmd_complete(cmd);
+
+	spin_unlock_irq(&cmd->t_state_lock);
 	cmd->se_tfo->queue_status(cmd);
+	spin_lock_irq(&cmd->t_state_lock);
 
 	return 1;
 }
+
+int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+{
+	int ret;
+
+	spin_lock_irq(&cmd->t_state_lock);
+	ret = __transport_check_aborted_status(cmd, send_status);
+	spin_unlock_irq(&cmd->t_state_lock);
+
+	return ret;
+}
 EXPORT_SYMBOL(transport_check_aborted_status);
 
 void transport_send_task_abort(struct se_cmd *cmd)
@@ -2888,11 +2946,17 @@ void transport_send_task_abort(struct se_cmd *cmd)
 	 */
 	if (cmd->data_direction == DMA_TO_DEVICE) {
 		if (cmd->se_tfo->write_pending_status(cmd) != 0) {
-			cmd->transport_state |= CMD_T_ABORTED;
+			spin_lock_irqsave(&cmd->t_state_lock, flags);
+			if (cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS) {
+				spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+				goto send_abort;
+			}
 			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
+			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 			return;
 		}
 	}
+send_abort:
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 
 	transport_lun_remove_cmd(cmd);
@@ -2909,8 +2973,17 @@ static void target_tmr_work(struct work_struct *work)
 	struct se_cmd *cmd = container_of(work, struct se_cmd, work);
 	struct se_device *dev = cmd->se_dev;
 	struct se_tmr_req *tmr = cmd->se_tmr_req;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		tmr->response = TMR_FUNCTION_REJECTED;
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	switch (tmr->function) {
 	case TMR_ABORT_TASK:
 		core_tmr_abort_task(dev, tmr, cmd->se_sess);
@@ -2943,9 +3016,17 @@ static void target_tmr_work(struct work_struct *work)
 		break;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
 	cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	cmd->se_tfo->queue_tm_rsp(cmd);
 
+check_stop:
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index dd600e5ead71..94f5154ac788 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -903,7 +903,7 @@ static int tcmu_configure_device(struct se_device *dev)
 	info->version = __stringify(TCMU_MAILBOX_VERSION);
 
 	info->mem[0].name = "tcm-user command & data buffer";
-	info->mem[0].addr = (phys_addr_t) udev->mb_addr;
+	info->mem[0].addr = (phys_addr_t)(uintptr_t)udev->mb_addr;
 	info->mem[0].size = TCMU_RING_SIZE;
 	info->mem[0].memtype = UIO_MEM_VIRTUAL;
 
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 8cc4ac64a91c..7c92c09be213 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -195,7 +195,7 @@ config IMX_THERMAL
 	  passive trip is crossed.
 
 config SPEAR_THERMAL
-	bool "SPEAr thermal sensor driver"
+	tristate "SPEAr thermal sensor driver"
 	depends on PLAT_SPEAR || COMPILE_TEST
 	depends on OF
 	help
@@ -237,8 +237,8 @@ config DOVE_THERMAL
 	  framework.
 
 config DB8500_THERMAL
-	bool "DB8500 thermal management"
-	depends on ARCH_U8500
+	tristate "DB8500 thermal management"
+	depends on MFD_DB8500_PRCMU
 	default y
 	help
 	  Adds DB8500 thermal management implementation according to the thermal
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index e3fbc5a5d88f..6ceac4f2d4b2 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -377,26 +377,28 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device,
  * get_load() - get load for a cpu since last updated
  * @cpufreq_device:	&struct cpufreq_cooling_device for this cpu
  * @cpu:	cpu number
+ * @cpu_idx:	index of the cpu in cpufreq_device->allowed_cpus
  *
  * Return: The average load of cpu @cpu in percentage since this
  * function was last called.
  */
-static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu)
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu,
+		    int cpu_idx)
 {
 	u32 load;
 	u64 now, now_idle, delta_time, delta_idle;
 
 	now_idle = get_cpu_idle_time(cpu, &now, 0);
-	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu];
-	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu];
+	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu_idx];
+	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu_idx];
 
 	if (delta_time <= delta_idle)
 		load = 0;
 	else
 		load = div64_u64(100 * (delta_time - delta_idle), delta_time);
 
-	cpufreq_device->time_in_idle[cpu] = now_idle;
-	cpufreq_device->time_in_idle_timestamp[cpu] = now;
+	cpufreq_device->time_in_idle[cpu_idx] = now_idle;
+	cpufreq_device->time_in_idle_timestamp[cpu_idx] = now;
 
 	return load;
 }
@@ -598,7 +600,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 		u32 load;
 
 		if (cpu_online(cpu))
-			load = get_load(cpufreq_device, cpu);
+			load = get_load(cpufreq_device, cpu, i);
 		else
 			load = 0;
 
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index be4eedcb839a..9043f8f91852 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -475,14 +475,10 @@ thermal_zone_of_sensor_register(struct device *dev, int sensor_id, void *data,
 
 	sensor_np = of_node_get(dev->of_node);
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct of_phandle_args sensor_specs;
 		int ret, id;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		/* For now, thermal framework supports only 1 sensor per zone */
 		ret = of_parse_phandle_with_args(child, "thermal-sensors",
 						 "#thermal-sensor-cells",
@@ -881,16 +877,12 @@ int __init of_parse_thermal_zones(void)
 		return 0; /* Run successfully on systems without thermal DT */
 	}
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 		struct thermal_zone_params *tzp;
 		int i, mask = 0;
 		u32 prop;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		tz = thermal_of_build_thermal_zone(child);
 		if (IS_ERR(tz)) {
 			pr_err("failed to build thermal zone %s: %ld\n",
@@ -968,13 +960,9 @@ void of_thermal_destroy_zones(void)
 		return;
 	}
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		zone = thermal_zone_get_zone_by_name(child->name);
 		if (IS_ERR(zone))
 			continue;
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 44b9c485157d..0e735acea33a 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/reboot.h>
@@ -75,8 +76,10 @@ struct rcar_thermal_priv {
 #define rcar_has_irq_support(priv)	((priv)->common->base)
 #define rcar_id_to_shift(priv)		((priv)->id * 8)
 
+#define USE_OF_THERMAL	1
 static const struct of_device_id rcar_thermal_dt_ids[] = {
 	{ .compatible = "renesas,rcar-thermal", },
+	{ .compatible = "renesas,rcar-gen2-thermal", .data = (void *)USE_OF_THERMAL },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rcar_thermal_dt_ids);
@@ -200,9 +203,9 @@ err_out_unlock:
 	return ret;
 }
 
-static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
+static int rcar_thermal_get_current_temp(struct rcar_thermal_priv *priv,
+					 int *temp)
 {
-	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
 	int tmp;
 	int ret;
 
@@ -226,6 +229,20 @@ static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
 	return 0;
 }
 
+static int rcar_thermal_of_get_temp(void *data, int *temp)
+{
+	struct rcar_thermal_priv *priv = data;
+
+	return rcar_thermal_get_current_temp(priv, temp);
+}
+
+static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
+{
+	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
+
+	return rcar_thermal_get_current_temp(priv, temp);
+}
+
 static int rcar_thermal_get_trip_type(struct thermal_zone_device *zone,
 				      int trip, enum thermal_trip_type *type)
 {
@@ -282,6 +299,10 @@ static int rcar_thermal_notify(struct thermal_zone_device *zone,
 	return 0;
 }
 
+static const struct thermal_zone_of_device_ops rcar_thermal_zone_of_ops = {
+	.get_temp	= rcar_thermal_of_get_temp,
+};
+
 static struct thermal_zone_device_ops rcar_thermal_zone_ops = {
 	.get_temp	= rcar_thermal_get_temp,
 	.get_trip_type	= rcar_thermal_get_trip_type,
@@ -318,14 +339,20 @@ static void rcar_thermal_work(struct work_struct *work)
 
 	priv = container_of(work, struct rcar_thermal_priv, work.work);
 
-	rcar_thermal_get_temp(priv->zone, &cctemp);
+	ret = rcar_thermal_get_current_temp(priv, &cctemp);
+	if (ret < 0)
+		return;
+
 	ret = rcar_thermal_update_temp(priv);
 	if (ret < 0)
 		return;
 
 	rcar_thermal_irq_enable(priv);
 
-	rcar_thermal_get_temp(priv->zone, &nctemp);
+	ret = rcar_thermal_get_current_temp(priv, &nctemp);
+	if (ret < 0)
+		return;
+
 	if (nctemp != cctemp)
 		thermal_zone_device_update(priv->zone);
 }
@@ -403,6 +430,8 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 	struct rcar_thermal_priv *priv;
 	struct device *dev = &pdev->dev;
 	struct resource *res, *irq;
+	const struct of_device_id *of_id = of_match_device(rcar_thermal_dt_ids, dev);
+	unsigned long of_data = (unsigned long)of_id->data;
 	int mres = 0;
 	int i;
 	int ret = -ENODEV;
@@ -463,7 +492,13 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 		if (ret < 0)
 			goto error_unregister;
 
-		priv->zone = thermal_zone_device_register("rcar_thermal",
+		if (of_data == USE_OF_THERMAL)
+			priv->zone = thermal_zone_of_sensor_register(
+						dev, i, priv,
+						&rcar_thermal_zone_of_ops);
+		else
+			priv->zone = thermal_zone_device_register(
+						"rcar_thermal",
 						1, 0, priv,
 						&rcar_thermal_zone_ops, NULL, 0,
 						idle);
diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c
index 534dd9136662..81b35aace9de 100644
--- a/drivers/thermal/spear_thermal.c
+++ b/drivers/thermal/spear_thermal.c
@@ -54,8 +54,7 @@ static struct thermal_zone_device_ops ops = {
 	.get_temp = thermal_get_temp,
 };
 
-#ifdef CONFIG_PM
-static int spear_thermal_suspend(struct device *dev)
+static int __maybe_unused spear_thermal_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
@@ -72,7 +71,7 @@ static int spear_thermal_suspend(struct device *dev)
 	return 0;
 }
 
-static int spear_thermal_resume(struct device *dev)
+static int __maybe_unused spear_thermal_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
@@ -94,7 +93,6 @@ static int spear_thermal_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
 static SIMPLE_DEV_PM_OPS(spear_thermal_pm_ops, spear_thermal_suspend,
 		spear_thermal_resume);
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index b3110040164a..2348fa613707 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -681,7 +681,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
 /* this is called once with whichever end is closed last */
 static void pty_unix98_shutdown(struct tty_struct *tty)
 {
-	devpts_kill_index(tty->driver_data, tty->index);
+	struct inode *ptmx_inode;
+
+	if (tty->driver->subtype == PTY_TYPE_MASTER)
+		ptmx_inode = tty->driver_data;
+	else
+		ptmx_inode = tty->link->driver_data;
+	devpts_kill_index(ptmx_inode, tty->index);
+	devpts_del_ref(ptmx_inode);
 }
 
 static const struct tty_operations ptm_unix98_ops = {
@@ -773,6 +780,18 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
 	tty->driver_data = inode;
 
+	/*
+	 * In the case where all references to ptmx inode are dropped and we
+	 * still have /dev/tty opened pointing to the master/slave pair (ptmx
+	 * is closed/released before /dev/tty), we must make sure that the inode
+	 * is still valid when we call the final pty_unix98_shutdown, thus we
+	 * hold an additional reference to the ptmx inode. For the same /dev/tty
+	 * last close case, we also need to make sure the super_block isn't
+	 * destroyed (devpts instance unmounted), before /dev/tty is closed and
+	 * on its release devpts_kill_index is called.
+	 */
+	devpts_add_ref(inode);
+
 	tty_add_file(tty, filp);
 
 	slave_inode = devpts_pty_new(inode,
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index e71ec78fc11e..7cd6f9a90542 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1941,6 +1941,7 @@ pci_wch_ch38x_setup(struct serial_private *priv,
 #define PCIE_VENDOR_ID_WCH		0x1c00
 #define PCIE_DEVICE_ID_WCH_CH382_2S1P	0x3250
 #define PCIE_DEVICE_ID_WCH_CH384_4S	0x3470
+#define PCIE_DEVICE_ID_WCH_CH382_2S	0x3253
 
 #define PCI_VENDOR_ID_PERICOM			0x12D8
 #define PCI_DEVICE_ID_PERICOM_PI7C9X7951	0x7951
@@ -2637,6 +2638,14 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_wch_ch353_setup,
 	},
+	/* WCH CH382 2S card (16850 clone) */
+	{
+		.vendor         = PCIE_VENDOR_ID_WCH,
+		.device         = PCIE_DEVICE_ID_WCH_CH382_2S,
+		.subvendor      = PCI_ANY_ID,
+		.subdevice      = PCI_ANY_ID,
+		.setup          = pci_wch_ch38x_setup,
+	},
 	/* WCH CH382 2S1P card (16850 clone) */
 	{
 		.vendor         = PCIE_VENDOR_ID_WCH,
@@ -2955,6 +2964,7 @@ enum pci_board_num_t {
 	pbn_fintek_4,
 	pbn_fintek_8,
 	pbn_fintek_12,
+	pbn_wch382_2,
 	pbn_wch384_4,
 	pbn_pericom_PI7C9X7951,
 	pbn_pericom_PI7C9X7952,
@@ -3775,6 +3785,13 @@ static struct pciserial_board pci_boards[] = {
 		.base_baud	= 115200,
 		.first_offset	= 0x40,
 	},
+	[pbn_wch382_2] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 2,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+		.first_offset	= 0xC0,
+	},
 	[pbn_wch384_4] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 4,
@@ -5574,6 +5591,10 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_2_115200 },
 
+	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0, pbn_wch382_2 },
+
 	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_4 },
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index b645f9228ed7..fa49eb1e2fa2 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1165,7 +1165,7 @@ serial_omap_type(struct uart_port *port)
 
 #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
 
-static void wait_for_xmitr(struct uart_omap_port *up)
+static void __maybe_unused wait_for_xmitr(struct uart_omap_port *up)
 {
 	unsigned int status, tmout = 10000;
 
@@ -1343,7 +1343,7 @@ static inline void serial_omap_add_console_port(struct uart_omap_port *up)
 
 /* Enable or disable the rs485 support */
 static int
-serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf)
+serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485)
 {
 	struct uart_omap_port *up = to_uart_omap_port(port);
 	unsigned int mode;
@@ -1356,8 +1356,12 @@ serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf)
 	up->ier = 0;
 	serial_out(up, UART_IER, 0);
 
+	/* Clamp the delays to [0, 100ms] */
+	rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U);
+	rs485->delay_rts_after_send  = min(rs485->delay_rts_after_send, 100U);
+
 	/* store new config */
-	port->rs485 = *rs485conf;
+	port->rs485 = *rs485;
 
 	/*
 	 * Just as a precaution, only allow rs485
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 5cec01c75691..a7eacef1bd22 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2066,13 +2066,12 @@ retry_open:
 		if (tty) {
 			mutex_unlock(&tty_mutex);
 			retval = tty_lock_interruptible(tty);
+			tty_kref_put(tty);  /* drop kref from tty_driver_lookup_tty() */
 			if (retval) {
 				if (retval == -EINTR)
 					retval = -ERESTARTSYS;
 				goto err_unref;
 			}
-			/* safe to drop the kref from tty_driver_lookup_tty() */
-			tty_kref_put(tty);
 			retval = tty_reopen(tty);
 			if (retval < 0) {
 				tty_unlock(tty);
diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c
index d2f3c4cd697f..dfa9ec03fa8e 100644
--- a/drivers/tty/tty_mutex.c
+++ b/drivers/tty/tty_mutex.c
@@ -21,10 +21,15 @@ EXPORT_SYMBOL(tty_lock);
 
 int tty_lock_interruptible(struct tty_struct *tty)
 {
+	int ret;
+
 	if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty))
 		return -EIO;
 	tty_kref_get(tty);
-	return mutex_lock_interruptible(&tty->legacy_mutex);
+	ret = mutex_lock_interruptible(&tty->legacy_mutex);
+	if (ret)
+		tty_kref_put(tty);
+	return ret;
 }
 
 void __lockfunc tty_unlock(struct tty_struct *tty)
diff --git a/drivers/usb/chipidea/ci_hdrc_pci.c b/drivers/usb/chipidea/ci_hdrc_pci.c
index b59195edf636..b635ab67490d 100644
--- a/drivers/usb/chipidea/ci_hdrc_pci.c
+++ b/drivers/usb/chipidea/ci_hdrc_pci.c
@@ -85,8 +85,8 @@ static int ci_hdrc_pci_probe(struct pci_dev *pdev,
 
 	/* register a nop PHY */
 	ci->phy = usb_phy_generic_register();
-	if (!ci->phy)
-		return -ENOMEM;
+	if (IS_ERR(ci->phy))
+		return PTR_ERR(ci->phy);
 
 	memset(res, 0, sizeof(res));
 	res[0].start	= pci_resource_start(pdev, 0);
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index a4f7db2e18dd..df47110bad2d 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -100,6 +100,9 @@ static ssize_t ci_port_test_write(struct file *file, const char __user *ubuf,
 	if (sscanf(buf, "%u", &mode) != 1)
 		return -EINVAL;
 
+	if (mode > 255)
+		return -EBADRQC;
+
 	pm_runtime_get_sync(ci->dev);
 	spin_lock_irqsave(&ci->lock, flags);
 	ret = hw_port_test_set(ci, mode);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 350dcd9af5d8..51b436918f78 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5401,6 +5401,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	}
 
 	bos = udev->bos;
+	udev->bos = NULL;
 
 	for (i = 0; i < SET_CONFIG_TRIES; ++i) {
 
@@ -5493,11 +5494,8 @@ done:
 	usb_set_usb2_hardware_lpm(udev, 1);
 	usb_unlocked_enable_lpm(udev);
 	usb_enable_ltm(udev);
-	/* release the new BOS descriptor allocated  by hub_port_init() */
-	if (udev->bos != bos) {
-		usb_release_bos_descriptor(udev);
-		udev->bos = bos;
-	}
+	usb_release_bos_descriptor(udev);
+	udev->bos = bos;
 	return 0;
 
 re_enumerate:
diff --git a/drivers/usb/dwc2/Kconfig b/drivers/usb/dwc2/Kconfig
index fd95ba6ec317..f0decc0d69b5 100644
--- a/drivers/usb/dwc2/Kconfig
+++ b/drivers/usb/dwc2/Kconfig
@@ -1,5 +1,6 @@
 config USB_DWC2
 	tristate "DesignWare USB2 DRD Core Support"
+	depends on HAS_DMA
 	depends on USB || USB_GADGET
 	help
 	  Say Y here if your system has a Dual Role Hi-Speed USB
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index e991d55914db..46c4ba75dc2a 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -619,6 +619,12 @@ void dwc2_force_dr_mode(struct dwc2_hsotg *hsotg)
 			 __func__, hsotg->dr_mode);
 		break;
 	}
+
+	/*
+	 * NOTE: This is required for some rockchip soc based
+	 * platforms.
+	 */
+	msleep(50);
 }
 
 /*
diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c
index 36606fc33c0d..a41274aa52ad 100644
--- a/drivers/usb/dwc2/hcd_ddma.c
+++ b/drivers/usb/dwc2/hcd_ddma.c
@@ -1174,14 +1174,11 @@ static int dwc2_process_non_isoc_desc(struct dwc2_hsotg *hsotg,
 	failed = dwc2_update_non_isoc_urb_state_ddma(hsotg, chan, qtd, dma_desc,
 						     halt_status, n_bytes,
 						     xfer_done);
-	if (*xfer_done && urb->status != -EINPROGRESS)
-		failed = 1;
-
-	if (failed) {
+	if (failed || (*xfer_done && urb->status != -EINPROGRESS)) {
 		dwc2_host_complete(hsotg, qtd, urb->status);
 		dwc2_hcd_qtd_unlink_and_free(hsotg, qtd, qh);
-		dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x status=%08x\n",
-			 failed, *xfer_done, urb->status);
+		dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x\n",
+			 failed, *xfer_done);
 		return failed;
 	}
 
@@ -1236,21 +1233,23 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg,
 
 	list_for_each_safe(qtd_item, qtd_tmp, &qh->qtd_list) {
 		int i;
+		int qtd_desc_count;
 
 		qtd = list_entry(qtd_item, struct dwc2_qtd, qtd_list_entry);
 		xfer_done = 0;
+		qtd_desc_count = qtd->n_desc;
 
-		for (i = 0; i < qtd->n_desc; i++) {
+		for (i = 0; i < qtd_desc_count; i++) {
 			if (dwc2_process_non_isoc_desc(hsotg, chan, chnum, qtd,
 						       desc_num, halt_status,
-						       &xfer_done)) {
-				qtd = NULL;
-				break;
-			}
+						       &xfer_done))
+				goto stop_scan;
+
 			desc_num++;
 		}
 	}
 
+stop_scan:
 	if (qh->ep_type != USB_ENDPOINT_XFER_CONTROL) {
 		/*
 		 * Resetting the data toggle for bulk and interrupt endpoints
@@ -1258,7 +1257,7 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg,
 		 */
 		if (halt_status == DWC2_HC_XFER_STALL)
 			qh->data_toggle = DWC2_HC_PID_DATA0;
-		else if (qtd)
+		else
 			dwc2_hcd_save_data_toggle(hsotg, chan, chnum, qtd);
 	}
 
diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c
index f8253803a050..cadba8b13c48 100644
--- a/drivers/usb/dwc2/hcd_intr.c
+++ b/drivers/usb/dwc2/hcd_intr.c
@@ -525,11 +525,19 @@ void dwc2_hcd_save_data_toggle(struct dwc2_hsotg *hsotg,
 	u32 pid = (hctsiz & TSIZ_SC_MC_PID_MASK) >> TSIZ_SC_MC_PID_SHIFT;
 
 	if (chan->ep_type != USB_ENDPOINT_XFER_CONTROL) {
+		if (WARN(!chan || !chan->qh,
+			 "chan->qh must be specified for non-control eps\n"))
+			return;
+
 		if (pid == TSIZ_SC_MC_PID_DATA0)
 			chan->qh->data_toggle = DWC2_HC_PID_DATA0;
 		else
 			chan->qh->data_toggle = DWC2_HC_PID_DATA1;
 	} else {
+		if (WARN(!qtd,
+			 "qtd must be specified for control eps\n"))
+			return;
+
 		if (pid == TSIZ_SC_MC_PID_DATA0)
 			qtd->data_toggle = DWC2_HC_PID_DATA0;
 		else
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 29130682e547..e4f8b90d9627 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -856,7 +856,6 @@ struct dwc3 {
 	unsigned		pullups_connected:1;
 	unsigned		resize_fifos:1;
 	unsigned		setup_packet_pending:1;
-	unsigned		start_config_issued:1;
 	unsigned		three_stage_setup:1;
 	unsigned		usb3_lpm_capable:1;
 
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 3a9354abcb68..8d6b75c2f53b 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -555,7 +555,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
 	int ret;
 	u32 reg;
 
-	dwc->start_config_issued = false;
 	cfg = le16_to_cpu(ctrl->wValue);
 
 	switch (state) {
@@ -737,10 +736,6 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
 		dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY");
 		ret = dwc3_ep0_set_isoch_delay(dwc, ctrl);
 		break;
-	case USB_REQ_SET_INTERFACE:
-		dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_INTERFACE");
-		dwc->start_config_issued = false;
-		/* Fall through */
 	default:
 		dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver");
 		ret = dwc3_ep0_delegate_req(dwc, ctrl);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 7d1dd82a95ac..2363bad45af8 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -385,24 +385,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep)
 	dep->trb_pool_dma = 0;
 }
 
+static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep);
+
+/**
+ * dwc3_gadget_start_config - Configure EP resources
+ * @dwc: pointer to our controller context structure
+ * @dep: endpoint that is being enabled
+ *
+ * The assignment of transfer resources cannot perfectly follow the
+ * data book due to the fact that the controller driver does not have
+ * all knowledge of the configuration in advance. It is given this
+ * information piecemeal by the composite gadget framework after every
+ * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook
+ * programming model in this scenario can cause errors. For two
+ * reasons:
+ *
+ * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION
+ * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of
+ * multiple interfaces.
+ *
+ * 2) The databook does not mention doing more DEPXFERCFG for new
+ * endpoint on alt setting (8.1.6).
+ *
+ * The following simplified method is used instead:
+ *
+ * All hardware endpoints can be assigned a transfer resource and this
+ * setting will stay persistent until either a core reset or
+ * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and
+ * do DEPXFERCFG for every hardware endpoint as well. We are
+ * guaranteed that there are as many transfer resources as endpoints.
+ *
+ * This function is called for each endpoint when it is being enabled
+ * but is triggered only when called for EP0-out, which always happens
+ * first, and which should only happen in one of the above conditions.
+ */
 static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep)
 {
 	struct dwc3_gadget_ep_cmd_params params;
 	u32			cmd;
+	int			i;
+	int			ret;
+
+	if (dep->number)
+		return 0;
 
 	memset(&params, 0x00, sizeof(params));
+	cmd = DWC3_DEPCMD_DEPSTARTCFG;
 
-	if (dep->number != 1) {
-		cmd = DWC3_DEPCMD_DEPSTARTCFG;
-		/* XferRscIdx == 0 for ep0 and 2 for the remaining */
-		if (dep->number > 1) {
-			if (dwc->start_config_issued)
-				return 0;
-			dwc->start_config_issued = true;
-			cmd |= DWC3_DEPCMD_PARAM(2);
-		}
+	ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, &params);
+	if (ret)
+		return ret;
 
-		return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, &params);
+	for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) {
+		struct dwc3_ep *dep = dwc->eps[i];
+
+		if (!dep)
+			continue;
+
+		ret = dwc3_gadget_set_xfer_resource(dwc, dep);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -516,10 +558,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 		struct dwc3_trb	*trb_st_hw;
 		struct dwc3_trb	*trb_link;
 
-		ret = dwc3_gadget_set_xfer_resource(dwc, dep);
-		if (ret)
-			return ret;
-
 		dep->endpoint.desc = desc;
 		dep->comp_desc = comp_desc;
 		dep->type = usb_endpoint_type(desc);
@@ -1636,8 +1674,6 @@ static int dwc3_gadget_start(struct usb_gadget *g,
 	}
 	dwc3_writel(dwc->regs, DWC3_DCFG, reg);
 
-	dwc->start_config_issued = false;
-
 	/* Start with SuperSpeed Default */
 	dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512);
 
@@ -2237,7 +2273,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc)
 	dwc3_writel(dwc->regs, DWC3_DCTL, reg);
 
 	dwc3_disconnect_gadget(dwc);
-	dwc->start_config_issued = false;
 
 	dwc->gadget.speed = USB_SPEED_UNKNOWN;
 	dwc->setup_packet_pending = false;
@@ -2288,7 +2323,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc)
 
 	dwc3_stop_active_transfers(dwc);
 	dwc3_clear_stall_all_ep(dwc);
-	dwc->start_config_issued = false;
 
 	/* Reset device address to zero */
 	reg = dwc3_readl(dwc->regs, DWC3_DCFG);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 7e179f81d05c..87fb0fd6aaab 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -130,7 +130,8 @@ struct dev_data {
 					setup_can_stall : 1,
 					setup_out_ready : 1,
 					setup_out_error : 1,
-					setup_abort : 1;
+					setup_abort : 1,
+					gadget_registered : 1;
 	unsigned			setup_wLength;
 
 	/* the rest is basically write-once */
@@ -1179,7 +1180,8 @@ dev_release (struct inode *inode, struct file *fd)
 
 	/* closing ep0 === shutdown all */
 
-	usb_gadget_unregister_driver (&gadgetfs_driver);
+	if (dev->gadget_registered)
+		usb_gadget_unregister_driver (&gadgetfs_driver);
 
 	/* at this point "good" hardware has disconnected the
 	 * device from USB; the host won't see it any more.
@@ -1847,6 +1849,7 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 		 * kick in after the ep0 descriptor is closed.
 		 */
 		value = len;
+		dev->gadget_registered = true;
 	}
 	return value;
 
diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c
index 53c0692f1b09..93d28cb00b76 100644
--- a/drivers/usb/gadget/udc/fsl_qe_udc.c
+++ b/drivers/usb/gadget/udc/fsl_qe_udc.c
@@ -2340,7 +2340,7 @@ static struct qe_udc *qe_udc_config(struct platform_device *ofdev)
 {
 	struct qe_udc *udc;
 	struct device_node *np = ofdev->dev.of_node;
-	unsigned int tmp_addr = 0;
+	unsigned long tmp_addr = 0;
 	struct usb_device_para __iomem *usbpram;
 	unsigned int i;
 	u64 size;
diff --git a/drivers/usb/gadget/udc/net2280.h b/drivers/usb/gadget/udc/net2280.h
index 4dff60d34f73..0d32052bf16f 100644
--- a/drivers/usb/gadget/udc/net2280.h
+++ b/drivers/usb/gadget/udc/net2280.h
@@ -369,9 +369,20 @@ static inline void set_max_speed(struct net2280_ep *ep, u32 max)
 	static const u32 ep_enhanced[9] = { 0x10, 0x60, 0x30, 0x80,
 					  0x50, 0x20, 0x70, 0x40, 0x90 };
 
-	if (ep->dev->enhanced_mode)
+	if (ep->dev->enhanced_mode) {
 		reg = ep_enhanced[ep->num];
-	else{
+		switch (ep->dev->gadget.speed) {
+		case USB_SPEED_SUPER:
+			reg += 2;
+			break;
+		case USB_SPEED_FULL:
+			reg += 1;
+			break;
+		case USB_SPEED_HIGH:
+		default:
+			break;
+		}
+	} else {
 		reg = (ep->num + 1) * 0x10;
 		if (ep->dev->gadget.speed != USB_SPEED_HIGH)
 			reg += 1;
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index fd73a3ea07c2..b86a6f03592e 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -413,9 +413,10 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
 		if (!driver->udc_name || strcmp(driver->udc_name,
 						dev_name(&udc->dev)) == 0) {
 			ret = udc_bind_to_driver(udc, driver);
+			if (ret != -EPROBE_DEFER)
+				list_del(&driver->pending);
 			if (ret)
 				goto err4;
-			list_del(&driver->pending);
 			break;
 		}
 	}
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 795a45b1b25b..58487a473521 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -662,7 +662,7 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
 		csr &= ~(MUSB_TXCSR_AUTOSET | MUSB_TXCSR_DMAMODE);
 		csr |= MUSB_TXCSR_DMAENAB; /* against programmer's guide */
 	}
-	channel->desired_mode = mode;
+	channel->desired_mode = *mode;
 	musb_writew(epio, MUSB_TXCSR, csr);
 
 	return 0;
@@ -2003,10 +2003,8 @@ void musb_host_rx(struct musb *musb, u8 epnum)
 				qh->offset,
 				urb->transfer_buffer_length);
 
-			done = musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh,
-							      urb, xfer_len,
-							      iso_err);
-			if (done)
+			if (musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, urb,
+							   xfer_len, iso_err))
 				goto finish;
 			else
 				dev_err(musb->controller, "error: rx_dma failed\n");
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 970a30e155cb..72b387d592c2 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -757,14 +757,8 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 	otg->host = host;
 	dev_dbg(otg->usb_phy->dev, "host driver registered w/ tranceiver\n");
 
-	/*
-	 * Kick the state machine work, if peripheral is not supported
-	 * or peripheral is already registered with us.
-	 */
-	if (motg->pdata->mode == USB_DR_MODE_HOST || otg->gadget) {
-		pm_runtime_get_sync(otg->usb_phy->dev);
-		schedule_work(&motg->sm_work);
-	}
+	pm_runtime_get_sync(otg->usb_phy->dev);
+	schedule_work(&motg->sm_work);
 
 	return 0;
 }
@@ -827,14 +821,8 @@ static int msm_otg_set_peripheral(struct usb_otg *otg,
 	dev_dbg(otg->usb_phy->dev,
 		"peripheral driver registered w/ tranceiver\n");
 
-	/*
-	 * Kick the state machine work, if host is not supported
-	 * or host is already registered with us.
-	 */
-	if (motg->pdata->mode == USB_DR_MODE_PERIPHERAL || otg->host) {
-		pm_runtime_get_sync(otg->usb_phy->dev);
-		schedule_work(&motg->sm_work);
-	}
+	pm_runtime_get_sync(otg->usb_phy->dev);
+	schedule_work(&motg->sm_work);
 
 	return 0;
 }
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 987813b8a7f9..7c319e7edda2 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -163,6 +163,8 @@ static const struct usb_device_id id_table[] = {
 	{ 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(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */
+	{ USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
 	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
 	{ USB_DEVICE(0x1BA4, 0x0002) },	/* Silicon Labs 358x factory default */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index db86e512e0fc..8849439a8f18 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -315,6 +315,7 @@ static void option_instat_callback(struct urb *urb);
 #define TOSHIBA_PRODUCT_G450			0x0d45
 
 #define ALINK_VENDOR_ID				0x1e0e
+#define SIMCOM_PRODUCT_SIM7100E			0x9001 /* Yes, ALINK_VENDOR_ID */
 #define ALINK_PRODUCT_PH300			0x9100
 #define ALINK_PRODUCT_3GU			0x9200
 
@@ -607,6 +608,10 @@ static const struct option_blacklist_info zte_1255_blacklist = {
 	.reserved = BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info simcom_sim7100e_blacklist = {
+	.reserved = BIT(5) | BIT(6),
+};
+
 static const struct option_blacklist_info telit_le910_blacklist = {
 	.sendsetup = BIT(0),
 	.reserved = BIT(1) | BIT(2),
@@ -1122,6 +1127,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) },
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUALCOMM_VENDOR_ID, 0x6001, 0xff, 0xff, 0xff), /* 4G LTE usb-modem U901 */
+	  .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
@@ -1645,6 +1652,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(ALINK_VENDOR_ID, 0x9000) },
 	{ USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E),
+	  .driver_info = (kernel_ulong_t)&simcom_sim7100e_blacklist },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
 	  .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist
 	},
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index 0081725c6b5b..6b2a06d09f2b 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -152,7 +152,7 @@ static void lcdc_write(unsigned int val, unsigned int addr)
 
 struct da8xx_fb_par {
 	struct device		*dev;
-	resource_size_t p_palette_base;
+	dma_addr_t		p_palette_base;
 	unsigned char *v_palette_base;
 	dma_addr_t		vram_phys;
 	unsigned long		vram_size;
@@ -1428,7 +1428,7 @@ static int fb_probe(struct platform_device *device)
 
 	par->vram_virt = dma_alloc_coherent(NULL,
 					    par->vram_size,
-					    (resource_size_t *) &par->vram_phys,
+					    &par->vram_phys,
 					    GFP_KERNEL | GFP_DMA);
 	if (!par->vram_virt) {
 		dev_err(&device->dev,
@@ -1448,7 +1448,7 @@ static int fb_probe(struct platform_device *device)
 
 	/* allocate palette buffer */
 	par->v_palette_base = dma_zalloc_coherent(NULL, PALETTE_SIZE,
-						  (resource_size_t *)&par->p_palette_base,
+						  &par->p_palette_base,
 						  GFP_KERNEL | GFP_DMA);
 	if (!par->v_palette_base) {
 		dev_err(&device->dev,
diff --git a/drivers/video/fbdev/exynos/s6e8ax0.c b/drivers/video/fbdev/exynos/s6e8ax0.c
index 95873f26e39c..de2f3e793786 100644
--- a/drivers/video/fbdev/exynos/s6e8ax0.c
+++ b/drivers/video/fbdev/exynos/s6e8ax0.c
@@ -829,8 +829,7 @@ static int s6e8ax0_probe(struct mipi_dsim_lcd_device *dsim_dev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
+static int __maybe_unused s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
 {
 	struct s6e8ax0 *lcd = dev_get_drvdata(&dsim_dev->dev);
 
@@ -843,7 +842,7 @@ static int s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
 	return 0;
 }
 
-static int s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
+static int __maybe_unused s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
 {
 	struct s6e8ax0 *lcd = dev_get_drvdata(&dsim_dev->dev);
 
@@ -855,10 +854,6 @@ static int s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
 
 	return 0;
 }
-#else
-#define s6e8ax0_suspend		NULL
-#define s6e8ax0_resume		NULL
-#endif
 
 static struct mipi_dsim_lcd_driver s6e8ax0_dsim_ddi_driver = {
 	.name = "s6e8ax0",
@@ -867,8 +862,8 @@ static struct mipi_dsim_lcd_driver s6e8ax0_dsim_ddi_driver = {
 	.power_on = s6e8ax0_power_on,
 	.set_sequence = s6e8ax0_set_sequence,
 	.probe = s6e8ax0_probe,
-	.suspend = s6e8ax0_suspend,
-	.resume = s6e8ax0_resume,
+	.suspend = IS_ENABLED(CONFIG_PM) ? s6e8ax0_suspend : NULL,
+	.resume = IS_ENABLED(CONFIG_PM) ? s6e8ax0_resume : NULL,
 };
 
 static int s6e8ax0_init(void)
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index cee88603efc9..bb2f1e866020 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -902,6 +902,21 @@ static int imxfb_probe(struct platform_device *pdev)
 		goto failed_getclock;
 	}
 
+	/*
+	 * The LCDC controller does not have an enable bit. The
+	 * controller starts directly when the clocks are enabled.
+	 * If the clocks are enabled when the controller is not yet
+	 * programmed with proper register values (enabled at the
+	 * bootloader, for example) then it just goes into some undefined
+	 * state.
+	 * To avoid this issue, let's enable and disable LCDC IPG clock
+	 * so that we force some kind of 'reset' to the LCDC block.
+	 */
+	ret = clk_prepare_enable(fbi->clk_ipg);
+	if (ret)
+		goto failed_getclock;
+	clk_disable_unprepare(fbi->clk_ipg);
+
 	fbi->clk_ahb = devm_clk_get(&pdev->dev, "ahb");
 	if (IS_ERR(fbi->clk_ahb)) {
 		ret = PTR_ERR(fbi->clk_ahb);
diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
index de54a4748065..b6f83d5df9fd 100644
--- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
+++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
@@ -503,8 +503,7 @@ static int mmphw_probe(struct platform_device *pdev)
 	ctrl->reg_base = devm_ioremap_nocache(ctrl->dev,
 			res->start, resource_size(res));
 	if (ctrl->reg_base == NULL) {
-		dev_err(ctrl->dev, "%s: res %x - %x map failed\n", __func__,
-			res->start, res->end);
+		dev_err(ctrl->dev, "%s: res %pR map failed\n", __func__, res);
 		ret = -ENOMEM;
 		goto failed;
 	}
diff --git a/drivers/video/fbdev/ocfb.c b/drivers/video/fbdev/ocfb.c
index c9293aea8ec3..a970edc2a6f8 100644
--- a/drivers/video/fbdev/ocfb.c
+++ b/drivers/video/fbdev/ocfb.c
@@ -123,11 +123,11 @@ static int ocfb_setupfb(struct ocfb_dev *fbdev)
 
 	/* Horizontal timings */
 	ocfb_writereg(fbdev, OCFB_HTIM, (var->hsync_len - 1) << 24 |
-		      (var->right_margin - 1) << 16 | (var->xres - 1));
+		      (var->left_margin - 1) << 16 | (var->xres - 1));
 
 	/* Vertical timings */
 	ocfb_writereg(fbdev, OCFB_VTIM, (var->vsync_len - 1) << 24 |
-		      (var->lower_margin - 1) << 16 | (var->yres - 1));
+		      (var->upper_margin - 1) << 16 | (var->yres - 1));
 
 	/* Total length of frame */
 	hlen = var->left_margin + var->right_margin + var->hsync_len +
diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index 73dafdc494aa..fb0221434f81 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -227,8 +227,9 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
 	/*
 	 * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able
 	 * to access the BARs where the MSI-X entries reside.
+	 * But VF devices are unique in which the PF needs to be checked.
 	 */
-	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd);
 	if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY))
 		return -ENXIO;
 
@@ -332,6 +333,9 @@ void xen_pcibk_do_op(struct work_struct *data)
 	struct xen_pcibk_dev_data *dev_data = NULL;
 	struct xen_pci_op *op = &pdev->op;
 	int test_intx = 0;
+#ifdef CONFIG_PCI_MSI
+	unsigned int nr = 0;
+#endif
 
 	*op = pdev->sh_info->op;
 	barrier();
@@ -360,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data)
 			op->err = xen_pcibk_disable_msi(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_enable_msix:
+			nr = op->value;
 			op->err = xen_pcibk_enable_msix(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_disable_msix:
@@ -382,7 +387,7 @@ void xen_pcibk_do_op(struct work_struct *data)
 	if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) {
 		unsigned int i;
 
-		for (i = 0; i < op->value; i++)
+		for (i = 0; i < nr; i++)
 			pdev->sh_info->op.msix_entries[i].vector =
 				op->msix_entries[i].vector;
 	}
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index ad4eb1024d1f..c46ee189466f 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -849,15 +849,31 @@ static int scsiback_map(struct vscsibk_info *info)
 }
 
 /*
+  Check for a translation entry being present
+*/
+static struct v2p_entry *scsiback_chk_translation_entry(
+	struct vscsibk_info *info, struct ids_tuple *v)
+{
+	struct list_head *head = &(info->v2p_entry_lists);
+	struct v2p_entry *entry;
+
+	list_for_each_entry(entry, head, l)
+		if ((entry->v.chn == v->chn) &&
+		    (entry->v.tgt == v->tgt) &&
+		    (entry->v.lun == v->lun))
+			return entry;
+
+	return NULL;
+}
+
+/*
   Add a new translation entry
 */
 static int scsiback_add_translation_entry(struct vscsibk_info *info,
 					  char *phy, struct ids_tuple *v)
 {
 	int err = 0;
-	struct v2p_entry *entry;
 	struct v2p_entry *new;
-	struct list_head *head = &(info->v2p_entry_lists);
 	unsigned long flags;
 	char *lunp;
 	unsigned long long unpacked_lun;
@@ -917,15 +933,10 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info,
 	spin_lock_irqsave(&info->v2p_lock, flags);
 
 	/* Check double assignment to identical virtual ID */
-	list_for_each_entry(entry, head, l) {
-		if ((entry->v.chn == v->chn) &&
-		    (entry->v.tgt == v->tgt) &&
-		    (entry->v.lun == v->lun)) {
-			pr_warn("Virtual ID is already used. Assignment was not performed.\n");
-			err = -EEXIST;
-			goto out;
-		}
-
+	if (scsiback_chk_translation_entry(info, v)) {
+		pr_warn("Virtual ID is already used. Assignment was not performed.\n");
+		err = -EEXIST;
+		goto out;
 	}
 
 	/* Create a new translation entry and add to the list */
@@ -933,18 +944,18 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info,
 	new->v = *v;
 	new->tpg = tpg;
 	new->lun = unpacked_lun;
-	list_add_tail(&new->l, head);
+	list_add_tail(&new->l, &info->v2p_entry_lists);
 
 out:
 	spin_unlock_irqrestore(&info->v2p_lock, flags);
 
 out_free:
-	mutex_lock(&tpg->tv_tpg_mutex);
-	tpg->tv_tpg_fe_count--;
-	mutex_unlock(&tpg->tv_tpg_mutex);
-
-	if (err)
+	if (err) {
+		mutex_lock(&tpg->tv_tpg_mutex);
+		tpg->tv_tpg_fe_count--;
+		mutex_unlock(&tpg->tv_tpg_mutex);
 		kfree(new);
+	}
 
 	return err;
 }
@@ -956,39 +967,40 @@ static void __scsiback_del_translation_entry(struct v2p_entry *entry)
 }
 
 /*
-  Delete the translation entry specfied
+  Delete the translation entry specified
 */
 static int scsiback_del_translation_entry(struct vscsibk_info *info,
 					  struct ids_tuple *v)
 {
 	struct v2p_entry *entry;
-	struct list_head *head = &(info->v2p_entry_lists);
 	unsigned long flags;
+	int ret = 0;
 
 	spin_lock_irqsave(&info->v2p_lock, flags);
 	/* Find out the translation entry specified */
-	list_for_each_entry(entry, head, l) {
-		if ((entry->v.chn == v->chn) &&
-		    (entry->v.tgt == v->tgt) &&
-		    (entry->v.lun == v->lun)) {
-			goto found;
-		}
-	}
-
-	spin_unlock_irqrestore(&info->v2p_lock, flags);
-	return 1;
-
-found:
-	/* Delete the translation entry specfied */
-	__scsiback_del_translation_entry(entry);
+	entry = scsiback_chk_translation_entry(info, v);
+	if (entry)
+		__scsiback_del_translation_entry(entry);
+	else
+		ret = -ENOENT;
 
 	spin_unlock_irqrestore(&info->v2p_lock, flags);
-	return 0;
+	return ret;
 }
 
 static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state,
 				char *phy, struct ids_tuple *vir, int try)
 {
+	struct v2p_entry *entry;
+	unsigned long flags;
+
+	if (try) {
+		spin_lock_irqsave(&info->v2p_lock, flags);
+		entry = scsiback_chk_translation_entry(info, vir);
+		spin_unlock_irqrestore(&info->v2p_lock, flags);
+		if (entry)
+			return;
+	}
 	if (!scsiback_add_translation_entry(info, phy, vir)) {
 		if (xenbus_printf(XBT_NIL, info->dev->nodename, state,
 				  "%d", XenbusStateInitialised)) {
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 9433e46518c8..912b64edb42b 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -188,6 +188,8 @@ static int queue_reply(struct list_head *queue, const void *data, size_t len)
 
 	if (len == 0)
 		return 0;
+	if (len > XENSTORE_PAYLOAD_MAX)
+		return -EINVAL;
 
 	rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL);
 	if (rb == NULL)
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 0548c53f41d5..22fc7c802d69 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -511,8 +511,6 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 	pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino,
 		 page->index, to);
 	BUG_ON(to > PAGE_CACHE_SIZE);
-	kmap(page);
-	data = page_address(page);
 	bsize = AFFS_SB(sb)->s_data_blksize;
 	tmp = page->index << PAGE_CACHE_SHIFT;
 	bidx = tmp / bsize;
@@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, to - pos);
 		BUG_ON(pos + tmp > to || tmp > bsize);
+		data = kmap_atomic(page);
 		memcpy(data + pos, AFFS_DATA(bh) + boff, tmp);
+		kunmap_atomic(data);
 		affs_brelse(bh);
 		bidx++;
 		pos += tmp;
 		boff = 0;
 	}
 	flush_dcache_page(page);
-	kunmap(page);
 	return 0;
 }
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 051ea4809c14..7d914c67a9d0 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -653,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top)
 
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		random_variable = (unsigned long) get_random_int();
+		random_variable = get_random_long();
 		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
 	}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 39b3a174a425..826b164a4b5b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1201,7 +1201,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+			bdev->bd_inode->i_flags = S_DAX;
+		else
+			bdev->bd_inode->i_flags = 0;
+
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
@@ -1693,13 +1697,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	if (dax_mapping(mapping)) {
+		struct block_device *bdev = I_BDEV(mapping->host);
+
+		return dax_writeback_mapping_range(mapping, bdev, wbc);
+	}
+	return generic_writepages(mapping, wbc);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.readpages	= blkdev_readpages,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
-	.writepages	= generic_writepages,
+	.writepages	= blkdev_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 	.is_dirty_writeback = buffer_check_dirty_writeback,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b90cd3776f8e..f6dac40f87ff 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1406,7 +1406,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			read_extent_buffer(eb, dest + bytes_left,
 					   name_off, name_len);
 		if (eb != eb_in) {
-			btrfs_tree_read_unlock_blocking(eb);
+			if (!path->skip_locking)
+				btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
 		ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1426,9 +1427,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			if (!path->skip_locking)
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->nodes[0] = NULL;
+			path->locks[0] = 0;
 		}
 		btrfs_release_path(path);
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c473c42d7d6c..3346cd8f9910 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -637,11 +637,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	faili = nr_pages - 1;
 	cb->nr_pages = nr_pages;
 
-	/* In the parent-locked case, we only locked the range we are
-	 * interested in.  In all other cases, we can opportunistically
-	 * cache decompressed data that goes beyond the requested range. */
-	if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
-		add_ra_bio_pages(inode, em_start + em_len, cb);
+	add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
 	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 0be47e4b8136..b57daa895cea 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1689,7 +1689,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
  *
  */
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list)
+				    struct list_head *ins_list, bool *emitted)
 {
 	struct btrfs_dir_item *di;
 	struct btrfs_delayed_item *curr, *next;
@@ -1733,6 +1733,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 
 		if (over)
 			return 1;
+		*emitted = true;
 	}
 	return 0;
 }
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f25421..0167853c84ae 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list);
+				    struct list_head *ins_list, bool *emitted);
 
 /* for init */
 int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2e7c97a3f344..392592dc7010 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2897,12 +2897,11 @@ static int __do_readpage(struct extent_io_tree *tree,
 	struct block_device *bdev;
 	int ret;
 	int nr = 0;
-	int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
-	unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
+	unsigned long this_bio_flag = 0;
 
 	set_page_extent_mapped(page);
 
@@ -2942,18 +2941,16 @@ static int __do_readpage(struct extent_io_tree *tree,
 			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (!parent_locked)
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			break;
 		}
 		em = __get_extent_map(inode, page, pg_offset, cur,
 				      end - cur + 1, get_extent, em_cached);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, end);
+			unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
@@ -3038,12 +3035,9 @@ static int __do_readpage(struct extent_io_tree *tree,
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (parent_locked)
-				free_extent_state(cached);
-			else
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3052,8 +3046,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3063,8 +3056,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3083,8 +3075,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3213,20 +3204,6 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num)
-{
-	struct bio *bio = NULL;
-	unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
-	int ret;
-
-	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-			    &bio_flags, READ, NULL);
-	if (bio)
-		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
-	return ret;
-}
-
 static noinline void update_nr_written(struct page *page,
 				      struct writeback_control *wbc,
 				      unsigned long nr_written)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0377413bd4b9..880d5292e972 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -29,7 +29,6 @@
  */
 #define EXTENT_BIO_COMPRESSED 1
 #define EXTENT_BIO_TREE_LOG 2
-#define EXTENT_BIO_PARENT_LOCKED 4
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
@@ -210,8 +209,6 @@ static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5f06eb1f4384..d96f5cf38a2d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5717,6 +5717,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	char *name_ptr;
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
+	bool emitted;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5745,6 +5746,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (ret < 0)
 		goto err;
 
+	emitted = false;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -5824,6 +5826,7 @@ skip:
 
 			if (over)
 				goto nopos;
+			emitted = true;
 			di_len = btrfs_dir_name_len(leaf, di) +
 				 btrfs_dir_data_len(leaf, di) + sizeof(*di);
 			di_cur += di_len;
@@ -5836,11 +5839,20 @@ next:
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		if (is_curr)
 			ctx->pos++;
-		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
 		if (ret)
 			goto nopos;
 	}
 
+	/*
+	 * If we haven't emitted any dir entry, we must not touch ctx->pos as
+	 * it was was set to the termination value in previous call. We assume
+	 * that "." and ".." were emitted if we reach this point and set the
+	 * termination value as well for an empty directory.
+	 */
+	if (ctx->pos > 2 && !emitted)
+		goto nopos;
+
 	/* Reached end of directory/root. Bump pos past the last item. */
 	ctx->pos++;
 
@@ -7974,6 +7986,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 
 	if (io_bio->end_io)
@@ -8028,6 +8041,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 	bio_put(bio);
 }
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 952172ca7e45..48aee9846329 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2794,24 +2794,29 @@ out:
 static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (!PageUptodate(page)) {
-		if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
-						 0))
-			return NULL;
+		int ret;
+
+		ret = btrfs_readpage(NULL, page);
+		if (ret)
+			return ERR_PTR(ret);
 		lock_page(page);
 		if (!PageUptodate(page)) {
 			unlock_page(page);
 			page_cache_release(page);
-			return NULL;
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != inode->i_mapping) {
+			unlock_page(page);
+			page_cache_release(page);
+			return ERR_PTR(-EAGAIN);
 		}
 	}
-	unlock_page(page);
 
 	return page;
 }
@@ -2823,17 +2828,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages,
 	pgoff_t index = off >> PAGE_CACHE_SHIFT;
 
 	for (i = 0; i < num_pages; i++) {
+again:
 		pages[i] = extent_same_get_page(inode, index + i);
-		if (!pages[i])
-			return -ENOMEM;
+		if (IS_ERR(pages[i])) {
+			int err = PTR_ERR(pages[i]);
+
+			if (err == -EAGAIN)
+				goto again;
+			pages[i] = NULL;
+			return err;
+		}
 	}
 	return 0;
 }
 
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+			     bool retry_range_locking)
 {
-	/* do any pending delalloc/csum calc on src, one way or
-	   another, and lock file content */
+	/*
+	 * Do any pending delalloc/csum calculations on inode, one way or
+	 * another, and lock file content.
+	 * The locking order is:
+	 *
+	 *   1) pages
+	 *   2) range in the inode's io tree
+	 */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2851,8 +2870,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 		unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
+		if (!retry_range_locking)
+			return -EAGAIN;
 		btrfs_wait_ordered_range(inode, off, len);
 	}
+	return 0;
 }
 
 static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
@@ -2877,15 +2899,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
 	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
 }
 
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
-				     struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				    struct inode *inode2, u64 loff2, u64 len,
+				    bool retry_range_locking)
 {
+	int ret;
+
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-	lock_extent_range(inode1, loff1, len);
-	lock_extent_range(inode2, loff2, len);
+	ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+	if (ret)
+		return ret;
+	ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+	if (ret)
+		unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+			      loff1 + len - 1);
+	return ret;
 }
 
 struct cmp_pages {
@@ -2901,11 +2932,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 
 	for (i = 0; i < cmp->num_pages; i++) {
 		pg = cmp->src_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 		pg = cmp->dst_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 	}
 	kfree(cmp->src_pages);
 	kfree(cmp->dst_pages);
@@ -2966,6 +3001,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
 
 		src_page = cmp->src_pages[i];
 		dst_page = cmp->dst_pages[i];
+		ASSERT(PageLocked(src_page));
+		ASSERT(PageLocked(dst_page));
 
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
@@ -3078,14 +3115,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		goto out_unlock;
 	}
 
+again:
 	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
 	if (ret)
 		goto out_unlock;
 
 	if (same_inode)
-		lock_extent_range(src, same_lock_start, same_lock_len);
+		ret = lock_extent_range(src, same_lock_start, same_lock_len,
+					false);
 	else
-		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+		ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+					       false);
+	/*
+	 * If one of the inodes has dirty pages in the respective range or
+	 * ordered extents, we need to flush dellaloc and wait for all ordered
+	 * extents in the range. We must unlock the pages and the ranges in the
+	 * io trees to avoid deadlocks when flushing delalloc (requires locking
+	 * pages) and when waiting for ordered extents to complete (they require
+	 * range locking).
+	 */
+	if (ret == -EAGAIN) {
+		/*
+		 * Ranges in the io trees already unlocked. Now unlock all
+		 * pages before waiting for all IO to complete.
+		 */
+		btrfs_cmp_data_free(&cmp);
+		if (same_inode) {
+			btrfs_wait_ordered_range(src, same_lock_start,
+						 same_lock_len);
+		} else {
+			btrfs_wait_ordered_range(src, loff, len);
+			btrfs_wait_ordered_range(dst, dst_loff, len);
+		}
+		goto again;
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		btrfs_cmp_data_free(&cmp);
+		return ret;
+	}
 
 	/* pass original length for comparison so we stay within i_size */
 	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3795,9 +3864,15 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 		u64 lock_start = min_t(u64, off, destoff);
 		u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
 
-		lock_extent_range(src, lock_start, lock_len);
+		ret = lock_extent_range(src, lock_start, lock_len, true);
 	} else {
-		btrfs_double_extent_lock(src, off, inode, destoff, len);
+		ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+					       true);
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		goto out_unlock;
 	}
 
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 7dc886c9a78f..e956cba94338 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -175,7 +175,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 	 * string to the length of the original string to allow for worst case.
 	 */
 	md_len = strlen(sb_mountdata) + INET6_ADDRSTRLEN;
-	mountdata = kzalloc(md_len + 1, GFP_KERNEL);
+	mountdata = kzalloc(md_len + sizeof("ip=") + 1, GFP_KERNEL);
 	if (mountdata == NULL) {
 		rc = -ENOMEM;
 		goto compose_mount_options_err;
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index afa09fce8151..e682b36a210f 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -714,7 +714,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 
 	ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL);
 	if (!ses->auth_key.response) {
-		rc = ENOMEM;
+		rc = -ENOMEM;
 		ses->auth_key.len = 0;
 		goto setup_ntlmv2_rsp_ret;
 	}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 4fbd92d2e113..a763cd3d9e7c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2999,8 +2999,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server)
 	if (ses_init_buf) {
 		ses_init_buf->trailer.session_req.called_len = 32;
 
-		if (server->server_RFC1001_name &&
-		    server->server_RFC1001_name[0] != 0)
+		if (server->server_RFC1001_name[0] != 0)
 			rfc1002mangle(ses_init_buf->trailer.
 				      session_req.called_name,
 				      server->server_RFC1001_name,
diff --git a/fs/dax.c b/fs/dax.c
index fc2e3141138b..711172450da6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -79,15 +79,14 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n)
 }
 
 /*
- * dax_clear_blocks() is called from within transaction context from XFS,
+ * dax_clear_sectors() is called from within transaction context from XFS,
  * and hence this means the stack from this point must follow GFP_NOFS
  * semantics for all operations.
  */
-int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
 {
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	struct blk_dax_ctl dax = {
-		.sector = block << (inode->i_blkbits - 9),
+		.sector = _sector,
 		.size = _size,
 	};
 
@@ -109,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
 	wmb_pmem();
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dax_clear_blocks);
+EXPORT_SYMBOL_GPL(dax_clear_sectors);
 
 /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
 static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
@@ -485,11 +484,10 @@ static int dax_writeback_one(struct block_device *bdev,
  * end]. This is required by data integrity operations to ensure file data is
  * on persistent storage prior to completion of the operation.
  */
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end)
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	pgoff_t start_index, end_index, pmd_index;
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
@@ -500,8 +498,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
 	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
 		return -EIO;
 
-	start_index = start >> PAGE_CACHE_SHIFT;
-	end_index = end >> PAGE_CACHE_SHIFT;
+	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+		return 0;
+
+	start_index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end_index = wbc->range_end >> PAGE_CACHE_SHIFT;
 	pmd_index = DAX_PMD_INDEX(start_index);
 
 	rcu_read_lock();
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 1f107fd51328..655f21f99160 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
+/*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+
+void devpts_add_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	atomic_inc(&sb->s_active);
+	ihold(ptmx_inode);
+}
+
+void devpts_del_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	iput(ptmx_inode);
+	deactivate_super(sb);
+}
+
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 1b2f7ffc8b84..d6a9012d42ad 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -472,8 +472,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 		dio->io_error = -EIO;
 
 	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
-		bio_check_pages_dirty(bio);	/* transfers ownership */
 		err = bio->bi_error;
+		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index c424e4813ec8..d48e0d261d78 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -103,9 +104,78 @@ out_free:
 	return size;
 }
 
+static int
+efivarfs_ioc_getxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int i_flags;
+	unsigned int flags = 0;
+
+	i_flags = inode->i_flags;
+	if (i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+efivarfs_ioc_setxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int flags;
+	unsigned int i_flags = 0;
+	int error;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~FS_IMMUTABLE_FL)
+		return -EOPNOTSUPP;
+
+	if (!capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	if (flags & FS_IMMUTABLE_FL)
+		i_flags |= S_IMMUTABLE;
+
+
+	error = mnt_want_write_file(file);
+	if (error)
+		return error;
+
+	inode_lock(inode);
+	inode_set_flags(inode, i_flags, S_IMMUTABLE);
+	inode_unlock(inode);
+
+	mnt_drop_write_file(file);
+
+	return 0;
+}
+
+long
+efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
+{
+	void __user *arg = (void __user *)p;
+
+	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		return efivarfs_ioc_getxflags(file, arg);
+	case FS_IOC_SETFLAGS:
+		return efivarfs_ioc_setxflags(file, arg);
+	}
+
+	return -ENOTTY;
+}
+
 const struct file_operations efivarfs_file_operations = {
 	.open	= simple_open,
 	.read	= efivarfs_file_read,
 	.write	= efivarfs_file_write,
 	.llseek	= no_llseek,
+	.unlocked_ioctl = efivarfs_file_ioctl,
 };
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 3381b9da9ee6..e2ab6d0497f2 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -15,7 +15,8 @@
 #include "internal.h"
 
 struct inode *efivarfs_get_inode(struct super_block *sb,
-				const struct inode *dir, int mode, dev_t dev)
+				const struct inode *dir, int mode,
+				dev_t dev, bool is_removable)
 {
 	struct inode *inode = new_inode(sb);
 
@@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
 		switch (mode & S_IFMT) {
 		case S_IFREG:
 			inode->i_fop = &efivarfs_file_operations;
@@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
 static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 			  umode_t mode, bool excl)
 {
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct efivar_entry *var;
 	int namelen, i = 0, err = 0;
+	bool is_removable = false;
 
 	if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len))
 		return -EINVAL;
 
-	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
-	if (!inode)
-		return -ENOMEM;
-
 	var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
-	if (!var) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!var)
+		return -ENOMEM;
 
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
@@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
 			&var->var.VendorGuid);
 
+	if (efivar_variable_is_removable(var->var.VendorGuid,
+					 dentry->d_name.name, namelen))
+		is_removable = true;
+
+	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable);
+	if (!inode) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < namelen; i++)
 		var->var.VariableName[i] = dentry->d_name.name[i];
 
@@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 out:
 	if (err) {
 		kfree(var);
-		iput(inode);
+		if (inode)
+			iput(inode);
 	}
 	return err;
 }
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index b5ff16addb7c..b4505188e799 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations;
 extern const struct inode_operations efivarfs_dir_inode_operations;
 extern bool efivarfs_valid_name(const char *str, int len);
 extern struct inode *efivarfs_get_inode(struct super_block *sb,
-			const struct inode *dir, int mode, dev_t dev);
+			const struct inode *dir, int mode, dev_t dev,
+			bool is_removable);
 
 extern struct list_head efivarfs_list;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index b8a564f29107..dd029d13ea61 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -118,8 +118,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	struct dentry *dentry, *root = sb->s_root;
 	unsigned long size = 0;
 	char *name;
-	int len, i;
+	int len;
 	int err = -ENOMEM;
+	bool is_removable = false;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
@@ -128,15 +129,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	memcpy(entry->var.VariableName, name16, name_size);
 	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
 
-	len = ucs2_strlen(entry->var.VariableName);
+	len = ucs2_utf8size(entry->var.VariableName);
 
 	/* name, plus '-', plus GUID, plus NUL*/
 	name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
 	if (!name)
 		goto fail;
 
-	for (i = 0; i < len; i++)
-		name[i] = entry->var.VariableName[i] & 0xFF;
+	ucs2_as_utf8(name, entry->var.VariableName, len);
+
+	if (efivar_variable_is_removable(entry->var.VendorGuid, name, len))
+		is_removable = true;
 
 	name[len] = '-';
 
@@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 	name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
 
-	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0);
+	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0,
+				   is_removable);
 	if (!inode)
 		goto fail_name;
 
@@ -200,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
-	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
 	inode->i_op = &efivarfs_dir_inode_operations;
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 2c88d683cd91..c1400b109805 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -80,23 +80,6 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return ret;
 }
 
-static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
-	down_read(&ei->dax_sem);
-
-	ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL);
-
-	up_read(&ei->dax_sem);
-	sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
@@ -124,7 +107,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
 	.pmd_fault	= ext2_dax_pmd_fault,
-	.page_mkwrite	= ext2_dax_mkwrite,
+	.page_mkwrite	= ext2_dax_fault,
 	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 338eefda70c6..6bd58e6ff038 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode,
 		 * so that it's not found by another thread before it's
 		 * initialised
 		 */
-		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
-						1 << inode->i_blkbits);
+		err = dax_clear_sectors(inode->i_sb->s_bdev,
+				le32_to_cpu(chain[depth-1].key) <<
+				(inode->i_blkbits - 9),
+				1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
@@ -874,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
+#ifdef CONFIG_FS_DAX
+	if (dax_mapping(mapping)) {
+		return dax_writeback_mapping_range(mapping,
+						   mapping->host->i_sb->s_bdev,
+						   wbc);
+	}
+#endif
+
 	return mpage_writepages(mapping, wbc, ext2_get_block);
 }
 
@@ -1296,7 +1306,7 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		inode->i_flags |= S_DAX;
 }
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ec0668a60678..fe1f50fe764f 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init block bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		goto verify;
 	}
 	ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index c8021208a7eb..38f7562489bb 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -467,3 +467,59 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
 		return size;
 	return 0;
 }
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct inode *dir = d_inode(dentry->d_parent);
+	struct ext4_crypt_info *ci = EXT4_I(dir)->i_crypt_info;
+	int dir_has_key, cached_with_key;
+
+	if (!ext4_encrypted_inode(dir))
+		return 0;
+
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	cached_with_key = dentry->d_fsdata != NULL;
+	dir_has_key = (ci != NULL);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+	    (!cached_with_key && dir_has_key) ||
+	    (cached_with_key && !dir_has_key)) {
+#if 0				/* Revalidation debug */
+		char buf[80];
+		char *cp = simple_dname(dentry, buf, sizeof(buf));
+
+		if (IS_ERR(cp))
+			cp = (char *) "???";
+		pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
+		       cached_with_key, d_is_negative(dentry),
+		       dir_has_key);
+#endif
+		return 0;
+	}
+	return 1;
+}
+
+const struct dentry_operations ext4_encrypted_d_ops = {
+	.d_revalidate = ext4_d_revalidate,
+};
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d1bca74f844..33f5e2a50cf8 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	int dir_has_error = 0;
 	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
 
+	if (ext4_encrypted_inode(inode)) {
+		err = ext4_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
+			return err;
+	}
+
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
 		if (err != ERR_BAD_DX_DIR) {
@@ -157,8 +163,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					index, 1);
 			file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
 			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
-			if (IS_ERR(bh))
-				return PTR_ERR(bh);
+			if (IS_ERR(bh)) {
+				err = PTR_ERR(bh);
+				bh = NULL;
+				goto errout;
+			}
 		}
 
 		if (!bh) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0662b285dc8a..157b458a69d4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2302,6 +2302,7 @@ struct page *ext4_encrypt(struct inode *inode,
 int ext4_decrypt(struct page *page);
 int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
 			   ext4_fsblk_t pblk, ext4_lblk_t len);
+extern const struct dentry_operations ext4_encrypted_d_ops;
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 int ext4_init_crypto(void);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0ffabaf90aa5..3753ceb0b0dd 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3928,7 +3928,7 @@ static int
 convert_initialized_extent(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map,
 			   struct ext4_ext_path **ppath, int flags,
-			   unsigned int allocated, ext4_fsblk_t newblock)
+			   unsigned int allocated)
 {
 	struct ext4_ext_path *path = *ppath;
 	struct ext4_extent *ex;
@@ -4347,7 +4347,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
 				allocated = convert_initialized_extent(
 						handle, inode, map, &path,
-						flags, allocated, newblock);
+						flags, allocated);
 				goto out2;
 			} else if (!ext4_ext_is_unwritten(ex))
 				goto out;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1126436dada1..4cd318f31cbe 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -262,23 +262,8 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return result;
 }
 
-static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	int err;
-	struct inode *inode = file_inode(vma->vm_file);
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	sb_end_pagefault(inode->i_sb);
-
-	return err;
-}
-
 /*
- * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
  * handler we check for races agaist truncate. Note that since we cycle through
  * i_mmap_sem, we are sure that also any hole punching that began before we
  * were called is finished by now and so if it included part of the file we
@@ -311,7 +296,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.pmd_fault	= ext4_dax_pmd_fault,
-	.page_mkwrite	= ext4_dax_mkwrite,
+	.page_mkwrite	= ext4_dax_fault,
 	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
 #else
@@ -350,6 +335,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	struct super_block *sb = inode->i_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct vfsmount *mnt = filp->f_path.mnt;
+	struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
 	struct path path;
 	char buf[64], *cp;
 	int ret;
@@ -393,6 +379,14 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ext4_encryption_info(inode) == NULL)
 			return -ENOKEY;
 	}
+	if (ext4_encrypted_inode(dir) &&
+	    !ext4_is_child_context_consistent_with_parent(dir, inode)) {
+		ext4_warning(inode->i_sb,
+			     "Inconsistent encryption contexts: %lu/%lu\n",
+			     (unsigned long) dir->i_ino,
+			     (unsigned long) inode->i_ino);
+		return -EPERM;
+	}
 	/*
 	 * Set up the jbd2_inode if we are opening the inode for
 	 * writing and the journal is present
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 3fcfd50a2e8a..acc0ad56bf2f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init inode bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 83bc8bfb3bea..aee960b1af34 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -686,6 +686,34 @@ out_sem:
 	return retval;
 }
 
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = READ_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -722,7 +750,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_io_end_t *io_end = ext4_inode_aio(inode);
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		ext4_update_bh_state(bh, map.m_flags);
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -1685,7 +1713,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked
@@ -2450,6 +2478,10 @@ static int ext4_writepages(struct address_space *mapping,
 
 	trace_ext4_writepages(inode, wbc);
 
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+						   wbc);
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -3253,29 +3285,29 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * case, we allocate an io_end structure to hook to the iocb.
 	 */
 	iocb->private = NULL;
-	ext4_inode_aio_set(inode, NULL);
-	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
-		if (!io_end) {
-			ret = -ENOMEM;
-			goto retake_lock;
-		}
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
-		/*
-		 * we save the io structure for current async direct
-		 * IO, so that later ext4_map_blocks() could flag the
-		 * io structure whether there is a unwritten extents
-		 * needs to be converted when IO is completed.
-		 */
-		ext4_inode_aio_set(inode, io_end);
-	}
-
 	if (overwrite) {
 		get_block_func = ext4_get_block_overwrite;
 	} else {
+		ext4_inode_aio_set(inode, NULL);
+		if (!is_sync_kiocb(iocb)) {
+			io_end = ext4_init_io_end(inode, GFP_NOFS);
+			if (!io_end) {
+				ret = -ENOMEM;
+				goto retake_lock;
+			}
+			/*
+			 * Grab reference for DIO. Will be dropped in
+			 * ext4_end_io_dio()
+			 */
+			iocb->private = ext4_get_io_end(io_end);
+			/*
+			 * we save the io structure for current async direct
+			 * IO, so that later ext4_map_blocks() could flag the
+			 * io structure whether there is a unwritten extents
+			 * needs to be converted when IO is completed.
+			 */
+			ext4_inode_aio_set(inode, io_end);
+		}
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
@@ -4127,7 +4159,7 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 0f6c36922c24..eae5917c534e 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -208,7 +208,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	handle_t *handle = NULL;
-	int err = EPERM, migrate = 0;
+	int err = -EPERM, migrate = 0;
 	struct ext4_iloc iloc;
 	unsigned int oldflags, mask, i;
 	unsigned int jflag;
@@ -583,6 +583,11 @@ group_extend_out:
 				 "Online defrag not supported with bigalloc");
 			err = -EOPNOTSUPP;
 			goto mext_out;
+		} else if (IS_DAX(inode)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online defrag not supported with DAX");
+			err = -EOPNOTSUPP;
+			goto mext_out;
 		}
 
 		err = mnt_want_write_file(filp);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 61eaf74dca37..4424b7bf8ac6 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2285,7 +2285,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	if (group == 0)
 		seq_puts(seq, "#group: free  frags first ["
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
-			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]");
+			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
 		sizeof(struct ext4_group_info);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index fb6f11709ae6..e032a0423e35 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	ext4_lblk_t orig_blk_offset, donor_blk_offset;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int tmp_data_size, data_size, replaced_size;
-	int err2, jblocks, retries = 0;
+	int i, err2, jblocks, retries = 0;
 	int replaced_count = 0;
 	int from = data_offset_in_page << orig_inode->i_blkbits;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 	struct super_block *sb = orig_inode->i_sb;
+	struct buffer_head *bh = NULL;
 
 	/*
 	 * It needs twice the amount of ordinary journal buffers because
@@ -380,8 +381,16 @@ data_copy:
 	}
 	/* Perform all necessary steps similar write_begin()/write_end()
 	 * but keeping in mind that i_size will not change */
-	*err = __block_write_begin(pagep[0], from, replaced_size,
-				   ext4_get_block);
+	if (!page_has_buffers(pagep[0]))
+		create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0);
+	bh = page_buffers(pagep[0]);
+	for (i = 0; i < data_offset_in_page; i++)
+		bh = bh->b_this_page;
+	for (i = 0; i < block_len_in_page; i++) {
+		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
+		if (*err < 0)
+			break;
+	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 06574dd77614..48e4b8907826 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1558,6 +1558,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 	struct ext4_dir_entry_2 *de;
 	struct buffer_head *bh;
 
+       if (ext4_encrypted_inode(dir)) {
+               int res = ext4_get_encryption_info(dir);
+
+		/*
+		 * This should be a properly defined flag for
+		 * dentry->d_flags when we uplift this to the VFS.
+		 * d_fsdata is set to (void *) 1 if if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+	       dentry->d_fsdata = NULL;
+	       if (ext4_encryption_info(dir))
+		       dentry->d_fsdata = (void *) 1;
+	       d_set_d_op(dentry, &ext4_encrypted_d_ops);
+	       if (res && res != -ENOKEY)
+		       return ERR_PTR(res);
+       }
+
 	if (dentry->d_name.len > EXT4_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
@@ -1585,11 +1603,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 			return ERR_PTR(-EFSCORRUPTED);
 		}
 		if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
-		    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		     S_ISLNK(inode->i_mode)) &&
+		    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 		    !ext4_is_child_context_consistent_with_parent(dir,
 								  inode)) {
+			int nokey = ext4_encrypted_inode(inode) &&
+				!ext4_encryption_info(inode);
+
 			iput(inode);
+			if (nokey)
+				return ERR_PTR(-ENOKEY);
 			ext4_warning(inode->i_sb,
 				     "Inconsistent encryption contexts: %lu/%lu\n",
 				     (unsigned long) dir->i_ino,
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ad62d7acc315..34038e3598d5 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
 		goto out2;
 	flex_gd->count = flexbg_size;
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6915c950e6e8..1f76d8950a57 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -317,6 +317,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 	struct inode_switch_wbs_context *isw =
 		container_of(work, struct inode_switch_wbs_context, work);
 	struct inode *inode = isw->inode;
+	struct super_block *sb = inode->i_sb;
 	struct address_space *mapping = inode->i_mapping;
 	struct bdi_writeback *old_wb = inode->i_wb;
 	struct bdi_writeback *new_wb = isw->new_wb;
@@ -423,6 +424,7 @@ skip_switch:
 	wb_put(new_wb);
 
 	iput(inode);
+	deactivate_super(sb);
 	kfree(isw);
 }
 
@@ -469,11 +471,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
 	/* while holding I_WB_SWITCH, no one else can update the association */
 	spin_lock(&inode->i_lock);
+
 	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
-	    inode_to_wb(inode) == isw->new_wb) {
-		spin_unlock(&inode->i_lock);
-		goto out_free;
-	}
+	    inode_to_wb(inode) == isw->new_wb)
+		goto out_unlock;
+
+	if (!atomic_inc_not_zero(&inode->i_sb->s_active))
+		goto out_unlock;
+
 	inode->i_state |= I_WB_SWITCH;
 	spin_unlock(&inode->i_lock);
 
@@ -489,6 +494,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
 	return;
 
+out_unlock:
+	spin_unlock(&inode->i_lock);
 out_free:
 	if (isw->new_wb)
 		wb_put(isw->new_wb);
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 506765afa1a3..bb8d67e2740a 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -376,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = d_inode(dentry);
 	dnode_secno dno;
 	int r;
-	int rep = 0;
 	int err;
 
 	hpfs_lock(dir->i_sb);
 	hpfs_adjust_length(name, &len);
-again:
+
 	err = -ENOENT;
 	de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh);
 	if (!de)
@@ -401,33 +400,9 @@ again:
 		hpfs_error(dir->i_sb, "there was error when removing dirent");
 		err = -EFSERROR;
 		break;
-	case 2:		/* no space for deleting, try to truncate file */
-
+	case 2:		/* no space for deleting */
 		err = -ENOSPC;
-		if (rep++)
-			break;
-
-		dentry_unhash(dentry);
-		if (!d_unhashed(dentry)) {
-			hpfs_unlock(dir->i_sb);
-			return -ENOSPC;
-		}
-		if (generic_permission(inode, MAY_WRITE) ||
-		    !S_ISREG(inode->i_mode) ||
-		    get_write_access(inode)) {
-			d_rehash(dentry);
-		} else {
-			struct iattr newattrs;
-			/*pr_info("truncating file before delete.\n");*/
-			newattrs.ia_size = 0;
-			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs, NULL);
-			put_write_access(inode);
-			if (!err)
-				goto again;
-		}
-		hpfs_unlock(dir->i_sb);
-		return -ENOSPC;
+		break;
 	default:
 		drop_nlink(inode);
 		err = 0;
diff --git a/fs/inode.c b/fs/inode.c
index 9f62db3bcc3e..69b8b526c194 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -154,6 +154,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_rdev = 0;
 	inode->dirtied_when = 0;
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+	inode->i_wb_frn_winner = 0;
+	inode->i_wb_frn_avg_time = 0;
+	inode->i_wb_frn_history = 0;
+#endif
+
 	if (security_inode_alloc(inode))
 		goto out;
 	spin_lock_init(&inode->i_lock);
diff --git a/fs/namei.c b/fs/namei.c
index f624d132e01e..9c590e0f66e9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1712,6 +1712,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link,
 		return 0;
 	if (!follow)
 		return 0;
+	/* make sure that d_is_symlink above matches inode */
+	if (nd->flags & LOOKUP_RCU) {
+		if (read_seqcount_retry(&link->dentry->d_seq, seq))
+			return -ECHILD;
+	}
 	return pick_link(nd, link, inode, seq);
 }
 
@@ -1743,11 +1748,11 @@ static int walk_component(struct nameidata *nd, int flags)
 		if (err < 0)
 			return err;
 
-		inode = d_backing_inode(path.dentry);
 		seq = 0;	/* we are already out of RCU mode */
 		err = -ENOENT;
 		if (d_is_negative(path.dentry))
 			goto out_path_put;
+		inode = d_backing_inode(path.dentry);
 	}
 
 	if (flags & WALK_PUT)
@@ -3192,12 +3197,12 @@ retry_lookup:
 		return error;
 
 	BUG_ON(nd->flags & LOOKUP_RCU);
-	inode = d_backing_inode(path.dentry);
 	seq = 0;	/* out of RCU mode, so the value doesn't matter */
 	if (unlikely(d_is_negative(path.dentry))) {
 		path_to_nameidata(&path, nd);
 		return -ENOENT;
 	}
+	inode = d_backing_inode(path.dentry);
 finish_lookup:
 	if (nd->depth)
 		put_link(nd);
@@ -3206,11 +3211,6 @@ finish_lookup:
 	if (unlikely(error))
 		return error;
 
-	if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) {
-		path_to_nameidata(&path, nd);
-		return -ELOOP;
-	}
-
 	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
 		path_to_nameidata(&path, nd);
 	} else {
@@ -3229,6 +3229,10 @@ finish_open:
 		return error;
 	}
 	audit_inode(nd->name, nd->path.dentry, 0);
+	if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) {
+		error = -ELOOP;
+		goto out;
+	}
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
@@ -3273,6 +3277,10 @@ opened:
 			goto exit_fput;
 	}
 out:
+	if (unlikely(error > 0)) {
+		WARN_ON(1);
+		error = -EINVAL;
+	}
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 	path_put(&save_parent);
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index c59a59c37f3d..35ab51c04814 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -476,6 +476,7 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
 
 		for (i = 0; i < nr_pages; i++)
 			put_page(arg->layoutupdate_pages[i]);
+		vfree(arg->start_p);
 		kfree(arg->layoutupdate_pages);
 	} else {
 		put_page(arg->layoutupdate_page);
@@ -559,10 +560,15 @@ retry:
 
 	if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) {
 		void *p = start_p, *end = p + arg->layoutupdate_len;
+		struct page *page = NULL;
 		int i = 0;
 
-		for ( ; p < end; p += PAGE_SIZE)
-			arg->layoutupdate_pages[i++] = vmalloc_to_page(p);
+		arg->start_p = start_p;
+		for ( ; p < end; p += PAGE_SIZE) {
+			page = vmalloc_to_page(p);
+			arg->layoutupdate_pages[i++] = page;
+			get_page(page);
+		}
 	}
 
 	dprintk("%s found %zu ranges\n", __func__, count);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index bd25dc7077f7..dff83460e5a6 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -16,29 +16,8 @@
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 
-static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
-				fmode_t fmode)
-{
-	struct nfs_open_context *open;
-	struct nfs_lock_context *lock;
-	int ret;
-
-	open = get_nfs_open_context(nfs_file_open_context(file));
-	lock = nfs_get_lock_context(open);
-	if (IS_ERR(lock)) {
-		put_nfs_open_context(open);
-		return PTR_ERR(lock);
-	}
-
-	ret = nfs4_set_rw_stateid(dst, open, lock, fmode);
-
-	nfs_put_lock_context(lock);
-	put_nfs_open_context(open);
-	return ret;
-}
-
 static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
-				 loff_t offset, loff_t len)
+		struct nfs_lock_context *lock, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	msg->rpc_argp = &args;
 	msg->rpc_resp = &res;
 
-	status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE);
+	status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context,
+			lock, FMODE_WRITE);
 	if (status)
 		return status;
 
@@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	int err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_fallocate(msg, filep, offset, len);
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -135,7 +126,8 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
-static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+static loff_t _nfs42_proc_llseek(struct file *filep,
+		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs42_seek_args args = {
@@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 	if (!nfs_server_capable(inode, NFS_CAP_SEEK))
 		return -ENOTSUPP;
 
-	status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ);
+	status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context,
+			lock, FMODE_READ);
 	if (status)
 		return status;
 
@@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	loff_t err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_llseek(filep, offset, whence);
+		err = _nfs42_proc_llseek(filep, lock, offset, whence);
 		if (err >= 0)
 			break;
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -298,8 +302,9 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
 }
 
 static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
-			     struct file *dst_f, loff_t src_offset,
-			     loff_t dst_offset, loff_t count)
+		struct file *dst_f, struct nfs_lock_context *src_lock,
+		struct nfs_lock_context *dst_lock, loff_t src_offset,
+		loff_t dst_offset, loff_t count)
 {
 	struct inode *src_inode = file_inode(src_f);
 	struct inode *dst_inode = file_inode(dst_f);
@@ -320,11 +325,13 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
 	msg->rpc_argp = &args;
 	msg->rpc_resp = &res;
 
-	status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ);
+	status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+			src_lock, FMODE_READ);
 	if (status)
 		return status;
 
-	status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE);
+	status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+			dst_lock, FMODE_WRITE);
 	if (status)
 		return status;
 
@@ -349,22 +356,48 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f,
 	};
 	struct inode *inode = file_inode(src_f);
 	struct nfs_server *server = NFS_SERVER(file_inode(src_f));
-	struct nfs4_exception exception = { };
-	int err;
+	struct nfs_lock_context *src_lock;
+	struct nfs_lock_context *dst_lock;
+	struct nfs4_exception src_exception = { };
+	struct nfs4_exception dst_exception = { };
+	int err, err2;
 
 	if (!nfs_server_capable(inode, NFS_CAP_CLONE))
 		return -EOPNOTSUPP;
 
+	src_lock = nfs_get_lock_context(nfs_file_open_context(src_f));
+	if (IS_ERR(src_lock))
+		return PTR_ERR(src_lock);
+
+	src_exception.inode = file_inode(src_f);
+	src_exception.state = src_lock->open_context->state;
+
+	dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f));
+	if (IS_ERR(dst_lock)) {
+		err = PTR_ERR(dst_lock);
+		goto out_put_src_lock;
+	}
+
+	dst_exception.inode = file_inode(dst_f);
+	dst_exception.state = dst_lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset,
-					dst_offset, count);
+		err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock,
+					src_offset, dst_offset, count);
 		if (err == -ENOTSUPP || err == -EOPNOTSUPP) {
 			NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE;
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			break;
 		}
-		err = nfs4_handle_exception(server, err, &exception);
-	} while (exception.retry);
 
-	return err;
+		err2 = nfs4_handle_exception(server, err, &src_exception);
+		err = nfs4_handle_exception(server, err, &dst_exception);
+		if (!err)
+			err = err2;
+	} while (src_exception.retry || dst_exception.retry);
 
+	nfs_put_lock_context(dst_lock);
+out_put_src_lock:
+	nfs_put_lock_context(src_lock);
+	return err;
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4bfc33ad0563..14881594dd07 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2466,9 +2466,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 		dentry = d_add_unique(dentry, igrab(state->inode));
 		if (dentry == NULL) {
 			dentry = opendata->dentry;
-		} else if (dentry != ctx->dentry) {
+		} else {
 			dput(ctx->dentry);
-			ctx->dentry = dget(dentry);
+			ctx->dentry = dentry;
 		}
 		nfs_set_verifier(dentry,
 				nfs_save_change_attribute(d_inode(opendata->dir)));
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 482b6e94bb37..2fa483e6dbe2 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 	}
 }
 
+/*
+ * Mark a pnfs_layout_hdr and all associated layout segments as invalid
+ *
+ * In order to continue using the pnfs_layout_hdr, a full recovery
+ * is required.
+ * Note that caller must hold inode->i_lock.
+ */
+static int
+pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
+		struct list_head *lseg_list)
+{
+	struct pnfs_layout_range range = {
+		.iomode = IOMODE_ANY,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+
+	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+	return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range);
+}
+
 static int
 pnfs_iomode_to_fail_bit(u32 iomode)
 {
@@ -554,9 +575,8 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	spin_lock(&nfsi->vfs_inode.i_lock);
 	lo = nfsi->layout;
 	if (lo) {
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 		pnfs_get_layout_hdr(lo);
+		pnfs_mark_layout_stateid_invalid(lo, &tmp_list);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
 		spin_unlock(&nfsi->vfs_inode.i_lock);
@@ -617,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 {
 	struct pnfs_layout_hdr *lo;
 	struct inode *inode;
-	struct pnfs_layout_range range = {
-		.iomode = IOMODE_ANY,
-		.offset = 0,
-		.length = NFS4_MAX_UINT64,
-	};
 	LIST_HEAD(lseg_list);
 	int ret = 0;
 
@@ -636,11 +651,11 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 
 		spin_lock(&inode->i_lock);
 		list_del_init(&lo->plh_bulk_destroy);
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		if (is_bulk_recall)
-			set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range))
+		if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) {
+			if (is_bulk_recall)
+				set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 			ret = -EAGAIN;
+		}
 		spin_unlock(&inode->i_lock);
 		pnfs_free_lseg_list(&lseg_list);
 		/* Free all lsegs that are attached to commit buckets */
@@ -1738,8 +1753,19 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
 	if (lo->plh_return_iomode != 0)
 		iomode = IOMODE_ANY;
 	lo->plh_return_iomode = iomode;
+	set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
 }
 
+/**
+ * pnfs_mark_matching_lsegs_return - Free or return matching layout segments
+ * @lo: pointer to layout header
+ * @tmp_list: list header to be used with pnfs_free_lseg_list()
+ * @return_range: describe layout segment ranges to be returned
+ *
+ * This function is mainly intended for use by layoutrecall. It attempts
+ * to free the layout segment immediately, or else to mark it for return
+ * as soon as its reference count drops to zero.
+ */
 int
 pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
@@ -1762,12 +1788,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				lseg, lseg->pls_range.iomode,
 				lseg->pls_range.offset,
 				lseg->pls_range.length);
+			if (mark_lseg_invalid(lseg, tmp_list))
+				continue;
+			remaining++;
 			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
 			pnfs_set_plh_return_iomode(lo, return_range->iomode);
-			if (!mark_lseg_invalid(lseg, tmp_list))
-				remaining++;
-			set_bit(NFS_LAYOUT_RETURN_REQUESTED,
-					&lo->plh_flags);
 		}
 	return remaining;
 }
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index cfcbf114676e..7115c5d7d373 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -91,7 +91,14 @@
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
 
+#define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */
+
 struct srcu_struct fsnotify_mark_srcu;
+static DEFINE_SPINLOCK(destroy_lock);
+static LIST_HEAD(destroy_list);
+
+static void fsnotify_mark_destroy(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy);
 
 void fsnotify_get_mark(struct fsnotify_mark *mark)
 {
@@ -165,19 +172,10 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
 	atomic_dec(&group->num_marks);
 }
 
-static void
-fsnotify_mark_free_rcu(struct rcu_head *rcu)
-{
-	struct fsnotify_mark	*mark;
-
-	mark = container_of(rcu, struct fsnotify_mark, g_rcu);
-	fsnotify_put_mark(mark);
-}
-
 /*
- * Free fsnotify mark. The freeing is actually happening from a call_srcu
- * callback. Caller must have a reference to the mark or be protected by
- * fsnotify_mark_srcu.
+ * Free fsnotify mark. The freeing is actually happening from a kthread which
+ * first waits for srcu period end. Caller must have a reference to the mark
+ * or be protected by fsnotify_mark_srcu.
  */
 void fsnotify_free_mark(struct fsnotify_mark *mark)
 {
@@ -192,7 +190,11 @@ void fsnotify_free_mark(struct fsnotify_mark *mark)
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 	spin_unlock(&mark->lock);
 
-	call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu);
+	spin_lock(&destroy_lock);
+	list_add(&mark->g_list, &destroy_list);
+	spin_unlock(&destroy_lock);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
 
 	/*
 	 * Some groups like to know that marks are being freed.  This is a
@@ -388,7 +390,12 @@ err:
 
 	spin_unlock(&mark->lock);
 
-	call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu);
+	spin_lock(&destroy_lock);
+	list_add(&mark->g_list, &destroy_list);
+	spin_unlock(&destroy_lock);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
+
 	return ret;
 }
 
@@ -491,3 +498,21 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	atomic_set(&mark->refcnt, 1);
 	mark->free_mark = free_mark;
 }
+
+static void fsnotify_mark_destroy(struct work_struct *work)
+{
+	struct fsnotify_mark *mark, *next;
+	struct list_head private_destroy_list;
+
+	spin_lock(&destroy_lock);
+	/* exchange the list head */
+	list_replace_init(&destroy_list, &private_destroy_list);
+	spin_unlock(&destroy_lock);
+
+	synchronize_srcu(&fsnotify_mark_srcu);
+
+	list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
+		list_del_init(&mark->g_list);
+		fsnotify_put_mark(mark);
+	}
+}
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 794fd1587f34..cda0361e95a4 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -956,6 +956,7 @@ clean_orphan:
 		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
 				update_isize, end);
 		if (tmp_ret < 0) {
+			ocfs2_inode_unlock(inode, 1);
 			ret = tmp_ret;
 			mlog_errno(ret);
 			brelse(di_bh);
diff --git a/fs/pnode.c b/fs/pnode.c
index 6367e1e435c6..c524fdddc7fb 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master;
 static struct mountpoint *mp;
 static struct hlist_head *list;
 
+static inline bool peers(struct mount *m1, struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
+}
+
 static int propagate_one(struct mount *m)
 {
 	struct mount *child;
@@ -212,7 +217,7 @@ static int propagate_one(struct mount *m)
 	/* skip if mountpoint isn't covered by it */
 	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
 		return 0;
-	if (m->mnt_group_id == last_dest->mnt_group_id) {
+	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
 	} else {
 		struct mount *n, *p;
@@ -223,7 +228,7 @@ static int propagate_one(struct mount *m)
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
-				if (n->mnt_group_id != last_dest->mnt_group_id) {
+				if (!peers(n, last_dest)) {
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
diff --git a/fs/read_write.c b/fs/read_write.c
index 324ec271cc4e..dadf24e5c95b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -17,6 +17,7 @@
 #include <linux/splice.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
+#include <linux/fs.h>
 #include "internal.h"
 
 #include <asm/uaccess.h>
@@ -183,7 +184,7 @@ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 	case SEEK_SET: case SEEK_CUR:
 		return generic_file_llseek_size(file, offset, whence,
-						~0ULL, 0);
+						OFFSET_MAX, 0);
 	default:
 		return -EINVAL;
 	}
@@ -1532,10 +1533,12 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 
 	if (!(file_in->f_mode & FMODE_READ) ||
 	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND) ||
-	    !file_in->f_op->clone_file_range)
+	    (file_out->f_flags & O_APPEND))
 		return -EBADF;
 
+	if (!file_in->f_op->clone_file_range)
+		return -EOPNOTSUPP;
+
 	ret = clone_verify_area(file_in, pos_in, len, false);
 	if (ret)
 		return ret;
diff --git a/fs/xattr.c b/fs/xattr.c
index 07d0e47f6a7f..4861322e28e8 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -940,7 +940,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 	bool trusted = capable(CAP_SYS_ADMIN);
 	struct simple_xattr *xattr;
 	ssize_t remaining_size = size;
-	int err;
+	int err = 0;
 
 #ifdef CONFIG_FS_POSIX_ACL
 	if (inode->i_acl) {
@@ -965,11 +965,11 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 
 		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
 		if (err)
-			return err;
+			break;
 	}
 	spin_unlock(&xattrs->lock);
 
-	return size - remaining_size;
+	return err ? err : size - remaining_size;
 }
 
 /*
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 379c089fb051..a9ebabfe7587 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -55,7 +55,7 @@ xfs_count_page_state(
 	} while ((bh = bh->b_this_page) != head);
 }
 
-STATIC struct block_device *
+struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
 {
@@ -1208,6 +1208,10 @@ xfs_vm_writepages(
 	struct writeback_control *wbc)
 {
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping,
+				xfs_find_bdev_for_inode(mapping->host), wbc);
+
 	return generic_writepages(mapping, wbc);
 }
 
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index f6ffc9ae5ceb..a4343c63fb38 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -62,5 +62,6 @@ int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
 			         struct buffer_head *map_bh, int create);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
+extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
 
 #endif /* __XFS_AOPS_H__ */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 45ec9e40150c..6c876012b2e5 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -75,7 +75,8 @@ xfs_zero_extent(
 	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
 
 	if (IS_DAX(VFS_I(ip)))
-		return dax_clear_blocks(VFS_I(ip), block, size);
+		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
+				sector, size);
 
 	/*
 	 * let the block layer decide on the fastest method of
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index da37beb76f6e..594f7e63b432 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4491,7 +4491,7 @@ xlog_recover_process(
 	 * know precisely what failed.
 	 */
 	if (pass == XLOG_RECOVER_CRCPASS) {
-		if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc))
+		if (rhead->h_crc && crc != rhead->h_crc)
 			return -EFSBADCRC;
 		return 0;
 	}
@@ -4502,7 +4502,7 @@ xlog_recover_process(
 	 * zero CRC check prevents warnings from being emitted when upgrading
 	 * the kernel from one that does not add CRCs by default.
 	 */
-	if (crc != le32_to_cpu(rhead->h_crc)) {
+	if (crc != rhead->h_crc) {
 		if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
 			xfs_alert(log->l_mp,
 		"log record CRC mismatch: found 0x%x, expected 0x%x.",
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
index 0419485891f2..0f1c6f315cdc 100644
--- a/include/asm-generic/cputime_nsecs.h
+++ b/include/asm-generic/cputime_nsecs.h
@@ -75,7 +75,7 @@ typedef u64 __nocast cputime64_t;
  */
 static inline cputime_t timespec_to_cputime(const struct timespec *val)
 {
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
+	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
 	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
@@ -91,7 +91,8 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
  */
 static inline cputime_t timeval_to_cputime(const struct timeval *val)
 {
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
+	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC +
+			val->tv_usec * NSEC_PER_USEC;
 	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 0b3c0d39ef75..c370b261c720 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -239,6 +239,14 @@ extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+					   unsigned long address, pmd_t *pmdp)
+{
+
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index c65a212db77e..c5b4b81a831b 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1166,6 +1166,7 @@ struct drm_connector {
 	struct drm_mode_object base;
 
 	char *name;
+	int connector_id;
 	int connector_type;
 	int connector_type_id;
 	bool interlace_allowed;
@@ -2047,6 +2048,7 @@ struct drm_mode_config {
 	struct list_head fb_list;
 
 	int num_connector;
+	struct ida connector_ida;
 	struct list_head connector_list;
 	int num_encoder;
 	struct list_head encoder_list;
@@ -2200,7 +2202,11 @@ int drm_connector_register(struct drm_connector *connector);
 void drm_connector_unregister(struct drm_connector *connector);
 
 extern void drm_connector_cleanup(struct drm_connector *connector);
-extern unsigned int drm_connector_index(struct drm_connector *connector);
+static inline unsigned drm_connector_index(struct drm_connector *connector)
+{
+	return connector->connector_id;
+}
+
 /* helper to unplug all connectors from sysfs for device */
 extern void drm_connector_unplug_all(struct drm_device *dev);
 
diff --git a/include/dt-bindings/clock/tegra210-car.h b/include/dt-bindings/clock/tegra210-car.h
index 6f45aea49e4f..0a05b0d36ae7 100644
--- a/include/dt-bindings/clock/tegra210-car.h
+++ b/include/dt-bindings/clock/tegra210-car.h
@@ -126,7 +126,7 @@
 /* 104 */
 /* 105 */
 #define TEGRA210_CLK_D_AUDIO 106
-/* 107 ( affects abp -> ape) */
+#define TEGRA210_CLK_APB2APE 107
 /* 108 */
 /* 109 */
 /* 110 */
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 1800227af9d6..b651aed9dc6b 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -55,6 +55,9 @@ struct arch_timer_cpu {
 
 	/* VGIC mapping */
 	struct irq_phys_map		*map;
+
+	/* Active IRQ state caching */
+	bool				active_cleared_last;
 };
 
 int kvm_timer_hyp_init(void);
@@ -74,4 +77,6 @@ bool kvm_timer_should_fire(struct kvm_vcpu *vcpu);
 void kvm_timer_schedule(struct kvm_vcpu *vcpu);
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu);
 
+void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu);
+
 #endif
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
new file mode 100644
index 000000000000..fe389ac31489
--- /dev/null
+++ b/include/kvm/arm_pmu.h
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd.
+ * Author: Shannon Zhao <shannon.zhao@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_ARM_KVM_PMU_H
+#define __ASM_ARM_KVM_PMU_H
+
+#ifdef CONFIG_KVM_ARM_PMU
+
+#include <linux/perf_event.h>
+#include <asm/perf_event.h>
+
+#define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
+
+struct kvm_pmc {
+	u8 idx;	/* index into the pmu->pmc array */
+	struct perf_event *perf_event;
+	u64 bitmask;
+};
+
+struct kvm_pmu {
+	int irq_num;
+	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
+	bool ready;
+	bool irq_level;
+};
+
+#define kvm_arm_pmu_v3_ready(v)		((v)->arch.pmu.ready)
+#define kvm_arm_pmu_irq_initialized(v)	((v)->arch.pmu.irq_num >= VGIC_NR_SGIS)
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
+void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
+u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu);
+void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
+void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
+void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
+				    u64 select_idx);
+bool kvm_arm_support_pmu_v3(void);
+int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+#else
+struct kvm_pmu {
+};
+
+#define kvm_arm_pmu_v3_ready(v)		(false)
+#define kvm_arm_pmu_irq_initialized(v)	(false)
+static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu,
+					    u64 select_idx)
+{
+	return 0;
+}
+static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu,
+					     u64 select_idx, u64 val) {}
+static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu,
+						  u64 data, u64 select_idx) {}
+static inline bool kvm_arm_support_pmu_v3(void) { return false; }
+static inline int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
+					  struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
+					  struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
+					  struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+#endif
+
+#endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 13a3d537811b..281caf847fad 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -279,12 +279,6 @@ struct vgic_v2_cpu_if {
 	u32		vgic_lr[VGIC_V2_MAX_LRS];
 };
 
-/*
- * LRs are stored in reverse order in memory. make sure we index them
- * correctly.
- */
-#define VGIC_V3_LR_INDEX(lr)		(VGIC_V3_MAX_LRS - 1 - lr)
-
 struct vgic_v3_cpu_if {
 #ifdef CONFIG_KVM_ARM_VGIC_V3
 	u32		vgic_hcr;
@@ -321,6 +315,8 @@ struct vgic_cpu {
 
 	/* Protected by the distributor's irq_phys_map_lock */
 	struct list_head	irq_phys_map_list;
+
+	u64		live_lrs;
 };
 
 #define LR_EMPTY	0xff
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 29189aeace19..4571ef1a12a9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -682,9 +682,12 @@ static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
 /*
  * q->prep_rq_fn return values
  */
-#define BLKPREP_OK		0	/* serve it */
-#define BLKPREP_KILL		1	/* fatal error, kill */
-#define BLKPREP_DEFER		2	/* leave on queue */
+enum {
+	BLKPREP_OK,		/* serve it */
+	BLKPREP_KILL,		/* fatal error, kill, return -EIO */
+	BLKPREP_DEFER,		/* leave on queue */
+	BLKPREP_INVALID,	/* invalid command, kill, return -EREMOTEIO */
+};
 
 extern unsigned long blk_max_low_pfn, blk_max_pfn;
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 7f540f7f588d..789471dba6fb 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -127,6 +127,12 @@ struct cgroup_subsys_state {
 	 */
 	u64 serial_nr;
 
+	/*
+	 * Incremented by online self and children.  Used to guarantee that
+	 * parents are not offlined before their children.
+	 */
+	atomic_t online_cnt;
+
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 00b042c49ccd..48f5aab117ae 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -144,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  */
 #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
 #define __trace_if(cond) \
-	if (__builtin_constant_p((cond)) ? !!(cond) :			\
+	if (__builtin_constant_p(!!(cond)) ? !!(cond) :			\
 	({								\
 		int ______r;						\
 		static struct ftrace_branch_data			\
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 85a868ccb493..fea160ee5803 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -137,6 +137,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
+extern void cpuset_post_attach_flush(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -243,6 +245,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
+static inline void cpuset_post_attach_flush(void)
+{
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 818e45078929..636dd59ab505 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -7,7 +7,7 @@
 
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
 		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
@@ -52,6 +52,8 @@ static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
 }
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end);
+
+struct writeback_control;
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc);
 #endif
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 251a2090a554..e0ee0b3000b2 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -19,6 +19,8 @@
 
 int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
+void devpts_add_ref(struct inode *ptmx_inode);
+void devpts_del_ref(struct inode *ptmx_inode);
 /* mknod in devpts */
 struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
 		void *priv);
@@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode);
 /* Dummy stubs in the no-pty case */
 static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
 static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
+static inline void devpts_add_ref(struct inode *ptmx_inode) { }
+static inline void devpts_del_ref(struct inode *ptmx_inode) { }
 static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
 		dev_t device, int index, void *priv)
 {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 569b5a866bb1..47be3ad7d3e5 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1199,7 +1199,10 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *),
 struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 				       struct list_head *head, bool remove);
 
-bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len);
+bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		     unsigned long data_size);
+bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
+				  size_t len);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 6b7e89f45aa4..533c4408529a 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -220,10 +220,7 @@ struct fsnotify_mark {
 	/* List of marks by group->i_fsnotify_marks. Also reused for queueing
 	 * mark into destroy_list when it's waiting for the end of SRCU period
 	 * before it can be freed. [group->mark_mutex] */
-	union {
-		struct list_head g_list;
-		struct rcu_head g_rcu;
-	};
+	struct list_head g_list;
 	/* Protects inode / mnt pointers, flags, masks */
 	spinlock_t lock;
 	/* List of marks for inode / vfsmount [obj_lock] */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 81de7123959d..c2b340e23f62 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -603,6 +603,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
+extern void ftrace_module_enable(struct module *mod);
 extern void ftrace_release_mod(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
@@ -612,8 +613,9 @@ static inline int skip_trace(unsigned long ip) { return 0; }
 static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
-static inline void ftrace_release_mod(struct module *mod) {}
-static inline void ftrace_module_init(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) { }
+static inline void ftrace_module_enable(struct module *mod) { }
+static inline void ftrace_release_mod(struct module *mod) { }
 static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	return -EINVAL;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 821273ca4873..2d9b650047a5 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -235,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 /* low 64 bit */
 #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT))
 
+/* PRS_REG */
+#define DMA_PRS_PPR	((u32)1)
+
 #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)			\
 do {									\
 	cycles_t start_time = get_cycles();				\
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 851821bfd553..bec2abbd7ab2 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -526,6 +526,7 @@ enum ata_lpm_policy {
 enum ata_lpm_hints {
 	ATA_LPM_EMPTY		= (1 << 0), /* port empty/probing */
 	ATA_LPM_HIPM		= (1 << 1), /* may use HIPM */
+	ATA_LPM_WAKE_ONLY	= (1 << 2), /* only wake up link */
 };
 
 /* forward declarations */
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index bed40dff0e86..141ffdd59960 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -26,9 +26,8 @@ enum {
 
 	/* need to set a limit somewhere, but yes, this is likely overkill */
 	ND_IOCTL_MAX_BUFLEN = SZ_4M,
-	ND_CMD_MAX_ELEM = 4,
+	ND_CMD_MAX_ELEM = 5,
 	ND_CMD_MAX_ENVELOPE = 16,
-	ND_CMD_ARS_STATUS_MAX = SZ_4K,
 	ND_MAX_MAPPINGS = 32,
 
 	/* region flag indicating to direct-map persistent memory by default */
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index d6750111e48e..2190419bdf0a 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -135,6 +135,10 @@ enum {
 	/* Memory types */
 	NVM_ID_FMTYPE_SLC	= 0,
 	NVM_ID_FMTYPE_MLC	= 1,
+
+	/* Device capabilities */
+	NVM_ID_DCAP_BBLKMGMT	= 0x1,
+	NVM_UD_DCAP_ECC		= 0x2,
 };
 
 struct nvm_id_lp_mlc {
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index c57e424d914b..4dca42fd32f5 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -66,7 +66,7 @@ struct lock_class {
 	/*
 	 * class-hash:
 	 */
-	struct list_head		hash_entry;
+	struct hlist_node		hash_entry;
 
 	/*
 	 * global list of all lock-classes:
@@ -199,7 +199,7 @@ struct lock_chain {
 	u8				irq_context;
 	u8				depth;
 	u16				base;
-	struct list_head		entry;
+	struct hlist_node		entry;
 	u64				chain_key;
 };
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 430a929f048b..a0e8cc8dcc67 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -44,6 +44,8 @@
 
 #include <linux/timecounter.h>
 
+#define DEFAULT_UAR_PAGE_SHIFT  12
+
 #define MAX_MSIX_P_PORT		17
 #define MAX_MSIX		64
 #define MIN_MSIX_P_PORT		5
@@ -856,6 +858,7 @@ struct mlx4_dev {
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 	struct mlx4_vf_dev     *dev_vfs;
+	u8  uar_page_shift;
 };
 
 struct mlx4_clock_params {
@@ -1528,4 +1531,14 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev,
 int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
 				   struct mlx4_clock_params *params);
 
+static inline int mlx4_to_hw_uar_index(struct mlx4_dev *dev, int index)
+{
+	return (index << (PAGE_SHIFT - dev->uar_page_shift));
+}
+
+static inline int mlx4_get_num_reserved_uar(struct mlx4_dev *dev)
+{
+	/* The first 128 UARs are used for EQ doorbells */
+	return (128 >> (PAGE_SHIFT - dev->uar_page_shift));
+}
 #endif /* MLX4_DEVICE_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 231ab6bcea76..51f1e540fc2b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -207,15 +207,15 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_dmac[0x1];
 	u8         outer_smac[0x1];
 	u8         outer_ether_type[0x1];
-	u8         reserved_0[0x1];
+	u8         reserved_at_3[0x1];
 	u8         outer_first_prio[0x1];
 	u8         outer_first_cfi[0x1];
 	u8         outer_first_vid[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_7[0x1];
 	u8         outer_second_prio[0x1];
 	u8         outer_second_cfi[0x1];
 	u8         outer_second_vid[0x1];
-	u8         reserved_2[0x1];
+	u8         reserved_at_b[0x1];
 	u8         outer_sip[0x1];
 	u8         outer_dip[0x1];
 	u8         outer_frag[0x1];
@@ -230,21 +230,21 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_gre_protocol[0x1];
 	u8         outer_gre_key[0x1];
 	u8         outer_vxlan_vni[0x1];
-	u8         reserved_3[0x5];
+	u8         reserved_at_1a[0x5];
 	u8         source_eswitch_port[0x1];
 
 	u8         inner_dmac[0x1];
 	u8         inner_smac[0x1];
 	u8         inner_ether_type[0x1];
-	u8         reserved_4[0x1];
+	u8         reserved_at_23[0x1];
 	u8         inner_first_prio[0x1];
 	u8         inner_first_cfi[0x1];
 	u8         inner_first_vid[0x1];
-	u8         reserved_5[0x1];
+	u8         reserved_at_27[0x1];
 	u8         inner_second_prio[0x1];
 	u8         inner_second_cfi[0x1];
 	u8         inner_second_vid[0x1];
-	u8         reserved_6[0x1];
+	u8         reserved_at_2b[0x1];
 	u8         inner_sip[0x1];
 	u8         inner_dip[0x1];
 	u8         inner_frag[0x1];
@@ -256,37 +256,37 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         inner_tcp_sport[0x1];
 	u8         inner_tcp_dport[0x1];
 	u8         inner_tcp_flags[0x1];
-	u8         reserved_7[0x9];
+	u8         reserved_at_37[0x9];
 
-	u8         reserved_8[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         ft_support[0x1];
-	u8         reserved_0[0x2];
+	u8         reserved_at_1[0x2];
 	u8	   flow_modify_en[0x1];
 	u8         modify_root[0x1];
 	u8         identified_miss_table_mode[0x1];
 	u8         flow_table_modify[0x1];
-	u8         reserved_1[0x19];
+	u8         reserved_at_7[0x19];
 
-	u8         reserved_2[0x2];
+	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
-	u8         reserved_3[0x10];
+	u8         reserved_at_28[0x10];
 	u8         max_ft_level[0x8];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_5[0x18];
+	u8         reserved_at_60[0x18];
 	u8         log_max_ft_num[0x8];
 
-	u8         reserved_6[0x18];
+	u8         reserved_at_80[0x18];
 	u8         log_max_destination[0x8];
 
-	u8         reserved_7[0x18];
+	u8         reserved_at_a0[0x18];
 	u8         log_max_flow[0x8];
 
-	u8         reserved_8[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support;
 
@@ -298,13 +298,13 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits {
 	u8         receive[0x1];
 	u8         write[0x1];
 	u8         read[0x1];
-	u8         reserved_0[0x1];
+	u8         reserved_at_4[0x1];
 	u8         srq_receive[0x1];
-	u8         reserved_1[0x1a];
+	u8         reserved_at_6[0x1a];
 };
 
 struct mlx5_ifc_ipv4_layout_bits {
-	u8         reserved_0[0x60];
+	u8         reserved_at_0[0x60];
 
 	u8         ipv4[0x20];
 };
@@ -316,7 +316,7 @@ struct mlx5_ifc_ipv6_layout_bits {
 union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits {
 	struct mlx5_ifc_ipv6_layout_bits ipv6_layout;
 	struct mlx5_ifc_ipv4_layout_bits ipv4_layout;
-	u8         reserved_0[0x80];
+	u8         reserved_at_0[0x80];
 };
 
 struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
@@ -336,15 +336,15 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	u8         ip_dscp[0x6];
 	u8         ip_ecn[0x2];
 	u8         vlan_tag[0x1];
-	u8         reserved_0[0x1];
+	u8         reserved_at_91[0x1];
 	u8         frag[0x1];
-	u8         reserved_1[0x4];
+	u8         reserved_at_93[0x4];
 	u8         tcp_flags[0x9];
 
 	u8         tcp_sport[0x10];
 	u8         tcp_dport[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_c0[0x20];
 
 	u8         udp_sport[0x10];
 	u8         udp_dport[0x10];
@@ -355,9 +355,9 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 };
 
 struct mlx5_ifc_fte_match_set_misc_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         source_port[0x10];
 
 	u8         outer_second_prio[0x3];
@@ -369,31 +369,31 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 
 	u8         outer_second_vlan_tag[0x1];
 	u8         inner_second_vlan_tag[0x1];
-	u8         reserved_2[0xe];
+	u8         reserved_at_62[0xe];
 	u8         gre_protocol[0x10];
 
 	u8         gre_key_h[0x18];
 	u8         gre_key_l[0x8];
 
 	u8         vxlan_vni[0x18];
-	u8         reserved_3[0x8];
+	u8         reserved_at_b8[0x8];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_c0[0x20];
 
-	u8         reserved_5[0xc];
+	u8         reserved_at_e0[0xc];
 	u8         outer_ipv6_flow_label[0x14];
 
-	u8         reserved_6[0xc];
+	u8         reserved_at_100[0xc];
 	u8         inner_ipv6_flow_label[0x14];
 
-	u8         reserved_7[0xe0];
+	u8         reserved_at_120[0xe0];
 };
 
 struct mlx5_ifc_cmd_pas_bits {
 	u8         pa_h[0x20];
 
 	u8         pa_l[0x14];
-	u8         reserved_0[0xc];
+	u8         reserved_at_34[0xc];
 };
 
 struct mlx5_ifc_uint64_bits {
@@ -418,31 +418,31 @@ enum {
 struct mlx5_ifc_ads_bits {
 	u8         fl[0x1];
 	u8         free_ar[0x1];
-	u8         reserved_0[0xe];
+	u8         reserved_at_2[0xe];
 	u8         pkey_index[0x10];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_20[0x8];
 	u8         grh[0x1];
 	u8         mlid[0x7];
 	u8         rlid[0x10];
 
 	u8         ack_timeout[0x5];
-	u8         reserved_2[0x3];
+	u8         reserved_at_45[0x3];
 	u8         src_addr_index[0x8];
-	u8         reserved_3[0x4];
+	u8         reserved_at_50[0x4];
 	u8         stat_rate[0x4];
 	u8         hop_limit[0x8];
 
-	u8         reserved_4[0x4];
+	u8         reserved_at_60[0x4];
 	u8         tclass[0x8];
 	u8         flow_label[0x14];
 
 	u8         rgid_rip[16][0x8];
 
-	u8         reserved_5[0x4];
+	u8         reserved_at_100[0x4];
 	u8         f_dscp[0x1];
 	u8         f_ecn[0x1];
-	u8         reserved_6[0x1];
+	u8         reserved_at_106[0x1];
 	u8         f_eth_prio[0x1];
 	u8         ecn[0x2];
 	u8         dscp[0x6];
@@ -458,25 +458,25 @@ struct mlx5_ifc_ads_bits {
 };
 
 struct mlx5_ifc_flow_table_nic_cap_bits {
-	u8         reserved_0[0x200];
+	u8         reserved_at_0[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive;
 
-	u8         reserved_1[0x200];
+	u8         reserved_at_400[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer;
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit;
 
-	u8         reserved_2[0x200];
+	u8         reserved_at_a00[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer;
 
-	u8         reserved_3[0x7200];
+	u8         reserved_at_e00[0x7200];
 };
 
 struct mlx5_ifc_flow_table_eswitch_cap_bits {
-	u8     reserved_0[0x200];
+	u8     reserved_at_0[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb;
 
@@ -484,7 +484,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress;
 
-	u8      reserved_1[0x7800];
+	u8      reserved_at_800[0x7800];
 };
 
 struct mlx5_ifc_e_switch_cap_bits {
@@ -493,9 +493,9 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_0[0x1b];
+	u8         reserved_at_5[0x1b];
 
-	u8         reserved_1[0x7e0];
+	u8         reserved_at_20[0x7e0];
 };
 
 struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
@@ -504,51 +504,51 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         lro_cap[0x1];
 	u8         lro_psh_flag[0x1];
 	u8         lro_time_stamp[0x1];
-	u8         reserved_0[0x3];
+	u8         reserved_at_5[0x3];
 	u8         self_lb_en_modifiable[0x1];
-	u8         reserved_1[0x2];
+	u8         reserved_at_9[0x2];
 	u8         max_lso_cap[0x5];
-	u8         reserved_2[0x4];
+	u8         reserved_at_10[0x4];
 	u8         rss_ind_tbl_cap[0x4];
-	u8         reserved_3[0x3];
+	u8         reserved_at_18[0x3];
 	u8         tunnel_lso_const_out_ip_id[0x1];
-	u8         reserved_4[0x2];
+	u8         reserved_at_1c[0x2];
 	u8         tunnel_statless_gre[0x1];
 	u8         tunnel_stateless_vxlan[0x1];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_6[0x10];
+	u8         reserved_at_40[0x10];
 	u8         lro_min_mss_size[0x10];
 
-	u8         reserved_7[0x120];
+	u8         reserved_at_60[0x120];
 
 	u8         lro_timer_supported_periods[4][0x20];
 
-	u8         reserved_8[0x600];
+	u8         reserved_at_200[0x600];
 };
 
 struct mlx5_ifc_roce_cap_bits {
 	u8         roce_apm[0x1];
-	u8         reserved_0[0x1f];
+	u8         reserved_at_1[0x1f];
 
-	u8         reserved_1[0x60];
+	u8         reserved_at_20[0x60];
 
-	u8         reserved_2[0xc];
+	u8         reserved_at_80[0xc];
 	u8         l3_type[0x4];
-	u8         reserved_3[0x8];
+	u8         reserved_at_90[0x8];
 	u8         roce_version[0x8];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         r_roce_dest_udp_port[0x10];
 
 	u8         r_roce_max_src_udp_port[0x10];
 	u8         r_roce_min_src_udp_port[0x10];
 
-	u8         reserved_5[0x10];
+	u8         reserved_at_e0[0x10];
 	u8         roce_address_table_size[0x10];
 
-	u8         reserved_6[0x700];
+	u8         reserved_at_100[0x700];
 };
 
 enum {
@@ -576,35 +576,35 @@ enum {
 };
 
 struct mlx5_ifc_atomic_caps_bits {
-	u8         reserved_0[0x40];
+	u8         reserved_at_0[0x40];
 
 	u8         atomic_req_8B_endianess_mode[0x2];
-	u8         reserved_1[0x4];
+	u8         reserved_at_42[0x4];
 	u8         supported_atomic_req_8B_endianess_mode_1[0x1];
 
-	u8         reserved_2[0x19];
+	u8         reserved_at_47[0x19];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_80[0x10];
 	u8         atomic_operations[0x10];
 
-	u8         reserved_5[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         atomic_size_qp[0x10];
 
-	u8         reserved_6[0x10];
+	u8         reserved_at_c0[0x10];
 	u8         atomic_size_dc[0x10];
 
-	u8         reserved_7[0x720];
+	u8         reserved_at_e0[0x720];
 };
 
 struct mlx5_ifc_odp_cap_bits {
-	u8         reserved_0[0x40];
+	u8         reserved_at_0[0x40];
 
 	u8         sig[0x1];
-	u8         reserved_1[0x1f];
+	u8         reserved_at_41[0x1f];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_odp_per_transport_service_cap_bits rc_odp_caps;
 
@@ -612,7 +612,7 @@ struct mlx5_ifc_odp_cap_bits {
 
 	struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps;
 
-	u8         reserved_3[0x720];
+	u8         reserved_at_e0[0x720];
 };
 
 enum {
@@ -660,55 +660,55 @@ enum {
 };
 
 struct mlx5_ifc_cmd_hca_cap_bits {
-	u8         reserved_0[0x80];
+	u8         reserved_at_0[0x80];
 
 	u8         log_max_srq_sz[0x8];
 	u8         log_max_qp_sz[0x8];
-	u8         reserved_1[0xb];
+	u8         reserved_at_90[0xb];
 	u8         log_max_qp[0x5];
 
-	u8         reserved_2[0xb];
+	u8         reserved_at_a0[0xb];
 	u8         log_max_srq[0x5];
-	u8         reserved_3[0x10];
+	u8         reserved_at_b0[0x10];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         log_max_cq_sz[0x8];
-	u8         reserved_5[0xb];
+	u8         reserved_at_d0[0xb];
 	u8         log_max_cq[0x5];
 
 	u8         log_max_eq_sz[0x8];
-	u8         reserved_6[0x2];
+	u8         reserved_at_e8[0x2];
 	u8         log_max_mkey[0x6];
-	u8         reserved_7[0xc];
+	u8         reserved_at_f0[0xc];
 	u8         log_max_eq[0x4];
 
 	u8         max_indirection[0x8];
-	u8         reserved_8[0x1];
+	u8         reserved_at_108[0x1];
 	u8         log_max_mrw_sz[0x7];
-	u8         reserved_9[0x2];
+	u8         reserved_at_110[0x2];
 	u8         log_max_bsf_list_size[0x6];
-	u8         reserved_10[0x2];
+	u8         reserved_at_118[0x2];
 	u8         log_max_klm_list_size[0x6];
 
-	u8         reserved_11[0xa];
+	u8         reserved_at_120[0xa];
 	u8         log_max_ra_req_dc[0x6];
-	u8         reserved_12[0xa];
+	u8         reserved_at_130[0xa];
 	u8         log_max_ra_res_dc[0x6];
 
-	u8         reserved_13[0xa];
+	u8         reserved_at_140[0xa];
 	u8         log_max_ra_req_qp[0x6];
-	u8         reserved_14[0xa];
+	u8         reserved_at_150[0xa];
 	u8         log_max_ra_res_qp[0x6];
 
 	u8         pad_cap[0x1];
 	u8         cc_query_allowed[0x1];
 	u8         cc_modify_allowed[0x1];
-	u8         reserved_15[0xd];
+	u8         reserved_at_163[0xd];
 	u8         gid_table_size[0x10];
 
 	u8         out_of_seq_cnt[0x1];
 	u8         vport_counters[0x1];
-	u8         reserved_16[0x4];
+	u8         reserved_at_182[0x4];
 	u8         max_qp_cnt[0xa];
 	u8         pkey_table_size[0x10];
 
@@ -716,158 +716,158 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vhca_group_manager[0x1];
 	u8         ib_virt[0x1];
 	u8         eth_virt[0x1];
-	u8         reserved_17[0x1];
+	u8         reserved_at_1a4[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
 	u8         eswitch_flow_table[0x1];
 	u8	   early_vf_enable;
-	u8         reserved_18[0x2];
+	u8         reserved_at_1a8[0x2];
 	u8         local_ca_ack_delay[0x5];
-	u8         reserved_19[0x6];
+	u8         reserved_at_1af[0x6];
 	u8         port_type[0x2];
 	u8         num_ports[0x8];
 
-	u8         reserved_20[0x3];
+	u8         reserved_at_1bf[0x3];
 	u8         log_max_msg[0x5];
-	u8         reserved_21[0x18];
+	u8         reserved_at_1c7[0x18];
 
 	u8         stat_rate_support[0x10];
-	u8         reserved_22[0xc];
+	u8         reserved_at_1ef[0xc];
 	u8         cqe_version[0x4];
 
 	u8         compact_address_vector[0x1];
-	u8         reserved_23[0xe];
+	u8         reserved_at_200[0xe];
 	u8         drain_sigerr[0x1];
 	u8         cmdif_checksum[0x2];
 	u8         sigerr_cqe[0x1];
-	u8         reserved_24[0x1];
+	u8         reserved_at_212[0x1];
 	u8         wq_signature[0x1];
 	u8         sctr_data_cqe[0x1];
-	u8         reserved_25[0x1];
+	u8         reserved_at_215[0x1];
 	u8         sho[0x1];
 	u8         tph[0x1];
 	u8         rf[0x1];
 	u8         dct[0x1];
-	u8         reserved_26[0x1];
+	u8         reserved_at_21a[0x1];
 	u8         eth_net_offloads[0x1];
 	u8         roce[0x1];
 	u8         atomic[0x1];
-	u8         reserved_27[0x1];
+	u8         reserved_at_21e[0x1];
 
 	u8         cq_oi[0x1];
 	u8         cq_resize[0x1];
 	u8         cq_moderation[0x1];
-	u8         reserved_28[0x3];
+	u8         reserved_at_222[0x3];
 	u8         cq_eq_remap[0x1];
 	u8         pg[0x1];
 	u8         block_lb_mc[0x1];
-	u8         reserved_29[0x1];
+	u8         reserved_at_228[0x1];
 	u8         scqe_break_moderation[0x1];
-	u8         reserved_30[0x1];
+	u8         reserved_at_22a[0x1];
 	u8         cd[0x1];
-	u8         reserved_31[0x1];
+	u8         reserved_at_22c[0x1];
 	u8         apm[0x1];
-	u8         reserved_32[0x7];
+	u8         reserved_at_22e[0x7];
 	u8         qkv[0x1];
 	u8         pkv[0x1];
-	u8         reserved_33[0x4];
+	u8         reserved_at_237[0x4];
 	u8         xrc[0x1];
 	u8         ud[0x1];
 	u8         uc[0x1];
 	u8         rc[0x1];
 
-	u8         reserved_34[0xa];
+	u8         reserved_at_23f[0xa];
 	u8         uar_sz[0x6];
-	u8         reserved_35[0x8];
+	u8         reserved_at_24f[0x8];
 	u8         log_pg_sz[0x8];
 
 	u8         bf[0x1];
-	u8         reserved_36[0x1];
+	u8         reserved_at_260[0x1];
 	u8         pad_tx_eth_packet[0x1];
-	u8         reserved_37[0x8];
+	u8         reserved_at_262[0x8];
 	u8         log_bf_reg_size[0x5];
-	u8         reserved_38[0x10];
+	u8         reserved_at_26f[0x10];
 
-	u8         reserved_39[0x10];
+	u8         reserved_at_27f[0x10];
 	u8         max_wqe_sz_sq[0x10];
 
-	u8         reserved_40[0x10];
+	u8         reserved_at_29f[0x10];
 	u8         max_wqe_sz_rq[0x10];
 
-	u8         reserved_41[0x10];
+	u8         reserved_at_2bf[0x10];
 	u8         max_wqe_sz_sq_dc[0x10];
 
-	u8         reserved_42[0x7];
+	u8         reserved_at_2df[0x7];
 	u8         max_qp_mcg[0x19];
 
-	u8         reserved_43[0x18];
+	u8         reserved_at_2ff[0x18];
 	u8         log_max_mcg[0x8];
 
-	u8         reserved_44[0x3];
+	u8         reserved_at_31f[0x3];
 	u8         log_max_transport_domain[0x5];
-	u8         reserved_45[0x3];
+	u8         reserved_at_327[0x3];
 	u8         log_max_pd[0x5];
-	u8         reserved_46[0xb];
+	u8         reserved_at_32f[0xb];
 	u8         log_max_xrcd[0x5];
 
-	u8         reserved_47[0x20];
+	u8         reserved_at_33f[0x20];
 
-	u8         reserved_48[0x3];
+	u8         reserved_at_35f[0x3];
 	u8         log_max_rq[0x5];
-	u8         reserved_49[0x3];
+	u8         reserved_at_367[0x3];
 	u8         log_max_sq[0x5];
-	u8         reserved_50[0x3];
+	u8         reserved_at_36f[0x3];
 	u8         log_max_tir[0x5];
-	u8         reserved_51[0x3];
+	u8         reserved_at_377[0x3];
 	u8         log_max_tis[0x5];
 
 	u8         basic_cyclic_rcv_wqe[0x1];
-	u8         reserved_52[0x2];
+	u8         reserved_at_380[0x2];
 	u8         log_max_rmp[0x5];
-	u8         reserved_53[0x3];
+	u8         reserved_at_387[0x3];
 	u8         log_max_rqt[0x5];
-	u8         reserved_54[0x3];
+	u8         reserved_at_38f[0x3];
 	u8         log_max_rqt_size[0x5];
-	u8         reserved_55[0x3];
+	u8         reserved_at_397[0x3];
 	u8         log_max_tis_per_sq[0x5];
 
-	u8         reserved_56[0x3];
+	u8         reserved_at_39f[0x3];
 	u8         log_max_stride_sz_rq[0x5];
-	u8         reserved_57[0x3];
+	u8         reserved_at_3a7[0x3];
 	u8         log_min_stride_sz_rq[0x5];
-	u8         reserved_58[0x3];
+	u8         reserved_at_3af[0x3];
 	u8         log_max_stride_sz_sq[0x5];
-	u8         reserved_59[0x3];
+	u8         reserved_at_3b7[0x3];
 	u8         log_min_stride_sz_sq[0x5];
 
-	u8         reserved_60[0x1b];
+	u8         reserved_at_3bf[0x1b];
 	u8         log_max_wq_sz[0x5];
 
 	u8         nic_vport_change_event[0x1];
-	u8         reserved_61[0xa];
+	u8         reserved_at_3e0[0xa];
 	u8         log_max_vlan_list[0x5];
-	u8         reserved_62[0x3];
+	u8         reserved_at_3ef[0x3];
 	u8         log_max_current_mc_list[0x5];
-	u8         reserved_63[0x3];
+	u8         reserved_at_3f7[0x3];
 	u8         log_max_current_uc_list[0x5];
 
-	u8         reserved_64[0x80];
+	u8         reserved_at_3ff[0x80];
 
-	u8         reserved_65[0x3];
+	u8         reserved_at_47f[0x3];
 	u8         log_max_l2_table[0x5];
-	u8         reserved_66[0x8];
+	u8         reserved_at_487[0x8];
 	u8         log_uar_page_sz[0x10];
 
-	u8         reserved_67[0x20];
+	u8         reserved_at_49f[0x20];
 	u8         device_frequency_mhz[0x20];
 	u8         device_frequency_khz[0x20];
-	u8         reserved_68[0x5f];
+	u8         reserved_at_4ff[0x5f];
 	u8         cqe_zip[0x1];
 
 	u8         cqe_zip_timeout[0x10];
 	u8         cqe_zip_max_num[0x10];
 
-	u8         reserved_69[0x220];
+	u8         reserved_at_57f[0x220];
 };
 
 enum mlx5_flow_destination_type {
@@ -880,7 +880,7 @@ struct mlx5_ifc_dest_format_struct_bits {
 	u8         destination_type[0x8];
 	u8         destination_id[0x18];
 
-	u8         reserved_0[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_fte_match_param_bits {
@@ -890,7 +890,7 @@ struct mlx5_ifc_fte_match_param_bits {
 
 	struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers;
 
-	u8         reserved_0[0xa00];
+	u8         reserved_at_600[0xa00];
 };
 
 enum {
@@ -922,18 +922,18 @@ struct mlx5_ifc_wq_bits {
 	u8         wq_signature[0x1];
 	u8         end_padding_mode[0x2];
 	u8         cd_slave[0x1];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         hds_skip_first_sge[0x1];
 	u8         log2_hds_buf_size[0x3];
-	u8         reserved_1[0x7];
+	u8         reserved_at_24[0x7];
 	u8         page_offset[0x5];
 	u8         lwm[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         pd[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_60[0x8];
 	u8         uar_page[0x18];
 
 	u8         dbr_addr[0x40];
@@ -942,60 +942,60 @@ struct mlx5_ifc_wq_bits {
 
 	u8         sw_counter[0x20];
 
-	u8         reserved_4[0xc];
+	u8         reserved_at_100[0xc];
 	u8         log_wq_stride[0x4];
-	u8         reserved_5[0x3];
+	u8         reserved_at_110[0x3];
 	u8         log_wq_pg_sz[0x5];
-	u8         reserved_6[0x3];
+	u8         reserved_at_118[0x3];
 	u8         log_wq_sz[0x5];
 
-	u8         reserved_7[0x4e0];
+	u8         reserved_at_120[0x4e0];
 
 	struct mlx5_ifc_cmd_pas_bits pas[0];
 };
 
 struct mlx5_ifc_rq_num_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         rq_num[0x18];
 };
 
 struct mlx5_ifc_mac_address_layout_bits {
-	u8         reserved_0[0x10];
+	u8         reserved_at_0[0x10];
 	u8         mac_addr_47_32[0x10];
 
 	u8         mac_addr_31_0[0x20];
 };
 
 struct mlx5_ifc_vlan_layout_bits {
-	u8         reserved_0[0x14];
+	u8         reserved_at_0[0x14];
 	u8         vlan[0x0c];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_cong_control_r_roce_ecn_np_bits {
-	u8         reserved_0[0xa0];
+	u8         reserved_at_0[0xa0];
 
 	u8         min_time_between_cnps[0x20];
 
-	u8         reserved_1[0x12];
+	u8         reserved_at_c0[0x12];
 	u8         cnp_dscp[0x6];
-	u8         reserved_2[0x5];
+	u8         reserved_at_d8[0x5];
 	u8         cnp_802p_prio[0x3];
 
-	u8         reserved_3[0x720];
+	u8         reserved_at_e0[0x720];
 };
 
 struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits {
-	u8         reserved_0[0x60];
+	u8         reserved_at_0[0x60];
 
-	u8         reserved_1[0x4];
+	u8         reserved_at_60[0x4];
 	u8         clamp_tgt_rate[0x1];
-	u8         reserved_2[0x3];
+	u8         reserved_at_65[0x3];
 	u8         clamp_tgt_rate_after_time_inc[0x1];
-	u8         reserved_3[0x17];
+	u8         reserved_at_69[0x17];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_80[0x20];
 
 	u8         rpg_time_reset[0x20];
 
@@ -1015,7 +1015,7 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits {
 
 	u8         rpg_min_rate[0x20];
 
-	u8         reserved_5[0xe0];
+	u8         reserved_at_1c0[0xe0];
 
 	u8         rate_to_set_on_first_cnp[0x20];
 
@@ -1025,15 +1025,15 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits {
 
 	u8         rate_reduce_monitor_period[0x20];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_320[0x20];
 
 	u8         initial_alpha_value[0x20];
 
-	u8         reserved_7[0x4a0];
+	u8         reserved_at_360[0x4a0];
 };
 
 struct mlx5_ifc_cong_control_802_1qau_rp_bits {
-	u8         reserved_0[0x80];
+	u8         reserved_at_0[0x80];
 
 	u8         rppp_max_rps[0x20];
 
@@ -1055,7 +1055,7 @@ struct mlx5_ifc_cong_control_802_1qau_rp_bits {
 
 	u8         rpg_min_rate[0x20];
 
-	u8         reserved_1[0x640];
+	u8         reserved_at_1c0[0x640];
 };
 
 enum {
@@ -1205,7 +1205,7 @@ struct mlx5_ifc_phys_layer_cntrs_bits {
 
 	u8         successful_recovery_events[0x20];
 
-	u8         reserved_0[0x180];
+	u8         reserved_at_640[0x180];
 };
 
 struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits {
@@ -1213,7 +1213,7 @@ struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits {
 
 	u8         transmit_queue_low[0x20];
 
-	u8         reserved_0[0x780];
+	u8         reserved_at_40[0x780];
 };
 
 struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
@@ -1221,7 +1221,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
 
 	u8         rx_octets_low[0x20];
 
-	u8         reserved_0[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	u8         rx_frames_high[0x20];
 
@@ -1231,7 +1231,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
 
 	u8         tx_octets_low[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_180[0xc0];
 
 	u8         tx_frames_high[0x20];
 
@@ -1257,7 +1257,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
 
 	u8         rx_pause_transition_low[0x20];
 
-	u8         reserved_2[0x400];
+	u8         reserved_at_3c0[0x400];
 };
 
 struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits {
@@ -1265,7 +1265,7 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits {
 
 	u8         port_transmit_wait_low[0x20];
 
-	u8         reserved_0[0x780];
+	u8         reserved_at_40[0x780];
 };
 
 struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits {
@@ -1333,7 +1333,7 @@ struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits {
 
 	u8         dot3out_pause_frames_low[0x20];
 
-	u8         reserved_0[0x3c0];
+	u8         reserved_at_400[0x3c0];
 };
 
 struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits {
@@ -1421,7 +1421,7 @@ struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits {
 
 	u8         ether_stats_pkts8192to10239octets_low[0x20];
 
-	u8         reserved_0[0x280];
+	u8         reserved_at_540[0x280];
 };
 
 struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits {
@@ -1477,7 +1477,7 @@ struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits {
 
 	u8         if_out_broadcast_pkts_low[0x20];
 
-	u8         reserved_0[0x480];
+	u8         reserved_at_340[0x480];
 };
 
 struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits {
@@ -1557,54 +1557,54 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits {
 
 	u8         a_pause_mac_ctrl_frames_transmitted_low[0x20];
 
-	u8         reserved_0[0x300];
+	u8         reserved_at_4c0[0x300];
 };
 
 struct mlx5_ifc_cmd_inter_comp_event_bits {
 	u8         command_completion_vector[0x20];
 
-	u8         reserved_0[0xc0];
+	u8         reserved_at_20[0xc0];
 };
 
 struct mlx5_ifc_stall_vl_event_bits {
-	u8         reserved_0[0x18];
+	u8         reserved_at_0[0x18];
 	u8         port_num[0x1];
-	u8         reserved_1[0x3];
+	u8         reserved_at_19[0x3];
 	u8         vl[0x4];
 
-	u8         reserved_2[0xa0];
+	u8         reserved_at_20[0xa0];
 };
 
 struct mlx5_ifc_db_bf_congestion_event_bits {
 	u8         event_subtype[0x8];
-	u8         reserved_0[0x8];
+	u8         reserved_at_8[0x8];
 	u8         congestion_level[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_2[0xa0];
+	u8         reserved_at_20[0xa0];
 };
 
 struct mlx5_ifc_gpio_event_bits {
-	u8         reserved_0[0x60];
+	u8         reserved_at_0[0x60];
 
 	u8         gpio_event_hi[0x20];
 
 	u8         gpio_event_lo[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_a0[0x40];
 };
 
 struct mlx5_ifc_port_state_change_event_bits {
-	u8         reserved_0[0x40];
+	u8         reserved_at_0[0x40];
 
 	u8         port_num[0x4];
-	u8         reserved_1[0x1c];
+	u8         reserved_at_44[0x1c];
 
-	u8         reserved_2[0x80];
+	u8         reserved_at_60[0x80];
 };
 
 struct mlx5_ifc_dropped_packet_logged_bits {
-	u8         reserved_0[0xe0];
+	u8         reserved_at_0[0xe0];
 };
 
 enum {
@@ -1613,15 +1613,15 @@ enum {
 };
 
 struct mlx5_ifc_cq_error_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         syndrome[0x8];
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_60[0x80];
 };
 
 struct mlx5_ifc_rdma_page_fault_event_bits {
@@ -1629,14 +1629,14 @@ struct mlx5_ifc_rdma_page_fault_event_bits {
 
 	u8         r_key[0x20];
 
-	u8         reserved_0[0x10];
+	u8         reserved_at_40[0x10];
 	u8         packet_len[0x10];
 
 	u8         rdma_op_len[0x20];
 
 	u8         rdma_va[0x40];
 
-	u8         reserved_1[0x5];
+	u8         reserved_at_c0[0x5];
 	u8         rdma[0x1];
 	u8         write[0x1];
 	u8         requestor[0x1];
@@ -1646,15 +1646,15 @@ struct mlx5_ifc_rdma_page_fault_event_bits {
 struct mlx5_ifc_wqe_associated_page_fault_event_bits {
 	u8         bytes_committed[0x20];
 
-	u8         reserved_0[0x10];
+	u8         reserved_at_20[0x10];
 	u8         wqe_index[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_40[0x10];
 	u8         len[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_60[0x60];
 
-	u8         reserved_3[0x5];
+	u8         reserved_at_c0[0x5];
 	u8         rdma[0x1];
 	u8         write_read[0x1];
 	u8         requestor[0x1];
@@ -1662,26 +1662,26 @@ struct mlx5_ifc_wqe_associated_page_fault_event_bits {
 };
 
 struct mlx5_ifc_qp_events_bits {
-	u8         reserved_0[0xa0];
+	u8         reserved_at_0[0xa0];
 
 	u8         type[0x8];
-	u8         reserved_1[0x18];
+	u8         reserved_at_a8[0x18];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         qpn_rqn_sqn[0x18];
 };
 
 struct mlx5_ifc_dct_events_bits {
-	u8         reserved_0[0xc0];
+	u8         reserved_at_0[0xc0];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         dct_number[0x18];
 };
 
 struct mlx5_ifc_comp_event_bits {
-	u8         reserved_0[0xc0];
+	u8         reserved_at_0[0xc0];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         cq_number[0x18];
 };
 
@@ -1754,41 +1754,41 @@ enum {
 
 struct mlx5_ifc_qpc_bits {
 	u8         state[0x4];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         st[0x8];
-	u8         reserved_1[0x3];
+	u8         reserved_at_10[0x3];
 	u8         pm_state[0x2];
-	u8         reserved_2[0x7];
+	u8         reserved_at_15[0x7];
 	u8         end_padding_mode[0x2];
-	u8         reserved_3[0x2];
+	u8         reserved_at_1e[0x2];
 
 	u8         wq_signature[0x1];
 	u8         block_lb_mc[0x1];
 	u8         atomic_like_write_en[0x1];
 	u8         latency_sensitive[0x1];
-	u8         reserved_4[0x1];
+	u8         reserved_at_24[0x1];
 	u8         drain_sigerr[0x1];
-	u8         reserved_5[0x2];
+	u8         reserved_at_26[0x2];
 	u8         pd[0x18];
 
 	u8         mtu[0x3];
 	u8         log_msg_max[0x5];
-	u8         reserved_6[0x1];
+	u8         reserved_at_48[0x1];
 	u8         log_rq_size[0x4];
 	u8         log_rq_stride[0x3];
 	u8         no_sq[0x1];
 	u8         log_sq_size[0x4];
-	u8         reserved_7[0x6];
+	u8         reserved_at_55[0x6];
 	u8         rlky[0x1];
-	u8         reserved_8[0x4];
+	u8         reserved_at_5c[0x4];
 
 	u8         counter_set_id[0x8];
 	u8         uar_page[0x18];
 
-	u8         reserved_9[0x8];
+	u8         reserved_at_80[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_10[0x3];
+	u8         reserved_at_a0[0x3];
 	u8         log_page_size[0x5];
 	u8         remote_qpn[0x18];
 
@@ -1797,66 +1797,66 @@ struct mlx5_ifc_qpc_bits {
 	struct mlx5_ifc_ads_bits secondary_address_path;
 
 	u8         log_ack_req_freq[0x4];
-	u8         reserved_11[0x4];
+	u8         reserved_at_384[0x4];
 	u8         log_sra_max[0x3];
-	u8         reserved_12[0x2];
+	u8         reserved_at_38b[0x2];
 	u8         retry_count[0x3];
 	u8         rnr_retry[0x3];
-	u8         reserved_13[0x1];
+	u8         reserved_at_393[0x1];
 	u8         fre[0x1];
 	u8         cur_rnr_retry[0x3];
 	u8         cur_retry_count[0x3];
-	u8         reserved_14[0x5];
+	u8         reserved_at_39b[0x5];
 
-	u8         reserved_15[0x20];
+	u8         reserved_at_3a0[0x20];
 
-	u8         reserved_16[0x8];
+	u8         reserved_at_3c0[0x8];
 	u8         next_send_psn[0x18];
 
-	u8         reserved_17[0x8];
+	u8         reserved_at_3e0[0x8];
 	u8         cqn_snd[0x18];
 
-	u8         reserved_18[0x40];
+	u8         reserved_at_400[0x40];
 
-	u8         reserved_19[0x8];
+	u8         reserved_at_440[0x8];
 	u8         last_acked_psn[0x18];
 
-	u8         reserved_20[0x8];
+	u8         reserved_at_460[0x8];
 	u8         ssn[0x18];
 
-	u8         reserved_21[0x8];
+	u8         reserved_at_480[0x8];
 	u8         log_rra_max[0x3];
-	u8         reserved_22[0x1];
+	u8         reserved_at_48b[0x1];
 	u8         atomic_mode[0x4];
 	u8         rre[0x1];
 	u8         rwe[0x1];
 	u8         rae[0x1];
-	u8         reserved_23[0x1];
+	u8         reserved_at_493[0x1];
 	u8         page_offset[0x6];
-	u8         reserved_24[0x3];
+	u8         reserved_at_49a[0x3];
 	u8         cd_slave_receive[0x1];
 	u8         cd_slave_send[0x1];
 	u8         cd_master[0x1];
 
-	u8         reserved_25[0x3];
+	u8         reserved_at_4a0[0x3];
 	u8         min_rnr_nak[0x5];
 	u8         next_rcv_psn[0x18];
 
-	u8         reserved_26[0x8];
+	u8         reserved_at_4c0[0x8];
 	u8         xrcd[0x18];
 
-	u8         reserved_27[0x8];
+	u8         reserved_at_4e0[0x8];
 	u8         cqn_rcv[0x18];
 
 	u8         dbr_addr[0x40];
 
 	u8         q_key[0x20];
 
-	u8         reserved_28[0x5];
+	u8         reserved_at_560[0x5];
 	u8         rq_type[0x3];
 	u8         srqn_rmpn[0x18];
 
-	u8         reserved_29[0x8];
+	u8         reserved_at_580[0x8];
 	u8         rmsn[0x18];
 
 	u8         hw_sq_wqebb_counter[0x10];
@@ -1866,33 +1866,33 @@ struct mlx5_ifc_qpc_bits {
 
 	u8         sw_rq_counter[0x20];
 
-	u8         reserved_30[0x20];
+	u8         reserved_at_600[0x20];
 
-	u8         reserved_31[0xf];
+	u8         reserved_at_620[0xf];
 	u8         cgs[0x1];
 	u8         cs_req[0x8];
 	u8         cs_res[0x8];
 
 	u8         dc_access_key[0x40];
 
-	u8         reserved_32[0xc0];
+	u8         reserved_at_680[0xc0];
 };
 
 struct mlx5_ifc_roce_addr_layout_bits {
 	u8         source_l3_address[16][0x8];
 
-	u8         reserved_0[0x3];
+	u8         reserved_at_80[0x3];
 	u8         vlan_valid[0x1];
 	u8         vlan_id[0xc];
 	u8         source_mac_47_32[0x10];
 
 	u8         source_mac_31_0[0x20];
 
-	u8         reserved_1[0x14];
+	u8         reserved_at_c0[0x14];
 	u8         roce_l3_type[0x4];
 	u8         roce_version[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_e0[0x20];
 };
 
 union mlx5_ifc_hca_cap_union_bits {
@@ -1904,7 +1904,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
-	u8         reserved_0[0x8000];
+	u8         reserved_at_0[0x8000];
 };
 
 enum {
@@ -1914,24 +1914,24 @@ enum {
 };
 
 struct mlx5_ifc_flow_context_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         group_id[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         flow_tag[0x18];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_60[0x10];
 	u8         action[0x10];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_80[0x8];
 	u8         destination_list_size[0x18];
 
-	u8         reserved_4[0x160];
+	u8         reserved_at_a0[0x160];
 
 	struct mlx5_ifc_fte_match_param_bits match_value;
 
-	u8         reserved_5[0x600];
+	u8         reserved_at_1200[0x600];
 
 	struct mlx5_ifc_dest_format_struct_bits destination[0];
 };
@@ -1944,43 +1944,43 @@ enum {
 struct mlx5_ifc_xrc_srqc_bits {
 	u8         state[0x4];
 	u8         log_xrc_srq_size[0x4];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         wq_signature[0x1];
 	u8         cont_srq[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_22[0x1];
 	u8         rlky[0x1];
 	u8         basic_cyclic_rcv_wqe[0x1];
 	u8         log_rq_stride[0x3];
 	u8         xrcd[0x18];
 
 	u8         page_offset[0x6];
-	u8         reserved_2[0x2];
+	u8         reserved_at_46[0x2];
 	u8         cqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         user_index_equal_xrc_srqn[0x1];
-	u8         reserved_4[0x1];
+	u8         reserved_at_81[0x1];
 	u8         log_page_size[0x6];
 	u8         user_index[0x18];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_a0[0x20];
 
-	u8         reserved_6[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
 
 	u8         lwm[0x10];
 	u8         wqe_cnt[0x10];
 
-	u8         reserved_7[0x40];
+	u8         reserved_at_100[0x40];
 
 	u8         db_record_addr_h[0x20];
 
 	u8         db_record_addr_l[0x1e];
-	u8         reserved_8[0x2];
+	u8         reserved_at_17e[0x2];
 
-	u8         reserved_9[0x80];
+	u8         reserved_at_180[0x80];
 };
 
 struct mlx5_ifc_traffic_counter_bits {
@@ -1990,16 +1990,16 @@ struct mlx5_ifc_traffic_counter_bits {
 };
 
 struct mlx5_ifc_tisc_bits {
-	u8         reserved_0[0xc];
+	u8         reserved_at_0[0xc];
 	u8         prio[0x4];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x100];
+	u8         reserved_at_20[0x100];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_120[0x8];
 	u8         transport_domain[0x18];
 
-	u8         reserved_4[0x3c0];
+	u8         reserved_at_140[0x3c0];
 };
 
 enum {
@@ -2024,31 +2024,31 @@ enum {
 };
 
 struct mlx5_ifc_tirc_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         disp_type[0x4];
-	u8         reserved_1[0x1c];
+	u8         reserved_at_24[0x1c];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
-	u8         reserved_3[0x4];
+	u8         reserved_at_80[0x4];
 	u8         lro_timeout_period_usecs[0x10];
 	u8         lro_enable_mask[0x4];
 	u8         lro_max_ip_payload_size[0x8];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_a0[0x40];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         inline_rqn[0x18];
 
 	u8         rx_hash_symmetric[0x1];
-	u8         reserved_6[0x1];
+	u8         reserved_at_101[0x1];
 	u8         tunneled_offload_en[0x1];
-	u8         reserved_7[0x5];
+	u8         reserved_at_103[0x5];
 	u8         indirect_table[0x18];
 
 	u8         rx_hash_fn[0x4];
-	u8         reserved_8[0x2];
+	u8         reserved_at_124[0x2];
 	u8         self_lb_block[0x2];
 	u8         transport_domain[0x18];
 
@@ -2058,7 +2058,7 @@ struct mlx5_ifc_tirc_bits {
 
 	struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_inner;
 
-	u8         reserved_9[0x4c0];
+	u8         reserved_at_2c0[0x4c0];
 };
 
 enum {
@@ -2069,39 +2069,39 @@ enum {
 struct mlx5_ifc_srqc_bits {
 	u8         state[0x4];
 	u8         log_srq_size[0x4];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         wq_signature[0x1];
 	u8         cont_srq[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_22[0x1];
 	u8         rlky[0x1];
-	u8         reserved_2[0x1];
+	u8         reserved_at_24[0x1];
 	u8         log_rq_stride[0x3];
 	u8         xrcd[0x18];
 
 	u8         page_offset[0x6];
-	u8         reserved_3[0x2];
+	u8         reserved_at_46[0x2];
 	u8         cqn[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_60[0x20];
 
-	u8         reserved_5[0x2];
+	u8         reserved_at_80[0x2];
 	u8         log_page_size[0x6];
-	u8         reserved_6[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_a0[0x20];
 
-	u8         reserved_8[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
 
 	u8         lwm[0x10];
 	u8         wqe_cnt[0x10];
 
-	u8         reserved_9[0x40];
+	u8         reserved_at_100[0x40];
 
 	u8         dbr_addr[0x40];
 
-	u8         reserved_10[0x80];
+	u8         reserved_at_180[0x80];
 };
 
 enum {
@@ -2115,39 +2115,39 @@ struct mlx5_ifc_sqc_bits {
 	u8         cd_master[0x1];
 	u8         fre[0x1];
 	u8         flush_in_error_en[0x1];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         state[0x4];
-	u8         reserved_1[0x14];
+	u8         reserved_at_c[0x14];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_20[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_4[0xa0];
+	u8         reserved_at_60[0xa0];
 
 	u8         tis_lst_sz[0x10];
-	u8         reserved_5[0x10];
+	u8         reserved_at_110[0x10];
 
-	u8         reserved_6[0x40];
+	u8         reserved_at_120[0x40];
 
-	u8         reserved_7[0x8];
+	u8         reserved_at_160[0x8];
 	u8         tis_num_0[0x18];
 
 	struct mlx5_ifc_wq_bits wq;
 };
 
 struct mlx5_ifc_rqtc_bits {
-	u8         reserved_0[0xa0];
+	u8         reserved_at_0[0xa0];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         rqt_max_size[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_c0[0x10];
 	u8         rqt_actual_size[0x10];
 
-	u8         reserved_3[0x6a0];
+	u8         reserved_at_e0[0x6a0];
 
 	struct mlx5_ifc_rq_num_bits rq_num[0];
 };
@@ -2165,27 +2165,27 @@ enum {
 
 struct mlx5_ifc_rqc_bits {
 	u8         rlky[0x1];
-	u8         reserved_0[0x2];
+	u8         reserved_at_1[0x2];
 	u8         vsd[0x1];
 	u8         mem_rq_type[0x4];
 	u8         state[0x4];
-	u8         reserved_1[0x1];
+	u8         reserved_at_c[0x1];
 	u8         flush_in_error_en[0x1];
-	u8         reserved_2[0x12];
+	u8         reserved_at_e[0x12];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_20[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
 	u8         counter_set_id[0x8];
-	u8         reserved_5[0x18];
+	u8         reserved_at_68[0x18];
 
-	u8         reserved_6[0x8];
+	u8         reserved_at_80[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_7[0xe0];
+	u8         reserved_at_a0[0xe0];
 
 	struct mlx5_ifc_wq_bits wq;
 };
@@ -2196,31 +2196,31 @@ enum {
 };
 
 struct mlx5_ifc_rmpc_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         state[0x4];
-	u8         reserved_1[0x14];
+	u8         reserved_at_c[0x14];
 
 	u8         basic_cyclic_rcv_wqe[0x1];
-	u8         reserved_2[0x1f];
+	u8         reserved_at_21[0x1f];
 
-	u8         reserved_3[0x140];
+	u8         reserved_at_40[0x140];
 
 	struct mlx5_ifc_wq_bits wq;
 };
 
 struct mlx5_ifc_nic_vport_context_bits {
-	u8         reserved_0[0x1f];
+	u8         reserved_at_0[0x1f];
 	u8         roce_en[0x1];
 
 	u8         arm_change_event[0x1];
-	u8         reserved_1[0x1a];
+	u8         reserved_at_21[0x1a];
 	u8         event_on_mtu[0x1];
 	u8         event_on_promisc_change[0x1];
 	u8         event_on_vlan_change[0x1];
 	u8         event_on_mc_address_change[0x1];
 	u8         event_on_uc_address_change[0x1];
 
-	u8         reserved_2[0xf0];
+	u8         reserved_at_40[0xf0];
 
 	u8         mtu[0x10];
 
@@ -2228,21 +2228,21 @@ struct mlx5_ifc_nic_vport_context_bits {
 	u8         port_guid[0x40];
 	u8         node_guid[0x40];
 
-	u8         reserved_3[0x140];
+	u8         reserved_at_200[0x140];
 	u8         qkey_violation_counter[0x10];
-	u8         reserved_4[0x430];
+	u8         reserved_at_350[0x430];
 
 	u8         promisc_uc[0x1];
 	u8         promisc_mc[0x1];
 	u8         promisc_all[0x1];
-	u8         reserved_5[0x2];
+	u8         reserved_at_783[0x2];
 	u8         allowed_list_type[0x3];
-	u8         reserved_6[0xc];
+	u8         reserved_at_788[0xc];
 	u8         allowed_list_size[0xc];
 
 	struct mlx5_ifc_mac_address_layout_bits permanent_address;
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_7e0[0x20];
 
 	u8         current_uc_mac_address[0][0x40];
 };
@@ -2254,9 +2254,9 @@ enum {
 };
 
 struct mlx5_ifc_mkc_bits {
-	u8         reserved_0[0x1];
+	u8         reserved_at_0[0x1];
 	u8         free[0x1];
-	u8         reserved_1[0xd];
+	u8         reserved_at_2[0xd];
 	u8         small_fence_on_rdma_read_response[0x1];
 	u8         umr_en[0x1];
 	u8         a[0x1];
@@ -2265,19 +2265,19 @@ struct mlx5_ifc_mkc_bits {
 	u8         lw[0x1];
 	u8         lr[0x1];
 	u8         access_mode[0x2];
-	u8         reserved_2[0x8];
+	u8         reserved_at_18[0x8];
 
 	u8         qpn[0x18];
 	u8         mkey_7_0[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         length64[0x1];
 	u8         bsf_en[0x1];
 	u8         sync_umr[0x1];
-	u8         reserved_4[0x2];
+	u8         reserved_at_63[0x2];
 	u8         expected_sigerr_count[0x1];
-	u8         reserved_5[0x1];
+	u8         reserved_at_66[0x1];
 	u8         en_rinval[0x1];
 	u8         pd[0x18];
 
@@ -2287,18 +2287,18 @@ struct mlx5_ifc_mkc_bits {
 
 	u8         bsf_octword_size[0x20];
 
-	u8         reserved_6[0x80];
+	u8         reserved_at_120[0x80];
 
 	u8         translations_octword_size[0x20];
 
-	u8         reserved_7[0x1b];
+	u8         reserved_at_1c0[0x1b];
 	u8         log_page_size[0x5];
 
-	u8         reserved_8[0x20];
+	u8         reserved_at_1e0[0x20];
 };
 
 struct mlx5_ifc_pkey_bits {
-	u8         reserved_0[0x10];
+	u8         reserved_at_0[0x10];
 	u8         pkey[0x10];
 };
 
@@ -2309,19 +2309,19 @@ struct mlx5_ifc_array128_auto_bits {
 struct mlx5_ifc_hca_vport_context_bits {
 	u8         field_select[0x20];
 
-	u8         reserved_0[0xe0];
+	u8         reserved_at_20[0xe0];
 
 	u8         sm_virt_aware[0x1];
 	u8         has_smi[0x1];
 	u8         has_raw[0x1];
 	u8         grh_required[0x1];
-	u8         reserved_1[0xc];
+	u8         reserved_at_104[0xc];
 	u8         port_physical_state[0x4];
 	u8         vport_state_policy[0x4];
 	u8         port_state[0x4];
 	u8         vport_state[0x4];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_120[0x20];
 
 	u8         system_image_guid[0x40];
 
@@ -2337,33 +2337,33 @@ struct mlx5_ifc_hca_vport_context_bits {
 
 	u8         cap_mask2_field_select[0x20];
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_280[0x80];
 
 	u8         lid[0x10];
-	u8         reserved_4[0x4];
+	u8         reserved_at_310[0x4];
 	u8         init_type_reply[0x4];
 	u8         lmc[0x3];
 	u8         subnet_timeout[0x5];
 
 	u8         sm_lid[0x10];
 	u8         sm_sl[0x4];
-	u8         reserved_5[0xc];
+	u8         reserved_at_334[0xc];
 
 	u8         qkey_violation_counter[0x10];
 	u8         pkey_violation_counter[0x10];
 
-	u8         reserved_6[0xca0];
+	u8         reserved_at_360[0xca0];
 };
 
 struct mlx5_ifc_esw_vport_context_bits {
-	u8         reserved_0[0x3];
+	u8         reserved_at_0[0x3];
 	u8         vport_svlan_strip[0x1];
 	u8         vport_cvlan_strip[0x1];
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert[0x2];
-	u8         reserved_1[0x18];
+	u8         reserved_at_8[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 
 	u8         svlan_cfi[0x1];
 	u8         svlan_pcp[0x3];
@@ -2372,7 +2372,7 @@ struct mlx5_ifc_esw_vport_context_bits {
 	u8         cvlan_pcp[0x3];
 	u8         cvlan_id[0xc];
 
-	u8         reserved_3[0x7a0];
+	u8         reserved_at_60[0x7a0];
 };
 
 enum {
@@ -2387,41 +2387,41 @@ enum {
 
 struct mlx5_ifc_eqc_bits {
 	u8         status[0x4];
-	u8         reserved_0[0x9];
+	u8         reserved_at_4[0x9];
 	u8         ec[0x1];
 	u8         oi[0x1];
-	u8         reserved_1[0x5];
+	u8         reserved_at_f[0x5];
 	u8         st[0x4];
-	u8         reserved_2[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_4[0x14];
+	u8         reserved_at_40[0x14];
 	u8         page_offset[0x6];
-	u8         reserved_5[0x6];
+	u8         reserved_at_5a[0x6];
 
-	u8         reserved_6[0x3];
+	u8         reserved_at_60[0x3];
 	u8         log_eq_size[0x5];
 	u8         uar_page[0x18];
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_80[0x20];
 
-	u8         reserved_8[0x18];
+	u8         reserved_at_a0[0x18];
 	u8         intr[0x8];
 
-	u8         reserved_9[0x3];
+	u8         reserved_at_c0[0x3];
 	u8         log_page_size[0x5];
-	u8         reserved_10[0x18];
+	u8         reserved_at_c8[0x18];
 
-	u8         reserved_11[0x60];
+	u8         reserved_at_e0[0x60];
 
-	u8         reserved_12[0x8];
+	u8         reserved_at_140[0x8];
 	u8         consumer_counter[0x18];
 
-	u8         reserved_13[0x8];
+	u8         reserved_at_160[0x8];
 	u8         producer_counter[0x18];
 
-	u8         reserved_14[0x80];
+	u8         reserved_at_180[0x80];
 };
 
 enum {
@@ -2445,14 +2445,14 @@ enum {
 };
 
 struct mlx5_ifc_dctc_bits {
-	u8         reserved_0[0x4];
+	u8         reserved_at_0[0x4];
 	u8         state[0x4];
-	u8         reserved_1[0x18];
+	u8         reserved_at_8[0x18];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_20[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
 	u8         counter_set_id[0x8];
@@ -2464,45 +2464,45 @@ struct mlx5_ifc_dctc_bits {
 	u8         latency_sensitive[0x1];
 	u8         rlky[0x1];
 	u8         free_ar[0x1];
-	u8         reserved_4[0xd];
+	u8         reserved_at_73[0xd];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_80[0x8];
 	u8         cs_res[0x8];
-	u8         reserved_6[0x3];
+	u8         reserved_at_90[0x3];
 	u8         min_rnr_nak[0x5];
-	u8         reserved_7[0x8];
+	u8         reserved_at_98[0x8];
 
-	u8         reserved_8[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_9[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
 
 	u8         tclass[0x8];
-	u8         reserved_10[0x4];
+	u8         reserved_at_e8[0x4];
 	u8         flow_label[0x14];
 
 	u8         dc_access_key[0x40];
 
-	u8         reserved_11[0x5];
+	u8         reserved_at_140[0x5];
 	u8         mtu[0x3];
 	u8         port[0x8];
 	u8         pkey_index[0x10];
 
-	u8         reserved_12[0x8];
+	u8         reserved_at_160[0x8];
 	u8         my_addr_index[0x8];
-	u8         reserved_13[0x8];
+	u8         reserved_at_170[0x8];
 	u8         hop_limit[0x8];
 
 	u8         dc_access_key_violation_count[0x20];
 
-	u8         reserved_14[0x14];
+	u8         reserved_at_1a0[0x14];
 	u8         dei_cfi[0x1];
 	u8         eth_prio[0x3];
 	u8         ecn[0x2];
 	u8         dscp[0x6];
 
-	u8         reserved_15[0x40];
+	u8         reserved_at_1c0[0x40];
 };
 
 enum {
@@ -2524,54 +2524,54 @@ enum {
 
 struct mlx5_ifc_cqc_bits {
 	u8         status[0x4];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         cqe_sz[0x3];
 	u8         cc[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_c[0x1];
 	u8         scqe_break_moderation_en[0x1];
 	u8         oi[0x1];
-	u8         reserved_2[0x2];
+	u8         reserved_at_f[0x2];
 	u8         cqe_zip_en[0x1];
 	u8         mini_cqe_res_format[0x2];
 	u8         st[0x4];
-	u8         reserved_3[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_5[0x14];
+	u8         reserved_at_40[0x14];
 	u8         page_offset[0x6];
-	u8         reserved_6[0x6];
+	u8         reserved_at_5a[0x6];
 
-	u8         reserved_7[0x3];
+	u8         reserved_at_60[0x3];
 	u8         log_cq_size[0x5];
 	u8         uar_page[0x18];
 
-	u8         reserved_8[0x4];
+	u8         reserved_at_80[0x4];
 	u8         cq_period[0xc];
 	u8         cq_max_count[0x10];
 
-	u8         reserved_9[0x18];
+	u8         reserved_at_a0[0x18];
 	u8         c_eqn[0x8];
 
-	u8         reserved_10[0x3];
+	u8         reserved_at_c0[0x3];
 	u8         log_page_size[0x5];
-	u8         reserved_11[0x18];
+	u8         reserved_at_c8[0x18];
 
-	u8         reserved_12[0x20];
+	u8         reserved_at_e0[0x20];
 
-	u8         reserved_13[0x8];
+	u8         reserved_at_100[0x8];
 	u8         last_notified_index[0x18];
 
-	u8         reserved_14[0x8];
+	u8         reserved_at_120[0x8];
 	u8         last_solicit_index[0x18];
 
-	u8         reserved_15[0x8];
+	u8         reserved_at_140[0x8];
 	u8         consumer_counter[0x18];
 
-	u8         reserved_16[0x8];
+	u8         reserved_at_160[0x8];
 	u8         producer_counter[0x18];
 
-	u8         reserved_17[0x40];
+	u8         reserved_at_180[0x40];
 
 	u8         dbr_addr[0x40];
 };
@@ -2580,16 +2580,16 @@ union mlx5_ifc_cong_control_roce_ecn_auto_bits {
 	struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp;
 	struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp;
 	struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np;
-	u8         reserved_0[0x800];
+	u8         reserved_at_0[0x800];
 };
 
 struct mlx5_ifc_query_adapter_param_block_bits {
-	u8         reserved_0[0xc0];
+	u8         reserved_at_0[0xc0];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         ieee_vendor_id[0x18];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_e0[0x10];
 	u8         vsd_vendor_id[0x10];
 
 	u8         vsd[208][0x8];
@@ -2600,14 +2600,14 @@ struct mlx5_ifc_query_adapter_param_block_bits {
 union mlx5_ifc_modify_field_select_resize_field_select_auto_bits {
 	struct mlx5_ifc_modify_field_select_bits modify_field_select;
 	struct mlx5_ifc_resize_field_select_bits resize_field_select;
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 };
 
 union mlx5_ifc_field_select_802_1_r_roce_auto_bits {
 	struct mlx5_ifc_field_select_802_1qau_rp_bits field_select_802_1qau_rp;
 	struct mlx5_ifc_field_select_r_roce_rp_bits field_select_r_roce_rp;
 	struct mlx5_ifc_field_select_r_roce_np_bits field_select_r_roce_np;
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 };
 
 union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
@@ -2619,7 +2619,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout;
 	struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout;
 	struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs;
-	u8         reserved_0[0x7c0];
+	u8         reserved_at_0[0x7c0];
 };
 
 union mlx5_ifc_event_auto_bits {
@@ -2635,23 +2635,23 @@ union mlx5_ifc_event_auto_bits {
 	struct mlx5_ifc_db_bf_congestion_event_bits db_bf_congestion_event;
 	struct mlx5_ifc_stall_vl_event_bits stall_vl_event;
 	struct mlx5_ifc_cmd_inter_comp_event_bits cmd_inter_comp_event;
-	u8         reserved_0[0xe0];
+	u8         reserved_at_0[0xe0];
 };
 
 struct mlx5_ifc_health_buffer_bits {
-	u8         reserved_0[0x100];
+	u8         reserved_at_0[0x100];
 
 	u8         assert_existptr[0x20];
 
 	u8         assert_callra[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_140[0x40];
 
 	u8         fw_version[0x20];
 
 	u8         hw_id[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_1c0[0x20];
 
 	u8         irisc_index[0x8];
 	u8         synd[0x8];
@@ -2660,20 +2660,20 @@ struct mlx5_ifc_health_buffer_bits {
 
 struct mlx5_ifc_register_loopback_control_bits {
 	u8         no_lb[0x1];
-	u8         reserved_0[0x7];
+	u8         reserved_at_1[0x7];
 	u8         port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_teardown_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -2683,108 +2683,108 @@ enum {
 
 struct mlx5_ifc_teardown_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         profile[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_sqerr2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_sqerr2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_sqd2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_sqd2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_set_roce_address_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_roce_address_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         roce_address_index[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_50[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_roce_addr_layout_bits roce_address;
 };
 
 struct mlx5_ifc_set_mad_demux_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -2794,89 +2794,89 @@ enum {
 
 struct mlx5_ifc_set_mad_demux_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x6];
+	u8         reserved_at_60[0x6];
 	u8         demux_mode[0x2];
-	u8         reserved_4[0x18];
+	u8         reserved_at_68[0x18];
 };
 
 struct mlx5_ifc_set_l2_table_entry_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_l2_table_entry_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_40[0x60];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_index[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_c0[0x20];
 
-	u8         reserved_5[0x13];
+	u8         reserved_at_e0[0x13];
 	u8         vlan_valid[0x1];
 	u8         vlan[0xc];
 
 	struct mlx5_ifc_mac_address_layout_bits mac_address;
 
-	u8         reserved_6[0xc0];
+	u8         reserved_at_140[0xc0];
 };
 
 struct mlx5_ifc_set_issi_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_issi_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         current_issi[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_set_hca_cap_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_hca_cap_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	union mlx5_ifc_hca_cap_union_bits capability;
 };
@@ -2890,156 +2890,156 @@ enum {
 
 struct mlx5_ifc_set_fte_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_fte_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x18];
+	u8         reserved_at_c0[0x18];
 	u8         modify_enable_mask[0x8];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_e0[0x20];
 
 	u8         flow_index[0x20];
 
-	u8         reserved_7[0xe0];
+	u8         reserved_at_120[0xe0];
 
 	struct mlx5_ifc_flow_context_bits flow_context;
 };
 
 struct mlx5_ifc_rts2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rts2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_rtr2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rtr2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_rst2init_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rst2init_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_query_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 enum {
@@ -3049,13 +3049,13 @@ enum {
 
 struct mlx5_ifc_query_vport_state_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_60[0x18];
 	u8         admin_state[0x4];
 	u8         state[0x4];
 };
@@ -3067,25 +3067,25 @@ enum {
 
 struct mlx5_ifc_query_vport_state_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_vport_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_traffic_counter_bits received_errors;
 
@@ -3111,7 +3111,7 @@ struct mlx5_ifc_query_vport_counter_out_bits {
 
 	struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast;
 
-	u8         reserved_2[0xa00];
+	u8         reserved_at_680[0xa00];
 };
 
 enum {
@@ -3120,328 +3120,328 @@ enum {
 
 struct mlx5_ifc_query_vport_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x60];
+	u8         reserved_at_60[0x60];
 
 	u8         clear[0x1];
-	u8         reserved_4[0x1f];
+	u8         reserved_at_c1[0x1f];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_e0[0x20];
 };
 
 struct mlx5_ifc_query_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_tisc_bits tis_context;
 };
 
 struct mlx5_ifc_query_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_tirc_bits tir_context;
 };
 
 struct mlx5_ifc_query_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_srqc_bits srq_context_entry;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_sqc_bits sq_context;
 };
 
 struct mlx5_ifc_query_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         sqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_special_contexts_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         resd_lkey[0x20];
 };
 
 struct mlx5_ifc_query_special_contexts_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqtc_bits rqt_context;
 };
 
 struct mlx5_ifc_query_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqc_bits rq_context;
 };
 
 struct mlx5_ifc_query_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_roce_address_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_roce_addr_layout_bits roce_address;
 };
 
 struct mlx5_ifc_query_roce_address_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         roce_address_index[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_50[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rmpc_bits rmp_context;
 };
 
 struct mlx5_ifc_query_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_800[0x80];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_q_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         rx_write_requests[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_a0[0x20];
 
 	u8         rx_read_requests[0x20];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_e0[0x20];
 
 	u8         rx_atomic_requests[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_120[0x20];
 
 	u8         rx_dct_connect[0x20];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_160[0x20];
 
 	u8         out_of_buffer[0x20];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_1a0[0x20];
 
 	u8         out_of_sequence[0x20];
 
-	u8         reserved_7[0x620];
+	u8         reserved_at_1e0[0x620];
 };
 
 struct mlx5_ifc_query_q_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x80];
+	u8         reserved_at_40[0x80];
 
 	u8         clear[0x1];
-	u8         reserved_3[0x1f];
+	u8         reserved_at_c1[0x1f];
 
-	u8         reserved_4[0x18];
+	u8         reserved_at_e0[0x18];
 	u8         counter_set_id[0x8];
 };
 
 struct mlx5_ifc_query_pages_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
 	u8         num_pages[0x20];
@@ -3455,55 +3455,55 @@ enum {
 
 struct mlx5_ifc_query_pages_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_nic_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_nic_vport_context_bits nic_vport_context;
 };
 
 struct mlx5_ifc_query_nic_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x5];
+	u8         reserved_at_60[0x5];
 	u8         allowed_list_type[0x3];
-	u8         reserved_4[0x18];
+	u8         reserved_at_68[0x18];
 };
 
 struct mlx5_ifc_query_mkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_mkc_bits memory_key_mkey_entry;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         bsf0_klm0_pas_mtt0_1[16][0x8];
 
@@ -3512,265 +3512,265 @@ struct mlx5_ifc_query_mkey_out_bits {
 
 struct mlx5_ifc_query_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         mkey_index[0x18];
 
 	u8         pg_access[0x1];
-	u8         reserved_3[0x1f];
+	u8         reserved_at_61[0x1f];
 };
 
 struct mlx5_ifc_query_mad_demux_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         mad_dumux_parameters_block[0x20];
 };
 
 struct mlx5_ifc_query_mad_demux_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_l2_table_entry_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xa0];
+	u8         reserved_at_40[0xa0];
 
-	u8         reserved_2[0x13];
+	u8         reserved_at_e0[0x13];
 	u8         vlan_valid[0x1];
 	u8         vlan[0xc];
 
 	struct mlx5_ifc_mac_address_layout_bits mac_address;
 
-	u8         reserved_3[0xc0];
+	u8         reserved_at_140[0xc0];
 };
 
 struct mlx5_ifc_query_l2_table_entry_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_40[0x60];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_index[0x18];
 
-	u8         reserved_4[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_query_issi_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_40[0x10];
 	u8         current_issi[0x10];
 
-	u8         reserved_2[0xa0];
+	u8         reserved_at_60[0xa0];
 
-	u8         supported_issi_reserved[76][0x8];
+	u8         reserved_at_100[76][0x8];
 	u8         supported_issi_dw0[0x20];
 };
 
 struct mlx5_ifc_query_issi_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_hca_vport_pkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_pkey_bits pkey[0];
 };
 
 struct mlx5_ifc_query_hca_vport_pkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         pkey_index[0x10];
 };
 
 struct mlx5_ifc_query_hca_vport_gid_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         gids_num[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_70[0x10];
 
 	struct mlx5_ifc_array128_auto_bits gid[0];
 };
 
 struct mlx5_ifc_query_hca_vport_gid_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         gid_index[0x10];
 };
 
 struct mlx5_ifc_query_hca_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_hca_vport_context_bits hca_vport_context;
 };
 
 struct mlx5_ifc_query_hca_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_hca_cap_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	union mlx5_ifc_hca_cap_union_bits capability;
 };
 
 struct mlx5_ifc_query_hca_cap_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x80];
+	u8         reserved_at_40[0x80];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         level[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_d0[0x8];
 	u8         log_size[0x8];
 
-	u8         reserved_4[0x120];
+	u8         reserved_at_e0[0x120];
 };
 
 struct mlx5_ifc_query_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_query_fte_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x1c0];
+	u8         reserved_at_40[0x1c0];
 
 	struct mlx5_ifc_flow_context_bits flow_context;
 };
 
 struct mlx5_ifc_query_fte_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x40];
+	u8         reserved_at_c0[0x40];
 
 	u8         flow_index[0x20];
 
-	u8         reserved_6[0xe0];
+	u8         reserved_at_120[0xe0];
 };
 
 enum {
@@ -3781,84 +3781,84 @@ enum {
 
 struct mlx5_ifc_query_flow_group_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xa0];
+	u8         reserved_at_40[0xa0];
 
 	u8         start_flow_index[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_100[0x20];
 
 	u8         end_flow_index[0x20];
 
-	u8         reserved_3[0xa0];
+	u8         reserved_at_140[0xa0];
 
-	u8         reserved_4[0x18];
+	u8         reserved_at_1e0[0x18];
 	u8         match_criteria_enable[0x8];
 
 	struct mlx5_ifc_fte_match_param_bits match_criteria;
 
-	u8         reserved_5[0xe00];
+	u8         reserved_at_1200[0xe00];
 };
 
 struct mlx5_ifc_query_flow_group_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
 	u8         group_id[0x20];
 
-	u8         reserved_5[0x120];
+	u8         reserved_at_e0[0x120];
 };
 
 struct mlx5_ifc_query_esw_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_esw_vport_context_bits esw_vport_context;
 };
 
 struct mlx5_ifc_query_esw_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_modify_esw_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_esw_vport_context_fields_select_bits {
-	u8         reserved[0x1c];
+	u8         reserved_at_0[0x1c];
 	u8         vport_cvlan_insert[0x1];
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_strip[0x1];
@@ -3867,13 +3867,13 @@ struct mlx5_ifc_esw_vport_context_fields_select_bits {
 
 struct mlx5_ifc_modify_esw_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
 	struct mlx5_ifc_esw_vport_context_fields_select_bits field_select;
@@ -3883,124 +3883,124 @@ struct mlx5_ifc_modify_esw_vport_context_in_bits {
 
 struct mlx5_ifc_query_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_eqc_bits eq_context_entry;
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_280[0x40];
 
 	u8         event_bitmask[0x40];
 
-	u8         reserved_3[0x580];
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_eq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_dctc_bits dct_context_entry;
 
-	u8         reserved_2[0x180];
+	u8         reserved_at_280[0x180];
 };
 
 struct mlx5_ifc_query_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cong_status_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         enable[0x1];
 	u8         tag_enable[0x1];
-	u8         reserved_2[0x1e];
+	u8         reserved_at_62[0x1e];
 };
 
 struct mlx5_ifc_query_cong_status_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         priority[0x4];
 	u8         cong_protocol[0x4];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cong_statistics_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         cur_flows[0x20];
 
@@ -4014,7 +4014,7 @@ struct mlx5_ifc_query_cong_statistics_out_bits {
 
 	u8         cnp_handled_low[0x20];
 
-	u8         reserved_2[0x100];
+	u8         reserved_at_140[0x100];
 
 	u8         time_stamp_high[0x20];
 
@@ -4030,453 +4030,453 @@ struct mlx5_ifc_query_cong_statistics_out_bits {
 
 	u8         cnps_sent_low[0x20];
 
-	u8         reserved_3[0x560];
+	u8         reserved_at_320[0x560];
 };
 
 struct mlx5_ifc_query_cong_statistics_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         clear[0x1];
-	u8         reserved_2[0x1f];
+	u8         reserved_at_41[0x1f];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cong_params_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters;
 };
 
 struct mlx5_ifc_query_cong_params_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x1c];
+	u8         reserved_at_40[0x1c];
 	u8         cong_protocol[0x4];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_adapter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_query_adapter_param_block_bits query_adapter_struct;
 };
 
 struct mlx5_ifc_query_adapter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_qp_2rst_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_qp_2rst_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_qp_2err_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_qp_2err_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_page_fault_resume_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_page_fault_resume_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         error[0x1];
-	u8         reserved_2[0x4];
+	u8         reserved_at_41[0x4];
 	u8         rdma[0x1];
 	u8         read_write[0x1];
 	u8         req_res[0x1];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_nop_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_nop_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_vport_state_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_vport_state_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x18];
+	u8         reserved_at_60[0x18];
 	u8         admin_state[0x4];
-	u8         reserved_4[0x4];
+	u8         reserved_at_7c[0x4];
 };
 
 struct mlx5_ifc_modify_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_tis_bitmask_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
-	u8         reserved_1[0x1f];
+	u8         reserved_at_20[0x1f];
 	u8         prio[0x1];
 };
 
 struct mlx5_ifc_modify_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_modify_tis_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_tisc_bits ctx;
 };
 
 struct mlx5_ifc_modify_tir_bitmask_bits {
-	u8	   reserved_0[0x20];
+	u8	   reserved_at_0[0x20];
 
-	u8         reserved_1[0x1b];
+	u8         reserved_at_20[0x1b];
 	u8         self_lb_en[0x1];
-	u8         reserved_2[0x3];
+	u8         reserved_at_3c[0x3];
 	u8         lro[0x1];
 };
 
 struct mlx5_ifc_modify_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_modify_tir_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_tirc_bits ctx;
 };
 
 struct mlx5_ifc_modify_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         sq_state[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         sqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         modify_bitmask[0x40];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_sqc_bits ctx;
 };
 
 struct mlx5_ifc_modify_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rqt_bitmask_bits {
-	u8	   reserved[0x20];
+	u8	   reserved_at_0[0x20];
 
-	u8         reserved1[0x1f];
+	u8         reserved_at_20[0x1f];
 	u8         rqn_list[0x1];
 };
 
 struct mlx5_ifc_modify_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_rqt_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_rqtc_bits ctx;
 };
 
 struct mlx5_ifc_modify_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         rq_state[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         rqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         modify_bitmask[0x40];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_rqc_bits ctx;
 };
 
 struct mlx5_ifc_modify_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rmp_bitmask_bits {
-	u8	   reserved[0x20];
+	u8	   reserved_at_0[0x20];
 
-	u8         reserved1[0x1f];
+	u8         reserved_at_20[0x1f];
 	u8         lwm[0x1];
 };
 
 struct mlx5_ifc_modify_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         rmp_state[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         rmpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_rmp_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_rmpc_bits ctx;
 };
 
 struct mlx5_ifc_modify_nic_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
-	u8         reserved_0[0x19];
+	u8         reserved_at_0[0x19];
 	u8         mtu[0x1];
 	u8         change_event[0x1];
 	u8         promisc[0x1];
 	u8         permanent_address[0x1];
 	u8         addresses_list[0x1];
 	u8         roce_en[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_1f[0x1];
 };
 
 struct mlx5_ifc_modify_nic_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
 	struct mlx5_ifc_modify_nic_vport_field_select_bits field_select;
 
-	u8         reserved_3[0x780];
+	u8         reserved_at_80[0x780];
 
 	struct mlx5_ifc_nic_vport_context_bits nic_vport_context;
 };
 
 struct mlx5_ifc_modify_hca_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_hca_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_hca_vport_context_bits hca_vport_context;
 };
 
 struct mlx5_ifc_modify_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -4486,83 +4486,83 @@ enum {
 
 struct mlx5_ifc_modify_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
 	union mlx5_ifc_modify_field_select_resize_field_select_auto_bits modify_field_select_resize_field_select;
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_modify_cong_status_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_cong_status_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         priority[0x4];
 	u8         cong_protocol[0x4];
 
 	u8         enable[0x1];
 	u8         tag_enable[0x1];
-	u8         reserved_3[0x1e];
+	u8         reserved_at_62[0x1e];
 };
 
 struct mlx5_ifc_modify_cong_params_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_cong_params_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x1c];
+	u8         reserved_at_40[0x1c];
 	u8         cong_protocol[0x4];
 
 	union mlx5_ifc_field_select_802_1_r_roce_auto_bits field_select;
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_80[0x80];
 
 	union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters;
 };
 
 struct mlx5_ifc_manage_pages_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
 	u8         output_num_entries[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         pas[0][0x40];
 };
@@ -4575,12 +4575,12 @@ enum {
 
 struct mlx5_ifc_manage_pages_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
 	u8         input_num_entries[0x20];
@@ -4590,117 +4590,117 @@ struct mlx5_ifc_manage_pages_in_bits {
 
 struct mlx5_ifc_mad_ifc_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         response_mad_packet[256][0x8];
 };
 
 struct mlx5_ifc_mad_ifc_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         remote_lid[0x10];
-	u8         reserved_2[0x8];
+	u8         reserved_at_50[0x8];
 	u8         port[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         mad[256][0x8];
 };
 
 struct mlx5_ifc_init_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init2rtr_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init2rtr_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_init2init_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init2init_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_get_dropped_packet_log_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         packet_headers_log[128][0x8];
 
@@ -4709,1029 +4709,1029 @@ struct mlx5_ifc_get_dropped_packet_log_out_bits {
 
 struct mlx5_ifc_get_dropped_packet_log_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_gen_eqe_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         eqe[64][0x8];
 };
 
 struct mlx5_ifc_gen_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_enable_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 };
 
 struct mlx5_ifc_enable_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_drain_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_drain_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_disable_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 };
 
 struct mlx5_ifc_disable_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_detach_from_mcg_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_detach_from_mcg_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         multicast_gid[16][0x8];
 };
 
 struct mlx5_ifc_destroy_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         sqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_psv_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_psv_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         psvn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_mkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         mkey_index[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_destroy_flow_group_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_flow_group_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
 	u8         group_id[0x20];
 
-	u8         reserved_5[0x120];
+	u8         reserved_at_e0[0x120];
 };
 
 struct mlx5_ifc_destroy_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_eq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_delete_vxlan_udp_dport_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_delete_vxlan_udp_dport_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         vxlan_udp_port[0x10];
 };
 
 struct mlx5_ifc_delete_l2_table_entry_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_delete_l2_table_entry_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_40[0x60];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_index[0x18];
 
-	u8         reserved_4[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_delete_fte_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_delete_fte_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x40];
+	u8         reserved_at_c0[0x40];
 
 	u8         flow_index[0x20];
 
-	u8         reserved_6[0xe0];
+	u8         reserved_at_120[0xe0];
 };
 
 struct mlx5_ifc_dealloc_xrcd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_xrcd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrcd[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_uar_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_uar_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         uar[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_transport_domain_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_transport_domain_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         transport_domain[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_q_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_q_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         counter_set_id[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_pd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_pd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         pd[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_tisc_bits ctx;
 };
 
 struct mlx5_ifc_create_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_tirc_bits ctx;
 };
 
 struct mlx5_ifc_create_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_srqc_bits srq_context_entry;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         sqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_sqc_bits ctx;
 };
 
 struct mlx5_ifc_create_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqtc_bits rqt_context;
 };
 
 struct mlx5_ifc_create_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqc_bits ctx;
 };
 
 struct mlx5_ifc_create_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rmpc_bits ctx;
 };
 
 struct mlx5_ifc_create_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_4[0x80];
+	u8         reserved_at_800[0x80];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_psv_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_80[0x8];
 	u8         psv0_index[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         psv1_index[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         psv2_index[0x18];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         psv3_index[0x18];
 };
 
 struct mlx5_ifc_create_psv_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         num_psv[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         pd[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_mkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         mkey_index[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         pg_access[0x1];
-	u8         reserved_3[0x1f];
+	u8         reserved_at_61[0x1f];
 
 	struct mlx5_ifc_mkc_bits memory_key_mkey_entry;
 
-	u8         reserved_4[0x80];
+	u8         reserved_at_280[0x80];
 
 	u8         translations_octword_actual_size[0x20];
 
-	u8         reserved_5[0x560];
+	u8         reserved_at_320[0x560];
 
 	u8         klm_pas_mtt[0][0x20];
 };
 
 struct mlx5_ifc_create_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
-	u8         reserved_5[0x4];
+	u8         reserved_at_c0[0x4];
 	u8         table_miss_mode[0x4];
 	u8         level[0x8];
-	u8         reserved_6[0x8];
+	u8         reserved_at_d0[0x8];
 	u8         log_size[0x8];
 
-	u8         reserved_7[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         table_miss_id[0x18];
 
-	u8         reserved_8[0x100];
+	u8         reserved_at_100[0x100];
 };
 
 struct mlx5_ifc_create_flow_group_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         group_id[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 enum {
@@ -5742,134 +5742,134 @@ enum {
 
 struct mlx5_ifc_create_flow_group_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_c0[0x20];
 
 	u8         start_flow_index[0x20];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_100[0x20];
 
 	u8         end_flow_index[0x20];
 
-	u8         reserved_7[0xa0];
+	u8         reserved_at_140[0xa0];
 
-	u8         reserved_8[0x18];
+	u8         reserved_at_1e0[0x18];
 	u8         match_criteria_enable[0x8];
 
 	struct mlx5_ifc_fte_match_param_bits match_criteria;
 
-	u8         reserved_9[0xe00];
+	u8         reserved_at_1200[0xe00];
 };
 
 struct mlx5_ifc_create_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_eq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_eqc_bits eq_context_entry;
 
-	u8         reserved_3[0x40];
+	u8         reserved_at_280[0x40];
 
 	u8         event_bitmask[0x40];
 
-	u8         reserved_4[0x580];
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_dctc_bits dct_context_entry;
 
-	u8         reserved_3[0x180];
+	u8         reserved_at_280[0x180];
 };
 
 struct mlx5_ifc_create_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_config_int_moderation_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x4];
+	u8         reserved_at_40[0x4];
 	u8         min_delay[0xc];
 	u8         int_vector[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 enum {
@@ -5879,49 +5879,49 @@ enum {
 
 struct mlx5_ifc_config_int_moderation_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x4];
+	u8         reserved_at_40[0x4];
 	u8         min_delay[0xc];
 	u8         int_vector[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_attach_to_mcg_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_attach_to_mcg_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         multicast_gid[16][0x8];
 };
 
 struct mlx5_ifc_arm_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -5930,25 +5930,25 @@ enum {
 
 struct mlx5_ifc_arm_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         lwm[0x10];
 };
 
 struct mlx5_ifc_arm_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -5957,179 +5957,179 @@ enum {
 
 struct mlx5_ifc_arm_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srq_number[0x18];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         lwm[0x10];
 };
 
 struct mlx5_ifc_arm_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_arm_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dct_number[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_xrcd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrcd[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_xrcd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_uar_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         uar[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_uar_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_transport_domain_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         transport_domain[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_transport_domain_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_q_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x18];
+	u8         reserved_at_40[0x18];
 	u8         counter_set_id[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_q_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_pd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         pd[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_pd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_add_vxlan_udp_dport_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         vxlan_udp_port[0x10];
 };
 
 struct mlx5_ifc_access_register_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         register_data[0][0x20];
 };
@@ -6141,12 +6141,12 @@ enum {
 
 struct mlx5_ifc_access_register_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         register_id[0x10];
 
 	u8         argument[0x20];
@@ -6159,24 +6159,24 @@ struct mlx5_ifc_sltp_reg_bits {
 	u8         version[0x4];
 	u8         local_port[0x8];
 	u8         pnat[0x2];
-	u8         reserved_0[0x2];
+	u8         reserved_at_12[0x2];
 	u8         lane[0x4];
-	u8         reserved_1[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_3[0x7];
+	u8         reserved_at_40[0x7];
 	u8         polarity[0x1];
 	u8         ob_tap0[0x8];
 	u8         ob_tap1[0x8];
 	u8         ob_tap2[0x8];
 
-	u8         reserved_4[0xc];
+	u8         reserved_at_60[0xc];
 	u8         ob_preemp_mode[0x4];
 	u8         ob_reg[0x8];
 	u8         ob_bias[0x8];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_80[0x20];
 };
 
 struct mlx5_ifc_slrg_reg_bits {
@@ -6184,36 +6184,36 @@ struct mlx5_ifc_slrg_reg_bits {
 	u8         version[0x4];
 	u8         local_port[0x8];
 	u8         pnat[0x2];
-	u8         reserved_0[0x2];
+	u8         reserved_at_12[0x2];
 	u8         lane[0x4];
-	u8         reserved_1[0x8];
+	u8         reserved_at_18[0x8];
 
 	u8         time_to_link_up[0x10];
-	u8         reserved_2[0xc];
+	u8         reserved_at_30[0xc];
 	u8         grade_lane_speed[0x4];
 
 	u8         grade_version[0x8];
 	u8         grade[0x18];
 
-	u8         reserved_3[0x4];
+	u8         reserved_at_60[0x4];
 	u8         height_grade_type[0x4];
 	u8         height_grade[0x18];
 
 	u8         height_dz[0x10];
 	u8         height_dv[0x10];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         height_sigma[0x10];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_c0[0x20];
 
-	u8         reserved_6[0x4];
+	u8         reserved_at_e0[0x4];
 	u8         phase_grade_type[0x4];
 	u8         phase_grade[0x18];
 
-	u8         reserved_7[0x8];
+	u8         reserved_at_100[0x8];
 	u8         phase_eo_pos[0x8];
-	u8         reserved_8[0x8];
+	u8         reserved_at_110[0x8];
 	u8         phase_eo_neg[0x8];
 
 	u8         ffe_set_tested[0x10];
@@ -6221,70 +6221,70 @@ struct mlx5_ifc_slrg_reg_bits {
 };
 
 struct mlx5_ifc_pvlc_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x1c];
+	u8         reserved_at_20[0x1c];
 	u8         vl_hw_cap[0x4];
 
-	u8         reserved_3[0x1c];
+	u8         reserved_at_40[0x1c];
 	u8         vl_admin[0x4];
 
-	u8         reserved_4[0x1c];
+	u8         reserved_at_60[0x1c];
 	u8         vl_operational[0x4];
 };
 
 struct mlx5_ifc_pude_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
-	u8         reserved_0[0x4];
+	u8         reserved_at_10[0x4];
 	u8         admin_status[0x4];
-	u8         reserved_1[0x4];
+	u8         reserved_at_18[0x4];
 	u8         oper_status[0x4];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_ptys_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0xd];
+	u8         reserved_at_10[0xd];
 	u8         proto_mask[0x3];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_20[0x40];
 
 	u8         eth_proto_capability[0x20];
 
 	u8         ib_link_width_capability[0x10];
 	u8         ib_proto_capability[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_a0[0x20];
 
 	u8         eth_proto_admin[0x20];
 
 	u8         ib_link_width_admin[0x10];
 	u8         ib_proto_admin[0x10];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_100[0x20];
 
 	u8         eth_proto_oper[0x20];
 
 	u8         ib_link_width_oper[0x10];
 	u8         ib_proto_oper[0x10];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_160[0x20];
 
 	u8         eth_proto_lp_advertise[0x20];
 
-	u8         reserved_6[0x60];
+	u8         reserved_at_1a0[0x60];
 };
 
 struct mlx5_ifc_ptas_reg_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         algorithm_options[0x10];
-	u8         reserved_1[0x4];
+	u8         reserved_at_30[0x4];
 	u8         repetitions_mode[0x4];
 	u8         num_of_repetitions[0x8];
 
@@ -6310,13 +6310,13 @@ struct mlx5_ifc_ptas_reg_bits {
 	u8         ndeo_error_threshold[0x10];
 
 	u8         mixer_offset_step_size[0x10];
-	u8         reserved_2[0x8];
+	u8         reserved_at_110[0x8];
 	u8         mix90_phase_for_voltage_bath[0x8];
 
 	u8         mixer_offset_start[0x10];
 	u8         mixer_offset_end[0x10];
 
-	u8         reserved_3[0x15];
+	u8         reserved_at_140[0x15];
 	u8         ber_test_time[0xb];
 };
 
@@ -6324,154 +6324,154 @@ struct mlx5_ifc_pspa_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
 	u8         sub_port[0x8];
-	u8         reserved_0[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_pqdr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x5];
+	u8         reserved_at_10[0x5];
 	u8         prio[0x3];
-	u8         reserved_2[0x6];
+	u8         reserved_at_18[0x6];
 	u8         mode[0x2];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_40[0x10];
 	u8         min_threshold[0x10];
 
-	u8         reserved_5[0x10];
+	u8         reserved_at_60[0x10];
 	u8         max_threshold[0x10];
 
-	u8         reserved_6[0x10];
+	u8         reserved_at_80[0x10];
 	u8         mark_probability_denominator[0x10];
 
-	u8         reserved_7[0x60];
+	u8         reserved_at_a0[0x60];
 };
 
 struct mlx5_ifc_ppsc_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 
-	u8         reserved_3[0x1c];
+	u8         reserved_at_80[0x1c];
 	u8         wrps_admin[0x4];
 
-	u8         reserved_4[0x1c];
+	u8         reserved_at_a0[0x1c];
 	u8         wrps_status[0x4];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         up_threshold[0x8];
-	u8         reserved_6[0x8];
+	u8         reserved_at_d0[0x8];
 	u8         down_threshold[0x8];
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_e0[0x20];
 
-	u8         reserved_8[0x1c];
+	u8         reserved_at_100[0x1c];
 	u8         srps_admin[0x4];
 
-	u8         reserved_9[0x1c];
+	u8         reserved_at_120[0x1c];
 	u8         srps_status[0x4];
 
-	u8         reserved_10[0x40];
+	u8         reserved_at_140[0x40];
 };
 
 struct mlx5_ifc_pplr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_20[0x8];
 	u8         lb_cap[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_30[0x8];
 	u8         lb_en[0x8];
 };
 
 struct mlx5_ifc_pplm_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 
 	u8         port_profile_mode[0x8];
 	u8         static_port_profile[0x8];
 	u8         active_port_profile[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_58[0x8];
 
 	u8         retransmission_active[0x8];
 	u8         fec_mode_active[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_80[0x20];
 };
 
 struct mlx5_ifc_ppcnt_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
 	u8         pnat[0x2];
-	u8         reserved_0[0x8];
+	u8         reserved_at_12[0x8];
 	u8         grp[0x6];
 
 	u8         clr[0x1];
-	u8         reserved_1[0x1c];
+	u8         reserved_at_21[0x1c];
 	u8         prio_tc[0x3];
 
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
 struct mlx5_ifc_ppad_reg_bits {
-	u8         reserved_0[0x3];
+	u8         reserved_at_0[0x3];
 	u8         single_mac[0x1];
-	u8         reserved_1[0x4];
+	u8         reserved_at_4[0x4];
 	u8         local_port[0x8];
 	u8         mac_47_32[0x10];
 
 	u8         mac_31_0[0x20];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_pmtu_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         max_mtu[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_30[0x10];
 
 	u8         admin_mtu[0x10];
-	u8         reserved_3[0x10];
+	u8         reserved_at_50[0x10];
 
 	u8         oper_mtu[0x10];
-	u8         reserved_4[0x10];
+	u8         reserved_at_70[0x10];
 };
 
 struct mlx5_ifc_pmpr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         module[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_20[0x18];
 	u8         attenuation_5g[0x8];
 
-	u8         reserved_3[0x18];
+	u8         reserved_at_40[0x18];
 	u8         attenuation_7g[0x8];
 
-	u8         reserved_4[0x18];
+	u8         reserved_at_60[0x18];
 	u8         attenuation_12g[0x8];
 };
 
 struct mlx5_ifc_pmpe_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         module[0x8];
-	u8         reserved_1[0xc];
+	u8         reserved_at_10[0xc];
 	u8         module_status[0x4];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_pmpc_reg_bits {
@@ -6479,20 +6479,20 @@ struct mlx5_ifc_pmpc_reg_bits {
 };
 
 struct mlx5_ifc_pmlpn_reg_bits {
-	u8         reserved_0[0x4];
+	u8         reserved_at_0[0x4];
 	u8         mlpn_status[0x4];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         e[0x1];
-	u8         reserved_2[0x1f];
+	u8         reserved_at_21[0x1f];
 };
 
 struct mlx5_ifc_pmlp_reg_bits {
 	u8         rxtx[0x1];
-	u8         reserved_0[0x7];
+	u8         reserved_at_1[0x7];
 	u8         local_port[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_10[0x8];
 	u8         width[0x8];
 
 	u8         lane0_module_mapping[0x20];
@@ -6503,36 +6503,36 @@ struct mlx5_ifc_pmlp_reg_bits {
 
 	u8         lane3_module_mapping[0x20];
 
-	u8         reserved_2[0x160];
+	u8         reserved_at_a0[0x160];
 };
 
 struct mlx5_ifc_pmaos_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         module[0x8];
-	u8         reserved_1[0x4];
+	u8         reserved_at_10[0x4];
 	u8         admin_status[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_18[0x4];
 	u8         oper_status[0x4];
 
 	u8         ase[0x1];
 	u8         ee[0x1];
-	u8         reserved_3[0x1c];
+	u8         reserved_at_22[0x1c];
 	u8         e[0x2];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_plpc_reg_bits {
-	u8         reserved_0[0x4];
+	u8         reserved_at_0[0x4];
 	u8         profile_id[0xc];
-	u8         reserved_1[0x4];
+	u8         reserved_at_10[0x4];
 	u8         proto_mask[0x4];
-	u8         reserved_2[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_20[0x10];
 	u8         lane_speed[0x10];
 
-	u8         reserved_4[0x17];
+	u8         reserved_at_40[0x17];
 	u8         lpbf[0x1];
 	u8         fec_mode_policy[0x8];
 
@@ -6545,44 +6545,44 @@ struct mlx5_ifc_plpc_reg_bits {
 	u8         retransmission_request_admin[0x8];
 	u8         fec_mode_request_admin[0x18];
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_c0[0x80];
 };
 
 struct mlx5_ifc_plib_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_10[0x8];
 	u8         ib_port[0x8];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_plbf_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0xd];
+	u8         reserved_at_10[0xd];
 	u8         lbf_mode[0x3];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_pipg_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         dic[0x1];
-	u8         reserved_2[0x19];
+	u8         reserved_at_21[0x19];
 	u8         ipg[0x4];
-	u8         reserved_3[0x2];
+	u8         reserved_at_3e[0x2];
 };
 
 struct mlx5_ifc_pifr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0xe0];
+	u8         reserved_at_20[0xe0];
 
 	u8         port_filter[8][0x20];
 
@@ -6590,36 +6590,36 @@ struct mlx5_ifc_pifr_reg_bits {
 };
 
 struct mlx5_ifc_pfcc_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         ppan[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_24[0x4];
 	u8         prio_mask_tx[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_30[0x8];
 	u8         prio_mask_rx[0x8];
 
 	u8         pptx[0x1];
 	u8         aptx[0x1];
-	u8         reserved_4[0x6];
+	u8         reserved_at_42[0x6];
 	u8         pfctx[0x8];
-	u8         reserved_5[0x10];
+	u8         reserved_at_50[0x10];
 
 	u8         pprx[0x1];
 	u8         aprx[0x1];
-	u8         reserved_6[0x6];
+	u8         reserved_at_62[0x6];
 	u8         pfcrx[0x8];
-	u8         reserved_7[0x10];
+	u8         reserved_at_70[0x10];
 
-	u8         reserved_8[0x80];
+	u8         reserved_at_80[0x80];
 };
 
 struct mlx5_ifc_pelc_reg_bits {
 	u8         op[0x4];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         op_admin[0x8];
 	u8         op_capability[0x8];
@@ -6634,28 +6634,28 @@ struct mlx5_ifc_pelc_reg_bits {
 
 	u8         active[0x40];
 
-	u8         reserved_2[0x80];
+	u8         reserved_at_140[0x80];
 };
 
 struct mlx5_ifc_peir_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0xc];
+	u8         reserved_at_20[0xc];
 	u8         error_count[0x4];
-	u8         reserved_3[0x10];
+	u8         reserved_at_30[0x10];
 
-	u8         reserved_4[0xc];
+	u8         reserved_at_40[0xc];
 	u8         lane[0x4];
-	u8         reserved_5[0x8];
+	u8         reserved_at_50[0x8];
 	u8         error_type[0x8];
 };
 
 struct mlx5_ifc_pcap_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         port_capability_mask[4][0x20];
 };
@@ -6663,46 +6663,46 @@ struct mlx5_ifc_pcap_reg_bits {
 struct mlx5_ifc_paos_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
-	u8         reserved_0[0x4];
+	u8         reserved_at_10[0x4];
 	u8         admin_status[0x4];
-	u8         reserved_1[0x4];
+	u8         reserved_at_18[0x4];
 	u8         oper_status[0x4];
 
 	u8         ase[0x1];
 	u8         ee[0x1];
-	u8         reserved_2[0x1c];
+	u8         reserved_at_22[0x1c];
 	u8         e[0x2];
 
-	u8         reserved_3[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_pamp_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         opamp_group[0x8];
-	u8         reserved_1[0xc];
+	u8         reserved_at_10[0xc];
 	u8         opamp_group_type[0x4];
 
 	u8         start_index[0x10];
-	u8         reserved_2[0x4];
+	u8         reserved_at_30[0x4];
 	u8         num_of_indices[0xc];
 
 	u8         index_data[18][0x10];
 };
 
 struct mlx5_ifc_lane_2_module_mapping_bits {
-	u8         reserved_0[0x6];
+	u8         reserved_at_0[0x6];
 	u8         rx_lane[0x2];
-	u8         reserved_1[0x6];
+	u8         reserved_at_8[0x6];
 	u8         tx_lane[0x2];
-	u8         reserved_2[0x8];
+	u8         reserved_at_10[0x8];
 	u8         module[0x8];
 };
 
 struct mlx5_ifc_bufferx_reg_bits {
-	u8         reserved_0[0x6];
+	u8         reserved_at_0[0x6];
 	u8         lossy[0x1];
 	u8         epsb[0x1];
-	u8         reserved_1[0xc];
+	u8         reserved_at_8[0xc];
 	u8         size[0xc];
 
 	u8         xoff_threshold[0x10];
@@ -6714,21 +6714,21 @@ struct mlx5_ifc_set_node_in_bits {
 };
 
 struct mlx5_ifc_register_power_settings_bits {
-	u8         reserved_0[0x18];
+	u8         reserved_at_0[0x18];
 	u8         power_settings_level[0x8];
 
-	u8         reserved_1[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_register_host_endianness_bits {
 	u8         he[0x1];
-	u8         reserved_0[0x1f];
+	u8         reserved_at_1[0x1f];
 
-	u8         reserved_1[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_umr_pointer_desc_argument_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         mkey[0x20];
 
@@ -6741,7 +6741,7 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 	u8         dc_key[0x40];
 
 	u8         ext[0x1];
-	u8         reserved_0[0x7];
+	u8         reserved_at_41[0x7];
 	u8         destination_qp_dct[0x18];
 
 	u8         static_rate[0x4];
@@ -6750,7 +6750,7 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 	u8         mlid[0x7];
 	u8         rlid_udp_sport[0x10];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_80[0x20];
 
 	u8         rmac_47_16[0x20];
 
@@ -6758,9 +6758,9 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 	u8         tclass[0x8];
 	u8         hop_limit[0x8];
 
-	u8         reserved_2[0x1];
+	u8         reserved_at_e0[0x1];
 	u8         grh[0x1];
-	u8         reserved_3[0x2];
+	u8         reserved_at_e2[0x2];
 	u8         src_addr_index[0x8];
 	u8         flow_label[0x14];
 
@@ -6768,27 +6768,27 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 };
 
 struct mlx5_ifc_pages_req_event_bits {
-	u8         reserved_0[0x10];
+	u8         reserved_at_0[0x10];
 	u8         function_id[0x10];
 
 	u8         num_pages[0x20];
 
-	u8         reserved_1[0xa0];
+	u8         reserved_at_40[0xa0];
 };
 
 struct mlx5_ifc_eqe_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         event_type[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_10[0x8];
 	u8         event_sub_type[0x8];
 
-	u8         reserved_2[0xe0];
+	u8         reserved_at_20[0xe0];
 
 	union mlx5_ifc_event_auto_bits event_data;
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_1e0[0x10];
 	u8         signature[0x8];
-	u8         reserved_4[0x7];
+	u8         reserved_at_1f8[0x7];
 	u8         owner[0x1];
 };
 
@@ -6798,14 +6798,14 @@ enum {
 
 struct mlx5_ifc_cmd_queue_entry_bits {
 	u8         type[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         input_length[0x20];
 
 	u8         input_mailbox_pointer_63_32[0x20];
 
 	u8         input_mailbox_pointer_31_9[0x17];
-	u8         reserved_1[0x9];
+	u8         reserved_at_77[0x9];
 
 	u8         command_input_inline_data[16][0x8];
 
@@ -6814,20 +6814,20 @@ struct mlx5_ifc_cmd_queue_entry_bits {
 	u8         output_mailbox_pointer_63_32[0x20];
 
 	u8         output_mailbox_pointer_31_9[0x17];
-	u8         reserved_2[0x9];
+	u8         reserved_at_1b7[0x9];
 
 	u8         output_length[0x20];
 
 	u8         token[0x8];
 	u8         signature[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_1f0[0x8];
 	u8         status[0x7];
 	u8         ownership[0x1];
 };
 
 struct mlx5_ifc_cmd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
@@ -6836,9 +6836,9 @@ struct mlx5_ifc_cmd_out_bits {
 
 struct mlx5_ifc_cmd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         command[0][0x20];
@@ -6847,16 +6847,16 @@ struct mlx5_ifc_cmd_in_bits {
 struct mlx5_ifc_cmd_if_box_bits {
 	u8         mailbox_data[512][0x8];
 
-	u8         reserved_0[0x180];
+	u8         reserved_at_1000[0x180];
 
 	u8         next_pointer_63_32[0x20];
 
 	u8         next_pointer_31_10[0x16];
-	u8         reserved_1[0xa];
+	u8         reserved_at_11b6[0xa];
 
 	u8         block_number[0x20];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_11e0[0x8];
 	u8         token[0x8];
 	u8         ctrl_signature[0x8];
 	u8         signature[0x8];
@@ -6866,7 +6866,7 @@ struct mlx5_ifc_mtt_bits {
 	u8         ptag_63_32[0x20];
 
 	u8         ptag_31_8[0x18];
-	u8         reserved_0[0x6];
+	u8         reserved_at_38[0x6];
 	u8         wr_en[0x1];
 	u8         rd_en[0x1];
 };
@@ -6904,38 +6904,38 @@ struct mlx5_ifc_initial_seg_bits {
 	u8         cmd_interface_rev[0x10];
 	u8         fw_rev_subminor[0x10];
 
-	u8         reserved_0[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         cmdq_phy_addr_63_32[0x20];
 
 	u8         cmdq_phy_addr_31_12[0x14];
-	u8         reserved_1[0x2];
+	u8         reserved_at_b4[0x2];
 	u8         nic_interface[0x2];
 	u8         log_cmdq_size[0x4];
 	u8         log_cmdq_stride[0x4];
 
 	u8         command_doorbell_vector[0x20];
 
-	u8         reserved_2[0xf00];
+	u8         reserved_at_e0[0xf00];
 
 	u8         initializing[0x1];
-	u8         reserved_3[0x4];
+	u8         reserved_at_fe1[0x4];
 	u8         nic_interface_supported[0x3];
-	u8         reserved_4[0x18];
+	u8         reserved_at_fe8[0x18];
 
 	struct mlx5_ifc_health_buffer_bits health_buffer;
 
 	u8         no_dram_nic_offset[0x20];
 
-	u8         reserved_5[0x6e40];
+	u8         reserved_at_1220[0x6e40];
 
-	u8         reserved_6[0x1f];
+	u8         reserved_at_8060[0x1f];
 	u8         clear_int[0x1];
 
 	u8         health_syndrome[0x8];
 	u8         health_counter[0x18];
 
-	u8         reserved_7[0x17fc0];
+	u8         reserved_at_80a0[0x17fc0];
 };
 
 union mlx5_ifc_ports_control_registers_document_bits {
@@ -6980,44 +6980,44 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pvlc_reg_bits pvlc_reg;
 	struct mlx5_ifc_slrg_reg_bits slrg_reg;
 	struct mlx5_ifc_sltp_reg_bits sltp_reg;
-	u8         reserved_0[0x60e0];
+	u8         reserved_at_0[0x60e0];
 };
 
 union mlx5_ifc_debug_enhancements_document_bits {
 	struct mlx5_ifc_health_buffer_bits health_buffer;
-	u8         reserved_0[0x200];
+	u8         reserved_at_0[0x200];
 };
 
 union mlx5_ifc_uplink_pci_interface_document_bits {
 	struct mlx5_ifc_initial_seg_bits initial_seg;
-	u8         reserved_0[0x20060];
+	u8         reserved_at_0[0x20060];
 };
 
 struct mlx5_ifc_set_flow_table_root_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_flow_table_root_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 enum {
@@ -7026,39 +7026,39 @@ enum {
 
 struct mlx5_ifc_modify_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         modify_field_select[0x10];
 
 	u8         table_type[0x8];
-	u8         reserved_4[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_6[0x4];
+	u8         reserved_at_c0[0x4];
 	u8         table_miss_mode[0x4];
-	u8         reserved_7[0x18];
+	u8         reserved_at_c8[0x18];
 
-	u8         reserved_8[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         table_miss_id[0x18];
 
-	u8         reserved_9[0x100];
+	u8         reserved_at_100[0x100];
 };
 
 #endif /* MLX5_IFC_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index 4560d8f1545d..2bb0c3085706 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -324,6 +324,12 @@ struct module_layout {
 #define __module_layout_align
 #endif
 
+struct mod_kallsyms {
+	Elf_Sym *symtab;
+	unsigned int num_symtab;
+	char *strtab;
+};
+
 struct module {
 	enum module_state state;
 
@@ -405,15 +411,10 @@ struct module {
 #endif
 
 #ifdef CONFIG_KALLSYMS
-	/*
-	 * We keep the symbol and string tables for kallsyms.
-	 * The core_* fields below are temporary, loader-only (they
-	 * could really be discarded after module init).
-	 */
-	Elf_Sym *symtab, *core_symtab;
-	unsigned int num_symtab, core_num_syms;
-	char *strtab, *core_strtab;
-
+	/* Protected by RCU and/or module_mutex: use rcu_dereference() */
+	struct mod_kallsyms *kallsyms;
+	struct mod_kallsyms core_kallsyms;
+	
 	/* Section attributes */
 	struct module_sect_attrs *sect_attrs;
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 289c2314d766..5440b7b705eb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3718,7 +3718,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 void *netdev_lower_get_next(struct net_device *dev,
 				struct list_head **iter);
 #define netdev_for_each_lower_dev(dev, ldev, iter) \
-	for (iter = &(dev)->adj_list.lower, \
+	for (iter = (dev)->adj_list.lower.next, \
 	     ldev = netdev_lower_get_next(dev, &(iter)); \
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 48e0320cd643..67300f8e5f2f 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -550,9 +550,7 @@ extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
 
 static inline loff_t nfs_size_to_loff_t(__u64 size)
 {
-	if (size > (__u64) OFFSET_MAX - 1)
-		return OFFSET_MAX - 1;
-	return (loff_t) size;
+	return min_t(u64, size, OFFSET_MAX);
 }
 
 static inline ino_t
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 791098a08a87..d320906cf13e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -275,6 +275,7 @@ struct nfs4_layoutcommit_args {
 	size_t layoutupdate_len;
 	struct page *layoutupdate_page;
 	struct page **layoutupdate_pages;
+	__be32 *start_p;
 };
 
 struct nfs4_layoutcommit_res {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 27df4a6585da..27716254dcc5 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -988,23 +988,6 @@ static inline int pci_is_managed(struct pci_dev *pdev)
 	return pdev->is_managed;
 }
 
-static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq)
-{
-	pdev->irq = irq;
-	pdev->irq_managed = 1;
-}
-
-static inline void pci_reset_managed_irq(struct pci_dev *pdev)
-{
-	pdev->irq = 0;
-	pdev->irq_managed = 0;
-}
-
-static inline bool pci_has_managed_irq(struct pci_dev *pdev)
-{
-	return pdev->irq_managed && pdev->irq > 0;
-}
-
 void pci_disable_device(struct pci_dev *dev);
 
 extern unsigned int pcibios_max_latency;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b35a61a481fa..f5c5a3fa2c81 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -397,6 +397,7 @@ struct pmu {
  * enum perf_event_active_state - the states of a event
  */
 enum perf_event_active_state {
+	PERF_EVENT_STATE_DEAD		= -4,
 	PERF_EVENT_STATE_EXIT		= -3,
 	PERF_EVENT_STATE_ERROR		= -2,
 	PERF_EVENT_STATE_OFF		= -1,
@@ -905,7 +906,7 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
 	}
 }
 
-extern struct static_key_deferred perf_sched_events;
+extern struct static_key_false perf_sched_events;
 
 static __always_inline bool
 perf_sw_migrate_enabled(void)
@@ -924,7 +925,7 @@ static inline void perf_event_task_migrate(struct task_struct *task)
 static inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
-	if (static_key_false(&perf_sched_events.key))
+	if (static_branch_unlikely(&perf_sched_events))
 		__perf_event_task_sched_in(prev, task);
 
 	if (perf_sw_migrate_enabled() && task->sched_migrated) {
@@ -941,7 +942,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 {
 	perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
 
-	if (static_key_false(&perf_sched_events.key))
+	if (static_branch_unlikely(&perf_sched_events))
 		__perf_event_task_sched_out(prev, next);
 }
 
diff --git a/include/linux/pfn.h b/include/linux/pfn.h
index 2d8e49711b63..1132953235c0 100644
--- a/include/linux/pfn.h
+++ b/include/linux/pfn.h
@@ -10,7 +10,7 @@
  * backing is indicated by flags in the high bits of the value.
  */
 typedef struct {
-	unsigned long val;
+	u64 val;
 } pfn_t;
 #endif
 
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 37448ab5fb5c..94994810c7c0 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -9,14 +9,13 @@
  * PFN_DEV - pfn is not covered by system memmap by default
  * PFN_MAP - pfn has a dynamic page mapping established by a device driver
  */
-#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \
-		<< (BITS_PER_LONG - PAGE_SHIFT))
-#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1))
-#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2))
-#define PFN_DEV (1UL << (BITS_PER_LONG - 3))
-#define PFN_MAP (1UL << (BITS_PER_LONG - 4))
-
-static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags)
+#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
+#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
+#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
+#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
+#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
+
+static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
 	pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
 
@@ -29,7 +28,7 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn)
 	return __pfn_to_pfn_t(pfn, 0);
 }
 
-extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags);
+extern pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags);
 
 static inline bool pfn_t_has_page(pfn_t pfn)
 {
@@ -87,7 +86,7 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
 #ifdef __HAVE_ARCH_PTE_DEVMAP
 static inline bool pfn_t_devmap(pfn_t pfn)
 {
-	const unsigned long flags = PFN_DEV|PFN_MAP;
+	const u64 flags = PFN_DEV|PFN_MAP;
 
 	return (pfn.val & flags) == flags;
 }
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 998d8f1c3c91..b50c0492629d 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -49,6 +49,7 @@ struct bq27xxx_reg_cache {
 
 struct bq27xxx_device_info {
 	struct device *dev;
+	int id;
 	enum bq27xxx_chip chip;
 	const char *name;
 	struct bq27xxx_access_methods bus;
diff --git a/include/linux/random.h b/include/linux/random.h
index a75840c1aa71..9c29122037f9 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops;
 #endif
 
 unsigned int get_random_int(void);
+unsigned long get_random_long(void);
 unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
 
 u32 prandom_u32(void);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 11f935c1a090..4ce9ff7086f4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -299,6 +299,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 
diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h
index 343c13ac4f71..35cb9264e0d5 100644
--- a/include/linux/soc/ti/knav_dma.h
+++ b/include/linux/soc/ti/knav_dma.h
@@ -44,6 +44,7 @@
 
 #define KNAV_DMA_NUM_EPIB_WORDS			4
 #define KNAV_DMA_NUM_PS_WORDS			16
+#define KNAV_DMA_NUM_SW_DATA_WORDS		4
 #define KNAV_DMA_FDQ_PER_CHAN			4
 
 /* Tx channel scheduling priority */
@@ -142,6 +143,7 @@ struct knav_dma_cfg {
  * @orig_buff:			buff pointer since 'buff' can be overwritten
  * @epib:			Extended packet info block
  * @psdata:			Protocol specific
+ * @sw_data:			Software private data not touched by h/w
  */
 struct knav_dma_desc {
 	__le32	desc_info;
@@ -154,7 +156,7 @@ struct knav_dma_desc {
 	__le32	orig_buff;
 	__le32	epib[KNAV_DMA_NUM_EPIB_WORDS];
 	__le32	psdata[KNAV_DMA_NUM_PS_WORDS];
-	__le32	pad[4];
+	u32	sw_data[KNAV_DMA_NUM_SW_DATA_WORDS];
 } ____cacheline_aligned;
 
 #if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index acd522a91539..acfdbf353a0b 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -14,8 +14,10 @@
  * See the file COPYING for more details.
  */
 
+#include <linux/smp.h>
 #include <linux/errno.h>
 #include <linux/types.h>
+#include <linux/cpumask.h>
 #include <linux/rcupdate.h>
 #include <linux/tracepoint-defs.h>
 
@@ -132,6 +134,9 @@ extern void syscall_unregfunc(void);
 		void *it_func;						\
 		void *__data;						\
 									\
+		if (!cpu_online(raw_smp_processor_id()))		\
+			return;						\
+									\
 		if (!(cond))						\
 			return;						\
 		prercu;							\
diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h
index cbb20afdbc01..bb679b48f408 100644
--- a/include/linux/ucs2_string.h
+++ b/include/linux/ucs2_string.h
@@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s);
 unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
 int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
 
+unsigned long ucs2_utf8size(const ucs2_char_t *src);
+unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
+			   unsigned long maxlength);
+
 #endif /* _LINUX_UCS2_STRING_H_ */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0e32bc71245e..ca73c503b92a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -311,6 +311,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -411,12 +412,12 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
-	alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
 #define create_freezable_workqueue(name)				\
-	alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
-			1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND |	\
+			WQ_MEM_RECLAIM, 1, (name))
 #define create_singlethread_workqueue(name)				\
-	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
+	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 2a91a0561a47..9b4c418bebd8 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -6,8 +6,8 @@
 #include <linux/mutex.h>
 #include <net/sock.h>
 
-void unix_inflight(struct file *fp);
-void unix_notinflight(struct file *fp);
+void unix_inflight(struct user_struct *user, struct file *fp);
+void unix_notinflight(struct user_struct *user, struct file *fp);
 void unix_gc(void);
 void wait_for_unix_gc(void);
 struct sock *unix_get_socket(struct file *filp);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 481fe1c9044c..49dcad4fe99e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -270,8 +270,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 					    struct sock *newsk,
 					    const struct request_sock *req);
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child);
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child);
 void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 				   unsigned long timeout);
 struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 7029527725dd..4079fc18ffe4 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -61,6 +61,7 @@ struct fib_nh_exception {
 	struct rtable __rcu		*fnhe_rth_input;
 	struct rtable __rcu		*fnhe_rth_output;
 	unsigned long			fnhe_stamp;
+	struct rcu_head			rcu;
 };
 
 struct fnhe_hash_bucket {
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6db96ea0144f..dda9abf6b89c 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -230,6 +230,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4);
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
 struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
diff --git a/include/net/scm.h b/include/net/scm.h
index 262532d111f5..59fa93c01d2a 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -21,6 +21,7 @@ struct scm_creds {
 struct scm_fp_list {
 	short			count;
 	short			max;
+	struct user_struct	*user;
 	struct file		*fp[SCM_MAX_FD];
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f6f8f032c73e..ae6468f5c9f3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -447,7 +447,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
 void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
 void tcp_v4_mtu_reduced(struct sock *sk);
-void tcp_req_err(struct sock *sk, u32 seq);
+void tcp_req_err(struct sock *sk, u32 seq, bool abort);
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_create_openreq_child(const struct sock *sk,
 				      struct request_sock *req,
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index e2b712c90d3f..c21c38ce7450 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -343,7 +343,7 @@ void snd_hdac_bus_enter_link_reset(struct hdac_bus *bus);
 void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus);
 
 void snd_hdac_bus_update_rirb(struct hdac_bus *bus);
-void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
+int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
 				    void (*ack)(struct hdac_bus *,
 						struct hdac_stream *));
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 56cf8e485ef2..28ee5c2e6bcd 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -94,5 +94,8 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
 	sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
 bool target_sense_desc_format(struct se_device *dev);
+sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
+bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
+				       struct request_queue *q, int block_size);
 
 #endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 5d82816cc4e3..e8c8c08bf575 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -140,6 +140,8 @@ enum se_cmd_flags_table {
 	SCF_COMPARE_AND_WRITE		= 0x00080000,
 	SCF_COMPARE_AND_WRITE_POST	= 0x00100000,
 	SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000,
+	SCF_ACK_KREF			= 0x00400000,
+	SCF_USE_CPUID			= 0x00800000,
 };
 
 /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */
@@ -187,6 +189,7 @@ enum target_sc_flags_table {
 	TARGET_SCF_BIDI_OP		= 0x01,
 	TARGET_SCF_ACK_KREF		= 0x02,
 	TARGET_SCF_UNKNOWN_SIZE		= 0x04,
+	TARGET_SCF_USE_CPUID	= 0x08,
 };
 
 /* fabric independent task management function values */
@@ -490,8 +493,9 @@ struct se_cmd {
 #define CMD_T_SENT		(1 << 4)
 #define CMD_T_STOP		(1 << 5)
 #define CMD_T_DEV_ACTIVE	(1 << 7)
-#define CMD_T_REQUEST_STOP	(1 << 8)
 #define CMD_T_BUSY		(1 << 9)
+#define CMD_T_TAS		(1 << 10)
+#define CMD_T_FABRIC_STOP	(1 << 11)
 	spinlock_t		t_state_lock;
 	struct kref		cmd_kref;
 	struct completion	t_transport_stop_comp;
@@ -511,9 +515,6 @@ struct se_cmd {
 
 	struct list_head	state_list;
 
-	/* old task stop completion, consider merging with some of the above */
-	struct completion	task_stop_comp;
-
 	/* backend private data */
 	void			*priv;
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index c251f06f4e11..a7f1f8032ec1 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -863,6 +863,8 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_HYPERV_SYNIC 123
 #define KVM_CAP_S390_RI 124
 #define KVM_CAP_SPAPR_TCE_64 125
+#define KVM_CAP_ARM_PMU_V3 126
+#define KVM_CAP_VCPU_ATTRIBUTES 127
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index 5b4a4be06e2b..cc68b92124d4 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -66,14 +66,18 @@ struct nd_cmd_ars_cap {
 	__u64 length;
 	__u32 status;
 	__u32 max_ars_out;
+	__u32 clear_err_unit;
+	__u32 reserved;
 } __packed;
 
 struct nd_cmd_ars_start {
 	__u64 address;
 	__u64 length;
 	__u16 type;
-	__u8 reserved[6];
+	__u8 flags;
+	__u8 reserved[5];
 	__u32 status;
+	__u32 scrub_time;
 } __packed;
 
 struct nd_cmd_ars_status {
@@ -81,11 +85,14 @@ struct nd_cmd_ars_status {
 	__u32 out_length;
 	__u64 address;
 	__u64 length;
+	__u64 restart_address;
+	__u64 restart_length;
 	__u16 type;
+	__u16 flags;
 	__u32 num_records;
 	struct nd_ars_record {
 		__u32 handle;
-		__u32 flags;
+		__u32 reserved;
 		__u64 err_address;
 		__u64 length;
 	} __packed records[0];
diff --git a/ipc/shm.c b/ipc/shm.c
index ed3027d0f277..331fc1b0b3c7 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -156,11 +156,12 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
 	struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id);
 
 	/*
-	 * We raced in the idr lookup or with shm_destroy().  Either way, the
-	 * ID is busted.
+	 * Callers of shm_lock() must validate the status of the returned ipc
+	 * object pointer (as returned by ipc_lock()), and error out as
+	 * appropriate.
 	 */
-	WARN_ON(IS_ERR(ipcp));
-
+	if (IS_ERR(ipcp))
+		return (void *)ipcp;
 	return container_of(ipcp, struct shmid_kernel, shm_perm);
 }
 
@@ -186,18 +187,33 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
 }
 
 
-/* This is called by fork, once for every shm attach. */
-static void shm_open(struct vm_area_struct *vma)
+static int __shm_open(struct vm_area_struct *vma)
 {
 	struct file *file = vma->vm_file;
 	struct shm_file_data *sfd = shm_file_data(file);
 	struct shmid_kernel *shp;
 
 	shp = shm_lock(sfd->ns, sfd->id);
+
+	if (IS_ERR(shp))
+		return PTR_ERR(shp);
+
 	shp->shm_atim = get_seconds();
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_nattch++;
 	shm_unlock(shp);
+	return 0;
+}
+
+/* This is called by fork, once for every shm attach. */
+static void shm_open(struct vm_area_struct *vma)
+{
+	int err = __shm_open(vma);
+	/*
+	 * We raced in the idr lookup or with shm_destroy().
+	 * Either way, the ID is busted.
+	 */
+	WARN_ON_ONCE(err);
 }
 
 /*
@@ -260,6 +276,14 @@ static void shm_close(struct vm_area_struct *vma)
 	down_write(&shm_ids(ns).rwsem);
 	/* remove from the list of attaches of the shm segment */
 	shp = shm_lock(ns, sfd->id);
+
+	/*
+	 * We raced in the idr lookup or with shm_destroy().
+	 * Either way, the ID is busted.
+	 */
+	if (WARN_ON_ONCE(IS_ERR(shp)))
+		goto done; /* no-op */
+
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_dtim = get_seconds();
 	shp->shm_nattch--;
@@ -267,6 +291,7 @@ static void shm_close(struct vm_area_struct *vma)
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
+done:
 	up_write(&shm_ids(ns).rwsem);
 }
 
@@ -388,17 +413,25 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	struct shm_file_data *sfd = shm_file_data(file);
 	int ret;
 
+	/*
+	 * In case of remap_file_pages() emulation, the file can represent
+	 * removed IPC ID: propogate shm_lock() error to caller.
+	 */
+	ret =__shm_open(vma);
+	if (ret)
+		return ret;
+
 	ret = sfd->file->f_op->mmap(sfd->file, vma);
-	if (ret != 0)
+	if (ret) {
+		shm_close(vma);
 		return ret;
+	}
 	sfd->vm_ops = vma->vm_ops;
 #ifdef CONFIG_MMU
 	WARN_ON(!sfd->vm_ops->fault);
 #endif
 	vma->vm_ops = &shm_vm_ops;
-	shm_open(vma);
-
-	return ret;
+	return 0;
 }
 
 static int shm_release(struct inode *ino, struct file *file)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1d3e8f57de9..2e7f7ab739e4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2082,7 +2082,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
 		/* adjust offset of jmps if necessary */
 		if (i < pos && i + insn->off + 1 > pos)
 			insn->off += delta;
-		else if (i > pos && i + insn->off + 1 < pos)
+		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
 			insn->off -= delta;
 	}
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c03a640ef6da..d27904c193da 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -58,6 +58,7 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/cpuset.h>
 #include <net/sock.h>
 
 /*
@@ -2739,6 +2740,7 @@ out_unlock_rcu:
 out_unlock_threadgroup:
 	percpu_up_write(&cgroup_threadgroup_rwsem);
 	cgroup_kn_unlock(of->kn);
+	cpuset_post_attach_flush();
 	return ret ?: nbytes;
 }
 
@@ -4655,14 +4657,15 @@ static void css_free_work_fn(struct work_struct *work)
 
 	if (ss) {
 		/* css free path */
+		struct cgroup_subsys_state *parent = css->parent;
 		int id = css->id;
 
-		if (css->parent)
-			css_put(css->parent);
-
 		ss->css_free(css);
 		cgroup_idr_remove(&ss->css_idr, id);
 		cgroup_put(cgrp);
+
+		if (parent)
+			css_put(parent);
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
@@ -4758,6 +4761,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
+	atomic_set(&css->online_cnt, 0);
 
 	if (cgroup_parent(cgrp)) {
 		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
@@ -4780,6 +4784,10 @@ static int online_css(struct cgroup_subsys_state *css)
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+
+		atomic_inc(&css->online_cnt);
+		if (css->parent)
+			atomic_inc(&css->parent->online_cnt);
 	}
 	return ret;
 }
@@ -5017,10 +5025,15 @@ static void css_killed_work_fn(struct work_struct *work)
 		container_of(work, struct cgroup_subsys_state, destroy_work);
 
 	mutex_lock(&cgroup_mutex);
-	offline_css(css);
-	mutex_unlock(&cgroup_mutex);
 
-	css_put(css);
+	do {
+		offline_css(css);
+		css_put(css);
+		/* @css can't go away while we're holding cgroup_mutex */
+		css = css->parent;
+	} while (css && atomic_dec_and_test(&css->online_cnt));
+
+	mutex_unlock(&cgroup_mutex);
 }
 
 /* css kill confirmation processing requires process context, bounce */
@@ -5029,8 +5042,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	INIT_WORK(&css->destroy_work, css_killed_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	if (atomic_dec_and_test(&css->online_cnt)) {
+		INIT_WORK(&css->destroy_work, css_killed_work_fn);
+		queue_work(cgroup_destroy_wq, &css->destroy_work);
+	}
 }
 
 /**
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3e945fcd8179..41989ab4db57 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -287,6 +287,8 @@ static struct cpuset top_cpuset = {
 static DEFINE_MUTEX(cpuset_mutex);
 static DEFINE_SPINLOCK(callback_lock);
 
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
 /*
  * CPU / memory hotplug is handled asynchronously.
  */
@@ -972,31 +974,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 }
 
 /*
- * cpuset_migrate_mm
- *
- *    Migrate memory region from one set of nodes to another.
- *
- *    Temporarilly set tasks mems_allowed to target nodes of migration,
- *    so that the migration code can allocate pages on these nodes.
- *
- *    While the mm_struct we are migrating is typically from some
- *    other task, the task_struct mems_allowed that we are hacking
- *    is for our current task, which must allocate new pages for that
- *    migrating memory region.
+ * Migrate memory region from one set of nodes to another.  This is
+ * performed asynchronously as it can be called from process migration path
+ * holding locks involved in process management.  All mm migrations are
+ * performed in the queued order and can be waited for by flushing
+ * cpuset_migrate_mm_wq.
  */
 
+struct cpuset_migrate_mm_work {
+	struct work_struct	work;
+	struct mm_struct	*mm;
+	nodemask_t		from;
+	nodemask_t		to;
+};
+
+static void cpuset_migrate_mm_workfn(struct work_struct *work)
+{
+	struct cpuset_migrate_mm_work *mwork =
+		container_of(work, struct cpuset_migrate_mm_work, work);
+
+	/* on a wq worker, no need to worry about %current's mems_allowed */
+	do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
+	mmput(mwork->mm);
+	kfree(mwork);
+}
+
 static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 							const nodemask_t *to)
 {
-	struct task_struct *tsk = current;
-
-	tsk->mems_allowed = *to;
+	struct cpuset_migrate_mm_work *mwork;
 
-	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+	mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
+	if (mwork) {
+		mwork->mm = mm;
+		mwork->from = *from;
+		mwork->to = *to;
+		INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
+		queue_work(cpuset_migrate_mm_wq, &mwork->work);
+	} else {
+		mmput(mm);
+	}
+}
 
-	rcu_read_lock();
-	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
-	rcu_read_unlock();
+void cpuset_post_attach_flush(void)
+{
+	flush_workqueue(cpuset_migrate_mm_wq);
 }
 
 /*
@@ -1097,7 +1119,8 @@ static void update_tasks_nodemask(struct cpuset *cs)
 		mpol_rebind_mm(mm, &cs->mems_allowed);
 		if (migrate)
 			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
-		mmput(mm);
+		else
+			mmput(mm);
 	}
 	css_task_iter_end(&it);
 
@@ -1545,11 +1568,11 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 			 * @old_mems_allowed is the right nodesets that we
 			 * migrate mm from.
 			 */
-			if (is_memory_migrate(cs)) {
+			if (is_memory_migrate(cs))
 				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
 						  &cpuset_attach_nodemask_to);
-			}
-			mmput(mm);
+			else
+				mmput(mm);
 		}
 	}
 
@@ -1714,6 +1737,7 @@ out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
+	flush_workqueue(cpuset_migrate_mm_wq);
 	return retval ?: nbytes;
 }
 
@@ -2359,6 +2383,9 @@ void __init cpuset_init_smp(void)
 	top_cpuset.effective_mems = node_states[N_MEMORY];
 
 	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+
+	cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
+	BUG_ON(!cpuset_migrate_mm_wq);
 }
 
 /**
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5946460b2425..614614821f00 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -64,8 +64,17 @@ static void remote_function(void *data)
 	struct task_struct *p = tfc->p;
 
 	if (p) {
-		tfc->ret = -EAGAIN;
-		if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+		/* -EAGAIN */
+		if (task_cpu(p) != smp_processor_id())
+			return;
+
+		/*
+		 * Now that we're on right CPU with IRQs disabled, we can test
+		 * if we hit the right task without races.
+		 */
+
+		tfc->ret = -ESRCH; /* No such (running) process */
+		if (p != current)
 			return;
 	}
 
@@ -92,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 		.p	= p,
 		.func	= func,
 		.info	= info,
-		.ret	= -ESRCH, /* No such (running) process */
+		.ret	= -EAGAIN,
 	};
+	int ret;
 
-	if (task_curr(p))
-		smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+	do {
+		ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+		if (!ret)
+			ret = data.ret;
+	} while (ret == -EAGAIN);
 
-	return data.ret;
+	return ret;
 }
 
 /**
@@ -169,19 +182,6 @@ static bool is_kernel_event(struct perf_event *event)
  *    rely on ctx->is_active and therefore cannot use event_function_call().
  *    See perf_install_in_context().
  *
- * This is because we need a ctx->lock serialized variable (ctx->is_active)
- * to reliably determine if a particular task/context is scheduled in. The
- * task_curr() use in task_function_call() is racy in that a remote context
- * switch is not a single atomic operation.
- *
- * As is, the situation is 'safe' because we set rq->curr before we do the
- * actual context switch. This means that task_curr() will fail early, but
- * we'll continue spinning on ctx->is_active until we've passed
- * perf_event_task_sched_out().
- *
- * Without this ctx->lock serialized variable we could have race where we find
- * the task (and hence the context) would not be active while in fact they are.
- *
  * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set.
  */
 
@@ -212,7 +212,7 @@ static int event_function(void *info)
 	 */
 	if (ctx->task) {
 		if (ctx->task != current) {
-			ret = -EAGAIN;
+			ret = -ESRCH;
 			goto unlock;
 		}
 
@@ -276,10 +276,10 @@ static void event_function_call(struct perf_event *event, event_f func, void *da
 		return;
 	}
 
-again:
 	if (task == TASK_TOMBSTONE)
 		return;
 
+again:
 	if (!task_function_call(task, event_function, &efs))
 		return;
 
@@ -289,13 +289,15 @@ again:
 	 * a concurrent perf_event_context_sched_out().
 	 */
 	task = ctx->task;
-	if (task != TASK_TOMBSTONE) {
-		if (ctx->is_active) {
-			raw_spin_unlock_irq(&ctx->lock);
-			goto again;
-		}
-		func(event, NULL, ctx, data);
+	if (task == TASK_TOMBSTONE) {
+		raw_spin_unlock_irq(&ctx->lock);
+		return;
 	}
+	if (ctx->is_active) {
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	func(event, NULL, ctx, data);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -314,6 +316,7 @@ again:
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
+	EVENT_TIME = 0x4,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
@@ -321,7 +324,13 @@ enum event_type_t {
  * perf_sched_events : >0 events exist
  * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
-struct static_key_deferred perf_sched_events __read_mostly;
+
+static void perf_sched_delayed(struct work_struct *work);
+DEFINE_STATIC_KEY_FALSE(perf_sched_events);
+static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed);
+static DEFINE_MUTEX(perf_sched_mutex);
+static atomic_t perf_sched_count;
+
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 
@@ -1288,16 +1297,18 @@ static u64 perf_event_time(struct perf_event *event)
 
 /*
  * Update the total_time_enabled and total_time_running fields for a event.
- * The caller of this function needs to hold the ctx->lock.
  */
 static void update_event_times(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	u64 run_end;
 
+	lockdep_assert_held(&ctx->lock);
+
 	if (event->state < PERF_EVENT_STATE_INACTIVE ||
 	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
 		return;
+
 	/*
 	 * in cgroup mode, time_enabled represents
 	 * the time the event was enabled AND active
@@ -1645,7 +1656,7 @@ out:
 
 static bool is_orphaned_event(struct perf_event *event)
 {
-	return event->state == PERF_EVENT_STATE_EXIT;
+	return event->state == PERF_EVENT_STATE_DEAD;
 }
 
 static inline int pmu_filter_match(struct perf_event *event)
@@ -1690,14 +1701,14 @@ event_sched_out(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_stopped = tstamp;
+	event->pmu->del(event, 0);
+	event->oncpu = -1;
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = tstamp;
-	event->pmu->del(event, 0);
-	event->oncpu = -1;
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
@@ -1732,7 +1743,6 @@ group_sched_out(struct perf_event *group_event,
 }
 
 #define DETACH_GROUP	0x01UL
-#define DETACH_STATE	0x02UL
 
 /*
  * Cross CPU call to remove a performance event
@@ -1752,8 +1762,6 @@ __perf_remove_from_context(struct perf_event *event,
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	list_del_event(event, ctx);
-	if (flags & DETACH_STATE)
-		event->state = PERF_EVENT_STATE_EXIT;
 
 	if (!ctx->nr_events && ctx->is_active) {
 		ctx->is_active = 0;
@@ -2063,14 +2071,27 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
-			       struct perf_event_context *ctx);
+static void ctx_sched_out(struct perf_event_context *ctx,
+			  struct perf_cpu_context *cpuctx,
+			  enum event_type_t event_type);
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
 	     enum event_type_t event_type,
 	     struct task_struct *task);
 
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+			       struct perf_event_context *ctx)
+{
+	if (!cpuctx->task_ctx)
+		return;
+
+	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
+		return;
+
+	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+}
+
 static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
 				struct perf_event_context *ctx,
 				struct task_struct *task)
@@ -2097,49 +2118,68 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 /*
  * Cross CPU call to install and enable a performance event
  *
- * Must be called with ctx->mutex held
+ * Very similar to remote_function() + event_function() but cannot assume that
+ * things like ctx->is_active and cpuctx->task_ctx are set.
  */
 static int  __perf_install_in_context(void *info)
 {
-	struct perf_event_context *ctx = info;
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
+	bool activate = true;
+	int ret = 0;
 
 	raw_spin_lock(&cpuctx->ctx.lock);
 	if (ctx->task) {
 		raw_spin_lock(&ctx->lock);
-		/*
-		 * If we hit the 'wrong' task, we've since scheduled and
-		 * everything should be sorted, nothing to do!
-		 */
 		task_ctx = ctx;
-		if (ctx->task != current)
+
+		/* If we're on the wrong CPU, try again */
+		if (task_cpu(ctx->task) != smp_processor_id()) {
+			ret = -ESRCH;
 			goto unlock;
+		}
 
 		/*
-		 * If task_ctx is set, it had better be to us.
+		 * If we're on the right CPU, see if the task we target is
+		 * current, if not we don't have to activate the ctx, a future
+		 * context switch will do that for us.
 		 */
-		WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx);
+		if (ctx->task != current)
+			activate = false;
+		else
+			WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+
 	} else if (task_ctx) {
 		raw_spin_lock(&task_ctx->lock);
 	}
 
-	ctx_resched(cpuctx, task_ctx);
+	if (activate) {
+		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+		add_event_to_ctx(event, ctx);
+		ctx_resched(cpuctx, task_ctx);
+	} else {
+		add_event_to_ctx(event, ctx);
+	}
+
 unlock:
 	perf_ctx_unlock(cpuctx, task_ctx);
 
-	return 0;
+	return ret;
 }
 
 /*
- * Attach a performance event to a context
+ * Attach a performance event to a context.
+ *
+ * Very similar to event_function_call, see comment there.
  */
 static void
 perf_install_in_context(struct perf_event_context *ctx,
 			struct perf_event *event,
 			int cpu)
 {
-	struct task_struct *task = NULL;
+	struct task_struct *task = READ_ONCE(ctx->task);
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -2147,40 +2187,46 @@ perf_install_in_context(struct perf_event_context *ctx,
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
+	if (!task) {
+		cpu_function_call(cpu, __perf_install_in_context, event);
+		return;
+	}
+
+	/*
+	 * Should not happen, we validate the ctx is still alive before calling.
+	 */
+	if (WARN_ON_ONCE(task == TASK_TOMBSTONE))
+		return;
+
 	/*
 	 * Installing events is tricky because we cannot rely on ctx->is_active
 	 * to be set in case this is the nr_events 0 -> 1 transition.
-	 *
-	 * So what we do is we add the event to the list here, which will allow
-	 * a future context switch to DTRT and then send a racy IPI. If the IPI
-	 * fails to hit the right task, this means a context switch must have
-	 * happened and that will have taken care of business.
 	 */
-	raw_spin_lock_irq(&ctx->lock);
-	task = ctx->task;
+again:
 	/*
-	 * Worse, we cannot even rely on the ctx actually existing anymore. If
-	 * between find_get_context() and perf_install_in_context() the task
-	 * went through perf_event_exit_task() its dead and we should not be
-	 * adding new events.
+	 * Cannot use task_function_call() because we need to run on the task's
+	 * CPU regardless of whether its current or not.
 	 */
-	if (task == TASK_TOMBSTONE) {
+	if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+		return;
+
+	raw_spin_lock_irq(&ctx->lock);
+	task = ctx->task;
+	if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) {
+		/*
+		 * Cannot happen because we already checked above (which also
+		 * cannot happen), and we hold ctx->mutex, which serializes us
+		 * against perf_event_exit_task_context().
+		 */
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
-	update_context_time(ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 	/*
-	 * Update cgrp time only if current cgrp matches event->cgrp.
-	 * Must be done before calling add_event_to_ctx().
+	 * Since !ctx->is_active doesn't mean anything, we must IPI
+	 * unconditionally.
 	 */
-	update_cgrp_time_from_event(event);
-	add_event_to_ctx(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
-
-	if (task)
-		task_function_call(task, __perf_install_in_context, ctx);
-	else
-		cpu_function_call(cpu, __perf_install_in_context, ctx);
+	goto again;
 }
 
 /*
@@ -2219,17 +2265,18 @@ static void __perf_event_enable(struct perf_event *event,
 	    event->state <= PERF_EVENT_STATE_ERROR)
 		return;
 
-	update_context_time(ctx);
+	if (ctx->is_active)
+		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+
 	__perf_event_mark_enabled(event);
 
 	if (!ctx->is_active)
 		return;
 
 	if (!event_filter_match(event)) {
-		if (is_cgroup_event(event)) {
-			perf_cgroup_set_timestamp(current, ctx); // XXX ?
+		if (is_cgroup_event(event))
 			perf_cgroup_defer_enabled(event);
-		}
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
 		return;
 	}
 
@@ -2237,8 +2284,10 @@ static void __perf_event_enable(struct perf_event *event,
 	 * If the event is in a group and isn't the group leader,
 	 * then don't put it on unless the group is on.
 	 */
-	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
+	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) {
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
 		return;
+	}
 
 	task_ctx = cpuctx->task_ctx;
 	if (ctx->task)
@@ -2344,24 +2393,33 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	}
 
 	ctx->is_active &= ~event_type;
+	if (!(ctx->is_active & EVENT_ALL))
+		ctx->is_active = 0;
+
 	if (ctx->task) {
 		WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 		if (!ctx->is_active)
 			cpuctx->task_ctx = NULL;
 	}
 
-	update_context_time(ctx);
-	update_cgrp_time_from_cpuctx(cpuctx);
-	if (!ctx->nr_active)
+	is_active ^= ctx->is_active; /* changed bits */
+
+	if (is_active & EVENT_TIME) {
+		/* update (and stop) ctx time */
+		update_context_time(ctx);
+		update_cgrp_time_from_cpuctx(cpuctx);
+	}
+
+	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
 	perf_pmu_disable(ctx->pmu);
-	if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) {
+	if (is_active & EVENT_PINNED) {
 		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
 	}
 
-	if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) {
+	if (is_active & EVENT_FLEXIBLE) {
 		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
 	}
@@ -2641,18 +2699,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 		perf_cgroup_sched_out(task, next);
 }
 
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
-			       struct perf_event_context *ctx)
-{
-	if (!cpuctx->task_ctx)
-		return;
-
-	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
-		return;
-
-	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-}
-
 /*
  * Called with IRQs disabled
  */
@@ -2735,7 +2781,7 @@ ctx_sched_in(struct perf_event_context *ctx,
 	if (likely(!ctx->nr_events))
 		return;
 
-	ctx->is_active |= event_type;
+	ctx->is_active |= (event_type | EVENT_TIME);
 	if (ctx->task) {
 		if (!is_active)
 			cpuctx->task_ctx = ctx;
@@ -2743,18 +2789,24 @@ ctx_sched_in(struct perf_event_context *ctx,
 			WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 	}
 
-	now = perf_clock();
-	ctx->timestamp = now;
-	perf_cgroup_set_timestamp(task, ctx);
+	is_active ^= ctx->is_active; /* changed bits */
+
+	if (is_active & EVENT_TIME) {
+		/* start ctx time */
+		now = perf_clock();
+		ctx->timestamp = now;
+		perf_cgroup_set_timestamp(task, ctx);
+	}
+
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
 	 */
-	if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED))
+	if (is_active & EVENT_PINNED)
 		ctx_pinned_sched_in(ctx, cpuctx);
 
 	/* Then walk through the lower prio flexible groups */
-	if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE))
+	if (is_active & EVENT_FLEXIBLE)
 		ctx_flexible_sched_in(ctx, cpuctx);
 }
 
@@ -3120,6 +3172,7 @@ static void perf_event_enable_on_exec(int ctxn)
 
 	cpuctx = __get_cpu_context(ctx);
 	perf_ctx_lock(cpuctx, ctx);
+	ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 	list_for_each_entry(event, &ctx->event_list, event_entry)
 		enabled |= event_enable_on_exec(event, ctx);
 
@@ -3537,12 +3590,22 @@ static void unaccount_event(struct perf_event *event)
 	if (has_branch_stack(event))
 		dec = true;
 
-	if (dec)
-		static_key_slow_dec_deferred(&perf_sched_events);
+	if (dec) {
+		if (!atomic_add_unless(&perf_sched_count, -1, 1))
+			schedule_delayed_work(&perf_sched_work, HZ);
+	}
 
 	unaccount_event_cpu(event, event->cpu);
 }
 
+static void perf_sched_delayed(struct work_struct *work)
+{
+	mutex_lock(&perf_sched_mutex);
+	if (atomic_dec_and_test(&perf_sched_count))
+		static_branch_disable(&perf_sched_events);
+	mutex_unlock(&perf_sched_mutex);
+}
+
 /*
  * The following implement mutual exclusion of events on "exclusive" pmus
  * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled
@@ -3752,30 +3815,42 @@ static void put_event(struct perf_event *event)
  */
 int perf_event_release_kernel(struct perf_event *event)
 {
-	struct perf_event_context *ctx;
+	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *child, *tmp;
 
+	/*
+	 * If we got here through err_file: fput(event_file); we will not have
+	 * attached to a context yet.
+	 */
+	if (!ctx) {
+		WARN_ON_ONCE(event->attach_state &
+				(PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP));
+		goto no_ctx;
+	}
+
 	if (!is_kernel_event(event))
 		perf_remove_from_owner(event);
 
 	ctx = perf_event_ctx_lock(event);
 	WARN_ON_ONCE(ctx->parent_ctx);
-	perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE);
-	perf_event_ctx_unlock(event, ctx);
+	perf_remove_from_context(event, DETACH_GROUP);
 
+	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * At this point we must have event->state == PERF_EVENT_STATE_EXIT,
-	 * either from the above perf_remove_from_context() or through
-	 * perf_event_exit_event().
+	 * Mark this even as STATE_DEAD, there is no external reference to it
+	 * anymore.
 	 *
-	 * Therefore, anybody acquiring event->child_mutex after the below
-	 * loop _must_ also see this, most importantly inherit_event() which
-	 * will avoid placing more children on the list.
+	 * Anybody acquiring event->child_mutex after the below loop _must_
+	 * also see this, most importantly inherit_event() which will avoid
+	 * placing more children on the list.
 	 *
 	 * Thus this guarantees that we will in fact observe and kill _ALL_
 	 * child events.
 	 */
-	WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT);
+	event->state = PERF_EVENT_STATE_DEAD;
+	raw_spin_unlock_irq(&ctx->lock);
+
+	perf_event_ctx_unlock(event, ctx);
 
 again:
 	mutex_lock(&event->child_mutex);
@@ -3830,8 +3905,8 @@ again:
 	}
 	mutex_unlock(&event->child_mutex);
 
-	/* Must be the last reference */
-	put_event(event);
+no_ctx:
+	put_event(event); /* Must be the 'last' reference */
 	return 0;
 }
 EXPORT_SYMBOL_GPL(perf_event_release_kernel);
@@ -3988,7 +4063,7 @@ static bool is_event_hup(struct perf_event *event)
 {
 	bool no_children;
 
-	if (event->state != PERF_EVENT_STATE_EXIT)
+	if (event->state > PERF_EVENT_STATE_EXIT)
 		return false;
 
 	mutex_lock(&event->child_mutex);
@@ -7769,8 +7844,28 @@ static void account_event(struct perf_event *event)
 	if (is_cgroup_event(event))
 		inc = true;
 
-	if (inc)
-		static_key_slow_inc(&perf_sched_events.key);
+	if (inc) {
+		if (atomic_inc_not_zero(&perf_sched_count))
+			goto enabled;
+
+		mutex_lock(&perf_sched_mutex);
+		if (!atomic_read(&perf_sched_count)) {
+			static_branch_enable(&perf_sched_events);
+			/*
+			 * Guarantee that all CPUs observe they key change and
+			 * call the perf scheduling hooks before proceeding to
+			 * install events that need them.
+			 */
+			synchronize_sched();
+		}
+		/*
+		 * Now that we have waited for the sync_sched(), allow further
+		 * increments to by-pass the mutex.
+		 */
+		atomic_inc(&perf_sched_count);
+		mutex_unlock(&perf_sched_mutex);
+	}
+enabled:
 
 	account_event_cpu(event, event->cpu);
 }
@@ -8389,10 +8484,19 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (move_group) {
 		gctx = group_leader->ctx;
 		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		if (gctx->task == TASK_TOMBSTONE) {
+			err = -ESRCH;
+			goto err_locked;
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
 
+	if (ctx->task == TASK_TOMBSTONE) {
+		err = -ESRCH;
+		goto err_locked;
+	}
+
 	if (!perf_event_validate_size(event)) {
 		err = -E2BIG;
 		goto err_locked;
@@ -8509,7 +8613,12 @@ err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
-	free_event(event);
+	/*
+	 * If event_file is set, the fput() above will have called ->release()
+	 * and that will take care of freeing the event.
+	 */
+	if (!event_file)
+		free_event(event);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8563,12 +8672,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
+	if (ctx->task == TASK_TOMBSTONE) {
+		err = -ESRCH;
+		goto err_unlock;
+	}
+
 	if (!exclusive_event_installable(event, ctx)) {
-		mutex_unlock(&ctx->mutex);
-		perf_unpin_context(ctx);
-		put_ctx(ctx);
 		err = -EBUSY;
-		goto err_free;
+		goto err_unlock;
 	}
 
 	perf_install_in_context(ctx, event, cpu);
@@ -8577,6 +8688,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	return event;
 
+err_unlock:
+	mutex_unlock(&ctx->mutex);
+	perf_unpin_context(ctx);
+	put_ctx(ctx);
 err_free:
 	free_event(event);
 err:
@@ -8695,7 +8810,7 @@ perf_event_exit_event(struct perf_event *child_event,
 	if (parent_event)
 		perf_group_detach(child_event);
 	list_del_event(child_event, child_ctx);
-	child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */
+	child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */
 	raw_spin_unlock_irq(&child_ctx->lock);
 
 	/*
@@ -9206,7 +9321,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (swhash->hlist_refcount > 0) {
+	if (swhash->hlist_refcount > 0 && !swevent_hlist_deref(swhash)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -9282,11 +9397,9 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
-	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
 		perf_event_exit_cpu(cpu);
 		break;
@@ -9315,9 +9428,6 @@ void __init perf_event_init(void)
 	ret = init_hw_breakpoint();
 	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
 
-	/* do not patch jump label more than once per second */
-	jump_label_rate_limit(&perf_sched_events, HZ);
-
 	/*
 	 * Build time assertion that we keep the data_head at the intended
 	 * location.  IOW, validation we got the __reserved[] size right.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 60ace56618f6..716547fdb873 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -292,7 +292,7 @@ LIST_HEAD(all_lock_classes);
 #define __classhashfn(key)	hash_long((unsigned long)key, CLASSHASH_BITS)
 #define classhashentry(key)	(classhash_table + __classhashfn((key)))
 
-static struct list_head classhash_table[CLASSHASH_SIZE];
+static struct hlist_head classhash_table[CLASSHASH_SIZE];
 
 /*
  * We put the lock dependency chains into a hash-table as well, to cache
@@ -303,7 +303,7 @@ static struct list_head classhash_table[CLASSHASH_SIZE];
 #define __chainhashfn(chain)	hash_long(chain, CHAINHASH_BITS)
 #define chainhashentry(chain)	(chainhash_table + __chainhashfn((chain)))
 
-static struct list_head chainhash_table[CHAINHASH_SIZE];
+static struct hlist_head chainhash_table[CHAINHASH_SIZE];
 
 /*
  * The hash key of the lock dependency chains is a hash itself too:
@@ -666,7 +666,7 @@ static inline struct lock_class *
 look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
 #ifdef CONFIG_DEBUG_LOCKDEP
@@ -719,7 +719,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return NULL;
 
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key) {
 			/*
 			 * Huh! same key, different name? Did someone trample
@@ -742,7 +742,7 @@ static inline struct lock_class *
 register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
@@ -774,7 +774,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * We have to do the hash-walk again, to avoid races
 	 * with another CPU:
 	 */
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key)
 			goto out_unlock_set;
 	}
@@ -805,7 +805,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * We use RCU's safe list-add method to make
 	 * parallel walking of the hash-list safe:
 	 */
-	list_add_tail_rcu(&class->hash_entry, hash_head);
+	hlist_add_head_rcu(&class->hash_entry, hash_head);
 	/*
 	 * Add it to the global list of classes:
 	 */
@@ -1822,7 +1822,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance, int trylock_loop)
+	       struct held_lock *next, int distance, int *stack_saved)
 {
 	struct lock_list *entry;
 	int ret;
@@ -1883,8 +1883,11 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		}
 	}
 
-	if (!trylock_loop && !save_trace(&trace))
-		return 0;
+	if (!*stack_saved) {
+		if (!save_trace(&trace))
+			return 0;
+		*stack_saved = 1;
+	}
 
 	/*
 	 * Ok, all validations passed, add the new lock
@@ -1907,6 +1910,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * Debugging printouts:
 	 */
 	if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
+		/* We drop graph lock, so another thread can overwrite trace. */
+		*stack_saved = 0;
 		graph_unlock();
 		printk("\n new dependency: ");
 		print_lock_name(hlock_class(prev));
@@ -1929,7 +1934,7 @@ static int
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
-	int trylock_loop = 0;
+	int stack_saved = 0;
 	struct held_lock *hlock;
 
 	/*
@@ -1956,7 +1961,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		 */
 		if (hlock->read != 2 && hlock->check) {
 			if (!check_prev_add(curr, hlock, next,
-						distance, trylock_loop))
+						distance, &stack_saved))
 				return 0;
 			/*
 			 * Stop after the first non-trylock entry,
@@ -1979,7 +1984,6 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		if (curr->held_locks[depth].irq_context !=
 				curr->held_locks[depth-1].irq_context)
 			break;
-		trylock_loop = 1;
 	}
 	return 1;
 out_bug:
@@ -2017,7 +2021,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 				     u64 chain_key)
 {
 	struct lock_class *class = hlock_class(hlock);
-	struct list_head *hash_head = chainhashentry(chain_key);
+	struct hlist_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
 	struct held_lock *hlock_curr;
 	int i, j;
@@ -2033,7 +2037,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	 * We can walk it lock-free, because entries only get added
 	 * to the hash:
 	 */
-	list_for_each_entry_rcu(chain, hash_head, entry) {
+	hlist_for_each_entry_rcu(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
 			debug_atomic_inc(chain_lookup_hits);
@@ -2057,7 +2061,7 @@ cache_hit:
 	/*
 	 * We have to walk the chain again locked - to avoid duplicates:
 	 */
-	list_for_each_entry(chain, hash_head, entry) {
+	hlist_for_each_entry(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 			graph_unlock();
 			goto cache_hit;
@@ -2091,7 +2095,7 @@ cache_hit:
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
-	list_add_tail_rcu(&chain->entry, hash_head);
+	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
 
@@ -3875,7 +3879,7 @@ void lockdep_reset(void)
 	nr_process_chains = 0;
 	debug_locks = 1;
 	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
+		INIT_HLIST_HEAD(chainhash_table + i);
 	raw_local_irq_restore(flags);
 }
 
@@ -3894,7 +3898,7 @@ static void zap_class(struct lock_class *class)
 	/*
 	 * Unhash the class and remove it from the all_lock_classes list:
 	 */
-	list_del_rcu(&class->hash_entry);
+	hlist_del_rcu(&class->hash_entry);
 	list_del_rcu(&class->lock_entry);
 
 	RCU_INIT_POINTER(class->key, NULL);
@@ -3917,7 +3921,7 @@ static inline int within(const void *addr, void *start, unsigned long size)
 void lockdep_free_key_range(void *start, unsigned long size)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i;
 	int locked;
@@ -3930,9 +3934,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 	 */
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			if (within(class->key, start, size))
 				zap_class(class);
 			else if (within(class->name, start, size))
@@ -3962,7 +3964,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i, j;
 	int locked;
@@ -3987,9 +3989,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 	locked = graph_lock();
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			int match = 0;
 
 			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
@@ -4027,10 +4027,10 @@ void lockdep_init(void)
 		return;
 
 	for (i = 0; i < CLASSHASH_SIZE; i++)
-		INIT_LIST_HEAD(classhash_table + i);
+		INIT_HLIST_HEAD(classhash_table + i);
 
 	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
+		INIT_HLIST_HEAD(chainhash_table + i);
 
 	lockdep_initialized = 1;
 }
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 70ee3775de24..b981a7b023f0 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -114,7 +114,7 @@ EXPORT_SYMBOL(memunmap);
 
 static void devm_memremap_release(struct device *dev, void *res)
 {
-	memunmap(res);
+	memunmap(*(void **)res);
 }
 
 static int devm_memremap_match(struct device *dev, void *res, void *match_data)
@@ -136,8 +136,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset,
 	if (addr) {
 		*ptr = addr;
 		devres_add(dev, ptr);
-	} else
+	} else {
 		devres_free(ptr);
+		return ERR_PTR(-ENXIO);
+	}
 
 	return addr;
 }
@@ -150,7 +152,7 @@ void devm_memunmap(struct device *dev, void *addr)
 }
 EXPORT_SYMBOL(devm_memunmap);
 
-pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
+pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
 {
 	return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
 }
diff --git a/kernel/module.c b/kernel/module.c
index 8358f4697c0c..794ebe8e878d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -303,6 +303,9 @@ struct load_info {
 	struct _ddebug *debug;
 	unsigned int num_debug;
 	bool sig_ok;
+#ifdef CONFIG_KALLSYMS
+	unsigned long mod_kallsyms_init_off;
+#endif
 	struct {
 		unsigned int sym, str, mod, vers, info, pcpu;
 	} index;
@@ -981,6 +984,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		mod->exit();
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	ftrace_release_mod(mod);
+
 	async_synchronize_full();
 
 	/* Store the name of the last unloaded module for diagnostic purposes */
@@ -2480,10 +2485,21 @@ static void layout_symtab(struct module *mod, struct load_info *info)
 	strsect->sh_flags |= SHF_ALLOC;
 	strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect,
 					 info->index.str) | INIT_OFFSET_MASK;
-	mod->init_layout.size = debug_align(mod->init_layout.size);
 	pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
+
+	/* We'll tack temporary mod_kallsyms on the end. */
+	mod->init_layout.size = ALIGN(mod->init_layout.size,
+				      __alignof__(struct mod_kallsyms));
+	info->mod_kallsyms_init_off = mod->init_layout.size;
+	mod->init_layout.size += sizeof(struct mod_kallsyms);
+	mod->init_layout.size = debug_align(mod->init_layout.size);
 }
 
+/*
+ * We use the full symtab and strtab which layout_symtab arranged to
+ * be appended to the init section.  Later we switch to the cut-down
+ * core-only ones.
+ */
 static void add_kallsyms(struct module *mod, const struct load_info *info)
 {
 	unsigned int i, ndst;
@@ -2492,29 +2508,34 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
 	char *s;
 	Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
 
-	mod->symtab = (void *)symsec->sh_addr;
-	mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
+	/* Set up to point into init section. */
+	mod->kallsyms = mod->init_layout.base + info->mod_kallsyms_init_off;
+
+	mod->kallsyms->symtab = (void *)symsec->sh_addr;
+	mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
 	/* Make sure we get permanent strtab: don't use info->strtab. */
-	mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
+	mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
 
 	/* Set types up while we still have access to sections. */
-	for (i = 0; i < mod->num_symtab; i++)
-		mod->symtab[i].st_info = elf_type(&mod->symtab[i], info);
-
-	mod->core_symtab = dst = mod->core_layout.base + info->symoffs;
-	mod->core_strtab = s = mod->core_layout.base + info->stroffs;
-	src = mod->symtab;
-	for (ndst = i = 0; i < mod->num_symtab; i++) {
+	for (i = 0; i < mod->kallsyms->num_symtab; i++)
+		mod->kallsyms->symtab[i].st_info
+			= elf_type(&mod->kallsyms->symtab[i], info);
+
+	/* Now populate the cut down core kallsyms for after init. */
+	mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs;
+	mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs;
+	src = mod->kallsyms->symtab;
+	for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) {
 		if (i == 0 ||
 		    is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
 				   info->index.pcpu)) {
 			dst[ndst] = src[i];
-			dst[ndst++].st_name = s - mod->core_strtab;
-			s += strlcpy(s, &mod->strtab[src[i].st_name],
+			dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
+			s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name],
 				     KSYM_NAME_LEN) + 1;
 		}
 	}
-	mod->core_num_syms = ndst;
+	mod->core_kallsyms.num_symtab = ndst;
 }
 #else
 static inline void layout_symtab(struct module *mod, struct load_info *info)
@@ -3263,9 +3284,8 @@ static noinline int do_init_module(struct module *mod)
 	module_put(mod);
 	trim_init_extable(mod);
 #ifdef CONFIG_KALLSYMS
-	mod->num_symtab = mod->core_num_syms;
-	mod->symtab = mod->core_symtab;
-	mod->strtab = mod->core_strtab;
+	/* Switch to core kallsyms now init is done: kallsyms may be walking! */
+	rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms);
 #endif
 	mod_tree_remove_init(mod);
 	disable_ro_nx(&mod->init_layout);
@@ -3295,6 +3315,7 @@ fail:
 	module_put(mod);
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	ftrace_release_mod(mod);
 	free_module(mod);
 	wake_up_all(&module_wq);
 	return ret;
@@ -3371,6 +3392,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
 	mod->state = MODULE_STATE_COMING;
 	mutex_unlock(&module_mutex);
 
+	ftrace_module_enable(mod);
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_COMING, mod);
 	return 0;
@@ -3496,7 +3518,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	/* Module is ready to execute: parsing args may do that. */
 	after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp,
-				  -32768, 32767, NULL,
+				  -32768, 32767, mod,
 				  unknown_module_param_cb);
 	if (IS_ERR(after_dashes)) {
 		err = PTR_ERR(after_dashes);
@@ -3627,6 +3649,11 @@ static inline int is_arm_mapping_symbol(const char *str)
 	       && (str[2] == '\0' || str[2] == '.');
 }
 
+static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum)
+{
+	return kallsyms->strtab + kallsyms->symtab[symnum].st_name;
+}
+
 static const char *get_ksymbol(struct module *mod,
 			       unsigned long addr,
 			       unsigned long *size,
@@ -3634,6 +3661,7 @@ static const char *get_ksymbol(struct module *mod,
 {
 	unsigned int i, best = 0;
 	unsigned long nextval;
+	struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
 
 	/* At worse, next value is at end of module */
 	if (within_module_init(addr, mod))
@@ -3643,32 +3671,32 @@ static const char *get_ksymbol(struct module *mod,
 
 	/* Scan for closest preceding symbol, and next symbol. (ELF
 	   starts real symbols at 1). */
-	for (i = 1; i < mod->num_symtab; i++) {
-		if (mod->symtab[i].st_shndx == SHN_UNDEF)
+	for (i = 1; i < kallsyms->num_symtab; i++) {
+		if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
 			continue;
 
 		/* We ignore unnamed symbols: they're uninformative
 		 * and inserted at a whim. */
-		if (mod->symtab[i].st_value <= addr
-		    && mod->symtab[i].st_value > mod->symtab[best].st_value
-		    && *(mod->strtab + mod->symtab[i].st_name) != '\0'
-		    && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
+		if (*symname(kallsyms, i) == '\0'
+		    || is_arm_mapping_symbol(symname(kallsyms, i)))
+			continue;
+
+		if (kallsyms->symtab[i].st_value <= addr
+		    && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value)
 			best = i;
-		if (mod->symtab[i].st_value > addr
-		    && mod->symtab[i].st_value < nextval
-		    && *(mod->strtab + mod->symtab[i].st_name) != '\0'
-		    && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
-			nextval = mod->symtab[i].st_value;
+		if (kallsyms->symtab[i].st_value > addr
+		    && kallsyms->symtab[i].st_value < nextval)
+			nextval = kallsyms->symtab[i].st_value;
 	}
 
 	if (!best)
 		return NULL;
 
 	if (size)
-		*size = nextval - mod->symtab[best].st_value;
+		*size = nextval - kallsyms->symtab[best].st_value;
 	if (offset)
-		*offset = addr - mod->symtab[best].st_value;
-	return mod->strtab + mod->symtab[best].st_name;
+		*offset = addr - kallsyms->symtab[best].st_value;
+	return symname(kallsyms, best);
 }
 
 /* For kallsyms to ask for address resolution.  NULL means not found.  Careful
@@ -3758,19 +3786,21 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		struct mod_kallsyms *kallsyms;
+
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
-		if (symnum < mod->num_symtab) {
-			*value = mod->symtab[symnum].st_value;
-			*type = mod->symtab[symnum].st_info;
-			strlcpy(name, mod->strtab + mod->symtab[symnum].st_name,
-				KSYM_NAME_LEN);
+		kallsyms = rcu_dereference_sched(mod->kallsyms);
+		if (symnum < kallsyms->num_symtab) {
+			*value = kallsyms->symtab[symnum].st_value;
+			*type = kallsyms->symtab[symnum].st_info;
+			strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN);
 			strlcpy(module_name, mod->name, MODULE_NAME_LEN);
 			*exported = is_exported(name, *value, mod);
 			preempt_enable();
 			return 0;
 		}
-		symnum -= mod->num_symtab;
+		symnum -= kallsyms->num_symtab;
 	}
 	preempt_enable();
 	return -ERANGE;
@@ -3779,11 +3809,12 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 static unsigned long mod_find_symname(struct module *mod, const char *name)
 {
 	unsigned int i;
+	struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
 
-	for (i = 0; i < mod->num_symtab; i++)
-		if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 &&
-		    mod->symtab[i].st_info != 'U')
-			return mod->symtab[i].st_value;
+	for (i = 0; i < kallsyms->num_symtab; i++)
+		if (strcmp(name, symname(kallsyms, i)) == 0 &&
+		    kallsyms->symtab[i].st_info != 'U')
+			return kallsyms->symtab[i].st_value;
 	return 0;
 }
 
@@ -3822,11 +3853,14 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
 	module_assert_mutex();
 
 	list_for_each_entry(mod, &modules, list) {
+		/* We hold module_mutex: no need for rcu_dereference_sched */
+		struct mod_kallsyms *kallsyms = mod->kallsyms;
+
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
-		for (i = 0; i < mod->num_symtab; i++) {
-			ret = fn(data, mod->strtab + mod->symtab[i].st_name,
-				 mod, mod->symtab[i].st_value);
+		for (i = 0; i < kallsyms->num_symtab; i++) {
+			ret = fn(data, symname(kallsyms, i),
+				 mod, kallsyms->symtab[i].st_value);
 			if (ret != 0)
 				return ret;
 		}
diff --git a/kernel/resource.c b/kernel/resource.c
index 09c0597840b0..3669d1bfc425 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1083,9 +1083,10 @@ struct resource * __request_region(struct resource *parent,
 		if (!conflict)
 			break;
 		if (conflict != parent) {
-			parent = conflict;
-			if (!(conflict->flags & IORESOURCE_BUSY))
+			if (!(conflict->flags & IORESOURCE_BUSY)) {
+				parent = conflict;
 				continue;
+			}
 		}
 		if (conflict->flags & flags & IORESOURCE_MUXED) {
 			add_wait_queue(&muxed_resource_wait, &wait);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index cd64c979d0e1..57b939c81bce 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -420,7 +420,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * entity.
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
-		printk_deferred_once("sched: DL replenish lagged to much\n");
+		printk_deferred_once("sched: DL replenish lagged too much\n");
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eca592f977b2..57a6eea84694 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4961,7 +4961,7 @@ void ftrace_release_mod(struct module *mod)
 	mutex_unlock(&ftrace_lock);
 }
 
-static void ftrace_module_enable(struct module *mod)
+void ftrace_module_enable(struct module *mod)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
@@ -5038,38 +5038,8 @@ void ftrace_module_init(struct module *mod)
 	ftrace_process_locs(mod, mod->ftrace_callsites,
 			    mod->ftrace_callsites + mod->num_ftrace_callsites);
 }
-
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
-{
-	struct module *mod = data;
-
-	switch (val) {
-	case MODULE_STATE_COMING:
-		ftrace_module_enable(mod);
-		break;
-	case MODULE_STATE_GOING:
-		ftrace_release_mod(mod);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-#else
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
-{
-	return 0;
-}
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_nb = {
-	.notifier_call = ftrace_module_notify,
-	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
-};
-
 void __init ftrace_init(void)
 {
 	extern unsigned long __start_mcount_loc[];
@@ -5098,10 +5068,6 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_nb);
-	if (ret)
-		pr_warning("Failed to register trace ftrace module exit notifier\n");
-
 	set_ftrace_early_filters();
 
 	return;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f333e57c4614..ab09829d3b97 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -869,7 +869,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
-		if (call->class && call->class->reg)
+		if (call->class && call->class->reg &&
+		    !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
 			return file;
 	}
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 202df6cffcca..2a1abbaca10e 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -156,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack)
 		for (; p < top && i < stack_trace_max.nr_entries; p++) {
 			if (stack_dump_trace[i] == ULONG_MAX)
 				break;
-			if (*p == stack_dump_trace[i]) {
+			/*
+			 * The READ_ONCE_NOCHECK is used to let KASAN know that
+			 * this is not a stack-out-of-bounds error.
+			 */
+			if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) {
 				stack_dump_trace[x] = stack_dump_trace[i++];
 				this_size = stack_trace_index[x++] =
 					(top - p) * sizeof(unsigned long);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 61a0264e28f9..7ff5dc7d2ac5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -301,7 +301,23 @@ static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
 static LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
 
-static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */
+/* PL: allowable cpus for unbound wqs and work items */
+static cpumask_var_t wq_unbound_cpumask;
+
+/* CPU where unbound work was last round robin scheduled from this CPU */
+static DEFINE_PER_CPU(int, wq_rr_cpu_last);
+
+/*
+ * Local execution of unbound work items is no longer guaranteed.  The
+ * following always forces round-robin CPU selection on unbound work items
+ * to uncover usages which depend on it.
+ */
+#ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU
+static bool wq_debug_force_rr_cpu = true;
+#else
+static bool wq_debug_force_rr_cpu = false;
+#endif
+module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
 
 /* the per-cpu worker pools */
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
@@ -570,6 +586,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
 						  int node)
 {
 	assert_rcu_or_wq_mutex_or_pool_mutex(wq);
+
+	/*
+	 * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
+	 * delayed item is pending.  The plan is to keep CPU -> NODE
+	 * mapping valid and stable across CPU on/offlines.  Once that
+	 * happens, this workaround can be removed.
+	 */
+	if (unlikely(node == NUMA_NO_NODE))
+		return wq->dfl_pwq;
+
 	return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
 }
 
@@ -1298,6 +1324,39 @@ static bool is_chained_work(struct workqueue_struct *wq)
 	return worker && worker->current_pwq->wq == wq;
 }
 
+/*
+ * When queueing an unbound work item to a wq, prefer local CPU if allowed
+ * by wq_unbound_cpumask.  Otherwise, round robin among the allowed ones to
+ * avoid perturbing sensitive tasks.
+ */
+static int wq_select_unbound_cpu(int cpu)
+{
+	static bool printed_dbg_warning;
+	int new_cpu;
+
+	if (likely(!wq_debug_force_rr_cpu)) {
+		if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
+			return cpu;
+	} else if (!printed_dbg_warning) {
+		pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n");
+		printed_dbg_warning = true;
+	}
+
+	if (cpumask_empty(wq_unbound_cpumask))
+		return cpu;
+
+	new_cpu = __this_cpu_read(wq_rr_cpu_last);
+	new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
+	if (unlikely(new_cpu >= nr_cpu_ids)) {
+		new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
+		if (unlikely(new_cpu >= nr_cpu_ids))
+			return cpu;
+	}
+	__this_cpu_write(wq_rr_cpu_last, new_cpu);
+
+	return new_cpu;
+}
+
 static void __queue_work(int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
@@ -1323,7 +1382,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 		return;
 retry:
 	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
+		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 
 	/* pwq which will be used unless @work is executing elsewhere */
 	if (!(wq->flags & WQ_UNBOUND))
@@ -1464,13 +1523,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	timer_stats_timer_set_start_info(&dwork->timer);
 
 	dwork->wq = wq;
-	/* timer isn't guaranteed to run in this cpu, record earlier */
-	if (cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
 
-	add_timer_on(timer, cpu);
+	if (unlikely(cpu != WORK_CPU_UNBOUND))
+		add_timer_on(timer, cpu);
+	else
+		add_timer(timer);
 }
 
 /**
@@ -2355,7 +2414,8 @@ static void check_flush_dependency(struct workqueue_struct *target_wq,
 	WARN_ONCE(current->flags & PF_MEMALLOC,
 		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  current->pid, current->comm, target_wq->name, target_func);
-	WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM),
+	WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
+			      (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
 		  "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  worker->current_pwq->wq->name, worker->current_func,
 		  target_wq->name, target_func);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ecb9e75614bf..8bfd1aca7a3d 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1400,6 +1400,21 @@ config RCU_EQS_DEBUG
 
 endmenu # "RCU Debugging"
 
+config DEBUG_WQ_FORCE_RR_CPU
+	bool "Force round-robin CPU selection for unbound work items"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  Workqueue used to implicitly guarantee that work items queued
+	  without explicit CPU specified are put on the local CPU.  This
+	  guarantee is no longer true and while local CPU is still
+	  preferred work items may be put on foreign CPUs.  Kernel
+	  parameter "workqueue.debug_force_rr_cpu" is added to force
+	  round-robin CPU selection to flush out usages which depend on the
+	  now broken guarantee.  This config option enables the debug
+	  feature by default.  When enabled, memory and cache locality will
+	  be impacted.
+
 config DEBUG_BLOCK_EXT_DEVT
         bool "Force extended block device numbers and spread them"
 	depends on DEBUG_KERNEL
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 49518fb48cab..e07c1ba9ba13 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -18,6 +18,8 @@ config UBSAN_SANITIZE_ALL
 	  This option activates instrumentation for the entire kernel.
 	  If you don't enable this option, you have to explicitly specify
 	  UBSAN_SANITIZE := y for the files/directories you want to check for UB.
+	  Enabling this option will get kernel image size increased
+	  significantly.
 
 config UBSAN_ALIGNMENT
 	bool "Enable checking of pointers alignment"
@@ -25,5 +27,5 @@ config UBSAN_ALIGNMENT
 	default y if !HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help
 	  This option enables detection of unaligned memory accesses.
-	  Enabling this option on architectures that support unalligned
+	  Enabling this option on architectures that support unaligned
 	  accesses may produce a lot of false positives.
diff --git a/lib/klist.c b/lib/klist.c
index d74cf7a29afd..0507fa5d84c5 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i,
 			  struct klist_node *n)
 {
 	i->i_klist = k;
-	i->i_cur = n;
-	if (n)
-		kref_get(&n->n_ref);
+	i->i_cur = NULL;
+	if (n && kref_get_unless_zero(&n->n_ref))
+		i->i_cur = n;
 }
 EXPORT_SYMBOL_GPL(klist_iter_init_node);
 
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 6f500ef2301d..f0b323abb4c6 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
         }
 }
 EXPORT_SYMBOL(ucs2_strncmp);
+
+unsigned long
+ucs2_utf8size(const ucs2_char_t *src)
+{
+	unsigned long i;
+	unsigned long j = 0;
+
+	for (i = 0; i < ucs2_strlen(src); i++) {
+		u16 c = src[i];
+
+		if (c >= 0x800)
+			j += 3;
+		else if (c >= 0x80)
+			j += 2;
+		else
+			j += 1;
+	}
+
+	return j;
+}
+EXPORT_SYMBOL(ucs2_utf8size);
+
+/*
+ * copy at most maxlength bytes of whole utf8 characters to dest from the
+ * ucs2 string src.
+ *
+ * The return value is the number of characters copied, not including the
+ * final NUL character.
+ */
+unsigned long
+ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
+{
+	unsigned int i;
+	unsigned long j = 0;
+	unsigned long limit = ucs2_strnlen(src, maxlength);
+
+	for (i = 0; maxlength && i < limit; i++) {
+		u16 c = src[i];
+
+		if (c >= 0x800) {
+			if (maxlength < 3)
+				break;
+			maxlength -= 3;
+			dest[j++] = 0xe0 | (c & 0xf000) >> 12;
+			dest[j++] = 0x80 | (c & 0x0fc0) >> 6;
+			dest[j++] = 0x80 | (c & 0x003f);
+		} else if (c >= 0x80) {
+			if (maxlength < 2)
+				break;
+			maxlength -= 2;
+			dest[j++] = 0xc0 | (c & 0x7c0) >> 6;
+			dest[j++] = 0x80 | (c & 0x03f);
+		} else {
+			maxlength -= 1;
+			dest[j++] = c & 0x7f;
+		}
+	}
+	if (maxlength)
+		dest[j] = '\0';
+	return j;
+}
+EXPORT_SYMBOL(ucs2_as_utf8);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 48ff9c36644d..f44e178e6ede 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1590,22 +1590,23 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			return buf;
 		}
 	case 'K':
-		/*
-		 * %pK cannot be used in IRQ context because its test
-		 * for CAP_SYSLOG would be meaningless.
-		 */
-		if (kptr_restrict && (in_irq() || in_serving_softirq() ||
-				      in_nmi())) {
-			if (spec.field_width == -1)
-				spec.field_width = default_width;
-			return string(buf, end, "pK-error", spec);
-		}
-
 		switch (kptr_restrict) {
 		case 0:
 			/* Always print %pK values */
 			break;
 		case 1: {
+			const struct cred *cred;
+
+			/*
+			 * kptr_restrict==1 cannot be used in IRQ context
+			 * because its test for CAP_SYSLOG would be meaningless.
+			 */
+			if (in_irq() || in_serving_softirq() || in_nmi()) {
+				if (spec.field_width == -1)
+					spec.field_width = default_width;
+				return string(buf, end, "pK-error", spec);
+			}
+
 			/*
 			 * Only print the real pointer value if the current
 			 * process has CAP_SYSLOG and is running with the
@@ -1615,8 +1616,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			 * leak pointer values if a binary opens a file using
 			 * %pK and then elevates privileges before reading it.
 			 */
-			const struct cred *cred = current_cred();
-
+			cred = current_cred();
 			if (!has_capability_noaudit(current, CAP_SYSLOG) ||
 			    !uid_eq(cred->euid, cred->uid) ||
 			    !gid_eq(cred->egid, cred->gid))
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 926c76d56388..c554d173a65f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -328,7 +328,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	return 0;
 
 out_destroy_stat:
-	while (--i)
+	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
 out_put_cong:
diff --git a/mm/filemap.c b/mm/filemap.c
index bc943867d68c..3461d97ecb30 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -446,7 +446,8 @@ int filemap_write_and_wait(struct address_space *mapping)
 {
 	int err = 0;
 
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = filemap_fdatawrite(mapping);
 		/*
 		 * Even if the above returned error, the pages may be
@@ -482,13 +483,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 {
 	int err = 0;
 
-	if (dax_mapping(mapping) && mapping->nrexceptional) {
-		err = dax_writeback_mapping_range(mapping, lstart, lend);
-		if (err)
-			return err;
-	}
-
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
 		/* See comment of filemap_write_and_wait() */
@@ -1890,6 +1886,7 @@ EXPORT_SYMBOL(generic_file_read_iter);
  * page_cache_read - adds requested page to the page cache if not already there
  * @file:	file to read
  * @offset:	page index
+ * @gfp_mask:	memory allocation flags
  *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 08fc0ba2207e..e10a4fee88d2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1700,7 +1700,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
-		if (pmd_move_must_withdraw(new_ptl, old_ptl)) {
+		if (pmd_move_must_withdraw(new_ptl, old_ptl) &&
+				vma_is_anonymous(vma)) {
 			pgtable_t pgtable;
 			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
@@ -2835,6 +2836,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pgtable_t pgtable;
 	pmd_t _pmd;
 	bool young, write, dirty;
+	unsigned long addr;
 	int i;
 
 	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
@@ -2860,10 +2862,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	young = pmd_young(*pmd);
 	dirty = pmd_dirty(*pmd);
 
+	pmdp_huge_split_prepare(vma, haddr, pmd);
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
-	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+	for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
 		pte_t entry, *pte;
 		/*
 		 * Note that NUMA hinting access restrictions are not
@@ -2884,9 +2887,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		}
 		if (dirty)
 			SetPageDirty(page + i);
-		pte = pte_offset_map(&_pmd, haddr);
+		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
-		set_pte_at(mm, haddr, pte, entry);
+		set_pte_at(mm, addr, pte, entry);
 		atomic_inc(&page[i]._mapcount);
 		pte_unmap(pte);
 	}
@@ -2936,7 +2939,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pmd_populate(mm, pmd, pgtable);
 
 	if (freeze) {
-		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+		for (i = 0; i < HPAGE_PMD_NR; i++) {
 			page_remove_rmap(page + i, false);
 			put_page(page + i);
 		}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 06ae13e869d0..01f2b48c8618 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2630,8 +2630,10 @@ static int __init hugetlb_init(void)
 			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
 	}
 	default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
-	if (default_hstate_max_huge_pages)
-		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+	if (default_hstate_max_huge_pages) {
+		if (!default_hstate.max_huge_pages)
+			default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+	}
 
 	hugetlb_init_hstates();
 	gather_bootmem_prealloc();
diff --git a/mm/memory.c b/mm/memory.c
index 635451abc8f7..8132787ae4d5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(pmd_none(*pmd)) &&
 	    unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
-	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+	/*
+	 * If a huge pmd materialized under us just retry later.  Use
+	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
+	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
+	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
+	 * in a different thread of this mm, in turn leading to a misleading
+	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
+	 * regular pmd that we can walk with pte_offset_map() and we can do that
+	 * through an atomic read in C, which is what pmd_trans_unstable()
+	 * provides.
+	 */
+	if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd
diff --git a/mm/migrate.c b/mm/migrate.c
index b1034f9c77e7..3ad0fea5c438 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1582,7 +1582,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					 (GFP_HIGHUSER_MOVABLE |
 					  __GFP_THISNODE | __GFP_NOMEMALLOC |
 					  __GFP_NORETRY | __GFP_NOWARN) &
-					 ~(__GFP_IO | __GFP_FS), 0);
+					 ~__GFP_RECLAIM, 0);
 
 	return newpage;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 2f2415a7a688..76d1ec29149b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2664,12 +2664,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (!vma || !(vma->vm_flags & VM_SHARED))
 		goto out;
 
-	if (start < vma->vm_start || start + size > vma->vm_end)
+	if (start < vma->vm_start)
 		goto out;
 
-	if (pgoff == linear_page_index(vma, start)) {
-		ret = 0;
-		goto out;
+	if (start + size > vma->vm_end) {
+		struct vm_area_struct *next;
+
+		for (next = vma->vm_next; next; next = next->vm_next) {
+			/* hole between vmas ? */
+			if (next->vm_start != next->vm_prev->vm_end)
+				goto out;
+
+			if (next->vm_file != vma->vm_file)
+				goto out;
+
+			if (next->vm_flags != vma->vm_flags)
+				goto out;
+
+			if (start + size <= next->vm_end)
+				break;
+		}
+
+		if (!next)
+			goto out;
 	}
 
 	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
@@ -2679,9 +2696,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	flags &= MAP_NONBLOCK;
 	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
 	if (vma->vm_flags & VM_LOCKED) {
+		struct vm_area_struct *tmp;
 		flags |= MAP_LOCKED;
+
 		/* drop PG_Mlocked flag for over-mapped range */
-		munlock_vma_pages_range(vma, start, start + size);
+		for (tmp = vma; tmp->vm_start >= start + size;
+				tmp = tmp->vm_next) {
+			munlock_vma_pages_range(tmp,
+					max(tmp->vm_start, start),
+					min(tmp->vm_end, start + size));
+		}
 	}
 
 	file = get_file(vma->vm_file);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 8eb7bb40dc40..f7cb3d4d9c2e 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -160,9 +160,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		}
 
 		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE)
+			if (next - addr != HPAGE_PMD_SIZE) {
 				split_huge_pmd(vma, pmd, addr);
-			else {
+				if (pmd_none(*pmd))
+					continue;
+			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 						newprot, prot_numa);
 
diff --git a/mm/mremap.c b/mm/mremap.c
index d77946a997f7..8eeba02fc991 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -210,6 +210,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
+			if (pmd_none(*old_pmd))
+				continue;
 			VM_BUG_ON(pmd_trans_huge(*old_pmd));
 		}
 		if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9d4767698a1c..06a005b979a7 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -90,9 +90,9 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
  * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshhold, which will
+ * entire TLB if flush span is greater than a threshold, which will
  * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
@@ -195,7 +195,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
-	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/* collapse entails shooting down ptes not pmd */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
 #endif
diff --git a/mm/slab.c b/mm/slab.c
index 6ecc697a8bc4..621fbcb35a36 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2275,7 +2275,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 
 	err = setup_cpu_cache(cachep, gfp);
 	if (err) {
-		__kmem_cache_shutdown(cachep);
+		__kmem_cache_release(cachep);
 		return err;
 	}
 
@@ -2414,12 +2414,13 @@ int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
 
 int __kmem_cache_shutdown(struct kmem_cache *cachep)
 {
+	return __kmem_cache_shrink(cachep, false);
+}
+
+void __kmem_cache_release(struct kmem_cache *cachep)
+{
 	int i;
 	struct kmem_cache_node *n;
-	int rc = __kmem_cache_shrink(cachep, false);
-
-	if (rc)
-		return rc;
 
 	free_percpu(cachep->cpu_cache);
 
@@ -2430,7 +2431,6 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
 		kfree(n);
 		cachep->node[i] = NULL;
 	}
-	return 0;
 }
 
 /*
diff --git a/mm/slab.h b/mm/slab.h
index 834ad240c0bb..2eedacea439d 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -140,6 +140,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
 
 int __kmem_cache_shutdown(struct kmem_cache *);
+void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *, bool);
 void slab_kmem_cache_release(struct kmem_cache *);
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index b50aef01ccf7..065b7bdabdc3 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -693,6 +693,7 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s,
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
+	__kmem_cache_release(s);
 	destroy_memcg_params(s);
 	kfree_const(s->name);
 	kmem_cache_free(kmem_cache, s);
diff --git a/mm/slob.c b/mm/slob.c
index 17e8f8cc7c53..5ec158054ffe 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -630,6 +630,10 @@ int __kmem_cache_shutdown(struct kmem_cache *c)
 	return 0;
 }
 
+void __kmem_cache_release(struct kmem_cache *c)
+{
+}
+
 int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
 {
 	return 0;
diff --git a/mm/slub.c b/mm/slub.c
index 2e1355ac056b..d8fbd4a6ed59 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1592,18 +1592,12 @@ static inline void add_partial(struct kmem_cache_node *n,
 	__add_partial(n, page, tail);
 }
 
-static inline void
-__remove_partial(struct kmem_cache_node *n, struct page *page)
-{
-	list_del(&page->lru);
-	n->nr_partial--;
-}
-
 static inline void remove_partial(struct kmem_cache_node *n,
 					struct page *page)
 {
 	lockdep_assert_held(&n->list_lock);
-	__remove_partial(n, page);
+	list_del(&page->lru);
+	n->nr_partial--;
 }
 
 /*
@@ -3184,6 +3178,12 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 	}
 }
 
+void __kmem_cache_release(struct kmem_cache *s)
+{
+	free_percpu(s->cpu_slab);
+	free_kmem_cache_nodes(s);
+}
+
 static int init_kmem_cache_nodes(struct kmem_cache *s)
 {
 	int node;
@@ -3443,28 +3443,31 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 
 /*
  * Attempt to free all partial slabs on a node.
- * This is called from kmem_cache_close(). We must be the last thread
- * using the cache and therefore we do not need to lock anymore.
+ * This is called from __kmem_cache_shutdown(). We must take list_lock
+ * because sysfs file might still access partial list after the shutdowning.
  */
 static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
 	struct page *page, *h;
 
+	BUG_ON(irqs_disabled());
+	spin_lock_irq(&n->list_lock);
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			__remove_partial(n, page);
+			remove_partial(n, page);
 			discard_slab(s, page);
 		} else {
 			list_slab_objects(s, page,
-			"Objects remaining in %s on kmem_cache_close()");
+			"Objects remaining in %s on __kmem_cache_shutdown()");
 		}
 	}
+	spin_unlock_irq(&n->list_lock);
 }
 
 /*
  * Release all resources used by a slab cache.
  */
-static inline int kmem_cache_close(struct kmem_cache *s)
+int __kmem_cache_shutdown(struct kmem_cache *s)
 {
 	int node;
 	struct kmem_cache_node *n;
@@ -3476,16 +3479,9 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
-	free_percpu(s->cpu_slab);
-	free_kmem_cache_nodes(s);
 	return 0;
 }
 
-int __kmem_cache_shutdown(struct kmem_cache *s)
-{
-	return kmem_cache_close(s);
-}
-
 /********************************************************************
  *		Kmalloc subsystem
  *******************************************************************/
@@ -3980,7 +3976,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 	memcg_propagate_slab_attrs(s);
 	err = sysfs_slab_add(s);
 	if (err)
-		kmem_cache_close(s);
+		__kmem_cache_release(s);
 
 	return err;
 }
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index d5871ac493eb..f066781be3c8 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1625,7 +1625,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 		rt = atrtr_find(&at_hint);
 	}
-	err = ENETUNREACH;
+	err = -ENETUNREACH;
 	if (!rt)
 		goto out;
 
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index e6c8382c79ba..ccf70bed0d0c 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -527,11 +527,12 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv,
 		 * gets dereferenced.
 		 */
 		spin_lock_bh(&bat_priv->gw.list_lock);
-		hlist_del_init_rcu(&gw_node->list);
+		if (!hlist_unhashed(&gw_node->list)) {
+			hlist_del_init_rcu(&gw_node->list);
+			batadv_gw_node_free_ref(gw_node);
+		}
 		spin_unlock_bh(&bat_priv->gw.list_lock);
 
-		batadv_gw_node_free_ref(gw_node);
-
 		curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
 		if (gw_node == curr_gw)
 			batadv_gw_reselect(bat_priv);
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 01acccc4d218..57f7107169f5 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -76,6 +76,28 @@ out:
 }
 
 /**
+ * batadv_mutual_parents - check if two devices are each others parent
+ * @dev1: 1st net_device
+ * @dev2: 2nd net_device
+ *
+ * veth devices come in pairs and each is the parent of the other!
+ *
+ * Return: true if the devices are each others parent, otherwise false
+ */
+static bool batadv_mutual_parents(const struct net_device *dev1,
+				  const struct net_device *dev2)
+{
+	int dev1_parent_iflink = dev_get_iflink(dev1);
+	int dev2_parent_iflink = dev_get_iflink(dev2);
+
+	if (!dev1_parent_iflink || !dev2_parent_iflink)
+		return false;
+
+	return (dev1_parent_iflink == dev2->ifindex) &&
+	       (dev2_parent_iflink == dev1->ifindex);
+}
+
+/**
  * batadv_is_on_batman_iface - check if a device is a batman iface descendant
  * @net_dev: the device to check
  *
@@ -108,6 +130,9 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 	if (WARN(!parent_dev, "Cannot find parent device"))
 		return false;
 
+	if (batadv_mutual_parents(net_dev, parent_dev))
+		return false;
+
 	ret = batadv_is_on_batman_iface(parent_dev);
 
 	return ret;
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index cdfc85fa2743..0e80fd1461ab 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -303,9 +303,11 @@ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node,
 
 	if (atomic_add_return(v, &vlan->tt.num_entries) == 0) {
 		spin_lock_bh(&orig_node->vlan_list_lock);
-		hlist_del_init_rcu(&vlan->list);
+		if (!hlist_unhashed(&vlan->list)) {
+			hlist_del_init_rcu(&vlan->list);
+			batadv_orig_node_vlan_free_ref(vlan);
+		}
 		spin_unlock_bh(&orig_node->vlan_list_lock);
-		batadv_orig_node_vlan_free_ref(vlan);
 	}
 
 	batadv_orig_node_vlan_free_ref(vlan);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 47bcef754796..883c821a9e78 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4112,8 +4112,10 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status,
 			break;
 		}
 
-		*req_complete = bt_cb(skb)->hci.req_complete;
-		*req_complete_skb = bt_cb(skb)->hci.req_complete_skb;
+		if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB)
+			*req_complete_skb = bt_cb(skb)->hci.req_complete_skb;
+		else
+			*req_complete = bt_cb(skb)->hci.req_complete;
 		kfree_skb(skb);
 	}
 	spin_unlock_irqrestore(&hdev->cmd_q.lock, flags);
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 30e105f57f0d..74c278e00225 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -425,8 +425,8 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 	mp = br_mdb_ip_get(mdb, group);
 	if (!mp) {
 		mp = br_multicast_new_group(br, port, group);
-		err = PTR_ERR(mp);
-		if (IS_ERR(mp))
+		err = PTR_ERR_OR_ZERO(mp);
+		if (err)
 			return err;
 	}
 
diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c
index 61d7617d9249..b82440e1fcb4 100644
--- a/net/caif/cfrfml.c
+++ b/net/caif/cfrfml.c
@@ -159,7 +159,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt)
 		tmppkt = NULL;
 
 		/* Verify that length is correct */
-		err = EPROTO;
+		err = -EPROTO;
 		if (rfml->pdu_size != cfpkt_getlen(pkt) - RFM_HEAD_SIZE + 1)
 			goto out;
 	}
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9cfedf565f5b..9382619a405b 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1197,6 +1197,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
 	return new_piece;
 }
 
+static size_t sizeof_footer(struct ceph_connection *con)
+{
+	return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ?
+	    sizeof(struct ceph_msg_footer) :
+	    sizeof(struct ceph_msg_footer_old);
+}
+
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
 	BUG_ON(!msg);
@@ -2335,9 +2342,9 @@ static int read_partial_message(struct ceph_connection *con)
 			ceph_pr_addr(&con->peer_addr.in_addr),
 			seq, con->in_seq + 1);
 		con->in_base_pos = -front_len - middle_len - data_len -
-			sizeof(m->footer);
+			sizeof_footer(con);
 		con->in_tag = CEPH_MSGR_TAG_READY;
-		return 0;
+		return 1;
 	} else if ((s64)seq - (s64)con->in_seq > 1) {
 		pr_err("read_partial_message bad seq %lld expected %lld\n",
 		       seq, con->in_seq + 1);
@@ -2360,10 +2367,10 @@ static int read_partial_message(struct ceph_connection *con)
 			/* skip this message */
 			dout("alloc_msg said skip message\n");
 			con->in_base_pos = -front_len - middle_len - data_len -
-				sizeof(m->footer);
+				sizeof_footer(con);
 			con->in_tag = CEPH_MSGR_TAG_READY;
 			con->in_seq++;
-			return 0;
+			return 1;
 		}
 
 		BUG_ON(!con->in_msg);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3534e12683d3..5bc053778fed 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2853,8 +2853,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	mutex_lock(&osdc->request_mutex);
 	req = __lookup_request(osdc, tid);
 	if (!req) {
-		pr_warn("%s osd%d tid %llu unknown, skipping\n",
-			__func__, osd->o_osd, tid);
+		dout("%s osd%d tid %llu unknown, skipping\n", __func__,
+		     osd->o_osd, tid);
 		m = NULL;
 		*skip = 1;
 		goto out;
diff --git a/net/core/dev.c b/net/core/dev.c
index 8cba3d852f25..0ef061b2badc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5379,12 +5379,12 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
 {
 	struct netdev_adjacent *lower;
 
-	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+	lower = list_entry(*iter, struct netdev_adjacent, list);
 
 	if (&lower->list == &dev->adj_list.lower)
 		return NULL;
 
-	*iter = &lower->list;
+	*iter = lower->list.next;
 
 	return lower->dev;
 }
@@ -7422,8 +7422,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
-	if (!dev->tx_queue_len)
+	if (!dev->tx_queue_len) {
 		dev->priv_flags |= IFF_NO_QUEUE;
+		dev->tx_queue_len = 1;
+	}
 
 	dev->num_tx_queues = txqs;
 	dev->real_num_tx_queues = txqs;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d79699c9d1b9..12e700332010 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -208,7 +208,6 @@ ip:
 	case htons(ETH_P_IPV6): {
 		const struct ipv6hdr *iph;
 		struct ipv6hdr _iph;
-		__be32 flow_label;
 
 ipv6:
 		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
@@ -230,8 +229,12 @@ ipv6:
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		}
 
-		flow_label = ip6_flowlabel(iph);
-		if (flow_label) {
+		if ((dissector_uses_key(flow_dissector,
+					FLOW_DISSECTOR_KEY_FLOW_LABEL) ||
+		     (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) &&
+		    ip6_flowlabel(iph)) {
+			__be32 flow_label = ip6_flowlabel(iph);
+
 			if (dissector_uses_key(flow_dissector,
 					       FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
 				key_tags = skb_flow_dissector_target(flow_dissector,
@@ -396,6 +399,13 @@ ip_proto_again:
 				goto out_bad;
 			proto = eth->h_proto;
 			nhoff += sizeof(*eth);
+
+			/* Cap headers that we access via pointers at the
+			 * end of the Ethernet header as our maximum alignment
+			 * at that point is only 2 bytes.
+			 */
+			if (NET_IP_ALIGN)
+				hlen = nhoff;
 		}
 
 		key_control->flags |= FLOW_DIS_ENCAPSULATION;
diff --git a/net/core/scm.c b/net/core/scm.c
index 14596fb37172..2696aefdc148 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fplp = fpl;
 		fpl->count = 0;
 		fpl->max = SCM_MAX_FD;
+		fpl->user = NULL;
 	}
 	fpp = &fpl->fp[fpl->count];
 
@@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fpp++ = file;
 		fpl->count++;
 	}
+
+	if (!fpl->user)
+		fpl->user = get_uid(current_user());
+
 	return num;
 }
 
@@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm)
 		scm->fp = NULL;
 		for (i=fpl->count-1; i>=0; i--)
 			fput(fpl->fp[i]);
+		free_uid(fpl->user);
 		kfree(fpl);
 	}
 }
@@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
 		for (i = 0; i < fpl->count; i++)
 			get_file(fpl->fp[i]);
 		new_fpl->max = new_fpl->count;
+		new_fpl->user = get_uid(fpl->user);
 	}
 	return new_fpl;
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b2df375ec9c2..5bf88f58bee7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,8 @@
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);
 
 /**
  *	skb_panic - private function for out-of-line support
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 95b6139d710c..a6beb7b6ae55 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,7 @@ static int zero = 0;
 static int one = 1;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &max_skb_frags,
+	},
 	{ }
 };
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 5684e14932bd..902d606324a0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -824,26 +824,26 @@ lookup:
 
 	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (likely(sk->sk_state == DCCP_LISTEN)) {
-			nsk = dccp_check_req(sk, skb, req);
-		} else {
+		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (dccp_child_process(sk, nsk, skb)) {
 			dccp_v4_ctl_send_reset(sk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9c6d0508e63a..b8608b71a66d 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -691,26 +691,26 @@ lookup:
 
 	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (likely(sk->sk_state == DCCP_LISTEN)) {
-			nsk = dccp_check_req(sk, skb, req);
-		} else {
+		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (dccp_child_process(sk, nsk, skb)) {
 			dccp_v6_ctl_send_reset(sk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 40b9ca72aae3..ab24521beb4d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1194,7 +1194,6 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
 			   ret, slave_dev->name);
-		phy_disconnect(p->phy);
 		ds->ports[port] = NULL;
 		free_netdev(slave_dev);
 		return ret;
@@ -1205,6 +1204,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	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_netdev(slave_dev);
 		return ret;
 	}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebd9d31e65a..f6303b17546b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 46b9c887bede..64148914803a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 	reqsk_put(req);
 }
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child)
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 
 	spin_lock(&queue->rskq_lock);
 	if (unlikely(sk->sk_state != TCP_LISTEN)) {
 		inet_child_forget(sk, req, child);
+		child = NULL;
 	} else {
 		req->sk = child;
 		req->dl_next = NULL;
@@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
 		sk_acceptq_added(sk);
 	}
 	spin_unlock(&queue->rskq_lock);
+	return child;
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
 
@@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
 	if (own_req) {
 		inet_csk_reqsk_queue_drop(sk, req);
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		inet_csk_reqsk_queue_add(sk, req, child);
-		/* Warning: caller must not call reqsk_put(req);
-		 * child stole last reference on it.
-		 */
-		return child;
+		if (inet_csk_reqsk_queue_add(sk, req, child))
+			return child;
 	}
 	/* Too bad, another child took ownership of the request, undo. */
 	bh_unlock_sock(child);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7c51c4e1661f..41ba68de46d8 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 static void ipgre_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
-	dev->netdev_ops		= &gre_tap_netdev_ops;
-	dev->priv_flags 	|= IFF_LIVE_ADDR_CHANGE;
+	dev->netdev_ops	= &gre_tap_netdev_ops;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags	|= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
@@ -1240,6 +1241,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	err = ipgre_newlink(net, dev, tb, NULL);
 	if (err < 0)
 		goto out;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto out;
+
 	return dev;
 out:
 	free_netdev(dev);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5f73a7c03e27..a50124260f5a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c7bd72e9b544..89e8861e05fc 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -943,17 +943,31 @@ done:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
 
-int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 
-	if (new_mtu < 68 ||
-	    new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+	if (new_mtu < 68)
 		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __ip_tunnel_change_mtu(dev, new_mtu, true);
+}
 EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
 
 static void ip_tunnel_dev_free(struct net_device *dev)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index c117b21b937d..d3a27165f9cc 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bc35f1842512..7113bae4e6a0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(net, msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 85f184e429c6..02c62299d717 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 19746b3fcbbe..483ffdf5aa4d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -940,7 +940,7 @@ new_segment:
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1213,7 +1213,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == MAX_SKB_FRAGS || !sg) {
+				if (i == sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -2950,7 +2950,7 @@ static void __tcp_alloc_md5sig_pool(void)
 			struct crypto_hash *hash;
 
 			hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-			if (IS_ERR_OR_NULL(hash))
+			if (IS_ERR(hash))
 				return;
 			per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash;
 		}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1c2a73406261..3b2c8e90a475 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2896,7 +2896,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
 {
 	const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ;
 	struct rtt_meas *m = tcp_sk(sk)->rtt_min;
-	struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now };
+	struct rtt_meas rttm = {
+		.rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1),
+		.ts = now,
+	};
 	u32 elapsed;
 
 	/* Check if the new measurement updates the 1st, 2nd, or 3rd choices */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a4d523709ab3..487ac67059e2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -311,7 +311,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 
 
 /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
-void tcp_req_err(struct sock *sk, u32 seq)
+void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 {
 	struct request_sock *req = inet_reqsk(sk);
 	struct net *net = sock_net(sk);
@@ -323,7 +323,7 @@ void tcp_req_err(struct sock *sk, u32 seq)
 
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-	} else {
+	} else if (abort) {
 		/*
 		 * Still in SYN_RECV, just remove it silently.
 		 * There is no good way to pass the error to the newly
@@ -383,7 +383,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 	seq = ntohl(th->seq);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq,
+				  type == ICMP_PARAMETERPROB ||
+				  type == ICMP_TIME_EXCEEDED ||
+				  (type == ICMP_DEST_UNREACH &&
+				   (code == ICMP_NET_UNREACH ||
+				    code == ICMP_HOST_UNREACH)));
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -1592,28 +1597,30 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (tcp_v4_inbound_md5_hash(sk, skb))
-			goto discard_and_relse;
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+			reqsk_put(req);
+			goto discard_it;
+		}
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index be0b21852b13..95d2f198017e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1048,8 +1048,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 38eeddedfc21..bdd7eac4307a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -583,7 +583,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
@@ -3538,6 +3538,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
+	bool notify = false;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
@@ -3583,7 +3584,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 			/* Because optimistic nodes can use this address,
 			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
 			 */
-			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+			notify = true;
 		}
 	}
 
@@ -3591,6 +3592,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 out:
 	spin_unlock(&ifp->lock);
 	read_unlock_bh(&idev->lock);
+	if (notify)
+		ipv6_ifa_notify(RTM_NEWADDR, ifp);
 }
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 1f9ebe3cbb4a..dc2db4f7b182 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
-		     (sfl = rcu_dereference(*sflp)) != NULL;
+		     (sfl = rcu_dereference_protected(*sflp,
+						      lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
 		     sflp = &sfl->next) {
 			if (sfl->fl->label == freq.flr_label) {
 				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
 					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
-				*sflp = rcu_dereference(sfl->next);
+				*sflp = sfl->next;
 				spin_unlock_bh(&ip6_sk_fl_lock);
 				fl_release(sfl->fl);
 				kfree_rcu(sfl, rcu);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f37f18b6b40c..a69aad1e29d1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1512,6 +1512,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->destructor = ip6gre_dev_free;
 
 	dev->features |= NETIF_F_NETNS_LOCAL;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 }
 
 static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 31ba7ca19757..051b6a6bfff6 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -21,6 +21,10 @@
 #include <net/ipv6.h>
 #include <net/netfilter/ipv6/nf_nat_masquerade.h>
 
+#define MAX_WORK_COUNT	16
+
+static atomic_t v6_worker_count;
+
 unsigned int
 nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
 		       const struct net_device *out)
@@ -78,14 +82,78 @@ static struct notifier_block masq_dev_notifier = {
 	.notifier_call	= masq_device_event,
 };
 
+struct masq_dev_work {
+	struct work_struct work;
+	struct net *net;
+	int ifindex;
+};
+
+static void iterate_cleanup_work(struct work_struct *work)
+{
+	struct masq_dev_work *w;
+	long index;
+
+	w = container_of(work, struct masq_dev_work, work);
+
+	index = w->ifindex;
+	nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0);
+
+	put_net(w->net);
+	kfree(w);
+	atomic_dec(&v6_worker_count);
+	module_put(THIS_MODULE);
+}
+
+/* ipv6 inet notifier is an atomic notifier, i.e. we cannot
+ * schedule.
+ *
+ * Unfortunately, nf_ct_iterate_cleanup can run for a long
+ * time if there are lots of conntracks and the system
+ * handles high softirq load, so it frequently calls cond_resched
+ * while iterating the conntrack table.
+ *
+ * So we defer nf_ct_iterate_cleanup walk to the system workqueue.
+ *
+ * As we can have 'a lot' of inet_events (depending on amount
+ * of ipv6 addresses being deleted), we also need to add an upper
+ * limit to the number of queued work items.
+ */
 static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *ifa = ptr;
-	struct netdev_notifier_info info;
+	const struct net_device *dev;
+	struct masq_dev_work *w;
+	struct net *net;
+
+	if (event != NETDEV_DOWN ||
+	    atomic_read(&v6_worker_count) >= MAX_WORK_COUNT)
+		return NOTIFY_DONE;
+
+	dev = ifa->idev->dev;
+	net = maybe_get_net(dev_net(dev));
+	if (!net)
+		return NOTIFY_DONE;
 
-	netdev_notifier_info_init(&info, ifa->idev->dev);
-	return masq_device_event(this, event, &info);
+	if (!try_module_get(THIS_MODULE))
+		goto err_module;
+
+	w = kmalloc(sizeof(*w), GFP_ATOMIC);
+	if (w) {
+		atomic_inc(&v6_worker_count);
+
+		INIT_WORK(&w->work, iterate_cleanup_work);
+		w->ifindex = dev->ifindex;
+		w->net = net;
+		schedule_work(&w->work);
+
+		return NOTIFY_DONE;
+	}
+
+	module_put(THIS_MODULE);
+ err_module:
+	put_net(net);
+	return NOTIFY_DONE;
 }
 
 static struct notifier_block masq_inet_notifier = {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 006396e31cb0..5c8c84273028 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -327,6 +327,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct tcp_sock *tp;
 	__u32 seq, snd_una;
 	struct sock *sk;
+	bool fatal;
 	int err;
 
 	sk = __inet6_lookup_established(net, &tcp_hashinfo,
@@ -345,8 +346,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		return;
 	}
 	seq = ntohl(th->seq);
+	fatal = icmpv6_err_convert(type, code, &err);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq, fatal);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -400,7 +402,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 	}
 
-	icmpv6_err_convert(type, code, &err);
 
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
@@ -1386,7 +1387,7 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
 		tcp_v6_fill_cb(skb, hdr, th);
@@ -1394,24 +1395,24 @@ process:
 			reqsk_put(req);
 			goto discard_it;
 		}
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 			tcp_v6_restore_cb(skb);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v6_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index f93c5be612a7..2caaa84ce92d 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family,
 	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
 				  NLM_F_ACK, tunnel, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
@@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family,
 	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
 				   NLM_F_ACK, session, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 8c067e6663a1..95e757c377f9 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -891,7 +891,7 @@ config NETFILTER_XT_TARGET_TEE
 	depends on IPV6 || IPV6=n
 	depends on !NF_CONNTRACK || NF_CONNTRACK
 	select NF_DUP_IPV4
-	select NF_DUP_IPV6 if IP6_NF_IPTABLES != n
+	select NF_DUP_IPV6 if IPV6
 	---help---
 	This option adds a "TEE" target with which a packet can be cloned and
 	this clone be rerouted to another nexthop.
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 58882de06bd7..f60b4fdeeb8c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1412,6 +1412,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 		}
 		spin_unlock(lockp);
 		local_bh_enable();
+		cond_resched();
 	}
 
 	for_each_possible_cpu(cpu) {
@@ -1424,6 +1425,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 				set_bit(IPS_DYING_BIT, &ct->status);
 		}
 		spin_unlock_bh(&pcpu->lock);
+		cond_resched();
 	}
 	return NULL;
 found:
@@ -1440,6 +1442,8 @@ void nf_ct_iterate_cleanup(struct net *net,
 	struct nf_conn *ct;
 	unsigned int bucket = 0;
 
+	might_sleep();
+
 	while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) {
 		/* Time to push up daises... */
 		if (del_timer(&ct->timeout))
@@ -1448,6 +1452,7 @@ void nf_ct_iterate_cleanup(struct net *net,
 		/* ... else the timer will get him soon. */
 
 		nf_ct_put(ct);
+		cond_resched();
 	}
 }
 EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index a7ba23353dab..857ae89633af 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -311,14 +311,14 @@ replay:
 #endif
 		{
 			nfnl_unlock(subsys_id);
-			netlink_ack(skb, nlh, -EOPNOTSUPP);
+			netlink_ack(oskb, nlh, -EOPNOTSUPP);
 			return kfree_skb(skb);
 		}
 	}
 
 	if (!ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
-		netlink_ack(skb, nlh, -EOPNOTSUPP);
+		netlink_ack(oskb, nlh, -EOPNOTSUPP);
 		return kfree_skb(skb);
 	}
 
@@ -328,10 +328,12 @@ replay:
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
-		if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) ||
-		    skb->len < nlh->nlmsg_len) {
-			err = -EINVAL;
-			goto ack;
+		if (nlh->nlmsg_len < NLMSG_HDRLEN ||
+		    skb->len < nlh->nlmsg_len ||
+		    nlmsg_len(nlh) < sizeof(struct nfgenmsg)) {
+			nfnl_err_reset(&err_list);
+			status |= NFNL_BATCH_FAILURE;
+			goto done;
 		}
 
 		/* Only requests are handled by the kernel */
@@ -406,7 +408,7 @@ ack:
 				 * pointing to the batch header.
 				 */
 				nfnl_err_reset(&err_list);
-				netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM);
+				netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM);
 				status |= NFNL_BATCH_FAILURE;
 				goto done;
 			}
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 94837d236ab0..2671b9deb103 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -312,7 +312,7 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout)
 			hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
 				untimeout(h, timeout);
 		}
-		nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+		spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
 	}
 	local_bh_enable();
 }
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index c7808fc19719..c9743f78f219 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -100,7 +100,7 @@ static int nft_counter_init(const struct nft_ctx *ctx,
 
 	cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu);
 	if (cpu_stats == NULL)
-		return ENOMEM;
+		return -ENOMEM;
 
 	preempt_disable();
 	this_cpu = this_cpu_ptr(cpu_stats);
@@ -138,7 +138,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src)
 	cpu_stats = __netdev_alloc_pcpu_stats(struct nft_counter_percpu,
 					      GFP_ATOMIC);
 	if (cpu_stats == NULL)
-		return ENOMEM;
+		return -ENOMEM;
 
 	preempt_disable();
 	this_cpu = this_cpu_ptr(cpu_stats);
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 3eff7b67cdf2..6e57a3966dc5 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -38,7 +38,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-#if IS_ENABLED(CONFIG_NF_DUP_IPV6)
+#if IS_ENABLED(CONFIG_IPV6)
 static unsigned int
 tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
@@ -131,7 +131,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
 		.destroy    = tee_tg_destroy,
 		.me         = THIS_MODULE,
 	},
-#if IS_ENABLED(CONFIG_NF_DUP_IPV6)
+#if IS_ENABLED(CONFIG_IPV6)
 	{
 		.name       = "TEE",
 		.revision   = 1,
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 1605691d9414..5eb7694348b5 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -90,7 +90,9 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	int err;
 	struct vxlan_config conf = {
 		.no_share = true,
-		.flags = VXLAN_F_COLLECT_METADATA,
+		.flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX,
+		/* Don't restrict the packets that can be sent by MTU */
+		.mtu = IP_MAX_MTU,
 	};
 
 	if (!options) {
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index b5c2cf2aa6d4..af1acf009866 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1852,6 +1852,7 @@ reset:
 	}
 
 	tp = old_tp;
+	protocol = tc_skb_protocol(skb);
 	goto reclassify;
 #endif
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index ab0d538a74ed..1099e99a53c4 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -60,6 +60,8 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 
+#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
+
 /* Global data structures. */
 struct sctp_globals sctp_globals __read_mostly;
 
@@ -1355,6 +1357,8 @@ static __init int sctp_init(void)
 	unsigned long limit;
 	int max_share;
 	int order;
+	int num_entries;
+	int max_entry_order;
 
 	sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));
 
@@ -1407,14 +1411,24 @@ static __init int sctp_init(void)
 
 	/* Size and allocate the association hash table.
 	 * The methodology is similar to that of the tcp hash tables.
+	 * Though not identical.  Start by getting a goal size
 	 */
 	if (totalram_pages >= (128 * 1024))
 		goal = totalram_pages >> (22 - PAGE_SHIFT);
 	else
 		goal = totalram_pages >> (24 - PAGE_SHIFT);
 
-	for (order = 0; (1UL << order) < goal; order++)
-		;
+	/* Then compute the page order for said goal */
+	order = get_order(goal);
+
+	/* Now compute the required page order for the maximum sized table we
+	 * want to create
+	 */
+	max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
+				    sizeof(struct sctp_bind_hashbucket));
+
+	/* Limit the page order by that maximum hash table size */
+	order = min(order, max_entry_order);
 
 	/* Allocate and initialize the endpoint hash table.  */
 	sctp_ep_hashsize = 64;
@@ -1430,20 +1444,35 @@ static __init int sctp_init(void)
 		INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
 	}
 
-	/* Allocate and initialize the SCTP port hash table.  */
+	/* Allocate and initialize the SCTP port hash table.
+	 * Note that order is initalized to start at the max sized
+	 * table we want to support.  If we can't get that many pages
+	 * reduce the order and try again
+	 */
 	do {
-		sctp_port_hashsize = (1UL << order) * PAGE_SIZE /
-					sizeof(struct sctp_bind_hashbucket);
-		if ((sctp_port_hashsize > (64 * 1024)) && order > 0)
-			continue;
 		sctp_port_hashtable = (struct sctp_bind_hashbucket *)
 			__get_free_pages(GFP_KERNEL | __GFP_NOWARN, order);
 	} while (!sctp_port_hashtable && --order > 0);
+
 	if (!sctp_port_hashtable) {
 		pr_err("Failed bind hash alloc\n");
 		status = -ENOMEM;
 		goto err_bhash_alloc;
 	}
+
+	/* Now compute the number of entries that will fit in the
+	 * port hash space we allocated
+	 */
+	num_entries = (1UL << order) * PAGE_SIZE /
+		      sizeof(struct sctp_bind_hashbucket);
+
+	/* And finish by rounding it down to the nearest power of two
+	 * this wastes some memory of course, but its needed because
+	 * the hash function operates based on the assumption that
+	 * that the number of entries is a power of two
+	 */
+	sctp_port_hashsize = rounddown_pow_of_two(num_entries);
+
 	for (i = 0; i < sctp_port_hashsize; i++) {
 		spin_lock_init(&sctp_port_hashtable[i].lock);
 		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
@@ -1452,7 +1481,8 @@ static __init int sctp_init(void)
 	if (sctp_transport_hashtable_init())
 		goto err_thash_alloc;
 
-	pr_info("Hash tables configured (bind %d)\n", sctp_port_hashsize);
+	pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize,
+		num_entries);
 
 	sctp_sysctl_register();
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5ca2ebfe0be8..e878da0949db 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5538,6 +5538,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
+	int i;
 
 	if (!ep->auth_enable)
 		return -EACCES;
@@ -5555,8 +5556,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 		return -EFAULT;
 	if (put_user(num_idents, &p->shmac_num_idents))
 		return -EFAULT;
-	if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len))
-		return -EFAULT;
+	for (i = 0; i < num_idents; i++) {
+		__u16 hmacid = ntohs(hmacs->hmac_ids[i]);
+
+		if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 799e65b944b9..cabf586f47d7 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -740,7 +740,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 		default:
 			printk(KERN_CRIT "%s: bad return from "
 				"gss_fill_context: %zd\n", __func__, err);
-			BUG();
+			gss_msg->msg.errno = -EIO;
 		}
 		goto err_release_msg;
 	}
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 2b32fd602669..273bc3a35425 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize)
 	if (bp[0] == '\\' && bp[1] == 'x') {
 		/* HEX STRING */
 		bp += 2;
-		while (len < bufsize) {
+		while (len < bufsize - 1) {
 			int h, l;
 
 			h = hex_to_bin(bp[0]);
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index cc1251d07297..2dcd7640eeb5 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -341,6 +341,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt,
 	rqst->rq_reply_bytes_recvd = 0;
 	rqst->rq_bytes_sent = 0;
 	rqst->rq_xid = headerp->rm_xid;
+
+	rqst->rq_private_buf.len = size;
 	set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state);
 
 	buf = &rqst->rq_rcv_buf;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 0c2944fb9ae0..347cdc99ed09 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1973,8 +1973,10 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
 
 	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
 			  NLM_F_MULTI, TIPC_NL_LINK_GET);
-	if (!hdr)
+	if (!hdr) {
+		tipc_bcast_unlock(net);
 		return -EMSGSIZE;
+	}
 
 	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
 	if (!attrs)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index fa97d9649a28..9d7a16fc5ca4 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -346,12 +346,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
 	skb_queue_head_init(&n->bc_entry.inputq2);
 	for (i = 0; i < MAX_BEARERS; i++)
 		spin_lock_init(&n->links[i].lock);
-	hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]);
-	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
-		if (n->addr < temp_node->addr)
-			break;
-	}
-	list_add_tail_rcu(&n->list, &temp_node->list);
 	n->state = SELF_DOWN_PEER_LEAVING;
 	n->signature = INVALID_NODE_SIG;
 	n->active_links[0] = INVALID_BEARER_ID;
@@ -372,6 +366,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
 	tipc_node_get(n);
 	setup_timer(&n->timer, tipc_node_timeout, (unsigned long)n);
 	n->keepalive_intv = U32_MAX;
+	hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]);
+	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+		if (n->addr < temp_node->addr)
+			break;
+	}
+	list_add_tail_rcu(&n->list, &temp_node->list);
 exit:
 	spin_unlock_bh(&tn->node_list_lock);
 	return n;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 49d5093eb055..f75f847e688d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1496,7 +1496,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	UNIXCB(skb).fp = NULL;
 
 	for (i = scm->fp->count-1; i >= 0; i--)
-		unix_notinflight(scm->fp->fp[i]);
+		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
 }
 
 static void unix_destruct_scm(struct sk_buff *skb)
@@ -1561,7 +1561,7 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 		return -ENOMEM;
 
 	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_inflight(scm->fp->fp[i]);
+		unix_inflight(scm->fp->user, scm->fp->fp[i]);
 	return max_level;
 }
 
@@ -1781,7 +1781,12 @@ restart_locked:
 			goto out_unlock;
 	}
 
-	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+	/* other == sk && unix_peer(other) != sk if
+	 * - unix_peer(sk) == NULL, destination address bound to sk
+	 * - unix_peer(sk) == sk by time of get but disconnected before lock
+	 */
+	if (other != sk &&
+	    unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
 		if (timeo) {
 			timeo = unix_wait_for_peer(other, timeo);
 
@@ -2277,13 +2282,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 	size_t size = state->size;
 	unsigned int last_len;
 
-	err = -EINVAL;
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (unlikely(sk->sk_state != TCP_ESTABLISHED)) {
+		err = -EINVAL;
 		goto out;
+	}
 
-	err = -EOPNOTSUPP;
-	if (flags & MSG_OOB)
+	if (unlikely(flags & MSG_OOB)) {
+		err = -EOPNOTSUPP;
 		goto out;
+	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
@@ -2305,6 +2312,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 		bool drop_skb;
 		struct sk_buff *skb, *last;
 
+redo:
 		unix_state_lock(sk);
 		if (sock_flag(sk, SOCK_DEAD)) {
 			err = -ECONNRESET;
@@ -2329,9 +2337,11 @@ again:
 				goto unlock;
 
 			unix_state_unlock(sk);
-			err = -EAGAIN;
-			if (!timeo)
+			if (!timeo) {
+				err = -EAGAIN;
 				break;
+			}
+
 			mutex_unlock(&u->readlock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
@@ -2344,7 +2354,7 @@ again:
 			}
 
 			mutex_lock(&u->readlock);
-			continue;
+			goto redo;
 unlock:
 			unix_state_unlock(sk);
 			break;
diff --git a/net/unix/diag.c b/net/unix/diag.c
index c512f64d5287..4d9679701a6d 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -220,7 +220,7 @@ done:
 	return skb->len;
 }
 
-static struct sock *unix_lookup_by_ino(int ino)
+static struct sock *unix_lookup_by_ino(unsigned int ino)
 {
 	int i;
 	struct sock *sk;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 8fcdc2283af5..6a0d48525fcf 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -116,7 +116,7 @@ struct sock *unix_get_socket(struct file *filp)
  * descriptor if it is for an AF_UNIX socket.
  */
 
-void unix_inflight(struct file *fp)
+void unix_inflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -133,11 +133,11 @@ void unix_inflight(struct file *fp)
 		}
 		unix_tot_inflight++;
 	}
-	fp->f_cred->user->unix_inflight++;
+	user->unix_inflight++;
 	spin_unlock(&unix_gc_lock);
 }
 
-void unix_notinflight(struct file *fp)
+void unix_notinflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -152,7 +152,7 @@ void unix_notinflight(struct file *fp)
 			list_del_init(&u->link);
 		unix_tot_inflight--;
 	}
-	fp->f_cred->user->unix_inflight--;
+	user->unix_inflight--;
 	spin_unlock(&unix_gc_lock);
 }
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 7fd1220fbfa0..bbe65dcb9738 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1557,8 +1557,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (err < 0)
 		goto out;
 
-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-
 	while (total_written < len) {
 		ssize_t written;
 
@@ -1578,7 +1576,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 				goto out_wait;
 
 			release_sock(sk);
+			prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 			timeout = schedule_timeout(timeout);
+			finish_wait(sk_sleep(sk), &wait);
 			lock_sock(sk);
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeout);
@@ -1588,8 +1588,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 				goto out_wait;
 			}
 
-			prepare_to_wait(sk_sleep(sk), &wait,
-					TASK_INTERRUPTIBLE);
 		}
 
 		/* These checks occur both as part of and after the loop
@@ -1635,7 +1633,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 out_wait:
 	if (total_written > 0)
 		err = total_written;
-	finish_wait(sk_sleep(sk), &wait);
 out:
 	release_sock(sk);
 	return err;
@@ -1716,7 +1713,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (err < 0)
 		goto out;
 
-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
 	while (1) {
 		s64 ready = vsock_stream_has_data(vsk);
@@ -1727,7 +1723,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			 */
 
 			err = -ENOMEM;
-			goto out_wait;
+			goto out;
 		} else if (ready > 0) {
 			ssize_t read;
 
@@ -1750,7 +1746,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 					vsk, target, read,
 					!(flags & MSG_PEEK), &recv_data);
 			if (err < 0)
-				goto out_wait;
+				goto out;
 
 			if (read >= target || flags & MSG_PEEK)
 				break;
@@ -1773,7 +1769,9 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 				break;
 
 			release_sock(sk);
+			prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 			timeout = schedule_timeout(timeout);
+			finish_wait(sk_sleep(sk), &wait);
 			lock_sock(sk);
 
 			if (signal_pending(current)) {
@@ -1783,9 +1781,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 				err = -EAGAIN;
 				break;
 			}
-
-			prepare_to_wait(sk_sleep(sk), &wait,
-					TASK_INTERRUPTIBLE);
 		}
 	}
 
@@ -1816,8 +1811,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		err = copied;
 	}
 
-out_wait:
-	finish_wait(sk_sleep(sk), &wait);
 out:
 	release_sock(sk);
 	return err;
diff --git a/scripts/prune-kernel b/scripts/prune-kernel
new file mode 100755
index 000000000000..ab5034e1d081
--- /dev/null
+++ b/scripts/prune-kernel
@@ -0,0 +1,20 @@
+#!/bin/bash
+
+# because I use CONFIG_LOCALVERSION_AUTO, not the same version again and
+# again, /boot and /lib/modules/ eventually fill up.
+# Dumb script to purge that stuff:
+
+for f in "$@"
+do
+        if rpm -qf "/lib/modules/$f" >/dev/null; then
+                echo "keeping $f (installed from rpm)"
+        elif [ $(uname -r) = "$f" ]; then
+                echo "keeping $f (running kernel) "
+        else
+                echo "removing $f"
+                rm -f "/boot/initramfs-$f.img" "/boot/System.map-$f"
+                rm -f "/boot/vmlinuz-$f"   "/boot/config-$f"
+                rm -rf "/lib/modules/$f"
+                new-kernel-pkg --remove $f
+        fi
+done
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index f7160253f17f..e6ea9d4b1de9 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -23,6 +23,7 @@
 #include <linux/integrity.h>
 #include <linux/evm.h>
 #include <crypto/hash.h>
+#include <crypto/algapi.h>
 #include "evm.h"
 
 int evm_initialized;
@@ -148,7 +149,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 				   xattr_value_len, calc.digest);
 		if (rc)
 			break;
-		rc = memcmp(xattr_data->digest, calc.digest,
+		rc = crypto_memneq(xattr_data->digest, calc.digest,
 			    sizeof(calc.digest));
 		if (rc)
 			rc = -EINVAL;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index f8110cfd80ff..f1ab71504e1d 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3249,7 +3249,7 @@ static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t
 
 static void selinux_inode_getsecid(struct inode *inode, u32 *secid)
 {
-	struct inode_security_struct *isec = inode_security(inode);
+	struct inode_security_struct *isec = inode_security_novalidate(inode);
 	*secid = isec->sid;
 }
 
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2bbb41822d8e..8495b9368190 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -83,6 +83,7 @@ static struct nlmsg_perm nlmsg_tcpdiag_perms[] =
 	{ TCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ DCCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ SOCK_DIAG_BY_FAMILY,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+	{ SOCK_DESTROY,		NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE },
 };
 
 static struct nlmsg_perm nlmsg_xfrm_perms[] =
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index fadd3eb8e8bb..9106d8e2300e 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -74,6 +74,18 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream);
 static DEFINE_RWLOCK(snd_pcm_link_rwlock);
 static DECLARE_RWSEM(snd_pcm_link_rwsem);
 
+/* Writer in rwsem may block readers even during its waiting in queue,
+ * and this may lead to a deadlock when the code path takes read sem
+ * twice (e.g. one in snd_pcm_action_nonatomic() and another in
+ * snd_pcm_stream_lock()).  As a (suboptimal) workaround, let writer to
+ * spin until it gets the lock.
+ */
+static inline void down_write_nonblock(struct rw_semaphore *lock)
+{
+	while (!down_write_trylock(lock))
+		cond_resched();
+}
+
 /**
  * snd_pcm_stream_lock - Lock the PCM stream
  * @substream: PCM substream
@@ -1813,7 +1825,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 		res = -ENOMEM;
 		goto _nolock;
 	}
-	down_write(&snd_pcm_link_rwsem);
+	down_write_nonblock(&snd_pcm_link_rwsem);
 	write_lock_irq(&snd_pcm_link_rwlock);
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN ||
 	    substream->runtime->status->state != substream1->runtime->status->state ||
@@ -1860,7 +1872,7 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream)
 	struct snd_pcm_substream *s;
 	int res = 0;
 
-	down_write(&snd_pcm_link_rwsem);
+	down_write_nonblock(&snd_pcm_link_rwsem);
 	write_lock_irq(&snd_pcm_link_rwlock);
 	if (!snd_pcm_stream_linked(substream)) {
 		res = -EALREADY;
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index 801076687bb1..c850345c43b5 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool)
 
 	if (snd_BUG_ON(!pool))
 		return -EINVAL;
-	if (pool->ptr)			/* should be atomic? */
-		return 0;
 
-	pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size);
-	if (!pool->ptr)
+	cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size);
+	if (!cellptr)
 		return -ENOMEM;
 
 	/* add new cells to the free cell list */
 	spin_lock_irqsave(&pool->lock, flags);
+	if (pool->ptr) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		vfree(cellptr);
+		return 0;
+	}
+
+	pool->ptr = cellptr;
 	pool->free = NULL;
 
 	for (cell = 0; cell < pool->size; cell++) {
diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c
index 921fb2bd8fad..fe686ee41c6d 100644
--- a/sound/core/seq/seq_ports.c
+++ b/sound/core/seq/seq_ports.c
@@ -535,19 +535,22 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client,
 					bool is_src, bool ack)
 {
 	struct snd_seq_port_subs_info *grp;
+	struct list_head *list;
+	bool empty;
 
 	grp = is_src ? &port->c_src : &port->c_dest;
+	list = is_src ? &subs->src_list : &subs->dest_list;
 	down_write(&grp->list_mutex);
 	write_lock_irq(&grp->list_lock);
-	if (is_src)
-		list_del(&subs->src_list);
-	else
-		list_del(&subs->dest_list);
+	empty = list_empty(list);
+	if (!empty)
+		list_del_init(list);
 	grp->exclusive = 0;
 	write_unlock_irq(&grp->list_lock);
 	up_write(&grp->list_mutex);
 
-	unsubscribe_port(client, port, grp, &subs->info, ack);
+	if (!empty)
+		unsubscribe_port(client, port, grp, &subs->info, ack);
 }
 
 /* connect two ports */
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 9b513a05765a..dca817fc7894 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -422,7 +422,7 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event)
 	spin_lock_irqsave(&timer->lock, flags);
 	list_for_each_entry(ts, &ti->slave_active_head, active_list)
 		if (ts->ccallback)
-			ts->ccallback(ti, event + 100, &tstamp, resolution);
+			ts->ccallback(ts, event + 100, &tstamp, resolution);
 	spin_unlock_irqrestore(&timer->lock, flags);
 }
 
@@ -518,9 +518,13 @@ static int _snd_timer_stop(struct snd_timer_instance *timeri, int event)
 			spin_unlock_irqrestore(&slave_active_lock, flags);
 			return -EBUSY;
 		}
+		if (timeri->timer)
+			spin_lock(&timeri->timer->lock);
 		timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING;
 		list_del_init(&timeri->ack_list);
 		list_del_init(&timeri->active_list);
+		if (timeri->timer)
+			spin_unlock(&timeri->timer->lock);
 		spin_unlock_irqrestore(&slave_active_lock, flags);
 		goto __end;
 	}
@@ -1929,6 +1933,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 {
 	struct snd_timer_user *tu;
 	long result = 0, unit;
+	int qhead;
 	int err = 0;
 
 	tu = file->private_data;
@@ -1940,7 +1945,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				err = -EAGAIN;
-				break;
+				goto _error;
 			}
 
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -1955,42 +1960,37 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 			if (tu->disconnected) {
 				err = -ENODEV;
-				break;
+				goto _error;
 			}
 			if (signal_pending(current)) {
 				err = -ERESTARTSYS;
-				break;
+				goto _error;
 			}
 		}
 
+		qhead = tu->qhead++;
+		tu->qhead %= tu->queue_size;
 		spin_unlock_irq(&tu->qlock);
-		if (err < 0)
-			goto _error;
 
 		if (tu->tread) {
-			if (copy_to_user(buffer, &tu->tqueue[tu->qhead++],
-					 sizeof(struct snd_timer_tread))) {
+			if (copy_to_user(buffer, &tu->tqueue[qhead],
+					 sizeof(struct snd_timer_tread)))
 				err = -EFAULT;
-				goto _error;
-			}
 		} else {
-			if (copy_to_user(buffer, &tu->queue[tu->qhead++],
-					 sizeof(struct snd_timer_read))) {
+			if (copy_to_user(buffer, &tu->queue[qhead],
+					 sizeof(struct snd_timer_read)))
 				err = -EFAULT;
-				goto _error;
-			}
 		}
 
-		tu->qhead %= tu->queue_size;
-
-		result += unit;
-		buffer += unit;
-
 		spin_lock_irq(&tu->qlock);
 		tu->qused--;
+		if (err < 0)
+			goto _error;
+		result += unit;
+		buffer += unit;
 	}
-	spin_unlock_irq(&tu->qlock);
  _error:
+	spin_unlock_irq(&tu->qlock);
 	return result > 0 ? result : err;
 }
 
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index bde33308f0d6..c0f8f613f1f1 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -87,7 +87,7 @@ MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-128) for dummy driver.");
 module_param(fake_buffer, bool, 0444);
 MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations.");
 #ifdef CONFIG_HIGH_RES_TIMERS
-module_param(hrtimer, bool, 0444);
+module_param(hrtimer, bool, 0644);
 MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source.");
 #endif
 
@@ -109,6 +109,9 @@ struct dummy_timer_ops {
 	snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *);
 };
 
+#define get_dummy_ops(substream) \
+	(*(const struct dummy_timer_ops **)(substream)->runtime->private_data)
+
 struct dummy_model {
 	const char *name;
 	int (*playback_constraints)(struct snd_pcm_runtime *runtime);
@@ -137,7 +140,6 @@ struct snd_dummy {
 	int iobox;
 	struct snd_kcontrol *cd_volume_ctl;
 	struct snd_kcontrol *cd_switch_ctl;
-	const struct dummy_timer_ops *timer_ops;
 };
 
 /*
@@ -231,6 +233,8 @@ static struct dummy_model *dummy_models[] = {
  */
 
 struct dummy_systimer_pcm {
+	/* ops must be the first item */
+	const struct dummy_timer_ops *timer_ops;
 	spinlock_t lock;
 	struct timer_list timer;
 	unsigned long base_time;
@@ -366,6 +370,8 @@ static const struct dummy_timer_ops dummy_systimer_ops = {
  */
 
 struct dummy_hrtimer_pcm {
+	/* ops must be the first item */
+	const struct dummy_timer_ops *timer_ops;
 	ktime_t base_time;
 	ktime_t period_time;
 	atomic_t running;
@@ -492,31 +498,25 @@ static const struct dummy_timer_ops dummy_hrtimer_ops = {
 
 static int dummy_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
-		return dummy->timer_ops->start(substream);
+		return get_dummy_ops(substream)->start(substream);
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		return dummy->timer_ops->stop(substream);
+		return get_dummy_ops(substream)->stop(substream);
 	}
 	return -EINVAL;
 }
 
 static int dummy_pcm_prepare(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
-	return dummy->timer_ops->prepare(substream);
+	return get_dummy_ops(substream)->prepare(substream);
 }
 
 static snd_pcm_uframes_t dummy_pcm_pointer(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
-	return dummy->timer_ops->pointer(substream);
+	return get_dummy_ops(substream)->pointer(substream);
 }
 
 static struct snd_pcm_hardware dummy_pcm_hardware = {
@@ -562,17 +562,19 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream)
 	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
 	struct dummy_model *model = dummy->model;
 	struct snd_pcm_runtime *runtime = substream->runtime;
+	const struct dummy_timer_ops *ops;
 	int err;
 
-	dummy->timer_ops = &dummy_systimer_ops;
+	ops = &dummy_systimer_ops;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	if (hrtimer)
-		dummy->timer_ops = &dummy_hrtimer_ops;
+		ops = &dummy_hrtimer_ops;
 #endif
 
-	err = dummy->timer_ops->create(substream);
+	err = ops->create(substream);
 	if (err < 0)
 		return err;
+	get_dummy_ops(substream) = ops;
 
 	runtime->hw = dummy->pcm_hw;
 	if (substream->pcm->device & 1) {
@@ -594,7 +596,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream)
 			err = model->capture_constraints(substream->runtime);
 	}
 	if (err < 0) {
-		dummy->timer_ops->free(substream);
+		get_dummy_ops(substream)->free(substream);
 		return err;
 	}
 	return 0;
@@ -602,8 +604,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream)
 
 static int dummy_pcm_close(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-	dummy->timer_ops->free(substream);
+	get_dummy_ops(substream)->free(substream);
 	return 0;
 }
 
diff --git a/sound/firewire/digi00x/amdtp-dot.c b/sound/firewire/digi00x/amdtp-dot.c
index b02a5e8cad44..0ac92aba5bc1 100644
--- a/sound/firewire/digi00x/amdtp-dot.c
+++ b/sound/firewire/digi00x/amdtp-dot.c
@@ -63,7 +63,7 @@ struct amdtp_dot {
 #define BYTE_PER_SAMPLE (4)
 #define MAGIC_DOT_BYTE (2)
 #define MAGIC_BYTE_OFF(x) (((x) * BYTE_PER_SAMPLE) + MAGIC_DOT_BYTE)
-static const u8 dot_scrt(const u8 idx, const unsigned int off)
+static u8 dot_scrt(const u8 idx, const unsigned int off)
 {
 	/*
 	 * the length of the added pattern only depends on the lower nibble
diff --git a/sound/firewire/tascam/tascam-transaction.c b/sound/firewire/tascam/tascam-transaction.c
index 904ce0329fa1..040a96d1ba8e 100644
--- a/sound/firewire/tascam/tascam-transaction.c
+++ b/sound/firewire/tascam/tascam-transaction.c
@@ -230,6 +230,7 @@ int snd_tscm_transaction_register(struct snd_tscm *tscm)
 	return err;
 error:
 	fw_core_remove_address_handler(&tscm->async_handler);
+	tscm->async_handler.callback_data = NULL;
 	return err;
 }
 
@@ -276,6 +277,9 @@ void snd_tscm_transaction_unregister(struct snd_tscm *tscm)
 	__be32 reg;
 	unsigned int i;
 
+	if (tscm->async_handler.callback_data == NULL)
+		return;
+
 	/* Turn off FireWire LED. */
 	reg = cpu_to_be32(0x0000008e);
 	snd_fw_transaction(tscm->unit, TCODE_WRITE_QUADLET_REQUEST,
@@ -297,6 +301,8 @@ void snd_tscm_transaction_unregister(struct snd_tscm *tscm)
 			   &reg, sizeof(reg), 0);
 
 	fw_core_remove_address_handler(&tscm->async_handler);
+	tscm->async_handler.callback_data = NULL;
+
 	for (i = 0; i < TSCM_MIDI_OUT_PORT_MAX; i++)
 		snd_fw_async_midi_port_destroy(&tscm->out_ports[i]);
 }
diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c
index ee0bc1839508..e281c338e562 100644
--- a/sound/firewire/tascam/tascam.c
+++ b/sound/firewire/tascam/tascam.c
@@ -21,7 +21,6 @@ static struct snd_tscm_spec model_specs[] = {
 		.pcm_playback_analog_channels = 8,
 		.midi_capture_ports = 4,
 		.midi_playback_ports = 4,
-		.is_controller = true,
 	},
 	{
 		.name = "FW-1082",
@@ -31,9 +30,16 @@ static struct snd_tscm_spec model_specs[] = {
 		.pcm_playback_analog_channels = 2,
 		.midi_capture_ports = 2,
 		.midi_playback_ports = 2,
-		.is_controller = true,
 	},
-	/* FW-1804 may be supported. */
+	{
+		.name = "FW-1804",
+		.has_adat = true,
+		.has_spdif = true,
+		.pcm_capture_analog_channels = 8,
+		.pcm_playback_analog_channels = 2,
+		.midi_capture_ports = 2,
+		.midi_playback_ports = 4,
+	},
 };
 
 static int identify_model(struct snd_tscm *tscm)
diff --git a/sound/firewire/tascam/tascam.h b/sound/firewire/tascam/tascam.h
index 2d028d2bd3bd..30ab77e924f7 100644
--- a/sound/firewire/tascam/tascam.h
+++ b/sound/firewire/tascam/tascam.h
@@ -39,7 +39,6 @@ struct snd_tscm_spec {
 	unsigned int pcm_playback_analog_channels;
 	unsigned int midi_capture_ports;
 	unsigned int midi_playback_ports;
-	bool is_controller;
 };
 
 #define TSCM_MIDI_IN_PORT_MAX	4
@@ -72,9 +71,6 @@ struct snd_tscm {
 	struct snd_fw_async_midi_port out_ports[TSCM_MIDI_OUT_PORT_MAX];
 	u8 running_status[TSCM_MIDI_OUT_PORT_MAX];
 	bool on_sysex[TSCM_MIDI_OUT_PORT_MAX];
-
-	/* For control messages. */
-	struct snd_firewire_tascam_status *status;
 };
 
 #define TSCM_ADDR_BASE			0xffff00000000ull
diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c
index b5a17cb510a0..8c486235c905 100644
--- a/sound/hda/hdac_controller.c
+++ b/sound/hda/hdac_controller.c
@@ -426,18 +426,22 @@ EXPORT_SYMBOL_GPL(snd_hdac_bus_stop_chip);
  * @bus: HD-audio core bus
  * @status: INTSTS register value
  * @ask: callback to be called for woken streams
+ *
+ * Returns the bits of handled streams, or zero if no stream is handled.
  */
-void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
+int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
 				    void (*ack)(struct hdac_bus *,
 						struct hdac_stream *))
 {
 	struct hdac_stream *azx_dev;
 	u8 sd_status;
+	int handled = 0;
 
 	list_for_each_entry(azx_dev, &bus->stream_list, list) {
 		if (status & azx_dev->sd_int_sta_mask) {
 			sd_status = snd_hdac_stream_readb(azx_dev, SD_STS);
 			snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK);
+			handled |= 1 << azx_dev->index;
 			if (!azx_dev->substream || !azx_dev->running ||
 			    !(sd_status & SD_INT_COMPLETE))
 				continue;
@@ -445,6 +449,7 @@ void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
 				ack(bus, azx_dev);
 		}
 	}
+	return handled;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_bus_handle_stream_irq);
 
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 37cf9cee9835..27de8015717d 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -930,6 +930,8 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)
 	struct azx *chip = dev_id;
 	struct hdac_bus *bus = azx_bus(chip);
 	u32 status;
+	bool active, handled = false;
+	int repeat = 0; /* count for avoiding endless loop */
 
 #ifdef CONFIG_PM
 	if (azx_has_pm_runtime(chip))
@@ -939,33 +941,36 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)
 
 	spin_lock(&bus->reg_lock);
 
-	if (chip->disabled) {
-		spin_unlock(&bus->reg_lock);
-		return IRQ_NONE;
-	}
-
-	status = azx_readl(chip, INTSTS);
-	if (status == 0 || status == 0xffffffff) {
-		spin_unlock(&bus->reg_lock);
-		return IRQ_NONE;
-	}
+	if (chip->disabled)
+		goto unlock;
 
-	snd_hdac_bus_handle_stream_irq(bus, status, stream_update);
+	do {
+		status = azx_readl(chip, INTSTS);
+		if (status == 0 || status == 0xffffffff)
+			break;
 
-	/* clear rirb int */
-	status = azx_readb(chip, RIRBSTS);
-	if (status & RIRB_INT_MASK) {
-		if (status & RIRB_INT_RESPONSE) {
-			if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
-				udelay(80);
-			snd_hdac_bus_update_rirb(bus);
+		handled = true;
+		active = false;
+		if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update))
+			active = true;
+
+		/* clear rirb int */
+		status = azx_readb(chip, RIRBSTS);
+		if (status & RIRB_INT_MASK) {
+			active = true;
+			if (status & RIRB_INT_RESPONSE) {
+				if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
+					udelay(80);
+				snd_hdac_bus_update_rirb(bus);
+			}
+			azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
 		}
-		azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
-	}
+	} while (active && ++repeat < 10);
 
+ unlock:
 	spin_unlock(&bus->reg_lock);
 
-	return IRQ_HANDLED;
+	return IRQ_RETVAL(handled);
 }
 EXPORT_SYMBOL_GPL(azx_interrupt);
 
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 30c8efe0f80a..7ca5b89f088a 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -4028,9 +4028,9 @@ static void pin_power_callback(struct hda_codec *codec,
 			       struct hda_jack_callback *jack,
 			       bool on)
 {
-	if (jack && jack->tbl->nid)
+	if (jack && jack->nid)
 		sync_power_state_change(codec,
-					set_pin_power_jack(codec, jack->tbl->nid, on));
+					set_pin_power_jack(codec, jack->nid, on));
 }
 
 /* callback only doing power up -- called at first */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 4045dca3d699..e5240cb3749f 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -363,7 +363,10 @@ enum {
 					((pci)->device == 0x0d0c) || \
 					((pci)->device == 0x160c))
 
-#define IS_BROXTON(pci)	((pci)->device == 0x5a98)
+#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
+#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
+#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
+#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
 
 static char *driver_short_names[] = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
@@ -540,13 +543,13 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset)
 
 	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
 		snd_hdac_set_codec_wakeup(bus, true);
-	if (IS_BROXTON(pci)) {
+	if (IS_SKL_PLUS(pci)) {
 		pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val);
 		val = val & ~INTEL_HDA_CGCTL_MISCBDCGE;
 		pci_write_config_dword(pci, INTEL_HDA_CGCTL, val);
 	}
 	azx_init_chip(chip, full_reset);
-	if (IS_BROXTON(pci)) {
+	if (IS_SKL_PLUS(pci)) {
 		pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val);
 		val = val | INTEL_HDA_CGCTL_MISCBDCGE;
 		pci_write_config_dword(pci, INTEL_HDA_CGCTL, val);
@@ -555,7 +558,7 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset)
 		snd_hdac_set_codec_wakeup(bus, false);
 
 	/* reduce dma latency to avoid noise */
-	if (IS_BROXTON(pci))
+	if (IS_BXT(pci))
 		bxt_reduce_dma_latency(chip);
 }
 
@@ -977,11 +980,6 @@ static int azx_resume(struct device *dev)
 /* put codec down to D3 at hibernation for Intel SKL+;
  * otherwise BIOS may still access the codec and screw up the driver
  */
-#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
-#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
-#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
-#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
-
 static int azx_freeze_noirq(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
@@ -2168,10 +2166,10 @@ static void azx_remove(struct pci_dev *pci)
 	struct hda_intel *hda;
 
 	if (card) {
-		/* flush the pending probing work */
+		/* cancel the pending probing work */
 		chip = card->private_data;
 		hda = container_of(chip, struct hda_intel, chip);
-		flush_work(&hda->probe_work);
+		cancel_work_sync(&hda->probe_work);
 
 		snd_card_free(card);
 	}
diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c
index c945e257d368..a33234e04d4f 100644
--- a/sound/pci/hda/hda_jack.c
+++ b/sound/pci/hda/hda_jack.c
@@ -259,7 +259,7 @@ snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
 		if (!callback)
 			return ERR_PTR(-ENOMEM);
 		callback->func = func;
-		callback->tbl = jack;
+		callback->nid = jack->nid;
 		callback->next = jack->callback;
 		jack->callback = callback;
 	}
diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h
index 858708a044f5..e9814c0168ea 100644
--- a/sound/pci/hda/hda_jack.h
+++ b/sound/pci/hda/hda_jack.h
@@ -21,7 +21,7 @@ struct hda_jack_callback;
 typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callback *);
 
 struct hda_jack_callback {
-	struct hda_jack_tbl *tbl;
+	hda_nid_t nid;
 	hda_jack_callback_fn func;
 	unsigned int private_data;	/* arbitrary data */
 	struct hda_jack_callback *next;
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 4ef2259f88ca..9ceb2bc36e68 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -4427,13 +4427,16 @@ static void ca0132_process_dsp_response(struct hda_codec *codec,
 static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 {
 	struct ca0132_spec *spec = codec->spec;
+	struct hda_jack_tbl *tbl;
 
 	/* Delay enabling the HP amp, to let the mic-detection
 	 * state machine run.
 	 */
 	cancel_delayed_work_sync(&spec->unsol_hp_work);
 	schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500));
-	cb->tbl->block_report = 1;
+	tbl = snd_hda_jack_tbl_get(codec, cb->nid);
+	if (tbl)
+		tbl->block_report = 1;
 }
 
 static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1f52b55d77c9..8ee78dbd4c60 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -448,7 +448,8 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 	eld = &per_pin->sink_eld;
 
 	mutex_lock(&per_pin->lock);
-	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data)) {
+	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) ||
+	    eld->eld_size > ELD_MAX_SIZE) {
 		mutex_unlock(&per_pin->lock);
 		snd_BUG();
 		return -EINVAL;
@@ -1193,7 +1194,7 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid)
 static void jack_callback(struct hda_codec *codec,
 			  struct hda_jack_callback *jack)
 {
-	check_presence_and_report(codec, jack->tbl->nid);
+	check_presence_and_report(codec, jack->nid);
 }
 
 static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 21992fb7035d..1f357cd72d9c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -282,7 +282,7 @@ static void alc_update_knob_master(struct hda_codec *codec,
 	uctl = kzalloc(sizeof(*uctl), GFP_KERNEL);
 	if (!uctl)
 		return;
-	val = snd_hda_codec_read(codec, jack->tbl->nid, 0,
+	val = snd_hda_codec_read(codec, jack->nid, 0,
 				 AC_VERB_GET_VOLUME_KNOB_CONTROL, 0);
 	val &= HDA_AMP_VOLMASK;
 	uctl->value.integer.value[0] = val;
@@ -1787,7 +1787,6 @@ enum {
 	ALC882_FIXUP_NO_PRIMARY_HP,
 	ALC887_FIXUP_ASUS_BASS,
 	ALC887_FIXUP_BASS_CHMAP,
-	ALC882_FIXUP_DISABLE_AAMIX,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -1949,8 +1948,6 @@ static void alc882_fixup_no_primary_hp(struct hda_codec *codec,
 
 static void alc_fixup_bass_chmap(struct hda_codec *codec,
 				 const struct hda_fixup *fix, int action);
-static void alc_fixup_disable_aamix(struct hda_codec *codec,
-				    const struct hda_fixup *fix, int action);
 
 static const struct hda_fixup alc882_fixups[] = {
 	[ALC882_FIXUP_ABIT_AW9D_MAX] = {
@@ -2188,10 +2185,6 @@ static const struct hda_fixup alc882_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_bass_chmap,
 	},
-	[ALC882_FIXUP_DISABLE_AAMIX] = {
-		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_disable_aamix,
-	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2230,6 +2223,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT),
 	SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP),
+	SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP),
 
 	/* All Apple entries are in codec SSIDs */
 	SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF),
@@ -2259,7 +2253,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1458, 0xa182, "Gigabyte Z170X-UD3", ALC882_FIXUP_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
@@ -3808,6 +3801,10 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 
 static void alc_headset_mode_default(struct hda_codec *codec)
 {
+	static struct coef_fw coef0225[] = {
+		UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10),
+		{}
+	};
 	static struct coef_fw coef0255[] = {
 		WRITE_COEF(0x45, 0xc089),
 		WRITE_COEF(0x45, 0xc489),
@@ -3849,6 +3846,9 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 	};
 
 	switch (codec->core.vendor_id) {
+	case 0x10ec0225:
+		alc_process_coef_fw(codec, coef0225);
+		break;
 	case 0x10ec0255:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
@@ -4756,6 +4756,9 @@ enum {
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
+	ALC255_FIXUP_DELL_SPK_NOISE,
+	ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC280_FIXUP_HP_HEADSET_MIC,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5375,6 +5378,29 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc233_fixup_lenovo_line2_mic_hotkey,
 	},
+	[ALC255_FIXUP_DELL_SPK_NOISE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
+	[ALC225_FIXUP_DELL1_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* Disable pass-through path for FRONT 14h */
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x36 },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 },
+			{}
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
+	[ALC280_FIXUP_HP_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -5417,6 +5443,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -5477,6 +5504,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -5645,10 +5673,10 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{0x21, 0x03211020}
 
 static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
-	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC225_STANDARD_PINS,
 		{0x14, 0x901701a0}),
-	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC225_STANDARD_PINS,
 		{0x14, 0x901701b0}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 2c7c5eb8b1e9..37b70f8e878f 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -493,9 +493,9 @@ static void jack_update_power(struct hda_codec *codec,
 	if (!spec->num_pwrs)
 		return;
 
-	if (jack && jack->tbl->nid) {
-		stac_toggle_power_map(codec, jack->tbl->nid,
-				      snd_hda_jack_detect(codec, jack->tbl->nid),
+	if (jack && jack->nid) {
+		stac_toggle_power_map(codec, jack->nid,
+				      snd_hda_jack_detect(codec, jack->nid),
 				      true);
 		return;
 	}
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 3191e0a7d273..d1fb035f44db 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -635,6 +635,7 @@ static int acp_dma_open(struct snd_pcm_substream *substream)
 					    SNDRV_PCM_HW_PARAM_PERIODS);
 	if (ret < 0) {
 		dev_err(prtd->platform->dev, "set integer constraint failed\n");
+		kfree(adata);
 		return ret;
 	}
 
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 33143fe1de0b..91785318b283 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1929,6 +1929,25 @@ static struct {
 	{ 1000000, 13500000, 0,  1 },
 };
 
+static const unsigned int pseudo_fref_max[ARIZONA_FLL_MAX_FRATIO] = {
+	13500000,
+	 6144000,
+	 6144000,
+	 3072000,
+	 3072000,
+	 2822400,
+	 2822400,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	  768000,
+};
+
 static struct {
 	unsigned int min;
 	unsigned int max;
@@ -2042,16 +2061,32 @@ static int arizona_calc_fratio(struct arizona_fll *fll,
 	/* Adjust FRATIO/refdiv to avoid integer mode if possible */
 	refdiv = cfg->refdiv;
 
+	arizona_fll_dbg(fll, "pseudo: initial ratio=%u fref=%u refdiv=%u\n",
+			init_ratio, Fref, refdiv);
+
 	while (div <= ARIZONA_FLL_MAX_REFDIV) {
 		for (ratio = init_ratio; ratio <= ARIZONA_FLL_MAX_FRATIO;
 		     ratio++) {
 			if ((ARIZONA_FLL_VCO_CORNER / 2) /
-			    (fll->vco_mult * ratio) < Fref)
+			    (fll->vco_mult * ratio) < Fref) {
+				arizona_fll_dbg(fll, "pseudo: hit VCO corner\n");
 				break;
+			}
+
+			if (Fref > pseudo_fref_max[ratio - 1]) {
+				arizona_fll_dbg(fll,
+					"pseudo: exceeded max fref(%u) for ratio=%u\n",
+					pseudo_fref_max[ratio - 1],
+					ratio);
+				break;
+			}
 
 			if (target % (ratio * Fref)) {
 				cfg->refdiv = refdiv;
 				cfg->fratio = ratio - 1;
+				arizona_fll_dbg(fll,
+					"pseudo: found fref=%u refdiv=%d(%d) ratio=%d\n",
+					Fref, refdiv, div, ratio);
 				return ratio;
 			}
 		}
@@ -2060,6 +2095,9 @@ static int arizona_calc_fratio(struct arizona_fll *fll,
 			if (target % (ratio * Fref)) {
 				cfg->refdiv = refdiv;
 				cfg->fratio = ratio - 1;
+				arizona_fll_dbg(fll,
+					"pseudo: found fref=%u refdiv=%d(%d) ratio=%d\n",
+					Fref, refdiv, div, ratio);
 				return ratio;
 			}
 		}
@@ -2068,6 +2106,9 @@ static int arizona_calc_fratio(struct arizona_fll *fll,
 		Fref /= 2;
 		refdiv++;
 		init_ratio = arizona_find_fratio(Fref, NULL);
+		arizona_fll_dbg(fll,
+				"pseudo: change fref=%u refdiv=%d(%d) ratio=%u\n",
+				Fref, refdiv, div, init_ratio);
 	}
 
 	arizona_fll_warn(fll, "Falling back to integer mode operation\n");
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index bc08f0c5a5f6..1bd31644a782 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -266,6 +266,8 @@ static int rt286_jack_detect(struct rt286_priv *rt286, bool *hp, bool *mic)
 		} else {
 			*mic = false;
 			regmap_write(rt286->regmap, RT286_SET_MIC1, 0x20);
+			regmap_update_bits(rt286->regmap,
+				RT286_CBJ_CTRL1, 0x0400, 0x0000);
 		}
 	} else {
 		regmap_read(rt286->regmap, RT286_GET_HP_SENSE, &buf);
@@ -470,24 +472,6 @@ static int rt286_set_dmic1_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
-static int rt286_vref_event(struct snd_soc_dapm_widget *w,
-			     struct snd_kcontrol *kcontrol, int event)
-{
-	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
-
-	switch (event) {
-	case SND_SOC_DAPM_PRE_PMU:
-		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0000);
-		mdelay(50);
-		break;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
 static int rt286_ldo2_event(struct snd_soc_dapm_widget *w,
 			     struct snd_kcontrol *kcontrol, int event)
 {
@@ -536,7 +520,7 @@ static const struct snd_soc_dapm_widget rt286_dapm_widgets[] = {
 	SND_SOC_DAPM_SUPPLY_S("HV", 1, RT286_POWER_CTRL1,
 		12, 1, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("VREF", RT286_POWER_CTRL1,
-		0, 1, rt286_vref_event, SND_SOC_DAPM_PRE_PMU),
+		0, 1, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("LDO1", 1, RT286_POWER_CTRL2,
 		2, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("LDO2", 2, RT286_POWER_CTRL1,
@@ -911,8 +895,6 @@ static int rt286_set_bias_level(struct snd_soc_codec *codec,
 	case SND_SOC_BIAS_ON:
 		mdelay(10);
 		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0400);
-		snd_soc_update_bits(codec,
 			RT286_DC_GAIN, 0x200, 0x0);
 
 		break;
@@ -920,8 +902,6 @@ static int rt286_set_bias_level(struct snd_soc_codec *codec,
 	case SND_SOC_BIAS_STANDBY:
 		snd_soc_write(codec,
 			RT286_SET_AUDIO_POWER, AC_PWRST_D3);
-		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0000);
 		break;
 
 	default:
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index c61d38b585fb..93e8c9017633 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -776,7 +776,7 @@ static const struct snd_kcontrol_new rt5645_snd_controls[] = {
 
 	/* IN1/IN2 Control */
 	SOC_SINGLE_TLV("IN1 Boost", RT5645_IN1_CTRL1,
-		RT5645_BST_SFT1, 8, 0, bst_tlv),
+		RT5645_BST_SFT1, 12, 0, bst_tlv),
 	SOC_SINGLE_TLV("IN2 Boost", RT5645_IN2_CTRL,
 		RT5645_BST_SFT2, 8, 0, bst_tlv),
 
diff --git a/sound/soc/codecs/rt5659.c b/sound/soc/codecs/rt5659.c
index 820d8fa62b5e..fb8ea05c0de1 100644
--- a/sound/soc/codecs/rt5659.c
+++ b/sound/soc/codecs/rt5659.c
@@ -3985,7 +3985,6 @@ static int rt5659_i2c_probe(struct i2c_client *i2c,
 	if (rt5659 == NULL)
 		return -ENOMEM;
 
-	rt5659->i2c = i2c;
 	i2c_set_clientdata(i2c, rt5659);
 
 	if (pdata)
@@ -4157,24 +4156,17 @@ static int rt5659_i2c_probe(struct i2c_client *i2c,
 
 	INIT_DELAYED_WORK(&rt5659->jack_detect_work, rt5659_jack_detect_work);
 
-	if (rt5659->i2c->irq) {
-		ret = request_threaded_irq(rt5659->i2c->irq, NULL, rt5659_irq,
-			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+	if (i2c->irq) {
+		ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL,
+			rt5659_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
 			| IRQF_ONESHOT, "rt5659", rt5659);
 		if (ret)
 			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
 
 	}
 
-	ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5659,
+	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5659,
 			rt5659_dai, ARRAY_SIZE(rt5659_dai));
-
-	if (ret) {
-		if (rt5659->i2c->irq)
-			free_irq(rt5659->i2c->irq, rt5659);
-	}
-
-	return 0;
 }
 
 static int rt5659_i2c_remove(struct i2c_client *i2c)
@@ -4191,24 +4183,29 @@ void rt5659_i2c_shutdown(struct i2c_client *client)
 	regmap_write(rt5659->regmap, RT5659_RESET, 0);
 }
 
+#ifdef CONFIG_OF
 static const struct of_device_id rt5659_of_match[] = {
 	{ .compatible = "realtek,rt5658", },
 	{ .compatible = "realtek,rt5659", },
-	{},
+	{ },
 };
+MODULE_DEVICE_TABLE(of, rt5659_of_match);
+#endif
 
+#ifdef CONFIG_ACPI
 static struct acpi_device_id rt5659_acpi_match[] = {
-		{ "10EC5658", 0},
-		{ "10EC5659", 0},
-		{ },
+	{ "10EC5658", 0, },
+	{ "10EC5659", 0, },
+	{ },
 };
 MODULE_DEVICE_TABLE(acpi, rt5659_acpi_match);
+#endif
 
 struct i2c_driver rt5659_i2c_driver = {
 	.driver = {
 		.name = "rt5659",
 		.owner = THIS_MODULE,
-		.of_match_table = rt5659_of_match,
+		.of_match_table = of_match_ptr(rt5659_of_match),
 		.acpi_match_table = ACPI_PTR(rt5659_acpi_match),
 	},
 	.probe = rt5659_i2c_probe,
diff --git a/sound/soc/codecs/rt5659.h b/sound/soc/codecs/rt5659.h
index 8f07ee903eaa..d31c9e5bcec8 100644
--- a/sound/soc/codecs/rt5659.h
+++ b/sound/soc/codecs/rt5659.h
@@ -1792,7 +1792,6 @@ struct rt5659_priv {
 	struct snd_soc_codec *codec;
 	struct rt5659_platform_data pdata;
 	struct regmap *regmap;
-	struct i2c_client *i2c;
 	struct gpio_desc *gpiod_ldo1_en;
 	struct gpio_desc *gpiod_reset;
 	struct snd_soc_jack *hs_jack;
diff --git a/sound/soc/codecs/sigmadsp-i2c.c b/sound/soc/codecs/sigmadsp-i2c.c
index 21ca3a5e9f66..d374c18d4db7 100644
--- a/sound/soc/codecs/sigmadsp-i2c.c
+++ b/sound/soc/codecs/sigmadsp-i2c.c
@@ -31,7 +31,10 @@ static int sigmadsp_write_i2c(void *control_data,
 
 	kfree(buf);
 
-	return ret;
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int sigmadsp_read_i2c(void *control_data,
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 6088d30962a9..97c0f1e23886 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -2382,6 +2382,7 @@ error:
 
 static int wm5110_remove(struct platform_device *pdev)
 {
+	snd_soc_unregister_platform(&pdev->dev);
 	snd_soc_unregister_codec(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index ff237726775a..d7f444f87460 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -240,13 +240,13 @@ SOC_DOUBLE_R("Capture Volume ZC Switch", WM8960_LINVOL, WM8960_RINVOL,
 SOC_DOUBLE_R("Capture Switch", WM8960_LINVOL, WM8960_RINVOL,
 	7, 1, 1),
 
-SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
+SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT3 Volume",
 	       WM8960_INBMIX1, 4, 7, 0, lineinboost_tlv),
-SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT2 Volume",
+SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT2 Volume",
 	       WM8960_INBMIX1, 1, 7, 0, lineinboost_tlv),
-SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT3 Volume",
+SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
 	       WM8960_INBMIX2, 4, 7, 0, lineinboost_tlv),
-SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT2 Volume",
+SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT2 Volume",
 	       WM8960_INBMIX2, 1, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT1 Volume",
 		WM8960_RINPATH, 4, 3, 0, micboost_tlv),
@@ -643,29 +643,31 @@ static int wm8960_configure_clocking(struct snd_soc_codec *codec)
 		return -EINVAL;
 	}
 
-	/* check if the sysclk frequency is available. */
-	for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
-		if (sysclk_divs[i] == -1)
-			continue;
-		sysclk = freq_out / sysclk_divs[i];
-		for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {
-			if (sysclk == dac_divs[j] * lrclk) {
+	if (wm8960->clk_id != WM8960_SYSCLK_PLL) {
+		/* check if the sysclk frequency is available. */
+		for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
+			if (sysclk_divs[i] == -1)
+				continue;
+			sysclk = freq_out / sysclk_divs[i];
+			for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {
+				if (sysclk != dac_divs[j] * lrclk)
+					continue;
 				for (k = 0; k < ARRAY_SIZE(bclk_divs); ++k)
 					if (sysclk == bclk * bclk_divs[k] / 10)
 						break;
 				if (k != ARRAY_SIZE(bclk_divs))
 					break;
 			}
+			if (j != ARRAY_SIZE(dac_divs))
+				break;
 		}
-		if (j != ARRAY_SIZE(dac_divs))
-			break;
-	}
 
-	if (i != ARRAY_SIZE(sysclk_divs)) {
-		goto configure_clock;
-	} else if (wm8960->clk_id != WM8960_SYSCLK_AUTO) {
-		dev_err(codec->dev, "failed to configure clock\n");
-		return -EINVAL;
+		if (i != ARRAY_SIZE(sysclk_divs)) {
+			goto configure_clock;
+		} else if (wm8960->clk_id != WM8960_SYSCLK_AUTO) {
+			dev_err(codec->dev, "failed to configure clock\n");
+			return -EINVAL;
+		}
 	}
 	/* get a available pll out frequency and set pll */
 	for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index ce664c239be3..bff258d7bcea 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -645,6 +645,8 @@ static int dw_i2s_probe(struct platform_device *pdev)
 
 	dev->dev = &pdev->dev;
 
+	dev->i2s_reg_comp1 = I2S_COMP_PARAM_1;
+	dev->i2s_reg_comp2 = I2S_COMP_PARAM_2;
 	if (pdata) {
 		dev->capability = pdata->cap;
 		clk_id = NULL;
@@ -652,9 +654,6 @@ static int dw_i2s_probe(struct platform_device *pdev)
 		if (dev->quirks & DW_I2S_QUIRK_COMP_REG_OFFSET) {
 			dev->i2s_reg_comp1 = pdata->i2s_reg_comp1;
 			dev->i2s_reg_comp2 = pdata->i2s_reg_comp2;
-		} else {
-			dev->i2s_reg_comp1 = I2S_COMP_PARAM_1;
-			dev->i2s_reg_comp2 = I2S_COMP_PARAM_2;
 		}
 		ret = dw_configure_dai_by_pd(dev, dw_i2s_dai, res, pdata);
 	} else {
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 40dfd8a36484..ed8de1035cda 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -112,20 +112,6 @@ struct fsl_ssi_rxtx_reg_val {
 	struct fsl_ssi_reg_val tx;
 };
 
-static const struct reg_default fsl_ssi_reg_defaults[] = {
-	{CCSR_SSI_SCR,     0x00000000},
-	{CCSR_SSI_SIER,    0x00003003},
-	{CCSR_SSI_STCR,    0x00000200},
-	{CCSR_SSI_SRCR,    0x00000200},
-	{CCSR_SSI_STCCR,   0x00040000},
-	{CCSR_SSI_SRCCR,   0x00040000},
-	{CCSR_SSI_SACNT,   0x00000000},
-	{CCSR_SSI_STMSK,   0x00000000},
-	{CCSR_SSI_SRMSK,   0x00000000},
-	{CCSR_SSI_SACCEN,  0x00000000},
-	{CCSR_SSI_SACCDIS, 0x00000000},
-};
-
 static bool fsl_ssi_readable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -190,8 +176,7 @@ static const struct regmap_config fsl_ssi_regconfig = {
 	.val_bits = 32,
 	.reg_stride = 4,
 	.val_format_endian = REGMAP_ENDIAN_NATIVE,
-	.reg_defaults = fsl_ssi_reg_defaults,
-	.num_reg_defaults = ARRAY_SIZE(fsl_ssi_reg_defaults),
+	.num_reg_defaults_raw = CCSR_SSI_SACCDIS / sizeof(uint32_t) + 1,
 	.readable_reg = fsl_ssi_readable_reg,
 	.volatile_reg = fsl_ssi_volatile_reg,
 	.precious_reg = fsl_ssi_precious_reg,
@@ -201,6 +186,7 @@ static const struct regmap_config fsl_ssi_regconfig = {
 
 struct fsl_ssi_soc_data {
 	bool imx;
+	bool imx21regs; /* imx21-class SSI - no SACC{ST,EN,DIS} regs */
 	bool offline_config;
 	u32 sisr_write_mask;
 };
@@ -303,6 +289,7 @@ static struct fsl_ssi_soc_data fsl_ssi_mpc8610 = {
 
 static struct fsl_ssi_soc_data fsl_ssi_imx21 = {
 	.imx = true,
+	.imx21regs = true,
 	.offline_config = true,
 	.sisr_write_mask = 0,
 };
@@ -586,8 +573,12 @@ static void fsl_ssi_setup_ac97(struct fsl_ssi_private *ssi_private)
 	 */
 	regmap_write(regs, CCSR_SSI_SACNT,
 			CCSR_SSI_SACNT_AC97EN | CCSR_SSI_SACNT_FV);
-	regmap_write(regs, CCSR_SSI_SACCDIS, 0xff);
-	regmap_write(regs, CCSR_SSI_SACCEN, 0x300);
+
+	/* no SACC{ST,EN,DIS} regs on imx21-class SSI */
+	if (!ssi_private->soc->imx21regs) {
+		regmap_write(regs, CCSR_SSI_SACCDIS, 0xff);
+		regmap_write(regs, CCSR_SSI_SACCEN, 0x300);
+	}
 
 	/*
 	 * Enable SSI, Transmit and Receive. AC97 has to communicate with the
@@ -1397,6 +1388,7 @@ static int fsl_ssi_probe(struct platform_device *pdev)
 	struct resource *res;
 	void __iomem *iomem;
 	char name[64];
+	struct regmap_config regconfig = fsl_ssi_regconfig;
 
 	of_id = of_match_device(fsl_ssi_ids, &pdev->dev);
 	if (!of_id || !of_id->data)
@@ -1444,15 +1436,25 @@ static int fsl_ssi_probe(struct platform_device *pdev)
 		return PTR_ERR(iomem);
 	ssi_private->ssi_phys = res->start;
 
+	if (ssi_private->soc->imx21regs) {
+		/*
+		 * According to datasheet imx21-class SSI
+		 * don't have SACC{ST,EN,DIS} regs.
+		 */
+		regconfig.max_register = CCSR_SSI_SRMSK;
+		regconfig.num_reg_defaults_raw =
+			CCSR_SSI_SRMSK / sizeof(uint32_t) + 1;
+	}
+
 	ret = of_property_match_string(np, "clock-names", "ipg");
 	if (ret < 0) {
 		ssi_private->has_ipg_clk_name = false;
 		ssi_private->regs = devm_regmap_init_mmio(&pdev->dev, iomem,
-			&fsl_ssi_regconfig);
+			&regconfig);
 	} else {
 		ssi_private->has_ipg_clk_name = true;
 		ssi_private->regs = devm_regmap_init_mmio_clk(&pdev->dev,
-			"ipg", iomem, &fsl_ssi_regconfig);
+			"ipg", iomem, &regconfig);
 	}
 	if (IS_ERR(ssi_private->regs)) {
 		dev_err(&pdev->dev, "Failed to init register map\n");
diff --git a/sound/soc/fsl/imx-spdif.c b/sound/soc/fsl/imx-spdif.c
index a407e833c612..fb896b2c9ba3 100644
--- a/sound/soc/fsl/imx-spdif.c
+++ b/sound/soc/fsl/imx-spdif.c
@@ -72,8 +72,6 @@ static int imx_spdif_audio_probe(struct platform_device *pdev)
 		goto end;
 	}
 
-	platform_set_drvdata(pdev, data);
-
 end:
 	of_node_put(spdif_np);
 
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 1ded8811598e..2389ab47e25f 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -99,7 +99,7 @@ static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 		if (ret && ret != -ENOTSUPP)
 			goto err;
 	}
-
+	return 0;
 err:
 	return ret;
 }
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 803f95e40679..7d7c872c280d 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -30,11 +30,15 @@ config SND_SST_IPC_ACPI
 config SND_SOC_INTEL_SST
 	tristate
 	select SND_SOC_INTEL_SST_ACPI if ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	depends on (X86 || COMPILE_TEST)
 
 config SND_SOC_INTEL_SST_ACPI
 	tristate
 
+config SND_SOC_INTEL_SST_MATCH
+	tristate
+
 config SND_SOC_INTEL_HASWELL
 	tristate
 
@@ -57,7 +61,7 @@ config SND_SOC_INTEL_HASWELL_MACH
 config SND_SOC_INTEL_BYT_RT5640_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with RT5640 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y && (SND_SOC_INTEL_BYTCR_RT5640_MACH = n)
+	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_RT5640
@@ -69,7 +73,7 @@ config SND_SOC_INTEL_BYT_RT5640_MACH
 config SND_SOC_INTEL_BYT_MAX98090_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with MAX98090 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y
+	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_MAX98090
@@ -97,6 +101,7 @@ config SND_SOC_INTEL_BYTCR_RT5640_MACH
 	select SND_SOC_RT5640
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5640 audio codec.
@@ -109,6 +114,7 @@ config SND_SOC_INTEL_BYTCR_RT5651_MACH
 	select SND_SOC_RT5651
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5651 audio codec.
@@ -121,6 +127,7 @@ config SND_SOC_INTEL_CHT_BSW_RT5672_MACH
         select SND_SOC_RT5670
         select SND_SST_MFLD_PLATFORM
         select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
         help
           This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
           platforms with RT5672 audio codec.
@@ -133,6 +140,7 @@ config SND_SOC_INTEL_CHT_BSW_RT5645_MACH
 	select SND_SOC_RT5645
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
 	  This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
 	  platforms with RT5645/5650 audio codec.
@@ -145,6 +153,7 @@ config SND_SOC_INTEL_CHT_BSW_MAX98090_TI_MACH
 	select SND_SOC_TS3A227E
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
       This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
       platforms with MAX98090 audio codec it also can support TI jack chip as aux device.
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 55c33dc76ce4..52ed434cbca6 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -528,6 +528,7 @@ static struct snd_soc_dai_driver sst_platform_dai[] = {
 	.ops = &sst_compr_dai_ops,
 	.playback = {
 		.stream_name = "Compress Playback",
+		.channels_min = 1,
 	},
 },
 /* BE CPU  Dais */
diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c
index 7396ddb427d8..2cbcbe412661 100644
--- a/sound/soc/intel/boards/skl_rt286.c
+++ b/sound/soc/intel/boards/skl_rt286.c
@@ -212,7 +212,10 @@ static int skylake_dmic_fixup(struct snd_soc_pcm_runtime *rtd,
 {
 	struct snd_interval *channels = hw_param_interval(params,
 						SNDRV_PCM_HW_PARAM_CHANNELS);
-	channels->min = channels->max = 4;
+	if (params_channels(params) == 2)
+		channels->min = channels->max = 2;
+	else
+		channels->min = channels->max = 4;
 
 	return 0;
 }
diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile
index 668fdeee195e..fbbb25c2ceed 100644
--- a/sound/soc/intel/common/Makefile
+++ b/sound/soc/intel/common/Makefile
@@ -1,13 +1,10 @@
 snd-soc-sst-dsp-objs := sst-dsp.o
-ifneq ($(CONFIG_SND_SST_IPC_ACPI),)
-snd-soc-sst-acpi-objs := sst-match-acpi.o
-else
-snd-soc-sst-acpi-objs := sst-acpi.o sst-match-acpi.o
-endif
-
+snd-soc-sst-acpi-objs := sst-acpi.o
+snd-soc-sst-match-objs := sst-match-acpi.o
 snd-soc-sst-ipc-objs := sst-ipc.o
 
 snd-soc-sst-dsp-$(CONFIG_DW_DMAC_CORE) += sst-firmware.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o
 obj-$(CONFIG_SND_SOC_INTEL_SST_ACPI) += snd-soc-sst-acpi.o
+obj-$(CONFIG_SND_SOC_INTEL_SST_MATCH) += snd-soc-sst-match.o
diff --git a/sound/soc/intel/common/sst-acpi.c b/sound/soc/intel/common/sst-acpi.c
index 7a85c576dad3..2c5eda14d510 100644
--- a/sound/soc/intel/common/sst-acpi.c
+++ b/sound/soc/intel/common/sst-acpi.c
@@ -215,6 +215,7 @@ static struct sst_acpi_desc sst_acpi_broadwell_desc = {
 	.dma_size = SST_LPT_DSP_DMA_SIZE,
 };
 
+#if !IS_ENABLED(CONFIG_SND_SST_IPC_ACPI)
 static struct sst_acpi_mach baytrail_machines[] = {
 	{ "10EC5640", "byt-rt5640", "intel/fw_sst_0f28.bin-48kHz_i2s_master", NULL, NULL, NULL },
 	{ "193C9890", "byt-max98090", "intel/fw_sst_0f28.bin-48kHz_i2s_master", NULL, NULL, NULL },
@@ -231,11 +232,14 @@ static struct sst_acpi_desc sst_acpi_baytrail_desc = {
 	.sst_id = SST_DEV_ID_BYT,
 	.resindex_dma_base = -1,
 };
+#endif
 
 static const struct acpi_device_id sst_acpi_match[] = {
 	{ "INT33C8", (unsigned long)&sst_acpi_haswell_desc },
 	{ "INT3438", (unsigned long)&sst_acpi_broadwell_desc },
+#if !IS_ENABLED(CONFIG_SND_SST_IPC_ACPI)
 	{ "80860F28", (unsigned long)&sst_acpi_baytrail_desc },
+#endif
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, sst_acpi_match);
diff --git a/sound/soc/intel/common/sst-match-acpi.c b/sound/soc/intel/common/sst-match-acpi.c
index dd077e116d25..3b4539d21492 100644
--- a/sound/soc/intel/common/sst-match-acpi.c
+++ b/sound/soc/intel/common/sst-match-acpi.c
@@ -41,3 +41,6 @@ struct sst_acpi_mach *sst_acpi_find_machine(struct sst_acpi_mach *machines)
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(sst_acpi_find_machine);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index de6dac496a0d..4629372d7c8e 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -688,14 +688,14 @@ int skl_unbind_modules(struct skl_sst *ctx,
 	/* get src queue index */
 	src_index = skl_get_queue_index(src_mcfg->m_out_pin, dst_id, out_max);
 	if (src_index < 0)
-		return -EINVAL;
+		return 0;
 
 	msg.src_queue = src_index;
 
 	/* get dst queue index */
 	dst_index  = skl_get_queue_index(dst_mcfg->m_in_pin, src_id, in_max);
 	if (dst_index < 0)
-		return -EINVAL;
+		return 0;
 
 	msg.dst_queue = dst_index;
 
@@ -747,7 +747,7 @@ int skl_bind_modules(struct skl_sst *ctx,
 
 	skl_dump_bind_info(ctx, src_mcfg, dst_mcfg);
 
-	if (src_mcfg->m_state < SKL_MODULE_INIT_DONE &&
+	if (src_mcfg->m_state < SKL_MODULE_INIT_DONE ||
 		dst_mcfg->m_state < SKL_MODULE_INIT_DONE)
 		return 0;
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index f3553258091a..b6e6b61d10ec 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -863,6 +863,7 @@ static int skl_get_delay_from_lpib(struct hdac_ext_bus *ebus,
 		else
 			delay += hstream->bufsize;
 	}
+	delay = (hstream->bufsize == delay) ? 0 : delay;
 
 	if (delay >= hstream->period_bytes) {
 		dev_info(bus->dev,
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index 4624556f486d..a294fee431f0 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -54,12 +54,9 @@ static int is_skl_dsp_widget_type(struct snd_soc_dapm_widget *w)
 
 /*
  * Each pipelines needs memory to be allocated. Check if we have free memory
- * from available pool. Then only add this to pool
- * This is freed when pipe is deleted
- * Note: DSP does actual memory management we only keep track for complete
- * pool
+ * from available pool.
  */
-static bool skl_tplg_alloc_pipe_mem(struct skl *skl,
+static bool skl_is_pipe_mem_avail(struct skl *skl,
 				struct skl_module_cfg *mconfig)
 {
 	struct skl_sst *ctx = skl->skl_sst;
@@ -74,10 +71,20 @@ static bool skl_tplg_alloc_pipe_mem(struct skl *skl,
 				"exceeds ppl memory available %d mem %d\n",
 				skl->resource.max_mem, skl->resource.mem);
 		return false;
+	} else {
+		return true;
 	}
+}
 
+/*
+ * Add the mem to the mem pool. This is freed when pipe is deleted.
+ * Note: DSP does actual memory management we only keep track for complete
+ * pool
+ */
+static void skl_tplg_alloc_pipe_mem(struct skl *skl,
+				struct skl_module_cfg *mconfig)
+{
 	skl->resource.mem += mconfig->pipe->memory_pages;
-	return true;
 }
 
 /*
@@ -85,10 +92,10 @@ static bool skl_tplg_alloc_pipe_mem(struct skl *skl,
  * quantified in MCPS (Million Clocks Per Second) required for module/pipe
  *
  * Each pipelines needs mcps to be allocated. Check if we have mcps for this
- * pipe. This adds the mcps to driver counter
- * This is removed on pipeline delete
+ * pipe.
  */
-static bool skl_tplg_alloc_pipe_mcps(struct skl *skl,
+
+static bool skl_is_pipe_mcps_avail(struct skl *skl,
 				struct skl_module_cfg *mconfig)
 {
 	struct skl_sst *ctx = skl->skl_sst;
@@ -98,13 +105,18 @@ static bool skl_tplg_alloc_pipe_mcps(struct skl *skl,
 			"%s: module_id %d instance %d\n", __func__,
 			mconfig->id.module_id, mconfig->id.instance_id);
 		dev_err(ctx->dev,
-			"exceeds ppl memory available %d > mem %d\n",
+			"exceeds ppl mcps available %d > mem %d\n",
 			skl->resource.max_mcps, skl->resource.mcps);
 		return false;
+	} else {
+		return true;
 	}
+}
 
+static void skl_tplg_alloc_pipe_mcps(struct skl *skl,
+				struct skl_module_cfg *mconfig)
+{
 	skl->resource.mcps += mconfig->mcps;
-	return true;
 }
 
 /*
@@ -411,7 +423,7 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe)
 		mconfig = w->priv;
 
 		/* check resource available */
-		if (!skl_tplg_alloc_pipe_mcps(skl, mconfig))
+		if (!skl_is_pipe_mcps_avail(skl, mconfig))
 			return -ENOMEM;
 
 		if (mconfig->is_loadable && ctx->dsp->fw_ops.load_mod) {
@@ -435,6 +447,7 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe)
 		ret = skl_tplg_set_module_params(w, ctx);
 		if (ret < 0)
 			return ret;
+		skl_tplg_alloc_pipe_mcps(skl, mconfig);
 	}
 
 	return 0;
@@ -477,10 +490,10 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 	struct skl_sst *ctx = skl->skl_sst;
 
 	/* check resource available */
-	if (!skl_tplg_alloc_pipe_mcps(skl, mconfig))
+	if (!skl_is_pipe_mcps_avail(skl, mconfig))
 		return -EBUSY;
 
-	if (!skl_tplg_alloc_pipe_mem(skl, mconfig))
+	if (!skl_is_pipe_mem_avail(skl, mconfig))
 		return -ENOMEM;
 
 	/*
@@ -526,11 +539,15 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 		src_module = dst_module;
 	}
 
+	skl_tplg_alloc_pipe_mem(skl, mconfig);
+	skl_tplg_alloc_pipe_mcps(skl, mconfig);
+
 	return 0;
 }
 
 static int skl_tplg_bind_sinks(struct snd_soc_dapm_widget *w,
 				struct skl *skl,
+				struct snd_soc_dapm_widget *src_w,
 				struct skl_module_cfg *src_mconfig)
 {
 	struct snd_soc_dapm_path *p;
@@ -547,6 +564,10 @@ static int skl_tplg_bind_sinks(struct snd_soc_dapm_widget *w,
 		dev_dbg(ctx->dev, "%s: sink widget=%s\n", __func__, p->sink->name);
 
 		next_sink = p->sink;
+
+		if (!is_skl_dsp_widget_type(p->sink))
+			return skl_tplg_bind_sinks(p->sink, skl, src_w, src_mconfig);
+
 		/*
 		 * here we will check widgets in sink pipelines, so that
 		 * can be any widgets type and we are only interested if
@@ -576,7 +597,7 @@ static int skl_tplg_bind_sinks(struct snd_soc_dapm_widget *w,
 	}
 
 	if (!sink)
-		return skl_tplg_bind_sinks(next_sink, skl, src_mconfig);
+		return skl_tplg_bind_sinks(next_sink, skl, src_w, src_mconfig);
 
 	return 0;
 }
@@ -605,7 +626,7 @@ static int skl_tplg_pga_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 	 * if sink is not started, start sink pipe first, then start
 	 * this pipe
 	 */
-	ret = skl_tplg_bind_sinks(w, skl, src_mconfig);
+	ret = skl_tplg_bind_sinks(w, skl, w, src_mconfig);
 	if (ret)
 		return ret;
 
@@ -773,10 +794,7 @@ static int skl_tplg_mixer_dapm_post_pmd_event(struct snd_soc_dapm_widget *w,
 			continue;
 		}
 
-		ret = skl_unbind_modules(ctx, src_module, dst_module);
-		if (ret < 0)
-			return ret;
-
+		skl_unbind_modules(ctx, src_module, dst_module);
 		src_module = dst_module;
 	}
 
@@ -814,9 +832,6 @@ static int skl_tplg_pga_dapm_post_pmd_event(struct snd_soc_dapm_widget *w,
 			 * This is a connecter and if path is found that means
 			 * unbind between source and sink has not happened yet
 			 */
-			ret = skl_stop_pipe(ctx, sink_mconfig->pipe);
-			if (ret < 0)
-				return ret;
 			ret = skl_unbind_modules(ctx, src_mconfig,
 							sink_mconfig);
 		}
@@ -842,6 +857,12 @@ static int skl_tplg_vmixer_event(struct snd_soc_dapm_widget *w,
 	case SND_SOC_DAPM_PRE_PMU:
 		return skl_tplg_mixer_dapm_pre_pmu_event(w, skl);
 
+	case SND_SOC_DAPM_POST_PMU:
+		return skl_tplg_mixer_dapm_post_pmu_event(w, skl);
+
+	case SND_SOC_DAPM_PRE_PMD:
+		return skl_tplg_mixer_dapm_pre_pmd_event(w, skl);
+
 	case SND_SOC_DAPM_POST_PMD:
 		return skl_tplg_mixer_dapm_post_pmd_event(w, skl);
 	}
@@ -916,6 +937,13 @@ static int skl_tplg_tlv_control_get(struct snd_kcontrol *kcontrol,
 		skl_get_module_params(skl->skl_sst, (u32 *)bc->params,
 				      bc->max, bc->param_id, mconfig);
 
+	/* decrement size for TLV header */
+	size -= 2 * sizeof(u32);
+
+	/* check size as we don't want to send kernel data */
+	if (size > bc->max)
+		size = bc->max;
+
 	if (bc->params) {
 		if (copy_to_user(data, &bc->param_id, sizeof(u32)))
 			return -EFAULT;
@@ -1510,6 +1538,7 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus)
 					&skl_tplg_ops, fw, 0);
 	if (ret < 0) {
 		dev_err(bus->dev, "tplg component load failed%d\n", ret);
+		release_firmware(fw);
 		return -EINVAL;
 	}
 
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 443a15de94b5..092705e73db4 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -614,8 +614,6 @@ static int skl_probe(struct pci_dev *pci,
 		goto out_unregister;
 
 	/*configure PM */
-	pm_runtime_set_autosuspend_delay(bus->dev, SKL_SUSPEND_DELAY);
-	pm_runtime_use_autosuspend(bus->dev);
 	pm_runtime_put_noidle(bus->dev);
 	pm_runtime_allow(bus->dev);
 
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 15c04e2eae34..976967675387 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -9,7 +9,7 @@ config SND_SOC_MEDIATEK
 
 config SND_SOC_MT8173_MAX98090
 	tristate "ASoC Audio driver for MT8173 with MAX98090 codec"
-	depends on SND_SOC_MEDIATEK
+	depends on SND_SOC_MEDIATEK && I2C
 	select SND_SOC_MAX98090
 	help
 	  This adds ASoC driver for Mediatek MT8173 boards
@@ -19,7 +19,7 @@ config SND_SOC_MT8173_MAX98090
 
 config SND_SOC_MT8173_RT5650_RT5676
 	tristate "ASoC Audio driver for MT8173 with RT5650 RT5676 codecs"
-	depends on SND_SOC_MEDIATEK
+	depends on SND_SOC_MEDIATEK && I2C
 	select SND_SOC_RT5645
 	select SND_SOC_RT5677
 	help
diff --git a/sound/soc/mxs/mxs-saif.c b/sound/soc/mxs/mxs-saif.c
index c866ade28ad0..a6c7b8d87cd2 100644
--- a/sound/soc/mxs/mxs-saif.c
+++ b/sound/soc/mxs/mxs-saif.c
@@ -381,9 +381,19 @@ static int mxs_saif_startup(struct snd_pcm_substream *substream,
 	__raw_writel(BM_SAIF_CTRL_CLKGATE,
 		saif->base + SAIF_CTRL + MXS_CLR_ADDR);
 
+	clk_prepare(saif->clk);
+
 	return 0;
 }
 
+static void mxs_saif_shutdown(struct snd_pcm_substream *substream,
+			      struct snd_soc_dai *cpu_dai)
+{
+	struct mxs_saif *saif = snd_soc_dai_get_drvdata(cpu_dai);
+
+	clk_unprepare(saif->clk);
+}
+
 /*
  * Should only be called when port is inactive.
  * although can be called multiple times by upper layers.
@@ -424,8 +434,6 @@ static int mxs_saif_hw_params(struct snd_pcm_substream *substream,
 		return ret;
 	}
 
-	/* prepare clk in hw_param, enable in trigger */
-	clk_prepare(saif->clk);
 	if (saif != master_saif) {
 		/*
 		* Set an initial clock rate for the saif internal logic to work
@@ -611,6 +619,7 @@ static int mxs_saif_trigger(struct snd_pcm_substream *substream, int cmd,
 
 static const struct snd_soc_dai_ops mxs_saif_dai_ops = {
 	.startup = mxs_saif_startup,
+	.shutdown = mxs_saif_shutdown,
 	.trigger = mxs_saif_trigger,
 	.prepare = mxs_saif_prepare,
 	.hw_params = mxs_saif_hw_params,
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 79688aa1941a..4aeb8e1a7160 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -440,18 +440,18 @@ static irqreturn_t lpass_platform_lpaif_irq(int irq, void *data)
 }
 
 static int lpass_platform_alloc_buffer(struct snd_pcm_substream *substream,
-		struct snd_soc_pcm_runtime *soc_runtime)
+		struct snd_soc_pcm_runtime *rt)
 {
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
 	size_t size = lpass_platform_pcm_hardware.buffer_bytes_max;
 
 	buf->dev.type = SNDRV_DMA_TYPE_DEV;
-	buf->dev.dev = soc_runtime->dev;
+	buf->dev.dev = rt->platform->dev;
 	buf->private_data = NULL;
-	buf->area = dma_alloc_coherent(soc_runtime->dev, size, &buf->addr,
+	buf->area = dma_alloc_coherent(rt->platform->dev, size, &buf->addr,
 			GFP_KERNEL);
 	if (!buf->area) {
-		dev_err(soc_runtime->dev, "%s: Could not allocate DMA buffer\n",
+		dev_err(rt->platform->dev, "%s: Could not allocate DMA buffer\n",
 				__func__);
 		return -ENOMEM;
 	}
@@ -461,12 +461,12 @@ static int lpass_platform_alloc_buffer(struct snd_pcm_substream *substream,
 }
 
 static void lpass_platform_free_buffer(struct snd_pcm_substream *substream,
-		struct snd_soc_pcm_runtime *soc_runtime)
+		struct snd_soc_pcm_runtime *rt)
 {
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
 
 	if (buf->area) {
-		dma_free_coherent(soc_runtime->dev, buf->bytes, buf->area,
+		dma_free_coherent(rt->dev, buf->bytes, buf->area,
 				buf->addr);
 	}
 	buf->area = NULL;
@@ -499,9 +499,6 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
 
 	snd_soc_pcm_set_drvdata(soc_runtime, data);
 
-	soc_runtime->dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	soc_runtime->dev->dma_mask = &soc_runtime->dev->coherent_dma_mask;
-
 	ret = lpass_platform_alloc_buffer(substream, soc_runtime);
 	if (ret)
 		return ret;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 5a2812fa8946..0d3707987900 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -310,7 +310,7 @@ struct dapm_kcontrol_data {
 };
 
 static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
-	struct snd_kcontrol *kcontrol)
+	struct snd_kcontrol *kcontrol, const char *ctrl_name)
 {
 	struct dapm_kcontrol_data *data;
 	struct soc_mixer_control *mc;
@@ -333,7 +333,7 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 		if (mc->autodisable) {
 			struct snd_soc_dapm_widget template;
 
-			name = kasprintf(GFP_KERNEL, "%s %s", kcontrol->id.name,
+			name = kasprintf(GFP_KERNEL, "%s %s", ctrl_name,
 					 "Autodisable");
 			if (!name) {
 				ret = -ENOMEM;
@@ -371,7 +371,7 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 		if (e->autodisable) {
 			struct snd_soc_dapm_widget template;
 
-			name = kasprintf(GFP_KERNEL, "%s %s", kcontrol->id.name,
+			name = kasprintf(GFP_KERNEL, "%s %s", ctrl_name,
 					 "Autodisable");
 			if (!name) {
 				ret = -ENOMEM;
@@ -871,7 +871,7 @@ static int dapm_create_or_share_kcontrol(struct snd_soc_dapm_widget *w,
 
 		kcontrol->private_free = dapm_kcontrol_free;
 
-		ret = dapm_kcontrol_data_alloc(w, kcontrol);
+		ret = dapm_kcontrol_data_alloc(w, kcontrol, name);
 		if (ret) {
 			snd_ctl_free_one(kcontrol);
 			goto exit_free;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index e898b427be7e..1af4f23697a7 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1810,7 +1810,8 @@ int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream)
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_FREE) &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED) &&
-		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP))
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND))
 			continue;
 
 		dev_dbg(be->dev, "ASoC: hw_free BE %s\n",
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index cc39f63299ef..007cf5831121 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -2455,7 +2455,6 @@ int snd_usbmidi_create(struct snd_card *card,
 	else
 		err = snd_usbmidi_create_endpoints(umidi, endpoints);
 	if (err < 0) {
-		snd_usbmidi_free(umidi);
 		return err;
 	}
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 81a2eb77ba7f..05d815851be1 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2068,6 +2068,15 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 		err = -ENOMEM;
 		goto err_free_queues;
 	}
+
+	/*
+	 * Since this thread will not be kept in any rbtree not in a
+	 * list, initialize its list node so that at thread__put() the
+	 * current thread lifetime assuption is kept and we don't segfault
+	 * at list_del_init().
+	 */
+	INIT_LIST_HEAD(&pt->unknown_thread->node);
+
 	err = thread__set_comm(pt->unknown_thread, "unknown", 0);
 	if (err)
 		goto err_delete_thread;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4f7b0efdde2f..813d9b272c81 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -399,6 +399,9 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 {
 	char help[BUFSIZ];
 
+	if (!e)
+		return;
+
 	/*
 	 * We get error directly from syscall errno ( > 0),
 	 * or from encoded pointer's error ( < 0).
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2be10fb27172..4ce5c5e18f48 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -686,8 +686,9 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 		pf->fb_ops = NULL;
 #if _ELFUTILS_PREREQ(0, 142)
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
-		   pf->cfi != NULL) {
-		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
+		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
+		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
+		     (dwarf_cfi_addrframe(pf->cfi_dbg, pf->addr, &frame) != 0)) ||
 		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
 			pr_warning("Failed to get call frame on 0x%jx\n",
 				   (uintmax_t)pf->addr);
@@ -1015,8 +1016,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
 	return DWARF_CB_OK;
 }
 
-/* Find probe points from debuginfo */
-static int debuginfo__find_probes(struct debuginfo *dbg,
+static int debuginfo__find_probe_location(struct debuginfo *dbg,
 				  struct probe_finder *pf)
 {
 	struct perf_probe_point *pp = &pf->pev->point;
@@ -1025,27 +1025,6 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	Dwarf_Die *diep;
 	int ret = 0;
 
-#if _ELFUTILS_PREREQ(0, 142)
-	Elf *elf;
-	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
-
-	/* Get the call frame information from this dwarf */
-	elf = dwarf_getelf(dbg->dbg);
-	if (elf == NULL)
-		return -EINVAL;
-
-	if (gelf_getehdr(elf, &ehdr) == NULL)
-		return -EINVAL;
-
-	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
-	    shdr.sh_type == SHT_PROGBITS) {
-		pf->cfi = dwarf_getcfi_elf(elf);
-	} else {
-		pf->cfi = dwarf_getcfi(dbg->dbg);
-	}
-#endif
-
 	off = 0;
 	pf->lcache = intlist__new(NULL);
 	if (!pf->lcache)
@@ -1108,6 +1087,39 @@ found:
 	return ret;
 }
 
+/* Find probe points from debuginfo */
+static int debuginfo__find_probes(struct debuginfo *dbg,
+				  struct probe_finder *pf)
+{
+	int ret = 0;
+
+#if _ELFUTILS_PREREQ(0, 142)
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+
+	if (pf->cfi_eh || pf->cfi_dbg)
+		return debuginfo__find_probe_location(dbg, pf);
+
+	/* Get the call frame information from this dwarf */
+	elf = dwarf_getelf(dbg->dbg);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		return -EINVAL;
+
+	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+	    shdr.sh_type == SHT_PROGBITS)
+		pf->cfi_eh = dwarf_getcfi_elf(elf);
+
+	pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+#endif
+
+	ret = debuginfo__find_probe_location(dbg, pf);
+	return ret;
+}
+
 struct local_vars_finder {
 	struct probe_finder *pf;
 	struct perf_probe_arg *args;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index bed82716e1b4..0aec7704e395 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -76,7 +76,10 @@ struct probe_finder {
 
 	/* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
-	Dwarf_CFI		*cfi;		/* Call Frame Information */
+	/* Call Frame Information from .eh_frame */
+	Dwarf_CFI		*cfi_eh;
+	/* Call Frame Information from .debug_frame */
+	Dwarf_CFI		*cfi_dbg;
 #endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
 	struct perf_probe_arg	*pvar;		/* Current target variable */
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2b58edccd56f..afb0c45eba34 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -311,6 +311,16 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 
 	aggr->val = aggr->ena = aggr->run = 0;
 
+	/*
+	 * We calculate counter's data every interval,
+	 * and the display code shows ps->res_stats
+	 * avg value. We need to zero the stats for
+	 * interval mode, otherwise overall avg running
+	 * averages will be shown for each interval.
+	 */
+	if (config->interval)
+		init_stats(ps->res_stats);
+
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 90bd2ea41032..b3281dcd4a5d 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -217,13 +217,16 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd,
 	return rc;
 }
 
+#define NFIT_TEST_ARS_RECORDS 4
+
 static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd,
 		unsigned int buf_len)
 {
 	if (buf_len < sizeof(*nd_cmd))
 		return -EINVAL;
 
-	nd_cmd->max_ars_out = 256;
+	nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status)
+		+ NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record);
 	nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16;
 
 	return 0;
@@ -246,7 +249,8 @@ static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd,
 	if (buf_len < sizeof(*nd_cmd))
 		return -EINVAL;
 
-	nd_cmd->out_length = 256;
+	nd_cmd->out_length = sizeof(struct nd_cmd_ars_status);
+	/* TODO: emit error records */
 	nd_cmd->num_records = 0;
 	nd_cmd->address = 0;
 	nd_cmd->length = -1ULL;
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index 77edcdcc016b..057278448515 100755
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -88,7 +88,11 @@ test_delete()
 		exit 1
 	fi
 
-	rm $file
+	rm $file 2>/dev/null
+	if [ $? -ne 0 ]; then
+		chattr -i $file
+		rm $file
+	fi
 
 	if [ -e $file ]; then
 		echo "$file couldn't be deleted" >&2
@@ -111,6 +115,7 @@ test_zero_size_delete()
 		exit 1
 	fi
 
+	chattr -i $file
 	printf "$attrs" > $file
 
 	if [ -e $file ]; then
@@ -141,7 +146,11 @@ test_valid_filenames()
 			echo "$file could not be created" >&2
 			ret=1
 		else
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 		fi
 	done
 
@@ -174,7 +183,11 @@ test_invalid_filenames()
 
 		if [ -e $file ]; then
 			echo "Creating $file should have failed" >&2
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 			ret=1
 		fi
 	done
diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c
index 8c0764407b3c..4af74f733036 100644
--- a/tools/testing/selftests/efivarfs/open-unlink.c
+++ b/tools/testing/selftests/efivarfs/open-unlink.c
@@ -1,10 +1,68 @@
+#include <errno.h>
 #include <stdio.h>
 #include <stdint.h>
 #include <stdlib.h>
 #include <unistd.h>
+#include <sys/ioctl.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <linux/fs.h>
+
+static int set_immutable(const char *path, int immutable)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+
+	if (immutable)
+		flags |= FS_IMMUTABLE_FL;
+	else
+		flags &= ~FS_IMMUTABLE_FL;
+
+	rc = ioctl(fd, FS_IOC_SETFLAGS, &flags);
+	error = errno;
+	close(fd);
+	errno = error;
+	return rc;
+}
+
+static int get_immutable(const char *path)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+	close(fd);
+	if (flags & FS_IMMUTABLE_FL)
+		return 1;
+	return 0;
+}
 
 int main(int argc, char **argv)
 {
@@ -27,7 +85,7 @@ int main(int argc, char **argv)
 	buf[4] = 0;
 
 	/* create a test variable */
-	fd = open(path, O_WRONLY | O_CREAT);
+	fd = open(path, O_WRONLY | O_CREAT, 0600);
 	if (fd < 0) {
 		perror("open(O_WRONLY)");
 		return EXIT_FAILURE;
@@ -41,6 +99,18 @@ int main(int argc, char **argv)
 
 	close(fd);
 
+	rc = get_immutable(path);
+	if (rc < 0) {
+		perror("ioctl(FS_IOC_GETFLAGS)");
+		return EXIT_FAILURE;
+	} else if (rc) {
+		rc = set_immutable(path, 0);
+		if (rc < 0) {
+			perror("ioctl(FS_IOC_SETFLAGS)");
+			return EXIT_FAILURE;
+		}
+	}
+
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
 		perror("open");
diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance.tc b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
index 773e276ff90b..1e1abe0ad354 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
@@ -39,28 +39,23 @@ instance_slam() {
 }
 
 instance_slam &
-x=`jobs -l`
-p1=`echo $x | cut -d' ' -f2`
+p1=$!
 echo $p1
 
 instance_slam &
-x=`jobs -l | tail -1`
-p2=`echo $x | cut -d' ' -f2`
+p2=$!
 echo $p2
 
 instance_slam &
-x=`jobs -l | tail -1`
-p3=`echo $x | cut -d' ' -f2`
+p3=$!
 echo $p3
 
 instance_slam &
-x=`jobs -l | tail -1`
-p4=`echo $x | cut -d' ' -f2`
+p4=$!
 echo $p4
 
 instance_slam &
-x=`jobs -l | tail -1`
-p5=`echo $x | cut -d' ' -f2`
+p5=$!
 echo $p5
 
 ls -lR >/dev/null
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 69bca185c471..a9ad4fe3f68f 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -34,6 +34,11 @@ static struct timecounter *timecounter;
 static struct workqueue_struct *wqueue;
 static unsigned int host_vtimer_irq;
 
+void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.timer_cpu.active_cleared_last = false;
+}
+
 static cycle_t kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
@@ -130,6 +135,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
 
 	BUG_ON(!vgic_initialized(vcpu->kvm));
 
+	timer->active_cleared_last = false;
 	timer->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq,
 				   timer->irq.level);
@@ -143,7 +149,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
  * Check if there was a change in the timer state (should we raise or lower
  * the line level to the GIC).
  */
-static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
+static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 
@@ -154,10 +160,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
 	 * until we call this function from kvm_timer_flush_hwstate.
 	 */
 	if (!vgic_initialized(vcpu->kvm))
-	    return;
+		return -ENODEV;
 
 	if (kvm_timer_should_fire(vcpu) != timer->irq.level)
 		kvm_timer_update_irq(vcpu, !timer->irq.level);
+
+	return 0;
 }
 
 /*
@@ -218,7 +226,8 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	bool phys_active;
 	int ret;
 
-	kvm_timer_update_state(vcpu);
+	if (kvm_timer_update_state(vcpu))
+		return;
 
 	/*
 	* If we enter the guest with the virtual input level to the VGIC
@@ -242,10 +251,35 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	else
 		phys_active = false;
 
+	/*
+	 * We want to avoid hitting the (re)distributor as much as
+	 * possible, as this is a potentially expensive MMIO access
+	 * (not to mention locks in the irq layer), and a solution for
+	 * this is to cache the "active" state in memory.
+	 *
+	 * Things to consider: we cannot cache an "active set" state,
+	 * because the HW can change this behind our back (it becomes
+	 * "clear" in the HW). We must then restrict the caching to
+	 * the "clear" state.
+	 *
+	 * The cache is invalidated on:
+	 * - vcpu put, indicating that the HW cannot be trusted to be
+	 *   in a sane state on the next vcpu load,
+	 * - any change in the interrupt state
+	 *
+	 * Usage conditions:
+	 * - cached value is "active clear"
+	 * - value to be programmed is "active clear"
+	 */
+	if (timer->active_cleared_last && !phys_active)
+		return;
+
 	ret = irq_set_irqchip_state(timer->map->irq,
 				    IRQCHIP_STATE_ACTIVE,
 				    phys_active);
 	WARN_ON(ret);
+
+	timer->active_cleared_last = !phys_active;
 }
 
 /**
diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/virt/kvm/arm/hyp/timer-sr.c
index 1051e5d7320f..ea00d69e7078 100644
--- a/arch/arm64/kvm/hyp/timer-sr.c
+++ b/virt/kvm/arm/hyp/timer-sr.c
@@ -19,9 +19,7 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 /* vcpu is already in the HYP VA space */
 void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
@@ -31,12 +29,12 @@ void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
 	u64 val;
 
 	if (kvm->arch.timer.enabled) {
-		timer->cntv_ctl = read_sysreg(cntv_ctl_el0);
-		timer->cntv_cval = read_sysreg(cntv_cval_el0);
+		timer->cntv_ctl = read_sysreg_el0(cntv_ctl);
+		timer->cntv_cval = read_sysreg_el0(cntv_cval);
 	}
 
 	/* Disable the virtual timer */
-	write_sysreg(0, cntv_ctl_el0);
+	write_sysreg_el0(0, cntv_ctl);
 
 	/* Allow physical timer/counter access for the host */
 	val = read_sysreg(cnthctl_el2);
@@ -64,8 +62,8 @@ void __hyp_text __timer_restore_state(struct kvm_vcpu *vcpu)
 
 	if (kvm->arch.timer.enabled) {
 		write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2);
-		write_sysreg(timer->cntv_cval, cntv_cval_el0);
+		write_sysreg_el0(timer->cntv_cval, cntv_cval);
 		isb();
-		write_sysreg(timer->cntv_ctl, cntv_ctl_el0);
+		write_sysreg_el0(timer->cntv_ctl, cntv_ctl);
 	}
 }
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
new file mode 100644
index 000000000000..674bdf8ecf4f
--- /dev/null
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -0,0 +1,170 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.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 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
+					    void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	u32 eisr0, eisr1;
+	int i;
+	bool expect_mi;
+
+	expect_mi = !!(cpu_if->vgic_hcr & GICH_HCR_UIE);
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+		expect_mi |= (!(cpu_if->vgic_lr[i] & GICH_LR_HW) &&
+			      (cpu_if->vgic_lr[i] & GICH_LR_EOI));
+	}
+
+	if (expect_mi) {
+		cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
+
+		if (cpu_if->vgic_misr & GICH_MISR_EOI) {
+			eisr0  = readl_relaxed(base + GICH_EISR0);
+			if (unlikely(nr_lr > 32))
+				eisr1  = readl_relaxed(base + GICH_EISR1);
+			else
+				eisr1 = 0;
+		} else {
+			eisr0 = eisr1 = 0;
+		}
+	} else {
+		cpu_if->vgic_misr = 0;
+		eisr0 = eisr1 = 0;
+	}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	cpu_if->vgic_eisr = ((u64)eisr0 << 32) | eisr1;
+#else
+	cpu_if->vgic_eisr = ((u64)eisr1 << 32) | eisr0;
+#endif
+}
+
+static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	u32 elrsr0, elrsr1;
+
+	elrsr0 = readl_relaxed(base + GICH_ELRSR0);
+	if (unlikely(nr_lr > 32))
+		elrsr1 = readl_relaxed(base + GICH_ELRSR1);
+	else
+		elrsr1 = 0;
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1;
+#else
+	cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0;
+#endif
+}
+
+static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	int i;
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+			continue;
+
+		if (cpu_if->vgic_elrsr & (1UL << i)) {
+			cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
+			continue;
+		}
+
+		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
+		writel_relaxed(0, base + GICH_LR0 + (i * 4));
+	}
+}
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+
+	if (!base)
+		return;
+
+	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
+
+	if (vcpu->arch.vgic_cpu.live_lrs) {
+		cpu_if->vgic_apr = readl_relaxed(base + GICH_APR);
+
+		save_maint_int_state(vcpu, base);
+		save_elrsr(vcpu, base);
+		save_lrs(vcpu, base);
+
+		writel_relaxed(0, base + GICH_HCR);
+
+		vcpu->arch.vgic_cpu.live_lrs = 0;
+	} else {
+		cpu_if->vgic_eisr = 0;
+		cpu_if->vgic_elrsr = ~0UL;
+		cpu_if->vgic_misr = 0;
+		cpu_if->vgic_apr = 0;
+	}
+}
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+	int i, nr_lr;
+	u64 live_lrs = 0;
+
+	if (!base)
+		return;
+
+	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+
+	for (i = 0; i < nr_lr; i++)
+		if (cpu_if->vgic_lr[i] & GICH_LR_STATE)
+			live_lrs |= 1UL << i;
+
+	if (live_lrs) {
+		writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
+		writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
+		for (i = 0; i < nr_lr; i++) {
+			if (!(live_lrs & (1UL << i)))
+				continue;
+
+			writel_relaxed(cpu_if->vgic_lr[i],
+				       base + GICH_LR0 + (i * 4));
+		}
+	}
+
+	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
+	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
+}
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
new file mode 100644
index 000000000000..b5754c6c5508
--- /dev/null
+++ b/virt/kvm/arm/pmu.c
@@ -0,0 +1,529 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd.
+ * Author: Shannon Zhao <shannon.zhao@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+#include <asm/kvm_emulate.h>
+#include <kvm/arm_pmu.h>
+#include <kvm/arm_vgic.h>
+
+/**
+ * kvm_pmu_get_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ */
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	u64 counter, reg, enabled, running;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
+	counter = vcpu_sys_reg(vcpu, reg);
+
+	/* The real counter value is equal to the value of counter register plus
+	 * the value perf event counts.
+	 */
+	if (pmc->perf_event)
+		counter += perf_event_read_value(pmc->perf_event, &enabled,
+						 &running);
+
+	return counter & pmc->bitmask;
+}
+
+/**
+ * kvm_pmu_set_counter_value - set PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ * @val: The counter value
+ */
+void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
+{
+	u64 reg;
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
+	vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
+}
+
+/**
+ * kvm_pmu_stop_counter - stop PMU counter
+ * @pmc: The PMU counter pointer
+ *
+ * If this counter has been configured to monitor some event, release it here.
+ */
+static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
+{
+	u64 counter, reg;
+
+	if (pmc->perf_event) {
+		counter = kvm_pmu_get_counter_value(vcpu, pmc->idx);
+		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
+		vcpu_sys_reg(vcpu, reg) = counter;
+		perf_event_disable(pmc->perf_event);
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+	}
+}
+
+/**
+ * kvm_pmu_vcpu_reset - reset pmu state for cpu
+ * @vcpu: The vcpu pointer
+ *
+ */
+void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
+		pmu->pmc[i].idx = i;
+		pmu->pmc[i].bitmask = 0xffffffffUL;
+	}
+}
+
+/**
+ * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu
+ * @vcpu: The vcpu pointer
+ *
+ */
+void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		struct kvm_pmc *pmc = &pmu->pmc[i];
+
+		if (pmc->perf_event) {
+			perf_event_disable(pmc->perf_event);
+			perf_event_release_kernel(pmc->perf_event);
+			pmc->perf_event = NULL;
+		}
+	}
+}
+
+u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
+{
+	u64 val = vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT;
+
+	val &= ARMV8_PMU_PMCR_N_MASK;
+	if (val == 0)
+		return BIT(ARMV8_PMU_CYCLE_IDX);
+	else
+		return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX);
+}
+
+/**
+ * kvm_pmu_enable_counter - enable selected PMU counter
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCNTENSET register
+ *
+ * Call perf_event_enable to start counting the perf event
+ */
+void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+
+	if (!(vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val)
+		return;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		if (!(val & BIT(i)))
+			continue;
+
+		pmc = &pmu->pmc[i];
+		if (pmc->perf_event) {
+			perf_event_enable(pmc->perf_event);
+			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
+				kvm_debug("fail to enable perf event\n");
+		}
+	}
+}
+
+/**
+ * kvm_pmu_disable_counter - disable selected PMU counter
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCNTENCLR register
+ *
+ * Call perf_event_disable to stop counting the perf event
+ */
+void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+
+	if (!val)
+		return;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		if (!(val & BIT(i)))
+			continue;
+
+		pmc = &pmu->pmc[i];
+		if (pmc->perf_event)
+			perf_event_disable(pmc->perf_event);
+	}
+}
+
+static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
+{
+	u64 reg = 0;
+
+	if ((vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+		reg = vcpu_sys_reg(vcpu, PMOVSSET_EL0);
+		reg &= vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+		reg &= vcpu_sys_reg(vcpu, PMINTENSET_EL1);
+		reg &= kvm_pmu_valid_counter_mask(vcpu);
+
+	return reg;
+}
+
+/**
+ * kvm_pmu_overflow_set - set PMU overflow interrupt
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMOVSSET register
+ */
+void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val)
+{
+	u64 reg;
+
+	if (val == 0)
+		return;
+
+	vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= val;
+	reg = kvm_pmu_overflow_status(vcpu);
+	if (reg != 0)
+		kvm_vcpu_kick(vcpu);
+}
+
+static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	bool overflow;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return;
+
+	overflow = !!kvm_pmu_overflow_status(vcpu);
+	if (pmu->irq_level != overflow) {
+		pmu->irq_level = overflow;
+		kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+				    pmu->irq_num, overflow);
+	}
+}
+
+/**
+ * kvm_pmu_flush_hwstate - flush pmu state to cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the PMU has overflowed while we were running in the host, and inject
+ * an interrupt if that was the case.
+ */
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	kvm_pmu_update_state(vcpu);
+}
+
+/**
+ * kvm_pmu_sync_hwstate - sync pmu state from cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the PMU has overflowed while we were running in the guest, and
+ * inject an interrupt if that was the case.
+ */
+void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+	kvm_pmu_update_state(vcpu);
+}
+
+static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu;
+	struct kvm_vcpu_arch *vcpu_arch;
+
+	pmc -= pmc->idx;
+	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
+	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
+	return container_of(vcpu_arch, struct kvm_vcpu, arch);
+}
+
+/**
+ * When perf event overflows, call kvm_pmu_overflow_set to set overflow status.
+ */
+static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
+				  struct perf_sample_data *data,
+				  struct pt_regs *regs)
+{
+	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	int idx = pmc->idx;
+
+	kvm_pmu_overflow_set(vcpu, BIT(idx));
+}
+
+/**
+ * kvm_pmu_software_increment - do software increment
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMSWINC register
+ */
+void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	u64 type, enable, reg;
+
+	if (val == 0)
+		return;
+
+	enable = vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+	for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) {
+		if (!(val & BIT(i)))
+			continue;
+		type = vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
+		       & ARMV8_PMU_EVTYPE_EVENT;
+		if ((type == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		    && (enable & BIT(i))) {
+			reg = vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+			reg = lower_32_bits(reg);
+			vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
+			if (!reg)
+				kvm_pmu_overflow_set(vcpu, BIT(i));
+		}
+	}
+}
+
+/**
+ * kvm_pmu_handle_pmcr - handle PMCR register
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCR register
+ */
+void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+	u64 mask;
+	int i;
+
+	mask = kvm_pmu_valid_counter_mask(vcpu);
+	if (val & ARMV8_PMU_PMCR_E) {
+		kvm_pmu_enable_counter(vcpu,
+				vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
+	} else {
+		kvm_pmu_disable_counter(vcpu, mask);
+	}
+
+	if (val & ARMV8_PMU_PMCR_C)
+		kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
+
+	if (val & ARMV8_PMU_PMCR_P) {
+		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
+			kvm_pmu_set_counter_value(vcpu, i, 0);
+	}
+
+	if (val & ARMV8_PMU_PMCR_LC) {
+		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
+		pmc->bitmask = 0xffffffffffffffffUL;
+	}
+}
+
+static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	return (vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) &&
+	       (vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(select_idx));
+}
+
+/**
+ * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
+ * @vcpu: The vcpu pointer
+ * @data: The data guest writes to PMXEVTYPER_EL0
+ * @select_idx: The number of selected counter
+ *
+ * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an
+ * event with given hardware event number. Here we call perf_event API to
+ * emulate this action and create a kernel perf event for it.
+ */
+void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
+				    u64 select_idx)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	struct perf_event *event;
+	struct perf_event_attr attr;
+	u64 eventsel, counter;
+
+	kvm_pmu_stop_counter(vcpu, pmc);
+	eventsel = data & ARMV8_PMU_EVTYPE_EVENT;
+
+	/* Software increment event does't need to be backed by a perf event */
+	if (eventsel == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		return;
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.type = PERF_TYPE_RAW;
+	attr.size = sizeof(attr);
+	attr.pinned = 1;
+	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, select_idx);
+	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
+	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
+	attr.exclude_hv = 1; /* Don't count EL2 events */
+	attr.exclude_host = 1; /* Don't count host events */
+	attr.config = eventsel;
+
+	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
+	/* The initial sample period (overflow count) of an event. */
+	attr.sample_period = (-counter) & pmc->bitmask;
+
+	event = perf_event_create_kernel_counter(&attr, -1, current,
+						 kvm_pmu_perf_overflow, pmc);
+	if (IS_ERR(event)) {
+		pr_err_once("kvm: pmu event creation failed %ld\n",
+			    PTR_ERR(event));
+		return;
+	}
+
+	pmc->perf_event = event;
+}
+
+bool kvm_arm_support_pmu_v3(void)
+{
+	/*
+	 * Check if HW_PERF_EVENTS are supported by checking the number of
+	 * hardware performance counters. This could ensure the presence of
+	 * a physical PMU and CONFIG_PERF_EVENT is selected.
+	 */
+	return (perf_num_counters() > 0);
+}
+
+static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_arm_support_pmu_v3())
+		return -ENODEV;
+
+	if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features) ||
+	    !kvm_arm_pmu_irq_initialized(vcpu))
+		return -ENXIO;
+
+	if (kvm_arm_pmu_v3_ready(vcpu))
+		return -EBUSY;
+
+	kvm_pmu_vcpu_reset(vcpu);
+	vcpu->arch.pmu.ready = true;
+
+	return 0;
+}
+
+static bool irq_is_valid(struct kvm *kvm, int irq, bool is_ppi)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			continue;
+
+		if (is_ppi) {
+			if (vcpu->arch.pmu.irq_num != irq)
+				return false;
+		} else {
+			if (vcpu->arch.pmu.irq_num == irq)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+
+int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ: {
+		int __user *uaddr = (int __user *)(long)attr->addr;
+		int irq;
+
+		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return -ENODEV;
+
+		if (get_user(irq, uaddr))
+			return -EFAULT;
+
+		/*
+		 * The PMU overflow interrupt could be a PPI or SPI, but for one
+		 * VM the interrupt type must be same for each vcpu. As a PPI,
+		 * the interrupt number is the same for all vcpus, while as an
+		 * SPI it must be a separate number per vcpu.
+		 */
+		if (irq < VGIC_NR_SGIS || irq >= vcpu->kvm->arch.vgic.nr_irqs ||
+		    !irq_is_valid(vcpu->kvm, irq, irq < VGIC_NR_PRIVATE_IRQS))
+			return -EINVAL;
+
+		if (kvm_arm_pmu_irq_initialized(vcpu))
+			return -EBUSY;
+
+		kvm_debug("Set kvm ARM PMU irq: %d\n", irq);
+		vcpu->arch.pmu.irq_num = irq;
+		return 0;
+	}
+	case KVM_ARM_VCPU_PMU_V3_INIT:
+		return kvm_arm_pmu_v3_init(vcpu);
+	}
+
+	return -ENXIO;
+}
+
+int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ: {
+		int __user *uaddr = (int __user *)(long)attr->addr;
+		int irq;
+
+		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return -ENODEV;
+
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			return -ENXIO;
+
+		irq = vcpu->arch.pmu.irq_num;
+		return put_user(irq, uaddr);
+	}
+	}
+
+	return -ENXIO;
+}
+
+int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ:
+	case KVM_ARM_VCPU_PMU_V3_INIT:
+		if (kvm_arm_support_pmu_v3() &&
+		    test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return 0;
+	}
+
+	return -ENXIO;
+}
diff --git a/virt/kvm/arm/vgic-v2-emul.c b/virt/kvm/arm/vgic-v2-emul.c
index 13907970d11c..1b0bee095427 100644
--- a/virt/kvm/arm/vgic-v2-emul.c
+++ b/virt/kvm/arm/vgic-v2-emul.c
@@ -321,6 +321,11 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
 
 static const struct vgic_io_range vgic_dist_ranges[] = {
 	{
+		.base		= GIC_DIST_SOFTINT,
+		.len		= 4,
+		.handle_mmio	= handle_mmio_sgi_reg,
+	},
+	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,
 		.bits_per_irq	= 0,
@@ -387,11 +392,6 @@ static const struct vgic_io_range vgic_dist_ranges[] = {
 		.handle_mmio	= handle_mmio_cfg_reg,
 	},
 	{
-		.base		= GIC_DIST_SOFTINT,
-		.len		= 4,
-		.handle_mmio	= handle_mmio_sgi_reg,
-	},
-	{
 		.base		= GIC_DIST_SGI_PENDING_CLEAR,
 		.len		= VGIC_NR_SGIS,
 		.handle_mmio	= handle_mmio_sgi_clear,
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index ff02f08df74d..67ec334ce1d0 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -176,6 +176,15 @@ static const struct vgic_ops vgic_v2_ops = {
 
 static struct vgic_params vgic_v2_params;
 
+static void vgic_cpu_init_lrs(void *params)
+{
+	struct vgic_params *vgic = params;
+	int i;
+
+	for (i = 0; i < vgic->nr_lr; i++)
+		writel_relaxed(0, vgic->vctrl_base + GICH_LR0 + (i * 4));
+}
+
 /**
  * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
  * @node:	pointer to the DT node
@@ -257,6 +266,9 @@ int vgic_v2_probe(struct device_node *vgic_node,
 
 	vgic->type = VGIC_V2;
 	vgic->max_gic_vcpus = VGIC_V2_MAX_CPUS;
+
+	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
+
 	*ops = &vgic_v2_ops;
 	*params = vgic;
 	goto out;
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 453eafd4dd6e..999bdc6d9d9f 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -42,7 +42,7 @@ static u32 ich_vtr_el2;
 static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
 {
 	struct vgic_lr lr_desc;
-	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)];
+	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr];
 
 	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
 		lr_desc.irq = val & ICH_LR_VIRTUALID_MASK;
@@ -106,7 +106,7 @@ static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
 		lr_val |= ((u64)lr_desc.hwirq) << ICH_LR_PHYS_ID_SHIFT;
 	}
 
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)] = lr_val;
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = lr_val;
 
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
@@ -216,6 +216,11 @@ static const struct vgic_ops vgic_v3_ops = {
 
 static struct vgic_params vgic_v3_params;
 
+static void vgic_cpu_init_lrs(void *params)
+{
+	kvm_call_hyp(__vgic_v3_init_lrs);
+}
+
 /**
  * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
  * @node:	pointer to the DT node
@@ -284,6 +289,8 @@ int vgic_v3_probe(struct device_node *vgic_node,
 	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
 		 vcpu_res.start, vgic->maint_irq);
 
+	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
+
 	*ops = &vgic_v3_ops;
 	*params = vgic;
 
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 043032c6a5a4..00429b392c61 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1875,8 +1875,8 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-
-	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
+	int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
+	int sz = nr_longs * sizeof(unsigned long);
 	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
 	vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL);
 	vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL);
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index c7e447c4296e..b866374282be 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -172,7 +172,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 	 * do alloc nowait since if we are going to sleep anyway we
 	 * may as well sleep faulting in page
 	 */
-	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT);
+	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
 	if (!work)
 		return 0;
author	Paolo Bonzini <pbonzini@redhat.com>	2016-03-09 11:50:42 +0100
committer	Paolo Bonzini <pbonzini@redhat.com>	2016-03-09 11:50:42 +0100
commit	ab92f30875a7ec3e84644a5494febd8901e66742 (patch)
tree	5254eb36b20b0d1c584c15d0bf3d6a5a9c1bb451
parent	bb9eadf0c35f2e7eb5ca6468f46ebb7473b85537 (diff)
parent	b40c4892d175874d118860c8282a85ee7b64bcbb (diff)
download	linux-ab92f30875a7ec3e84644a5494febd8901e66742.tar.bz2