Merge branch 'drm-etnaviv-fixes' of https://git.pengutronix.de/git/lst/linux into drm-fixes

a single fix for a FE hang after IOVA rollover on GC3000. This isn't
pretty, but is the minimal fix for the issue. A larger rework of the
code, that will also fix this issue properly, is currently in the works,
but that needs to wait for at least the next feature pull.

* 'drm-etnaviv-fixes' of https://git.pengutronix.de/git/lst/linux:
  drm/etnaviv: trick drm_mm into giving out a low IOVA
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index c75e5d6..a6eb7dc 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -12,7 +12,7 @@
 	    kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-	    80211.xml sh.xml regulator.xml w1.xml \
+	    sh.xml regulator.xml w1.xml \
 	    writing_musb_glue_layer.xml iio.xml
 
 ifeq ($(DOCBOOKS),)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 21e2d88..be7c0d9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -106,6 +106,16 @@
 			use by PCI
 			Format: <irq>,<irq>...
 
+	acpi_mask_gpe=  [HW,ACPI]
+			Due to the existence of _Lxx/_Exx, some GPEs triggered
+			by unsupported hardware/firmware features can result in
+                        GPE floodings that cannot be automatically disabled by
+                        the GPE dispatcher.
+			This facility can be used to prevent such uncontrolled
+			GPE floodings.
+			Format: <int>
+			Support masking of GPEs numbered from 0x00 to 0x7f.
+
 	acpi_no_auto_serialize	[HW,ACPI]
 			Disable auto-serialization of AML methods
 			AML control methods that contain the opcodes to create
@@ -3811,10 +3821,11 @@
 			it if 0 is given (See Documentation/cgroup-v1/memory.txt)
 
 	swiotlb=	[ARM,IA-64,PPC,MIPS,X86]
-			Format: { <int> | force }
+			Format: { <int> | force | noforce }
 			<int> -- Number of I/O TLB slabs
 			force -- force using of bounce buffers even if they
 			         wouldn't be automatically used by the kernel
+			noforce -- Never use bounce buffers (for debugging)
 
 	switches=	[HW,M68k]
 
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index 5164215..c0a3bb5 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -54,9 +54,9 @@
 
 io_poll (RW)
 ------------
-When read, this file shows the total number of block IO polls and how
-many returned success.  Writing '0' to this file will disable polling
-for this device.  Writing any non-zero value will enable this feature.
+When read, this file shows whether polling is enabled (1) or disabled
+(0).  Writing '0' to this file will disable polling for this device.
+Writing any non-zero value will enable this feature.
 
 io_poll_delay (RW)
 ------------------
diff --git a/Documentation/devicetree/bindings/input/tps65218-pwrbutton.txt b/Documentation/devicetree/bindings/input/tps65218-pwrbutton.txt
index 3e5b979..8682ab6 100644
--- a/Documentation/devicetree/bindings/input/tps65218-pwrbutton.txt
+++ b/Documentation/devicetree/bindings/input/tps65218-pwrbutton.txt
@@ -8,8 +8,9 @@
 Required properties:
 - compatible: should be "ti,tps65217-pwrbutton" or "ti,tps65218-pwrbutton"
 
-Required properties for TPS65218:
+Required properties:
 - interrupts: should be one of the following
+   - <2>: For controllers compatible with tps65217
    - <3 IRQ_TYPE_EDGE_BOTH>: For controllers compatible with tps65218
 
 Examples:
@@ -17,6 +18,7 @@
 &tps {
 	tps65217-pwrbutton {
 		compatible = "ti,tps65217-pwrbutton";
+		interrupts = <2>;
 	};
 };
 
diff --git a/Documentation/devicetree/bindings/power/supply/tps65217_charger.txt b/Documentation/devicetree/bindings/power/supply/tps65217_charger.txt
index 98d131a..a11072c 100644
--- a/Documentation/devicetree/bindings/power/supply/tps65217_charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/tps65217_charger.txt
@@ -2,11 +2,16 @@
 
 Required Properties:
 -compatible: "ti,tps65217-charger"
+-interrupts: TPS65217 interrupt numbers for the AC and USB charger input change.
+             Should be <0> for the USB charger and <1> for the AC adapter.
+-interrupt-names: Should be "USB" and "AC"
 
 This node is a subnode of the tps65217 PMIC.
 
 Example:
 
 	tps65217-charger {
-		compatible = "ti,tps65090-charger";
+		compatible = "ti,tps65217-charger";
+		interrupts = <0>, <1>;
+		interrupt-names = "USB", "AC";
 	};
diff --git a/Documentation/driver-api/infrastructure.rst b/Documentation/driver-api/infrastructure.rst
index 0bb0b5f..6d9ff31 100644
--- a/Documentation/driver-api/infrastructure.rst
+++ b/Documentation/driver-api/infrastructure.rst
@@ -55,21 +55,6 @@
 .. kernel-doc:: drivers/base/dma-mapping.c
    :export:
 
-Device Drivers Power Management
--------------------------------
-
-.. kernel-doc:: drivers/base/power/main.c
-   :export:
-
-Device Drivers ACPI Support
----------------------------
-
-.. kernel-doc:: drivers/acpi/scan.c
-   :export:
-
-.. kernel-doc:: drivers/acpi/scan.c
-   :internal:
-
 Device drivers PnP support
 --------------------------
 
diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt
index 9ed15f8..15d8d16 100644
--- a/Documentation/networking/mpls-sysctl.txt
+++ b/Documentation/networking/mpls-sysctl.txt
@@ -5,8 +5,8 @@
 	possible to configure forwarding for label values equal to or
 	greater than the number of platform labels.
 
-	A dense utliziation of the entries in the platform label table
-	is possible and expected aas the platform labels are locally
+	A dense utilization of the entries in the platform label table
+	is possible and expected as the platform labels are locally
 	allocated.
 
 	If the number of platform label table entries is set to 0 no
diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt
index a445da0..3f76c0c 100644
--- a/Documentation/unaligned-memory-access.txt
+++ b/Documentation/unaligned-memory-access.txt
@@ -151,7 +151,7 @@
 #else
 	const u16 *a = (const u16 *)addr1;
 	const u16 *b = (const u16 *)addr2;
-	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0;
+	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0;
 #endif
 }
 
diff --git a/Documentation/vfio-mediated-device.txt b/Documentation/vfio-mediated-device.txt
index b38afec..d226c7a 100644
--- a/Documentation/vfio-mediated-device.txt
+++ b/Documentation/vfio-mediated-device.txt
@@ -127,22 +127,22 @@
 Physical Device Driver Interface
 --------------------------------
 
-The physical device driver interface provides the parent_ops[3] structure to
-define the APIs to manage work in the mediated core driver that is related to
-the physical device.
+The physical device driver interface provides the mdev_parent_ops[3] structure
+to define the APIs to manage work in the mediated core driver that is related
+to the physical device.
 
-The structures in the parent_ops structure are as follows:
+The structures in the mdev_parent_ops structure are as follows:
 
 * dev_attr_groups: attributes of the parent device
 * mdev_attr_groups: attributes of the mediated device
 * supported_config: attributes to define supported configurations
 
-The functions in the parent_ops structure are as follows:
+The functions in the mdev_parent_ops structure are as follows:
 
 * create: allocate basic resources in a driver for a mediated device
 * remove: free resources in a driver when a mediated device is destroyed
 
-The callbacks in the parent_ops structure are as follows:
+The callbacks in the mdev_parent_ops structure are as follows:
 
 * open: open callback of mediated device
 * close: close callback of mediated device
@@ -151,14 +151,14 @@
 * write: write emulation callback
 * mmap: mmap emulation callback
 
-A driver should use the parent_ops structure in the function call to register
-itself with the mdev core driver:
+A driver should use the mdev_parent_ops structure in the function call to
+register itself with the mdev core driver:
 
 extern int  mdev_register_device(struct device *dev,
-                                 const struct parent_ops *ops);
+                                 const struct mdev_parent_ops *ops);
 
-However, the parent_ops structure is not required in the function call that a
-driver should use to unregister itself with the mdev core driver:
+However, the mdev_parent_ops structure is not required in the function call
+that a driver should use to unregister itself with the mdev core driver:
 
 extern void mdev_unregister_device(struct device *dev);
 
@@ -223,6 +223,9 @@
 
 	sprintf(buf, "%s-%s", dev_driver_string(parent->dev), group->name);
 
+  (or using mdev_parent_dev(mdev) to arrive at the parent device outside
+   of the core mdev code)
+
 * device_api
 
   This attribute should show which device API is being created, for example,
@@ -394,5 +397,5 @@
 
 [1] See Documentation/vfio.txt for more information on VFIO.
 [2] struct mdev_driver in include/linux/mdev.h
-[3] struct parent_ops in include/linux/mdev.h
+[3] struct mdev_parent_ops in include/linux/mdev.h
 [4] struct vfio_iommu_driver_ops in include/linux/vfio.h
diff --git a/MAINTAINERS b/MAINTAINERS
index cfff2c9..35c9cbf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3800,6 +3800,7 @@
 DEVICE FREQUENCY (DEVFREQ)
 M:	MyungJoo Ham <myungjoo.ham@samsung.com>
 M:	Kyungmin Park <kyungmin.park@samsung.com>
+R:	Chanwoo Choi <cw00.choi@samsung.com>
 L:	linux-pm@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq.git
 S:	Maintained
@@ -4116,7 +4117,7 @@
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <alexander.deucher@amd.com>
 M:	Christian König <christian.koenig@amd.com>
-L:	dri-devel@lists.freedesktop.org
+L:	amd-gfx@lists.freedesktop.org
 T:	git git://people.freedesktop.org/~agd5f/linux
 S:	Supported
 F:	drivers/gpu/drm/radeon/
@@ -5080,9 +5081,11 @@
 F:	drivers/net/wan/sdla.c
 
 FRAMEBUFFER LAYER
+M:	Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
 L:	linux-fbdev@vger.kernel.org
+T:	git git://github.com/bzolnier/linux.git
 Q:	http://patchwork.kernel.org/project/linux-fbdev/list/
-S:	Orphan
+S:	Maintained
 F:	Documentation/fb/
 F:	drivers/video/
 F:	include/video/
@@ -5504,6 +5507,7 @@
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Maintained
 F:	drivers/staging/greybus/
+L:	greybus-dev@lists.linaro.org
 
 GREYBUS AUDIO PROTOCOLS DRIVERS
 M:	Vaibhav Agarwal <vaibhav.sr@gmail.com>
@@ -5961,6 +5965,7 @@
 Hyper-V CORE AND DRIVERS
 M:	"K. Y. Srinivasan" <kys@microsoft.com>
 M:	Haiyang Zhang <haiyangz@microsoft.com>
+M:	Stephen Hemminger <sthemmin@microsoft.com>
 L:	devel@linuxdriverproject.org
 S:	Maintained
 F:	arch/x86/include/asm/mshyperv.h
@@ -8852,17 +8857,22 @@
 NVM EXPRESS DRIVER
 M:	Keith Busch <keith.busch@intel.com>
 M:	Jens Axboe <axboe@fb.com>
+M:	Christoph Hellwig <hch@lst.de>
+M:	Sagi Grimberg <sagi@grimberg.me>
 L:	linux-nvme@lists.infradead.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
-W:	https://kernel.googlesource.com/pub/scm/linux/kernel/git/axboe/linux-block/
+T:	git://git.infradead.org/nvme.git
+W:	http://git.infradead.org/nvme.git
 S:	Supported
 F:	drivers/nvme/host/
 F:	include/linux/nvme.h
+F:	include/uapi/linux/nvme_ioctl.h
 
 NVM EXPRESS TARGET DRIVER
 M:	Christoph Hellwig <hch@lst.de>
 M:	Sagi Grimberg <sagi@grimberg.me>
 L:	linux-nvme@lists.infradead.org
+T:	git://git.infradead.org/nvme.git
+W:	http://git.infradead.org/nvme.git
 S:	Supported
 F:	drivers/nvme/target/
 
@@ -9842,7 +9852,7 @@
 M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
 L:	linux-arm-kernel@lists.infradead.org
 S:	Maintained
-F:	drivers/firmware/psci.c
+F:	drivers/firmware/psci*.c
 F:	include/linux/psci.h
 F:	include/uapi/linux/psci.h
 
@@ -13527,11 +13537,11 @@
 F:	drivers/xen/*swiotlb*
 
 XFS FILESYSTEM
-M:	Dave Chinner <david@fromorbit.com>
+M:	Darrick J. Wong <darrick.wong@oracle.com>
 M:	linux-xfs@vger.kernel.org
 L:	linux-xfs@vger.kernel.org
 W:	http://xfs.org/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs.git
+T:	git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
 S:	Supported
 F:	Documentation/filesystems/xfs.txt
 F:	fs/xfs/
diff --git a/Makefile b/Makefile
index ec411ba..5f1a847 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Roaring Lionus
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5fab553..186c4c2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1502,8 +1502,7 @@
 
 config HZ_FIXED
 	int
-	default 200 if ARCH_EBSA110 || ARCH_S3C24XX || \
-		ARCH_S5PV210 || ARCH_EXYNOS4
+	default 200 if ARCH_EBSA110
 	default 128 if SOC_AT91RM9200
 	default 0
 
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index cccdbcb..7327250 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -501,6 +501,7 @@
 	am3517-evm.dtb \
 	am3517_mt_ventoux.dtb \
 	logicpd-torpedo-37xx-devkit.dtb \
+	logicpd-som-lv-37xx-devkit.dtb \
 	omap3430-sdp.dtb \
 	omap3-beagle.dtb \
 	omap3-beagle-xm.dtb \
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index dc561d5..3e32dd1 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -6,8 +6,6 @@
  * published by the Free Software Foundation.
  */
 
-#include <dt-bindings/mfd/tps65217.h>
-
 / {
 	cpus {
 		cpu@0 {
@@ -319,13 +317,13 @@
 	ti,pmic-shutdown-controller;
 
 	charger {
-		interrupts = <TPS65217_IRQ_AC>, <TPS65217_IRQ_USB>;
-		interrupts-names = "AC", "USB";
+		interrupts = <0>, <1>;
+		interrupt-names = "USB", "AC";
 		status = "okay";
 	};
 
 	pwrbutton {
-		interrupts = <TPS65217_IRQ_PB>;
+		interrupts = <2>;
 		status = "okay";
 	};
 
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 64c8aa9..18d72a2 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -16,6 +16,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c0;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index ac55f93..2df9e60 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -16,6 +16,7 @@
 	interrupt-parent = <&wakeupgen>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	memory@0 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts
index d6e43e5..ad68d1e 100644
--- a/arch/arm/boot/dts/am571x-idk.dts
+++ b/arch/arm/boot/dts/am571x-idk.dts
@@ -62,11 +62,6 @@
 			linux,default-trigger = "mmc0";
 		};
 	};
-
-	extcon_usb2: extcon_usb2 {
-	     compatible = "linux,extcon-usb-gpio";
-	     id-gpio = <&gpio5 7 GPIO_ACTIVE_HIGH>;
-	};
 };
 
 &mmc1 {
@@ -79,3 +74,8 @@
 &omap_dwc3_2 {
 	extcon = <&extcon_usb2>;
 };
+
+&extcon_usb2 {
+	id-gpio = <&gpio5 7 GPIO_ACTIVE_HIGH>;
+	vbus-gpio = <&gpio7 22 GPIO_ACTIVE_HIGH>;
+};
diff --git a/arch/arm/boot/dts/am572x-idk.dts b/arch/arm/boot/dts/am572x-idk.dts
index 27d9149..8350b4b 100644
--- a/arch/arm/boot/dts/am572x-idk.dts
+++ b/arch/arm/boot/dts/am572x-idk.dts
@@ -23,11 +23,6 @@
 		reg = <0x0 0x80000000 0x0 0x80000000>;
 	};
 
-	extcon_usb2: extcon_usb2 {
-		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&gpio3 16 GPIO_ACTIVE_HIGH>;
-	};
-
 	status-leds {
 		compatible = "gpio-leds";
 		cpu0-led {
@@ -76,6 +71,11 @@
 	extcon = <&extcon_usb2>;
 };
 
+&extcon_usb2 {
+	id-gpio = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+	vbus-gpio = <&gpio3 26 GPIO_ACTIVE_HIGH>;
+};
+
 &mmc1 {
 	status = "okay";
 	vmmc-supply = <&v3_3d>;
@@ -87,3 +87,7 @@
 &sn65hvs882 {
 	load-gpios = <&gpio3 19 GPIO_ACTIVE_LOW>;
 };
+
+&pcie1 {
+	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+};
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index 555ae21..814a720 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -303,6 +303,13 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 		};
+
+		extcon_usb2: tps659038_usb {
+			compatible = "ti,palmas-usb-vid";
+			ti,enable-vbus-detection;
+			ti,enable-id-detection;
+			/* ID & VBUS GPIOs provided in board dts */
+		};
 	};
 };
 
@@ -369,7 +376,7 @@
 };
 
 &usb2 {
-	dr_mode = "otg";
+	dr_mode = "peripheral";
 };
 
 &mmc2 {
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index 1facc5f..81b8cec 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -12,6 +12,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 61dd2f6..6db652a 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -12,6 +12,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index addb753..1faf24a 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -18,6 +18,7 @@
 
 	compatible = "ti,dra7xx";
 	interrupt-parent = <&crossbar_mpu>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/dra72-evm-tps65917.dtsi b/arch/arm/boot/dts/dra72-evm-tps65917.dtsi
index ee6dac4..e6df676 100644
--- a/arch/arm/boot/dts/dra72-evm-tps65917.dtsi
+++ b/arch/arm/boot/dts/dra72-evm-tps65917.dtsi
@@ -132,3 +132,19 @@
 		ti,palmas-long-press-seconds = <6>;
 	};
 };
+
+&usb2_phy1 {
+	phy-supply = <&ldo4_reg>;
+};
+
+&usb2_phy2 {
+	phy-supply = <&ldo4_reg>;
+};
+
+&dss {
+	vdda_video-supply = <&ldo5_reg>;
+};
+
+&mmc1 {
+	vmmc_aux-supply = <&ldo1_reg>;
+};
diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi
index 685916e..85cd8be 100644
--- a/arch/arm/boot/dts/imx31.dtsi
+++ b/arch/arm/boot/dts/imx31.dtsi
@@ -31,11 +31,11 @@
 		};
 	};
 
-	avic: avic-interrupt-controller@60000000 {
+	avic: interrupt-controller@68000000 {
 		compatible = "fsl,imx31-avic", "fsl,avic";
 		interrupt-controller;
 		#interrupt-cells = <1>;
-		reg = <0x60000000 0x100000>;
+		reg = <0x68000000 0x100000>;
 	};
 
 	soc {
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
index e476d01..26d0604 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
@@ -533,7 +533,6 @@
 				MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x17071
 				MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x17071
 				MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x17071
-				MX6QDL_PAD_NANDF_CS2__GPIO6_IO15	0x000b0
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 53e6e63..89b834f 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -1100,6 +1100,7 @@
 				interrupts = <0 14 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6QDL_CLK_EIM_SLOW>;
 				fsl,weim-cs-gpr = <&gpr>;
+				status = "disabled";
 			};
 
 			ocotp: ocotp@021bc000 {
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index 4fd6de2..19cbd87 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -900,6 +900,7 @@
 				reg = <0x021b8000 0x4000>;
 				interrupts = <0 14 IRQ_TYPE_LEVEL_HIGH>;
 				fsl,weim-cs-gpr = <&gpr>;
+				status = "disabled";
 			};
 
 			ocotp: ocotp@021bc000 {
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 076a30f..10f3330 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -977,6 +977,7 @@
 				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6SX_CLK_EIM_SLOW>;
 				fsl,weim-cs-gpr = <&gpr>;
+				status = "disabled";
 			};
 
 			ocotp: ocotp@021bc000 {
diff --git a/arch/arm/boot/dts/omap2.dtsi b/arch/arm/boot/dts/omap2.dtsi
index 4f793a0..f1d6de8 100644
--- a/arch/arm/boot/dts/omap2.dtsi
+++ b/arch/arm/boot/dts/omap2.dtsi
@@ -17,6 +17,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		serial0 = &uart1;
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 87ca50b..4d448f1 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -734,6 +734,8 @@
 	vmmc_aux-supply = <&vsim>;
 	bus-width = <8>;
 	non-removable;
+	no-sdio;
+	no-sd;
 };
 
 &mmc3 {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index ecf5eb5..a3ff493 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -17,6 +17,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 8087456..578c53f 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -15,6 +15,7 @@
 	interrupt-parent = <&wakeupgen>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 968c67a..7cd92ba 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -17,6 +17,7 @@
 
 	compatible = "ti,omap5";
 	interrupt-parent = <&wakeupgen>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi
index 268bd47..407a461 100644
--- a/arch/arm/boot/dts/qcom-apq8064.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8064.dtsi
@@ -4,6 +4,7 @@
 #include <dt-bindings/clock/qcom,gcc-msm8960.h>
 #include <dt-bindings/reset/qcom,gcc-msm8960.h>
 #include <dt-bindings/clock/qcom,mmcc-msm8960.h>
+#include <dt-bindings/clock/qcom,rpmcc.h>
 #include <dt-bindings/soc/qcom,gsbi.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -303,6 +304,9 @@
 	firmware {
 		scm {
 			compatible = "qcom,scm-apq8064";
+
+			clocks = <&rpmcc RPM_DAYTONA_FABRIC_CLK>;
+			clock-names = "core";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
index 102838f..15f4fd3 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
@@ -81,7 +81,7 @@
 		#address-cells = <0>;
 		interrupt-controller;
 		reg = <0 0x2c001000 0 0x1000>,
-		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c002000 0 0x2000>,
 		      <0 0x2c004000 0 0x2000>,
 		      <0 0x2c006000 0 0x2000>;
 		interrupts = <1 9 0xf04>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 45d08cc..bd107c5 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -131,7 +131,7 @@
 		#address-cells = <0>;
 		interrupt-controller;
 		reg = <0 0x2c001000 0 0x1000>,
-		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c002000 0 0x2000>,
 		      <0 0x2c004000 0 0x2000>,
 		      <0 0x2c006000 0 0x2000>;
 		interrupts = <1 9 0xf04>;
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index 7ea617e..958b4c4 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -153,7 +153,8 @@
 					switch0phy1: switch1phy0@1 {
 						reg = <1>;
 						interrupt-parent = <&switch0>;
-						interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;					};
+						interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+					};
 					switch0phy2: switch1phy0@2 {
 						reg = <2>;
 						interrupt-parent = <&switch0>;
diff --git a/arch/arm/mach-davinci/clock.c b/arch/arm/mach-davinci/clock.c
index df42c93..f5dce9b 100644
--- a/arch/arm/mach-davinci/clock.c
+++ b/arch/arm/mach-davinci/clock.c
@@ -31,10 +31,10 @@
 static DEFINE_MUTEX(clocks_mutex);
 static DEFINE_SPINLOCK(clockfw_lock);
 
-static void __clk_enable(struct clk *clk)
+void davinci_clk_enable(struct clk *clk)
 {
 	if (clk->parent)
-		__clk_enable(clk->parent);
+		davinci_clk_enable(clk->parent);
 	if (clk->usecount++ == 0) {
 		if (clk->flags & CLK_PSC)
 			davinci_psc_config(clk->domain, clk->gpsc, clk->lpsc,
@@ -44,7 +44,7 @@
 	}
 }
 
-static void __clk_disable(struct clk *clk)
+void davinci_clk_disable(struct clk *clk)
 {
 	if (WARN_ON(clk->usecount == 0))
 		return;
@@ -56,7 +56,7 @@
 			clk->clk_disable(clk);
 	}
 	if (clk->parent)
-		__clk_disable(clk->parent);
+		davinci_clk_disable(clk->parent);
 }
 
 int davinci_clk_reset(struct clk *clk, bool reset)
@@ -103,7 +103,7 @@
 		return -EINVAL;
 
 	spin_lock_irqsave(&clockfw_lock, flags);
-	__clk_enable(clk);
+	davinci_clk_enable(clk);
 	spin_unlock_irqrestore(&clockfw_lock, flags);
 
 	return 0;
@@ -118,7 +118,7 @@
 		return;
 
 	spin_lock_irqsave(&clockfw_lock, flags);
-	__clk_disable(clk);
+	davinci_clk_disable(clk);
 	spin_unlock_irqrestore(&clockfw_lock, flags);
 }
 EXPORT_SYMBOL(clk_disable);
diff --git a/arch/arm/mach-davinci/clock.h b/arch/arm/mach-davinci/clock.h
index e2a5437..fa2b837 100644
--- a/arch/arm/mach-davinci/clock.h
+++ b/arch/arm/mach-davinci/clock.h
@@ -132,6 +132,8 @@
 int davinci_set_refclk_rate(unsigned long rate);
 int davinci_simple_set_rate(struct clk *clk, unsigned long rate);
 int davinci_clk_reset(struct clk *clk, bool reset);
+void davinci_clk_enable(struct clk *clk);
+void davinci_clk_disable(struct clk *clk);
 
 extern struct platform_device davinci_wdt_device;
 extern void davinci_watchdog_reset(struct platform_device *);
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index e770c97..1d873d1 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -319,6 +319,16 @@
 	.gpsc		= 1,
 };
 
+/*
+ * In order to avoid adding the emac_clk to the clock lookup table twice (and
+ * screwing up the linked list in the process) create a separate clock for
+ * mdio inheriting the rate from emac_clk.
+ */
+static struct clk mdio_clk = {
+	.name		= "mdio",
+	.parent		= &emac_clk,
+};
+
 static struct clk mcasp_clk = {
 	.name		= "mcasp",
 	.parent		= &async3_clk,
@@ -367,6 +377,16 @@
 	.flags		= ALWAYS_ENABLED,
 };
 
+/*
+ * In order to avoid adding the aemif_clk to the clock lookup table twice (and
+ * screwing up the linked list in the process) create a separate clock for
+ * nand inheriting the rate from aemif_clk.
+ */
+static struct clk aemif_nand_clk = {
+	.name		= "nand",
+	.parent		= &aemif_clk,
+};
+
 static struct clk usb11_clk = {
 	.name		= "usb11",
 	.parent		= &pll0_sysclk4,
@@ -529,7 +549,7 @@
 	CLK(NULL,		"arm",		&arm_clk),
 	CLK(NULL,		"rmii",		&rmii_clk),
 	CLK("davinci_emac.1",	NULL,		&emac_clk),
-	CLK("davinci_mdio.0",	"fck",		&emac_clk),
+	CLK("davinci_mdio.0",	"fck",		&mdio_clk),
 	CLK("davinci-mcasp.0",	NULL,		&mcasp_clk),
 	CLK("davinci-mcbsp.0",	NULL,		&mcbsp0_clk),
 	CLK("davinci-mcbsp.1",	NULL,		&mcbsp1_clk),
@@ -537,7 +557,15 @@
 	CLK("da830-mmc.0",	NULL,		&mmcsd0_clk),
 	CLK("da830-mmc.1",	NULL,		&mmcsd1_clk),
 	CLK("ti-aemif",		NULL,		&aemif_clk),
-	CLK(NULL,		"aemif",	&aemif_clk),
+	/*
+	 * The only user of this clock is davinci_nand and it get's it through
+	 * con_id. The nand node itself is created from within the aemif
+	 * driver to guarantee that it's probed after the aemif timing
+	 * parameters are configured. of_dev_auxdata is not accessible from
+	 * the aemif driver and can't be passed to of_platform_populate(). For
+	 * that reason we're leaving the dev_id here as NULL.
+	 */
+	CLK(NULL,		"aemif",	&aemif_nand_clk),
 	CLK("ohci-da8xx",	"usb11",	&usb11_clk),
 	CLK("musb-da8xx",	"usb20",	&usb20_clk),
 	CLK("spi_davinci.0",	NULL,		&spi0_clk),
diff --git a/arch/arm/mach-davinci/usb-da8xx.c b/arch/arm/mach-davinci/usb-da8xx.c
index c6feecf..9a6af0b 100644
--- a/arch/arm/mach-davinci/usb-da8xx.c
+++ b/arch/arm/mach-davinci/usb-da8xx.c
@@ -22,6 +22,8 @@
 #define DA8XX_USB0_BASE		0x01e00000
 #define DA8XX_USB1_BASE		0x01e25000
 
+static struct clk *usb20_clk;
+
 static struct platform_device da8xx_usb_phy = {
 	.name		= "da8xx-usb-phy",
 	.id		= -1,
@@ -158,26 +160,13 @@
 
 static void usb20_phy_clk_enable(struct clk *clk)
 {
-	struct clk *usb20_clk;
-	int err;
 	u32 val;
 	u32 timeout = 500000; /* 500 msec */
 
 	val = readl(DA8XX_SYSCFG0_VIRT(DA8XX_CFGCHIP2_REG));
 
-	usb20_clk = clk_get(&da8xx_usb20_dev.dev, "usb20");
-	if (IS_ERR(usb20_clk)) {
-		pr_err("could not get usb20 clk: %ld\n", PTR_ERR(usb20_clk));
-		return;
-	}
-
 	/* The USB 2.O PLL requires that the USB 2.O PSC is enabled as well. */
-	err = clk_prepare_enable(usb20_clk);
-	if (err) {
-		pr_err("failed to enable usb20 clk: %d\n", err);
-		clk_put(usb20_clk);
-		return;
-	}
+	davinci_clk_enable(usb20_clk);
 
 	/*
 	 * Turn on the USB 2.0 PHY, but just the PLL, and not OTG. The USB 1.1
@@ -197,8 +186,7 @@
 
 	pr_err("Timeout waiting for USB 2.0 PHY clock good\n");
 done:
-	clk_disable_unprepare(usb20_clk);
-	clk_put(usb20_clk);
+	davinci_clk_disable(usb20_clk);
 }
 
 static void usb20_phy_clk_disable(struct clk *clk)
@@ -285,11 +273,19 @@
 int __init da8xx_register_usb20_phy_clk(bool use_usb_refclkin)
 {
 	struct clk *parent;
-	int ret = 0;
+	int ret;
+
+	usb20_clk = clk_get(&da8xx_usb20_dev.dev, "usb20");
+	ret = PTR_ERR_OR_ZERO(usb20_clk);
+	if (ret)
+		return ret;
 
 	parent = clk_get(NULL, use_usb_refclkin ? "usb_refclkin" : "pll0_aux");
-	if (IS_ERR(parent))
-		return PTR_ERR(parent);
+	ret = PTR_ERR_OR_ZERO(parent);
+	if (ret) {
+		clk_put(usb20_clk);
+		return ret;
+	}
 
 	usb20_phy_clk.parent = parent;
 	ret = clk_register(&usb20_phy_clk);
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 98ffe1e..a5d6841 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -385,36 +385,6 @@
 	return pen_release != -1 ? ret : 0;
 }
 
-/*
- * Initialise the CPU possible map early - this describes the CPUs
- * which may be present or become present in the system.
- */
-
-static void __init exynos_smp_init_cpus(void)
-{
-	void __iomem *scu_base = scu_base_addr();
-	unsigned int i, ncores;
-
-	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
-		ncores = scu_base ? scu_get_core_count(scu_base) : 1;
-	else
-		/*
-		 * CPU Nodes are passed thru DT and set_cpu_possible
-		 * is set by "arm_dt_init_cpu_maps".
-		 */
-		return;
-
-	/* sanity check */
-	if (ncores > nr_cpu_ids) {
-		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
-			ncores, nr_cpu_ids);
-		ncores = nr_cpu_ids;
-	}
-
-	for (i = 0; i < ncores; i++)
-		set_cpu_possible(i, true);
-}
-
 static void __init exynos_smp_prepare_cpus(unsigned int max_cpus)
 {
 	int i;
@@ -479,7 +449,6 @@
 #endif /* CONFIG_HOTPLUG_CPU */
 
 const struct smp_operations exynos_smp_ops __initconst = {
-	.smp_init_cpus		= exynos_smp_init_cpus,
 	.smp_prepare_cpus	= exynos_smp_prepare_cpus,
 	.smp_secondary_init	= exynos_secondary_init,
 	.smp_boot_secondary	= exynos_boot_secondary,
diff --git a/arch/arm/mach-imx/mach-imx1.c b/arch/arm/mach-imx/mach-imx1.c
index de5ab8d..3a8406e 100644
--- a/arch/arm/mach-imx/mach-imx1.c
+++ b/arch/arm/mach-imx/mach-imx1.c
@@ -37,7 +37,6 @@
 };
 
 DT_MACHINE_START(IMX1_DT, "Freescale i.MX1 (Device Tree Support)")
-	.map_io		= debug_ll_io_init,
 	.init_early	= imx1_init_early,
 	.init_irq	= imx1_init_irq,
 	.dt_compat	= imx1_dt_board_compat,
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 4698940..093458b 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -7,7 +7,7 @@
 
 # Common support
 obj-y := id.o io.o control.o devices.o fb.o timer.o pm.o \
-	 common.o gpio.o dma.o wd_timer.o display.o i2c.o hdq1w.o omap_hwmod.o \
+	 common.o dma.o wd_timer.o display.o i2c.o hdq1w.o omap_hwmod.o \
 	 omap_device.o omap-headsmp.o sram.o drm.o
 
 hwmod-common				= omap_hwmod.o omap_hwmod_reset.o \
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 36d9943..dc9e34e 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -304,7 +304,7 @@
 	.init_late	= am43xx_init_late,
 	.init_irq	= omap_gic_of_init,
 	.init_machine	= omap_generic_init,
-	.init_time	= omap4_local_timer_init,
+	.init_time	= omap3_gptimer_timer_init,
 	.dt_compat	= am43_boards_compat,
 	.restart	= omap44xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-omap2/gpio.c b/arch/arm/mach-omap2/gpio.c
deleted file mode 100644
index 7a57714..0000000
--- a/arch/arm/mach-omap2/gpio.c
+++ /dev/null
@@ -1,160 +0,0 @@
-/*
- * OMAP2+ specific gpio initialization
- *
- * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com/
- *
- * Author:
- *	Charulatha V <charu@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/gpio.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/of.h>
-#include <linux/platform_data/gpio-omap.h>
-
-#include "soc.h"
-#include "omap_hwmod.h"
-#include "omap_device.h"
-#include "omap-pm.h"
-
-#include "powerdomain.h"
-
-static int __init omap2_gpio_dev_init(struct omap_hwmod *oh, void *unused)
-{
-	struct platform_device *pdev;
-	struct omap_gpio_platform_data *pdata;
-	struct omap_gpio_dev_attr *dev_attr;
-	char *name = "omap_gpio";
-	int id;
-	struct powerdomain *pwrdm;
-
-	/*
-	 * extract the device id from name field available in the
-	 * hwmod database and use the same for constructing ids for
-	 * gpio devices.
-	 * CAUTION: Make sure the name in the hwmod database does
-	 * not change. If changed, make corresponding change here
-	 * or make use of static variable mechanism to handle this.
-	 */
-	sscanf(oh->name, "gpio%d", &id);
-
-	pdata = kzalloc(sizeof(struct omap_gpio_platform_data), GFP_KERNEL);
-	if (!pdata) {
-		pr_err("gpio%d: Memory allocation failed\n", id);
-		return -ENOMEM;
-	}
-
-	dev_attr = (struct omap_gpio_dev_attr *)oh->dev_attr;
-	pdata->bank_width = dev_attr->bank_width;
-	pdata->dbck_flag = dev_attr->dbck_flag;
-	pdata->get_context_loss_count = omap_pm_get_dev_context_loss_count;
-	pdata->regs = kzalloc(sizeof(struct omap_gpio_reg_offs), GFP_KERNEL);
-	if (!pdata->regs) {
-		pr_err("gpio%d: Memory allocation failed\n", id);
-		kfree(pdata);
-		return -ENOMEM;
-	}
-
-	switch (oh->class->rev) {
-	case 0:
-		if (id == 1)
-			/* non-wakeup GPIO pins for OMAP2 Bank1 */
-			pdata->non_wakeup_gpios = 0xe203ffc0;
-		else if (id == 2)
-			/* non-wakeup GPIO pins for OMAP2 Bank2 */
-			pdata->non_wakeup_gpios = 0x08700040;
-		/* fall through */
-
-	case 1:
-		pdata->regs->revision = OMAP24XX_GPIO_REVISION;
-		pdata->regs->direction = OMAP24XX_GPIO_OE;
-		pdata->regs->datain = OMAP24XX_GPIO_DATAIN;
-		pdata->regs->dataout = OMAP24XX_GPIO_DATAOUT;
-		pdata->regs->set_dataout = OMAP24XX_GPIO_SETDATAOUT;
-		pdata->regs->clr_dataout = OMAP24XX_GPIO_CLEARDATAOUT;
-		pdata->regs->irqstatus = OMAP24XX_GPIO_IRQSTATUS1;
-		pdata->regs->irqstatus2 = OMAP24XX_GPIO_IRQSTATUS2;
-		pdata->regs->irqenable = OMAP24XX_GPIO_IRQENABLE1;
-		pdata->regs->irqenable2 = OMAP24XX_GPIO_IRQENABLE2;
-		pdata->regs->set_irqenable = OMAP24XX_GPIO_SETIRQENABLE1;
-		pdata->regs->clr_irqenable = OMAP24XX_GPIO_CLEARIRQENABLE1;
-		pdata->regs->debounce = OMAP24XX_GPIO_DEBOUNCE_VAL;
-		pdata->regs->debounce_en = OMAP24XX_GPIO_DEBOUNCE_EN;
-		pdata->regs->ctrl = OMAP24XX_GPIO_CTRL;
-		pdata->regs->wkup_en = OMAP24XX_GPIO_WAKE_EN;
-		pdata->regs->leveldetect0 = OMAP24XX_GPIO_LEVELDETECT0;
-		pdata->regs->leveldetect1 = OMAP24XX_GPIO_LEVELDETECT1;
-		pdata->regs->risingdetect = OMAP24XX_GPIO_RISINGDETECT;
-		pdata->regs->fallingdetect = OMAP24XX_GPIO_FALLINGDETECT;
-		break;
-	case 2:
-		pdata->regs->revision = OMAP4_GPIO_REVISION;
-		pdata->regs->direction = OMAP4_GPIO_OE;
-		pdata->regs->datain = OMAP4_GPIO_DATAIN;
-		pdata->regs->dataout = OMAP4_GPIO_DATAOUT;
-		pdata->regs->set_dataout = OMAP4_GPIO_SETDATAOUT;
-		pdata->regs->clr_dataout = OMAP4_GPIO_CLEARDATAOUT;
-		pdata->regs->irqstatus_raw0 = OMAP4_GPIO_IRQSTATUSRAW0;
-		pdata->regs->irqstatus_raw1 = OMAP4_GPIO_IRQSTATUSRAW1;
-		pdata->regs->irqstatus = OMAP4_GPIO_IRQSTATUS0;
-		pdata->regs->irqstatus2 = OMAP4_GPIO_IRQSTATUS1;
-		pdata->regs->irqenable = OMAP4_GPIO_IRQSTATUSSET0;
-		pdata->regs->irqenable2 = OMAP4_GPIO_IRQSTATUSSET1;
-		pdata->regs->set_irqenable = OMAP4_GPIO_IRQSTATUSSET0;
-		pdata->regs->clr_irqenable = OMAP4_GPIO_IRQSTATUSCLR0;
-		pdata->regs->debounce = OMAP4_GPIO_DEBOUNCINGTIME;
-		pdata->regs->debounce_en = OMAP4_GPIO_DEBOUNCENABLE;
-		pdata->regs->ctrl = OMAP4_GPIO_CTRL;
-		pdata->regs->wkup_en = OMAP4_GPIO_IRQWAKEN0;
-		pdata->regs->leveldetect0 = OMAP4_GPIO_LEVELDETECT0;
-		pdata->regs->leveldetect1 = OMAP4_GPIO_LEVELDETECT1;
-		pdata->regs->risingdetect = OMAP4_GPIO_RISINGDETECT;
-		pdata->regs->fallingdetect = OMAP4_GPIO_FALLINGDETECT;
-		break;
-	default:
-		WARN(1, "Invalid gpio bank_type\n");
-		kfree(pdata->regs);
-		kfree(pdata);
-		return -EINVAL;
-	}
-
-	pwrdm = omap_hwmod_get_pwrdm(oh);
-	pdata->loses_context = pwrdm_can_ever_lose_context(pwrdm);
-
-	pdev = omap_device_build(name, id - 1, oh, pdata, sizeof(*pdata));
-	kfree(pdata);
-
-	if (IS_ERR(pdev)) {
-		WARN(1, "Can't build omap_device for %s:%s.\n",
-					name, oh->name);
-		return PTR_ERR(pdev);
-	}
-
-	return 0;
-}
-
-/*
- * gpio_init needs to be done before
- * machine_init functions access gpio APIs.
- * Hence gpio_init is a omap_postcore_initcall.
- */
-static int __init omap2_gpio_init(void)
-{
-	/* If dtb is there, the devices will be created dynamically */
-	if (of_have_populated_dt())
-		return -ENODEV;
-
-	return omap_hwmod_for_each_by_class("gpio", omap2_gpio_dev_init, NULL);
-}
-omap_postcore_initcall(omap2_gpio_init);
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 759e1d4..e8b9887 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -741,14 +741,14 @@
 	int ret = 0;
 	char name[MOD_CLK_MAX_NAME_LEN];
 	struct clk *clk;
+	static const char modck[] = "_mod_ck";
 
-	/* +7 magic comes from '_mod_ck' suffix */
-	if (strlen(oh->name) + 7 > MOD_CLK_MAX_NAME_LEN)
+	if (strlen(oh->name) >= MOD_CLK_MAX_NAME_LEN - strlen(modck))
 		pr_warn("%s: warning: cropping name for %s\n", __func__,
 			oh->name);
 
-	strncpy(name, oh->name, MOD_CLK_MAX_NAME_LEN - 7);
-	strcat(name, "_mod_ck");
+	strlcpy(name, oh->name, MOD_CLK_MAX_NAME_LEN - strlen(modck));
+	strlcat(name, modck, MOD_CLK_MAX_NAME_LEN);
 
 	clk = clk_get(NULL, name);
 	if (!IS_ERR(clk)) {
diff --git a/arch/arm/mach-omap2/omap_hwmod_common_data.h b/arch/arm/mach-omap2/omap_hwmod_common_data.h
index cdfbb44..f22e9cb 100644
--- a/arch/arm/mach-omap2/omap_hwmod_common_data.h
+++ b/arch/arm/mach-omap2/omap_hwmod_common_data.h
@@ -121,10 +121,6 @@
 extern struct omap_hwmod_irq_info omap2_dispc_irqs[];
 extern struct omap_hwmod_irq_info omap2_i2c1_mpu_irqs[];
 extern struct omap_hwmod_irq_info omap2_i2c2_mpu_irqs[];
-extern struct omap_hwmod_irq_info omap2_gpio1_irqs[];
-extern struct omap_hwmod_irq_info omap2_gpio2_irqs[];
-extern struct omap_hwmod_irq_info omap2_gpio3_irqs[];
-extern struct omap_hwmod_irq_info omap2_gpio4_irqs[];
 extern struct omap_hwmod_irq_info omap2_dma_system_irqs[];
 extern struct omap_hwmod_irq_info omap2_mcspi1_mpu_irqs[];
 extern struct omap_hwmod_irq_info omap2_mcspi2_mpu_irqs[];
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 5b2f513..2b138b6 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -295,10 +295,8 @@
 		GFP_KERNEL);
 
 	if (!prcm_irq_chips || !prcm_irq_setup->saved_mask ||
-	    !prcm_irq_setup->priority_mask) {
-		pr_err("PRCM: kzalloc failed\n");
+	    !prcm_irq_setup->priority_mask)
 		goto err;
-	}
 
 	memset(mask, 0, sizeof(mask));
 
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 56128da..07dd692 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -510,18 +510,19 @@
 }
 #endif /* CONFIG_ARCH_OMAP3 */
 
-#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM33XX)
+#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM33XX) || \
+	defined(CONFIG_SOC_AM43XX)
 void __init omap3_gptimer_timer_init(void)
 {
 	__omap_sync32k_timer_init(2, "timer_sys_ck", NULL,
 			1, "timer_sys_ck", "ti,timer-alwon", true);
-
-	clocksource_probe();
+	if (of_have_populated_dt())
+		clocksource_probe();
 }
 #endif
 
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) ||		\
-	defined(CONFIG_SOC_DRA7XX) || defined(CONFIG_SOC_AM43XX)
+	defined(CONFIG_SOC_DRA7XX)
 static void __init omap4_sync32k_timer_init(void)
 {
 	__omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon",
diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index f6c3f15..b59f4f4 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -345,10 +345,40 @@
 	[DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 3), },
 };
 
+static const struct dma_slave_map s3c2410_dma_slave_map[] = {
+	{ "s3c2410-sdi", "rx-tx", (void *)DMACH_SDI },
+	{ "s3c2410-spi.0", "rx", (void *)DMACH_SPI0_RX },
+	{ "s3c2410-spi.0", "tx", (void *)DMACH_SPI0_TX },
+	{ "s3c2410-spi.1", "rx", (void *)DMACH_SPI1_RX },
+	{ "s3c2410-spi.1", "tx", (void *)DMACH_SPI1_TX },
+	/*
+	 * The DMA request source[1] (DMACH_UARTx_SRC2) are
+	 * not used in the UART driver.
+	 */
+	{ "s3c2410-uart.0", "rx", (void *)DMACH_UART0 },
+	{ "s3c2410-uart.0", "tx", (void *)DMACH_UART0 },
+	{ "s3c2410-uart.1", "rx", (void *)DMACH_UART1 },
+	{ "s3c2410-uart.1", "tx", (void *)DMACH_UART1 },
+	{ "s3c2410-uart.2", "rx", (void *)DMACH_UART2 },
+	{ "s3c2410-uart.2", "tx", (void *)DMACH_UART2 },
+	{ "s3c24xx-iis", "rx", (void *)DMACH_I2S_IN },
+	{ "s3c24xx-iis", "tx", (void *)DMACH_I2S_OUT },
+	{ "s3c-hsudc", "rx0", (void *)DMACH_USB_EP1 },
+	{ "s3c-hsudc", "tx0", (void *)DMACH_USB_EP1 },
+	{ "s3c-hsudc", "rx1", (void *)DMACH_USB_EP2 },
+	{ "s3c-hsudc", "tx1", (void *)DMACH_USB_EP2 },
+	{ "s3c-hsudc", "rx2", (void *)DMACH_USB_EP3 },
+	{ "s3c-hsudc", "tx2", (void *)DMACH_USB_EP3 },
+	{ "s3c-hsudc", "rx3", (void *)DMACH_USB_EP4 },
+	{ "s3c-hsudc", "tx3", (void *)DMACH_USB_EP4 }
+};
+
 static struct s3c24xx_dma_platdata s3c2410_dma_platdata = {
 	.num_phy_channels = 4,
 	.channels = s3c2410_dma_channels,
 	.num_channels = DMACH_MAX,
+	.slave_map = s3c2410_dma_slave_map,
+	.slavecnt = ARRAY_SIZE(s3c2410_dma_slave_map),
 };
 
 struct platform_device s3c2410_device_dma = {
@@ -388,10 +418,36 @@
 	[DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, 16 },
 };
 
+static const struct dma_slave_map s3c2412_dma_slave_map[] = {
+	{ "s3c2412-sdi", "rx-tx", (void *)DMACH_SDI },
+	{ "s3c2412-spi.0", "rx", (void *)DMACH_SPI0_RX },
+	{ "s3c2412-spi.0", "tx", (void *)DMACH_SPI0_TX },
+	{ "s3c2412-spi.1", "rx", (void *)DMACH_SPI1_RX },
+	{ "s3c2412-spi.1", "tx", (void *)DMACH_SPI1_TX },
+	{ "s3c2440-uart.0", "rx", (void *)DMACH_UART0 },
+	{ "s3c2440-uart.0", "tx", (void *)DMACH_UART0 },
+	{ "s3c2440-uart.1", "rx", (void *)DMACH_UART1 },
+	{ "s3c2440-uart.1", "tx", (void *)DMACH_UART1 },
+	{ "s3c2440-uart.2", "rx", (void *)DMACH_UART2 },
+	{ "s3c2440-uart.2", "tx", (void *)DMACH_UART2 },
+	{ "s3c2412-iis", "rx", (void *)DMACH_I2S_IN },
+	{ "s3c2412-iis", "tx", (void *)DMACH_I2S_OUT },
+	{ "s3c-hsudc", "rx0", (void *)DMACH_USB_EP1 },
+	{ "s3c-hsudc", "tx0", (void *)DMACH_USB_EP1 },
+	{ "s3c-hsudc", "rx1", (void *)DMACH_USB_EP2 },
+	{ "s3c-hsudc", "tx1", (void *)DMACH_USB_EP2 },
+	{ "s3c-hsudc", "rx2", (void *)DMACH_USB_EP3 },
+	{ "s3c-hsudc", "tx2", (void *)DMACH_USB_EP3 },
+	{ "s3c-hsudc", "rx3", (void *)DMACH_USB_EP4 },
+	{ "s3c-hsudc", "tx3", (void *)DMACH_USB_EP4 }
+};
+
 static struct s3c24xx_dma_platdata s3c2412_dma_platdata = {
 	.num_phy_channels = 4,
 	.channels = s3c2412_dma_channels,
 	.num_channels = DMACH_MAX,
+	.slave_map = s3c2412_dma_slave_map,
+	.slavecnt = ARRAY_SIZE(s3c2412_dma_slave_map),
 };
 
 struct platform_device s3c2412_device_dma = {
@@ -534,10 +590,30 @@
 	[DMACH_MIC_IN] = { S3C24XX_DMA_APB, true, 29 },
 };
 
+static const struct dma_slave_map s3c2443_dma_slave_map[] = {
+	{ "s3c2440-sdi", "rx-tx", (void *)DMACH_SDI },
+	{ "s3c2443-spi.0", "rx", (void *)DMACH_SPI0_RX },
+	{ "s3c2443-spi.0", "tx", (void *)DMACH_SPI0_TX },
+	{ "s3c2443-spi.1", "rx", (void *)DMACH_SPI1_RX },
+	{ "s3c2443-spi.1", "tx", (void *)DMACH_SPI1_TX },
+	{ "s3c2440-uart.0", "rx", (void *)DMACH_UART0 },
+	{ "s3c2440-uart.0", "tx", (void *)DMACH_UART0 },
+	{ "s3c2440-uart.1", "rx", (void *)DMACH_UART1 },
+	{ "s3c2440-uart.1", "tx", (void *)DMACH_UART1 },
+	{ "s3c2440-uart.2", "rx", (void *)DMACH_UART2 },
+	{ "s3c2440-uart.2", "tx", (void *)DMACH_UART2 },
+	{ "s3c2440-uart.3", "rx", (void *)DMACH_UART3 },
+	{ "s3c2440-uart.3", "tx", (void *)DMACH_UART3 },
+	{ "s3c24xx-iis", "rx", (void *)DMACH_I2S_IN },
+	{ "s3c24xx-iis", "tx", (void *)DMACH_I2S_OUT },
+};
+
 static struct s3c24xx_dma_platdata s3c2443_dma_platdata = {
 	.num_phy_channels = 6,
 	.channels = s3c2443_dma_channels,
 	.num_channels = DMACH_MAX,
+	.slave_map = s3c2443_dma_slave_map,
+	.slavecnt = ARRAY_SIZE(s3c2443_dma_slave_map),
 };
 
 struct platform_device s3c2443_device_dma = {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index fc033c0..eada0b5 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -356,5 +356,21 @@
 				status = "disabled";
 			};
 		};
+
+		vpu: vpu@d0100000 {
+			compatible = "amlogic,meson-gx-vpu";
+			reg = <0x0 0xd0100000 0x0 0x100000>,
+			      <0x0 0xc883c000 0x0 0x1000>,
+			      <0x0 0xc8838000 0x0 0x1000>;
+			reg-names = "vpu", "hhi", "dmc";
+			interrupts = <GIC_SPI 3 IRQ_TYPE_EDGE_RISING>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* CVBS VDAC output port */
+			cvbs_vdac_port: port@0 {
+				reg = <0>;
+			};
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
index 9696820..4cbd626 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
@@ -142,6 +142,16 @@
 		clocks = <&wifi32k>;
 		clock-names = "ext_clock";
 	};
+
+	cvbs-connector {
+		compatible = "composite-video-connector";
+
+		port {
+			cvbs_connector_in: endpoint {
+				remote-endpoint = <&cvbs_vdac_out>;
+			};
+		};
+	};
 };
 
 &uart_AO {
@@ -229,3 +239,9 @@
 	clocks = <&clkc CLKID_FCLK_DIV4>;
 	clock-names = "clkin0";
 };
+
+&cvbs_vdac_port {
+	cvbs_vdac_out: endpoint {
+		remote-endpoint = <&cvbs_connector_in>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
index 203be28..4a96e0f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
@@ -125,6 +125,16 @@
 		clocks = <&wifi32k>;
 		clock-names = "ext_clock";
 	};
+
+	cvbs-connector {
+		compatible = "composite-video-connector";
+
+		port {
+			cvbs_connector_in: endpoint {
+				remote-endpoint = <&cvbs_vdac_out>;
+			};
+		};
+	};
 };
 
 /* This UART is brought out to the DB9 connector */
@@ -234,3 +244,9 @@
 	clocks = <&clkc CLKID_FCLK_DIV4>;
 	clock-names = "clkin0";
 };
+
+&cvbs_vdac_port {
+	cvbs_vdac_out: endpoint {
+		remote-endpoint = <&cvbs_connector_in>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 51edd5b5..596240c 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -506,3 +506,7 @@
 		 <&clkc CLKID_FCLK_DIV2>;
 	clock-names = "core", "clkin0", "clkin1";
 };
+
+&vpu {
+	compatible = "amlogic,meson-gxbb-vpu", "amlogic,meson-gx-vpu";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-nexbox-a95x.dts
index e99101a..cea4a3e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-nexbox-a95x.dts
@@ -117,6 +117,16 @@
 		clocks = <&wifi32k>;
 		clock-names = "ext_clock";
 	};
+
+	cvbs-connector {
+		compatible = "composite-video-connector";
+
+		port {
+			cvbs_connector_in: endpoint {
+				remote-endpoint = <&cvbs_vdac_out>;
+			};
+		};
+	};
 };
 
 &uart_AO {
@@ -203,3 +213,9 @@
 	clocks = <&clkc CLKID_FCLK_DIV4>;
 	clock-names = "clkin0";
 };
+
+&cvbs_vdac_port {
+	cvbs_vdac_out: endpoint {
+		remote-endpoint = <&cvbs_connector_in>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 9f89b99..6921624 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -43,7 +43,7 @@
 
 #include "meson-gx.dtsi"
 #include <dt-bindings/clock/gxbb-clkc.h>
-#include <dt-bindings/gpio/meson-gxbb-gpio.h>
+#include <dt-bindings/gpio/meson-gxl-gpio.h>
 
 / {
 	compatible = "amlogic,meson-gxl";
@@ -299,3 +299,7 @@
 		 <&clkc CLKID_FCLK_DIV2>;
 	clock-names = "core", "clkin0", "clkin1";
 };
+
+&vpu {
+	compatible = "amlogic,meson-gxl-vpu", "amlogic,meson-gx-vpu";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
index f859d75..5a337d3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
@@ -90,6 +90,16 @@
 		compatible = "mmc-pwrseq-emmc";
 		reset-gpios = <&gpio BOOT_9 GPIO_ACTIVE_LOW>;
 	};
+
+	cvbs-connector {
+		compatible = "composite-video-connector";
+
+		port {
+			cvbs_connector_in: endpoint {
+				remote-endpoint = <&cvbs_vdac_out>;
+			};
+		};
+	};
 };
 
 /* This UART is brought out to the DB9 connector */
@@ -167,3 +177,9 @@
 		max-speed = <1000>;
 	};
 };
+
+&cvbs_vdac_port {
+	cvbs_vdac_out: endpoint {
+		remote-endpoint = <&cvbs_connector_in>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
index c1974bb..eb2f0c3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
@@ -112,3 +112,7 @@
 		};
 	};
 };
+
+&vpu {
+	compatible = "amlogic,meson-gxm-vpu", "amlogic,meson-gx-vpu";
+};
diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts
index a852e28..a83ed2c 100644
--- a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts
+++ b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts
@@ -81,7 +81,7 @@
 		#address-cells = <0>;
 		interrupt-controller;
 		reg = <0x0 0x2c001000 0 0x1000>,
-		      <0x0 0x2c002000 0 0x1000>,
+		      <0x0 0x2c002000 0 0x2000>,
 		      <0x0 0x2c004000 0 0x2000>,
 		      <0x0 0x2c006000 0 0x2000>;
 		interrupts = <1 9 0xf04>;
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 9d1d7ad..29ed6b6 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -64,6 +64,16 @@
 			reg = <0x0 0x86000000 0x0 0x200000>;
 			no-map;
 		};
+
+		memory@85800000 {
+			reg = <0x0 0x85800000 0x0 0x800000>;
+			no-map;
+		};
+
+		memory@86200000 {
+			reg = <0x0 0x86200000 0x0 0x2600000>;
+			no-map;
+		};
 	};
 
 	cpus {
diff --git a/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts b/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts
index 6ffb051..dbea2c3 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts
@@ -169,7 +169,7 @@
 		power-source = <3300>;
 	};
 
-	sdhi0_pins_uhs: sd0 {
+	sdhi0_pins_uhs: sd0_uhs {
 		groups = "sdhi0_data4", "sdhi0_ctrl";
 		function = "sdhi0";
 		power-source = <1800>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 869dded..33b744d 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -331,6 +331,7 @@
 CONFIG_DRM_PANEL_SIMPLE=m
 CONFIG_DRM_I2C_ADV7511=m
 CONFIG_DRM_HISI_KIRIN=m
+CONFIG_DRM_MESON=m
 CONFIG_FB=y
 CONFIG_FB_ARMCLCD=y
 CONFIG_BACKLIGHT_GENERIC=m
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
new file mode 100644
index 0000000..df411f3
--- /dev/null
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -0,0 +1,65 @@
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	.macro	__uaccess_ttbr0_disable, tmp1
+	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
+	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
+	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
+	isb
+	.endm
+
+	.macro	__uaccess_ttbr0_enable, tmp1
+	get_thread_info \tmp1
+	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
+	isb
+	.endm
+
+	.macro	uaccess_ttbr0_disable, tmp1
+alternative_if_not ARM64_HAS_PAN
+	__uaccess_ttbr0_disable \tmp1
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1
+	restore_irq \tmp2
+alternative_else_nop_endif
+	.endm
+#else
+	.macro	uaccess_ttbr0_disable, tmp1
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.endm
+#endif
+
+/*
+ * These macros are no-ops when UAO is present.
+ */
+	.macro	uaccess_disable_not_uao, tmp1
+	uaccess_ttbr0_disable \tmp1
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_enable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_enable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+	.endm
+
+#endif
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
index f2bcbe2..86c4041 100644
--- a/arch/arm64/include/asm/current.h
+++ b/arch/arm64/include/asm/current.h
@@ -9,9 +9,17 @@
 
 struct task_struct;
 
+/*
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
+ */
 static __always_inline struct task_struct *get_current(void)
 {
-	return (struct task_struct *)read_sysreg(sp_el0);
+	unsigned long sp_el0;
+
+	asm ("mrs %0, sp_el0" : "=r" (sp_el0));
+
+	return (struct task_struct *)sp_el0;
 }
 
 #define current get_current()
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index d26750c..46da3ea 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -22,8 +22,6 @@
 #include <asm/kernel-pgtable.h>
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
-
 /*
  * User space memory access functions
  */
@@ -424,66 +422,4 @@
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-#else	/* __ASSEMBLY__ */
-
-#include <asm/assembler.h>
-
-/*
- * User access enabling/disabling macros.
- */
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-	.macro	__uaccess_ttbr0_disable, tmp1
-	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
-	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
-	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
-	isb
-	.endm
-
-	.macro	__uaccess_ttbr0_enable, tmp1
-	get_thread_info \tmp1
-	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
-	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
-	isb
-	.endm
-
-	.macro	uaccess_ttbr0_disable, tmp1
-alternative_if_not ARM64_HAS_PAN
-	__uaccess_ttbr0_disable \tmp1
-alternative_else_nop_endif
-	.endm
-
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
-alternative_if_not ARM64_HAS_PAN
-	save_and_disable_irq \tmp2		// avoid preemption
-	__uaccess_ttbr0_enable \tmp1
-	restore_irq \tmp2
-alternative_else_nop_endif
-	.endm
-#else
-	.macro	uaccess_ttbr0_disable, tmp1
-	.endm
-
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
-	.endm
-#endif
-
-/*
- * These macros are no-ops when UAO is present.
- */
-	.macro	uaccess_disable_not_uao, tmp1
-	uaccess_ttbr0_disable \tmp1
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(1)
-alternative_else_nop_endif
-	.endm
-
-	.macro	uaccess_enable_not_uao, tmp1, tmp2
-	uaccess_ttbr0_enable \tmp1, \tmp2
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(0)
-alternative_else_nop_endif
-	.endm
-
-#endif	/* __ASSEMBLY__ */
-
 #endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a7504f4..923841f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -31,7 +31,7 @@
 #include <asm/memory.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
 
 /*
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index add4a13..e88fb99 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -17,7 +17,7 @@
  */
 #include <linux/linkage.h>
 
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 	.text
 
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index fd6cd055..4b5d826 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -17,7 +17,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index d828540..47184c3 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -19,7 +19,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 3e6ae26..351f076 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -17,7 +17,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 17f422a..83c27b6e 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -23,7 +23,7 @@
 #include <asm/assembler.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  *	flush_icache_range(start,end)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 290a84f..e040827 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -524,7 +524,8 @@
 
 static int __init arm64_dma_init(void)
 {
-	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	if (swiotlb_force == SWIOTLB_FORCE ||
+	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
 		swiotlb = 1;
 
 	return atomic_pool_init();
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index a78a5c4..156169c 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -88,21 +88,21 @@
 			break;
 
 		pud = pud_offset(pgd, addr);
-		printk(", *pud=%016llx", pud_val(*pud));
+		pr_cont(", *pud=%016llx", pud_val(*pud));
 		if (pud_none(*pud) || pud_bad(*pud))
 			break;
 
 		pmd = pmd_offset(pud, addr);
-		printk(", *pmd=%016llx", pmd_val(*pmd));
+		pr_cont(", *pmd=%016llx", pmd_val(*pmd));
 		if (pmd_none(*pmd) || pmd_bad(*pmd))
 			break;
 
 		pte = pte_offset_map(pmd, addr);
-		printk(", *pte=%016llx", pte_val(*pte));
+		pr_cont(", *pte=%016llx", pte_val(*pte));
 		pte_unmap(pte);
 	} while(0);
 
-	printk("\n");
+	pr_cont("\n");
 }
 
 #ifdef CONFIG_ARM64_HW_AFDBM
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 212c4d1..716d122 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -401,7 +401,8 @@
  */
 void __init mem_init(void)
 {
-	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	if (swiotlb_force == SWIOTLB_FORCE ||
+	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
 		swiotlb_init(1);
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 47cf3f9..947830a 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -49,7 +49,7 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <xen/interface/xen.h>
 
 
diff --git a/arch/mips/kvm/entry.c b/arch/mips/kvm/entry.c
index 6a02b3a..e92fb19 100644
--- a/arch/mips/kvm/entry.c
+++ b/arch/mips/kvm/entry.c
@@ -521,6 +521,9 @@
 	uasm_i_and(&p, V0, V0, AT);
 	uasm_i_lui(&p, AT, ST0_CU0 >> 16);
 	uasm_i_or(&p, V0, V0, AT);
+#ifdef CONFIG_64BIT
+	uasm_i_ori(&p, V0, V0, ST0_SX | ST0_UX);
+#endif
 	uasm_i_mtc0(&p, V0, C0_STATUS);
 	uasm_i_ehb(&p);
 
@@ -643,7 +646,7 @@
 
 	/* Setup status register for running guest in UM */
 	uasm_i_ori(&p, V1, V1, ST0_EXL | KSU_USER | ST0_IE);
-	UASM_i_LA(&p, AT, ~(ST0_CU0 | ST0_MX));
+	UASM_i_LA(&p, AT, ~(ST0_CU0 | ST0_MX | ST0_SX | ST0_UX));
 	uasm_i_and(&p, V1, V1, AT);
 	uasm_i_mtc0(&p, V1, C0_STATUS);
 	uasm_i_ehb(&p);
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 06a60b1..29ec9ab 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -360,8 +360,8 @@
 	dump_handler("kvm_exit", gebase + 0x2000, vcpu->arch.vcpu_run);
 
 	/* Invalidate the icache for these ranges */
-	local_flush_icache_range((unsigned long)gebase,
-				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
+	flush_icache_range((unsigned long)gebase,
+			   (unsigned long)gebase + ALIGN(size, PAGE_SIZE));
 
 	/*
 	 * Allocate comm page for guest kernel, a TLB will be reserved for
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index ef31fc2..5525446 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -44,6 +44,8 @@
         /* Read-only sections, merged into text segment: */
         . = LOAD_BASE ;
 
+	_text = .;
+
 	/* _s_kernel_ro must be page aligned */
 	. = ALIGN(PAGE_SIZE);
 	_s_kernel_ro = .;
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index 7581330e..88fe0aa 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -49,7 +49,6 @@
 #define TIF_POLLING_NRFLAG	3	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_32BIT               4       /* 32 bit binary */
 #define TIF_MEMDIE		5	/* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK	6	/* restore saved signal mask */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_NOTIFY_RESUME	8	/* callback before returning to user */
 #define TIF_SINGLESTEP		9	/* single stepping? */
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index da0d9cb..1e22f98 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -235,9 +235,26 @@
 
 	cr16_hz = 100 * PAGE0->mem_10msec;  /* Hz */
 
-	/* register at clocksource framework */
-	clocksource_register_hz(&clocksource_cr16, cr16_hz);
-
 	/* register as sched_clock source */
 	sched_clock_register(read_cr16_sched_clock, BITS_PER_LONG, cr16_hz);
 }
+
+static int __init init_cr16_clocksource(void)
+{
+	/*
+	 * The cr16 interval timers are not syncronized across CPUs, so mark
+	 * them unstable and lower rating on SMP systems.
+	 */
+	if (num_online_cpus() > 1) {
+		clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
+		clocksource_cr16.rating = 0;
+	}
+
+	/* register at clocksource framework */
+	clocksource_register_hz(&clocksource_cr16,
+		100 * PAGE0->mem_10msec);
+
+	return 0;
+}
+
+device_initcall(init_cr16_clocksource);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 8ff9253..1a0b4f6 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -234,7 +234,7 @@
 	    tsk->comm, code, address);
 	print_vma_addr(KERN_CONT " in ", regs->iaoq[0]);
 
-	pr_cont(" trap #%lu: %s%c", code, trap_name(code),
+	pr_cont("\ntrap #%lu: %s%c", code, trap_name(code),
 		vma ? ',':'\n');
 
 	if (vma)
diff --git a/arch/s390/include/asm/asm-prototypes.h b/arch/s390/include/asm/asm-prototypes.h
new file mode 100644
index 0000000..2c3413b
--- /dev/null
+++ b/arch/s390/include/asm/asm-prototypes.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_S390_PROTOTYPES_H
+
+#include <linux/kvm_host.h>
+#include <linux/ftrace.h>
+#include <asm/fpu/api.h>
+#include <asm-generic/asm-prototypes.h>
+
+#endif /* _ASM_S390_PROTOTYPES_H */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 6b246aa..1b5c5ee 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -94,7 +94,7 @@
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
  */
-static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
+static int do_account_vtime(struct task_struct *tsk)
 {
 	u64 timer, clock, user, system, steal;
 	u64 user_scaled, system_scaled;
@@ -138,7 +138,7 @@
 	}
 	account_user_time(tsk, user);
 	tsk->utimescaled += user_scaled;
-	account_system_time(tsk, hardirq_offset, system);
+	account_system_time(tsk, 0, system);
 	tsk->stimescaled += system_scaled;
 
 	steal = S390_lowcore.steal_timer;
@@ -152,7 +152,7 @@
 
 void vtime_task_switch(struct task_struct *prev)
 {
-	do_account_vtime(prev, 0);
+	do_account_vtime(prev);
 	prev->thread.user_timer = S390_lowcore.user_timer;
 	prev->thread.system_timer = S390_lowcore.system_timer;
 	S390_lowcore.user_timer = current->thread.user_timer;
@@ -166,7 +166,7 @@
  */
 void vtime_account_user(struct task_struct *tsk)
 {
-	if (do_account_vtime(tsk, HARDIRQ_OFFSET))
+	if (do_account_vtime(tsk))
 		virt_timer_expire();
 }
 
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 68557f52..8540227 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -139,6 +139,19 @@
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
 
+static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+	bool negative;
+	asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+		CC_SET(s)
+		: CC_OUT(s) (negative), ADDR
+		: "ir" ((char) ~(1 << nr)) : "memory");
+	return negative;
+}
+
+// Let everybody know we have it
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+
 /*
  * __clear_bit_unlock - Clears a bit in memory
  * @nr: Bit to clear
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ffacfdc..a5fd137 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1182,6 +1182,9 @@
 	const char *name = get_name(bank, NULL);
 	int err = 0;
 
+	if (!dev)
+		return -ENODEV;
+
 	if (is_shared_bank(bank)) {
 		nb = node_to_amd_nb(amd_get_nb_id(cpu));
 
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index b47edb8..410efb2 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -68,12 +68,10 @@
  */
 int __init pci_swiotlb_detect_override(void)
 {
-	int use_swiotlb = swiotlb | swiotlb_force;
-
-	if (swiotlb_force)
+	if (swiotlb_force == SWIOTLB_FORCE)
 		swiotlb = 1;
 
-	return use_swiotlb;
+	return swiotlb;
 }
 IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
 		  pci_xen_swiotlb_detect,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 24db5fb..a236dec 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -132,12 +132,6 @@
 
 #define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
 
-#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
-	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
-	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
-	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
-	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
-
 /*
  * Hyper-V requires all of these, so mark them as supported even though
  * they are just treated the same as all-context.
@@ -10473,12 +10467,12 @@
 	    !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) {
 		nested_vmx_entry_failure(vcpu, vmcs12,
 			EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
-		goto out;
+		return 1;
 	}
 	if (vmcs12->vmcs_link_pointer != -1ull) {
 		nested_vmx_entry_failure(vcpu, vmcs12,
 			EXIT_REASON_INVALID_STATE, ENTRY_FAIL_VMCS_LINK_PTR);
-		goto out;
+		return 1;
 	}
 
 	/*
@@ -10498,7 +10492,7 @@
 		     ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) {
 			nested_vmx_entry_failure(vcpu, vmcs12,
 				EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
-			goto out;
+			return 1;
 		}
 	}
 
@@ -10516,7 +10510,7 @@
 		    ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) {
 			nested_vmx_entry_failure(vcpu, vmcs12,
 				EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
-			goto out;
+			return 1;
 		}
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 51ccfe0..2f22810 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3070,6 +3070,8 @@
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
 {
@@ -3106,10 +3108,13 @@
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+		u32 hflags = vcpu->arch.hflags;
 		if (events->smi.smm)
-			vcpu->arch.hflags |= HF_SMM_MASK;
+			hflags |= HF_SMM_MASK;
 		else
-			vcpu->arch.hflags &= ~HF_SMM_MASK;
+			hflags &= ~HF_SMM_MASK;
+		kvm_set_hflags(vcpu, hflags);
+
 		vcpu->arch.smi_pending = events->smi.pending;
 		if (events->smi.smm_inside_nmi)
 			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index a9fafb5..a0b36a9 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -48,7 +48,7 @@
 	 * activate this IOMMU. If running as PV privileged, activate it
 	 * irregardless.
 	 */
-	if ((xen_initial_domain() || swiotlb || swiotlb_force))
+	if (xen_initial_domain() || swiotlb || swiotlb_force == SWIOTLB_FORCE)
 		xen_swiotlb = 1;
 
 	/* If we are running under Xen, we MUST disable the native SWIOTLB.
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 8c394e30..f3f7b41 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -713,10 +713,9 @@
 		size = PFN_PHYS(xen_start_info->nr_p2m_frames);
 	}
 
-	if (!xen_is_e820_reserved(start, size)) {
-		memblock_reserve(start, size);
+	memblock_reserve(start, size);
+	if (!xen_is_e820_reserved(start, size))
 		return;
-	}
 
 #ifdef CONFIG_X86_32
 	/*
@@ -727,6 +726,7 @@
 	BUG();
 #else
 	xen_relocate_p2m();
+	memblock_free(start, size);
 #endif
 }
 
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 6e82769..f0a9c07 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -544,6 +544,8 @@
  * the timer to kick off queuing again.
  */
 static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock)
+	__releases(lock)
+	__acquires(lock)
 {
 	struct rq_wait *rqw = get_rq_wait(rwb, current_is_kswapd());
 	DEFINE_WAIT(wait);
@@ -558,13 +560,12 @@
 		if (may_queue(rwb, rqw, &wait, rw))
 			break;
 
-		if (lock)
+		if (lock) {
 			spin_unlock_irq(lock);
-
-		io_schedule();
-
-		if (lock)
+			io_schedule();
 			spin_lock_irq(lock);
+		} else
+			io_schedule();
 	} while (1);
 
 	finish_wait(&rqw->wait, &wait);
@@ -595,7 +596,7 @@
  * in an irq held spinlock, if it holds one when calling this function.
  * If we do sleep, we'll release and re-grab it.
  */
-unsigned int wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
+enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 {
 	unsigned int ret = 0;
 
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f616ad7..44e888b 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1461,16 +1461,25 @@
 	for (i = 0; i < ctcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = ctemplate[i].inlen;
+		void *input_vec;
 
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(input_vec, ctemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, ctemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1483,6 +1492,7 @@
 		if (ret) {
 			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1491,6 +1501,7 @@
 			pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1500,26 +1511,37 @@
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 
 	for (i = 0; i < dtcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = dtemplate[i].inlen;
+		void *input_vec;
 
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(input_vec, dtemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, dtemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1532,6 +1554,7 @@
 		if (ret) {
 			pr_err("alg: acomp: decompression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1540,6 +1563,7 @@
 			pr_err("alg: acomp: Decompression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1549,10 +1573,12 @@
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 
diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c
index 13caebd..8c4e0a1 100644
--- a/drivers/acpi/acpi_watchdog.c
+++ b/drivers/acpi/acpi_watchdog.c
@@ -114,7 +114,7 @@
 	pdev = platform_device_register_simple("wdat_wdt", PLATFORM_DEVID_NONE,
 					       resources, nresources);
 	if (IS_ERR(pdev))
-		pr_err("Failed to create platform device\n");
+		pr_err("Device creation failed: %ld\n", PTR_ERR(pdev));
 
 	kfree(resources);
 
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index f8d6564..fb19e1c 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -98,7 +98,15 @@
 	if (check_children && list_empty(&adev->children))
 		return -ENODEV;
 
-	return sta_present ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
+	/*
+	 * If the device has a _HID (or _CID) returning a valid ACPI/PNP
+	 * device ID, it is better to make it look less attractive here, so that
+	 * the other device with the same _ADR value (that may not have a valid
+	 * device ID) can be matched going forward.  [This means a second spec
+	 * violation in a row, so whatever we do here is best effort anyway.]
+	 */
+	return sta_present && list_empty(&adev->pnp.ids) ?
+			FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
 }
 
 struct acpi_device *acpi_find_child_device(struct acpi_device *parent,
@@ -250,7 +258,6 @@
 	return 0;
 
  err:
-	acpi_dma_deconfigure(dev);
 	ACPI_COMPANION_SET(dev, NULL);
 	put_device(dev);
 	put_device(&acpi_dev->dev);
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 1b41a27..0c45226 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -37,6 +37,7 @@
 static inline void acpi_amba_init(void) {}
 #endif
 int acpi_sysfs_init(void);
+void acpi_gpe_apply_masked_gpes(void);
 void acpi_container_init(void);
 void acpi_memory_hotplug_init(void);
 #ifdef	CONFIG_ACPI_HOTPLUG_IOAPIC
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 45dec87..1926918 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2074,6 +2074,7 @@
 		}
 	}
 
+	acpi_gpe_apply_masked_gpes();
 	acpi_update_all_gpes();
 	acpi_ec_ecdt_start();
 
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 703c26e..cf05ae9 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -708,6 +708,62 @@
 	return result ? result : size;
 }
 
+/*
+ * A Quirk Mechanism for GPE Flooding Prevention:
+ *
+ * Quirks may be needed to prevent GPE flooding on a specific GPE. The
+ * flooding typically cannot be detected and automatically prevented by
+ * ACPI_GPE_DISPATCH_NONE check because there is a _Lxx/_Exx prepared in
+ * the AML tables. This normally indicates a feature gap in Linux, thus
+ * instead of providing endless quirk tables, we provide a boot parameter
+ * for those who want this quirk. For example, if the users want to prevent
+ * the GPE flooding for GPE 00, they need to specify the following boot
+ * parameter:
+ *   acpi_mask_gpe=0x00
+ * The masking status can be modified by the following runtime controlling
+ * interface:
+ *   echo unmask > /sys/firmware/acpi/interrupts/gpe00
+ */
+
+/*
+ * Currently, the GPE flooding prevention only supports to mask the GPEs
+ * numbered from 00 to 7f.
+ */
+#define ACPI_MASKABLE_GPE_MAX	0x80
+
+static u64 __initdata acpi_masked_gpes;
+
+static int __init acpi_gpe_set_masked_gpes(char *val)
+{
+	u8 gpe;
+
+	if (kstrtou8(val, 0, &gpe) || gpe > ACPI_MASKABLE_GPE_MAX)
+		return -EINVAL;
+	acpi_masked_gpes |= ((u64)1<<gpe);
+
+	return 1;
+}
+__setup("acpi_mask_gpe=", acpi_gpe_set_masked_gpes);
+
+void __init acpi_gpe_apply_masked_gpes(void)
+{
+	acpi_handle handle;
+	acpi_status status;
+	u8 gpe;
+
+	for (gpe = 0;
+	     gpe < min_t(u8, ACPI_MASKABLE_GPE_MAX, acpi_current_gpe_count);
+	     gpe++) {
+		if (acpi_masked_gpes & ((u64)1<<gpe)) {
+			status = acpi_get_gpe_device(gpe, &handle);
+			if (ACPI_SUCCESS(status)) {
+				pr_info("Masking GPE 0x%x.\n", gpe);
+				(void)acpi_mask_gpe(handle, gpe, TRUE);
+			}
+		}
+	}
+}
+
 void acpi_irq_stats_init(void)
 {
 	acpi_status status;
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index a5e1262..2997026 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -626,6 +626,7 @@
 
  out:
 	/* Measure resume latency. */
+	time_start = 0;
 	if (timed && runtime_pm)
 		time_start = ktime_get();
 
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
index 5eb05db..fc585f3 100644
--- a/drivers/clk/clk-stm32f4.c
+++ b/drivers/clk/clk-stm32f4.c
@@ -768,5 +768,5 @@
 	kfree(clks);
 	iounmap(base);
 }
-CLK_OF_DECLARE(stm32f42xx_rcc, "st,stm32f42xx-rcc", stm32f4_rcc_init);
-CLK_OF_DECLARE(stm32f46xx_rcc, "st,stm32f469-rcc", stm32f4_rcc_init);
+CLK_OF_DECLARE_DRIVER(stm32f42xx_rcc, "st,stm32f42xx-rcc", stm32f4_rcc_init);
+CLK_OF_DECLARE_DRIVER(stm32f46xx_rcc, "st,stm32f469-rcc", stm32f4_rcc_init);
diff --git a/drivers/clk/renesas/clk-mstp.c b/drivers/clk/renesas/clk-mstp.c
index 9375777..b533f99 100644
--- a/drivers/clk/renesas/clk-mstp.c
+++ b/drivers/clk/renesas/clk-mstp.c
@@ -37,12 +37,14 @@
  * @smstpcr: module stop control register
  * @mstpsr: module stop status register (optional)
  * @lock: protects writes to SMSTPCR
+ * @width_8bit: registers are 8-bit, not 32-bit
  */
 struct mstp_clock_group {
 	struct clk_onecell_data data;
 	void __iomem *smstpcr;
 	void __iomem *mstpsr;
 	spinlock_t lock;
+	bool width_8bit;
 };
 
 /**
@@ -59,6 +61,18 @@
 
 #define to_mstp_clock(_hw) container_of(_hw, struct mstp_clock, hw)
 
+static inline u32 cpg_mstp_read(struct mstp_clock_group *group,
+				u32 __iomem *reg)
+{
+	return group->width_8bit ? readb(reg) : clk_readl(reg);
+}
+
+static inline void cpg_mstp_write(struct mstp_clock_group *group, u32 val,
+				  u32 __iomem *reg)
+{
+	group->width_8bit ? writeb(val, reg) : clk_writel(val, reg);
+}
+
 static int cpg_mstp_clock_endisable(struct clk_hw *hw, bool enable)
 {
 	struct mstp_clock *clock = to_mstp_clock(hw);
@@ -70,12 +84,12 @@
 
 	spin_lock_irqsave(&group->lock, flags);
 
-	value = clk_readl(group->smstpcr);
+	value = cpg_mstp_read(group, group->smstpcr);
 	if (enable)
 		value &= ~bitmask;
 	else
 		value |= bitmask;
-	clk_writel(value, group->smstpcr);
+	cpg_mstp_write(group, value, group->smstpcr);
 
 	spin_unlock_irqrestore(&group->lock, flags);
 
@@ -83,7 +97,7 @@
 		return 0;
 
 	for (i = 1000; i > 0; --i) {
-		if (!(clk_readl(group->mstpsr) & bitmask))
+		if (!(cpg_mstp_read(group, group->mstpsr) & bitmask))
 			break;
 		cpu_relax();
 	}
@@ -114,9 +128,9 @@
 	u32 value;
 
 	if (group->mstpsr)
-		value = clk_readl(group->mstpsr);
+		value = cpg_mstp_read(group, group->mstpsr);
 	else
-		value = clk_readl(group->smstpcr);
+		value = cpg_mstp_read(group, group->smstpcr);
 
 	return !(value & BIT(clock->bit_index));
 }
@@ -188,6 +202,9 @@
 		return;
 	}
 
+	if (of_device_is_compatible(np, "renesas,r7s72100-mstp-clocks"))
+		group->width_8bit = true;
+
 	for (i = 0; i < MSTP_MAX_CLOCKS; ++i)
 		clks[i] = ERR_PTR(-ENOENT);
 
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index bc97b6a..7fcaf26 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -26,6 +26,8 @@
 	{ .compatible = "allwinner,sun8i-a83t", },
 	{ .compatible = "allwinner,sun8i-h3", },
 
+	{ .compatible = "apm,xgene-shadowcat", },
+
 	{ .compatible = "arm,integrator-ap", },
 	{ .compatible = "arm,integrator-cp", },
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 6acbd4a..f91c257 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -857,13 +857,13 @@
 	NULL,
 };
 
-static void intel_pstate_hwp_set(const struct cpumask *cpumask)
+static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
 {
 	int min, hw_min, max, hw_max, cpu, range, adj_range;
 	struct perf_limits *perf_limits = limits;
 	u64 value, cap;
 
-	for_each_cpu(cpu, cpumask) {
+	for_each_cpu(cpu, policy->cpus) {
 		int max_perf_pct, min_perf_pct;
 		struct cpudata *cpu_data = all_cpu_data[cpu];
 		s16 epp;
@@ -949,7 +949,7 @@
 static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy)
 {
 	if (hwp_active)
-		intel_pstate_hwp_set(policy->cpus);
+		intel_pstate_hwp_set(policy);
 
 	return 0;
 }
@@ -968,19 +968,28 @@
 
 static int intel_pstate_resume(struct cpufreq_policy *policy)
 {
+	int ret;
+
 	if (!hwp_active)
 		return 0;
 
+	mutex_lock(&intel_pstate_limits_lock);
+
 	all_cpu_data[policy->cpu]->epp_policy = 0;
 
-	return intel_pstate_hwp_set_policy(policy);
+	ret = intel_pstate_hwp_set_policy(policy);
+
+	mutex_unlock(&intel_pstate_limits_lock);
+
+	return ret;
 }
 
-static void intel_pstate_hwp_set_online_cpus(void)
+static void intel_pstate_update_policies(void)
 {
-	get_online_cpus();
-	intel_pstate_hwp_set(cpu_online_mask);
-	put_online_cpus();
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		cpufreq_update_policy(cpu);
 }
 
 /************************** debugfs begin ************************/
@@ -1018,10 +1027,6 @@
 	struct dentry *debugfs_parent;
 	int i = 0;
 
-	if (hwp_active ||
-	    pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load)
-		return;
-
 	debugfs_parent = debugfs_create_dir("pstate_snb", NULL);
 	if (IS_ERR_OR_NULL(debugfs_parent))
 		return;
@@ -1105,11 +1110,10 @@
 
 	limits->no_turbo = clamp_t(int, input, 0, 1);
 
-	if (hwp_active)
-		intel_pstate_hwp_set_online_cpus();
-
 	mutex_unlock(&intel_pstate_limits_lock);
 
+	intel_pstate_update_policies();
+
 	return count;
 }
 
@@ -1134,11 +1138,10 @@
 				   limits->max_perf_pct);
 	limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
 
-	if (hwp_active)
-		intel_pstate_hwp_set_online_cpus();
-
 	mutex_unlock(&intel_pstate_limits_lock);
 
+	intel_pstate_update_policies();
+
 	return count;
 }
 
@@ -1163,11 +1166,10 @@
 				   limits->min_perf_pct);
 	limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
 
-	if (hwp_active)
-		intel_pstate_hwp_set_online_cpus();
-
 	mutex_unlock(&intel_pstate_limits_lock);
 
+	intel_pstate_update_policies();
+
 	return count;
 }
 
@@ -2153,8 +2155,12 @@
 	if (per_cpu_limits)
 		perf_limits = cpu->perf_limits;
 
+	mutex_lock(&intel_pstate_limits_lock);
+
 	intel_pstate_update_perf_limits(policy, perf_limits);
 
+	mutex_unlock(&intel_pstate_limits_lock);
+
 	return 0;
 }
 
@@ -2487,7 +2493,10 @@
 	if (rc)
 		goto out;
 
-	intel_pstate_debug_expose_params();
+	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
+	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+		intel_pstate_debug_expose_params();
+
 	intel_pstate_sysfs_expose_params();
 
 	if (hwp_active)
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index a768da7..b7872f6 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -273,7 +273,8 @@
 #define CESA_TDMA_SRC_IN_SRAM			BIT(30)
 #define CESA_TDMA_END_OF_REQ			BIT(29)
 #define CESA_TDMA_BREAK_CHAIN			BIT(28)
-#define CESA_TDMA_TYPE_MSK			GENMASK(27, 0)
+#define CESA_TDMA_SET_STATE			BIT(27)
+#define CESA_TDMA_TYPE_MSK			GENMASK(26, 0)
 #define CESA_TDMA_DUMMY				0
 #define CESA_TDMA_DATA				1
 #define CESA_TDMA_OP				2
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 317cf02..77c0fb9 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -280,13 +280,32 @@
 	sreq->offset = 0;
 }
 
+static void mv_cesa_ahash_dma_step(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_req *base = &creq->base;
+
+	/* We must explicitly set the digest state. */
+	if (base->chain.first->flags & CESA_TDMA_SET_STATE) {
+		struct mv_cesa_engine *engine = base->engine;
+		int i;
+
+		/* Set the hash state in the IVDIG regs. */
+		for (i = 0; i < ARRAY_SIZE(creq->state); i++)
+			writel_relaxed(creq->state[i], engine->regs +
+				       CESA_IVDIG(i));
+	}
+
+	mv_cesa_dma_step(base);
+}
+
 static void mv_cesa_ahash_step(struct crypto_async_request *req)
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
 
 	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->base);
+		mv_cesa_ahash_dma_step(ahashreq);
 	else
 		mv_cesa_ahash_std_step(ahashreq);
 }
@@ -584,12 +603,16 @@
 	struct mv_cesa_ahash_dma_iter iter;
 	struct mv_cesa_op_ctx *op = NULL;
 	unsigned int frag_len;
+	bool set_state = false;
 	int ret;
 	u32 type;
 
 	basereq->chain.first = NULL;
 	basereq->chain.last = NULL;
 
+	if (!mv_cesa_mac_op_is_first_frag(&creq->op_tmpl))
+		set_state = true;
+
 	if (creq->src_nents) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
 				 DMA_TO_DEVICE);
@@ -683,6 +706,15 @@
 	if (type != CESA_TDMA_RESULT)
 		basereq->chain.last->flags |= CESA_TDMA_BREAK_CHAIN;
 
+	if (set_state) {
+		/*
+		 * Put the CESA_TDMA_SET_STATE flag on the first tdma desc to
+		 * let the step logic know that the IVDIG registers should be
+		 * explicitly set before launching a TDMA chain.
+		 */
+		basereq->chain.first->flags |= CESA_TDMA_SET_STATE;
+	}
+
 	return 0;
 
 err_free_tdma:
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
index 4416b88..c76375f 100644
--- a/drivers/crypto/marvell/tdma.c
+++ b/drivers/crypto/marvell/tdma.c
@@ -109,7 +109,14 @@
 		last->next = dreq->chain.first;
 		engine->chain.last = dreq->chain.last;
 
-		if (!(last->flags & CESA_TDMA_BREAK_CHAIN))
+		/*
+		 * Break the DMA chain if the CESA_TDMA_BREAK_CHAIN is set on
+		 * the last element of the current chain, or if the request
+		 * being queued needs the IV regs to be set before lauching
+		 * the request.
+		 */
+		if (!(last->flags & CESA_TDMA_BREAK_CHAIN) &&
+		    !(dreq->chain.first->flags & CESA_TDMA_SET_STATE))
 			last->next_dma = dreq->chain.first->cur_dma;
 	}
 }
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index a324801..47206a2 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -593,11 +593,16 @@
 	list_add(&devfreq->node, &devfreq_list);
 
 	governor = find_devfreq_governor(devfreq->governor_name);
-	if (!IS_ERR(governor))
-		devfreq->governor = governor;
-	if (devfreq->governor)
-		err = devfreq->governor->event_handler(devfreq,
-					DEVFREQ_GOV_START, NULL);
+	if (IS_ERR(governor)) {
+		dev_err(dev, "%s: Unable to find governor for the device\n",
+			__func__);
+		err = PTR_ERR(governor);
+		goto err_init;
+	}
+
+	devfreq->governor = governor;
+	err = devfreq->governor->event_handler(devfreq, DEVFREQ_GOV_START,
+						NULL);
 	if (err) {
 		dev_err(dev, "%s: Unable to start governor for the device\n",
 			__func__);
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index a8ed779..9af86f4 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -497,7 +497,7 @@
 	if (IS_ERR(bus->devfreq)) {
 		dev_err(dev,
 			"failed to add devfreq dev with passive governor\n");
-		ret = -EPROBE_DEFER;
+		ret = PTR_ERR(bus->devfreq);
 		goto err;
 	}
 
diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index 70e1323..9ad0b19 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -721,11 +721,17 @@
 
 	ret = scpi_send_message(CMD_SENSOR_VALUE, &id, sizeof(id),
 				&buf, sizeof(buf));
-	if (!ret)
+	if (ret)
+		return ret;
+
+	if (scpi_info->is_legacy)
+		/* only 32-bits supported, hi_val can be junk */
+		*val = le32_to_cpu(buf.lo_val);
+	else
 		*val = (u64)le32_to_cpu(buf.hi_val) << 32 |
 			le32_to_cpu(buf.lo_val);
 
-	return ret;
+	return 0;
 }
 
 static int scpi_device_get_power_state(u16 dev_id)
diff --git a/drivers/firmware/psci_checker.c b/drivers/firmware/psci_checker.c
index 44bdb78..29d58fe 100644
--- a/drivers/firmware/psci_checker.c
+++ b/drivers/firmware/psci_checker.c
@@ -270,8 +270,7 @@
 	struct cpuidle_device *dev;
 	struct cpuidle_driver *drv;
 	/* No need for an actual callback, we just want to wake up the CPU. */
-	struct timer_list wakeup_timer =
-		TIMER_INITIALIZER(dummy_callback, 0, 0);
+	struct timer_list wakeup_timer;
 
 	/* Wait for the main thread to give the start signal. */
 	wait_for_completion(&suspend_threads_started);
@@ -287,6 +286,7 @@
 	pr_info("CPU %d entering suspend cycles, states 1 through %d\n",
 		cpu, drv->state_count - 1);
 
+	setup_timer_on_stack(&wakeup_timer, dummy_callback, 0);
 	for (i = 0; i < NUM_SUSPEND_CYCLE; ++i) {
 		int index;
 		/*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 9ada56c..4c851fde 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -840,6 +840,9 @@
 				else if (type == CGS_UCODE_ID_SMU_SK)
 					strcpy(fw_name, "amdgpu/polaris10_smc_sk.bin");
 				break;
+			case CHIP_POLARIS12:
+				strcpy(fw_name, "amdgpu/polaris12_smc.bin");
+				break;
 			default:
 				DRM_ERROR("SMC firmware not supported\n");
 				return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 60bd4afe..fe3bb94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -73,6 +73,7 @@
 	"STONEY",
 	"POLARIS10",
 	"POLARIS11",
+	"POLARIS12",
 	"LAST",
 };
 
@@ -1277,6 +1278,7 @@
 	case CHIP_FIJI:
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS12:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
 		if (adev->asic_type == CHIP_CARRIZO || adev->asic_type == CHIP_STONEY)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 8cb937b..2534ada 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -418,6 +418,13 @@
 	{0x1002, 0x67CA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
 	{0x1002, 0x67CC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
 	{0x1002, 0x67CF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+	/* Polaris12 */
+	{0x1002, 0x6980, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+	{0x1002, 0x6981, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+	{0x1002, 0x6985, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+	{0x1002, 0x6986, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+	{0x1002, 0x6987, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+	{0x1002, 0x699F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 
 	{0, 0, 0}
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index fc592c2..95a568d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -98,6 +98,7 @@
 	switch (adev->asic_type) {
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS12:
 	case CHIP_TONGA:
 	case CHIP_FIJI:
 	case CHIP_TOPAZ:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index a81dfae..1d564be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -65,6 +65,7 @@
 #define FIRMWARE_STONEY		"amdgpu/stoney_uvd.bin"
 #define FIRMWARE_POLARIS10	"amdgpu/polaris10_uvd.bin"
 #define FIRMWARE_POLARIS11	"amdgpu/polaris11_uvd.bin"
+#define FIRMWARE_POLARIS12	"amdgpu/polaris12_uvd.bin"
 
 /**
  * amdgpu_uvd_cs_ctx - Command submission parser context
@@ -98,6 +99,7 @@
 MODULE_FIRMWARE(FIRMWARE_STONEY);
 MODULE_FIRMWARE(FIRMWARE_POLARIS10);
 MODULE_FIRMWARE(FIRMWARE_POLARIS11);
+MODULE_FIRMWARE(FIRMWARE_POLARIS12);
 
 static void amdgpu_uvd_idle_work_handler(struct work_struct *work);
 
@@ -149,6 +151,9 @@
 	case CHIP_POLARIS11:
 		fw_name = FIRMWARE_POLARIS11;
 		break;
+	case CHIP_POLARIS12:
+		fw_name = FIRMWARE_POLARIS12;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 69b66b9..8fec802 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -52,6 +52,7 @@
 #define FIRMWARE_STONEY		"amdgpu/stoney_vce.bin"
 #define FIRMWARE_POLARIS10	"amdgpu/polaris10_vce.bin"
 #define FIRMWARE_POLARIS11         "amdgpu/polaris11_vce.bin"
+#define FIRMWARE_POLARIS12         "amdgpu/polaris12_vce.bin"
 
 #ifdef CONFIG_DRM_AMDGPU_CIK
 MODULE_FIRMWARE(FIRMWARE_BONAIRE);
@@ -66,6 +67,7 @@
 MODULE_FIRMWARE(FIRMWARE_STONEY);
 MODULE_FIRMWARE(FIRMWARE_POLARIS10);
 MODULE_FIRMWARE(FIRMWARE_POLARIS11);
+MODULE_FIRMWARE(FIRMWARE_POLARIS12);
 
 static void amdgpu_vce_idle_work_handler(struct work_struct *work);
 
@@ -121,6 +123,9 @@
 	case CHIP_POLARIS11:
 		fw_name = FIRMWARE_POLARIS11;
 		break;
+	case CHIP_POLARIS12:
+		fw_name = FIRMWARE_POLARIS12;
+		break;
 
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 9999dc7..ccb5e02 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2512,6 +2512,8 @@
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -2537,7 +2539,6 @@
 				      int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -2578,7 +2579,9 @@
 
 	dce_v10_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -2587,16 +2590,10 @@
 
 		dce_v10_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v10_0_show_cursor(crtc);
@@ -2620,7 +2617,6 @@
 static void dce_v10_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v10_0_lock_cursor(crtc, true);
@@ -2628,10 +2624,6 @@
 		dce_v10_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					     amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v10_0_show_cursor(crtc);
 
 		dce_v10_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index b3d62b9..a7af5b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -167,6 +167,7 @@
 						 (const u32)ARRAY_SIZE(stoney_golden_settings_a11));
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		amdgpu_program_register_sequence(adev,
 						 polaris11_golden_settings_a11,
 						 (const u32)ARRAY_SIZE(polaris11_golden_settings_a11));
@@ -608,6 +609,7 @@
 		num_crtc = 6;
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		num_crtc = 5;
 		break;
 	default:
@@ -1589,6 +1591,7 @@
 		adev->mode_info.audio.num_pins = 8;
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		adev->mode_info.audio.num_pins = 6;
 		break;
 	default:
@@ -2388,7 +2391,8 @@
 	int pll;
 
 	if ((adev->asic_type == CHIP_POLARIS10) ||
-	    (adev->asic_type == CHIP_POLARIS11)) {
+	    (adev->asic_type == CHIP_POLARIS11) ||
+	    (adev->asic_type == CHIP_POLARIS12)) {
 		struct amdgpu_encoder *amdgpu_encoder =
 			to_amdgpu_encoder(amdgpu_crtc->encoder);
 		struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
@@ -2528,6 +2532,8 @@
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -2553,7 +2559,6 @@
 				      int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -2594,7 +2599,9 @@
 
 	dce_v11_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -2603,16 +2610,10 @@
 
 		dce_v11_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v11_0_show_cursor(crtc);
@@ -2636,7 +2637,6 @@
 static void dce_v11_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v11_0_lock_cursor(crtc, true);
@@ -2644,10 +2644,6 @@
 		dce_v11_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					     amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v11_0_show_cursor(crtc);
 
 		dce_v11_0_lock_cursor(crtc, false);
@@ -2822,7 +2818,8 @@
 		return -EINVAL;
 
 	if ((adev->asic_type == CHIP_POLARIS10) ||
-	    (adev->asic_type == CHIP_POLARIS11)) {
+	    (adev->asic_type == CHIP_POLARIS11) ||
+	    (adev->asic_type == CHIP_POLARIS12)) {
 		struct amdgpu_encoder *amdgpu_encoder =
 			to_amdgpu_encoder(amdgpu_crtc->encoder);
 		int encoder_mode =
@@ -2992,6 +2989,7 @@
 		adev->mode_info.num_dig = 6;
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		adev->mode_info.num_hpd = 5;
 		adev->mode_info.num_dig = 5;
 		break;
@@ -3101,7 +3099,8 @@
 	amdgpu_atombios_crtc_powergate_init(adev);
 	amdgpu_atombios_encoder_init_dig(adev);
 	if ((adev->asic_type == CHIP_POLARIS10) ||
-	    (adev->asic_type == CHIP_POLARIS11)) {
+	    (adev->asic_type == CHIP_POLARIS11) ||
+	    (adev->asic_type == CHIP_POLARIS12)) {
 		amdgpu_atombios_crtc_set_dce_clock(adev, adev->clock.default_dispclk,
 						   DCE_CLOCK_TYPE_DISPCLK, ATOM_GCK_DFS);
 		amdgpu_atombios_crtc_set_dce_clock(adev, 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index b4e4ec6..39df6a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1859,6 +1859,8 @@
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	int xorigin = 0, yorigin = 0;
 
+	int w = amdgpu_crtc->cursor_width;
+
 	amdgpu_crtc->cursor_x = x;
 	amdgpu_crtc->cursor_y = y;
 
@@ -1878,6 +1880,8 @@
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((w - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -1903,7 +1907,6 @@
 				     int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -1944,7 +1947,9 @@
 
 	dce_v6_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -1953,16 +1958,10 @@
 
 		dce_v6_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v6_0_show_cursor(crtc);
@@ -1986,7 +1985,6 @@
 static void dce_v6_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v6_0_lock_cursor(crtc, true);
@@ -1994,10 +1992,6 @@
 		dce_v6_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					    amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v6_0_show_cursor(crtc);
 		dce_v6_0_lock_cursor(crtc, false);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 584abe8..28102bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2363,6 +2363,8 @@
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -2388,7 +2390,6 @@
 				     int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -2429,7 +2430,9 @@
 
 	dce_v8_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -2438,16 +2441,10 @@
 
 		dce_v8_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v8_0_show_cursor(crtc);
@@ -2471,7 +2468,6 @@
 static void dce_v8_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v8_0_lock_cursor(crtc, true);
@@ -2479,10 +2475,6 @@
 		dce_v8_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					    amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v8_0_show_cursor(crtc);
 
 		dce_v8_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index d0ec009..3733741 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -139,6 +139,13 @@
 MODULE_FIRMWARE("amdgpu/polaris10_mec2.bin");
 MODULE_FIRMWARE("amdgpu/polaris10_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/polaris12_ce.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_pfp.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_me.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_mec.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_mec2.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_rlc.bin");
+
 static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] =
 {
 	{mmGDS_VMID0_BASE, mmGDS_VMID0_SIZE, mmGDS_GWS_VMID0, mmGDS_OA_VMID0},
@@ -689,6 +696,7 @@
 						 (const u32)ARRAY_SIZE(tonga_golden_common_all));
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		amdgpu_program_register_sequence(adev,
 						 golden_settings_polaris11_a11,
 						 (const u32)ARRAY_SIZE(golden_settings_polaris11_a11));
@@ -903,6 +911,9 @@
 	case CHIP_POLARIS10:
 		chip_name = "polaris10";
 		break;
+	case CHIP_POLARIS12:
+		chip_name = "polaris12";
+		break;
 	case CHIP_STONEY:
 		chip_name = "stoney";
 		break;
@@ -1768,6 +1779,7 @@
 		gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		ret = amdgpu_atombios_get_gfx_info(adev);
 		if (ret)
 			return ret;
@@ -2682,6 +2694,7 @@
 
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		modearray[0] = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 				PIPE_CONFIG(ADDR_SURF_P4_16x16) |
 				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
@@ -3503,6 +3516,7 @@
 		*rconf1 |= 0x0;
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		*rconf |= RB_MAP_PKR0(2) | RB_XSEL2(1) | SE_MAP(2) |
 			  SE_XSEL(1) | SE_YSEL(1);
 		*rconf1 |= 0x0;
@@ -4021,7 +4035,8 @@
 			cz_enable_cp_power_gating(adev, true);
 		else
 			cz_enable_cp_power_gating(adev, false);
-	} else if (adev->asic_type == CHIP_POLARIS11) {
+	} else if ((adev->asic_type == CHIP_POLARIS11) ||
+		   (adev->asic_type == CHIP_POLARIS12)) {
 		gfx_v8_0_init_csb(adev);
 		gfx_v8_0_init_save_restore_list(adev);
 		gfx_v8_0_enable_save_restore_machine(adev);
@@ -4095,7 +4110,8 @@
 		 RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK);
 	WREG32(mmRLC_CGCG_CGLS_CTRL, tmp);
 	if (adev->asic_type == CHIP_POLARIS11 ||
-	    adev->asic_type == CHIP_POLARIS10) {
+	    adev->asic_type == CHIP_POLARIS10 ||
+	    adev->asic_type == CHIP_POLARIS12) {
 		tmp = RREG32(mmRLC_CGCG_CGLS_CTRL_3D);
 		tmp &= ~0x3;
 		WREG32(mmRLC_CGCG_CGLS_CTRL_3D, tmp);
@@ -4283,6 +4299,7 @@
 		amdgpu_ring_write(ring, 0x0000002A);
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		amdgpu_ring_write(ring, 0x16000012);
 		amdgpu_ring_write(ring, 0x00000000);
 		break;
@@ -4664,7 +4681,8 @@
 			    (adev->asic_type == CHIP_FIJI) ||
 			    (adev->asic_type == CHIP_STONEY) ||
 			    (adev->asic_type == CHIP_POLARIS11) ||
-			    (adev->asic_type == CHIP_POLARIS10)) {
+			    (adev->asic_type == CHIP_POLARIS10) ||
+			    (adev->asic_type == CHIP_POLARIS12)) {
 				WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
 				       AMDGPU_DOORBELL_KIQ << 2);
 				WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
@@ -4700,7 +4718,8 @@
 		mqd->cp_hqd_persistent_state = tmp;
 		if (adev->asic_type == CHIP_STONEY ||
 			adev->asic_type == CHIP_POLARIS11 ||
-			adev->asic_type == CHIP_POLARIS10) {
+			adev->asic_type == CHIP_POLARIS10 ||
+			adev->asic_type == CHIP_POLARIS12) {
 			tmp = RREG32(mmCP_ME1_PIPE3_INT_CNTL);
 			tmp = REG_SET_FIELD(tmp, CP_ME1_PIPE3_INT_CNTL, GENERIC2_INT_ENABLE, 1);
 			WREG32(mmCP_ME1_PIPE3_INT_CNTL, tmp);
@@ -5279,7 +5298,8 @@
 static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
 						       bool enable)
 {
-	if (adev->asic_type == CHIP_POLARIS11)
+	if ((adev->asic_type == CHIP_POLARIS11) ||
+	    (adev->asic_type == CHIP_POLARIS12))
 		/* Send msg to SMU via Powerplay */
 		amdgpu_set_powergating_state(adev,
 					     AMD_IP_BLOCK_TYPE_SMC,
@@ -5353,6 +5373,7 @@
 			gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, false);
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable)
 			gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true);
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 45a573e..e2b0b16 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -44,6 +44,7 @@
 MODULE_FIRMWARE("radeon/pitcairn_mc.bin");
 MODULE_FIRMWARE("radeon/verde_mc.bin");
 MODULE_FIRMWARE("radeon/oland_mc.bin");
+MODULE_FIRMWARE("radeon/si58_mc.bin");
 
 #define MC_SEQ_MISC0__MT__MASK   0xf0000000
 #define MC_SEQ_MISC0__MT__GDDR1  0x10000000
@@ -113,6 +114,7 @@
 	const char *chip_name;
 	char fw_name[30];
 	int err;
+	bool is_58_fw = false;
 
 	DRM_DEBUG("\n");
 
@@ -135,7 +137,14 @@
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+	/* this memory configuration requires special firmware */
+	if (((RREG32(mmMC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58)
+		is_58_fw = true;
+
+	if (is_58_fw)
+		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+	else
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
 	err = request_firmware(&adev->mc.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -463,19 +472,11 @@
 	WREG32(mmVM_CONTEXT1_CNTL,
 	       VM_CONTEXT1_CNTL__ENABLE_CONTEXT_MASK |
 	       (1UL << VM_CONTEXT1_CNTL__PAGE_TABLE_DEPTH__SHIFT) |
-	       ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT) |
-	       VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK);
+	       ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT));
+	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
+		gmc_v6_0_set_fault_enable_default(adev, false);
+	else
+		gmc_v6_0_set_fault_enable_default(adev, true);
 
 	gmc_v6_0_gart_flush_gpu_tlb(adev, 0);
 	dev_info(adev->dev, "PCIE GART of %uM enabled (table at 0x%016llX).\n",
@@ -754,7 +755,10 @@
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
+		return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	else
+		return 0;
 }
 
 static int gmc_v6_0_sw_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 0daac3a..476bc9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -46,6 +46,7 @@
 MODULE_FIRMWARE("amdgpu/tonga_mc.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_mc.bin");
 MODULE_FIRMWARE("amdgpu/polaris10_mc.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_mc.bin");
 
 static const u32 golden_settings_tonga_a11[] =
 {
@@ -130,6 +131,7 @@
 						 (const u32)ARRAY_SIZE(golden_settings_tonga_a11));
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		amdgpu_program_register_sequence(adev,
 						 golden_settings_polaris11_a11,
 						 (const u32)ARRAY_SIZE(golden_settings_polaris11_a11));
@@ -225,6 +227,9 @@
 	case CHIP_POLARIS10:
 		chip_name = "polaris10";
 		break;
+	case CHIP_POLARIS12:
+		chip_name = "polaris12";
+		break;
 	case CHIP_FIJI:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 1170a64..034ace7 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -60,6 +60,8 @@
 MODULE_FIRMWARE("amdgpu/polaris10_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_sdma.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_sdma.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_sdma1.bin");
 
 
 static const u32 sdma_offsets[SDMA_MAX_INSTANCE] =
@@ -206,6 +208,7 @@
 						 (const u32)ARRAY_SIZE(golden_settings_tonga_a11));
 		break;
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		amdgpu_program_register_sequence(adev,
 						 golden_settings_polaris11_a11,
 						 (const u32)ARRAY_SIZE(golden_settings_polaris11_a11));
@@ -278,6 +281,9 @@
 	case CHIP_POLARIS10:
 		chip_name = "polaris10";
 		break;
+	case CHIP_POLARIS12:
+		chip_name = "polaris12";
+		break;
 	case CHIP_CARRIZO:
 		chip_name = "carrizo";
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 6c65a1a2..6e150db 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -56,7 +56,6 @@
 #define BIOS_SCRATCH_4                                    0x5cd
 
 MODULE_FIRMWARE("radeon/tahiti_smc.bin");
-MODULE_FIRMWARE("radeon/tahiti_k_smc.bin");
 MODULE_FIRMWARE("radeon/pitcairn_smc.bin");
 MODULE_FIRMWARE("radeon/pitcairn_k_smc.bin");
 MODULE_FIRMWARE("radeon/verde_smc.bin");
@@ -65,6 +64,7 @@
 MODULE_FIRMWARE("radeon/oland_k_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
+MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
 
 union power_info {
 	struct _ATOM_POWERPLAY_INFO info;
@@ -3488,30 +3488,6 @@
 		    (adev->pdev->device == 0x6817) ||
 		    (adev->pdev->device == 0x6806))
 			max_mclk = 120000;
-	} else if (adev->asic_type == CHIP_VERDE) {
-		if ((adev->pdev->revision == 0x81) ||
-		    (adev->pdev->revision == 0x83) ||
-		    (adev->pdev->revision == 0x87) ||
-		    (adev->pdev->device == 0x6820) ||
-		    (adev->pdev->device == 0x6821) ||
-		    (adev->pdev->device == 0x6822) ||
-		    (adev->pdev->device == 0x6823) ||
-		    (adev->pdev->device == 0x682A) ||
-		    (adev->pdev->device == 0x682B)) {
-			max_sclk = 75000;
-			max_mclk = 80000;
-		}
-	} else if (adev->asic_type == CHIP_OLAND) {
-		if ((adev->pdev->revision == 0xC7) ||
-		    (adev->pdev->revision == 0x80) ||
-		    (adev->pdev->revision == 0x81) ||
-		    (adev->pdev->revision == 0x83) ||
-		    (adev->pdev->revision == 0x87) ||
-		    (adev->pdev->device == 0x6604) ||
-		    (adev->pdev->device == 0x6605)) {
-			max_sclk = 75000;
-			max_mclk = 80000;
-		}
 	} else if (adev->asic_type == CHIP_HAINAN) {
 		if ((adev->pdev->revision == 0x81) ||
 		    (adev->pdev->revision == 0x83) ||
@@ -3520,7 +3496,6 @@
 		    (adev->pdev->device == 0x6665) ||
 		    (adev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
-			max_mclk = 80000;
 		}
 	}
 	/* Apply dpm quirks */
@@ -7687,50 +7662,51 @@
 		chip_name = "tahiti";
 		break;
 	case CHIP_PITCAIRN:
-		if ((adev->pdev->revision == 0x81) ||
-		    (adev->pdev->device == 0x6810) ||
-		    (adev->pdev->device == 0x6811) ||
-		    (adev->pdev->device == 0x6816) ||
-		    (adev->pdev->device == 0x6817) ||
-		    (adev->pdev->device == 0x6806))
+		if ((adev->pdev->revision == 0x81) &&
+		    ((adev->pdev->device == 0x6810) ||
+		    (adev->pdev->device == 0x6811)))
 			chip_name = "pitcairn_k";
 		else
 			chip_name = "pitcairn";
 		break;
 	case CHIP_VERDE:
-		if ((adev->pdev->revision == 0x81) ||
-		    (adev->pdev->revision == 0x83) ||
-		    (adev->pdev->revision == 0x87) ||
-		    (adev->pdev->device == 0x6820) ||
-		    (adev->pdev->device == 0x6821) ||
-		    (adev->pdev->device == 0x6822) ||
-		    (adev->pdev->device == 0x6823) ||
-		    (adev->pdev->device == 0x682A) ||
-		    (adev->pdev->device == 0x682B))
+		if (((adev->pdev->device == 0x6820) &&
+			((adev->pdev->revision == 0x81) ||
+			(adev->pdev->revision == 0x83))) ||
+		    ((adev->pdev->device == 0x6821) &&
+			((adev->pdev->revision == 0x83) ||
+			(adev->pdev->revision == 0x87))) ||
+		    ((adev->pdev->revision == 0x87) &&
+			((adev->pdev->device == 0x6823) ||
+			(adev->pdev->device == 0x682b))))
 			chip_name = "verde_k";
 		else
 			chip_name = "verde";
 		break;
 	case CHIP_OLAND:
-		if ((adev->pdev->revision == 0xC7) ||
-		    (adev->pdev->revision == 0x80) ||
-		    (adev->pdev->revision == 0x81) ||
-		    (adev->pdev->revision == 0x83) ||
-		    (adev->pdev->revision == 0x87) ||
-		    (adev->pdev->device == 0x6604) ||
-		    (adev->pdev->device == 0x6605))
+		if (((adev->pdev->revision == 0x81) &&
+			((adev->pdev->device == 0x6600) ||
+			(adev->pdev->device == 0x6604) ||
+			(adev->pdev->device == 0x6605) ||
+			(adev->pdev->device == 0x6610))) ||
+		    ((adev->pdev->revision == 0x83) &&
+			(adev->pdev->device == 0x6610)))
 			chip_name = "oland_k";
 		else
 			chip_name = "oland";
 		break;
 	case CHIP_HAINAN:
-		if ((adev->pdev->revision == 0x81) ||
-		    (adev->pdev->revision == 0x83) ||
-		    (adev->pdev->revision == 0xC3) ||
-		    (adev->pdev->device == 0x6664) ||
-		    (adev->pdev->device == 0x6665) ||
-		    (adev->pdev->device == 0x6667))
+		if (((adev->pdev->revision == 0x81) &&
+			(adev->pdev->device == 0x6660)) ||
+		    ((adev->pdev->revision == 0x83) &&
+			((adev->pdev->device == 0x6660) ||
+			(adev->pdev->device == 0x6663) ||
+			(adev->pdev->device == 0x6665) ||
+			 (adev->pdev->device == 0x6667))))
 			chip_name = "hainan_k";
+		else if ((adev->pdev->revision == 0xc3) &&
+			 (adev->pdev->device == 0x6665))
+			chip_name = "banks_k_2";
 		else
 			chip_name = "hainan";
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 96444e4..7fb9137 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -40,13 +40,14 @@
 #include "smu/smu_7_0_1_sh_mask.h"
 
 static void uvd_v4_2_mc_resume(struct amdgpu_device *adev);
-static void uvd_v4_2_init_cg(struct amdgpu_device *adev);
 static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v4_2_set_irq_funcs(struct amdgpu_device *adev);
 static int uvd_v4_2_start(struct amdgpu_device *adev);
 static void uvd_v4_2_stop(struct amdgpu_device *adev);
 static int uvd_v4_2_set_clockgating_state(void *handle,
 				enum amd_clockgating_state state);
+static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
+			     bool sw_mode);
 /**
  * uvd_v4_2_ring_get_rptr - get read pointer
  *
@@ -140,7 +141,8 @@
 
 	return r;
 }
-
+static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
+				 bool enable);
 /**
  * uvd_v4_2_hw_init - start and test UVD block
  *
@@ -155,8 +157,7 @@
 	uint32_t tmp;
 	int r;
 
-	uvd_v4_2_init_cg(adev);
-	uvd_v4_2_set_clockgating_state(adev, AMD_CG_STATE_GATE);
+	uvd_v4_2_enable_mgcg(adev, true);
 	amdgpu_asic_set_uvd_clocks(adev, 10000, 10000);
 	r = uvd_v4_2_start(adev);
 	if (r)
@@ -266,11 +267,13 @@
 	struct amdgpu_ring *ring = &adev->uvd.ring;
 	uint32_t rb_bufsz;
 	int i, j, r;
-
 	/* disable byte swapping */
 	u32 lmi_swap_cntl = 0;
 	u32 mp_swap_cntl = 0;
 
+	WREG32(mmUVD_CGC_GATE, 0);
+	uvd_v4_2_set_dcm(adev, true);
+
 	uvd_v4_2_mc_resume(adev);
 
 	/* disable interupt */
@@ -406,6 +409,8 @@
 
 	/* Unstall UMC and register bus */
 	WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8));
+
+	uvd_v4_2_set_dcm(adev, false);
 }
 
 /**
@@ -619,19 +624,6 @@
 	WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2);
 }
 
-static void uvd_v4_2_init_cg(struct amdgpu_device *adev)
-{
-	bool hw_mode = true;
-
-	if (hw_mode) {
-		uvd_v4_2_set_dcm(adev, false);
-	} else {
-		u32 tmp = RREG32(mmUVD_CGC_CTRL);
-		tmp &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
-		WREG32(mmUVD_CGC_CTRL, tmp);
-	}
-}
-
 static bool uvd_v4_2_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -685,17 +677,6 @@
 static int uvd_v4_2_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
-	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;
-
-	uvd_v4_2_enable_mgcg(adev, gate);
-
 	return 0;
 }
 
@@ -711,9 +692,6 @@
 	 */
 	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);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index a79e283..6de6bec 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -791,15 +791,10 @@
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
-	static int curstate = -1;
 
 	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
 		return 0;
 
-	if (curstate == state)
-		return 0;
-
-	curstate = state;
 	if (enable) {
 		/* wait for STATUS to clear */
 		if (uvd_v5_0_wait_for_idle(handle))
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 6b3293a..37ca685 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -43,9 +43,13 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
+#define GRBM_GFX_INDEX__VCE_ALL_PIPE		0x07
+
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0	0x8616
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1	0x8617
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2	0x8618
+#define mmGRBM_GFX_INDEX_DEFAULT 0xE0000000
+
 #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
@@ -54,6 +58,9 @@
 
 #define FW_52_8_3	((52 << 24) | (8 << 16) | (3 << 8))
 
+#define GET_VCE_INSTANCE(i)  ((i) << GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT \
+					| GRBM_GFX_INDEX__VCE_ALL_PIPE)
+
 static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx);
 static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -175,7 +182,7 @@
 		WREG32(mmVCE_UENC_CLOCK_GATING_2, data);
 
 		data = RREG32(mmVCE_UENC_REG_CLOCK_GATING);
-		data &= ~0xffc00000;
+		data &= ~0x3ff;
 		WREG32(mmVCE_UENC_REG_CLOCK_GATING, data);
 
 		data = RREG32(mmVCE_UENC_DMA_DCLK_CTRL);
@@ -249,7 +256,7 @@
 		if (adev->vce.harvest_config & (1 << idx))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
 		vce_v3_0_mc_resume(adev, idx);
 		WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1);
 
@@ -273,7 +280,7 @@
 		}
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
@@ -288,7 +295,7 @@
 		if (adev->vce.harvest_config & (1 << idx))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
 
 		if (adev->asic_type >= CHIP_STONEY)
 			WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x200001);
@@ -306,7 +313,7 @@
 			vce_v3_0_set_vce_sw_clock_gating(adev, false);
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
@@ -320,11 +327,12 @@
 {
 	u32 tmp;
 
-	/* Fiji, Stoney, Polaris10, Polaris11 are single pipe */
+	/* Fiji, Stoney, Polaris10, Polaris11, Polaris12 are single pipe */
 	if ((adev->asic_type == CHIP_FIJI) ||
 	    (adev->asic_type == CHIP_STONEY) ||
 	    (adev->asic_type == CHIP_POLARIS10) ||
-	    (adev->asic_type == CHIP_POLARIS11))
+	    (adev->asic_type == CHIP_POLARIS11) ||
+	    (adev->asic_type == CHIP_POLARIS12))
 		return AMDGPU_VCE_HARVEST_VCE1;
 
 	/* Tonga and CZ are dual or single pipe */
@@ -585,17 +593,17 @@
 	 * VCE team suggest use bit 3--bit 6 for busy status check
 	 */
 	mutex_lock(&adev->grbm_idx_mutex);
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
 	if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
 	}
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0x10);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 	if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
 	}
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	if (srbm_soft_reset) {
@@ -733,7 +741,7 @@
 		if (adev->vce.harvest_config & (1 << i))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, i);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(i));
 
 		if (enable) {
 			/* initialize VCE_CLOCK_GATING_A: Clock ON/OFF delay */
@@ -752,7 +760,7 @@
 		vce_v3_0_set_vce_sw_clock_gating(adev, enable);
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index bf088d6..c2ac54f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -88,6 +88,7 @@
 MODULE_FIRMWARE("amdgpu/polaris10_smc_sk.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_smc.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_smc_sk.bin");
+MODULE_FIRMWARE("amdgpu/polaris12_smc.bin");
 
 /*
  * Indirect registers accessor
@@ -312,6 +313,7 @@
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS12:
 	default:
 		break;
 	}
@@ -671,6 +673,7 @@
 	case CHIP_TONGA:
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS12:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
 		asic_register_table = cz_allowed_read_registers;
@@ -994,6 +997,11 @@
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x50;
 		break;
+	case CHIP_POLARIS12:
+		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG;
+		adev->pg_flags = 0;
+		adev->external_rev_id = adev->rev_id + 0x64;
+		break;
 	case CHIP_CARRIZO:
 		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG |
 			AMD_CG_SUPPORT_GFX_MGCG |
@@ -1346,6 +1354,7 @@
 	case CHIP_TONGA:
 	case CHIP_POLARIS10:
 	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
 		vi_common_set_clockgating_state_by_smu(adev, state);
 	default:
 		break;
@@ -1429,6 +1438,7 @@
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS12:
 		amdgpu_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_ip_block_add(adev, &gmc_v8_1_ip_block);
 		amdgpu_ip_block_add(adev, &tonga_ih_ip_block);
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index c02469a..85f3587 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -23,7 +23,7 @@
 #ifndef __AMD_SHARED_H__
 #define __AMD_SHARED_H__
 
-#define AMD_MAX_USEC_TIMEOUT		100000  /* 100 ms */
+#define AMD_MAX_USEC_TIMEOUT		200000  /* 200 ms */
 
 /*
  * Supported ASIC types
@@ -46,6 +46,7 @@
 	CHIP_STONEY,
 	CHIP_POLARIS10,
 	CHIP_POLARIS11,
+	CHIP_POLARIS12,
 	CHIP_LAST,
 };
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
index b0c63c5..6bb79c9 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
@@ -200,7 +200,7 @@
 				cgs_set_clockgating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
-							AMD_CG_STATE_UNGATE);
+							AMD_CG_STATE_GATE);
 				cgs_set_powergating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
@@ -218,7 +218,7 @@
 				cgs_set_clockgating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
-							AMD_PG_STATE_GATE);
+							AMD_PG_STATE_UNGATE);
 				cz_dpm_update_vce_dpm(hwmgr);
 				cz_enable_disable_vce_dpm(hwmgr, true);
 				return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 4b14f25..0fb4e8c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -1402,14 +1402,22 @@
 					     cz_hwmgr->vce_dpm.hard_min_clk,
 						PPSMC_MSG_SetEclkHardMin));
 	} else {
-		/*EPR# 419220 -HW limitation to to */
-		cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
-		smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
-					    PPSMC_MSG_SetEclkHardMin,
-					    cz_get_eclk_level(hwmgr,
-				     cz_hwmgr->vce_dpm.hard_min_clk,
-					  PPSMC_MSG_SetEclkHardMin));
-
+		/*Program HardMin based on the vce_arbiter.ecclk */
+		if (hwmgr->vce_arbiter.ecclk == 0) {
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+					    PPSMC_MSG_SetEclkHardMin, 0);
+		/* disable ECLK DPM 0. Otherwise VCE could hang if
+		 * switching SCLK from DPM 0 to 6/7 */
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+					PPSMC_MSG_SetEclkSoftMin, 1);
+		} else {
+			cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+						PPSMC_MSG_SetEclkHardMin,
+						cz_get_eclk_level(hwmgr,
+						cz_hwmgr->vce_dpm.hard_min_clk,
+						PPSMC_MSG_SetEclkHardMin));
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index dc6700a..b036064 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -95,6 +95,7 @@
 			break;
 		case CHIP_POLARIS11:
 		case CHIP_POLARIS10:
+		case CHIP_POLARIS12:
 			polaris_set_asic_special_caps(hwmgr);
 			hwmgr->feature_mask &= ~(PP_UVD_HANDSHAKE_MASK);
 			break;
@@ -745,7 +746,7 @@
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_TablelessHardwareInterface);
 
-	if (hwmgr->chip_id == CHIP_POLARIS11)
+	if ((hwmgr->chip_id == CHIP_POLARIS11) || (hwmgr->chip_id == CHIP_POLARIS12))
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 					PHM_PlatformCaps_SPLLShutdownSupport);
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
index 26477f0..6cd1287 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
@@ -521,7 +521,7 @@
 				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
 				result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris10);
 				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
-			} else if (hwmgr->chip_id == CHIP_POLARIS11) {
+			} else if ((hwmgr->chip_id == CHIP_POLARIS11) || (hwmgr->chip_id == CHIP_POLARIS12)) {
 				result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11);
 				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
 				result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index e5812aa..6e618aa 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -65,6 +65,7 @@
 			break;
 		case CHIP_POLARIS11:
 		case CHIP_POLARIS10:
+		case CHIP_POLARIS12:
 			polaris10_smum_init(smumgr);
 			break;
 		default:
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index eb9bf87..18eefdc 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1382,6 +1382,7 @@
 
 	pm_runtime_enable(dev);
 
+	pm_runtime_get_sync(dev);
 	phy_power_on(dp->phy);
 
 	analogix_dp_init_dp(dp);
@@ -1414,9 +1415,15 @@
 		goto err_disable_pm_runtime;
 	}
 
+	phy_power_off(dp->phy);
+	pm_runtime_put(dev);
+
 	return 0;
 
 err_disable_pm_runtime:
+
+	phy_power_off(dp->phy);
+	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
 
 	return ret;
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 583f47f..34f757b 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1259,8 +1259,10 @@
 
 	if (!nonblock) {
 		ret = drm_atomic_helper_wait_for_fences(dev, state, true);
-		if (ret)
+		if (ret) {
+			drm_atomic_helper_cleanup_planes(dev, state);
 			return ret;
+		}
 	}
 
 	/*
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index ac6a352..e6b19bc 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1460,6 +1460,13 @@
 		return NULL;
 
 	mode->type |= DRM_MODE_TYPE_USERDEF;
+	/* fix up 1368x768: GFT/CVT can't express 1366 width due to alignment */
+	if (cmd->xres == 1366 && mode->hdisplay == 1368) {
+		mode->hdisplay = 1366;
+		mode->hsync_start--;
+		mode->hsync_end--;
+		drm_mode_set_name(mode);
+	}
 	drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
 	return mode;
 }
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index ac953f0..b452a7c 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -115,24 +115,27 @@
 
 #define DRM_OUTPUT_POLL_PERIOD (10*HZ)
 /**
- * drm_kms_helper_poll_enable_locked - re-enable output polling.
+ * drm_kms_helper_poll_enable - re-enable output polling.
  * @dev: drm_device
  *
- * This function re-enables the output polling work without
- * locking the mode_config mutex.
+ * This function re-enables the output polling work, after it has been
+ * temporarily disabled using drm_kms_helper_poll_disable(), for example over
+ * suspend/resume.
  *
- * This is like drm_kms_helper_poll_enable() however it is to be
- * called from a context where the mode_config mutex is locked
- * already.
+ * Drivers can call this helper from their device resume implementation. It is
+ * an error to call this when the output polling support has not yet been set
+ * up.
+ *
+ * Note that calls to enable and disable polling must be strictly ordered, which
+ * is automatically the case when they're only call from suspend/resume
+ * callbacks.
  */
-void drm_kms_helper_poll_enable_locked(struct drm_device *dev)
+void drm_kms_helper_poll_enable(struct drm_device *dev)
 {
 	bool poll = false;
 	struct drm_connector *connector;
 	unsigned long delay = DRM_OUTPUT_POLL_PERIOD;
 
-	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
-
 	if (!dev->mode_config.poll_enabled || !drm_kms_helper_poll)
 		return;
 
@@ -143,14 +146,24 @@
 	}
 
 	if (dev->mode_config.delayed_event) {
+		/*
+		 * FIXME:
+		 *
+		 * Use short (1s) delay to handle the initial delayed event.
+		 * This delay should not be needed, but Optimus/nouveau will
+		 * fail in a mysterious way if the delayed event is handled as
+		 * soon as possible like it is done in
+		 * drm_helper_probe_single_connector_modes() in case the poll
+		 * was enabled before.
+		 */
 		poll = true;
-		delay = 0;
+		delay = HZ;
 	}
 
 	if (poll)
 		schedule_delayed_work(&dev->mode_config.output_poll_work, delay);
 }
-EXPORT_SYMBOL(drm_kms_helper_poll_enable_locked);
+EXPORT_SYMBOL(drm_kms_helper_poll_enable);
 
 static enum drm_connector_status
 drm_connector_detect(struct drm_connector *connector, bool force)
@@ -277,7 +290,7 @@
 
 	/* Re-enable polling in case the global poll config changed. */
 	if (drm_kms_helper_poll != dev->mode_config.poll_running)
-		drm_kms_helper_poll_enable_locked(dev);
+		drm_kms_helper_poll_enable(dev);
 
 	dev->mode_config.poll_running = drm_kms_helper_poll;
 
@@ -469,8 +482,12 @@
  * This function disables the output polling work.
  *
  * Drivers can call this helper from their device suspend implementation. It is
- * not an error to call this even when output polling isn't enabled or arlready
- * disabled.
+ * not an error to call this even when output polling isn't enabled or already
+ * disabled. Polling is re-enabled by calling drm_kms_helper_poll_enable().
+ *
+ * Note that calls to enable and disable polling must be strictly ordered, which
+ * is automatically the case when they're only call from suspend/resume
+ * callbacks.
  */
 void drm_kms_helper_poll_disable(struct drm_device *dev)
 {
@@ -481,24 +498,6 @@
 EXPORT_SYMBOL(drm_kms_helper_poll_disable);
 
 /**
- * drm_kms_helper_poll_enable - re-enable output polling.
- * @dev: drm_device
- *
- * This function re-enables the output polling work.
- *
- * Drivers can call this helper from their device resume implementation. It is
- * an error to call this when the output polling support has not yet been set
- * up.
- */
-void drm_kms_helper_poll_enable(struct drm_device *dev)
-{
-	mutex_lock(&dev->mode_config.mutex);
-	drm_kms_helper_poll_enable_locked(dev);
-	mutex_unlock(&dev->mode_config.mutex);
-}
-EXPORT_SYMBOL(drm_kms_helper_poll_enable);
-
-/**
  * drm_kms_helper_poll_init - initialize and enable output polling
  * @dev: drm_device
  *
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 6ca1f31..75eeb83 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -46,7 +46,8 @@
 	BIT_CLKS_ENABLED,
 	BIT_IRQS_ENABLED,
 	BIT_WIN_UPDATED,
-	BIT_SUSPENDED
+	BIT_SUSPENDED,
+	BIT_REQUEST_UPDATE
 };
 
 struct decon_context {
@@ -141,12 +142,6 @@
 		m->crtc_vsync_end = m->crtc_vsync_start + 1;
 	}
 
-	decon_set_bits(ctx, DECON_VIDCON0, VIDCON0_ENVID, 0);
-
-	/* enable clock gate */
-	val = CMU_CLKGAGE_MODE_SFR_F | CMU_CLKGAGE_MODE_MEM_F;
-	writel(val, ctx->addr + DECON_CMU);
-
 	if (ctx->out_type & (IFTYPE_I80 | I80_HW_TRG))
 		decon_setup_trigger(ctx);
 
@@ -315,6 +310,7 @@
 
 	/* window enable */
 	decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, ~0);
+	set_bit(BIT_REQUEST_UPDATE, &ctx->flags);
 }
 
 static void decon_disable_plane(struct exynos_drm_crtc *crtc,
@@ -327,6 +323,7 @@
 		return;
 
 	decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, 0);
+	set_bit(BIT_REQUEST_UPDATE, &ctx->flags);
 }
 
 static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
@@ -340,8 +337,8 @@
 	for (i = ctx->first_win; i < WINDOWS_NR; i++)
 		decon_shadow_protect_win(ctx, i, false);
 
-	/* standalone update */
-	decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0);
+	if (test_and_clear_bit(BIT_REQUEST_UPDATE, &ctx->flags))
+		decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0);
 
 	if (ctx->out_type & IFTYPE_I80)
 		set_bit(BIT_WIN_UPDATED, &ctx->flags);
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 0d41ebc..f7bce86 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -37,13 +37,6 @@
 #include "i915_drv.h"
 #include "gvt.h"
 
-#define MB_TO_BYTES(mb) ((mb) << 20ULL)
-#define BYTES_TO_MB(b) ((b) >> 20ULL)
-
-#define HOST_LOW_GM_SIZE MB_TO_BYTES(128)
-#define HOST_HIGH_GM_SIZE MB_TO_BYTES(384)
-#define HOST_FENCE 4
-
 static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
@@ -165,6 +158,14 @@
 	POSTING_READ(fence_reg_lo);
 }
 
+static void _clear_vgpu_fence(struct intel_vgpu *vgpu)
+{
+	int i;
+
+	for (i = 0; i < vgpu_fence_sz(vgpu); i++)
+		intel_vgpu_write_fence(vgpu, i, 0);
+}
+
 static void free_vgpu_fence(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
@@ -178,9 +179,9 @@
 	intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
+	_clear_vgpu_fence(vgpu);
 	for (i = 0; i < vgpu_fence_sz(vgpu); i++) {
 		reg = vgpu->fence.regs[i];
-		intel_vgpu_write_fence(vgpu, i, 0);
 		list_add_tail(&reg->link,
 			      &dev_priv->mm.fence_list);
 	}
@@ -208,13 +209,14 @@
 			continue;
 		list_del(pos);
 		vgpu->fence.regs[i] = reg;
-		intel_vgpu_write_fence(vgpu, i, 0);
 		if (++i == vgpu_fence_sz(vgpu))
 			break;
 	}
 	if (i != vgpu_fence_sz(vgpu))
 		goto out_free_fence;
 
+	_clear_vgpu_fence(vgpu);
+
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	intel_runtime_pm_put(dev_priv);
 	return 0;
@@ -314,6 +316,22 @@
 }
 
 /**
+ * intel_vgpu_reset_resource - reset resource state owned by a vGPU
+ * @vgpu: a vGPU
+ *
+ * This function is used to reset resource state owned by a vGPU.
+ *
+ */
+void intel_vgpu_reset_resource(struct intel_vgpu *vgpu)
+{
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+
+	intel_runtime_pm_get(dev_priv);
+	_clear_vgpu_fence(vgpu);
+	intel_runtime_pm_put(dev_priv);
+}
+
+/**
  * intel_alloc_vgpu_resource - allocate HW resource for a vGPU
  * @vgpu: vGPU
  * @param: vGPU creation params
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index db51638..4a6a2ed 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -123,6 +123,7 @@
 	u8 changed = old ^ new;
 	int ret;
 
+	memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
 	if (!(changed & PCI_COMMAND_MEMORY))
 		return 0;
 
@@ -142,7 +143,6 @@
 			return ret;
 	}
 
-	memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
 	return 0;
 }
 
@@ -240,7 +240,7 @@
 	if (WARN_ON(bytes > 4))
 		return -EINVAL;
 
-	if (WARN_ON(offset + bytes >= INTEL_GVT_MAX_CFG_SPACE_SZ))
+	if (WARN_ON(offset + bytes > INTEL_GVT_MAX_CFG_SPACE_SZ))
 		return -EINVAL;
 
 	/* First check if it's PCI_COMMAND */
@@ -282,3 +282,77 @@
 	}
 	return 0;
 }
+
+/**
+ * intel_vgpu_init_cfg_space - init vGPU configuration space when create vGPU
+ *
+ * @vgpu: a vGPU
+ * @primary: is the vGPU presented as primary
+ *
+ */
+void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
+			       bool primary)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	const struct intel_gvt_device_info *info = &gvt->device_info;
+	u16 *gmch_ctl;
+	int i;
+
+	memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
+	       info->cfg_space_size);
+
+	if (!primary) {
+		vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] =
+			INTEL_GVT_PCI_CLASS_VGA_OTHER;
+		vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] =
+			INTEL_GVT_PCI_CLASS_VGA_OTHER;
+	}
+
+	/* Show guest that there isn't any stolen memory.*/
+	gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL);
+	*gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT);
+
+	intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2,
+				 gvt_aperture_pa_base(gvt), true);
+
+	vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO
+					     | PCI_COMMAND_MEMORY
+					     | PCI_COMMAND_MASTER);
+	/*
+	 * Clear the bar upper 32bit and let guest to assign the new value
+	 */
+	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
+	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
+	memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
+
+	for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
+		vgpu->cfg_space.bar[i].size = pci_resource_len(
+					      gvt->dev_priv->drm.pdev, i * 2);
+		vgpu->cfg_space.bar[i].tracked = false;
+	}
+}
+
+/**
+ * intel_vgpu_reset_cfg_space - reset vGPU configuration space
+ *
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu)
+{
+	u8 cmd = vgpu_cfg_space(vgpu)[PCI_COMMAND];
+	bool primary = vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] !=
+				INTEL_GVT_PCI_CLASS_VGA_OTHER;
+
+	if (cmd & PCI_COMMAND_MEMORY) {
+		trap_gttmmio(vgpu, false);
+		map_aperture(vgpu, false);
+	}
+
+	/**
+	 * Currently we only do such reset when vGPU is not
+	 * owned by any VM, so we simply restore entire cfg
+	 * space to default value.
+	 */
+	intel_vgpu_init_cfg_space(vgpu, primary);
+}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 7eaaf1c..47dec4a 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -240,15 +240,8 @@
 static u64 read_pte64(struct drm_i915_private *dev_priv, unsigned long index)
 {
 	void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index;
-	u64 pte;
 
-#ifdef readq
-	pte = readq(addr);
-#else
-	pte = ioread32(addr);
-	pte |= (u64)ioread32(addr + 4) << 32;
-#endif
-	return pte;
+	return readq(addr);
 }
 
 static void write_pte64(struct drm_i915_private *dev_priv,
@@ -256,12 +249,8 @@
 {
 	void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index;
 
-#ifdef writeq
 	writeq(pte, addr);
-#else
-	iowrite32((u32)pte, addr);
-	iowrite32(pte >> 32, addr + 4);
-#endif
+
 	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
 	POSTING_READ(GFX_FLSH_CNTL_GEN6);
 }
@@ -1380,8 +1369,7 @@
 			info->gtt_entry_size;
 		mem = kzalloc(mm->has_shadow_page_table ?
 			mm->page_table_entry_size * 2
-				: mm->page_table_entry_size,
-			GFP_ATOMIC);
+				: mm->page_table_entry_size, GFP_KERNEL);
 		if (!mem)
 			return -ENOMEM;
 		mm->virtual_page_table = mem;
@@ -1532,7 +1520,7 @@
 	struct intel_vgpu_mm *mm;
 	int ret;
 
-	mm = kzalloc(sizeof(*mm), GFP_ATOMIC);
+	mm = kzalloc(sizeof(*mm), GFP_KERNEL);
 	if (!mm) {
 		ret = -ENOMEM;
 		goto fail;
@@ -1886,30 +1874,27 @@
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	int page_entry_num = GTT_PAGE_SIZE >>
 				vgpu->gvt->device_info.gtt_entry_size_shift;
-	struct page *scratch_pt;
+	void *scratch_pt;
 	unsigned long mfn;
 	int i;
-	void *p;
 
 	if (WARN_ON(type < GTT_TYPE_PPGTT_PTE_PT || type >= GTT_TYPE_MAX))
 		return -EINVAL;
 
-	scratch_pt = alloc_page(GFP_KERNEL | GFP_ATOMIC | __GFP_ZERO);
+	scratch_pt = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!scratch_pt) {
 		gvt_err("fail to allocate scratch page\n");
 		return -ENOMEM;
 	}
 
-	p = kmap_atomic(scratch_pt);
-	mfn = intel_gvt_hypervisor_virt_to_mfn(p);
+	mfn = intel_gvt_hypervisor_virt_to_mfn(scratch_pt);
 	if (mfn == INTEL_GVT_INVALID_ADDR) {
-		gvt_err("fail to translate vaddr:0x%llx\n", (u64)p);
-		kunmap_atomic(p);
-		__free_page(scratch_pt);
+		gvt_err("fail to translate vaddr:0x%lx\n", (unsigned long)scratch_pt);
+		free_page((unsigned long)scratch_pt);
 		return -EFAULT;
 	}
 	gtt->scratch_pt[type].page_mfn = mfn;
-	gtt->scratch_pt[type].page = scratch_pt;
+	gtt->scratch_pt[type].page = virt_to_page(scratch_pt);
 	gvt_dbg_mm("vgpu%d create scratch_pt: type %d mfn=0x%lx\n",
 			vgpu->id, type, mfn);
 
@@ -1918,7 +1903,7 @@
 	 * scratch_pt[type] indicate the scratch pt/scratch page used by the
 	 * 'type' pt.
 	 * e.g. scratch_pt[GTT_TYPE_PPGTT_PDE_PT] is used by
-	 * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scatch_pt it self
+	 * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scratch_pt it self
 	 * is GTT_TYPE_PPGTT_PTE_PT, and full filled by scratch page mfn.
 	 */
 	if (type > GTT_TYPE_PPGTT_PTE_PT && type < GTT_TYPE_MAX) {
@@ -1936,11 +1921,9 @@
 			se.val64 |= PPAT_CACHED_INDEX;
 
 		for (i = 0; i < page_entry_num; i++)
-			ops->set_entry(p, &se, i, false, 0, vgpu);
+			ops->set_entry(scratch_pt, &se, i, false, 0, vgpu);
 	}
 
-	kunmap_atomic(p);
-
 	return 0;
 }
 
@@ -1998,6 +1981,8 @@
 	INIT_LIST_HEAD(&gtt->oos_page_list_head);
 	INIT_LIST_HEAD(&gtt->post_shadow_list_head);
 
+	intel_vgpu_reset_ggtt(vgpu);
+
 	ggtt_mm = intel_vgpu_create_mm(vgpu, INTEL_GVT_MM_GGTT,
 			NULL, 1, 0);
 	if (IS_ERR(ggtt_mm)) {
@@ -2206,6 +2191,7 @@
 int intel_gvt_init_gtt(struct intel_gvt *gvt)
 {
 	int ret;
+	void *page;
 
 	gvt_dbg_core("init gtt\n");
 
@@ -2218,6 +2204,20 @@
 		return -ENODEV;
 	}
 
+	page = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!page) {
+		gvt_err("fail to allocate scratch ggtt page\n");
+		return -ENOMEM;
+	}
+	gvt->gtt.scratch_ggtt_page = virt_to_page(page);
+
+	gvt->gtt.scratch_ggtt_mfn = intel_gvt_hypervisor_virt_to_mfn(page);
+	if (gvt->gtt.scratch_ggtt_mfn == INTEL_GVT_INVALID_ADDR) {
+		gvt_err("fail to translate scratch ggtt page\n");
+		__free_page(gvt->gtt.scratch_ggtt_page);
+		return -EFAULT;
+	}
+
 	if (enable_out_of_sync) {
 		ret = setup_spt_oos(gvt);
 		if (ret) {
@@ -2239,6 +2239,68 @@
  */
 void intel_gvt_clean_gtt(struct intel_gvt *gvt)
 {
+	__free_page(gvt->gtt.scratch_ggtt_page);
+
 	if (enable_out_of_sync)
 		clean_spt_oos(gvt);
 }
+
+/**
+ * intel_vgpu_reset_ggtt - reset the GGTT entry
+ * @vgpu: a vGPU
+ *
+ * This function is called at the vGPU create stage
+ * to reset all the GGTT entries.
+ *
+ */
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	u32 index;
+	u32 offset;
+	u32 num_entries;
+	struct intel_gvt_gtt_entry e;
+
+	memset(&e, 0, sizeof(struct intel_gvt_gtt_entry));
+	e.type = GTT_TYPE_GGTT_PTE;
+	ops->set_pfn(&e, gvt->gtt.scratch_ggtt_mfn);
+	e.val64 |= _PAGE_PRESENT;
+
+	index = vgpu_aperture_gmadr_base(vgpu) >> PAGE_SHIFT;
+	num_entries = vgpu_aperture_sz(vgpu) >> PAGE_SHIFT;
+	for (offset = 0; offset < num_entries; offset++)
+		ops->set_entry(NULL, &e, index + offset, false, 0, vgpu);
+
+	index = vgpu_hidden_gmadr_base(vgpu) >> PAGE_SHIFT;
+	num_entries = vgpu_hidden_sz(vgpu) >> PAGE_SHIFT;
+	for (offset = 0; offset < num_entries; offset++)
+		ops->set_entry(NULL, &e, index + offset, false, 0, vgpu);
+}
+
+/**
+ * intel_vgpu_reset_gtt - reset the all GTT related status
+ * @vgpu: a vGPU
+ * @dmlr: true for vGPU Device Model Level Reset, false for GT Reset
+ *
+ * This function is called from vfio core to reset reset all
+ * GTT related status, including GGTT, PPGTT, scratch page.
+ *
+ */
+void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr)
+{
+	int i;
+
+	ppgtt_free_all_shadow_page(vgpu);
+	if (!dmlr)
+		return;
+
+	intel_vgpu_reset_ggtt(vgpu);
+
+	/* clear scratch page for security */
+	for (i = GTT_TYPE_PPGTT_PTE_PT; i < GTT_TYPE_MAX; i++) {
+		if (vgpu->gtt.scratch_pt[i].page != NULL)
+			memset(page_address(vgpu->gtt.scratch_pt[i].page),
+				0, PAGE_SIZE);
+	}
+}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index d250013..f88eb5e 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -81,6 +81,9 @@
 	struct list_head oos_page_use_list_head;
 	struct list_head oos_page_free_list_head;
 	struct list_head mm_lru_list_head;
+
+	struct page *scratch_ggtt_page;
+	unsigned long scratch_ggtt_mfn;
 };
 
 enum {
@@ -202,8 +205,10 @@
 
 extern int intel_vgpu_init_gtt(struct intel_vgpu *vgpu);
 extern void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu);
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu);
 
 extern int intel_gvt_init_gtt(struct intel_gvt *gvt);
+extern void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr);
 extern void intel_gvt_clean_gtt(struct intel_gvt *gvt);
 
 extern struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 398877c..e6bf5c5 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -201,6 +201,8 @@
 	intel_gvt_hypervisor_host_exit(&dev_priv->drm.pdev->dev, gvt);
 	intel_gvt_clean_vgpu_types(gvt);
 
+	idr_destroy(&gvt->vgpu_idr);
+
 	kfree(dev_priv->gvt);
 	dev_priv->gvt = NULL;
 }
@@ -237,6 +239,8 @@
 
 	gvt_dbg_core("init gvt device\n");
 
+	idr_init(&gvt->vgpu_idr);
+
 	mutex_init(&gvt->lock);
 	gvt->dev_priv = dev_priv;
 
@@ -244,7 +248,7 @@
 
 	ret = intel_gvt_setup_mmio_info(gvt);
 	if (ret)
-		return ret;
+		goto out_clean_idr;
 
 	ret = intel_gvt_load_firmware(gvt);
 	if (ret)
@@ -313,6 +317,8 @@
 	intel_gvt_free_firmware(gvt);
 out_clean_mmio_info:
 	intel_gvt_clean_mmio_info(gvt);
+out_clean_idr:
+	idr_destroy(&gvt->vgpu_idr);
 	kfree(gvt);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index ad0e936..e227caf 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -175,6 +175,7 @@
 		struct notifier_block group_notifier;
 		struct kvm *kvm;
 		struct work_struct release_work;
+		atomic_t released;
 	} vdev;
 #endif
 };
@@ -322,6 +323,7 @@
 
 int intel_vgpu_alloc_resource(struct intel_vgpu *vgpu,
 			      struct intel_vgpu_creation_params *param);
+void intel_vgpu_reset_resource(struct intel_vgpu *vgpu);
 void intel_vgpu_free_resource(struct intel_vgpu *vgpu);
 void intel_vgpu_write_fence(struct intel_vgpu *vgpu,
 	u32 fence, u64 value);
@@ -374,6 +376,8 @@
 struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 					 struct intel_vgpu_type *type);
 void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu);
+void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
+				 unsigned int engine_mask);
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
 
 
@@ -410,6 +414,10 @@
 int intel_gvt_ggtt_h2g_index(struct intel_vgpu *vgpu, unsigned long h_index,
 			     unsigned long *g_index);
 
+void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
+		bool primary);
+void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu);
+
 int intel_vgpu_emulate_cfg_read(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes);
 
@@ -423,7 +431,6 @@
 int intel_vgpu_init_opregion(struct intel_vgpu *vgpu, u32 gpa);
 
 int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci);
-int setup_vgpu_mmio(struct intel_vgpu *vgpu);
 void populate_pvinfo_page(struct intel_vgpu *vgpu);
 
 struct intel_gvt_ops {
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 5228097..ab2ea15 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -93,7 +93,8 @@
 static int new_mmio_info(struct intel_gvt *gvt,
 		u32 offset, u32 flags, u32 size,
 		u32 addr_mask, u32 ro_mask, u32 device,
-		void *read, void *write)
+		int (*read)(struct intel_vgpu *, unsigned int, void *, unsigned int),
+		int (*write)(struct intel_vgpu *, unsigned int, void *, unsigned int))
 {
 	struct intel_gvt_mmio_info *info, *p;
 	u32 start, end, i;
@@ -219,7 +220,7 @@
 		default:
 			/*should not hit here*/
 			gvt_err("invalid forcewake offset 0x%x\n", offset);
-			return 1;
+			return -EINVAL;
 		}
 	} else {
 		ack_reg_offset = FORCEWAKE_ACK_HSW_REG;
@@ -230,77 +231,45 @@
 	return 0;
 }
 
-static int handle_device_reset(struct intel_vgpu *vgpu, unsigned int offset,
-		void *p_data, unsigned int bytes, unsigned long bitmap)
-{
-	struct intel_gvt_workload_scheduler *scheduler =
-		&vgpu->gvt->scheduler;
-
-	vgpu->resetting = true;
-
-	intel_vgpu_stop_schedule(vgpu);
-	/*
-	 * The current_vgpu will set to NULL after stopping the
-	 * scheduler when the reset is triggered by current vgpu.
-	 */
-	if (scheduler->current_vgpu == NULL) {
-		mutex_unlock(&vgpu->gvt->lock);
-		intel_gvt_wait_vgpu_idle(vgpu);
-		mutex_lock(&vgpu->gvt->lock);
-	}
-
-	intel_vgpu_reset_execlist(vgpu, bitmap);
-
-	/* full GPU reset */
-	if (bitmap == 0xff) {
-		mutex_unlock(&vgpu->gvt->lock);
-		intel_vgpu_clean_gtt(vgpu);
-		mutex_lock(&vgpu->gvt->lock);
-		setup_vgpu_mmio(vgpu);
-		populate_pvinfo_page(vgpu);
-		intel_vgpu_init_gtt(vgpu);
-	}
-
-	vgpu->resetting = false;
-
-	return 0;
-}
-
 static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
-		void *p_data, unsigned int bytes)
+			    void *p_data, unsigned int bytes)
 {
+	unsigned int engine_mask = 0;
 	u32 data;
-	u64 bitmap = 0;
 
 	write_vreg(vgpu, offset, p_data, bytes);
 	data = vgpu_vreg(vgpu, offset);
 
 	if (data & GEN6_GRDOM_FULL) {
 		gvt_dbg_mmio("vgpu%d: request full GPU reset\n", vgpu->id);
-		bitmap = 0xff;
+		engine_mask = ALL_ENGINES;
+	} else {
+		if (data & GEN6_GRDOM_RENDER) {
+			gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id);
+			engine_mask |= (1 << RCS);
+		}
+		if (data & GEN6_GRDOM_MEDIA) {
+			gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id);
+			engine_mask |= (1 << VCS);
+		}
+		if (data & GEN6_GRDOM_BLT) {
+			gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id);
+			engine_mask |= (1 << BCS);
+		}
+		if (data & GEN6_GRDOM_VECS) {
+			gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id);
+			engine_mask |= (1 << VECS);
+		}
+		if (data & GEN8_GRDOM_MEDIA2) {
+			gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id);
+			if (HAS_BSD2(vgpu->gvt->dev_priv))
+				engine_mask |= (1 << VCS2);
+		}
 	}
-	if (data & GEN6_GRDOM_RENDER) {
-		gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id);
-		bitmap |= (1 << RCS);
-	}
-	if (data & GEN6_GRDOM_MEDIA) {
-		gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id);
-		bitmap |= (1 << VCS);
-	}
-	if (data & GEN6_GRDOM_BLT) {
-		gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id);
-		bitmap |= (1 << BCS);
-	}
-	if (data & GEN6_GRDOM_VECS) {
-		gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id);
-		bitmap |= (1 << VECS);
-	}
-	if (data & GEN8_GRDOM_MEDIA2) {
-		gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id);
-		if (HAS_BSD2(vgpu->gvt->dev_priv))
-			bitmap |= (1 << VCS2);
-	}
-	return handle_device_reset(vgpu, offset, p_data, bytes, bitmap);
+
+	intel_gvt_reset_vgpu_locked(vgpu, false, engine_mask);
+
+	return 0;
 }
 
 static int gmbus_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
@@ -974,7 +943,7 @@
 	return 0;
 }
 
-static bool sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+static int sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
 	u32 data;
@@ -1366,7 +1335,6 @@
 static int gvt_reg_tlb_control_handler(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
-	int rc = 0;
 	unsigned int id = 0;
 
 	write_vreg(vgpu, offset, p_data, bytes);
@@ -1389,12 +1357,11 @@
 		id = VECS;
 		break;
 	default:
-		rc = -EINVAL;
-		break;
+		return -EINVAL;
 	}
 	set_bit(id, (void *)vgpu->tlb_handle_pending);
 
-	return rc;
+	return 0;
 }
 
 static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 4dd6722..0c9234a 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -114,12 +114,15 @@
 static kvm_pfn_t gvt_cache_find(struct intel_vgpu *vgpu, gfn_t gfn)
 {
 	struct gvt_dma *entry;
+	kvm_pfn_t pfn;
 
 	mutex_lock(&vgpu->vdev.cache_lock);
-	entry = __gvt_cache_find(vgpu, gfn);
-	mutex_unlock(&vgpu->vdev.cache_lock);
 
-	return entry == NULL ? 0 : entry->pfn;
+	entry = __gvt_cache_find(vgpu, gfn);
+	pfn = (entry == NULL) ? 0 : entry->pfn;
+
+	mutex_unlock(&vgpu->vdev.cache_lock);
+	return pfn;
 }
 
 static void gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, kvm_pfn_t pfn)
@@ -166,7 +169,7 @@
 
 static void gvt_cache_remove(struct intel_vgpu *vgpu, gfn_t gfn)
 {
-	struct device *dev = &vgpu->vdev.mdev->dev;
+	struct device *dev = mdev_dev(vgpu->vdev.mdev);
 	struct gvt_dma *this;
 	unsigned long g1;
 	int rc;
@@ -195,7 +198,7 @@
 {
 	struct gvt_dma *dma;
 	struct rb_node *node = NULL;
-	struct device *dev = &vgpu->vdev.mdev->dev;
+	struct device *dev = mdev_dev(vgpu->vdev.mdev);
 	unsigned long gfn;
 
 	mutex_lock(&vgpu->vdev.cache_lock);
@@ -395,21 +398,24 @@
 	struct intel_vgpu_type *type;
 	struct device *pdev;
 	void *gvt;
+	int ret;
 
-	pdev = mdev->parent->dev;
+	pdev = mdev_parent_dev(mdev);
 	gvt = kdev_to_i915(pdev)->gvt;
 
 	type = intel_gvt_find_vgpu_type(gvt, kobject_name(kobj));
 	if (!type) {
 		gvt_err("failed to find type %s to create\n",
 						kobject_name(kobj));
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	vgpu = intel_gvt_ops->vgpu_create(gvt, type);
 	if (IS_ERR_OR_NULL(vgpu)) {
-		gvt_err("create intel vgpu failed\n");
-		return -EINVAL;
+		ret = vgpu == NULL ? -EFAULT : PTR_ERR(vgpu);
+		gvt_err("failed to create intel vgpu: %d\n", ret);
+		goto out;
 	}
 
 	INIT_WORK(&vgpu->vdev.release_work, intel_vgpu_release_work);
@@ -418,8 +424,11 @@
 	mdev_set_drvdata(mdev, vgpu);
 
 	gvt_dbg_core("intel_vgpu_create succeeded for mdev: %s\n",
-		     dev_name(&mdev->dev));
-	return 0;
+		     dev_name(mdev_dev(mdev)));
+	ret = 0;
+
+out:
+	return ret;
 }
 
 static int intel_vgpu_remove(struct mdev_device *mdev)
@@ -482,7 +491,7 @@
 	vgpu->vdev.group_notifier.notifier_call = intel_vgpu_group_notifier;
 
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(&mdev->dev, VFIO_IOMMU_NOTIFY, &events,
+	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, &events,
 				&vgpu->vdev.iommu_notifier);
 	if (ret != 0) {
 		gvt_err("vfio_register_notifier for iommu failed: %d\n", ret);
@@ -490,17 +499,26 @@
 	}
 
 	events = VFIO_GROUP_NOTIFY_SET_KVM;
-	ret = vfio_register_notifier(&mdev->dev, VFIO_GROUP_NOTIFY, &events,
+	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &events,
 				&vgpu->vdev.group_notifier);
 	if (ret != 0) {
 		gvt_err("vfio_register_notifier for group failed: %d\n", ret);
 		goto undo_iommu;
 	}
 
-	return kvmgt_guest_init(mdev);
+	ret = kvmgt_guest_init(mdev);
+	if (ret)
+		goto undo_group;
+
+	atomic_set(&vgpu->vdev.released, 0);
+	return ret;
+
+undo_group:
+	vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY,
+					&vgpu->vdev.group_notifier);
 
 undo_iommu:
-	vfio_unregister_notifier(&mdev->dev, VFIO_IOMMU_NOTIFY,
+	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
 					&vgpu->vdev.iommu_notifier);
 out:
 	return ret;
@@ -509,17 +527,26 @@
 static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 {
 	struct kvmgt_guest_info *info;
+	int ret;
 
 	if (!handle_valid(vgpu->handle))
 		return;
 
-	vfio_unregister_notifier(&vgpu->vdev.mdev->dev, VFIO_IOMMU_NOTIFY,
+	if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1))
+		return;
+
+	ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY,
 					&vgpu->vdev.iommu_notifier);
-	vfio_unregister_notifier(&vgpu->vdev.mdev->dev, VFIO_GROUP_NOTIFY,
+	WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret);
+
+	ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_GROUP_NOTIFY,
 					&vgpu->vdev.group_notifier);
+	WARN(ret, "vfio_unregister_notifier for group failed: %d\n", ret);
 
 	info = (struct kvmgt_guest_info *)vgpu->handle;
 	kvmgt_guest_exit(info);
+
+	vgpu->vdev.kvm = NULL;
 	vgpu->handle = 0;
 }
 
@@ -534,6 +561,7 @@
 {
 	struct intel_vgpu *vgpu = container_of(work, struct intel_vgpu,
 					vdev.release_work);
+
 	__intel_vgpu_release(vgpu);
 }
 
@@ -1089,7 +1117,7 @@
 	return 0;
 }
 
-static const struct parent_ops intel_vgpu_ops = {
+static const struct mdev_parent_ops intel_vgpu_ops = {
 	.supported_type_groups	= intel_vgpu_type_groups,
 	.create			= intel_vgpu_create,
 	.remove			= intel_vgpu_remove,
@@ -1134,6 +1162,10 @@
 
 	idx = srcu_read_lock(&kvm->srcu);
 	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
 
 	spin_lock(&kvm->mmu_lock);
 
@@ -1164,6 +1196,10 @@
 
 	idx = srcu_read_lock(&kvm->srcu);
 	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
 
 	spin_lock(&kvm->mmu_lock);
 
@@ -1311,18 +1347,14 @@
 
 static bool kvmgt_guest_exit(struct kvmgt_guest_info *info)
 {
-	struct intel_vgpu *vgpu;
-
 	if (!info) {
 		gvt_err("kvmgt_guest_info invalid\n");
 		return false;
 	}
 
-	vgpu = info->vgpu;
-
 	kvm_page_track_unregister_notifier(info->kvm, &info->track_node);
 	kvmgt_protect_table_destroy(info);
-	gvt_cache_destroy(vgpu);
+	gvt_cache_destroy(info->vgpu);
 	vfree(info);
 
 	return true;
@@ -1372,7 +1404,7 @@
 		return pfn;
 
 	pfn = INTEL_GVT_INVALID_ADDR;
-	dev = &info->vgpu->vdev.mdev->dev;
+	dev = mdev_dev(info->vgpu->vdev.mdev);
 	rc = vfio_pin_pages(dev, &gfn, 1, IOMMU_READ | IOMMU_WRITE, &pfn);
 	if (rc != 1) {
 		gvt_err("vfio_pin_pages failed for gfn 0x%lx: %d\n", gfn, rc);
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 09c9450..4df078b 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -125,25 +125,12 @@
 	if (WARN_ON(!reg_is_mmio(gvt, offset + bytes - 1)))
 		goto err;
 
-	mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
-	if (!mmio && !vgpu->mmio.disable_warn_untrack) {
-		gvt_err("vgpu%d: read untracked MMIO %x len %d val %x\n",
-				vgpu->id, offset, bytes, *(u32 *)p_data);
-
-		if (offset == 0x206c) {
-			gvt_err("------------------------------------------\n");
-			gvt_err("vgpu%d: likely triggers a gfx reset\n",
-			vgpu->id);
-			gvt_err("------------------------------------------\n");
-			vgpu->mmio.disable_warn_untrack = true;
-		}
-	}
-
 	if (!intel_gvt_mmio_is_unalign(gvt, offset)) {
 		if (WARN_ON(!IS_ALIGNED(offset, bytes)))
 			goto err;
 	}
 
+	mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
 	if (mmio) {
 		if (!intel_gvt_mmio_is_unalign(gvt, mmio->offset)) {
 			if (WARN_ON(offset + bytes > mmio->offset + mmio->size))
@@ -152,9 +139,23 @@
 				goto err;
 		}
 		ret = mmio->read(vgpu, offset, p_data, bytes);
-	} else
+	} else {
 		ret = intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
 
+		if (!vgpu->mmio.disable_warn_untrack) {
+			gvt_err("vgpu%d: read untracked MMIO %x(%dB) val %x\n",
+				vgpu->id, offset, bytes, *(u32 *)p_data);
+
+			if (offset == 0x206c) {
+				gvt_err("------------------------------------------\n");
+				gvt_err("vgpu%d: likely triggers a gfx reset\n",
+					vgpu->id);
+				gvt_err("------------------------------------------\n");
+				vgpu->mmio.disable_warn_untrack = true;
+			}
+		}
+	}
+
 	if (ret)
 		goto err;
 
@@ -302,3 +303,56 @@
 	mutex_unlock(&gvt->lock);
 	return ret;
 }
+
+
+/**
+ * intel_vgpu_reset_mmio - reset virtual MMIO space
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	const struct intel_gvt_device_info *info = &gvt->device_info;
+
+	memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size);
+	memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size);
+
+	vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0;
+
+	/* set the bit 0:2(Core C-State ) to C0 */
+	vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
+}
+
+/**
+ * intel_vgpu_init_mmio - init MMIO  space
+ * @vgpu: a vGPU
+ *
+ * Returns:
+ * Zero on success, negative error code if failed
+ */
+int intel_vgpu_init_mmio(struct intel_vgpu *vgpu)
+{
+	const struct intel_gvt_device_info *info = &vgpu->gvt->device_info;
+
+	vgpu->mmio.vreg = vzalloc(info->mmio_size * 2);
+	if (!vgpu->mmio.vreg)
+		return -ENOMEM;
+
+	vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size;
+
+	intel_vgpu_reset_mmio(vgpu);
+
+	return 0;
+}
+
+/**
+ * intel_vgpu_clean_mmio - clean MMIO space
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu)
+{
+	vfree(vgpu->mmio.vreg);
+	vgpu->mmio.vreg = vgpu->mmio.sreg = NULL;
+}
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 87d5b5e..3bc620f 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -86,6 +86,10 @@
 	*offset; \
 })
 
+int intel_vgpu_init_mmio(struct intel_vgpu *vgpu);
+void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu);
+void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu);
+
 int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa);
 
 int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, u64 pa,
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index d2a0fbc..d9fb41a 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -36,9 +36,9 @@
 			vgpu->id))
 		return -EINVAL;
 
-	vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_ATOMIC |
-			GFP_DMA32 | __GFP_ZERO,
-			INTEL_GVT_OPREGION_PORDER);
+	vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_KERNEL |
+			__GFP_ZERO,
+			get_order(INTEL_GVT_OPREGION_SIZE));
 
 	if (!vgpu_opregion(vgpu)->va)
 		return -ENOMEM;
@@ -65,7 +65,7 @@
 	int i, ret;
 
 	for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++) {
-		mfn = intel_gvt_hypervisor_virt_to_mfn(vgpu_opregion(vgpu)
+		mfn = intel_gvt_hypervisor_virt_to_mfn(vgpu_opregion(vgpu)->va
 			+ i * PAGE_SIZE);
 		if (mfn == INTEL_GVT_INVALID_ADDR) {
 			gvt_err("fail to get MFN from VA\n");
@@ -97,7 +97,7 @@
 	if (intel_gvt_host.hypervisor_type == INTEL_GVT_HYPERVISOR_XEN) {
 		map_vgpu_opregion(vgpu, false);
 		free_pages((unsigned long)vgpu_opregion(vgpu)->va,
-				INTEL_GVT_OPREGION_PORDER);
+				get_order(INTEL_GVT_OPREGION_SIZE));
 
 		vgpu_opregion(vgpu)->va = NULL;
 	}
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 0dfe789..fbd023a 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -50,8 +50,7 @@
 #define INTEL_GVT_OPREGION_PARM                   0x204
 
 #define INTEL_GVT_OPREGION_PAGES	2
-#define INTEL_GVT_OPREGION_PORDER	1
-#define INTEL_GVT_OPREGION_SIZE		(2 * 4096)
+#define INTEL_GVT_OPREGION_SIZE		(INTEL_GVT_OPREGION_PAGES * PAGE_SIZE)
 
 #define VGT_SPRSTRIDE(pipe)	_PIPE(pipe, _SPRA_STRIDE, _PLANE_STRIDE_2_B)
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 4db2422..e91885d 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -350,13 +350,15 @@
 {
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct intel_vgpu_workload *workload;
+	struct intel_vgpu *vgpu;
 	int event;
 
 	mutex_lock(&gvt->lock);
 
 	workload = scheduler->current_workload[ring_id];
+	vgpu = workload->vgpu;
 
-	if (!workload->status && !workload->vgpu->resetting) {
+	if (!workload->status && !vgpu->resetting) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
@@ -364,8 +366,7 @@
 
 		for_each_set_bit(event, workload->pending_events,
 				 INTEL_GVT_EVENT_MAX)
-			intel_vgpu_trigger_virtual_event(workload->vgpu,
-					event);
+			intel_vgpu_trigger_virtual_event(vgpu, event);
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -373,11 +374,10 @@
 
 	scheduler->current_workload[ring_id] = NULL;
 
-	atomic_dec(&workload->vgpu->running_workload_num);
-
 	list_del_init(&workload->list);
 	workload->complete(workload);
 
+	atomic_dec(&vgpu->running_workload_num);
 	wake_up(&scheduler->workload_complete_wq);
 	mutex_unlock(&gvt->lock);
 }
@@ -459,11 +459,11 @@
 		gvt_dbg_sched("will complete workload %p\n, status: %d\n",
 				workload, workload->status);
 
-		complete_current_workload(gvt, ring_id);
-
 		if (workload->req)
 			i915_gem_request_put(fetch_and_zero(&workload->req));
 
+		complete_current_workload(gvt, ring_id);
+
 		if (need_force_wake)
 			intel_uncore_forcewake_put(gvt->dev_priv,
 					FORCEWAKE_ALL);
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 536d2b9..7295bc8 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -35,79 +35,6 @@
 #include "gvt.h"
 #include "i915_pvinfo.h"
 
-static void clean_vgpu_mmio(struct intel_vgpu *vgpu)
-{
-	vfree(vgpu->mmio.vreg);
-	vgpu->mmio.vreg = vgpu->mmio.sreg = NULL;
-}
-
-int setup_vgpu_mmio(struct intel_vgpu *vgpu)
-{
-	struct intel_gvt *gvt = vgpu->gvt;
-	const struct intel_gvt_device_info *info = &gvt->device_info;
-
-	if (vgpu->mmio.vreg)
-		memset(vgpu->mmio.vreg, 0, info->mmio_size * 2);
-	else {
-		vgpu->mmio.vreg = vzalloc(info->mmio_size * 2);
-		if (!vgpu->mmio.vreg)
-			return -ENOMEM;
-	}
-
-	vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size;
-
-	memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size);
-	memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size);
-
-	vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0;
-
-	/* set the bit 0:2(Core C-State ) to C0 */
-	vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
-	return 0;
-}
-
-static void setup_vgpu_cfg_space(struct intel_vgpu *vgpu,
-	struct intel_vgpu_creation_params *param)
-{
-	struct intel_gvt *gvt = vgpu->gvt;
-	const struct intel_gvt_device_info *info = &gvt->device_info;
-	u16 *gmch_ctl;
-	int i;
-
-	memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
-	       info->cfg_space_size);
-
-	if (!param->primary) {
-		vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] =
-			INTEL_GVT_PCI_CLASS_VGA_OTHER;
-		vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] =
-			INTEL_GVT_PCI_CLASS_VGA_OTHER;
-	}
-
-	/* Show guest that there isn't any stolen memory.*/
-	gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL);
-	*gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT);
-
-	intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2,
-				 gvt_aperture_pa_base(gvt), true);
-
-	vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO
-					     | PCI_COMMAND_MEMORY
-					     | PCI_COMMAND_MASTER);
-	/*
-	 * Clear the bar upper 32bit and let guest to assign the new value
-	 */
-	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
-	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
-	memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
-
-	for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
-		vgpu->cfg_space.bar[i].size = pci_resource_len(
-					      gvt->dev_priv->drm.pdev, i * 2);
-		vgpu->cfg_space.bar[i].tracked = false;
-	}
-}
-
 void populate_pvinfo_page(struct intel_vgpu *vgpu)
 {
 	/* setup the ballooning information */
@@ -177,7 +104,7 @@
 		if (low_avail / min_low == 0)
 			break;
 		gvt->types[i].low_gm_size = min_low;
-		gvt->types[i].high_gm_size = 3 * gvt->types[i].low_gm_size;
+		gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U));
 		gvt->types[i].fence = 4;
 		gvt->types[i].max_instance = low_avail / min_low;
 		gvt->types[i].avail_instance = gvt->types[i].max_instance;
@@ -217,7 +144,7 @@
 	 */
 	low_gm_avail = MB_TO_BYTES(256) - HOST_LOW_GM_SIZE -
 		gvt->gm.vgpu_allocated_low_gm_size;
-	high_gm_avail = MB_TO_BYTES(256) * 3 - HOST_HIGH_GM_SIZE -
+	high_gm_avail = MB_TO_BYTES(256) * 8UL - HOST_HIGH_GM_SIZE -
 		gvt->gm.vgpu_allocated_high_gm_size;
 	fence_avail = gvt_fence_sz(gvt) - HOST_FENCE -
 		gvt->fence.vgpu_allocated_fence_num;
@@ -268,7 +195,7 @@
 	intel_vgpu_clean_gtt(vgpu);
 	intel_gvt_hypervisor_detach_vgpu(vgpu);
 	intel_vgpu_free_resource(vgpu);
-	clean_vgpu_mmio(vgpu);
+	intel_vgpu_clean_mmio(vgpu);
 	vfree(vgpu);
 
 	intel_gvt_update_vgpu_types(gvt);
@@ -300,11 +227,11 @@
 	vgpu->gvt = gvt;
 	bitmap_zero(vgpu->tlb_handle_pending, I915_NUM_ENGINES);
 
-	setup_vgpu_cfg_space(vgpu, param);
+	intel_vgpu_init_cfg_space(vgpu, param->primary);
 
-	ret = setup_vgpu_mmio(vgpu);
+	ret = intel_vgpu_init_mmio(vgpu);
 	if (ret)
-		goto out_free_vgpu;
+		goto out_clean_idr;
 
 	ret = intel_vgpu_alloc_resource(vgpu, param);
 	if (ret)
@@ -354,7 +281,9 @@
 out_clean_vgpu_resource:
 	intel_vgpu_free_resource(vgpu);
 out_clean_vgpu_mmio:
-	clean_vgpu_mmio(vgpu);
+	intel_vgpu_clean_mmio(vgpu);
+out_clean_idr:
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
 out_free_vgpu:
 	vfree(vgpu);
 	mutex_unlock(&gvt->lock);
@@ -398,7 +327,75 @@
 }
 
 /**
- * intel_gvt_reset_vgpu - reset a virtual GPU
+ * intel_gvt_reset_vgpu_locked - reset a virtual GPU by DMLR or GT reset
+ * @vgpu: virtual GPU
+ * @dmlr: vGPU Device Model Level Reset or GT Reset
+ * @engine_mask: engines to reset for GT reset
+ *
+ * This function is called when user wants to reset a virtual GPU through
+ * device model reset or GT reset. The caller should hold the gvt lock.
+ *
+ * vGPU Device Model Level Reset (DMLR) simulates the PCI level reset to reset
+ * the whole vGPU to default state as when it is created. This vGPU function
+ * is required both for functionary and security concerns.The ultimate goal
+ * of vGPU FLR is that reuse a vGPU instance by virtual machines. When we
+ * assign a vGPU to a virtual machine we must isse such reset first.
+ *
+ * Full GT Reset and Per-Engine GT Reset are soft reset flow for GPU engines
+ * (Render, Blitter, Video, Video Enhancement). It is defined by GPU Spec.
+ * Unlike the FLR, GT reset only reset particular resource of a vGPU per
+ * the reset request. Guest driver can issue a GT reset by programming the
+ * virtual GDRST register to reset specific virtual GPU engine or all
+ * engines.
+ *
+ * The parameter dev_level is to identify if we will do DMLR or GT reset.
+ * The parameter engine_mask is to specific the engines that need to be
+ * resetted. If value ALL_ENGINES is given for engine_mask, it means
+ * the caller requests a full GT reset that we will reset all virtual
+ * GPU engines. For FLR, engine_mask is ignored.
+ */
+void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
+				 unsigned int engine_mask)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
+
+	gvt_dbg_core("------------------------------------------\n");
+	gvt_dbg_core("resseting vgpu%d, dmlr %d, engine_mask %08x\n",
+		     vgpu->id, dmlr, engine_mask);
+	vgpu->resetting = true;
+
+	intel_vgpu_stop_schedule(vgpu);
+	/*
+	 * The current_vgpu will set to NULL after stopping the
+	 * scheduler when the reset is triggered by current vgpu.
+	 */
+	if (scheduler->current_vgpu == NULL) {
+		mutex_unlock(&gvt->lock);
+		intel_gvt_wait_vgpu_idle(vgpu);
+		mutex_lock(&gvt->lock);
+	}
+
+	intel_vgpu_reset_execlist(vgpu, dmlr ? ALL_ENGINES : engine_mask);
+
+	/* full GPU reset or device model level reset */
+	if (engine_mask == ALL_ENGINES || dmlr) {
+		intel_vgpu_reset_gtt(vgpu, dmlr);
+		intel_vgpu_reset_resource(vgpu);
+		intel_vgpu_reset_mmio(vgpu);
+		populate_pvinfo_page(vgpu);
+
+		if (dmlr)
+			intel_vgpu_reset_cfg_space(vgpu);
+	}
+
+	vgpu->resetting = false;
+	gvt_dbg_core("reset vgpu%d done\n", vgpu->id);
+	gvt_dbg_core("------------------------------------------\n");
+}
+
+/**
+ * intel_gvt_reset_vgpu - reset a virtual GPU (Function Level)
  * @vgpu: virtual GPU
  *
  * This function is called when user wants to reset a virtual GPU.
@@ -406,4 +403,7 @@
  */
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu)
 {
+	mutex_lock(&vgpu->gvt->lock);
+	intel_gvt_reset_vgpu_locked(vgpu, true, 0);
+	mutex_unlock(&vgpu->gvt->lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4a31b7a..4b23a78 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -244,14 +244,16 @@
 
 static void
 __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
-				struct sg_table *pages)
+				struct sg_table *pages,
+				bool needs_clflush)
 {
 	GEM_BUG_ON(obj->mm.madv == __I915_MADV_PURGED);
 
 	if (obj->mm.madv == I915_MADV_DONTNEED)
 		obj->mm.dirty = false;
 
-	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0 &&
+	if (needs_clflush &&
+	    (obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0 &&
 	    !cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
 		drm_clflush_sg(pages);
 
@@ -263,7 +265,7 @@
 i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
-	__i915_gem_object_release_shmem(obj, pages);
+	__i915_gem_object_release_shmem(obj, pages, false);
 
 	if (obj->mm.dirty) {
 		struct address_space *mapping = obj->base.filp->f_mapping;
@@ -593,47 +595,21 @@
 		     struct drm_i915_gem_pwrite *args,
 		     struct drm_file *file)
 {
-	struct drm_device *dev = obj->base.dev;
 	void *vaddr = obj->phys_handle->vaddr + args->offset;
 	char __user *user_data = u64_to_user_ptr(args->data_ptr);
-	int ret;
 
 	/* We manually control the domain here and pretend that it
 	 * remains coherent i.e. in the GTT domain, like shmem_pwrite.
 	 */
-	lockdep_assert_held(&obj->base.dev->struct_mutex);
-	ret = i915_gem_object_wait(obj,
-				   I915_WAIT_INTERRUPTIBLE |
-				   I915_WAIT_LOCKED |
-				   I915_WAIT_ALL,
-				   MAX_SCHEDULE_TIMEOUT,
-				   to_rps_client(file));
-	if (ret)
-		return ret;
-
 	intel_fb_obj_invalidate(obj, ORIGIN_CPU);
-	if (__copy_from_user_inatomic_nocache(vaddr, user_data, args->size)) {
-		unsigned long unwritten;
-
-		/* The physical object once assigned is fixed for the lifetime
-		 * of the obj, so we can safely drop the lock and continue
-		 * to access vaddr.
-		 */
-		mutex_unlock(&dev->struct_mutex);
-		unwritten = copy_from_user(vaddr, user_data, args->size);
-		mutex_lock(&dev->struct_mutex);
-		if (unwritten) {
-			ret = -EFAULT;
-			goto out;
-		}
-	}
+	if (copy_from_user(vaddr, user_data, args->size))
+		return -EFAULT;
 
 	drm_clflush_virt_range(vaddr, args->size);
-	i915_gem_chipset_flush(to_i915(dev));
+	i915_gem_chipset_flush(to_i915(obj->base.dev));
 
-out:
 	intel_fb_obj_flush(obj, false, ORIGIN_CPU);
-	return ret;
+	return 0;
 }
 
 void *i915_gem_object_alloc(struct drm_device *dev)
@@ -2231,7 +2207,7 @@
 	struct sgt_iter sgt_iter;
 	struct page *page;
 
-	__i915_gem_object_release_shmem(obj, pages);
+	__i915_gem_object_release_shmem(obj, pages, true);
 
 	i915_gem_gtt_finish_pages(obj, pages);
 
@@ -2304,15 +2280,6 @@
 	mutex_unlock(&obj->mm.lock);
 }
 
-static unsigned int swiotlb_max_size(void)
-{
-#if IS_ENABLED(CONFIG_SWIOTLB)
-	return rounddown(swiotlb_nr_tbl() << IO_TLB_SHIFT, PAGE_SIZE);
-#else
-	return 0;
-#endif
-}
-
 static void i915_sg_trim(struct sg_table *orig_st)
 {
 	struct sg_table new_st;
@@ -2322,7 +2289,7 @@
 	if (orig_st->nents == orig_st->orig_nents)
 		return;
 
-	if (sg_alloc_table(&new_st, orig_st->nents, GFP_KERNEL))
+	if (sg_alloc_table(&new_st, orig_st->nents, GFP_KERNEL | __GFP_NOWARN))
 		return;
 
 	new_sg = new_st.sgl;
@@ -2360,7 +2327,7 @@
 	GEM_BUG_ON(obj->base.read_domains & I915_GEM_GPU_DOMAINS);
 	GEM_BUG_ON(obj->base.write_domain & I915_GEM_GPU_DOMAINS);
 
-	max_segment = swiotlb_max_size();
+	max_segment = swiotlb_max_segment();
 	if (!max_segment)
 		max_segment = rounddown(UINT_MAX, PAGE_SIZE);
 
@@ -2728,6 +2695,7 @@
 	struct drm_i915_gem_request *request;
 	struct i915_gem_context *incomplete_ctx;
 	struct intel_timeline *timeline;
+	unsigned long flags;
 	bool ring_hung;
 
 	if (engine->irq_seqno_barrier)
@@ -2763,13 +2731,20 @@
 	if (i915_gem_context_is_default(incomplete_ctx))
 		return;
 
+	timeline = i915_gem_context_lookup_timeline(incomplete_ctx, engine);
+
+	spin_lock_irqsave(&engine->timeline->lock, flags);
+	spin_lock(&timeline->lock);
+
 	list_for_each_entry_continue(request, &engine->timeline->requests, link)
 		if (request->ctx == incomplete_ctx)
 			reset_request(request);
 
-	timeline = i915_gem_context_lookup_timeline(incomplete_ctx, engine);
 	list_for_each_entry(request, &timeline->requests, link)
 		reset_request(request);
+
+	spin_unlock(&timeline->lock);
+	spin_unlock_irqrestore(&engine->timeline->lock, flags);
 }
 
 void i915_gem_reset(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index bd08814..d534a31 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -199,6 +199,7 @@
 	}
 
 	/* Unbinding will emit any required flushes */
+	ret = 0;
 	while (!list_empty(&eviction_list)) {
 		vma = list_first_entry(&eviction_list,
 				       struct i915_vma,
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index e2b077d..d229f47d 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -413,6 +413,25 @@
 	rcu_assign_pointer(active->request, request);
 }
 
+/**
+ * i915_gem_active_set_retire_fn - updates the retirement callback
+ * @active - the active tracker
+ * @fn - the routine called when the request is retired
+ * @mutex - struct_mutex used to guard retirements
+ *
+ * i915_gem_active_set_retire_fn() updates the function pointer that
+ * is called when the final request associated with the @active tracker
+ * is retired.
+ */
+static inline void
+i915_gem_active_set_retire_fn(struct i915_gem_active *active,
+			      i915_gem_retire_fn fn,
+			      struct mutex *mutex)
+{
+	lockdep_assert_held(mutex);
+	active->retire = fn ?: i915_gem_retire_noop;
+}
+
 static inline struct drm_i915_gem_request *
 __i915_gem_active_peek(const struct i915_gem_active *active)
 {
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 6daad86..8d702cf 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2967,6 +2967,9 @@
 	unsigned int rotation = plane_state->base.rotation;
 	int ret;
 
+	if (!plane_state->base.visible)
+		return 0;
+
 	/* Rotate src coordinates to match rotated GTT view */
 	if (drm_rotation_90_or_270(rotation))
 		drm_rect_rotate(&plane_state->base.src,
@@ -16791,7 +16794,6 @@
 
 	for_each_intel_crtc(dev, crtc) {
 		struct intel_crtc_state *crtc_state = crtc->config;
-		int pixclk = 0;
 
 		__drm_atomic_helper_crtc_destroy_state(&crtc_state->base);
 		memset(crtc_state, 0, sizeof(*crtc_state));
@@ -16803,23 +16805,9 @@
 		crtc->base.enabled = crtc_state->base.enable;
 		crtc->active = crtc_state->base.active;
 
-		if (crtc_state->base.active) {
+		if (crtc_state->base.active)
 			dev_priv->active_crtcs |= 1 << crtc->pipe;
 
-			if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
-				pixclk = ilk_pipe_pixel_rate(crtc_state);
-			else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-				pixclk = crtc_state->base.adjusted_mode.crtc_clock;
-			else
-				WARN_ON(dev_priv->display.modeset_calc_cdclk);
-
-			/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
-			if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled)
-				pixclk = DIV_ROUND_UP(pixclk * 100, 95);
-		}
-
-		dev_priv->min_pixclk[crtc->pipe] = pixclk;
-
 		readout_plane_state(crtc);
 
 		DRM_DEBUG_KMS("[CRTC:%d:%s] hw state readout: %s\n",
@@ -16892,6 +16880,8 @@
 	}
 
 	for_each_intel_crtc(dev, crtc) {
+		int pixclk = 0;
+
 		crtc->base.hwmode = crtc->config->base.adjusted_mode;
 
 		memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
@@ -16919,10 +16909,23 @@
 			 */
 			crtc->base.state->mode.private_flags = I915_MODE_FLAG_INHERITED;
 
+			if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
+				pixclk = ilk_pipe_pixel_rate(crtc->config);
+			else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+				pixclk = crtc->config->base.adjusted_mode.crtc_clock;
+			else
+				WARN_ON(dev_priv->display.modeset_calc_cdclk);
+
+			/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
+			if (IS_BROADWELL(dev_priv) && crtc->config->ips_enabled)
+				pixclk = DIV_ROUND_UP(pixclk * 100, 95);
+
 			drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode);
 			update_scanline_offset(crtc);
 		}
 
+		dev_priv->min_pixclk[crtc->pipe] = pixclk;
+
 		intel_pipe_config_sanity_check(dev_priv, crtc->config);
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index d9bc19b..0b8e8eb 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -355,7 +355,8 @@
 				    struct intel_dp *intel_dp);
 static void
 intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
-					      struct intel_dp *intel_dp);
+					      struct intel_dp *intel_dp,
+					      bool force_disable_vdd);
 static void
 intel_dp_pps_init(struct drm_device *dev, struct intel_dp *intel_dp);
 
@@ -516,7 +517,7 @@
 
 	/* init power sequencer on this pipe and port */
 	intel_dp_init_panel_power_sequencer(dev, intel_dp);
-	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, true);
 
 	/*
 	 * Even vdd force doesn't work until we've made
@@ -553,7 +554,7 @@
 	 * Only the HW needs to be reprogrammed, the SW state is fixed and
 	 * has been setup during connector init.
 	 */
-	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, false);
 
 	return 0;
 }
@@ -636,7 +637,7 @@
 		      port_name(port), pipe_name(intel_dp->pps_pipe));
 
 	intel_dp_init_panel_power_sequencer(dev, intel_dp);
-	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, false);
 }
 
 void intel_power_sequencer_reset(struct drm_i915_private *dev_priv)
@@ -2912,7 +2913,7 @@
 
 	/* init power sequencer on this pipe and port */
 	intel_dp_init_panel_power_sequencer(dev, intel_dp);
-	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, true);
 }
 
 static void vlv_pre_enable_dp(struct intel_encoder *encoder,
@@ -5055,7 +5056,8 @@
 
 static void
 intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
-					      struct intel_dp *intel_dp)
+					      struct intel_dp *intel_dp,
+					      bool force_disable_vdd)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 pp_on, pp_off, pp_div, port_sel = 0;
@@ -5068,6 +5070,31 @@
 
 	intel_pps_get_registers(dev_priv, intel_dp, &regs);
 
+	/*
+	 * On some VLV machines the BIOS can leave the VDD
+	 * enabled even on power seqeuencers which aren't
+	 * hooked up to any port. This would mess up the
+	 * power domain tracking the first time we pick
+	 * one of these power sequencers for use since
+	 * edp_panel_vdd_on() would notice that the VDD was
+	 * already on and therefore wouldn't grab the power
+	 * domain reference. Disable VDD first to avoid this.
+	 * This also avoids spuriously turning the VDD on as
+	 * soon as the new power seqeuencer gets initialized.
+	 */
+	if (force_disable_vdd) {
+		u32 pp = ironlake_get_pp_control(intel_dp);
+
+		WARN(pp & PANEL_POWER_ON, "Panel power already on\n");
+
+		if (pp & EDP_FORCE_VDD)
+			DRM_DEBUG_KMS("VDD already on, disabling first\n");
+
+		pp &= ~EDP_FORCE_VDD;
+
+		I915_WRITE(regs.pp_ctrl, pp);
+	}
+
 	pp_on = (seq->t1_t3 << PANEL_POWER_UP_DELAY_SHIFT) |
 		(seq->t8 << PANEL_LIGHT_ON_DELAY_SHIFT);
 	pp_off = (seq->t9 << PANEL_LIGHT_OFF_DELAY_SHIFT) |
@@ -5122,7 +5149,7 @@
 		vlv_initial_power_sequencer_setup(intel_dp);
 	} else {
 		intel_dp_init_panel_power_sequencer(dev, intel_dp);
-		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
+		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, false);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index 3d546c0..b62e3f8 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -180,7 +180,7 @@
 
 	/* Enable polling and queue hotplug re-enabling. */
 	if (hpd_disabled) {
-		drm_kms_helper_poll_enable_locked(dev);
+		drm_kms_helper_poll_enable(dev);
 		mod_delayed_work(system_wq, &dev_priv->hotplug.reenable_work,
 				 msecs_to_jiffies(HPD_STORM_REENABLE_DELAY));
 	}
@@ -511,7 +511,7 @@
 	}
 
 	if (enabled)
-		drm_kms_helper_poll_enable_locked(dev);
+		drm_kms_helper_poll_enable(dev);
 
 	mutex_unlock(&dev->mode_config.mutex);
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d4961fa..beabc17 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -979,18 +979,8 @@
 						uint32_t *batch,
 						uint32_t index)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);
 
-	/*
-	 * WaDisableLSQCROPERFforOCL:kbl
-	 * This WA is implemented in skl_init_clock_gating() but since
-	 * this batch updates GEN8_L3SQCREG4 with default value we need to
-	 * set this bit here to retain the WA during flush.
-	 */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
-		l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;
-
 	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index fd0e4da..e589e17 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -216,7 +216,8 @@
 {
 	GEM_BUG_ON(i915_gem_active_peek(&overlay->last_flip,
 					&overlay->i915->drm.struct_mutex));
-	overlay->last_flip.retire = retire;
+	i915_gem_active_set_retire_fn(&overlay->last_flip, retire,
+				      &overlay->i915->drm.struct_mutex);
 	i915_gem_active_set(&overlay->last_flip, req);
 	i915_add_request(req);
 }
@@ -839,8 +840,8 @@
 	if (ret)
 		goto out_unpin;
 
-	i915_gem_track_fb(overlay->vma->obj, new_bo,
-			  INTEL_FRONTBUFFER_OVERLAY(pipe));
+	i915_gem_track_fb(overlay->vma ? overlay->vma->obj : NULL,
+			  vma->obj, INTEL_FRONTBUFFER_OVERLAY(pipe));
 
 	overlay->old_vma = overlay->vma;
 	overlay->vma = vma;
@@ -1430,6 +1431,8 @@
 	overlay->contrast = 75;
 	overlay->saturation = 146;
 
+	init_request_active(&overlay->last_flip, NULL);
+
 	regs = intel_overlay_map_regs(overlay);
 	if (!regs)
 		goto out_unpin_bo;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index aeb637d..91cb4c4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1095,14 +1095,6 @@
 		WA_SET_BIT_MASKED(HDC_CHICKEN0,
 				  HDC_FENCE_DEST_SLM_DISABLE);
 
-	/* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
-	 * involving this register should also be added to WA batch as required.
-	 */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
-		/* WaDisableLSQCROPERFforOCL:kbl */
-		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
-			   GEN8_LQSC_RO_PERF_DIS);
-
 	/* WaToEnableHwFixForPushConstHWBug:kbl */
 	if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
 		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index 4942ca0..7890e30 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -51,6 +51,9 @@
 	struct drm_crtc_state *crtc_state;
 	struct drm_rect clip = { 0, };
 
+	if (!state->crtc)
+		return 0;
+
 	crtc_state = drm_atomic_get_crtc_state(state->state, state->crtc);
 	if (IS_ERR(crtc_state))
 		return PTR_ERR(crtc_state);
diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c
index d836b22..f7c87017 100644
--- a/drivers/gpu/drm/meson/meson_venc.c
+++ b/drivers/gpu/drm/meson/meson_venc.c
@@ -38,6 +38,11 @@
  * - TV Panel encoding via ENCT
  */
 
+/* HHI Registers */
+#define HHI_VDAC_CNTL0		0x2F4 /* 0xbd offset in data sheet */
+#define HHI_VDAC_CNTL1		0x2F8 /* 0xbe offset in data sheet */
+#define HHI_HDMI_PHY_CNTL0	0x3a0 /* 0xe8 offset in data sheet */
+
 struct meson_cvbs_enci_mode meson_cvbs_enci_pal = {
 	.mode_tag = MESON_VENC_MODE_CVBS_PAL,
 	.hso_begin = 3,
@@ -242,6 +247,20 @@
 
 void meson_venc_init(struct meson_drm *priv)
 {
+	/* Disable CVBS VDAC */
+	regmap_write(priv->hhi, HHI_VDAC_CNTL0, 0);
+	regmap_write(priv->hhi, HHI_VDAC_CNTL1, 8);
+
+	/* Power Down Dacs */
+	writel_relaxed(0xff, priv->io_base + _REG(VENC_VDAC_SETTING));
+
+	/* Disable HDMI PHY */
+	regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, 0);
+
+	/* Disable HDMI */
+	writel_bits_relaxed(0x3, 0,
+			    priv->io_base + _REG(VPU_HDMI_SETTING));
+
 	/* Disable all encoders */
 	writel_relaxed(0, priv->io_base + _REG(ENCI_VIDEO_EN));
 	writel_relaxed(0, priv->io_base + _REG(ENCP_VIDEO_EN));
diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c
index c809c08..a2bcc70 100644
--- a/drivers/gpu/drm/meson/meson_venc_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c
@@ -167,7 +167,7 @@
 
 	/* Disable CVBS VDAC */
 	regmap_write(priv->hhi, HHI_VDAC_CNTL0, 0);
-	regmap_write(priv->hhi, HHI_VDAC_CNTL1, 0);
+	regmap_write(priv->hhi, HHI_VDAC_CNTL1, 8);
 }
 
 static void meson_venc_cvbs_encoder_enable(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index a181261..686a580 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -213,7 +213,14 @@
 void adreno_flush(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	uint32_t wptr = get_wptr(gpu->rb);
+	uint32_t wptr;
+
+	/*
+	 * Mask wptr value that we calculate to fit in the HW range. This is
+	 * to account for the possibility that the last command fit exactly into
+	 * the ringbuffer and rb->next hasn't wrapped to zero yet
+	 */
+	wptr = get_wptr(gpu->rb) & ((gpu->rb->size / 4) - 1);
 
 	/* ensure writes to ringbuffer have hit system memory: */
 	mb();
@@ -338,7 +345,6 @@
 {
 	struct adreno_platform_config *config = pdev->dev.platform_data;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	struct msm_mmu *mmu;
 	int ret;
 
 	adreno_gpu->funcs = funcs;
@@ -378,8 +384,8 @@
 		return ret;
 	}
 
-	mmu = gpu->aspace->mmu;
-	if (mmu) {
+	if (gpu->aspace && gpu->aspace->mmu) {
+		struct msm_mmu *mmu = gpu->aspace->mmu;
 		ret = mmu->funcs->attach(mmu, iommu_ports,
 				ARRAY_SIZE(iommu_ports));
 		if (ret)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 5f6cd87..c396d45 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -119,13 +119,7 @@
 
 static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
-	int i;
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
-	struct drm_plane *plane;
-	struct drm_plane_state *plane_state;
-
-	for_each_plane_in_state(state, plane, plane_state, i)
-		mdp5_plane_complete_commit(plane, plane_state);
 
 	if (mdp5_kms->smp)
 		mdp5_smp_complete_commit(mdp5_kms->smp, &mdp5_kms->state->smp);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index 17b0cc1..cdfc63d 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -104,8 +104,6 @@
 
 	/* assigned by crtc blender */
 	enum mdp_mixer_stage_id stage;
-
-	bool pending : 1;
 };
 #define to_mdp5_plane_state(x) \
 		container_of(x, struct mdp5_plane_state, base)
@@ -232,8 +230,6 @@
 void mdp5_irq_domain_fini(struct mdp5_kms *mdp5_kms);
 
 uint32_t mdp5_plane_get_flush(struct drm_plane *plane);
-void mdp5_plane_complete_commit(struct drm_plane *plane,
-	struct drm_plane_state *state);
 enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane);
 struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary);
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index c099da7..25d9d0a 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -179,7 +179,6 @@
 	drm_printf(p, "\tzpos=%u\n", pstate->zpos);
 	drm_printf(p, "\talpha=%u\n", pstate->alpha);
 	drm_printf(p, "\tstage=%s\n", stage2name(pstate->stage));
-	drm_printf(p, "\tpending=%u\n", pstate->pending);
 }
 
 static void mdp5_plane_reset(struct drm_plane *plane)
@@ -220,8 +219,6 @@
 	if (mdp5_state && mdp5_state->base.fb)
 		drm_framebuffer_reference(mdp5_state->base.fb);
 
-	mdp5_state->pending = false;
-
 	return &mdp5_state->base;
 }
 
@@ -288,13 +285,6 @@
 	DBG("%s: check (%d -> %d)", plane->name,
 			plane_enabled(old_state), plane_enabled(state));
 
-	/* We don't allow faster-than-vblank updates.. if we did add this
-	 * some day, we would need to disallow in cases where hwpipe
-	 * changes
-	 */
-	if (WARN_ON(to_mdp5_plane_state(old_state)->pending))
-		return -EBUSY;
-
 	max_width = config->hw->lm.max_width << 16;
 	max_height = config->hw->lm.max_height << 16;
 
@@ -370,12 +360,9 @@
 				     struct drm_plane_state *old_state)
 {
 	struct drm_plane_state *state = plane->state;
-	struct mdp5_plane_state *mdp5_state = to_mdp5_plane_state(state);
 
 	DBG("%s: update", plane->name);
 
-	mdp5_state->pending = true;
-
 	if (plane_enabled(state)) {
 		int ret;
 
@@ -851,15 +838,6 @@
 	return pstate->hwpipe->flush_mask;
 }
 
-/* called after vsync in thread context */
-void mdp5_plane_complete_commit(struct drm_plane *plane,
-	struct drm_plane_state *state)
-{
-	struct mdp5_plane_state *pstate = to_mdp5_plane_state(plane->state);
-
-	pstate->pending = false;
-}
-
 /* initialize plane */
 struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary)
 {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index d8bc59c..8098677 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -294,6 +294,8 @@
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
 	for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) {
+		if (!priv->aspace[id])
+			continue;
 		msm_gem_unmap_vma(priv->aspace[id],
 				&msm_obj->domain[id], msm_obj->sgt);
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 166e84e..4896765 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -106,7 +106,8 @@
 			pagefault_disable();
 		}
 
-		if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) {
+		if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) ||
+			!(submit_bo.flags & MSM_SUBMIT_BO_FLAGS)) {
 			DRM_ERROR("invalid flags: %x\n", submit_bo.flags);
 			ret = -EINVAL;
 			goto out_unlock;
@@ -290,7 +291,7 @@
 {
 	uint32_t i, last_offset = 0;
 	uint32_t *ptr;
-	int ret;
+	int ret = 0;
 
 	if (offset % 4) {
 		DRM_ERROR("non-aligned cmdstream buffer: %u\n", offset);
@@ -318,12 +319,13 @@
 
 		ret = copy_from_user(&submit_reloc, userptr, sizeof(submit_reloc));
 		if (ret)
-			return -EFAULT;
+			goto out;
 
 		if (submit_reloc.submit_offset % 4) {
 			DRM_ERROR("non-aligned reloc offset: %u\n",
 					submit_reloc.submit_offset);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 
 		/* offset in dwords: */
@@ -332,12 +334,13 @@
 		if ((off >= (obj->base.size / 4)) ||
 				(off < last_offset)) {
 			DRM_ERROR("invalid offset %u at reloc %u\n", off, i);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 
 		ret = submit_bo(submit, submit_reloc.reloc_idx, NULL, &iova, &valid);
 		if (ret)
-			return ret;
+			goto out;
 
 		if (valid)
 			continue;
@@ -354,9 +357,10 @@
 		last_offset = off;
 	}
 
+out:
 	msm_gem_put_vaddr_locked(&obj->base);
 
-	return 0;
+	return ret;
 }
 
 static void submit_cleanup(struct msm_gem_submit *submit)
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index f326cf6..67b34e0 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -23,7 +23,8 @@
 	struct msm_ringbuffer *ring;
 	int ret;
 
-	size = ALIGN(size, 4);   /* size should be dword aligned */
+	if (WARN_ON(!is_power_of_2(size)))
+		return ERR_PTR(-EINVAL);
 
 	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
 	if (!ring) {
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ad4d7b8..4147768 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -50,7 +50,6 @@
 MODULE_FIRMWARE("radeon/tahiti_mc.bin");
 MODULE_FIRMWARE("radeon/tahiti_rlc.bin");
 MODULE_FIRMWARE("radeon/tahiti_smc.bin");
-MODULE_FIRMWARE("radeon/tahiti_k_smc.bin");
 
 MODULE_FIRMWARE("radeon/PITCAIRN_pfp.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_me.bin");
@@ -115,6 +114,9 @@
 MODULE_FIRMWARE("radeon/hainan_rlc.bin");
 MODULE_FIRMWARE("radeon/hainan_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
+MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
+
+MODULE_FIRMWARE("radeon/si58_mc.bin");
 
 static u32 si_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
 static void si_pcie_gen3_enable(struct radeon_device *rdev);
@@ -1651,15 +1653,14 @@
 	int err;
 	int new_fw = 0;
 	bool new_smc = false;
+	bool si58_fw = false;
+	bool banks2_fw = false;
 
 	DRM_DEBUG("\n");
 
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 		chip_name = "TAHITI";
-		/* XXX: figure out which Tahitis need the new ucode */
-		if (0)
-			new_smc = true;
 		new_chip_name = "tahiti";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1671,12 +1672,9 @@
 		break;
 	case CHIP_PITCAIRN:
 		chip_name = "PITCAIRN";
-		if ((rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->device == 0x6810) ||
-		    (rdev->pdev->device == 0x6811) ||
-		    (rdev->pdev->device == 0x6816) ||
-		    (rdev->pdev->device == 0x6817) ||
-		    (rdev->pdev->device == 0x6806))
+		if ((rdev->pdev->revision == 0x81) &&
+		    ((rdev->pdev->device == 0x6810) ||
+		     (rdev->pdev->device == 0x6811)))
 			new_smc = true;
 		new_chip_name = "pitcairn";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
@@ -1689,15 +1687,15 @@
 		break;
 	case CHIP_VERDE:
 		chip_name = "VERDE";
-		if ((rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->revision == 0x83) ||
-		    (rdev->pdev->revision == 0x87) ||
-		    (rdev->pdev->device == 0x6820) ||
-		    (rdev->pdev->device == 0x6821) ||
-		    (rdev->pdev->device == 0x6822) ||
-		    (rdev->pdev->device == 0x6823) ||
-		    (rdev->pdev->device == 0x682A) ||
-		    (rdev->pdev->device == 0x682B))
+		if (((rdev->pdev->device == 0x6820) &&
+		     ((rdev->pdev->revision == 0x81) ||
+		      (rdev->pdev->revision == 0x83))) ||
+		    ((rdev->pdev->device == 0x6821) &&
+		     ((rdev->pdev->revision == 0x83) ||
+		      (rdev->pdev->revision == 0x87))) ||
+		    ((rdev->pdev->revision == 0x87) &&
+		     ((rdev->pdev->device == 0x6823) ||
+		      (rdev->pdev->device == 0x682b))))
 			new_smc = true;
 		new_chip_name = "verde";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
@@ -1710,13 +1708,13 @@
 		break;
 	case CHIP_OLAND:
 		chip_name = "OLAND";
-		if ((rdev->pdev->revision == 0xC7) ||
-		    (rdev->pdev->revision == 0x80) ||
-		    (rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->revision == 0x83) ||
-		    (rdev->pdev->revision == 0x87) ||
-		    (rdev->pdev->device == 0x6604) ||
-		    (rdev->pdev->device == 0x6605))
+		if (((rdev->pdev->revision == 0x81) &&
+		     ((rdev->pdev->device == 0x6600) ||
+		      (rdev->pdev->device == 0x6604) ||
+		      (rdev->pdev->device == 0x6605) ||
+		      (rdev->pdev->device == 0x6610))) ||
+		    ((rdev->pdev->revision == 0x83) &&
+		     (rdev->pdev->device == 0x6610)))
 			new_smc = true;
 		new_chip_name = "oland";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
@@ -1728,13 +1726,17 @@
 		break;
 	case CHIP_HAINAN:
 		chip_name = "HAINAN";
-		if ((rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->revision == 0x83) ||
-		    (rdev->pdev->revision == 0xC3) ||
-		    (rdev->pdev->device == 0x6664) ||
-		    (rdev->pdev->device == 0x6665) ||
-		    (rdev->pdev->device == 0x6667))
+		if (((rdev->pdev->revision == 0x81) &&
+		     (rdev->pdev->device == 0x6660)) ||
+		    ((rdev->pdev->revision == 0x83) &&
+		     ((rdev->pdev->device == 0x6660) ||
+		      (rdev->pdev->device == 0x6663) ||
+		      (rdev->pdev->device == 0x6665) ||
+		      (rdev->pdev->device == 0x6667))))
 			new_smc = true;
+		else if ((rdev->pdev->revision == 0xc3) &&
+			 (rdev->pdev->device == 0x6665))
+			banks2_fw = true;
 		new_chip_name = "hainan";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1746,6 +1748,10 @@
 	default: BUG();
 	}
 
+	/* this memory configuration requires special firmware */
+	if (((RREG32(MC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58)
+		si58_fw = true;
+
 	DRM_INFO("Loading %s Microcode\n", new_chip_name);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", new_chip_name);
@@ -1849,7 +1855,10 @@
 		}
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
+	if (si58_fw)
+		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+	else
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
 	err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
 	if (err) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name);
@@ -1880,7 +1889,9 @@
 		}
 	}
 
-	if (new_smc)
+	if (banks2_fw)
+		snprintf(fw_name, sizeof(fw_name), "radeon/banks_k_2_smc.bin");
+	else if (new_smc)
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_k_smc.bin", new_chip_name);
 	else
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 8b5e697..2944916 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3008,30 +3008,6 @@
 		    (rdev->pdev->device == 0x6817) ||
 		    (rdev->pdev->device == 0x6806))
 			max_mclk = 120000;
-	} else if (rdev->family == CHIP_VERDE) {
-		if ((rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->revision == 0x83) ||
-		    (rdev->pdev->revision == 0x87) ||
-		    (rdev->pdev->device == 0x6820) ||
-		    (rdev->pdev->device == 0x6821) ||
-		    (rdev->pdev->device == 0x6822) ||
-		    (rdev->pdev->device == 0x6823) ||
-		    (rdev->pdev->device == 0x682A) ||
-		    (rdev->pdev->device == 0x682B)) {
-			max_sclk = 75000;
-			max_mclk = 80000;
-		}
-	} else if (rdev->family == CHIP_OLAND) {
-		if ((rdev->pdev->revision == 0xC7) ||
-		    (rdev->pdev->revision == 0x80) ||
-		    (rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->revision == 0x83) ||
-		    (rdev->pdev->revision == 0x87) ||
-		    (rdev->pdev->device == 0x6604) ||
-		    (rdev->pdev->device == 0x6605)) {
-			max_sclk = 75000;
-			max_mclk = 80000;
-		}
 	} else if (rdev->family == CHIP_HAINAN) {
 		if ((rdev->pdev->revision == 0x81) ||
 		    (rdev->pdev->revision == 0x83) ||
@@ -3040,7 +3016,6 @@
 		    (rdev->pdev->device == 0x6665) ||
 		    (rdev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
-			max_mclk = 80000;
 		}
 	}
 	/* Apply dpm quirks */
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index 725dffa..6dfdb14 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -856,7 +856,7 @@
 	struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct tilcdc_drm_private *priv = dev->dev_private;
-	uint32_t stat;
+	uint32_t stat, reg;
 
 	stat = tilcdc_read_irqstatus(dev);
 	tilcdc_clear_irqstatus(dev, stat);
@@ -921,17 +921,26 @@
 		dev_err_ratelimited(dev->dev, "%s(0x%08x): Sync lost",
 				    __func__, stat);
 		tilcdc_crtc->frame_intact = false;
-		if (tilcdc_crtc->sync_lost_count++ >
-		    SYNC_LOST_COUNT_LIMIT) {
-			dev_err(dev->dev, "%s(0x%08x): Sync lost flood detected, recovering", __func__, stat);
-			queue_work(system_wq, &tilcdc_crtc->recover_work);
-			if (priv->rev == 1)
+		if (priv->rev == 1) {
+			reg = tilcdc_read(dev, LCDC_RASTER_CTRL_REG);
+			if (reg & LCDC_RASTER_ENABLE) {
 				tilcdc_clear(dev, LCDC_RASTER_CTRL_REG,
-					     LCDC_V1_SYNC_LOST_INT_ENA);
-			else
+					     LCDC_RASTER_ENABLE);
+				tilcdc_set(dev, LCDC_RASTER_CTRL_REG,
+					   LCDC_RASTER_ENABLE);
+			}
+		} else {
+			if (tilcdc_crtc->sync_lost_count++ >
+			    SYNC_LOST_COUNT_LIMIT) {
+				dev_err(dev->dev,
+					"%s(0x%08x): Sync lost flood detected, recovering",
+					__func__, stat);
+				queue_work(system_wq,
+					   &tilcdc_crtc->recover_work);
 				tilcdc_write(dev, LCDC_INT_ENABLE_CLR_REG,
 					     LCDC_SYNC_LOST);
-			tilcdc_crtc->sync_lost_count = 0;
+				tilcdc_crtc->sync_lost_count = 0;
+			}
 		}
 	}
 
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index d40ed9f..70b12f8 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -64,7 +64,8 @@
 #define QUIRK_SKIP_INPUT_MAPPING	BIT(2)
 #define QUIRK_IS_MULTITOUCH		BIT(3)
 
-#define NOTEBOOK_QUIRKS			QUIRK_FIX_NOTEBOOK_REPORT
+#define KEYBOARD_QUIRKS			(QUIRK_FIX_NOTEBOOK_REPORT | \
+						 QUIRK_NO_INIT_REPORTS)
 #define TOUCHPAD_QUIRKS			(QUIRK_NO_INIT_REPORTS | \
 						 QUIRK_SKIP_INPUT_MAPPING | \
 						 QUIRK_IS_MULTITOUCH)
@@ -170,11 +171,11 @@
 
 static int asus_input_configured(struct hid_device *hdev, struct hid_input *hi)
 {
+	struct input_dev *input = hi->input;
 	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
 
 	if (drvdata->quirks & QUIRK_IS_MULTITOUCH) {
 		int ret;
-		struct input_dev *input = hi->input;
 
 		input_set_abs_params(input, ABS_MT_POSITION_X, 0, MAX_X, 0, 0);
 		input_set_abs_params(input, ABS_MT_POSITION_Y, 0, MAX_Y, 0, 0);
@@ -191,10 +192,10 @@
 			hid_err(hdev, "Asus input mt init slots failed: %d\n", ret);
 			return ret;
 		}
-
-		drvdata->input = input;
 	}
 
+	drvdata->input = input;
+
 	return 0;
 }
 
@@ -286,7 +287,11 @@
 		goto err_stop_hw;
 	}
 
-	drvdata->input->name = "Asus TouchPad";
+	if (drvdata->quirks & QUIRK_IS_MULTITOUCH) {
+		drvdata->input->name = "Asus TouchPad";
+	} else {
+		drvdata->input->name = "Asus Keyboard";
+	}
 
 	if (drvdata->quirks & QUIRK_IS_MULTITOUCH) {
 		ret = asus_start_multitouch(hdev);
@@ -315,7 +320,7 @@
 
 static const struct hid_device_id asus_devices[] = {
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK,
-		 USB_DEVICE_ID_ASUSTEK_NOTEBOOK_KEYBOARD), NOTEBOOK_QUIRKS},
+		 USB_DEVICE_ID_ASUSTEK_NOTEBOOK_KEYBOARD), KEYBOARD_QUIRKS},
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK,
 			 USB_DEVICE_ID_ASUSTEK_TOUCHPAD), TOUCHPAD_QUIRKS },
 	{ }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index ec277b9..54bd22d 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -319,6 +319,7 @@
 #define USB_VENDOR_ID_DRAGONRISE		0x0079
 #define USB_DEVICE_ID_DRAGONRISE_WIIU		0x1800
 #define USB_DEVICE_ID_DRAGONRISE_PS3		0x1801
+#define USB_DEVICE_ID_DRAGONRISE_DOLPHINBAR	0x1803
 #define USB_DEVICE_ID_DRAGONRISE_GAMECUBE	0x1843
 
 #define USB_VENDOR_ID_DWAV		0x0eef
@@ -365,6 +366,9 @@
 #define USB_VENDOR_ID_FLATFROG		0x25b5
 #define USB_DEVICE_ID_MULTITOUCH_3200	0x0002
 
+#define USB_VENDOR_ID_FUTABA            0x0547
+#define USB_DEVICE_ID_LED_DISPLAY       0x7000
+
 #define USB_VENDOR_ID_ESSENTIAL_REALITY	0x0d7f
 #define USB_DEVICE_ID_ESSENTIAL_REALITY_P5 0x0100
 
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 5c92522..4ef7337 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -212,7 +212,6 @@
 	__s32 value;
 	int ret = 0;
 
-	memset(buffer, 0, buffer_size);
 	mutex_lock(&data->mutex);
 	report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
 	if (!report || (field_index >= report->maxfield)) {
@@ -256,6 +255,8 @@
 	int buffer_index = 0;
 	int i;
 
+	memset(buffer, 0, buffer_size);
+
 	mutex_lock(&data->mutex);
 	report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
 	if (!report || (field_index >= report->maxfield) ||
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 7687c08..f405b07 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -1099,8 +1099,11 @@
 	u8 led_delay_on[MAX_LEDS];
 	u8 led_delay_off[MAX_LEDS];
 	u8 led_count;
+	bool ds4_dongle_connected;
 };
 
+static void sony_set_leds(struct sony_sc *sc);
+
 static inline void sony_schedule_work(struct sony_sc *sc)
 {
 	if (!sc->defer_initialization)
@@ -1430,6 +1433,31 @@
 				return -EILSEQ;
 			}
 		}
+
+		/*
+		 * In the case of a DS4 USB dongle, bit[2] of byte 31 indicates
+		 * if a DS4 is actually connected (indicated by '0').
+		 * For non-dongle, this bit is always 0 (connected).
+		 */
+		if (sc->hdev->vendor == USB_VENDOR_ID_SONY &&
+		    sc->hdev->product == USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE) {
+			bool connected = (rd[31] & 0x04) ? false : true;
+
+			if (!sc->ds4_dongle_connected && connected) {
+				hid_info(sc->hdev, "DualShock 4 USB dongle: controller connected\n");
+				sony_set_leds(sc);
+				sc->ds4_dongle_connected = true;
+			} else if (sc->ds4_dongle_connected && !connected) {
+				hid_info(sc->hdev, "DualShock 4 USB dongle: controller disconnected\n");
+				sc->ds4_dongle_connected = false;
+				/* Return 0, so hidraw can get the report. */
+				return 0;
+			} else if (!sc->ds4_dongle_connected) {
+				/* Return 0, so hidraw can get the report. */
+				return 0;
+			}
+		}
+
 		dualshock4_parse_report(sc, rd, size);
 	}
 
@@ -2390,6 +2418,12 @@
 		}
 
 		memcpy(sc->mac_address, &buf[1], sizeof(sc->mac_address));
+
+		snprintf(sc->hdev->uniq, sizeof(sc->hdev->uniq),
+			"%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
+			sc->mac_address[5], sc->mac_address[4],
+			sc->mac_address[3], sc->mac_address[2],
+			sc->mac_address[1], sc->mac_address[0]);
 	} else if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
 			(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
 		buf = kmalloc(SIXAXIS_REPORT_0xF2_SIZE, GFP_KERNEL);
@@ -2548,7 +2582,7 @@
 			hid_err(sc->hdev,
 			"Unable to initialize multi-touch slots: %d\n",
 			ret);
-			return ret;
+			goto err_stop;
 		}
 
 		sony_init_output_report(sc, dualshock4_send_output_report);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index b3e01c8..e9d6cc7 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -83,11 +83,13 @@
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_DOLPHINBAR, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_GAMECUBE, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_FUTABA, USB_DEVICE_ID_LED_DISPLAY, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 322ed92..841f242 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -1036,7 +1036,7 @@
 };
 
 static const u8 lm90_min_alarm_bits[3] = { 5, 3, 11 };
-static const u8 lm90_max_alarm_bits[3] = { 0, 4, 12 };
+static const u8 lm90_max_alarm_bits[3] = { 6, 4, 12 };
 static const u8 lm90_crit_alarm_bits[3] = { 0, 1, 9 };
 static const u8 lm90_emergency_alarm_bits[3] = { 15, 13, 14 };
 static const u8 lm90_fault_bits[3] = { 0, 2, 10 };
diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c
index f6b6d42..784670e 100644
--- a/drivers/iio/accel/st_accel_core.c
+++ b/drivers/iio/accel/st_accel_core.c
@@ -353,12 +353,12 @@
 				[0] = {
 					.num = ST_ACCEL_FS_AVL_2G,
 					.value = 0x00,
-					.gain = IIO_G_TO_M_S_2(1024),
+					.gain = IIO_G_TO_M_S_2(1000),
 				},
 				[1] = {
 					.num = ST_ACCEL_FS_AVL_6G,
 					.value = 0x01,
-					.gain = IIO_G_TO_M_S_2(340),
+					.gain = IIO_G_TO_M_S_2(3000),
 				},
 			},
 		},
@@ -366,6 +366,14 @@
 			.addr = 0x21,
 			.mask = 0x40,
 		},
+		/*
+		 * Data Alignment Setting - needs to be set to get
+		 * left-justified data like all other sensors.
+		 */
+		.das = {
+			.addr = 0x21,
+			.mask = 0x01,
+		},
 		.drdy_irq = {
 			.addr = 0x21,
 			.mask_int1 = 0x04,
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 38bc319..9c8b558 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -561,7 +561,7 @@
 
 config TI_AM335X_ADC
 	tristate "TI's AM335X ADC driver"
-	depends on MFD_TI_AM335X_TSCADC
+	depends on MFD_TI_AM335X_TSCADC && HAS_DMA
 	select IIO_BUFFER
 	select IIO_KFIFO_BUF
 	help
diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c
index fe7775b..df40452 100644
--- a/drivers/iio/common/st_sensors/st_sensors_buffer.c
+++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c
@@ -30,7 +30,9 @@
 
 	for_each_set_bit(i, indio_dev->active_scan_mask, num_data_channels) {
 		const struct iio_chan_spec *channel = &indio_dev->channels[i];
-		unsigned int bytes_to_read = channel->scan_type.realbits >> 3;
+		unsigned int bytes_to_read =
+			DIV_ROUND_UP(channel->scan_type.realbits +
+				     channel->scan_type.shift, 8);
 		unsigned int storage_bytes =
 			channel->scan_type.storagebits >> 3;
 
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index 975a1f1..79c8c7c 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -401,6 +401,15 @@
 			return err;
 	}
 
+	/* set DAS */
+	if (sdata->sensor_settings->das.addr) {
+		err = st_sensors_write_data_with_mask(indio_dev,
+					sdata->sensor_settings->das.addr,
+					sdata->sensor_settings->das.mask, 1);
+		if (err < 0)
+			return err;
+	}
+
 	if (sdata->int_pin_open_drain) {
 		dev_info(&indio_dev->dev,
 			 "set interrupt line to open drain mode\n");
@@ -483,8 +492,10 @@
 	int err;
 	u8 *outdata;
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
-	unsigned int byte_for_channel = ch->scan_type.realbits >> 3;
+	unsigned int byte_for_channel;
 
+	byte_for_channel = DIV_ROUND_UP(ch->scan_type.realbits +
+					ch->scan_type.shift, 8);
 	outdata = kmalloc(byte_for_channel, GFP_KERNEL);
 	if (!outdata)
 		return -ENOMEM;
diff --git a/drivers/iio/counter/104-quad-8.c b/drivers/iio/counter/104-quad-8.c
index 2d2ee35..a5913e9 100644
--- a/drivers/iio/counter/104-quad-8.c
+++ b/drivers/iio/counter/104-quad-8.c
@@ -153,7 +153,7 @@
 		ior_cfg = val | priv->preset_enable[chan->channel] << 1;
 
 		/* Load I/O control configuration */
-		outb(0x40 | ior_cfg, base_offset);
+		outb(0x40 | ior_cfg, base_offset + 1);
 
 		return 0;
 	case IIO_CHAN_INFO_SCALE:
@@ -233,7 +233,7 @@
 	const struct quad8_iio *const priv = iio_priv(indio_dev);
 
 	return snprintf(buf, PAGE_SIZE, "%u\n",
-		priv->preset_enable[chan->channel]);
+		!priv->preset_enable[chan->channel]);
 }
 
 static ssize_t quad8_write_set_to_preset_on_index(struct iio_dev *indio_dev,
@@ -241,7 +241,7 @@
 	size_t len)
 {
 	struct quad8_iio *const priv = iio_priv(indio_dev);
-	const int base_offset = priv->base + 2 * chan->channel;
+	const int base_offset = priv->base + 2 * chan->channel + 1;
 	bool preset_enable;
 	int ret;
 	unsigned int ior_cfg;
@@ -250,6 +250,9 @@
 	if (ret)
 		return ret;
 
+	/* Preset enable is active low in Input/Output Control register */
+	preset_enable = !preset_enable;
+
 	priv->preset_enable[chan->channel] = preset_enable;
 
 	ior_cfg = priv->ab_enable[chan->channel] |
@@ -362,7 +365,7 @@
 	priv->synchronous_mode[chan->channel] = synchronous_mode;
 
 	/* Load Index Control configuration to Index Control Register */
-	outb(0x40 | idr_cfg, base_offset);
+	outb(0x60 | idr_cfg, base_offset);
 
 	return 0;
 }
@@ -444,7 +447,7 @@
 	priv->index_polarity[chan->channel] = index_polarity;
 
 	/* Load Index Control configuration to Index Control Register */
-	outb(0x40 | idr_cfg, base_offset);
+	outb(0x60 | idr_cfg, base_offset);
 
 	return 0;
 }
diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c
index 5355507..c9e319b 100644
--- a/drivers/iio/imu/bmi160/bmi160_core.c
+++ b/drivers/iio/imu/bmi160/bmi160_core.c
@@ -66,10 +66,8 @@
 
 #define BMI160_REG_DUMMY		0x7F
 
-#define BMI160_ACCEL_PMU_MIN_USLEEP	3200
-#define BMI160_ACCEL_PMU_MAX_USLEEP	3800
-#define BMI160_GYRO_PMU_MIN_USLEEP	55000
-#define BMI160_GYRO_PMU_MAX_USLEEP	80000
+#define BMI160_ACCEL_PMU_MIN_USLEEP	3800
+#define BMI160_GYRO_PMU_MIN_USLEEP	80000
 #define BMI160_SOFTRESET_USLEEP		1000
 
 #define BMI160_CHANNEL(_type, _axis, _index) {			\
@@ -151,20 +149,9 @@
 	},
 };
 
-struct bmi160_pmu_time {
-	unsigned long min;
-	unsigned long max;
-};
-
-static struct bmi160_pmu_time bmi160_pmu_time[] = {
-	[BMI160_ACCEL] = {
-		.min = BMI160_ACCEL_PMU_MIN_USLEEP,
-		.max = BMI160_ACCEL_PMU_MAX_USLEEP
-	},
-	[BMI160_GYRO] = {
-		.min = BMI160_GYRO_PMU_MIN_USLEEP,
-		.max = BMI160_GYRO_PMU_MIN_USLEEP,
-	},
+static unsigned long bmi160_pmu_time[] = {
+	[BMI160_ACCEL] = BMI160_ACCEL_PMU_MIN_USLEEP,
+	[BMI160_GYRO] = BMI160_GYRO_PMU_MIN_USLEEP,
 };
 
 struct bmi160_scale {
@@ -289,7 +276,7 @@
 	if (ret < 0)
 		return ret;
 
-	usleep_range(bmi160_pmu_time[t].min, bmi160_pmu_time[t].max);
+	usleep_range(bmi160_pmu_time[t], bmi160_pmu_time[t] + 1000);
 
 	return 0;
 }
diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c
index a144ca3..81bd8e8 100644
--- a/drivers/iio/light/max44000.c
+++ b/drivers/iio/light/max44000.c
@@ -113,7 +113,7 @@
 	"0.100 "
 	"0.025 "
 	"0.00625 "
-	"0.001625";
+	"0.0015625";
 
 /* Available scales (internal to ulux) with pretty manual alignment: */
 static const int max44000_scale_avail_ulux_array[] = {
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index c8413fc..7031a8dd 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1682,9 +1682,19 @@
 		size += ret;
 	}
 
+	if (mlx4_is_master(mdev->dev) && flow_type == MLX4_FS_REGULAR &&
+	    flow_attr->num_of_specs == 1) {
+		struct _rule_hw *rule_header = (struct _rule_hw *)(ctrl + 1);
+		enum ib_flow_spec_type header_spec =
+			((union ib_flow_spec *)(flow_attr + 1))->type;
+
+		if (header_spec == IB_FLOW_SPEC_ETH)
+			mlx4_handle_eth_header_mcast_prio(ctrl, rule_header);
+	}
+
 	ret = mlx4_cmd_imm(mdev->dev, mailbox->dma, reg_id, size >> 2, 0,
 			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
-			   MLX4_CMD_WRAPPED);
+			   MLX4_CMD_NATIVE);
 	if (ret == -ENOMEM)
 		pr_err("mcg table is full. Fail to register network rule.\n");
 	else if (ret == -ENXIO)
@@ -1701,7 +1711,7 @@
 	int err;
 	err = mlx4_cmd(dev, reg_id, 0, 0,
 		       MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
-		       MLX4_CMD_WRAPPED);
+		       MLX4_CMD_NATIVE);
 	if (err)
 		pr_err("Fail to detach network rule. registration id = 0x%llx\n",
 		       reg_id);
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 019e027..3ef0f42 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1023,7 +1023,7 @@
 	next_tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE;
 	left      = (head - next_tail) % CMD_BUFFER_SIZE;
 
-	if (left <= 2) {
+	if (left <= 0x20) {
 		struct iommu_cmd sync_cmd;
 		int ret;
 
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index a88576d..8ccbd70 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -903,8 +903,10 @@
 		x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
 
-	acpi_put_table(dmar_tbl);
-	dmar_tbl = NULL;
+	if (dmar_tbl) {
+		acpi_put_table(dmar_tbl);
+		dmar_tbl = NULL;
+	}
 	up_write(&dmar_global_lock);
 
 	return ret ? 1 : -ENODEV;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index c66c273..8a18525 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2037,6 +2037,25 @@
 	if (context_present(context))
 		goto out_unlock;
 
+	/*
+	 * For kdump cases, old valid entries may be cached due to the
+	 * in-flight DMA and copied pgtable, but there is no unmapping
+	 * behaviour for them, thus we need an explicit cache flush for
+	 * the newly-mapped device. For kdump, at this point, the device
+	 * is supposed to finish reset at its driver probe stage, so no
+	 * in-flight DMA will exist, and we don't need to worry anymore
+	 * hereafter.
+	 */
+	if (context_copied(context)) {
+		u16 did_old = context_domain_id(context);
+
+		if (did_old >= 0 && did_old < cap_ndoms(iommu->cap))
+			iommu->flush.flush_context(iommu, did_old,
+						   (((u16)bus) << 8) | devfn,
+						   DMA_CCMD_MASK_NOBIT,
+						   DMA_CCMD_DEVICE_INVL);
+	}
+
 	pgd = domain->pgd;
 
 	context_clear_entry(context);
@@ -5185,6 +5204,25 @@
 }
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
+#define MAX_NR_PASID_BITS (20)
+static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu)
+{
+	/*
+	 * Convert ecap_pss to extend context entry pts encoding, also
+	 * respect the soft pasid_max value set by the iommu.
+	 * - number of PASID bits = ecap_pss + 1
+	 * - number of PASID table entries = 2^(pts + 5)
+	 * Therefore, pts = ecap_pss - 4
+	 * e.g. KBL ecap_pss = 0x13, PASID has 20 bits, pts = 15
+	 */
+	if (ecap_pss(iommu->ecap) < 5)
+		return 0;
+
+	/* pasid_max is encoded as actual number of entries not the bits */
+	return find_first_bit((unsigned long *)&iommu->pasid_max,
+			MAX_NR_PASID_BITS) - 5;
+}
+
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev)
 {
 	struct device_domain_info *info;
@@ -5217,7 +5255,9 @@
 
 	if (!(ctx_lo & CONTEXT_PASIDE)) {
 		context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table);
-		context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | ecap_pss(iommu->ecap);
+		context[1].lo = (u64)virt_to_phys(iommu->pasid_table) |
+			intel_iommu_get_pts(iommu);
+
 		wmb();
 		/* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both
 		 * extended to permit requests-with-PASID if the PASIDE bit
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 0037153..2d9c5dd 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -450,7 +450,7 @@
 EXPORT_SYMBOL_GPL(mei_cldev_enabled);
 
 /**
- * mei_cldev_enable_device - enable me client device
+ * mei_cldev_enable - enable me client device
  *     create connection with me client
  *
  * @cldev: me client device
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 391936c..b039560 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -1541,7 +1541,7 @@
 
 	rets = first_chunk ? mei_cl_tx_flow_ctrl_creds(cl) : 1;
 	if (rets < 0)
-		return rets;
+		goto err;
 
 	if (rets == 0) {
 		cl_dbg(dev, cl, "No flow control credentials: not sending.\n");
@@ -1575,11 +1575,8 @@
 			cb->buf.size, cb->buf_idx);
 
 	rets = mei_write_message(dev, &mei_hdr, buf->data + cb->buf_idx);
-	if (rets) {
-		cl->status = rets;
-		list_move_tail(&cb->list, &cmpl_list->list);
-		return rets;
-	}
+	if (rets)
+		goto err;
 
 	cl->status = 0;
 	cl->writing_state = MEI_WRITING;
@@ -1587,14 +1584,21 @@
 	cb->completed = mei_hdr.msg_complete == 1;
 
 	if (first_chunk) {
-		if (mei_cl_tx_flow_ctrl_creds_reduce(cl))
-			return -EIO;
+		if (mei_cl_tx_flow_ctrl_creds_reduce(cl)) {
+			rets = -EIO;
+			goto err;
+		}
 	}
 
 	if (mei_hdr.msg_complete)
 		list_move_tail(&cb->list, &dev->write_waiting_list.list);
 
 	return 0;
+
+err:
+	cl->status = rets;
+	list_move_tail(&cb->list, &cmpl_list->list);
+	return rets;
 }
 
 /**
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 25d1eb4..7e8cf21 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1012,6 +1012,18 @@
 		goto out;
 	}
 
+	/* The Ethernet switch we are interfaced with needs packets to be at
+	 * least 64 bytes (including FCS) otherwise they will be discarded when
+	 * they enter the switch port logic. When Broadcom tags are enabled, we
+	 * need to make sure that packets are at least 68 bytes
+	 * (including FCS and tag) because the length verification is done after
+	 * the Broadcom tag is stripped off the ingress packet.
+	 */
+	if (skb_put_padto(skb, ETH_ZLEN + ENET_BRCM_TAG_LEN)) {
+		ret = NETDEV_TX_OK;
+		goto out;
+	}
+
 	/* Insert TSB and checksum infos */
 	if (priv->tsb_en) {
 		skb = bcm_sysport_insert_tsb(skb, dev);
@@ -1021,20 +1033,7 @@
 		}
 	}
 
-	/* The Ethernet switch we are interfaced with needs packets to be at
-	 * least 64 bytes (including FCS) otherwise they will be discarded when
-	 * they enter the switch port logic. When Broadcom tags are enabled, we
-	 * need to make sure that packets are at least 68 bytes
-	 * (including FCS and tag) because the length verification is done after
-	 * the Broadcom tag is stripped off the ingress packet.
-	 */
-	if (skb_padto(skb, ETH_ZLEN + ENET_BRCM_TAG_LEN)) {
-		ret = NETDEV_TX_OK;
-		goto out;
-	}
-
-	skb_len = skb->len < ETH_ZLEN + ENET_BRCM_TAG_LEN ?
-			ETH_ZLEN + ENET_BRCM_TAG_LEN : skb->len;
+	skb_len = skb->len;
 
 	mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE);
 	if (dma_mapping_error(kdev, mapping)) {
diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index 92be2cd..9906fda 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -1,5 +1,5 @@
 /**
- * macb_pci.c - Cadence GEM PCI wrapper.
+ * Cadence GEM PCI wrapper.
  *
  * Copyright (C) 2016 Cadence Design Systems - http://www.cadence.com
  *
@@ -45,32 +45,27 @@
 	struct macb_platform_data plat_data;
 	struct resource res[2];
 
-	/* sanity check */
-	if (!id)
-		return -EINVAL;
-
 	/* enable pci device */
-	err = pci_enable_device(pdev);
+	err = pcim_enable_device(pdev);
 	if (err < 0) {
-		dev_err(&pdev->dev, "Enabling PCI device has failed: 0x%04X",
-			err);
-		return -EACCES;
+		dev_err(&pdev->dev, "Enabling PCI device has failed: %d", err);
+		return err;
 	}
 
 	pci_set_master(pdev);
 
 	/* set up resources */
 	memset(res, 0x00, sizeof(struct resource) * ARRAY_SIZE(res));
-	res[0].start = pdev->resource[0].start;
-	res[0].end = pdev->resource[0].end;
+	res[0].start = pci_resource_start(pdev, 0);
+	res[0].end = pci_resource_end(pdev, 0);
 	res[0].name = PCI_DRIVER_NAME;
 	res[0].flags = IORESOURCE_MEM;
-	res[1].start = pdev->irq;
+	res[1].start = pci_irq_vector(pdev, 0);
 	res[1].name = PCI_DRIVER_NAME;
 	res[1].flags = IORESOURCE_IRQ;
 
-	dev_info(&pdev->dev, "EMAC physical base addr = 0x%p\n",
-		 (void *)(uintptr_t)pci_resource_start(pdev, 0));
+	dev_info(&pdev->dev, "EMAC physical base addr: %pa\n",
+		 &res[0].start);
 
 	/* set up macb platform data */
 	memset(&plat_data, 0, sizeof(plat_data));
@@ -100,7 +95,7 @@
 	plat_info.num_res = ARRAY_SIZE(res);
 	plat_info.data = &plat_data;
 	plat_info.size_data = sizeof(plat_data);
-	plat_info.dma_mask = DMA_BIT_MASK(32);
+	plat_info.dma_mask = pdev->dma_mask;
 
 	/* register platform device */
 	plat_dev = platform_device_register_full(&plat_info);
@@ -120,7 +115,6 @@
 	clk_unregister(plat_data.pclk);
 
 err_pclk_register:
-	pci_disable_device(pdev);
 	return err;
 }
 
@@ -130,7 +124,6 @@
 	struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev);
 
 	platform_device_unregister(plat_dev);
-	pci_disable_device(pdev);
 	clk_unregister(plat_data->pclk);
 	clk_unregister(plat_data->hclk);
 }
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index bbc8bd1..dcbce6c 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -77,7 +77,7 @@
 config LIQUIDIO_VF
 	tristate "Cavium LiquidIO VF support"
 	depends on 64BIT && PCI_MSI
-	select PTP_1588_CLOCK
+	imply PTP_1588_CLOCK
 	---help---
 	  This driver supports Cavium LiquidIO Intelligent Server Adapter
 	  based on CN23XX chips.
diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c
index 0f0de5b..d04a6c1 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c
@@ -133,17 +133,15 @@
 		if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
 			fl6.flowi6_oif = sin6_scope_id;
 		dst = ip6_route_output(&init_net, NULL, &fl6);
-		if (!dst)
-			goto out;
-		if (!cxgb_our_interface(lldi, get_real_dev,
-					ip6_dst_idev(dst)->dev) &&
-		    !(ip6_dst_idev(dst)->dev->flags & IFF_LOOPBACK)) {
+		if (dst->error ||
+		    (!cxgb_our_interface(lldi, get_real_dev,
+					 ip6_dst_idev(dst)->dev) &&
+		     !(ip6_dst_idev(dst)->dev->flags & IFF_LOOPBACK))) {
 			dst_release(dst);
-			dst = NULL;
+			return NULL;
 		}
 	}
 
-out:
 	return dst;
 }
 EXPORT_SYMBOL(cxgb_find_route6);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 7e1633b..225e9a4 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5155,7 +5155,9 @@
 	    skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
 	    skb->inner_protocol != htons(ETH_P_TEB) ||
 	    skb_inner_mac_header(skb) - skb_transport_header(skb) !=
-	    sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+		sizeof(struct udphdr) + sizeof(struct vxlanhdr) ||
+	    !adapter->vxlan_port ||
+	    udp_hdr(skb)->dest != adapter->vxlan_port)
 		return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 
 	return features;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 624ba90..c9b7ad6 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -733,6 +733,7 @@
 	priv->cgr_data.cgr.cb = dpaa_eth_cgscn;
 
 	/* Enable Congestion State Change Notifications and CS taildrop */
+	memset(&initcgr, 0, sizeof(initcgr));
 	initcgr.we_mask = cpu_to_be16(QM_CGR_WE_CSCN_EN | QM_CGR_WE_CS_THRES);
 	initcgr.cgr.cscn_en = QM_CGR_EN;
 
@@ -2291,7 +2292,8 @@
 	net_dev->phydev = mac_dev->init_phy(net_dev, priv->mac_dev);
 	if (!net_dev->phydev) {
 		netif_err(priv, ifup, net_dev, "init_phy() failed\n");
-		return -ENODEV;
+		err = -ENODEV;
+		goto phy_init_failed;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) {
@@ -2314,6 +2316,7 @@
 	for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++)
 		fman_port_disable(mac_dev->port[i]);
 
+phy_init_failed:
 	dpaa_eth_napi_disable(priv);
 
 	return err;
@@ -2420,6 +2423,7 @@
 	}
 
 	/* Enable CS TD, but disable Congestion State Change Notifications. */
+	memset(&initcgr, 0, sizeof(initcgr));
 	initcgr.we_mask = cpu_to_be16(QM_CGR_WE_CS_THRES);
 	initcgr.cgr.cscn_en = QM_CGR_EN;
 	cs_th = DPAA_INGRESS_CS_THRESHOLD;
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index cbeea91..8037426 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -900,10 +900,10 @@
 				DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR,
 				&lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
+	korina_free_ring(dev);
+
 	if (korina_init(dev) < 0) {
 		printk(KERN_ERR "%s: cannot restart device\n", dev->name);
 		return;
@@ -1064,12 +1064,12 @@
 	tmp = tmp | DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR;
 	writel(tmp, &lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
 	cancel_work_sync(&lp->restart_task);
 
+	korina_free_ring(dev);
+
 	free_irq(lp->rx_irq, dev);
 	free_irq(lp->tx_irq, dev);
 	free_irq(lp->ovr_irq, dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 015198c..504461a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -245,13 +245,9 @@
 {
 	u32 freq_khz = freq * 1000;
 	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
-	u64 tmp_rounded =
-		roundup_pow_of_two(max_val_cycles) > max_val_cycles ?
-		roundup_pow_of_two(max_val_cycles) - 1 : UINT_MAX;
-	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
-		max_val_cycles : tmp_rounded;
+	u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1);
 	/* calculate max possible multiplier in order to fit in 64bit */
-	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
+	u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded);
 
 	/* This comes from the reverse of clocksource_khz2mult */
 	return ilog2(div_u64(max_mul * freq_khz, 1000000));
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index bcd9553..edbe200 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1638,7 +1638,8 @@
 
 	/* Configure tx cq's and rings */
 	for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
-		u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up : 1;
+		u8 num_tx_rings_p_up = t == TX ?
+			priv->num_tx_rings_p_up : priv->tx_ring_num[t];
 
 		for (i = 0; i < priv->tx_ring_num[t]; i++) {
 			/* Configure cq */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 3c37e216b..eac527e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -445,8 +445,14 @@
 		ring->cqn = priv->rx_cq[ring_ind]->mcq.cqn;
 
 		ring->stride = stride;
-		if (ring->stride <= TXBB_SIZE)
+		if (ring->stride <= TXBB_SIZE) {
+			/* Stamp first unused send wqe */
+			__be32 *ptr = (__be32 *)ring->buf;
+			__be32 stamp = cpu_to_be32(1 << STAMP_SHIFT);
+			*ptr = stamp;
+			/* Move pointer to start of rx section */
 			ring->buf += TXBB_SIZE;
+		}
 
 		ring->log_stride = ffs(ring->stride) - 1;
 		ring->buf_size = ring->size * ring->stride;
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 2a9dd46..e1f9e7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -118,8 +118,13 @@
 	if (!buf)
 		return -ENOMEM;
 
+	if (offset_in_page(buf)) {
+		dma_free_coherent(dev, PAGE_SIZE << order,
+				  buf, sg_dma_address(mem));
+		return -ENOMEM;
+	}
+
 	sg_set_buf(mem, buf, PAGE_SIZE << order);
-	BUG_ON(mem->offset);
 	sg_dma_len(mem) = PAGE_SIZE << order;
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5e7840a..bffa6f3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -42,6 +42,7 @@
 #include <linux/io-mapping.h>
 #include <linux/delay.h>
 #include <linux/kmod.h>
+#include <linux/etherdevice.h>
 #include <net/devlink.h>
 
 #include <linux/mlx4/device.h>
@@ -782,6 +783,23 @@
 }
 EXPORT_SYMBOL(mlx4_is_slave_active);
 
+void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
+				       struct _rule_hw *eth_header)
+{
+	if (is_multicast_ether_addr(eth_header->eth.dst_mac) ||
+	    is_broadcast_ether_addr(eth_header->eth.dst_mac)) {
+		struct mlx4_net_trans_rule_hw_eth *eth =
+			(struct mlx4_net_trans_rule_hw_eth *)eth_header;
+		struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1);
+		bool last_rule = next_rule->size == 0 && next_rule->id == 0 &&
+			next_rule->rsvd == 0;
+
+		if (last_rule)
+			ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC);
+	}
+}
+EXPORT_SYMBOL(mlx4_handle_eth_header_mcast_prio);
+
 static void slave_adjust_steering_mode(struct mlx4_dev *dev,
 				       struct mlx4_dev_cap *dev_cap,
 				       struct mlx4_init_hca_param *hca_param)
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index c548bea..56185a0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -4164,22 +4164,6 @@
 	return 0;
 }
 
-static void handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
-					 struct _rule_hw *eth_header)
-{
-	if (is_multicast_ether_addr(eth_header->eth.dst_mac) ||
-	    is_broadcast_ether_addr(eth_header->eth.dst_mac)) {
-		struct mlx4_net_trans_rule_hw_eth *eth =
-			(struct mlx4_net_trans_rule_hw_eth *)eth_header;
-		struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1);
-		bool last_rule = next_rule->size == 0 && next_rule->id == 0 &&
-			next_rule->rsvd == 0;
-
-		if (last_rule)
-			ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC);
-	}
-}
-
 /*
  * In case of missing eth header, append eth header with a MAC address
  * assigned to the VF.
@@ -4363,10 +4347,7 @@
 	header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id));
 
 	if (header_id == MLX4_NET_TRANS_RULE_ID_ETH)
-		handle_eth_header_mcast_prio(ctrl, rule_header);
-
-	if (slave == dev->caps.function)
-		goto execute;
+		mlx4_handle_eth_header_mcast_prio(ctrl, rule_header);
 
 	switch (header_id) {
 	case MLX4_NET_TRANS_RULE_ID_ETH:
@@ -4394,7 +4375,6 @@
 		goto err_put_qp;
 	}
 
-execute:
 	err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param,
 			   vhcr->in_modifier, 0,
 			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
@@ -4473,6 +4453,7 @@
 	struct res_qp *rqp;
 	struct res_fs_rule *rrule;
 	u64 mirr_reg_id;
+	int qpn;
 
 	if (dev->caps.steering_mode !=
 	    MLX4_STEERING_MODE_DEVICE_MANAGED)
@@ -4489,10 +4470,11 @@
 	}
 	mirr_reg_id = rrule->mirr_rule_id;
 	kfree(rrule->mirr_mbox);
+	qpn = rrule->qpn;
 
 	/* Release the rule form busy state before removal */
 	put_res(dev, slave, vhcr->in_param, RES_FS_RULE);
-	err = get_res(dev, slave, rrule->qpn, RES_QP, &rqp);
+	err = get_res(dev, slave, qpn, RES_QP, &rqp);
 	if (err)
 		return err;
 
@@ -4517,7 +4499,7 @@
 	if (!err)
 		atomic_dec(&rqp->ref_count);
 out:
-	put_res(dev, slave, rrule->qpn, RES_QP);
+	put_res(dev, slave, qpn, RES_QP);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 7f6c225..f0b460f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -723,6 +723,9 @@
 	int i;
 	struct ieee_ets ets;
 
+	if (!MLX5_CAP_GEN(priv->mdev, ets))
+		return;
+
 	memset(&ets, 0, sizeof(ets));
 	ets.ets_cap = mlx5_max_tc(priv->mdev) + 1;
 	for (i = 0; i < ets.ets_cap; i++) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 352462a..33a399a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -171,7 +171,6 @@
 		return NUM_SW_COUNTERS +
 		       MLX5E_NUM_Q_CNTRS(priv) +
 		       NUM_VPORT_COUNTERS + NUM_PPORT_COUNTERS +
-		       NUM_PCIE_COUNTERS +
 		       MLX5E_NUM_RQ_STATS(priv) +
 		       MLX5E_NUM_SQ_STATS(priv) +
 		       MLX5E_NUM_PFC_COUNTERS(priv) +
@@ -219,14 +218,6 @@
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
 		       pport_2819_stats_desc[i].format);
 
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pcie_perf_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pcie_tas_stats_desc[i].format);
-
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
@@ -339,14 +330,6 @@
 		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters,
 						  pport_2819_stats_desc, i);
 
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
-						  pcie_perf_stats_desc, i);
-
-	for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_tas_counters,
-						  pcie_tas_stats_desc, i);
-
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
 			data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 3691451..d088eff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -247,6 +247,7 @@
 	}
 	if (fs->flow_type & FLOW_MAC_EXT &&
 	    !is_zero_ether_addr(fs->m_ext.h_dest)) {
+		mask_spec(fs->m_ext.h_dest, fs->h_ext.h_dest, ETH_ALEN);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
 					     outer_headers_c, dmac_47_16),
 				fs->m_ext.h_dest);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cbfa38f..1236b27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -291,36 +291,12 @@
 				      &qcnt->rx_out_of_buffer);
 }
 
-static void mlx5e_update_pcie_counters(struct mlx5e_priv *priv)
-{
-	struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int sz = MLX5_ST_SZ_BYTES(mpcnt_reg);
-	void *out;
-	u32 *in;
-
-	in = mlx5_vzalloc(sz);
-	if (!in)
-		return;
-
-	out = pcie_stats->pcie_perf_counters;
-	MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
-
-	out = pcie_stats->pcie_tas_counters;
-	MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
-
-	kvfree(in);
-}
-
 void mlx5e_update_stats(struct mlx5e_priv *priv)
 {
 	mlx5e_update_q_counter(priv);
 	mlx5e_update_vport_counters(priv);
 	mlx5e_update_pport_counters(priv);
 	mlx5e_update_sw_counters(priv);
-	mlx5e_update_pcie_counters(priv);
 }
 
 void mlx5e_update_stats_work(struct work_struct *work)
@@ -3805,14 +3781,7 @@
 
 	mlx5_lag_add(mdev, netdev);
 
-	if (mlx5e_vxlan_allowed(mdev)) {
-		rtnl_lock();
-		udp_tunnel_get_rx_info(netdev);
-		rtnl_unlock();
-	}
-
 	mlx5e_enable_async_events(priv);
-	queue_work(priv->wq, &priv->set_rx_mode_work);
 
 	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
 		mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
@@ -3822,6 +3791,18 @@
 		rep.netdev = netdev;
 		mlx5_eswitch_register_vport_rep(esw, 0, &rep);
 	}
+
+	if (netdev->reg_state != NETREG_REGISTERED)
+		return;
+
+	/* Device already registered: sync netdev system state */
+	if (mlx5e_vxlan_allowed(mdev)) {
+		rtnl_lock();
+		udp_tunnel_get_rx_info(netdev);
+		rtnl_unlock();
+	}
+
+	queue_work(priv->wq, &priv->set_rx_mode_work);
 }
 
 static void mlx5e_nic_disable(struct mlx5e_priv *priv)
@@ -3966,10 +3947,6 @@
 	const struct mlx5e_profile *profile = priv->profile;
 
 	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
-	if (profile->disable)
-		profile->disable(priv);
-
-	flush_workqueue(priv->wq);
 
 	rtnl_lock();
 	if (netif_running(netdev))
@@ -3977,6 +3954,10 @@
 	netif_device_detach(netdev);
 	rtnl_unlock();
 
+	if (profile->disable)
+		profile->disable(priv);
+	flush_workqueue(priv->wq);
+
 	mlx5e_destroy_q_counter(priv);
 	profile->cleanup_rx(priv);
 	mlx5e_close_drop_rq(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index f202f87..ba5db1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -39,7 +39,7 @@
 #define MLX5E_READ_CTR32_CPU(ptr, dsc, i) \
 	(*(u32 *)((char *)ptr + dsc[i].offset))
 #define MLX5E_READ_CTR32_BE(ptr, dsc, i) \
-	be32_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
+	be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
 
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
@@ -276,32 +276,6 @@
 	{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
 };
 
-#define PCIE_PERF_OFF(c) \
-	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c)
-#define PCIE_PERF_GET(pcie_stats, c) \
-	MLX5_GET(mpcnt_reg, pcie_stats->pcie_perf_counters, \
-		 counter_set.pcie_perf_cntrs_grp_data_layout.c)
-#define PCIE_TAS_OFF(c) \
-	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_tas_cntrs_grp_data_layout.c)
-#define PCIE_TAS_GET(pcie_stats, c) \
-	MLX5_GET(mpcnt_reg, pcie_stats->pcie_tas_counters, \
-		 counter_set.pcie_tas_cntrs_grp_data_layout.c)
-
-struct mlx5e_pcie_stats {
-	__be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
-	__be64 pcie_tas_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
-};
-
-static const struct counter_desc pcie_perf_stats_desc[] = {
-	{ "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) },
-	{ "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) },
-};
-
-static const struct counter_desc pcie_tas_stats_desc[] = {
-	{ "tx_pci_transport_nonfatal_msg", PCIE_TAS_OFF(non_fatal_err_msg_sent) },
-	{ "tx_pci_transport_fatal_msg", PCIE_TAS_OFF(fatal_err_msg_sent) },
-};
-
 struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
@@ -386,8 +360,6 @@
 #define NUM_PPORT_802_3_COUNTERS	ARRAY_SIZE(pport_802_3_stats_desc)
 #define NUM_PPORT_2863_COUNTERS		ARRAY_SIZE(pport_2863_stats_desc)
 #define NUM_PPORT_2819_COUNTERS		ARRAY_SIZE(pport_2819_stats_desc)
-#define NUM_PCIE_PERF_COUNTERS		ARRAY_SIZE(pcie_perf_stats_desc)
-#define NUM_PCIE_TAS_COUNTERS		ARRAY_SIZE(pcie_tas_stats_desc)
 #define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \
 	ARRAY_SIZE(pport_per_prio_traffic_stats_desc)
 #define NUM_PPORT_PER_PRIO_PFC_COUNTERS \
@@ -397,7 +369,6 @@
 					 NUM_PPORT_2819_COUNTERS  + \
 					 NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \
 					 NUM_PPORT_PRIO)
-#define NUM_PCIE_COUNTERS		(NUM_PCIE_PERF_COUNTERS + NUM_PCIE_TAS_COUNTERS)
 #define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
 
@@ -406,7 +377,6 @@
 	struct mlx5e_qcounter_stats qcnt;
 	struct mlx5e_vport_stats vport;
 	struct mlx5e_pport_stats pport;
-	struct mlx5e_pcie_stats pcie;
 	struct rtnl_link_stats64 vf_vport;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d6807c3..f14d9c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1860,7 +1860,7 @@
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
+	if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	mutex_lock(&esw->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 466e161..03293ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -695,6 +695,12 @@
 		if (err)
 			goto err_reps;
 	}
+
+	/* disable PF RoCE so missed packets don't go through RoCE steering */
+	mlx5_dev_list_lock();
+	mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+	mlx5_dev_list_unlock();
+
 	return 0;
 
 err_reps:
@@ -718,6 +724,11 @@
 {
 	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
 
+	/* enable back PF RoCE */
+	mlx5_dev_list_lock();
+	mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+	mlx5_dev_list_unlock();
+
 	mlx5_eswitch_disable_sriov(esw);
 	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a263d890..0ac7a2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1263,6 +1263,7 @@
 	nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
 	handle = add_rule_fte(fte, fg, dest, dest_num, false);
 	if (IS_ERR(handle)) {
+		unlock_ref_node(&fte->node);
 		kfree(fte);
 		goto unlock_fg;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 54e5a78..6547f22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -503,6 +503,13 @@
 	MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size,
 		 to_fw_pkey_sz(dev, 128));
 
+	/* Check log_max_qp from HCA caps to set in current profile */
+	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) {
+		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
+			       profile[prof_sel].log_max_qp,
+			       MLX5_CAP_GEN_MAX(dev, log_max_qp));
+		profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
+	}
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
 			 prof->log_max_qp);
@@ -575,7 +582,6 @@
 	struct mlx5_priv *priv  = &mdev->priv;
 	struct msix_entry *msix = priv->msix_arr;
 	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-	int numa_node           = priv->numa_node;
 	int err;
 
 	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
@@ -583,7 +589,7 @@
 		return -ENOMEM;
 	}
 
-	cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
 			priv->irq_info[i].mask);
 
 	err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
@@ -1189,6 +1195,8 @@
 {
 	int err = 0;
 
+	mlx5_drain_health_wq(dev);
+
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
 		dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n",
@@ -1351,10 +1359,9 @@
 
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv, false);
-	/* In case of kernel call save the pci state and drain health wq */
+	/* In case of kernel call save the pci state */
 	if (state) {
 		pci_save_state(pdev);
-		mlx5_drain_health_wq(dev);
 		mlx5_pci_disable_device(dev);
 	}
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f9b97f5..44389c9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -326,6 +326,7 @@
 static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index f341c1b..00fafab 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -819,6 +819,7 @@
 	.tsu		= 1,
 	.hw_crc		= 1,
 	.select_mii	= 1,
+	.shift_rd0	= 1,
 };
 
 /* SH7763 */
@@ -1656,7 +1657,7 @@
 	else
 		goto out;
 
-	if (!likely(mdp->irq_enabled)) {
+	if (unlikely(!mdp->irq_enabled)) {
 		sh_eth_write(ndev, 0, EESIPR);
 		goto out;
 	}
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index de2947c..5eb0e68 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1323,7 +1323,8 @@
 	}
 
 	/* don't fail init if RSS setup doesn't work */
-	efx->type->rx_push_rss_config(efx, false, efx->rx_indir_table);
+	rc = efx->type->rx_push_rss_config(efx, false, efx->rx_indir_table);
+	efx->rss_active = (rc == 0);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 87bdc56..18ebaea 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -975,6 +975,8 @@
 
 	case ETHTOOL_GRXFH: {
 		info->data = 0;
+		if (!efx->rss_active) /* No RSS */
+			return 0;
 		switch (info->flow_type) {
 		case UDP_V4_FLOW:
 			if (efx->rx_hash_udp_4tuple)
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 1a635ce..1c62c1a 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -860,6 +860,7 @@
  * @rx_hash_key: Toeplitz hash key for RSS
  * @rx_indir_table: Indirection table for RSS
  * @rx_scatter: Scatter mode enabled for receives
+ * @rss_active: RSS enabled on hardware
  * @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled
  * @int_error_count: Number of internal errors seen recently
  * @int_error_expire: Time at which error count will be expired
@@ -998,6 +999,7 @@
 	u8 rx_hash_key[40];
 	u32 rx_indir_table[128];
 	bool rx_scatter;
+	bool rss_active;
 	bool rx_hash_udp_4tuple;
 
 	unsigned int_error_count;
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index a3901bc..4e54e5d 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -403,6 +403,7 @@
 	efx_writeo(efx, &temp, FR_AZ_RX_CFG);
 
 	siena_rx_push_rss_config(efx, false, efx->rx_indir_table);
+	efx->rss_active = true;
 
 	/* Enable event logging */
 	rc = efx_mcdi_log_ctrl(efx, true, false, 0);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
index c355975..3dc7d27 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
@@ -60,8 +60,9 @@
 	struct regmap	*regmap;
 };
 
-static int oxnas_dwmac_init(struct oxnas_dwmac *dwmac)
+static int oxnas_dwmac_init(struct platform_device *pdev, void *priv)
 {
+	struct oxnas_dwmac *dwmac = priv;
 	unsigned int value;
 	int ret;
 
@@ -105,20 +106,20 @@
 	return 0;
 }
 
+static void oxnas_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct oxnas_dwmac *dwmac = priv;
+
+	clk_disable_unprepare(dwmac->clk);
+}
+
 static int oxnas_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
-	struct device_node *sysctrl;
 	struct oxnas_dwmac *dwmac;
 	int ret;
 
-	sysctrl = of_parse_phandle(pdev->dev.of_node, "oxsemi,sys-ctrl", 0);
-	if (!sysctrl) {
-		dev_err(&pdev->dev, "failed to get sys-ctrl node\n");
-		return -EINVAL;
-	}
-
 	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
 	if (ret)
 		return ret;
@@ -128,73 +129,49 @@
 		return PTR_ERR(plat_dat);
 
 	dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
-	if (!dwmac)
-		return -ENOMEM;
+	if (!dwmac) {
+		ret = -ENOMEM;
+		goto err_remove_config_dt;
+	}
 
 	dwmac->dev = &pdev->dev;
 	plat_dat->bsp_priv = dwmac;
+	plat_dat->init = oxnas_dwmac_init;
+	plat_dat->exit = oxnas_dwmac_exit;
 
-	dwmac->regmap = syscon_node_to_regmap(sysctrl);
+	dwmac->regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+							"oxsemi,sys-ctrl");
 	if (IS_ERR(dwmac->regmap)) {
 		dev_err(&pdev->dev, "failed to have sysctrl regmap\n");
-		return PTR_ERR(dwmac->regmap);
+		ret = PTR_ERR(dwmac->regmap);
+		goto err_remove_config_dt;
 	}
 
 	dwmac->clk = devm_clk_get(&pdev->dev, "gmac");
-	if (IS_ERR(dwmac->clk))
-		return PTR_ERR(dwmac->clk);
+	if (IS_ERR(dwmac->clk)) {
+		ret = PTR_ERR(dwmac->clk);
+		goto err_remove_config_dt;
+	}
 
-	ret = oxnas_dwmac_init(dwmac);
+	ret = oxnas_dwmac_init(pdev, plat_dat->bsp_priv);
 	if (ret)
-		return ret;
+		goto err_remove_config_dt;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
-		clk_disable_unprepare(dwmac->clk);
+		goto err_dwmac_exit;
+
+
+	return 0;
+
+err_dwmac_exit:
+	oxnas_dwmac_exit(pdev, plat_dat->bsp_priv);
+err_remove_config_dt:
+	stmmac_remove_config_dt(pdev, plat_dat);
 
 	return ret;
 }
 
-static int oxnas_dwmac_remove(struct platform_device *pdev)
-{
-	struct oxnas_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev);
-	int ret = stmmac_dvr_remove(&pdev->dev);
-
-	clk_disable_unprepare(dwmac->clk);
-
-	return ret;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int oxnas_dwmac_suspend(struct device *dev)
-{
-	struct oxnas_dwmac *dwmac = get_stmmac_bsp_priv(dev);
-	int ret;
-
-	ret = stmmac_suspend(dev);
-	clk_disable_unprepare(dwmac->clk);
-
-	return ret;
-}
-
-static int oxnas_dwmac_resume(struct device *dev)
-{
-	struct oxnas_dwmac *dwmac = get_stmmac_bsp_priv(dev);
-	int ret;
-
-	ret = oxnas_dwmac_init(dwmac);
-	if (ret)
-		return ret;
-
-	ret = stmmac_resume(dev);
-
-	return ret;
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static SIMPLE_DEV_PM_OPS(oxnas_dwmac_pm_ops,
-	oxnas_dwmac_suspend, oxnas_dwmac_resume);
-
 static const struct of_device_id oxnas_dwmac_match[] = {
 	{ .compatible = "oxsemi,ox820-dwmac" },
 	{ }
@@ -203,10 +180,10 @@
 
 static struct platform_driver oxnas_dwmac_driver = {
 	.probe  = oxnas_dwmac_probe,
-	.remove = oxnas_dwmac_remove,
+	.remove = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "oxnas-dwmac",
-		.pm		= &oxnas_dwmac_pm_ops,
+		.pm		= &stmmac_pltfr_pm_ops,
 		.of_match_table = oxnas_dwmac_match,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index bb40382..39eb7a6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3339,13 +3339,6 @@
 
 	spin_lock_init(&priv->lock);
 
-	ret = register_netdev(ndev);
-	if (ret) {
-		netdev_err(priv->dev, "%s: ERROR %i registering the device\n",
-			   __func__, ret);
-		goto error_netdev_register;
-	}
-
 	/* If a specific clk_csr value is passed from the platform
 	 * this means that the CSR Clock Range selection cannot be
 	 * changed at run-time and it is fixed. Viceversa the driver'll try to
@@ -3372,11 +3365,21 @@
 		}
 	}
 
-	return 0;
+	ret = register_netdev(ndev);
+	if (ret) {
+		netdev_err(priv->dev, "%s: ERROR %i registering the device\n",
+			   __func__, ret);
+		goto error_netdev_register;
+	}
 
-error_mdio_register:
-	unregister_netdev(ndev);
+	return ret;
+
 error_netdev_register:
+	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
+	    priv->hw->pcs != STMMAC_PCS_TBI &&
+	    priv->hw->pcs != STMMAC_PCS_RTBI)
+		stmmac_mdio_unregister(ndev);
+error_mdio_register:
 	netif_napi_del(&priv->napi);
 error_hw_init:
 	clk_disable_unprepare(priv->pclk);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index fda01f7..b0344c2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -116,7 +116,7 @@
 	unsigned int mii_address = priv->hw->mii.addr;
 	unsigned int mii_data = priv->hw->mii.data;
 
-	u32 value = MII_WRITE | MII_BUSY;
+	u32 value = MII_BUSY;
 
 	value |= (phyaddr << priv->hw->mii.addr_shift)
 		& priv->hw->mii.addr_mask;
@@ -126,6 +126,8 @@
 		& priv->hw->mii.clk_csr_mask;
 	if (priv->plat->has_gmac4)
 		value |= MII_GMAC4_WRITE;
+	else
+		value |= MII_WRITE;
 
 	/* Wait until any existing MII operation is complete */
 	if (stmmac_mdio_busy_wait(priv->ioaddr, mii_address))
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 031093e..dbfbb33 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -99,6 +99,11 @@
 	int			count;
 };
 
+struct ipvl_skb_cb {
+	bool tx_pkt;
+};
+#define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0]))
+
 static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
 {
 	return rcu_dereference(d->rx_handler_data);
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index b4e9907..83ce74a 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -198,7 +198,7 @@
 	unsigned int mac_hash;
 	int ret;
 	u8 pkt_type;
-	bool hlocal, dlocal;
+	bool tx_pkt;
 
 	__skb_queue_head_init(&list);
 
@@ -207,8 +207,11 @@
 	spin_unlock_bh(&port->backlog.lock);
 
 	while ((skb = __skb_dequeue(&list)) != NULL) {
+		struct net_device *dev = skb->dev;
+		bool consumed = false;
+
 		ethh = eth_hdr(skb);
-		hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
+		tx_pkt = IPVL_SKB_CB(skb)->tx_pkt;
 		mac_hash = ipvlan_mac_hash(ethh->h_dest);
 
 		if (ether_addr_equal(ethh->h_dest, port->dev->broadcast))
@@ -216,41 +219,45 @@
 		else
 			pkt_type = PACKET_MULTICAST;
 
-		dlocal = false;
 		rcu_read_lock();
 		list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
-			if (hlocal && (ipvlan->dev == skb->dev)) {
-				dlocal = true;
+			if (tx_pkt && (ipvlan->dev == skb->dev))
 				continue;
-			}
 			if (!test_bit(mac_hash, ipvlan->mac_filters))
 				continue;
-
+			if (!(ipvlan->dev->flags & IFF_UP))
+				continue;
 			ret = NET_RX_DROP;
 			len = skb->len + ETH_HLEN;
 			nskb = skb_clone(skb, GFP_ATOMIC);
-			if (!nskb)
-				goto acct;
-
-			nskb->pkt_type = pkt_type;
-			nskb->dev = ipvlan->dev;
-			if (hlocal)
-				ret = dev_forward_skb(ipvlan->dev, nskb);
-			else
-				ret = netif_rx(nskb);
-acct:
+			local_bh_disable();
+			if (nskb) {
+				consumed = true;
+				nskb->pkt_type = pkt_type;
+				nskb->dev = ipvlan->dev;
+				if (tx_pkt)
+					ret = dev_forward_skb(ipvlan->dev, nskb);
+				else
+					ret = netif_rx(nskb);
+			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+			local_bh_enable();
 		}
 		rcu_read_unlock();
 
-		if (dlocal) {
+		if (tx_pkt) {
 			/* If the packet originated here, send it out. */
 			skb->dev = port->dev;
 			skb->pkt_type = pkt_type;
 			dev_queue_xmit(skb);
 		} else {
-			kfree_skb(skb);
+			if (consumed)
+				consume_skb(skb);
+			else
+				kfree_skb(skb);
 		}
+		if (dev)
+			dev_put(dev);
 	}
 }
 
@@ -470,15 +477,24 @@
 }
 
 static void ipvlan_multicast_enqueue(struct ipvl_port *port,
-				     struct sk_buff *skb)
+				     struct sk_buff *skb, bool tx_pkt)
 {
 	if (skb->protocol == htons(ETH_P_PAUSE)) {
 		kfree_skb(skb);
 		return;
 	}
 
+	/* Record that the deferred packet is from TX or RX path. By
+	 * looking at mac-addresses on packet will lead to erronus decisions.
+	 * (This would be true for a loopback-mode on master device or a
+	 * hair-pin mode of the switch.)
+	 */
+	IPVL_SKB_CB(skb)->tx_pkt = tx_pkt;
+
 	spin_lock(&port->backlog.lock);
 	if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+		if (skb->dev)
+			dev_hold(skb->dev);
 		__skb_queue_tail(&port->backlog, skb);
 		spin_unlock(&port->backlog.lock);
 		schedule_work(&port->wq);
@@ -537,7 +553,7 @@
 
 	} else if (is_multicast_ether_addr(eth->h_dest)) {
 		ipvlan_skb_crossing_ns(skb, NULL);
-		ipvlan_multicast_enqueue(ipvlan->port, skb);
+		ipvlan_multicast_enqueue(ipvlan->port, skb, true);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -634,7 +650,7 @@
 			 */
 			if (nskb) {
 				ipvlan_skb_crossing_ns(nskb, NULL);
-				ipvlan_multicast_enqueue(port, nskb);
+				ipvlan_multicast_enqueue(port, nskb, false);
 			}
 		}
 	} else {
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 693ec5b..8b0f993 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -135,6 +135,7 @@
 static void ipvlan_port_destroy(struct net_device *dev)
 {
 	struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
 	if (port->mode == IPVLAN_MODE_L3S) {
@@ -144,7 +145,11 @@
 	}
 	netdev_rx_handler_unregister(dev);
 	cancel_work_sync(&port->wq);
-	__skb_queue_purge(&port->backlog);
+	while ((skb = __skb_dequeue(&port->backlog)) != NULL) {
+		if (skb->dev)
+			dev_put(skb->dev);
+		kfree_skb(skb);
+	}
 	kfree(port);
 }
 
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 6c646e2..6e98ede 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -1367,6 +1367,7 @@
 	.probe =	usbnet_probe,
 	.suspend =	asix_suspend,
 	.resume =	asix_resume,
+	.reset_resume =	asix_resume,
 	.disconnect =	usbnet_disconnect,
 	.supports_autosuspend = 1,
 	.disable_hub_initiated_lpm = 1,
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 7532646..23dfb0e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -967,6 +967,7 @@
 	 */
 	need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
 	if (!ipv6_ndisc_frame(skb) && !need_strict) {
+		vrf_rx_stats(vrf_dev, skb->len);
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 
@@ -1011,6 +1012,8 @@
 		goto out;
 	}
 
+	vrf_rx_stats(vrf_dev, skb->len);
+
 	skb_push(skb, skb->mac_len);
 	dev_queue_xmit_nit(skb, vrf_dev);
 	skb_pull(skb, skb->mac_len);
diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c
index b776a0a..9d9b4e0 100644
--- a/drivers/net/wan/slic_ds26522.c
+++ b/drivers/net/wan/slic_ds26522.c
@@ -218,7 +218,7 @@
 
 	ret = slic_ds26522_init_configure(spi);
 	if (ret == 0)
-		pr_info("DS26522 cs%d configurated\n", spi->chip_select);
+		pr_info("DS26522 cs%d configured\n", spi->chip_select);
 
 	return ret;
 }
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index b40cfb0..2fc86dc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1193,8 +1193,8 @@
 		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
 		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
 	}
-	if (ctrl->stripe_size)
-		blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9);
+	if (ctrl->quirks & NVME_QUIRK_STRIPE_SIZE)
+		blk_queue_chunk_sectors(q, ctrl->max_hw_sectors);
 	blk_queue_virt_boundary(q, ctrl->page_size - 1);
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
 		vwc = true;
@@ -1250,19 +1250,6 @@
 	ctrl->max_hw_sectors =
 		min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);
 
-	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) && id->vs[3]) {
-		unsigned int max_hw_sectors;
-
-		ctrl->stripe_size = 1 << (id->vs[3] + page_shift);
-		max_hw_sectors = ctrl->stripe_size >> (page_shift - 9);
-		if (ctrl->max_hw_sectors) {
-			ctrl->max_hw_sectors = min(max_hw_sectors,
-							ctrl->max_hw_sectors);
-		} else {
-			ctrl->max_hw_sectors = max_hw_sectors;
-		}
-	}
-
 	nvme_set_queue_limits(ctrl, ctrl->admin_q);
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 771e2e7..aa0bc60 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1491,19 +1491,20 @@
 nvme_fc_create_hw_io_queues(struct nvme_fc_ctrl *ctrl, u16 qsize)
 {
 	struct nvme_fc_queue *queue = &ctrl->queues[1];
-	int i, j, ret;
+	int i, ret;
 
 	for (i = 1; i < ctrl->queue_count; i++, queue++) {
 		ret = __nvme_fc_create_hw_queue(ctrl, queue, i, qsize);
-		if (ret) {
-			for (j = i-1; j >= 0; j--)
-				__nvme_fc_delete_hw_queue(ctrl,
-						&ctrl->queues[j], j);
-			return ret;
-		}
+		if (ret)
+			goto delete_queues;
 	}
 
 	return 0;
+
+delete_queues:
+	for (; i >= 0; i--)
+		__nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[i], i);
+	return ret;
 }
 
 static int
@@ -2401,8 +2402,8 @@
 	WARN_ON_ONCE(!changed);
 
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d}: new ctrl: NQN \"%s\" (%p)\n",
-		ctrl->cnum, ctrl->ctrl.opts->subsysnqn, &ctrl);
+		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
+		ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
 
 	kref_get(&ctrl->ctrl.kref);
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index bd53214..6377e14 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -135,7 +135,6 @@
 
 	u32 page_size;
 	u32 max_hw_sectors;
-	u32 stripe_size;
 	u16 oncs;
 	u16 vid;
 	atomic_t abort_limit;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3d21a15..19beeb7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -712,15 +712,8 @@
 		req = blk_mq_tag_to_rq(*nvmeq->tags, cqe.command_id);
 		nvme_req(req)->result = cqe.result;
 		blk_mq_complete_request(req, le16_to_cpu(cqe.status) >> 1);
-
 	}
 
-	/* If the controller ignores the cq head doorbell and continuously
-	 * writes to the queue, it is theoretically possible to wrap around
-	 * the queue twice and mistakenly return IRQ_NONE.  Linux only
-	 * requires that 0.1% of your interrupts are handled, so this isn't
-	 * a big problem.
-	 */
 	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
 		return;
 
@@ -1909,10 +1902,10 @@
 	if (!dev->bar)
 		goto release;
 
-       return 0;
+	return 0;
   release:
-       pci_release_mem_regions(pdev);
-       return -ENODEV;
+	pci_release_mem_regions(pdev);
+	return -ENODEV;
 }
 
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c
index b71e950..a5c09e7 100644
--- a/drivers/nvme/host/scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -2160,30 +2160,6 @@
 	return nvme_trans_status_code(hdr, nvme_sc);
 }
 
-static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
-							u8 *cmd)
-{
-	u8 immed, no_flush;
-
-	immed = cmd[1] & 0x01;
-	no_flush = cmd[4] & 0x04;
-
-	if (immed != 0) {
-		return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
-					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
-					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-	} else {
-		if (no_flush == 0) {
-			/* Issue NVME FLUSH command prior to START STOP UNIT */
-			int res = nvme_trans_synchronize_cache(ns, hdr);
-			if (res)
-				return res;
-		}
-
-		return 0;
-	}
-}
-
 static int nvme_trans_format_unit(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
@@ -2439,9 +2415,6 @@
 	case SECURITY_PROTOCOL_OUT:
 		retcode = nvme_trans_security_protocol(ns, hdr, cmd);
 		break;
-	case START_STOP:
-		retcode = nvme_trans_start_stop(ns, hdr, cmd);
-		break;
 	case SYNCHRONIZE_CACHE:
 		retcode = nvme_trans_synchronize_cache(ns, hdr);
 		break;
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index ec1ad2a..95ae523 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -382,7 +382,6 @@
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
-	u64 val;
 	u32 val32;
 	u16 status = 0;
 
@@ -392,8 +391,7 @@
 			(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
 		break;
 	case NVME_FEAT_KATO:
-		val = le64_to_cpu(req->cmd->prop_set.value);
-		val32 = val & 0xffff;
+		val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
 		req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
 		nvmet_set_result(req, req->sq->ctrl->kato);
 		break;
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index bcb8ebe..4e8e6a2 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -845,7 +845,7 @@
 	rport->lport = nport->lport;
 	nport->rport = rport;
 
-	return ret ? ret : count;
+	return count;
 }
 
 
@@ -952,7 +952,7 @@
 	tport->lport = nport->lport;
 	nport->tport = tport;
 
-	return ret ? ret : count;
+	return count;
 }
 
 
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 965911d..398ea7f 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -981,8 +981,8 @@
  * @cell: nvmem cell to be read.
  * @len: pointer to length of cell which will be populated on successful read.
  *
- * Return: ERR_PTR() on error or a valid pointer to a char * buffer on success.
- * The buffer should be freed by the consumer with a kfree().
+ * Return: ERR_PTR() on error or a valid pointer to a buffer on success. The
+ * buffer should be freed by the consumer with a kfree().
  */
 void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len)
 {
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index ac27b9b..8e7b120 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -71,7 +71,7 @@
 
 static const struct of_device_id imx_ocotp_dt_ids[] = {
 	{ .compatible = "fsl,imx6q-ocotp",  (void *)128 },
-	{ .compatible = "fsl,imx6sl-ocotp", (void *)32 },
+	{ .compatible = "fsl,imx6sl-ocotp", (void *)64 },
 	{ .compatible = "fsl,imx6sx-ocotp", (void *)128 },
 	{ },
 };
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index b5305f0..2bdb6c3 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -21,11 +21,11 @@
 			unsigned int reg, void *_val, size_t bytes)
 {
 	void __iomem *base = context;
-	u32 *val = _val;
-	int i = 0, words = bytes / 4;
+	u8 *val = _val;
+	int i = 0, words = bytes;
 
 	while (words--)
-		*val++ = readl(base + reg + (i++ * 4));
+		*val++ = readb(base + reg + i++);
 
 	return 0;
 }
@@ -34,11 +34,11 @@
 			 unsigned int reg, void *_val, size_t bytes)
 {
 	void __iomem *base = context;
-	u32 *val = _val;
-	int i = 0, words = bytes / 4;
+	u8 *val = _val;
+	int i = 0, words = bytes;
 
 	while (words--)
-		writel(*val++, base + reg + (i++ * 4));
+		writeb(*val++, base + reg + i++);
 
 	return 0;
 }
@@ -53,7 +53,7 @@
 static struct nvmem_config econfig = {
 	.name = "qfprom",
 	.owner = THIS_MODULE,
-	.stride = 4,
+	.stride = 1,
 	.word_size = 1,
 	.reg_read = qfprom_reg_read,
 	.reg_write = qfprom_reg_write,
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index a579126..620c231a 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -212,7 +212,7 @@
 {
 	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
 
-	meson_pmx_disable_other_groups(pc, range->pin_base + offset, -1);
+	meson_pmx_disable_other_groups(pc, offset, -1);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index aea310a..c9a1469 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -382,26 +382,21 @@
 {
 	int ret = 0;
 	u32 pin_reg;
-	unsigned long flags;
-	bool level_trig;
-	u32 active_level;
+	unsigned long flags, irq_flags;
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
 	spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
 
-	/*
-	 * When level_trig is set EDGE and active_level is set HIGH in BIOS
-	 * default settings, ignore incoming settings from client and use
-	 * BIOS settings to configure GPIO register.
+	/* Ignore the settings coming from the client and
+	 * read the values from the ACPI tables
+	 * while setting the trigger type
 	 */
-	level_trig = !(pin_reg & (LEVEL_TRIGGER << LEVEL_TRIG_OFF));
-	active_level = pin_reg & (ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF);
 
-	if(level_trig &&
-	   ((active_level >> ACTIVE_LEVEL_OFF) == ACTIVE_HIGH))
-		type = IRQ_TYPE_EDGE_FALLING;
+	irq_flags = irq_get_trigger_type(d->irq);
+	if (irq_flags != IRQ_TYPE_NONE)
+		type = irq_flags;
 
 	switch (type & IRQ_TYPE_SENSE_MASK) {
 	case IRQ_TYPE_EDGE_RISING:
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 12f7d1e..07409fd 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -56,6 +56,17 @@
 	.reg_offset = { 0x00, 0x04, 0x08, 0x0c, },
 };
 
+/* Exynos5433 has the 4bit widths for PINCFG_TYPE_DRV bitfields. */
+static const struct samsung_pin_bank_type exynos5433_bank_type_off = {
+	.fld_width = { 4, 1, 2, 4, 2, 2, },
+	.reg_offset = { 0x00, 0x04, 0x08, 0x0c, 0x10, 0x14, },
+};
+
+static const struct samsung_pin_bank_type exynos5433_bank_type_alive = {
+	.fld_width = { 4, 1, 2, 4, },
+	.reg_offset = { 0x00, 0x04, 0x08, 0x0c, },
+};
+
 static void exynos_irq_mask(struct irq_data *irqd)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
@@ -1335,82 +1346,82 @@
 
 /* pin banks of exynos5433 pin-controller - ALIVE */
 static const struct samsung_pin_bank_data exynos5433_pin_banks0[] = {
-	EXYNOS_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
-	EXYNOS_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
-	EXYNOS_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
-	EXYNOS_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
-	EXYNOS_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
 };
 
 /* pin banks of exynos5433 pin-controller - AUD */
 static const struct samsung_pin_bank_data exynos5433_pin_banks1[] = {
-	EXYNOS_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
-	EXYNOS_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
+	EXYNOS5433_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
 };
 
 /* pin banks of exynos5433 pin-controller - CPIF */
 static const struct samsung_pin_bank_data exynos5433_pin_banks2[] = {
-	EXYNOS_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - eSE */
 static const struct samsung_pin_bank_data exynos5433_pin_banks3[] = {
-	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - FINGER */
 static const struct samsung_pin_bank_data exynos5433_pin_banks4[] = {
-	EXYNOS_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - FSYS */
 static const struct samsung_pin_bank_data exynos5433_pin_banks5[] = {
-	EXYNOS_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
-	EXYNOS_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
-	EXYNOS_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
-	EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
-	EXYNOS_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
-	EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
 };
 
 /* pin banks of exynos5433 pin-controller - IMEM */
 static const struct samsung_pin_bank_data exynos5433_pin_banks6[] = {
-	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - NFC */
 static const struct samsung_pin_bank_data exynos5433_pin_banks7[] = {
-	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - PERIC */
 static const struct samsung_pin_bank_data exynos5433_pin_banks8[] = {
-	EXYNOS_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
-	EXYNOS_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
-	EXYNOS_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
-	EXYNOS_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
-	EXYNOS_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
-	EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
-	EXYNOS_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
-	EXYNOS_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
-	EXYNOS_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
-	EXYNOS_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
-	EXYNOS_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
-	EXYNOS_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
-	EXYNOS_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
-	EXYNOS_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
-	EXYNOS_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
-	EXYNOS_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
-	EXYNOS_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
+	EXYNOS5433_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
+	EXYNOS5433_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
 };
 
 /* pin banks of exynos5433 pin-controller - TOUCH */
 static const struct samsung_pin_bank_data exynos5433_pin_banks9[] = {
-	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
 };
 
 /*
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.h b/drivers/pinctrl/samsung/pinctrl-exynos.h
index 5821525..a473092 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.h
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.h
@@ -90,6 +90,37 @@
 		.pctl_res_idx   = pctl_idx,             \
 	}						\
 
+#define EXYNOS5433_PIN_BANK_EINTG(pins, reg, id, offs)		\
+	{							\
+		.type		= &exynos5433_bank_type_off,	\
+		.pctl_offset	= reg,				\
+		.nr_pins	= pins,				\
+		.eint_type	= EINT_TYPE_GPIO,		\
+		.eint_offset	= offs,				\
+		.name		= id				\
+	}
+
+#define EXYNOS5433_PIN_BANK_EINTW(pins, reg, id, offs)		\
+	{							\
+		.type		= &exynos5433_bank_type_alive,	\
+		.pctl_offset	= reg,				\
+		.nr_pins	= pins,				\
+		.eint_type	= EINT_TYPE_WKUP,		\
+		.eint_offset	= offs,				\
+		.name		= id				\
+	}
+
+#define EXYNOS5433_PIN_BANK_EINTW_EXT(pins, reg, id, offs, pctl_idx) \
+	{							\
+		.type           = &exynos5433_bank_type_alive,	\
+		.pctl_offset    = reg,				\
+		.nr_pins        = pins,				\
+		.eint_type      = EINT_TYPE_WKUP,		\
+		.eint_offset    = offs,				\
+		.name           = id,				\
+		.pctl_res_idx   = pctl_idx,			\
+	}							\
+
 /**
  * struct exynos_weint_data: irq specific data for all the wakeup interrupts
  * generated by the external wakeup interrupt controller.
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 5fe8be0..59aa8e3 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -1034,7 +1034,7 @@
 
 config SURFACE_3_BUTTON
 	tristate "Power/home/volume buttons driver for Microsoft Surface 3 tablet"
-	depends on ACPI && KEYBOARD_GPIO
+	depends on ACPI && KEYBOARD_GPIO && I2C
 	---help---
 	  This driver handles the power/home/volume buttons on the Microsoft Surface 3 tablet.
 
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index 61f39ab..82d6771 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -177,43 +177,43 @@
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 static enum led_brightness logolamp_get(struct led_classdev *cdev);
-static void logolamp_set(struct led_classdev *cdev,
+static int logolamp_set(struct led_classdev *cdev,
 			       enum led_brightness brightness);
 
 static struct led_classdev logolamp_led = {
  .name = "fujitsu::logolamp",
  .brightness_get = logolamp_get,
- .brightness_set = logolamp_set
+ .brightness_set_blocking = logolamp_set
 };
 
 static enum led_brightness kblamps_get(struct led_classdev *cdev);
-static void kblamps_set(struct led_classdev *cdev,
+static int kblamps_set(struct led_classdev *cdev,
 			       enum led_brightness brightness);
 
 static struct led_classdev kblamps_led = {
  .name = "fujitsu::kblamps",
  .brightness_get = kblamps_get,
- .brightness_set = kblamps_set
+ .brightness_set_blocking = kblamps_set
 };
 
 static enum led_brightness radio_led_get(struct led_classdev *cdev);
-static void radio_led_set(struct led_classdev *cdev,
+static int radio_led_set(struct led_classdev *cdev,
 			       enum led_brightness brightness);
 
 static struct led_classdev radio_led = {
  .name = "fujitsu::radio_led",
  .brightness_get = radio_led_get,
- .brightness_set = radio_led_set
+ .brightness_set_blocking = radio_led_set
 };
 
 static enum led_brightness eco_led_get(struct led_classdev *cdev);
-static void eco_led_set(struct led_classdev *cdev,
+static int eco_led_set(struct led_classdev *cdev,
 			       enum led_brightness brightness);
 
 static struct led_classdev eco_led = {
  .name = "fujitsu::eco_led",
  .brightness_get = eco_led_get,
- .brightness_set = eco_led_set
+ .brightness_set_blocking = eco_led_set
 };
 #endif
 
@@ -267,48 +267,48 @@
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 /* LED class callbacks */
 
-static void logolamp_set(struct led_classdev *cdev,
+static int logolamp_set(struct led_classdev *cdev,
 			       enum led_brightness brightness)
 {
 	if (brightness >= LED_FULL) {
 		call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_POWERON, FUNC_LED_ON);
-		call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_ALWAYS, FUNC_LED_ON);
+		return call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_ALWAYS, FUNC_LED_ON);
 	} else if (brightness >= LED_HALF) {
 		call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_POWERON, FUNC_LED_ON);
-		call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_ALWAYS, FUNC_LED_OFF);
+		return call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_ALWAYS, FUNC_LED_OFF);
 	} else {
-		call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_POWERON, FUNC_LED_OFF);
+		return call_fext_func(FUNC_LEDS, 0x1, LOGOLAMP_POWERON, FUNC_LED_OFF);
 	}
 }
 
-static void kblamps_set(struct led_classdev *cdev,
+static int kblamps_set(struct led_classdev *cdev,
 			       enum led_brightness brightness)
 {
 	if (brightness >= LED_FULL)
-		call_fext_func(FUNC_LEDS, 0x1, KEYBOARD_LAMPS, FUNC_LED_ON);
+		return call_fext_func(FUNC_LEDS, 0x1, KEYBOARD_LAMPS, FUNC_LED_ON);
 	else
-		call_fext_func(FUNC_LEDS, 0x1, KEYBOARD_LAMPS, FUNC_LED_OFF);
+		return call_fext_func(FUNC_LEDS, 0x1, KEYBOARD_LAMPS, FUNC_LED_OFF);
 }
 
-static void radio_led_set(struct led_classdev *cdev,
+static int radio_led_set(struct led_classdev *cdev,
 				enum led_brightness brightness)
 {
 	if (brightness >= LED_FULL)
-		call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, RADIO_LED_ON);
+		return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, RADIO_LED_ON);
 	else
-		call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0);
+		return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0);
 }
 
-static void eco_led_set(struct led_classdev *cdev,
+static int eco_led_set(struct led_classdev *cdev,
 				enum led_brightness brightness)
 {
 	int curr;
 
 	curr = call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0);
 	if (brightness >= LED_FULL)
-		call_fext_func(FUNC_LEDS, 0x1, ECO_LED, curr | ECO_LED_ON);
+		return call_fext_func(FUNC_LEDS, 0x1, ECO_LED, curr | ECO_LED_ON);
 	else
-		call_fext_func(FUNC_LEDS, 0x1, ECO_LED, curr & ~ECO_LED_ON);
+		return call_fext_func(FUNC_LEDS, 0x1, ECO_LED, curr & ~ECO_LED_ON);
 }
 
 static enum led_brightness logolamp_get(struct led_classdev *cdev)
diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c
index 8130dfe..4971aa5 100644
--- a/drivers/staging/octeon/ethernet.c
+++ b/drivers/staging/octeon/ethernet.c
@@ -770,6 +770,7 @@
 			/* Initialize the device private structure. */
 			struct octeon_ethernet *priv = netdev_priv(dev);
 
+			SET_NETDEV_DEV(dev, &pdev->dev);
 			dev->netdev_ops = &cvm_oct_pow_netdev_ops;
 			priv->imode = CVMX_HELPER_INTERFACE_MODE_DISABLED;
 			priv->port = CVMX_PIP_NUM_INPUT_PORTS;
@@ -816,6 +817,7 @@
 			}
 
 			/* Initialize the device private structure. */
+			SET_NETDEV_DEV(dev, &pdev->dev);
 			priv = netdev_priv(dev);
 			priv->netdev = dev;
 			priv->of_node = cvm_oct_node_for_port(pip, interface,
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 0aa9e7d..25dbd8c 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -239,6 +239,16 @@
 	if (ifp->desc.bNumEndpoints >= num_ep)
 		goto skip_to_next_endpoint_or_interface_descriptor;
 
+	/* Check for duplicate endpoint addresses */
+	for (i = 0; i < ifp->desc.bNumEndpoints; ++i) {
+		if (ifp->endpoint[i].desc.bEndpointAddress ==
+		    d->bEndpointAddress) {
+			dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n",
+			    cfgno, inum, asnum, d->bEndpointAddress);
+			goto skip_to_next_endpoint_or_interface_descriptor;
+		}
+	}
+
 	endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints];
 	++ifp->desc.bNumEndpoints;
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 1fa5c0f..a56c75e 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -103,8 +103,7 @@
 
 static void hub_release(struct kref *kref);
 static int usb_reset_and_verify_device(struct usb_device *udev);
-static void hub_usb3_port_prepare_disable(struct usb_hub *hub,
-					  struct usb_port *port_dev);
+static int hub_port_disable(struct usb_hub *hub, int port1, int set_state);
 
 static inline char *portspeed(struct usb_hub *hub, int portstatus)
 {
@@ -903,34 +902,6 @@
 }
 
 /*
- * USB-3 does not have a similar link state as USB-2 that will avoid negotiating
- * a connection with a plugged-in cable but will signal the host when the cable
- * is unplugged. Disable remote wake and set link state to U3 for USB-3 devices
- */
-static int hub_port_disable(struct usb_hub *hub, int port1, int set_state)
-{
-	struct usb_port *port_dev = hub->ports[port1 - 1];
-	struct usb_device *hdev = hub->hdev;
-	int ret = 0;
-
-	if (!hub->error) {
-		if (hub_is_superspeed(hub->hdev)) {
-			hub_usb3_port_prepare_disable(hub, port_dev);
-			ret = hub_set_port_link_state(hub, port_dev->portnum,
-						      USB_SS_PORT_LS_U3);
-		} else {
-			ret = usb_clear_port_feature(hdev, port1,
-					USB_PORT_FEAT_ENABLE);
-		}
-	}
-	if (port_dev->child && set_state)
-		usb_set_device_state(port_dev->child, USB_STATE_NOTATTACHED);
-	if (ret && ret != -ENODEV)
-		dev_err(&port_dev->dev, "cannot disable (err = %d)\n", ret);
-	return ret;
-}
-
-/*
  * Disable a port and mark a logical connect-change event, so that some
  * time later hub_wq will disconnect() any existing usb_device on the port
  * and will re-enumerate if there actually is a device attached.
@@ -4162,6 +4133,34 @@
 
 #endif	/* CONFIG_PM */
 
+/*
+ * USB-3 does not have a similar link state as USB-2 that will avoid negotiating
+ * a connection with a plugged-in cable but will signal the host when the cable
+ * is unplugged. Disable remote wake and set link state to U3 for USB-3 devices
+ */
+static int hub_port_disable(struct usb_hub *hub, int port1, int set_state)
+{
+	struct usb_port *port_dev = hub->ports[port1 - 1];
+	struct usb_device *hdev = hub->hdev;
+	int ret = 0;
+
+	if (!hub->error) {
+		if (hub_is_superspeed(hub->hdev)) {
+			hub_usb3_port_prepare_disable(hub, port_dev);
+			ret = hub_set_port_link_state(hub, port_dev->portnum,
+						      USB_SS_PORT_LS_U3);
+		} else {
+			ret = usb_clear_port_feature(hdev, port1,
+					USB_PORT_FEAT_ENABLE);
+		}
+	}
+	if (port_dev->child && set_state)
+		usb_set_device_state(port_dev->child, USB_STATE_NOTATTACHED);
+	if (ret && ret != -ENODEV)
+		dev_err(&port_dev->dev, "cannot disable (err = %d)\n", ret);
+	return ret;
+}
+
 
 /* USB 2.0 spec, 7.1.7.3 / fig 7-29:
  *
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index b95930f..c55db4a 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -3753,7 +3753,7 @@
 		hs_ep->desc_list = dma_alloc_coherent(hsotg->dev,
 			MAX_DMA_DESC_NUM_GENERIC *
 			sizeof(struct dwc2_dma_desc),
-			&hs_ep->desc_list_dma, GFP_KERNEL);
+			&hs_ep->desc_list_dma, GFP_ATOMIC);
 		if (!hs_ep->desc_list) {
 			ret = -ENOMEM;
 			goto error2;
diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index a786256..11fe68a 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -247,8 +247,6 @@
 static void dwc2_get_device_property(struct dwc2_hsotg *hsotg,
 				     char *property, u8 size, u64 *value)
 {
-	u8 val8;
-	u16 val16;
 	u32 val32;
 
 	switch (size) {
@@ -256,17 +254,7 @@
 		*value = device_property_read_bool(hsotg->dev, property);
 		break;
 	case 1:
-		if (device_property_read_u8(hsotg->dev, property, &val8))
-			return;
-
-		*value = val8;
-		break;
 	case 2:
-		if (device_property_read_u16(hsotg->dev, property, &val16))
-			return;
-
-		*value = val16;
-		break;
 	case 4:
 		if (device_property_read_u32(hsotg->dev, property, &val32))
 			return;
@@ -1100,13 +1088,13 @@
 	/* Buffer DMA */
 	dwc2_set_param_bool(hsotg, &p->g_dma,
 			    false, "gadget-dma",
-			    true, false,
+			    dma_capable, false,
 			    dma_capable);
 
 	/* DMA Descriptor */
 	dwc2_set_param_bool(hsotg, &p->g_dma_desc, false,
 			    "gadget-dma-desc",
-			    p->g_dma, false,
+			    !!hw->dma_desc_enable, false,
 			    !!hw->dma_desc_enable);
 }
 
@@ -1130,8 +1118,14 @@
 
 		dwc2_set_param_bool(hsotg, &p->host_dma,
 				    false, "host-dma",
-				    true, false,
+				    dma_capable, false,
 				    dma_capable);
+		dwc2_set_param_host_rx_fifo_size(hsotg,
+				params->host_rx_fifo_size);
+		dwc2_set_param_host_nperio_tx_fifo_size(hsotg,
+				params->host_nperio_tx_fifo_size);
+		dwc2_set_param_host_perio_tx_fifo_size(hsotg,
+				params->host_perio_tx_fifo_size);
 	}
 	dwc2_set_param_dma_desc_enable(hsotg, params->dma_desc_enable);
 	dwc2_set_param_dma_desc_fs_enable(hsotg, params->dma_desc_fs_enable);
@@ -1140,12 +1134,6 @@
 			params->host_support_fs_ls_low_power);
 	dwc2_set_param_enable_dynamic_fifo(hsotg,
 			params->enable_dynamic_fifo);
-	dwc2_set_param_host_rx_fifo_size(hsotg,
-			params->host_rx_fifo_size);
-	dwc2_set_param_host_nperio_tx_fifo_size(hsotg,
-			params->host_nperio_tx_fifo_size);
-	dwc2_set_param_host_perio_tx_fifo_size(hsotg,
-			params->host_perio_tx_fifo_size);
 	dwc2_set_param_max_transfer_size(hsotg,
 			params->max_transfer_size);
 	dwc2_set_param_max_packet_count(hsotg,
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index de5a857..14b7602 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -45,9 +45,7 @@
 #define DWC3_XHCI_RESOURCES_NUM	2
 
 #define DWC3_SCRATCHBUF_SIZE	4096	/* each buffer is assumed to be 4KiB */
-#define DWC3_EVENT_SIZE		4	/* bytes */
-#define DWC3_EVENT_MAX_NUM	64	/* 2 events/endpoint */
-#define DWC3_EVENT_BUFFERS_SIZE	(DWC3_EVENT_SIZE * DWC3_EVENT_MAX_NUM)
+#define DWC3_EVENT_BUFFERS_SIZE	4096
 #define DWC3_EVENT_TYPE_MASK	0xfe
 
 #define DWC3_EVENT_TYPE_DEV	0
@@ -311,9 +309,8 @@
 #define DWC3_DCFG_SUPERSPEED_PLUS (5 << 0)  /* DWC_usb31 only */
 #define DWC3_DCFG_SUPERSPEED	(4 << 0)
 #define DWC3_DCFG_HIGHSPEED	(0 << 0)
-#define DWC3_DCFG_FULLSPEED2	(1 << 0)
+#define DWC3_DCFG_FULLSPEED	(1 << 0)
 #define DWC3_DCFG_LOWSPEED	(2 << 0)
-#define DWC3_DCFG_FULLSPEED1	(3 << 0)
 
 #define DWC3_DCFG_NUMP_SHIFT	17
 #define DWC3_DCFG_NUMP(n)	(((n) >> DWC3_DCFG_NUMP_SHIFT) & 0x1f)
@@ -405,9 +402,8 @@
 #define DWC3_DSTS_SUPERSPEED_PLUS	(5 << 0) /* DWC_usb31 only */
 #define DWC3_DSTS_SUPERSPEED		(4 << 0)
 #define DWC3_DSTS_HIGHSPEED		(0 << 0)
-#define DWC3_DSTS_FULLSPEED2		(1 << 0)
+#define DWC3_DSTS_FULLSPEED		(1 << 0)
 #define DWC3_DSTS_LOWSPEED		(2 << 0)
-#define DWC3_DSTS_FULLSPEED1		(3 << 0)
 
 /* Device Generic Command Register */
 #define DWC3_DGCMD_SET_LMP		0x01
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 29e80cc..eb1b9cb 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/dwc3-omap.h>
@@ -510,7 +511,7 @@
 
 	/* check the DMA Status */
 	reg = dwc3_omap_readl(omap->base, USBOTGSS_SYSCONFIG);
-
+	irq_set_status_flags(omap->irq, IRQ_NOAUTOEN);
 	ret = devm_request_threaded_irq(dev, omap->irq, dwc3_omap_interrupt,
 					dwc3_omap_interrupt_thread, IRQF_SHARED,
 					"dwc3-omap", omap);
@@ -531,7 +532,7 @@
 	}
 
 	dwc3_omap_enable_irqs(omap);
-
+	enable_irq(omap->irq);
 	return 0;
 
 err2:
@@ -552,6 +553,7 @@
 	extcon_unregister_notifier(omap->edev, EXTCON_USB, &omap->vbus_nb);
 	extcon_unregister_notifier(omap->edev, EXTCON_USB_HOST, &omap->id_nb);
 	dwc3_omap_disable_irqs(omap);
+	disable_irq(omap->irq);
 	of_platform_depopulate(omap->dev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 2b73339..cce0a22 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -38,6 +38,7 @@
 #define PCI_DEVICE_ID_INTEL_BXT_M		0x1aaa
 #define PCI_DEVICE_ID_INTEL_APL			0x5aaa
 #define PCI_DEVICE_ID_INTEL_KBP			0xa2b0
+#define PCI_DEVICE_ID_INTEL_GLK			0x31aa
 
 #define PCI_INTEL_BXT_DSM_UUID		"732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
 #define PCI_INTEL_BXT_FUNC_PMU_PWR	4
@@ -73,16 +74,6 @@
 {
 	struct platform_device		*dwc3 = dwc->dwc3;
 	struct pci_dev			*pdev = dwc->pci;
-	int				ret;
-
-	struct property_entry sysdev_property[] = {
-		PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
-		{ },
-	};
-
-	ret = platform_device_add_properties(dwc3, sysdev_property);
-	if (ret)
-		return ret;
 
 	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
 	    pdev->device == PCI_DEVICE_ID_AMD_NL_USB) {
@@ -105,6 +96,7 @@
 			PROPERTY_ENTRY_BOOL("snps,disable_scramble_quirk"),
 			PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"),
 			PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"),
+			PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
 			{ },
 		};
 
@@ -115,7 +107,8 @@
 		int ret;
 
 		struct property_entry properties[] = {
-			PROPERTY_ENTRY_STRING("dr-mode", "peripheral"),
+			PROPERTY_ENTRY_STRING("dr_mode", "peripheral"),
+			PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
 			{ }
 		};
 
@@ -167,6 +160,7 @@
 			PROPERTY_ENTRY_BOOL("snps,usb3_lpm_capable"),
 			PROPERTY_ENTRY_BOOL("snps,has-lpm-erratum"),
 			PROPERTY_ENTRY_BOOL("snps,dis_enblslpm_quirk"),
+			PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
 			{ },
 		};
 
@@ -274,6 +268,7 @@
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT_M), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBP), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_GLK), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
 	{  }	/* Terminating Entry */
 };
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 4878d18..9bb1f85 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -39,18 +39,13 @@
 static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 		struct dwc3_ep *dep, struct dwc3_request *req);
 
-static int dwc3_ep0_start_trans(struct dwc3 *dwc, u8 epnum, dma_addr_t buf_dma,
-		u32 len, u32 type, bool chain)
+static void dwc3_ep0_prepare_one_trb(struct dwc3 *dwc, u8 epnum,
+		dma_addr_t buf_dma, u32 len, u32 type, bool chain)
 {
-	struct dwc3_gadget_ep_cmd_params params;
 	struct dwc3_trb			*trb;
 	struct dwc3_ep			*dep;
 
-	int				ret;
-
 	dep = dwc->eps[epnum];
-	if (dep->flags & DWC3_EP_BUSY)
-		return 0;
 
 	trb = &dwc->ep0_trb[dep->trb_enqueue];
 
@@ -71,15 +66,23 @@
 		trb->ctrl |= (DWC3_TRB_CTRL_IOC
 				| DWC3_TRB_CTRL_LST);
 
-	if (chain)
+	trace_dwc3_prepare_trb(dep, trb);
+}
+
+static int dwc3_ep0_start_trans(struct dwc3 *dwc, u8 epnum)
+{
+	struct dwc3_gadget_ep_cmd_params params;
+	struct dwc3_ep			*dep;
+	int				ret;
+
+	dep = dwc->eps[epnum];
+	if (dep->flags & DWC3_EP_BUSY)
 		return 0;
 
 	memset(&params, 0, sizeof(params));
 	params.param0 = upper_32_bits(dwc->ep0_trb_addr);
 	params.param1 = lower_32_bits(dwc->ep0_trb_addr);
 
-	trace_dwc3_prepare_trb(dep, trb);
-
 	ret = dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_STARTTRANSFER, &params);
 	if (ret < 0)
 		return ret;
@@ -280,8 +283,9 @@
 
 	complete(&dwc->ep0_in_setup);
 
-	ret = dwc3_ep0_start_trans(dwc, 0, dwc->ctrl_req_addr, 8,
+	dwc3_ep0_prepare_one_trb(dwc, 0, dwc->ctrl_req_addr, 8,
 			DWC3_TRBCTL_CONTROL_SETUP, false);
+	ret = dwc3_ep0_start_trans(dwc, 0);
 	WARN_ON(ret < 0);
 }
 
@@ -912,9 +916,9 @@
 
 			dwc->ep0_next_event = DWC3_EP0_COMPLETE;
 
-			ret = dwc3_ep0_start_trans(dwc, epnum,
-					dwc->ctrl_req_addr, 0,
-					DWC3_TRBCTL_CONTROL_DATA, false);
+			dwc3_ep0_prepare_one_trb(dwc, epnum, dwc->ctrl_req_addr,
+					0, DWC3_TRBCTL_CONTROL_DATA, false);
+			ret = dwc3_ep0_start_trans(dwc, epnum);
 			WARN_ON(ret < 0);
 		}
 	}
@@ -993,9 +997,10 @@
 	req->direction = !!dep->number;
 
 	if (req->request.length == 0) {
-		ret = dwc3_ep0_start_trans(dwc, dep->number,
+		dwc3_ep0_prepare_one_trb(dwc, dep->number,
 				dwc->ctrl_req_addr, 0,
 				DWC3_TRBCTL_CONTROL_DATA, false);
+		ret = dwc3_ep0_start_trans(dwc, dep->number);
 	} else if (!IS_ALIGNED(req->request.length, dep->endpoint.maxpacket)
 			&& (dep->number == 0)) {
 		u32	transfer_size = 0;
@@ -1011,7 +1016,7 @@
 		if (req->request.length > DWC3_EP0_BOUNCE_SIZE) {
 			transfer_size = ALIGN(req->request.length - maxpacket,
 					      maxpacket);
-			ret = dwc3_ep0_start_trans(dwc, dep->number,
+			dwc3_ep0_prepare_one_trb(dwc, dep->number,
 						   req->request.dma,
 						   transfer_size,
 						   DWC3_TRBCTL_CONTROL_DATA,
@@ -1023,18 +1028,20 @@
 
 		dwc->ep0_bounced = true;
 
-		ret = dwc3_ep0_start_trans(dwc, dep->number,
+		dwc3_ep0_prepare_one_trb(dwc, dep->number,
 				dwc->ep0_bounce_addr, transfer_size,
 				DWC3_TRBCTL_CONTROL_DATA, false);
+		ret = dwc3_ep0_start_trans(dwc, dep->number);
 	} else {
 		ret = usb_gadget_map_request_by_dev(dwc->sysdev,
 				&req->request, dep->number);
 		if (ret)
 			return;
 
-		ret = dwc3_ep0_start_trans(dwc, dep->number, req->request.dma,
+		dwc3_ep0_prepare_one_trb(dwc, dep->number, req->request.dma,
 				req->request.length, DWC3_TRBCTL_CONTROL_DATA,
 				false);
+		ret = dwc3_ep0_start_trans(dwc, dep->number);
 	}
 
 	WARN_ON(ret < 0);
@@ -1048,8 +1055,9 @@
 	type = dwc->three_stage_setup ? DWC3_TRBCTL_CONTROL_STATUS3
 		: DWC3_TRBCTL_CONTROL_STATUS2;
 
-	return dwc3_ep0_start_trans(dwc, dep->number,
+	dwc3_ep0_prepare_one_trb(dwc, dep->number,
 			dwc->ctrl_req_addr, 0, type, false);
+	return dwc3_ep0_start_trans(dwc, dep->number);
 }
 
 static void __dwc3_ep0_do_control_status(struct dwc3 *dwc, struct dwc3_ep *dep)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index efddaf5..204c754 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -180,11 +180,11 @@
 	if (req->request.status == -EINPROGRESS)
 		req->request.status = status;
 
-	if (dwc->ep0_bounced && dep->number == 0)
+	if (dwc->ep0_bounced && dep->number <= 1)
 		dwc->ep0_bounced = false;
-	else
-		usb_gadget_unmap_request_by_dev(dwc->sysdev,
-				&req->request, req->direction);
+
+	usb_gadget_unmap_request_by_dev(dwc->sysdev,
+			&req->request, req->direction);
 
 	trace_dwc3_gadget_giveback(req);
 
@@ -1720,7 +1720,7 @@
 			reg |= DWC3_DCFG_LOWSPEED;
 			break;
 		case USB_SPEED_FULL:
-			reg |= DWC3_DCFG_FULLSPEED1;
+			reg |= DWC3_DCFG_FULLSPEED;
 			break;
 		case USB_SPEED_HIGH:
 			reg |= DWC3_DCFG_HIGHSPEED;
@@ -2232,9 +2232,14 @@
 
 	dep = dwc->eps[epnum];
 
-	if (!(dep->flags & DWC3_EP_ENABLED) &&
-	    !(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
-		return;
+	if (!(dep->flags & DWC3_EP_ENABLED)) {
+		if (!(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
+			return;
+
+		/* Handle only EPCMDCMPLT when EP disabled */
+		if (event->endpoint_event != DWC3_DEPEVT_EPCMDCMPLT)
+			return;
+	}
 
 	if (epnum == 0 || epnum == 1) {
 		dwc3_ep0_interrupt(dwc, event);
@@ -2531,8 +2536,7 @@
 		dwc->gadget.ep0->maxpacket = 64;
 		dwc->gadget.speed = USB_SPEED_HIGH;
 		break;
-	case DWC3_DSTS_FULLSPEED2:
-	case DWC3_DSTS_FULLSPEED1:
+	case DWC3_DSTS_FULLSPEED:
 		dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(64);
 		dwc->gadget.ep0->maxpacket = 64;
 		dwc->gadget.speed = USB_SPEED_FULL;
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 41ab61f..002822d 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1694,9 +1694,7 @@
 		value = min(w_length, (u16) 1);
 		break;
 
-	/* function drivers must handle get/set altsetting; if there's
-	 * no get() method, we know only altsetting zero works.
-	 */
+	/* function drivers must handle get/set altsetting */
 	case USB_REQ_SET_INTERFACE:
 		if (ctrl->bRequestType != USB_RECIP_INTERFACE)
 			goto unknown;
@@ -1705,7 +1703,13 @@
 		f = cdev->config->interface[intf];
 		if (!f)
 			break;
-		if (w_value && !f->set_alt)
+
+		/*
+		 * If there's no get_alt() method, we know only altsetting zero
+		 * works. There is no need to check if set_alt() is not NULL
+		 * as we check this in usb_add_function().
+		 */
+		if (w_value && !f->get_alt)
 			break;
 		value = f->set_alt(f, w_index, w_value);
 		if (value == USB_GADGET_DELAYED_STATUS) {
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index aab3fc1..5e746ad 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2091,8 +2091,8 @@
 
 	case FFS_STRING:
 		/*
-		 * Strings are indexed from 1 (0 is magic ;) reserved
-		 * for languages list or some such)
+		 * Strings are indexed from 1 (0 is reserved
+		 * for languages list)
 		 */
 		if (*valuep > helper->ffs->strings_count)
 			helper->ffs->strings_count = *valuep;
@@ -2252,7 +2252,7 @@
 
 		if (len < sizeof(*d) ||
 		    d->bFirstInterfaceNumber >= ffs->interfaces_count ||
-		    !d->Reserved1)
+		    d->Reserved1)
 			return -EINVAL;
 		for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i)
 			if (d->Reserved2[i])
@@ -3666,6 +3666,7 @@
 {
 	struct ffs_dev *ffs_obj;
 	struct f_fs_opts *opts;
+	struct config_item *ci;
 
 	ENTER();
 	ffs_dev_lock();
@@ -3689,8 +3690,11 @@
 	    || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount))
 		goto done;
 
-	unregister_gadget_item(ffs_obj->opts->
-			       func_inst.group.cg_item.ci_parent->ci_parent);
+	ci = opts->func_inst.group.cg_item.ci_parent->ci_parent;
+	ffs_dev_unlock();
+
+	unregister_gadget_item(ci);
+	return;
 done:
 	ffs_dev_unlock();
 }
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 3151d2a0..5f8139b 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -593,7 +593,7 @@
 		}
 		status = usb_ep_enable(hidg->out_ep);
 		if (status < 0) {
-			ERROR(cdev, "Enable IN endpoint FAILED!\n");
+			ERROR(cdev, "Enable OUT endpoint FAILED!\n");
 			goto fail;
 		}
 		hidg->out_ep->driver_data = hidg;
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index e8f4102..6bde439 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -1126,7 +1126,7 @@
 	/* data and/or status stage for control request */
 	} else if (dev->state == STATE_DEV_SETUP) {
 
-		/* IN DATA+STATUS caller makes len <= wLength */
+		len = min_t(size_t, len, dev->setup_wLength);
 		if (dev->setup_in) {
 			retval = setup_req (dev->gadget->ep0, dev->req, len);
 			if (retval == 0) {
@@ -1734,10 +1734,12 @@
  * such as configuration notifications.
  */
 
-static int is_valid_config (struct usb_config_descriptor *config)
+static int is_valid_config(struct usb_config_descriptor *config,
+		unsigned int total)
 {
 	return config->bDescriptorType == USB_DT_CONFIG
 		&& config->bLength == USB_DT_CONFIG_SIZE
+		&& total >= USB_DT_CONFIG_SIZE
 		&& config->bConfigurationValue != 0
 		&& (config->bmAttributes & USB_CONFIG_ATT_ONE) != 0
 		&& (config->bmAttributes & USB_CONFIG_ATT_WAKEUP) == 0;
@@ -1762,7 +1764,8 @@
 	}
 	spin_unlock_irq(&dev->lock);
 
-	if (len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4))
+	if ((len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4)) ||
+	    (len > PAGE_SIZE * 4))
 		return -EINVAL;
 
 	/* we might need to change message format someday */
@@ -1786,7 +1789,8 @@
 	/* full or low speed config */
 	dev->config = (void *) kbuf;
 	total = le16_to_cpu(dev->config->wTotalLength);
-	if (!is_valid_config (dev->config) || total >= length)
+	if (!is_valid_config(dev->config, total) ||
+			total > length - USB_DT_DEVICE_SIZE)
 		goto fail;
 	kbuf += total;
 	length -= total;
@@ -1795,10 +1799,13 @@
 	if (kbuf [1] == USB_DT_CONFIG) {
 		dev->hs_config = (void *) kbuf;
 		total = le16_to_cpu(dev->hs_config->wTotalLength);
-		if (!is_valid_config (dev->hs_config) || total >= length)
+		if (!is_valid_config(dev->hs_config, total) ||
+				total > length - USB_DT_DEVICE_SIZE)
 			goto fail;
 		kbuf += total;
 		length -= total;
+	} else {
+		dev->hs_config = NULL;
 	}
 
 	/* could support multiple configs, using another encoding! */
@@ -1811,7 +1818,6 @@
 			|| dev->dev->bDescriptorType != USB_DT_DEVICE
 			|| dev->dev->bNumConfigurations != 1)
 		goto fail;
-	dev->dev->bNumConfigurations = 1;
 	dev->dev->bcdUSB = cpu_to_le16 (0x0200);
 
 	/* triggers gadgetfs_bind(); then we can enumerate. */
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 9483489..0402177 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1317,7 +1317,11 @@
 			if (!ret)
 				break;
 		}
-		if (!ret && !udc->driver)
+		if (ret)
+			ret = -ENODEV;
+		else if (udc->driver)
+			ret = -EBUSY;
+		else
 			goto found;
 	} else {
 		list_for_each_entry(udc, &udc_list, list) {
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 02b14e9..c60abe3 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -330,7 +330,7 @@
 /* caller must hold lock */
 static void stop_activity(struct dummy *dum)
 {
-	struct dummy_ep	*ep;
+	int i;
 
 	/* prevent any more requests */
 	dum->address = 0;
@@ -338,8 +338,8 @@
 	/* The timer is left running so that outstanding URBs can fail */
 
 	/* nuke any pending requests first, so driver i/o is quiesced */
-	list_for_each_entry(ep, &dum->gadget.ep_list, ep.ep_list)
-		nuke(dum, ep);
+	for (i = 0; i < DUMMY_ENDPOINTS; ++i)
+		nuke(dum, &dum->ep[i]);
 
 	/* driver now does any non-usb quiescing necessary */
 }
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index be9e638..414e3c3 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -43,7 +43,6 @@
 	struct gpio_desc *overcurrent_pin[AT91_MAX_USBH_PORTS];
 	u8 ports;				/* number of ports on root hub */
 	u8 overcurrent_supported;
-	u8 vbus_pin_active_low[AT91_MAX_USBH_PORTS];
 	u8 overcurrent_status[AT91_MAX_USBH_PORTS];
 	u8 overcurrent_changed[AT91_MAX_USBH_PORTS];
 };
@@ -266,8 +265,7 @@
 	if (!valid_port(port))
 		return;
 
-	gpiod_set_value(pdata->vbus_pin[port],
-			pdata->vbus_pin_active_low[port] ^ enable);
+	gpiod_set_value(pdata->vbus_pin[port], enable);
 }
 
 static int ohci_at91_usb_get_power(struct at91_usbh_data *pdata, int port)
@@ -275,8 +273,7 @@
 	if (!valid_port(port))
 		return -EINVAL;
 
-	return gpiod_get_value(pdata->vbus_pin[port]) ^
-	       pdata->vbus_pin_active_low[port];
+	return gpiod_get_value(pdata->vbus_pin[port]);
 }
 
 /*
@@ -533,18 +530,17 @@
 		pdata->ports = ports;
 
 	at91_for_each_port(i) {
-		pdata->vbus_pin[i] = devm_gpiod_get_optional(&pdev->dev,
-							     "atmel,vbus-gpio",
-							     GPIOD_IN);
+		if (i >= pdata->ports)
+			break;
+
+		pdata->vbus_pin[i] =
+			devm_gpiod_get_index_optional(&pdev->dev, "atmel,vbus",
+						      i, GPIOD_OUT_HIGH);
 		if (IS_ERR(pdata->vbus_pin[i])) {
 			err = PTR_ERR(pdata->vbus_pin[i]);
 			dev_err(&pdev->dev, "unable to claim gpio \"vbus\": %d\n", err);
 			continue;
 		}
-
-		pdata->vbus_pin_active_low[i] = gpiod_get_value(pdata->vbus_pin[i]);
-
-		ohci_at91_usb_set_power(pdata, i, 1);
 	}
 
 	at91_for_each_port(i) {
@@ -552,8 +548,8 @@
 			break;
 
 		pdata->overcurrent_pin[i] =
-			devm_gpiod_get_optional(&pdev->dev,
-						"atmel,oc-gpio", GPIOD_IN);
+			devm_gpiod_get_index_optional(&pdev->dev, "atmel,oc",
+						      i, GPIOD_IN);
 		if (IS_ERR(pdata->overcurrent_pin[i])) {
 			err = PTR_ERR(pdata->overcurrent_pin[i]);
 			dev_err(&pdev->dev, "unable to claim gpio \"overcurrent\": %d\n", err);
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 321de2e..8414ed2 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -979,6 +979,40 @@
 	xhci->devs[slot_id] = NULL;
 }
 
+/*
+ * Free a virt_device structure.
+ * If the virt_device added a tt_info (a hub) and has children pointing to
+ * that tt_info, then free the child first. Recursive.
+ * We can't rely on udev at this point to find child-parent relationships.
+ */
+void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_id)
+{
+	struct xhci_virt_device *vdev;
+	struct list_head *tt_list_head;
+	struct xhci_tt_bw_info *tt_info, *next;
+	int i;
+
+	vdev = xhci->devs[slot_id];
+	if (!vdev)
+		return;
+
+	tt_list_head = &(xhci->rh_bw[vdev->real_port - 1].tts);
+	list_for_each_entry_safe(tt_info, next, tt_list_head, tt_list) {
+		/* is this a hub device that added a tt_info to the tts list */
+		if (tt_info->slot_id == slot_id) {
+			/* are any devices using this tt_info? */
+			for (i = 1; i < HCS_MAX_SLOTS(xhci->hcs_params1); i++) {
+				vdev = xhci->devs[i];
+				if (vdev && (vdev->tt_info == tt_info))
+					xhci_free_virt_devices_depth_first(
+						xhci, i);
+			}
+		}
+	}
+	/* we are now at a leaf device */
+	xhci_free_virt_device(xhci, slot_id);
+}
+
 int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id,
 		struct usb_device *udev, gfp_t flags)
 {
@@ -1795,7 +1829,7 @@
 	int size;
 	int i, j, num_ports;
 
-	del_timer_sync(&xhci->cmd_timer);
+	cancel_delayed_work_sync(&xhci->cmd_timer);
 
 	/* Free the Event Ring Segment Table and the actual Event Ring */
 	size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries);
@@ -1828,8 +1862,8 @@
 		}
 	}
 
-	for (i = 1; i < MAX_HC_SLOTS; ++i)
-		xhci_free_virt_device(xhci, i);
+	for (i = HCS_MAX_SLOTS(xhci->hcs_params1); i > 0; i--)
+		xhci_free_virt_devices_depth_first(xhci, i);
 
 	dma_pool_destroy(xhci->segment_pool);
 	xhci->segment_pool = NULL;
@@ -2342,9 +2376,9 @@
 
 	INIT_LIST_HEAD(&xhci->cmd_list);
 
-	/* init command timeout timer */
-	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
-		    (unsigned long)xhci);
+	/* init command timeout work */
+	INIT_DELAYED_WORK(&xhci->cmd_timer, xhci_handle_command_timeout);
+	init_completion(&xhci->cmd_ring_stop_completion);
 
 	page_size = readl(&xhci->op_regs->page_size);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index 1094ebd..bac961c 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -579,8 +579,10 @@
 		goto disable_ldos;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
+	if (irq < 0) {
+		ret = irq;
 		goto disable_clk;
+	}
 
 	/* Initialize dma_mask and coherent_dma_mask to 32-bits */
 	ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index e96ae80..954abfd 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -165,7 +165,8 @@
 		 pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI ||
-		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI)) {
+		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI)) {
 		xhci->quirks |= XHCI_PME_STUCK_QUIRK;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index bdf6b13..25f522b 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -279,23 +279,76 @@
 	readl(&xhci->dba->doorbell[0]);
 }
 
-static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
+static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci, unsigned long delay)
+{
+	return mod_delayed_work(system_wq, &xhci->cmd_timer, delay);
+}
+
+static struct xhci_command *xhci_next_queued_cmd(struct xhci_hcd *xhci)
+{
+	return list_first_entry_or_null(&xhci->cmd_list, struct xhci_command,
+					cmd_list);
+}
+
+/*
+ * Turn all commands on command ring with status set to "aborted" to no-op trbs.
+ * If there are other commands waiting then restart the ring and kick the timer.
+ * This must be called with command ring stopped and xhci->lock held.
+ */
+static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
+					 struct xhci_command *cur_cmd)
+{
+	struct xhci_command *i_cmd;
+	u32 cycle_state;
+
+	/* Turn all aborted commands in list to no-ops, then restart */
+	list_for_each_entry(i_cmd, &xhci->cmd_list, cmd_list) {
+
+		if (i_cmd->status != COMP_CMD_ABORT)
+			continue;
+
+		i_cmd->status = COMP_CMD_STOP;
+
+		xhci_dbg(xhci, "Turn aborted command %p to no-op\n",
+			 i_cmd->command_trb);
+		/* get cycle state from the original cmd trb */
+		cycle_state = le32_to_cpu(
+			i_cmd->command_trb->generic.field[3]) &	TRB_CYCLE;
+		/* modify the command trb to no-op command */
+		i_cmd->command_trb->generic.field[0] = 0;
+		i_cmd->command_trb->generic.field[1] = 0;
+		i_cmd->command_trb->generic.field[2] = 0;
+		i_cmd->command_trb->generic.field[3] = cpu_to_le32(
+			TRB_TYPE(TRB_CMD_NOOP) | cycle_state);
+
+		/*
+		 * caller waiting for completion is called when command
+		 *  completion event is received for these no-op commands
+		 */
+	}
+
+	xhci->cmd_ring_state = CMD_RING_STATE_RUNNING;
+
+	/* ring command ring doorbell to restart the command ring */
+	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
+	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
+		xhci->current_cmd = cur_cmd;
+		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_ring_cmd_db(xhci);
+	}
+}
+
+/* Must be called with xhci->lock held, releases and aquires lock back */
+static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 {
 	u64 temp_64;
 	int ret;
 
 	xhci_dbg(xhci, "Abort command ring\n");
 
-	temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
-	xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
+	reinit_completion(&xhci->cmd_ring_stop_completion);
 
-	/*
-	 * Writing the CMD_RING_ABORT bit should cause a cmd completion event,
-	 * however on some host hw the CMD_RING_RUNNING bit is correctly cleared
-	 * but the completion event in never sent. Use the cmd timeout timer to
-	 * handle those cases. Use twice the time to cover the bit polling retry
-	 */
-	mod_timer(&xhci->cmd_timer, jiffies + (2 * XHCI_CMD_DEFAULT_TIMEOUT));
+	temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
 			&xhci->op_regs->cmd_ring);
 
@@ -315,17 +368,30 @@
 		udelay(1000);
 		ret = xhci_handshake(&xhci->op_regs->cmd_ring,
 				     CMD_RING_RUNNING, 0, 3 * 1000 * 1000);
-		if (ret == 0)
-			return 0;
-
-		xhci_err(xhci, "Stopped the command ring failed, "
-				"maybe the host is dead\n");
-		del_timer(&xhci->cmd_timer);
-		xhci->xhc_state |= XHCI_STATE_DYING;
-		xhci_halt(xhci);
-		return -ESHUTDOWN;
+		if (ret < 0) {
+			xhci_err(xhci, "Stopped the command ring failed, "
+				 "maybe the host is dead\n");
+			xhci->xhc_state |= XHCI_STATE_DYING;
+			xhci_halt(xhci);
+			return -ESHUTDOWN;
+		}
 	}
-
+	/*
+	 * Writing the CMD_RING_ABORT bit should cause a cmd completion event,
+	 * however on some host hw the CMD_RING_RUNNING bit is correctly cleared
+	 * but the completion event in never sent. Wait 2 secs (arbitrary
+	 * number) to handle those cases after negation of CMD_RING_RUNNING.
+	 */
+	spin_unlock_irqrestore(&xhci->lock, flags);
+	ret = wait_for_completion_timeout(&xhci->cmd_ring_stop_completion,
+					  msecs_to_jiffies(2000));
+	spin_lock_irqsave(&xhci->lock, flags);
+	if (!ret) {
+		xhci_dbg(xhci, "No stop event for abort, ring start fail?\n");
+		xhci_cleanup_command_queue(xhci);
+	} else {
+		xhci_handle_stopped_cmd_ring(xhci, xhci_next_queued_cmd(xhci));
+	}
 	return 0;
 }
 
@@ -1207,101 +1273,62 @@
 		xhci_complete_del_and_free_cmd(cur_cmd, COMP_CMD_ABORT);
 }
 
-/*
- * Turn all commands on command ring with status set to "aborted" to no-op trbs.
- * If there are other commands waiting then restart the ring and kick the timer.
- * This must be called with command ring stopped and xhci->lock held.
- */
-static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
-					 struct xhci_command *cur_cmd)
-{
-	struct xhci_command *i_cmd, *tmp_cmd;
-	u32 cycle_state;
-
-	/* Turn all aborted commands in list to no-ops, then restart */
-	list_for_each_entry_safe(i_cmd, tmp_cmd, &xhci->cmd_list,
-				 cmd_list) {
-
-		if (i_cmd->status != COMP_CMD_ABORT)
-			continue;
-
-		i_cmd->status = COMP_CMD_STOP;
-
-		xhci_dbg(xhci, "Turn aborted command %p to no-op\n",
-			 i_cmd->command_trb);
-		/* get cycle state from the original cmd trb */
-		cycle_state = le32_to_cpu(
-			i_cmd->command_trb->generic.field[3]) &	TRB_CYCLE;
-		/* modify the command trb to no-op command */
-		i_cmd->command_trb->generic.field[0] = 0;
-		i_cmd->command_trb->generic.field[1] = 0;
-		i_cmd->command_trb->generic.field[2] = 0;
-		i_cmd->command_trb->generic.field[3] = cpu_to_le32(
-			TRB_TYPE(TRB_CMD_NOOP) | cycle_state);
-
-		/*
-		 * caller waiting for completion is called when command
-		 *  completion event is received for these no-op commands
-		 */
-	}
-
-	xhci->cmd_ring_state = CMD_RING_STATE_RUNNING;
-
-	/* ring command ring doorbell to restart the command ring */
-	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
-	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
-		xhci->current_cmd = cur_cmd;
-		mod_timer(&xhci->cmd_timer, jiffies + XHCI_CMD_DEFAULT_TIMEOUT);
-		xhci_ring_cmd_db(xhci);
-	}
-	return;
-}
-
-
-void xhci_handle_command_timeout(unsigned long data)
+void xhci_handle_command_timeout(struct work_struct *work)
 {
 	struct xhci_hcd *xhci;
 	int ret;
 	unsigned long flags;
 	u64 hw_ring_state;
-	bool second_timeout = false;
-	xhci = (struct xhci_hcd *) data;
 
-	/* mark this command to be cancelled */
+	xhci = container_of(to_delayed_work(work), struct xhci_hcd, cmd_timer);
+
 	spin_lock_irqsave(&xhci->lock, flags);
-	if (xhci->current_cmd) {
-		if (xhci->current_cmd->status == COMP_CMD_ABORT)
-			second_timeout = true;
-		xhci->current_cmd->status = COMP_CMD_ABORT;
+
+	/*
+	 * If timeout work is pending, or current_cmd is NULL, it means we
+	 * raced with command completion. Command is handled so just return.
+	 */
+	if (!xhci->current_cmd || delayed_work_pending(&xhci->cmd_timer)) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		return;
 	}
+	/* mark this command to be cancelled */
+	xhci->current_cmd->status = COMP_CMD_ABORT;
 
 	/* Make sure command ring is running before aborting it */
 	hw_ring_state = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	if ((xhci->cmd_ring_state & CMD_RING_STATE_RUNNING) &&
 	    (hw_ring_state & CMD_RING_RUNNING))  {
-		spin_unlock_irqrestore(&xhci->lock, flags);
+		/* Prevent new doorbell, and start command abort */
+		xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
 		xhci_dbg(xhci, "Command timeout\n");
-		ret = xhci_abort_cmd_ring(xhci);
+		ret = xhci_abort_cmd_ring(xhci, flags);
 		if (unlikely(ret == -ESHUTDOWN)) {
 			xhci_err(xhci, "Abort command ring failed\n");
 			xhci_cleanup_command_queue(xhci);
+			spin_unlock_irqrestore(&xhci->lock, flags);
 			usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
 			xhci_dbg(xhci, "xHCI host controller is dead.\n");
+
+			return;
 		}
-		return;
+
+		goto time_out_completed;
 	}
 
-	/* command ring failed to restart, or host removed. Bail out */
-	if (second_timeout || xhci->xhc_state & XHCI_STATE_REMOVING) {
-		spin_unlock_irqrestore(&xhci->lock, flags);
-		xhci_dbg(xhci, "command timed out twice, ring start fail?\n");
+	/* host removed. Bail out */
+	if (xhci->xhc_state & XHCI_STATE_REMOVING) {
+		xhci_dbg(xhci, "host removed, ring start fail?\n");
 		xhci_cleanup_command_queue(xhci);
-		return;
+
+		goto time_out_completed;
 	}
 
 	/* command timeout on stopped ring, ring can't be aborted */
 	xhci_dbg(xhci, "Command timeout on stopped ring\n");
 	xhci_handle_stopped_cmd_ring(xhci, xhci->current_cmd);
+
+time_out_completed:
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	return;
 }
@@ -1333,7 +1360,7 @@
 
 	cmd = list_entry(xhci->cmd_list.next, struct xhci_command, cmd_list);
 
-	del_timer(&xhci->cmd_timer);
+	cancel_delayed_work(&xhci->cmd_timer);
 
 	trace_xhci_cmd_completion(cmd_trb, (struct xhci_generic_trb *) event);
 
@@ -1341,7 +1368,7 @@
 
 	/* If CMD ring stopped we own the trbs between enqueue and dequeue */
 	if (cmd_comp_code == COMP_CMD_STOP) {
-		xhci_handle_stopped_cmd_ring(xhci, cmd);
+		complete_all(&xhci->cmd_ring_stop_completion);
 		return;
 	}
 
@@ -1359,8 +1386,11 @@
 	 */
 	if (cmd_comp_code == COMP_CMD_ABORT) {
 		xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
-		if (cmd->status == COMP_CMD_ABORT)
+		if (cmd->status == COMP_CMD_ABORT) {
+			if (xhci->current_cmd == cmd)
+				xhci->current_cmd = NULL;
 			goto event_handled;
+		}
 	}
 
 	cmd_type = TRB_FIELD_TO_TYPE(le32_to_cpu(cmd_trb->generic.field[3]));
@@ -1421,7 +1451,9 @@
 	if (cmd->cmd_list.next != &xhci->cmd_list) {
 		xhci->current_cmd = list_entry(cmd->cmd_list.next,
 					       struct xhci_command, cmd_list);
-		mod_timer(&xhci->cmd_timer, jiffies + XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+	} else if (xhci->current_cmd == cmd) {
+		xhci->current_cmd = NULL;
 	}
 
 event_handled:
@@ -1939,8 +1971,9 @@
 	struct xhci_ep_ctx *ep_ctx;
 	u32 trb_comp_code;
 	u32 remaining, requested;
-	bool on_data_stage;
+	u32 trb_type;
 
+	trb_type = TRB_FIELD_TO_TYPE(le32_to_cpu(ep_trb->generic.field[3]));
 	slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
 	xdev = xhci->devs[slot_id];
 	ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
@@ -1950,14 +1983,11 @@
 	requested = td->urb->transfer_buffer_length;
 	remaining = EVENT_TRB_LEN(le32_to_cpu(event->transfer_len));
 
-	/* not setup (dequeue), or status stage means we are at data stage */
-	on_data_stage = (ep_trb != ep_ring->dequeue && ep_trb != td->last_trb);
-
 	switch (trb_comp_code) {
 	case COMP_SUCCESS:
-		if (ep_trb != td->last_trb) {
+		if (trb_type != TRB_STATUS) {
 			xhci_warn(xhci, "WARN: Success on ctrl %s TRB without IOC set?\n",
-				  on_data_stage ? "data" : "setup");
+				  (trb_type == TRB_DATA) ? "data" : "setup");
 			*status = -ESHUTDOWN;
 			break;
 		}
@@ -1967,15 +1997,25 @@
 		*status = 0;
 		break;
 	case COMP_STOP_SHORT:
-		if (on_data_stage)
+		if (trb_type == TRB_DATA || trb_type == TRB_NORMAL)
 			td->urb->actual_length = remaining;
 		else
 			xhci_warn(xhci, "WARN: Stopped Short Packet on ctrl setup or status TRB\n");
 		goto finish_td;
 	case COMP_STOP:
-		if (on_data_stage)
+		switch (trb_type) {
+		case TRB_SETUP:
+			td->urb->actual_length = 0;
+			goto finish_td;
+		case TRB_DATA:
+		case TRB_NORMAL:
 			td->urb->actual_length = requested - remaining;
-		goto finish_td;
+			goto finish_td;
+		default:
+			xhci_warn(xhci, "WARN: unexpected TRB Type %d\n",
+				  trb_type);
+			goto finish_td;
+		}
 	case COMP_STOP_INVAL:
 		goto finish_td;
 	default:
@@ -1987,7 +2027,7 @@
 		/* else fall through */
 	case COMP_STALL:
 		/* Did we transfer part of the data (middle) phase? */
-		if (on_data_stage)
+		if (trb_type == TRB_DATA || trb_type == TRB_NORMAL)
 			td->urb->actual_length = requested - remaining;
 		else if (!td->urb_length_set)
 			td->urb->actual_length = 0;
@@ -1995,14 +2035,15 @@
 	}
 
 	/* stopped at setup stage, no data transferred */
-	if (ep_trb == ep_ring->dequeue)
+	if (trb_type == TRB_SETUP)
 		goto finish_td;
 
 	/*
 	 * if on data stage then update the actual_length of the URB and flag it
 	 * as set, so it won't be overwritten in the event for the last TRB.
 	 */
-	if (on_data_stage) {
+	if (trb_type == TRB_DATA ||
+		trb_type == TRB_NORMAL) {
 		td->urb_length_set = true;
 		td->urb->actual_length = requested - remaining;
 		xhci_dbg(xhci, "Waiting for status stage event\n");
@@ -3790,9 +3831,9 @@
 
 	/* if there are no other commands queued we start the timeout timer */
 	if (xhci->cmd_list.next == &cmd->cmd_list &&
-	    !timer_pending(&xhci->cmd_timer)) {
+	    !delayed_work_pending(&xhci->cmd_timer)) {
 		xhci->current_cmd = cmd;
-		mod_timer(&xhci->cmd_timer, jiffies + XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
 	}
 
 	queue_trb(xhci, xhci->cmd_ring, false, field1, field2, field3,
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 1cd5641..0c8deb9 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3787,8 +3787,10 @@
 
 	mutex_lock(&xhci->mutex);
 
-	if (xhci->xhc_state)	/* dying, removing or halted */
+	if (xhci->xhc_state) {	/* dying, removing or halted */
+		ret = -ESHUTDOWN;
 		goto out;
+	}
 
 	if (!udev->slot_id) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_address,
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 8ccc11a..2d7b637 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1568,7 +1568,8 @@
 #define CMD_RING_STATE_STOPPED         (1 << 2)
 	struct list_head        cmd_list;
 	unsigned int		cmd_ring_reserved_trbs;
-	struct timer_list	cmd_timer;
+	struct delayed_work	cmd_timer;
+	struct completion	cmd_ring_stop_completion;
 	struct xhci_command	*current_cmd;
 	struct xhci_ring	*event_ring;
 	struct xhci_erst	erst;
@@ -1934,7 +1935,7 @@
 		unsigned int slot_id, unsigned int ep_index,
 		struct xhci_dequeue_state *deq_state);
 void xhci_stop_endpoint_command_watchdog(unsigned long arg);
-void xhci_handle_command_timeout(unsigned long data);
+void xhci_handle_command_timeout(struct work_struct *work);
 
 void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id,
 		unsigned int ep_index, unsigned int stream_id);
diff --git a/drivers/usb/musb/blackfin.c b/drivers/usb/musb/blackfin.c
index 310238c..8967980 100644
--- a/drivers/usb/musb/blackfin.c
+++ b/drivers/usb/musb/blackfin.c
@@ -469,6 +469,7 @@
 	.init		= bfin_musb_init,
 	.exit		= bfin_musb_exit,
 
+	.fifo_offset	= bfin_fifo_offset,
 	.readb		= bfin_readb,
 	.writeb		= bfin_writeb,
 	.readw		= bfin_readw,
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 9e22646..fca288bb 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2050,6 +2050,7 @@
 	struct list_head node;
 };
 
+#ifdef CONFIG_PM
 /*
  * Called from musb_runtime_resume(), musb_resume(), and
  * musb_queue_resume_work(). Callers must take musb->lock.
@@ -2077,6 +2078,7 @@
 
 	return error;
 }
+#endif
 
 /*
  * Called to run work if device is active or else queue the work to happen
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index a611e2f..ade902e 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -216,6 +216,7 @@
 	void	(*pre_root_reset_end)(struct musb *musb);
 	void	(*post_root_reset_end)(struct musb *musb);
 	int	(*phy_callback)(enum musb_vbus_id_status status);
+	void	(*clear_ep_rxintr)(struct musb *musb, int epnum);
 };
 
 /*
@@ -626,6 +627,12 @@
 		musb->ops->post_root_reset_end(musb);
 }
 
+static inline void musb_platform_clear_ep_rxintr(struct musb *musb, int epnum)
+{
+	if (musb->ops->clear_ep_rxintr)
+		musb->ops->clear_ep_rxintr(musb, epnum);
+}
+
 /*
  * gets the "dr_mode" property from DT and converts it into musb_mode
  * if the property is not found or not recognized returns MUSB_OTG
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index feae156..9f125e1 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -267,6 +267,17 @@
 	pm_runtime_put_autosuspend(dev);
 }
 
+void dsps_musb_clear_ep_rxintr(struct musb *musb, int epnum)
+{
+	u32 epintr;
+	struct dsps_glue *glue = dev_get_drvdata(musb->controller->parent);
+	const struct dsps_musb_wrapper *wrp = glue->wrp;
+
+	/* musb->lock might already been held */
+	epintr = (1 << epnum) << wrp->rxep_shift;
+	musb_writel(musb->ctrl_base, wrp->epintr_status, epintr);
+}
+
 static irqreturn_t dsps_interrupt(int irq, void *hci)
 {
 	struct musb  *musb = hci;
@@ -622,6 +633,7 @@
 
 	.set_mode	= dsps_musb_set_mode,
 	.recover	= dsps_musb_recover,
+	.clear_ep_rxintr = dsps_musb_clear_ep_rxintr,
 };
 
 static u64 musb_dmamask = DMA_BIT_MASK(32);
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index f6cdbad..ac3a495 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -2374,12 +2374,11 @@
 	int			is_in = usb_pipein(urb->pipe);
 	int			status = 0;
 	u16			csr;
+	struct dma_channel	*dma = NULL;
 
 	musb_ep_select(regs, hw_end);
 
 	if (is_dma_capable()) {
-		struct dma_channel	*dma;
-
 		dma = is_in ? ep->rx_channel : ep->tx_channel;
 		if (dma) {
 			status = ep->musb->dma_controller->channel_abort(dma);
@@ -2395,10 +2394,9 @@
 		/* giveback saves bulk toggle */
 		csr = musb_h_flush_rxfifo(ep, 0);
 
-		/* REVISIT we still get an irq; should likely clear the
-		 * endpoint's irq status here to avoid bogus irqs.
-		 * clearing that status is platform-specific...
-		 */
+		/* clear the endpoint's irq status here to avoid bogus irqs */
+		if (is_dma_capable() && dma)
+			musb_platform_clear_ep_rxintr(musb, ep->epnum);
 	} else if (ep->epnum) {
 		musb_h_tx_flush_fifo(ep);
 		csr = musb_readw(epio, MUSB_TXCSR);
diff --git a/drivers/usb/musb/musbhsdma.h b/drivers/usb/musb/musbhsdma.h
index f7b13fd2..a3dcbd5 100644
--- a/drivers/usb/musb/musbhsdma.h
+++ b/drivers/usb/musb/musbhsdma.h
@@ -157,5 +157,5 @@
 	void __iomem			*base;
 	u8				channel_count;
 	u8				used_channels;
-	u8				irq;
+	int				irq;
 };
diff --git a/drivers/usb/serial/cyberjack.c b/drivers/usb/serial/cyberjack.c
index 5f17a3b..80260b0 100644
--- a/drivers/usb/serial/cyberjack.c
+++ b/drivers/usb/serial/cyberjack.c
@@ -50,6 +50,7 @@
 #define CYBERJACK_PRODUCT_ID	0x0100
 
 /* Function prototypes */
+static int cyberjack_attach(struct usb_serial *serial);
 static int cyberjack_port_probe(struct usb_serial_port *port);
 static int cyberjack_port_remove(struct usb_serial_port *port);
 static int  cyberjack_open(struct tty_struct *tty,
@@ -77,6 +78,7 @@
 	.description =		"Reiner SCT Cyberjack USB card reader",
 	.id_table =		id_table,
 	.num_ports =		1,
+	.attach =		cyberjack_attach,
 	.port_probe =		cyberjack_port_probe,
 	.port_remove =		cyberjack_port_remove,
 	.open =			cyberjack_open,
@@ -100,6 +102,14 @@
 	short		wrsent;		/* Data already sent */
 };
 
+static int cyberjack_attach(struct usb_serial *serial)
+{
+	if (serial->num_bulk_out < serial->num_ports)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int cyberjack_port_probe(struct usb_serial_port *port)
 {
 	struct cyberjack_private *priv;
diff --git a/drivers/usb/serial/f81534.c b/drivers/usb/serial/f81534.c
index 8282a6a..22f23a4 100644
--- a/drivers/usb/serial/f81534.c
+++ b/drivers/usb/serial/f81534.c
@@ -1237,6 +1237,7 @@
 static int f81534_port_probe(struct usb_serial_port *port)
 {
 	struct f81534_port_private *port_priv;
+	int ret;
 
 	port_priv = devm_kzalloc(&port->dev, sizeof(*port_priv), GFP_KERNEL);
 	if (!port_priv)
@@ -1246,10 +1247,11 @@
 	mutex_init(&port_priv->mcr_mutex);
 
 	/* Assign logic-to-phy mapping */
-	port_priv->phy_num = f81534_logic_to_phy_port(port->serial, port);
-	if (port_priv->phy_num < 0 || port_priv->phy_num >= F81534_NUM_PORT)
-		return -ENODEV;
+	ret = f81534_logic_to_phy_port(port->serial, port);
+	if (ret < 0)
+		return ret;
 
+	port_priv->phy_num = ret;
 	usb_set_serial_port_data(port, port_priv);
 	dev_dbg(&port->dev, "%s: port_number: %d, phy_num: %d\n", __func__,
 			port->port_number, port_priv->phy_num);
diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c
index 97cabf8..b2f2e87 100644
--- a/drivers/usb/serial/garmin_gps.c
+++ b/drivers/usb/serial/garmin_gps.c
@@ -1043,6 +1043,7 @@
 		   "%s - usb_submit_urb(write bulk) failed with status = %d\n",
 				__func__, status);
 		count = status;
+		kfree(buffer);
 	}
 
 	/* we are done with this urb, so let the host driver
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index dcc0c58..d50e577 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -2751,6 +2751,11 @@
 					EDGE_COMPATIBILITY_MASK1,
 					EDGE_COMPATIBILITY_MASK2 };
 
+	if (serial->num_bulk_in < 1 || serial->num_interrupt_in < 1) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
 	dev = serial->dev;
 
 	/* create our private serial structure */
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index c339163..9a0db29 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -1499,8 +1499,7 @@
 
 		dev_dbg(dev, "%s - Download successful -- Device rebooting...\n", __func__);
 
-		/* return an error on purpose */
-		return -ENODEV;
+		return 1;
 	}
 
 stayinbootmode:
@@ -1508,7 +1507,7 @@
 	dev_dbg(dev, "%s - STAYING IN BOOT MODE\n", __func__);
 	serial->product_info.TiMode = TI_MODE_BOOT;
 
-	return 0;
+	return 1;
 }
 
 static int ti_do_config(struct edgeport_port *port, int feature, int on)
@@ -2546,6 +2545,13 @@
 	int status;
 	u16 product_id;
 
+	/* Make sure we have the required endpoints when in download mode. */
+	if (serial->interface->cur_altsetting->desc.bNumEndpoints > 1) {
+		if (serial->num_bulk_in < serial->num_ports ||
+				serial->num_bulk_out < serial->num_ports)
+			return -ENODEV;
+	}
+
 	/* create our private serial structure */
 	edge_serial = kzalloc(sizeof(struct edgeport_serial), GFP_KERNEL);
 	if (!edge_serial)
@@ -2553,14 +2559,18 @@
 
 	mutex_init(&edge_serial->es_lock);
 	edge_serial->serial = serial;
+	INIT_DELAYED_WORK(&edge_serial->heartbeat_work, edge_heartbeat_work);
 	usb_set_serial_data(serial, edge_serial);
 
 	status = download_fw(edge_serial);
-	if (status) {
+	if (status < 0) {
 		kfree(edge_serial);
 		return status;
 	}
 
+	if (status > 0)
+		return 1;	/* bind but do not register any ports */
+
 	product_id = le16_to_cpu(
 			edge_serial->serial->dev->descriptor.idProduct);
 
@@ -2572,7 +2582,6 @@
 		}
 	}
 
-	INIT_DELAYED_WORK(&edge_serial->heartbeat_work, edge_heartbeat_work);
 	edge_heartbeat_schedule(edge_serial);
 
 	return 0;
@@ -2580,6 +2589,9 @@
 
 static void edge_disconnect(struct usb_serial *serial)
 {
+	struct edgeport_serial *edge_serial = usb_get_serial_data(serial);
+
+	cancel_delayed_work_sync(&edge_serial->heartbeat_work);
 }
 
 static void edge_release(struct usb_serial *serial)
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index 344b4ee..d57fb51 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -68,6 +68,16 @@
 	u32 clk;
 };
 
+static int iuu_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_in < num_ports || serial->num_bulk_out < num_ports)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int iuu_port_probe(struct usb_serial_port *port)
 {
 	struct iuu_private *priv;
@@ -1196,6 +1206,7 @@
 	.tiocmset = iuu_tiocmset,
 	.set_termios = iuu_set_termios,
 	.init_termios = iuu_init_termios,
+	.attach = iuu_attach,
 	.port_probe = iuu_port_probe,
 	.port_remove = iuu_port_remove,
 };
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index e49ad0c..83523fc 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -699,6 +699,19 @@
 MODULE_FIRMWARE("keyspan_pda/xircom_pgs.fw");
 #endif
 
+static int keyspan_pda_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_out < num_ports ||
+			serial->num_interrupt_in < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int keyspan_pda_port_probe(struct usb_serial_port *port)
 {
 
@@ -776,6 +789,7 @@
 	.break_ctl =		keyspan_pda_break_ctl,
 	.tiocmget =		keyspan_pda_tiocmget,
 	.tiocmset =		keyspan_pda_tiocmset,
+	.attach =		keyspan_pda_attach,
 	.port_probe =		keyspan_pda_port_probe,
 	.port_remove =		keyspan_pda_port_remove,
 };
diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c
index 2363654..813035f 100644
--- a/drivers/usb/serial/kobil_sct.c
+++ b/drivers/usb/serial/kobil_sct.c
@@ -51,6 +51,7 @@
 
 
 /* Function prototypes */
+static int kobil_attach(struct usb_serial *serial);
 static int kobil_port_probe(struct usb_serial_port *probe);
 static int kobil_port_remove(struct usb_serial_port *probe);
 static int  kobil_open(struct tty_struct *tty, struct usb_serial_port *port);
@@ -86,6 +87,7 @@
 	.description =		"KOBIL USB smart card terminal",
 	.id_table =		id_table,
 	.num_ports =		1,
+	.attach =		kobil_attach,
 	.port_probe =		kobil_port_probe,
 	.port_remove =		kobil_port_remove,
 	.ioctl =		kobil_ioctl,
@@ -113,6 +115,16 @@
 };
 
 
+static int kobil_attach(struct usb_serial *serial)
+{
+	if (serial->num_interrupt_out < serial->num_ports) {
+		dev_err(&serial->interface->dev, "missing interrupt-out endpoint\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int kobil_port_probe(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index d52caa0..91bc170 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -65,8 +65,6 @@
 	struct urb		*write_urb_pool[NUM_URBS];
 };
 
-static struct usb_serial_driver moschip7720_2port_driver;
-
 #define USB_VENDOR_ID_MOSCHIP		0x9710
 #define MOSCHIP_DEVICE_ID_7720		0x7720
 #define MOSCHIP_DEVICE_ID_7715		0x7715
@@ -970,25 +968,6 @@
 		tty_port_tty_wakeup(&mos7720_port->port->port);
 }
 
-/*
- * mos77xx_probe
- *	this function installs the appropriate read interrupt endpoint callback
- *	depending on whether the device is a 7720 or 7715, thus avoiding costly
- *	run-time checks in the high-frequency callback routine itself.
- */
-static int mos77xx_probe(struct usb_serial *serial,
-			 const struct usb_device_id *id)
-{
-	if (id->idProduct == MOSCHIP_DEVICE_ID_7715)
-		moschip7720_2port_driver.read_int_callback =
-			mos7715_interrupt_callback;
-	else
-		moschip7720_2port_driver.read_int_callback =
-			mos7720_interrupt_callback;
-
-	return 0;
-}
-
 static int mos77xx_calc_num_ports(struct usb_serial *serial)
 {
 	u16 product = le16_to_cpu(serial->dev->descriptor.idProduct);
@@ -1917,6 +1896,11 @@
 	u16 product;
 	int ret_val;
 
+	if (serial->num_bulk_in < 2 || serial->num_bulk_out < 2) {
+		dev_err(&serial->interface->dev, "missing bulk endpoints\n");
+		return -ENODEV;
+	}
+
 	product = le16_to_cpu(serial->dev->descriptor.idProduct);
 	dev = serial->dev;
 
@@ -1941,19 +1925,18 @@
 			tmp->interrupt_in_endpointAddress;
 		serial->port[1]->interrupt_in_urb = NULL;
 		serial->port[1]->interrupt_in_buffer = NULL;
+
+		if (serial->port[0]->interrupt_in_urb) {
+			struct urb *urb = serial->port[0]->interrupt_in_urb;
+
+			urb->complete = mos7715_interrupt_callback;
+		}
 	}
 
 	/* setting configuration feature to one */
 	usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
 			(__u8)0x03, 0x00, 0x01, 0x00, NULL, 0x00, 5000);
 
-	/* start the interrupt urb */
-	ret_val = usb_submit_urb(serial->port[0]->interrupt_in_urb, GFP_KERNEL);
-	if (ret_val)
-		dev_err(&dev->dev,
-			"%s - Error %d submitting control urb\n",
-			__func__, ret_val);
-
 #ifdef CONFIG_USB_SERIAL_MOS7715_PARPORT
 	if (product == MOSCHIP_DEVICE_ID_7715) {
 		ret_val = mos7715_parport_init(serial);
@@ -1961,6 +1944,13 @@
 			return ret_val;
 	}
 #endif
+	/* start the interrupt urb */
+	ret_val = usb_submit_urb(serial->port[0]->interrupt_in_urb, GFP_KERNEL);
+	if (ret_val) {
+		dev_err(&dev->dev, "failed to submit interrupt urb: %d\n",
+			ret_val);
+	}
+
 	/* LSR For Port 1 */
 	read_mos_reg(serial, 0, MOS7720_LSR, &data);
 	dev_dbg(&dev->dev, "LSR:%x\n", data);
@@ -1970,6 +1960,8 @@
 
 static void mos7720_release(struct usb_serial *serial)
 {
+	usb_kill_urb(serial->port[0]->interrupt_in_urb);
+
 #ifdef CONFIG_USB_SERIAL_MOS7715_PARPORT
 	/* close the parallel port */
 
@@ -2019,11 +2011,6 @@
 	if (!mos7720_port)
 		return -ENOMEM;
 
-	/* Initialize all port interrupt end point to port 0 int endpoint.
-	 * Our device has only one interrupt endpoint common to all ports.
-	 */
-	port->interrupt_in_endpointAddress =
-		port->serial->port[0]->interrupt_in_endpointAddress;
 	mos7720_port->port = port;
 
 	usb_set_serial_port_data(port, mos7720_port);
@@ -2053,7 +2040,6 @@
 	.close			= mos7720_close,
 	.throttle		= mos7720_throttle,
 	.unthrottle		= mos7720_unthrottle,
-	.probe			= mos77xx_probe,
 	.attach			= mos7720_startup,
 	.release		= mos7720_release,
 	.port_probe		= mos7720_port_probe,
@@ -2067,7 +2053,7 @@
 	.chars_in_buffer	= mos7720_chars_in_buffer,
 	.break_ctl		= mos7720_break,
 	.read_bulk_callback	= mos7720_bulk_in_callback,
-	.read_int_callback	= NULL  /* dynamically assigned in probe() */
+	.read_int_callback	= mos7720_interrupt_callback,
 };
 
 static struct usb_serial_driver * const serial_drivers[] = {
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 9a220b8..ea27fb2 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -214,7 +214,6 @@
 
 struct moschip_port {
 	int port_num;		/*Actual port number in the device(1,2,etc) */
-	struct urb *write_urb;	/* write URB for this port */
 	struct urb *read_urb;	/* read URB for this port */
 	__u8 shadowLCR;		/* last LCR value received */
 	__u8 shadowMCR;		/* last MCR value received */
@@ -1037,9 +1036,7 @@
 				serial,
 				serial->port[0]->interrupt_in_urb->interval);
 
-			/* start interrupt read for mos7840               *
-			 * will continue as long as mos7840 is connected  */
-
+			/* start interrupt read for mos7840 */
 			response =
 			    usb_submit_urb(serial->port[0]->interrupt_in_urb,
 					   GFP_KERNEL);
@@ -1186,7 +1183,6 @@
 		}
 	}
 
-	usb_kill_urb(mos7840_port->write_urb);
 	usb_kill_urb(mos7840_port->read_urb);
 	mos7840_port->read_urb_busy = false;
 
@@ -1199,12 +1195,6 @@
 		}
 	}
 
-	if (mos7840_port->write_urb) {
-		/* if this urb had a transfer buffer already (old tx) free it */
-		kfree(mos7840_port->write_urb->transfer_buffer);
-		usb_free_urb(mos7840_port->write_urb);
-	}
-
 	Data = 0x0;
 	mos7840_set_uart_reg(port, MODEM_CONTROL_REGISTER, Data);
 
@@ -2113,6 +2103,17 @@
 	return mos7840_num_ports;
 }
 
+static int mos7840_attach(struct usb_serial *serial)
+{
+	if (serial->num_bulk_in < serial->num_ports ||
+			serial->num_bulk_out < serial->num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int mos7840_port_probe(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
@@ -2388,6 +2389,7 @@
 	.tiocmset = mos7840_tiocmset,
 	.tiocmiwait = usb_serial_generic_tiocmiwait,
 	.get_icount = usb_serial_generic_get_icount,
+	.attach = mos7840_attach,
 	.port_probe = mos7840_port_probe,
 	.port_remove = mos7840_port_remove,
 	.read_bulk_callback = mos7840_bulk_in_callback,
diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c
index f6c6900..a180b17 100644
--- a/drivers/usb/serial/omninet.c
+++ b/drivers/usb/serial/omninet.c
@@ -38,6 +38,7 @@
 				const unsigned char *buf, int count);
 static int  omninet_write_room(struct tty_struct *tty);
 static void omninet_disconnect(struct usb_serial *serial);
+static int omninet_attach(struct usb_serial *serial);
 static int omninet_port_probe(struct usb_serial_port *port);
 static int omninet_port_remove(struct usb_serial_port *port);
 
@@ -56,6 +57,7 @@
 	.description =		"ZyXEL - omni.net lcd plus usb",
 	.id_table =		id_table,
 	.num_ports =		1,
+	.attach =		omninet_attach,
 	.port_probe =		omninet_port_probe,
 	.port_remove =		omninet_port_remove,
 	.open =			omninet_open,
@@ -104,6 +106,17 @@
 	__u8	od_outseq;	/* Sequence number for bulk_out URBs */
 };
 
+static int omninet_attach(struct usb_serial *serial)
+{
+	/* The second bulk-out endpoint is used for writing. */
+	if (serial->num_bulk_out < 2) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int omninet_port_probe(struct usb_serial_port *port)
 {
 	struct omninet_data *od;
diff --git a/drivers/usb/serial/oti6858.c b/drivers/usb/serial/oti6858.c
index a4b88bc..b8bf52b 100644
--- a/drivers/usb/serial/oti6858.c
+++ b/drivers/usb/serial/oti6858.c
@@ -134,6 +134,7 @@
 static int oti6858_tiocmget(struct tty_struct *tty);
 static int oti6858_tiocmset(struct tty_struct *tty,
 				unsigned int set, unsigned int clear);
+static int oti6858_attach(struct usb_serial *serial);
 static int oti6858_port_probe(struct usb_serial_port *port);
 static int oti6858_port_remove(struct usb_serial_port *port);
 
@@ -158,6 +159,7 @@
 	.write_bulk_callback =	oti6858_write_bulk_callback,
 	.write_room =		oti6858_write_room,
 	.chars_in_buffer =	oti6858_chars_in_buffer,
+	.attach =		oti6858_attach,
 	.port_probe =		oti6858_port_probe,
 	.port_remove =		oti6858_port_remove,
 };
@@ -324,6 +326,20 @@
 	usb_serial_port_softint(port);
 }
 
+static int oti6858_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_in < num_ports ||
+			serial->num_bulk_out < num_ports ||
+			serial->num_interrupt_in < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int oti6858_port_probe(struct usb_serial_port *port)
 {
 	struct oti6858_private *priv;
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index ae682e4..46fca6b 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -220,9 +220,17 @@
 static int pl2303_startup(struct usb_serial *serial)
 {
 	struct pl2303_serial_private *spriv;
+	unsigned char num_ports = serial->num_ports;
 	enum pl2303_type type = TYPE_01;
 	unsigned char *buf;
 
+	if (serial->num_bulk_in < num_ports ||
+			serial->num_bulk_out < num_ports ||
+			serial->num_interrupt_in < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
 	spriv = kzalloc(sizeof(*spriv), GFP_KERNEL);
 	if (!spriv)
 		return -ENOMEM;
diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c
index 659cb86..5709cc9 100644
--- a/drivers/usb/serial/quatech2.c
+++ b/drivers/usb/serial/quatech2.c
@@ -408,16 +408,12 @@
 {
 	struct usb_serial *serial;
 	struct qt2_port_private *port_priv;
-	unsigned long flags;
 	int i;
 
 	serial = port->serial;
 	port_priv = usb_get_serial_port_data(port);
 
-	spin_lock_irqsave(&port_priv->urb_lock, flags);
 	usb_kill_urb(port_priv->write_urb);
-	port_priv->urb_in_use = false;
-	spin_unlock_irqrestore(&port_priv->urb_lock, flags);
 
 	/* flush the port transmit buffer */
 	i = usb_control_msg(serial->dev,
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index ef0dbf0..475e6c3 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -154,6 +154,19 @@
 	return 0;
 }
 
+static int spcp8x5_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_in < num_ports ||
+			serial->num_bulk_out < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int spcp8x5_port_probe(struct usb_serial_port *port)
 {
 	const struct usb_device_id *id = usb_get_serial_data(port->serial);
@@ -477,6 +490,7 @@
 	.tiocmget		= spcp8x5_tiocmget,
 	.tiocmset		= spcp8x5_tiocmset,
 	.probe			= spcp8x5_probe,
+	.attach			= spcp8x5_attach,
 	.port_probe		= spcp8x5_port_probe,
 	.port_remove		= spcp8x5_port_remove,
 };
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index 8db9d07..64b85b8 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -579,6 +579,13 @@
 		goto free_tdev;
 	}
 
+	if (serial->num_bulk_in < serial->num_ports ||
+			serial->num_bulk_out < serial->num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		status = -ENODEV;
+		goto free_tdev;
+	}
+
 	return 0;
 
 free_tdev:
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index af3c7ee..16cc183 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2109,6 +2109,13 @@
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_BROKEN_FUA ),
 
+/* Reported-by George Cherian <george.cherian@cavium.com> */
+UNUSUAL_DEV(0x152d, 0x9561, 0x0000, 0x9999,
+		"JMicron",
+		"JMS56x",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /*
  * Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI)
  * and Mac USB Dock USB-SCSI */
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index be1ee89..36d75c3 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -27,6 +27,45 @@
 static DEFINE_MUTEX(parent_list_lock);
 static struct class_compat *mdev_bus_compat_class;
 
+static LIST_HEAD(mdev_list);
+static DEFINE_MUTEX(mdev_list_lock);
+
+struct device *mdev_parent_dev(struct mdev_device *mdev)
+{
+	return mdev->parent->dev;
+}
+EXPORT_SYMBOL(mdev_parent_dev);
+
+void *mdev_get_drvdata(struct mdev_device *mdev)
+{
+	return mdev->driver_data;
+}
+EXPORT_SYMBOL(mdev_get_drvdata);
+
+void mdev_set_drvdata(struct mdev_device *mdev, void *data)
+{
+	mdev->driver_data = data;
+}
+EXPORT_SYMBOL(mdev_set_drvdata);
+
+struct device *mdev_dev(struct mdev_device *mdev)
+{
+	return &mdev->dev;
+}
+EXPORT_SYMBOL(mdev_dev);
+
+struct mdev_device *mdev_from_dev(struct device *dev)
+{
+	return dev_is_mdev(dev) ? to_mdev_device(dev) : NULL;
+}
+EXPORT_SYMBOL(mdev_from_dev);
+
+uuid_le mdev_uuid(struct mdev_device *mdev)
+{
+	return mdev->uuid;
+}
+EXPORT_SYMBOL(mdev_uuid);
+
 static int _find_mdev_device(struct device *dev, void *data)
 {
 	struct mdev_device *mdev;
@@ -42,7 +81,7 @@
 	return 0;
 }
 
-static bool mdev_device_exist(struct parent_device *parent, uuid_le uuid)
+static bool mdev_device_exist(struct mdev_parent *parent, uuid_le uuid)
 {
 	struct device *dev;
 
@@ -56,9 +95,9 @@
 }
 
 /* Should be called holding parent_list_lock */
-static struct parent_device *__find_parent_device(struct device *dev)
+static struct mdev_parent *__find_parent_device(struct device *dev)
 {
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 
 	list_for_each_entry(parent, &parent_list, next) {
 		if (parent->dev == dev)
@@ -69,8 +108,8 @@
 
 static void mdev_release_parent(struct kref *kref)
 {
-	struct parent_device *parent = container_of(kref, struct parent_device,
-						    ref);
+	struct mdev_parent *parent = container_of(kref, struct mdev_parent,
+						  ref);
 	struct device *dev = parent->dev;
 
 	kfree(parent);
@@ -78,7 +117,7 @@
 }
 
 static
-inline struct parent_device *mdev_get_parent(struct parent_device *parent)
+inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
 {
 	if (parent)
 		kref_get(&parent->ref);
@@ -86,7 +125,7 @@
 	return parent;
 }
 
-static inline void mdev_put_parent(struct parent_device *parent)
+static inline void mdev_put_parent(struct mdev_parent *parent)
 {
 	if (parent)
 		kref_put(&parent->ref, mdev_release_parent);
@@ -95,7 +134,7 @@
 static int mdev_device_create_ops(struct kobject *kobj,
 				  struct mdev_device *mdev)
 {
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 	int ret;
 
 	ret = parent->ops->create(kobj, mdev);
@@ -122,7 +161,7 @@
  */
 static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
 {
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 	int ret;
 
 	/*
@@ -153,10 +192,10 @@
  * Add device to list of registered parent devices.
  * Returns a negative value on error, otherwise 0.
  */
-int mdev_register_device(struct device *dev, const struct parent_ops *ops)
+int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 {
 	int ret;
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 
 	/* check for mandatory ops */
 	if (!ops || !ops->create || !ops->remove || !ops->supported_type_groups)
@@ -229,7 +268,7 @@
 
 void mdev_unregister_device(struct device *dev)
 {
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 	bool force_remove = true;
 
 	mutex_lock(&parent_list_lock);
@@ -266,7 +305,7 @@
 {
 	int ret;
 	struct mdev_device *mdev;
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 	struct mdev_type *type = to_mdev_type(kobj);
 
 	parent = mdev_get_parent(type->parent);
@@ -316,6 +355,11 @@
 	dev_dbg(&mdev->dev, "MDEV: created\n");
 
 	mutex_unlock(&parent->lock);
+
+	mutex_lock(&mdev_list_lock);
+	list_add(&mdev->next, &mdev_list);
+	mutex_unlock(&mdev_list_lock);
+
 	return ret;
 
 create_failed:
@@ -329,12 +373,30 @@
 
 int mdev_device_remove(struct device *dev, bool force_remove)
 {
-	struct mdev_device *mdev;
-	struct parent_device *parent;
+	struct mdev_device *mdev, *tmp;
+	struct mdev_parent *parent;
 	struct mdev_type *type;
 	int ret;
+	bool found = false;
 
 	mdev = to_mdev_device(dev);
+
+	mutex_lock(&mdev_list_lock);
+	list_for_each_entry(tmp, &mdev_list, next) {
+		if (tmp == mdev) {
+			found = true;
+			break;
+		}
+	}
+
+	if (found)
+		list_del(&mdev->next);
+
+	mutex_unlock(&mdev_list_lock);
+
+	if (!found)
+		return -ENODEV;
+
 	type = to_mdev_type(mdev->type_kobj);
 	parent = mdev->parent;
 	mutex_lock(&parent->lock);
@@ -342,6 +404,11 @@
 	ret = mdev_device_remove_ops(mdev, force_remove);
 	if (ret) {
 		mutex_unlock(&parent->lock);
+
+		mutex_lock(&mdev_list_lock);
+		list_add(&mdev->next, &mdev_list);
+		mutex_unlock(&mdev_list_lock);
+
 		return ret;
 	}
 
@@ -349,7 +416,8 @@
 	device_unregister(dev);
 	mutex_unlock(&parent->lock);
 	mdev_put_parent(parent);
-	return ret;
+
+	return 0;
 }
 
 static int __init mdev_init(void)
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index d35097c..a9cefd7 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -16,10 +16,33 @@
 int  mdev_bus_register(void);
 void mdev_bus_unregister(void);
 
+struct mdev_parent {
+	struct device *dev;
+	const struct mdev_parent_ops *ops;
+	struct kref ref;
+	struct mutex lock;
+	struct list_head next;
+	struct kset *mdev_types_kset;
+	struct list_head type_list;
+};
+
+struct mdev_device {
+	struct device dev;
+	struct mdev_parent *parent;
+	uuid_le uuid;
+	void *driver_data;
+	struct kref ref;
+	struct list_head next;
+	struct kobject *type_kobj;
+};
+
+#define to_mdev_device(dev)	container_of(dev, struct mdev_device, dev)
+#define dev_is_mdev(d)		((d)->bus == &mdev_bus_type)
+
 struct mdev_type {
 	struct kobject kobj;
 	struct kobject *devices_kobj;
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 	struct list_head next;
 	struct attribute_group *group;
 };
@@ -29,8 +52,8 @@
 #define to_mdev_type(_kobj)		\
 	container_of(_kobj, struct mdev_type, kobj)
 
-int  parent_create_sysfs_files(struct parent_device *parent);
-void parent_remove_sysfs_files(struct parent_device *parent);
+int  parent_create_sysfs_files(struct mdev_parent *parent);
+void parent_remove_sysfs_files(struct mdev_parent *parent);
 
 int  mdev_create_sysfs_files(struct device *dev, struct mdev_type *type);
 void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type);
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 1a53deb..802df21 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -92,7 +92,7 @@
 	.release = mdev_type_release,
 };
 
-struct mdev_type *add_mdev_supported_type(struct parent_device *parent,
+struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent,
 					  struct attribute_group *group)
 {
 	struct mdev_type *type;
@@ -158,7 +158,7 @@
 	kobject_put(&type->kobj);
 }
 
-static int add_mdev_supported_type_groups(struct parent_device *parent)
+static int add_mdev_supported_type_groups(struct mdev_parent *parent)
 {
 	int i;
 
@@ -183,7 +183,7 @@
 }
 
 /* mdev sysfs functions */
-void parent_remove_sysfs_files(struct parent_device *parent)
+void parent_remove_sysfs_files(struct mdev_parent *parent)
 {
 	struct mdev_type *type, *tmp;
 
@@ -196,7 +196,7 @@
 	kset_unregister(parent->mdev_types_kset);
 }
 
-int parent_create_sysfs_files(struct parent_device *parent)
+int parent_create_sysfs_files(struct mdev_parent *parent)
 {
 	int ret;
 
diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c
index ffc3675..fa848a7 100644
--- a/drivers/vfio/mdev/vfio_mdev.c
+++ b/drivers/vfio/mdev/vfio_mdev.c
@@ -27,7 +27,7 @@
 static int vfio_mdev_open(void *device_data)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 	int ret;
 
 	if (unlikely(!parent->ops->open))
@@ -46,7 +46,7 @@
 static void vfio_mdev_release(void *device_data)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (likely(parent->ops->release))
 		parent->ops->release(mdev);
@@ -58,7 +58,7 @@
 				     unsigned int cmd, unsigned long arg)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->ioctl))
 		return -EINVAL;
@@ -70,7 +70,7 @@
 			      size_t count, loff_t *ppos)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->read))
 		return -EINVAL;
@@ -82,7 +82,7 @@
 			       size_t count, loff_t *ppos)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->write))
 		return -EINVAL;
@@ -93,7 +93,7 @@
 static int vfio_mdev_mmap(void *device_data, struct vm_area_struct *vma)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->mmap))
 		return -EINVAL;
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index dcd7c2a..324c52e 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1142,6 +1142,10 @@
 			return ret;
 
 		vdev->barmap[index] = pci_iomap(pdev, index, 0);
+		if (!vdev->barmap[index]) {
+			pci_release_selected_regions(pdev, 1 << index);
+			return -ENOMEM;
+		}
 	}
 
 	vma->vm_private_data = vdev;
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 5ffd1d9..357243d 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -193,7 +193,10 @@
 	if (!vdev->has_vga)
 		return -EINVAL;
 
-	switch (pos) {
+	if (pos > 0xbfffful)
+		return -EINVAL;
+
+	switch ((u32)pos) {
 	case 0xa0000 ... 0xbffff:
 		count = min(count, (size_t)(0xc0000 - pos));
 		iomem = ioremap_nocache(0xa0000, 0xbffff - 0xa0000 + 1);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index f3726ba..9266271 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -268,28 +268,38 @@
 {
 	struct vwork *vwork;
 	struct mm_struct *mm;
+	bool is_current;
 
 	if (!npage)
 		return;
 
-	mm = get_task_mm(task);
+	is_current = (task->mm == current->mm);
+
+	mm = is_current ? task->mm : get_task_mm(task);
 	if (!mm)
-		return; /* process exited or nothing to do */
+		return; /* process exited */
 
 	if (down_write_trylock(&mm->mmap_sem)) {
 		mm->locked_vm += npage;
 		up_write(&mm->mmap_sem);
-		mmput(mm);
+		if (!is_current)
+			mmput(mm);
 		return;
 	}
 
+	if (is_current) {
+		mm = get_task_mm(task);
+		if (!mm)
+			return;
+	}
+
 	/*
 	 * Couldn't get mmap_sem lock, so must setup to update
 	 * mm->locked_vm later. If locked_vm were atomic, we
 	 * wouldn't need this silliness
 	 */
 	vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
-	if (!vwork) {
+	if (WARN_ON(!vwork)) {
 		mmput(mm);
 		return;
 	}
@@ -393,77 +403,71 @@
 static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 				  long npage, unsigned long *pfn_base)
 {
-	unsigned long limit;
-	bool lock_cap = ns_capable(task_active_pid_ns(dma->task)->user_ns,
-				   CAP_IPC_LOCK);
-	struct mm_struct *mm;
-	long ret, i = 0, lock_acct = 0;
+	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	bool lock_cap = capable(CAP_IPC_LOCK);
+	long ret, pinned = 0, lock_acct = 0;
 	bool rsvd;
 	dma_addr_t iova = vaddr - dma->vaddr + dma->iova;
 
-	mm = get_task_mm(dma->task);
-	if (!mm)
+	/* This code path is only user initiated */
+	if (!current->mm)
 		return -ENODEV;
 
-	ret = vaddr_get_pfn(mm, vaddr, dma->prot, pfn_base);
+	ret = vaddr_get_pfn(current->mm, vaddr, dma->prot, pfn_base);
 	if (ret)
-		goto pin_pg_remote_exit;
+		return ret;
 
+	pinned++;
 	rsvd = is_invalid_reserved_pfn(*pfn_base);
-	limit = task_rlimit(dma->task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
 	/*
 	 * Reserved pages aren't counted against the user, externally pinned
 	 * pages are already counted against the user.
 	 */
 	if (!rsvd && !vfio_find_vpfn(dma, iova)) {
-		if (!lock_cap && mm->locked_vm + 1 > limit) {
+		if (!lock_cap && current->mm->locked_vm + 1 > limit) {
 			put_pfn(*pfn_base, dma->prot);
 			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
 					limit << PAGE_SHIFT);
-			ret = -ENOMEM;
-			goto pin_pg_remote_exit;
+			return -ENOMEM;
 		}
 		lock_acct++;
 	}
 
-	i++;
-	if (likely(!disable_hugepages)) {
-		/* Lock all the consecutive pages from pfn_base */
-		for (vaddr += PAGE_SIZE, iova += PAGE_SIZE; i < npage;
-		     i++, vaddr += PAGE_SIZE, iova += PAGE_SIZE) {
-			unsigned long pfn = 0;
+	if (unlikely(disable_hugepages))
+		goto out;
 
-			ret = vaddr_get_pfn(mm, vaddr, dma->prot, &pfn);
-			if (ret)
-				break;
+	/* Lock all the consecutive pages from pfn_base */
+	for (vaddr += PAGE_SIZE, iova += PAGE_SIZE; pinned < npage;
+	     pinned++, vaddr += PAGE_SIZE, iova += PAGE_SIZE) {
+		unsigned long pfn = 0;
 
-			if (pfn != *pfn_base + i ||
-			    rsvd != is_invalid_reserved_pfn(pfn)) {
+		ret = vaddr_get_pfn(current->mm, vaddr, dma->prot, &pfn);
+		if (ret)
+			break;
+
+		if (pfn != *pfn_base + pinned ||
+		    rsvd != is_invalid_reserved_pfn(pfn)) {
+			put_pfn(pfn, dma->prot);
+			break;
+		}
+
+		if (!rsvd && !vfio_find_vpfn(dma, iova)) {
+			if (!lock_cap &&
+			    current->mm->locked_vm + lock_acct + 1 > limit) {
 				put_pfn(pfn, dma->prot);
+				pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
+					__func__, limit << PAGE_SHIFT);
 				break;
 			}
-
-			if (!rsvd && !vfio_find_vpfn(dma, iova)) {
-				if (!lock_cap &&
-				    mm->locked_vm + lock_acct + 1 > limit) {
-					put_pfn(pfn, dma->prot);
-					pr_warn("%s: RLIMIT_MEMLOCK (%ld) "
-						"exceeded\n", __func__,
-						limit << PAGE_SHIFT);
-					break;
-				}
-				lock_acct++;
-			}
+			lock_acct++;
 		}
 	}
 
-	vfio_lock_acct(dma->task, lock_acct);
-	ret = i;
+out:
+	vfio_lock_acct(current, lock_acct);
 
-pin_pg_remote_exit:
-	mmput(mm);
-	return ret;
+	return pinned;
 }
 
 static long vfio_unpin_pages_remote(struct vfio_dma *dma, dma_addr_t iova,
@@ -473,10 +477,10 @@
 	long unlocked = 0, locked = 0;
 	long i;
 
-	for (i = 0; i < npage; i++) {
+	for (i = 0; i < npage; i++, iova += PAGE_SIZE) {
 		if (put_pfn(pfn++, dma->prot)) {
 			unlocked++;
-			if (vfio_find_vpfn(dma, iova + (i << PAGE_SHIFT)))
+			if (vfio_find_vpfn(dma, iova))
 				locked++;
 		}
 	}
diff --git a/drivers/video/fbdev/cobalt_lcdfb.c b/drivers/video/fbdev/cobalt_lcdfb.c
index 2d3b691..038ac69 100644
--- a/drivers/video/fbdev/cobalt_lcdfb.c
+++ b/drivers/video/fbdev/cobalt_lcdfb.c
@@ -308,6 +308,11 @@
 	info->screen_size = resource_size(res);
 	info->screen_base = devm_ioremap(&dev->dev, res->start,
 					 info->screen_size);
+	if (!info->screen_base) {
+		framebuffer_release(info);
+		return -ENOMEM;
+	}
+
 	info->fbops = &cobalt_lcd_fbops;
 	info->fix = cobalt_lcdfb_fix;
 	info->fix.smem_start = res->start;
diff --git a/drivers/xen/arm-device.c b/drivers/xen/arm-device.c
index 778acf8..85dd20e 100644
--- a/drivers/xen/arm-device.c
+++ b/drivers/xen/arm-device.c
@@ -58,9 +58,13 @@
 	xen_pfn_t *gpfns;
 	xen_ulong_t *idxs;
 	int *errs;
-	struct xen_add_to_physmap_range xatp;
 
 	for (i = 0; i < count; i++) {
+		struct xen_add_to_physmap_range xatp = {
+			.domid = DOMID_SELF,
+			.space = XENMAPSPACE_dev_mmio
+		};
+
 		r = &resources[i];
 		nr = DIV_ROUND_UP(resource_size(r), XEN_PAGE_SIZE);
 		if ((resource_type(r) != IORESOURCE_MEM) || (nr == 0))
@@ -87,9 +91,7 @@
 			idxs[j] = XEN_PFN_DOWN(r->start) + j;
 		}
 
-		xatp.domid = DOMID_SELF;
 		xatp.size = nr;
-		xatp.space = XENMAPSPACE_dev_mmio;
 
 		set_xen_guest_handle(xatp.gpfns, gpfns);
 		set_xen_guest_handle(xatp.idxs, idxs);
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index c03f9c8..3c41470 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -369,8 +369,7 @@
 		}
 
 		ret = init_control_block(cpu, control_block);
-		if (ret < 0)
-			BUG();
+		BUG_ON(ret < 0);
 	}
 
 	/*
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index e8c7f09..6890897 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -125,7 +125,7 @@
 	while (*new) {
 		struct user_evtchn *this;
 
-		this = container_of(*new, struct user_evtchn, node);
+		this = rb_entry(*new, struct user_evtchn, node);
 
 		parent = *new;
 		if (this->port < evtchn->port)
@@ -157,7 +157,7 @@
 	while (node) {
 		struct user_evtchn *evtchn;
 
-		evtchn = container_of(node, struct user_evtchn, node);
+		evtchn = rb_entry(node, struct user_evtchn, node);
 
 		if (evtchn->port < port)
 			node = node->rb_left;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 478fb91..f905d6e 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -275,6 +275,10 @@
 		rc = 0;
 	} else
 		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
+
+	if (!rc)
+		swiotlb_set_max_segment(PAGE_SIZE);
+
 	return rc;
 error:
 	if (repeat--) {
@@ -392,7 +396,7 @@
 	if (dma_capable(dev, dev_addr, size) &&
 	    !range_straddles_page_boundary(phys, size) &&
 		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
-		!swiotlb_force) {
+		(swiotlb_force != SWIOTLB_FORCE)) {
 		/* we are not interested in the dma_addr returned by
 		 * xen_dma_map_page, only in the potential cache flushes executed
 		 * by the function. */
@@ -552,7 +556,7 @@
 		phys_addr_t paddr = sg_phys(sg);
 		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
 
-		if (swiotlb_force ||
+		if (swiotlb_force == SWIOTLB_FORCE ||
 		    xen_arch_need_swiotlb(hwdev, paddr, dev_addr) ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
diff --git a/drivers/xen/xenbus/xenbus_comms.h b/drivers/xen/xenbus/xenbus_comms.h
index e74f9c1..867a2e4 100644
--- a/drivers/xen/xenbus/xenbus_comms.h
+++ b/drivers/xen/xenbus/xenbus_comms.h
@@ -42,7 +42,6 @@
 int xb_read(void *data, unsigned len);
 int xb_data_to_read(void);
 int xb_wait_for_data_to_read(void);
-int xs_input_avail(void);
 extern struct xenstore_domain_interface *xen_store_interface;
 extern int xen_store_evtchn;
 extern enum xenstore_init xen_store_domain_type;
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 6c0ead4..79130b3 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -302,6 +302,29 @@
 	mutex_unlock(&adap->dev_data->reply_mutex);
 }
 
+static int xenbus_command_reply(struct xenbus_file_priv *u,
+				unsigned int msg_type, const char *reply)
+{
+	struct {
+		struct xsd_sockmsg hdr;
+		const char body[16];
+	} msg;
+	int rc;
+
+	msg.hdr = u->u.msg;
+	msg.hdr.type = msg_type;
+	msg.hdr.len = strlen(reply) + 1;
+	if (msg.hdr.len > sizeof(msg.body))
+		return -E2BIG;
+
+	mutex_lock(&u->reply_mutex);
+	rc = queue_reply(&u->read_buffers, &msg, sizeof(msg.hdr) + msg.hdr.len);
+	wake_up(&u->read_waitq);
+	mutex_unlock(&u->reply_mutex);
+
+	return rc;
+}
+
 static int xenbus_write_transaction(unsigned msg_type,
 				    struct xenbus_file_priv *u)
 {
@@ -316,12 +339,12 @@
 			rc = -ENOMEM;
 			goto out;
 		}
-	} else if (msg_type == XS_TRANSACTION_END) {
+	} else if (u->u.msg.tx_id != 0) {
 		list_for_each_entry(trans, &u->transactions, list)
 			if (trans->handle.id == u->u.msg.tx_id)
 				break;
 		if (&trans->list == &u->transactions)
-			return -ESRCH;
+			return xenbus_command_reply(u, XS_ERROR, "ENOENT");
 	}
 
 	reply = xenbus_dev_request_and_reply(&u->u.msg);
@@ -372,12 +395,12 @@
 	path = u->u.buffer + sizeof(u->u.msg);
 	token = memchr(path, 0, u->u.msg.len);
 	if (token == NULL) {
-		rc = -EILSEQ;
+		rc = xenbus_command_reply(u, XS_ERROR, "EINVAL");
 		goto out;
 	}
 	token++;
 	if (memchr(token, 0, u->u.msg.len - (token - path)) == NULL) {
-		rc = -EILSEQ;
+		rc = xenbus_command_reply(u, XS_ERROR, "EINVAL");
 		goto out;
 	}
 
@@ -411,23 +434,7 @@
 	}
 
 	/* Success.  Synthesize a reply to say all is OK. */
-	{
-		struct {
-			struct xsd_sockmsg hdr;
-			char body[3];
-		} __packed reply = {
-			{
-				.type = msg_type,
-				.len = sizeof(reply.body)
-			},
-			"OK"
-		};
-
-		mutex_lock(&u->reply_mutex);
-		rc = queue_reply(&u->read_buffers, &reply, sizeof(reply));
-		wake_up(&u->read_waitq);
-		mutex_unlock(&u->reply_mutex);
-	}
+	rc = xenbus_command_reply(u, msg_type, "OK");
 
 out:
 	return rc;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6254cee..5db5d13 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -328,6 +328,7 @@
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = bdev_file_inode(file);
 	struct block_device *bdev = I_BDEV(inode);
+	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
 	bool is_read = (iov_iter_rw(iter) == READ);
@@ -353,6 +354,7 @@
 	dio->multi_bio = false;
 	dio->should_dirty = is_read && (iter->type == ITER_IOVEC);
 
+	blk_start_plug(&plug);
 	for (;;) {
 		bio->bi_bdev = bdev;
 		bio->bi_iter.bi_sector = pos >> 9;
@@ -394,6 +396,7 @@
 		submit_bio(bio);
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 	}
+	blk_finish_plug(&plug);
 
 	if (!dio->is_sync)
 		return -EIOCBQUEUED;
diff --git a/fs/buffer.c b/fs/buffer.c
index d21771f..0e87401 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1660,7 +1660,7 @@
 			head = page_buffers(page);
 			bh = head;
 			do {
-				if (!buffer_mapped(bh))
+				if (!buffer_mapped(bh) || (bh->b_blocknr < block))
 					goto next;
 				if (bh->b_blocknr >= block + len)
 					break;
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 6eeea1d..95cd4c3 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -248,7 +248,8 @@
 		goto out;
 
 	if (fscrypt_dummy_context_enabled(inode)) {
-		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
+		memset(raw_key, 0x42, keysize/2);
+		memset(raw_key+keysize/2, 0x24, keysize - (keysize/2));
 		goto got_key;
 	}
 
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 6ed7c2e..d6cd7ea 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -179,6 +179,11 @@
 		BUG_ON(1);
 	}
 
+	/* No restrictions on file types which are never encrypted */
+	if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
+	    !S_ISLNK(child->i_mode))
+		return 1;
+
 	/* no restrictions if the parent directory is not encrypted */
 	if (!parent->i_sb->s_cop->is_encrypted(parent))
 		return 1;
diff --git a/fs/dax.c b/fs/dax.c
index a8732fb..5c74f60 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -451,16 +451,37 @@
 		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
 }
 
+static int __dax_invalidate_mapping_entry(struct address_space *mapping,
+					  pgoff_t index, bool trunc)
+{
+	int ret = 0;
+	void *entry;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = get_unlocked_mapping_entry(mapping, index, NULL);
+	if (!entry || !radix_tree_exceptional_entry(entry))
+		goto out;
+	if (!trunc &&
+	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
+		goto out;
+	radix_tree_delete(page_tree, index);
+	mapping->nrexceptional--;
+	ret = 1;
+out:
+	put_unlocked_mapping_entry(mapping, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
 /*
  * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
  * entry to get unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
-	void *entry;
+	int ret = __dax_invalidate_mapping_entry(mapping, index, true);
 
-	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, NULL);
 	/*
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
@@ -468,16 +489,46 @@
 	 * caller has seen exceptional entry for this index, we better find it
 	 * at that index as well...
 	 */
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
-		spin_unlock_irq(&mapping->tree_lock);
-		return 0;
-	}
-	radix_tree_delete(&mapping->page_tree, index);
-	mapping->nrexceptional--;
-	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	WARN_ON_ONCE(!ret);
+	return ret;
+}
 
-	return 1;
+/*
+ * Invalidate exceptional DAX entry if easily possible. This handles DAX
+ * entries for invalidate_inode_pages() so we evict the entry only if we can
+ * do so without blocking.
+ */
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+	int ret = 0;
+	void *entry, **slot;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
+	if (!entry || !radix_tree_exceptional_entry(entry) ||
+	    slot_locked(mapping, slot))
+		goto out;
+	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto out;
+	radix_tree_delete(page_tree, index);
+	mapping->nrexceptional--;
+	ret = 1;
+out:
+	spin_unlock_irq(&mapping->tree_lock);
+	if (ret)
+		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	return ret;
+}
+
+/*
+ * Invalidate exceptional DAX entry if it is clean.
+ */
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index)
+{
+	return __dax_invalidate_mapping_entry(mapping, index, false);
 }
 
 /*
@@ -488,15 +539,16 @@
  * otherwise it will simply fall out of the page cache under memory
  * pressure without ever having been dirtied.
  */
-static int dax_load_hole(struct address_space *mapping, void *entry,
+static int dax_load_hole(struct address_space *mapping, void **entry,
 			 struct vm_fault *vmf)
 {
 	struct page *page;
+	int ret;
 
 	/* Hole page already exists? Return it...  */
-	if (!radix_tree_exceptional_entry(entry)) {
-		vmf->page = entry;
-		return VM_FAULT_LOCKED;
+	if (!radix_tree_exceptional_entry(*entry)) {
+		page = *entry;
+		goto out;
 	}
 
 	/* This will replace locked radix tree entry with a hole page */
@@ -504,8 +556,17 @@
 				   vmf->gfp_mask | __GFP_ZERO);
 	if (!page)
 		return VM_FAULT_OOM;
+ out:
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = finish_fault(vmf);
+	vmf->page = NULL;
+	*entry = page;
+	if (!ret) {
+		/* Grab reference for PTE that is now referencing the page */
+		get_page(page);
+		return VM_FAULT_NOPAGE;
+	}
+	return ret;
 }
 
 static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
@@ -934,6 +995,17 @@
 	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
 		return -EIO;
 
+	/*
+	 * Write can allocate block for an area which has a hole page mapped
+	 * into page tables. We have to tear down these mappings so that data
+	 * written by write(2) is visible in mmap.
+	 */
+	if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+		invalidate_inode_pages2_range(inode->i_mapping,
+					      pos >> PAGE_SHIFT,
+					      (end - 1) >> PAGE_SHIFT);
+	}
+
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		struct blk_dax_ctl dax = { 0 };
@@ -992,23 +1064,6 @@
 	if (iov_iter_rw(iter) == WRITE)
 		flags |= IOMAP_WRITE;
 
-	/*
-	 * Yes, even DAX files can have page cache attached to them:  A zeroed
-	 * page is inserted into the pagecache when we have to serve a write
-	 * fault on a hole.  It should never be dirtied and can simply be
-	 * dropped from the pagecache once we get real data for the page.
-	 *
-	 * XXX: This is racy against mmap, and there's nothing we can do about
-	 * it. We'll eventually need to shift this down even further so that
-	 * we can check if we allocated blocks over a hole first.
-	 */
-	if (mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT,
-				(pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-	}
-
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
 				iter, dax_iomap_actor);
@@ -1023,6 +1078,15 @@
 }
 EXPORT_SYMBOL_GPL(dax_iomap_rw);
 
+static int dax_fault_return(int error)
+{
+	if (error == 0)
+		return VM_FAULT_NOPAGE;
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+}
+
 /**
  * dax_iomap_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
@@ -1055,12 +1119,6 @@
 	if (pos >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
 
-	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
-	if (IS_ERR(entry)) {
-		error = PTR_ERR(entry);
-		goto out;
-	}
-
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
 		flags |= IOMAP_WRITE;
 
@@ -1071,9 +1129,15 @@
 	 */
 	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		return dax_fault_return(error);
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		error = -EIO;		/* fs corruption? */
+		vmf_ret = dax_fault_return(-EIO);	/* fs corruption? */
+		goto finish_iomap;
+	}
+
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+	if (IS_ERR(entry)) {
+		vmf_ret = dax_fault_return(PTR_ERR(entry));
 		goto finish_iomap;
 	}
 
@@ -1096,13 +1160,13 @@
 		}
 
 		if (error)
-			goto finish_iomap;
+			goto error_unlock_entry;
 
 		__SetPageUptodate(vmf->cow_page);
 		vmf_ret = finish_fault(vmf);
 		if (!vmf_ret)
 			vmf_ret = VM_FAULT_DONE_COW;
-		goto finish_iomap;
+		goto unlock_entry;
 	}
 
 	switch (iomap.type) {
@@ -1114,12 +1178,15 @@
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, sector,
 				PAGE_SIZE, &entry, vma, vmf);
+		/* -EBUSY is fine, somebody else faulted on the same PTE */
+		if (error == -EBUSY)
+			error = 0;
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
-			vmf_ret = dax_load_hole(mapping, entry, vmf);
-			break;
+			vmf_ret = dax_load_hole(mapping, &entry, vmf);
+			goto unlock_entry;
 		}
 		/*FALLTHRU*/
 	default:
@@ -1128,31 +1195,25 @@
 		break;
 	}
 
+ error_unlock_entry:
+	vmf_ret = dax_fault_return(error) | major;
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (error || (vmf_ret & VM_FAULT_ERROR)) {
-			/* keep previous error */
-			ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PAGE_SIZE,
-					PAGE_SIZE, flags, &iomap);
-		}
+		int copied = PAGE_SIZE;
+
+		if (vmf_ret & VM_FAULT_ERROR)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PTE we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
- unlock_entry:
-	if (vmf_ret != VM_FAULT_LOCKED || error)
-		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
- out:
-	if (error == -ENOMEM)
-		return VM_FAULT_OOM | major;
-	/* -EBUSY is fine, somebody else faulted on the same PTE */
-	if (error < 0 && error != -EBUSY)
-		return VM_FAULT_SIGBUS | major;
-	if (vmf_ret) {
-		WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
-		return vmf_ret;
-	}
-	return VM_FAULT_NOPAGE | major;
+	return vmf_ret;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_fault);
 
@@ -1277,16 +1338,6 @@
 		goto fallback;
 
 	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto fallback;
-
-	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
 	 * to look up our filesystem block.
@@ -1294,10 +1345,21 @@
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		goto fallback;
+
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto finish_iomap;
+
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
@@ -1310,7 +1372,7 @@
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto finish_iomap;
+			goto unlock_entry;
 		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
 				&entry);
 		break;
@@ -1319,20 +1381,23 @@
 		break;
 	}
 
- finish_iomap:
-	if (ops->iomap_end) {
-		if (result == VM_FAULT_FALLBACK) {
-			ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE,
-					iomap_flags, &iomap);
-			if (error)
-				result = VM_FAULT_FALLBACK;
-		}
-	}
  unlock_entry:
 	put_locked_mapping_entry(mapping, pgoff, entry);
+ finish_iomap:
+	if (ops->iomap_end) {
+		int copied = PMD_SIZE;
+
+		if (result == VM_FAULT_FALLBACK)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PMD we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
+				&iomap);
+	}
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, pmd, address);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0093ea2..f073bfc 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -751,9 +751,8 @@
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
 		}
-	} else {
-		*new = true;
 	}
+	*new = true;
 
 	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
 	mutex_unlock(&ei->truncate_mutex);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b5f1844..d663d3d 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -258,7 +258,6 @@
 static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -266,24 +265,12 @@
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-						EXT4_DATA_TRANS_BLOCKS(sb));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else
-		result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	}
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
@@ -292,7 +279,6 @@
 						pmd_t *pmd, unsigned int flags)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = flags & FAULT_FLAG_WRITE;
@@ -300,27 +286,13 @@
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-				ext4_chunk_trans_blocks(inode,
-							PMD_SIZE / PAGE_SIZE));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else {
-		result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-					     &ext4_iomap_ops);
 	}
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
+				     &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d3fea0b..6043306 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -510,18 +510,6 @@
 	}
 }
 
-void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old)
-{
-	assert_spin_locked(&old->lock);
-	new->inode = old->inode;
-	new->mnt = old->mnt;
-	if (old->group)
-		fsnotify_get_group(old->group);
-	new->group = old->group;
-	new->mask = old->mask;
-	new->free_mark = old->free_mark;
-}
-
 /*
  * Nothing fancy, just initialize lists and locks and counters.
  */
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index e5ebc37..d346d42 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -256,6 +256,9 @@
 			goto out;
 	}
 
+	ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
+	       xfs_perag_resv(pag, XFS_AG_RESV_AGFL)->ar_reserved <=
+	       pag->pagf_freeblks + pag->pagf_flcount);
 out:
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 6fb2215..50add52 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -409,13 +409,14 @@
  */
 xfs_extlen_t
 xfs_refcountbt_max_size(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agblocks)
 {
 	/* Bail out if we're uninitialized, which can happen in mkfs. */
 	if (mp->m_refc_mxr[0] == 0)
 		return 0;
 
-	return xfs_refcountbt_calc_size(mp, mp->m_sb.sb_agblocks);
+	return xfs_refcountbt_calc_size(mp, agblocks);
 }
 
 /*
@@ -430,22 +431,24 @@
 {
 	struct xfs_buf		*agbp;
 	struct xfs_agf		*agf;
+	xfs_agblock_t		agblocks;
 	xfs_extlen_t		tree_len;
 	int			error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
-	*ask += xfs_refcountbt_max_size(mp);
 
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
+	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_refcount_blocks);
 	xfs_buf_relse(agbp);
 
+	*ask += xfs_refcountbt_max_size(mp, agblocks);
 	*used += tree_len;
 
 	return error;
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index 3be7768..9db008b 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -66,7 +66,8 @@
 
 extern xfs_extlen_t xfs_refcountbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
-extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp);
+extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp,
+		xfs_agblock_t agblocks);
 
 extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
 		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index de25771..74e5a54 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -550,13 +550,14 @@
  */
 xfs_extlen_t
 xfs_rmapbt_max_size(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agblocks)
 {
 	/* Bail out if we're uninitialized, which can happen in mkfs. */
 	if (mp->m_rmap_mxr[0] == 0)
 		return 0;
 
-	return xfs_rmapbt_calc_size(mp, mp->m_sb.sb_agblocks);
+	return xfs_rmapbt_calc_size(mp, agblocks);
 }
 
 /*
@@ -571,25 +572,24 @@
 {
 	struct xfs_buf		*agbp;
 	struct xfs_agf		*agf;
-	xfs_extlen_t		pool_len;
+	xfs_agblock_t		agblocks;
 	xfs_extlen_t		tree_len;
 	int			error;
 
 	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
 		return 0;
 
-	/* Reserve 1% of the AG or enough for 1 block per record. */
-	pool_len = max(mp->m_sb.sb_agblocks / 100, xfs_rmapbt_max_size(mp));
-	*ask += pool_len;
-
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
+	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_rmap_blocks);
 	xfs_buf_relse(agbp);
 
+	/* Reserve 1% of the AG or enough for 1 block per record. */
+	*ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks));
 	*used += tree_len;
 
 	return error;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 2a9ac47..19c08e9 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -60,7 +60,8 @@
 
 extern xfs_extlen_t xfs_rmapbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
-extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp);
+extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
+		xfs_agblock_t agblocks);
 
 extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp,
 		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 93d12fa..242e809 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -631,6 +631,20 @@
 	xfs_set_low_space_thresholds(mp);
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 
+	/*
+	 * If we expanded the last AG, free the per-AG reservation
+	 * so we can reinitialize it with the new size.
+	 */
+	if (new) {
+		struct xfs_perag	*pag;
+
+		pag = xfs_perag_get(mp, agno);
+		error = xfs_ag_resv_free(pag);
+		xfs_perag_put(pag);
+		if (error)
+			goto out;
+	}
+
 	/* Reserve AG metadata blocks. */
 	error = xfs_fs_reserve_ag_blocks(mp);
 	if (error && error != -ENOSPC)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index ff4d631..70ca4f6 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1597,7 +1597,8 @@
 	 * If the mapping is dirty or under writeback we cannot touch the
 	 * CoW fork.  Leave it alone if we're in the midst of a directio.
 	 */
-	if (mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
+	if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) ||
+	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
 	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
 	    atomic_read(&VFS_I(ip)->i_dio_count))
 		return 0;
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index fe86a66..6e4c744 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -526,13 +526,14 @@
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
-		goto abort_error;
+		goto abort_defer;
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
+abort_defer:
 	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	return error;
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 276d302..de6195e 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -396,7 +396,7 @@
 	int		retries;
 	struct xfs_error_cfg *cfg = to_error_cfg(kobject);
 
-	if (cfg->retry_timeout == XFS_ERR_RETRY_FOREVER)
+	if (cfg->max_retries == XFS_ERR_RETRY_FOREVER)
 		retries = -1;
 	else
 		retries = cfg->max_retries;
@@ -422,7 +422,7 @@
 		return -EINVAL;
 
 	if (val == -1)
-		cfg->retry_timeout = XFS_ERR_RETRY_FOREVER;
+		cfg->max_retries = XFS_ERR_RETRY_FOREVER;
 	else
 		cfg->max_retries = val;
 	return count;
diff --git a/include/asm-generic/asm-prototypes.h b/include/asm-generic/asm-prototypes.h
index df13637..939869c 100644
--- a/include/asm-generic/asm-prototypes.h
+++ b/include/asm-generic/asm-prototypes.h
@@ -1,7 +1,13 @@
 #include <linux/bitops.h>
+#undef __memset
 extern void *__memset(void *, int, __kernel_size_t);
+#undef __memcpy
 extern void *__memcpy(void *, const void *, __kernel_size_t);
+#undef __memmove
 extern void *__memmove(void *, const void *, __kernel_size_t);
+#undef memset
 extern void *memset(void *, int, __kernel_size_t);
+#undef memcpy
 extern void *memcpy(void *, const void *, __kernel_size_t);
+#undef memmove
 extern void *memmove(void *, const void *, __kernel_size_t);
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index 982c299..d026f50 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -73,6 +73,5 @@
 
 extern void drm_kms_helper_poll_disable(struct drm_device *dev);
 extern void drm_kms_helper_poll_enable(struct drm_device *dev);
-extern void drm_kms_helper_poll_enable_locked(struct drm_device *dev);
 
 #endif
diff --git a/include/dt-bindings/mfd/tps65217.h b/include/dt-bindings/mfd/tps65217.h
deleted file mode 100644
index cafb9e6..0000000
--- a/include/dt-bindings/mfd/tps65217.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * This header provides macros for TI TPS65217 DT bindings.
- *
- * Copyright (C) 2016 Texas Instruments
- *
- * 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 __DT_BINDINGS_TPS65217_H__
-#define __DT_BINDINGS_TPS65217_H__
-
-#define TPS65217_IRQ_USB	0
-#define TPS65217_IRQ_AC		1
-#define TPS65217_IRQ_PB		2
-
-#endif
diff --git a/include/linux/dax.h b/include/linux/dax.h
index f97bcfe..24ad711 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -41,6 +41,9 @@
 int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		pgoff_t index, void *entry, bool wake_all);
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7023142..a0934e6 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -610,7 +610,6 @@
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 void bpf_warn_invalid_xdp_action(u32 act);
-void bpf_warn_invalid_xdp_buffer(void);
 
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 0cf34d6..4872465 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -323,8 +323,6 @@
 extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group, struct inode *inode);
 /* find (and take a reference) to a mark associated with group and vfsmount */
 extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt);
-/* copy the values from old into new */
-extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old);
 /* set the ignored_mask of a mark */
 extern void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask);
 /* set the mask of a mark (might pin the object into memory */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index e0341af..76f3975 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -146,15 +146,6 @@
 	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
 };
 
-#define BLK_SCSI_MAX_CMDS	(256)
-#define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
-
-struct blk_scsi_cmd_filter {
-	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
-	unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
-	struct kobject kobj;
-};
-
 struct disk_part_tbl {
 	struct rcu_head rcu_head;
 	int len;
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 228bd44..497f2b3 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -116,6 +116,16 @@
 };
 
 /**
+ * struct st_sensor_das - ST sensor device data alignment selection
+ * @addr: address of the register.
+ * @mask: mask to write the das flag for left alignment.
+ */
+struct st_sensor_das {
+	u8 addr;
+	u8 mask;
+};
+
+/**
  * struct st_sensor_data_ready_irq - ST sensor device data-ready interrupt
  * @addr: address of the register.
  * @mask_int1: mask to enable/disable IRQ on INT1 pin.
@@ -185,6 +195,7 @@
  * @enable_axis: Enable one or more axis of the sensor.
  * @fs: Full scale register and full scale list available.
  * @bdu: Block data update register.
+ * @das: Data Alignment Selection register.
  * @drdy_irq: Data ready register of the sensor.
  * @multi_read_bit: Use or not particular bit for [I2C/SPI] multi-read.
  * @bootime: samples to discard when sensor passing from power-down to power-up.
@@ -200,6 +211,7 @@
 	struct st_sensor_axis enable_axis;
 	struct st_sensor_fullscale fs;
 	struct st_sensor_bdu bdu;
+	struct st_sensor_das das;
 	struct st_sensor_data_ready_irq drdy_irq;
 	bool multi_read_bit;
 	unsigned int bootime;
diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index ec819e9..b6e048e 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -13,34 +13,10 @@
 #ifndef MDEV_H
 #define MDEV_H
 
-/* Parent device */
-struct parent_device {
-	struct device		*dev;
-	const struct parent_ops	*ops;
-
-	/* internal */
-	struct kref		ref;
-	struct mutex		lock;
-	struct list_head	next;
-	struct kset		*mdev_types_kset;
-	struct list_head	type_list;
-};
-
-/* Mediated device */
-struct mdev_device {
-	struct device		dev;
-	struct parent_device	*parent;
-	uuid_le			uuid;
-	void			*driver_data;
-
-	/* internal */
-	struct kref		ref;
-	struct list_head	next;
-	struct kobject		*type_kobj;
-};
+struct mdev_device;
 
 /**
- * struct parent_ops - Structure to be registered for each parent device to
+ * struct mdev_parent_ops - Structure to be registered for each parent device to
  * register the device to mdev module.
  *
  * @owner:		The module owner.
@@ -86,10 +62,9 @@
  *			@mdev: mediated device structure
  *			@vma: vma structure
  * Parent device that support mediated device should be registered with mdev
- * module with parent_ops structure.
+ * module with mdev_parent_ops structure.
  **/
-
-struct parent_ops {
+struct mdev_parent_ops {
 	struct module   *owner;
 	const struct attribute_group **dev_attr_groups;
 	const struct attribute_group **mdev_attr_groups;
@@ -103,7 +78,7 @@
 			size_t count, loff_t *ppos);
 	ssize_t (*write)(struct mdev_device *mdev, const char __user *buf,
 			 size_t count, loff_t *ppos);
-	ssize_t (*ioctl)(struct mdev_device *mdev, unsigned int cmd,
+	long	(*ioctl)(struct mdev_device *mdev, unsigned int cmd,
 			 unsigned long arg);
 	int	(*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma);
 };
@@ -142,27 +117,22 @@
 };
 
 #define to_mdev_driver(drv)	container_of(drv, struct mdev_driver, driver)
-#define to_mdev_device(dev)	container_of(dev, struct mdev_device, dev)
 
-static inline void *mdev_get_drvdata(struct mdev_device *mdev)
-{
-	return mdev->driver_data;
-}
-
-static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data)
-{
-	mdev->driver_data = data;
-}
+extern void *mdev_get_drvdata(struct mdev_device *mdev);
+extern void mdev_set_drvdata(struct mdev_device *mdev, void *data);
+extern uuid_le mdev_uuid(struct mdev_device *mdev);
 
 extern struct bus_type mdev_bus_type;
 
-#define dev_is_mdev(d) ((d)->bus == &mdev_bus_type)
-
 extern int  mdev_register_device(struct device *dev,
-				 const struct parent_ops *ops);
+				 const struct mdev_parent_ops *ops);
 extern void mdev_unregister_device(struct device *dev);
 
 extern int  mdev_register_driver(struct mdev_driver *drv, struct module *owner);
 extern void mdev_unregister_driver(struct mdev_driver *drv);
 
+extern struct device *mdev_parent_dev(struct mdev_device *mdev);
+extern struct device *mdev_dev(struct mdev_device *mdev);
+extern struct mdev_device *mdev_from_dev(struct device *dev);
+
 #endif /* MDEV_H */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 93bdb34..6533c16 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1384,6 +1384,8 @@
 int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv);
 int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port,
 				      bool *vlan_offload_disabled);
+void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
+				       struct _rule_hw *eth_header);
 int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 9f48936..52b4374 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1071,11 +1071,6 @@
 	MLX5_INFINIBAND_PORT_COUNTERS_GROUP   = 0x20,
 };
 
-enum {
-	MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP       = 0x0,
-	MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP = 0x2,
-};
-
 static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
 {
 	if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 0ae5536..735b363 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -123,7 +123,6 @@
 	MLX5_REG_HOST_ENDIANNESS = 0x7004,
 	MLX5_REG_MCIA		 = 0x9014,
 	MLX5_REG_MLCR		 = 0x902b,
-	MLX5_REG_MPCNT		 = 0x9051,
 };
 
 enum mlx5_dcbx_oper_mode {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 57bec54..a852e9d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1757,80 +1757,6 @@
 	u8         reserved_at_4c0[0x300];
 };
 
-struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits {
-	u8         life_time_counter_high[0x20];
-
-	u8         life_time_counter_low[0x20];
-
-	u8         rx_errors[0x20];
-
-	u8         tx_errors[0x20];
-
-	u8         l0_to_recovery_eieos[0x20];
-
-	u8         l0_to_recovery_ts[0x20];
-
-	u8         l0_to_recovery_framing[0x20];
-
-	u8         l0_to_recovery_retrain[0x20];
-
-	u8         crc_error_dllp[0x20];
-
-	u8         crc_error_tlp[0x20];
-
-	u8         reserved_at_140[0x680];
-};
-
-struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits {
-	u8         life_time_counter_high[0x20];
-
-	u8         life_time_counter_low[0x20];
-
-	u8         time_to_boot_image_start[0x20];
-
-	u8         time_to_link_image[0x20];
-
-	u8         calibration_time[0x20];
-
-	u8         time_to_first_perst[0x20];
-
-	u8         time_to_detect_state[0x20];
-
-	u8         time_to_l0[0x20];
-
-	u8         time_to_crs_en[0x20];
-
-	u8         time_to_plastic_image_start[0x20];
-
-	u8         time_to_iron_image_start[0x20];
-
-	u8         perst_handler[0x20];
-
-	u8         times_in_l1[0x20];
-
-	u8         times_in_l23[0x20];
-
-	u8         dl_down[0x20];
-
-	u8         config_cycle1usec[0x20];
-
-	u8         config_cycle2to7usec[0x20];
-
-	u8         config_cycle_8to15usec[0x20];
-
-	u8         config_cycle_16_to_63usec[0x20];
-
-	u8         config_cycle_64usec[0x20];
-
-	u8         correctable_err_msg_sent[0x20];
-
-	u8         non_fatal_err_msg_sent[0x20];
-
-	u8         fatal_err_msg_sent[0x20];
-
-	u8         reserved_at_2e0[0x4e0];
-};
-
 struct mlx5_ifc_cmd_inter_comp_event_bits {
 	u8         command_completion_vector[0x20];
 
@@ -2995,12 +2921,6 @@
 	u8         reserved_at_0[0x7c0];
 };
 
-union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits {
-	struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits pcie_perf_cntrs_grp_data_layout;
-	struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits pcie_tas_cntrs_grp_data_layout;
-	u8         reserved_at_0[0x7c0];
-};
-
 union mlx5_ifc_event_auto_bits {
 	struct mlx5_ifc_comp_event_bits comp_event;
 	struct mlx5_ifc_dct_events_bits dct_events;
@@ -7320,18 +7240,6 @@
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
-struct mlx5_ifc_mpcnt_reg_bits {
-	u8         reserved_at_0[0x8];
-	u8         pcie_index[0x8];
-	u8         reserved_at_10[0xa];
-	u8         grp[0x6];
-
-	u8         clr[0x1];
-	u8         reserved_at_21[0x1f];
-
-	union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits counter_set;
-};
-
 struct mlx5_ifc_ppad_reg_bits {
 	u8         reserved_at_0[0x3];
 	u8         single_mac[0x1];
@@ -7937,7 +7845,6 @@
 	struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
 	struct mlx5_ifc_ppad_reg_bits ppad_reg;
 	struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
-	struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
 	struct mlx5_ifc_pplm_reg_bits pplm_reg;
 	struct mlx5_ifc_pplr_reg_bits pplr_reg;
 	struct mlx5_ifc_ppsc_reg_bits ppsc_reg;
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c56b398..6b5818d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -73,13 +73,13 @@
  */
 enum pageflags {
 	PG_locked,		/* Page is locked. Don't touch. */
-	PG_waiters,		/* Page has waiters, check its waitqueue */
 	PG_error,
 	PG_referenced,
 	PG_uptodate,
 	PG_dirty,
 	PG_lru,
 	PG_active,
+	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
 	PG_slab,
 	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
 	PG_arch_1,
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 5dea8f6..52bda85 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -306,7 +306,9 @@
 void radix_tree_replace_slot(struct radix_tree_root *root,
 			     void **slot, void *item);
 void __radix_tree_delete_node(struct radix_tree_root *root,
-			      struct radix_tree_node *node);
+			      struct radix_tree_node *node,
+			      radix_tree_update_node_t update_node,
+			      void *private);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
 void radix_tree_clear_tags(struct radix_tree_root *root,
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 183f37c..4ee479f 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -9,7 +9,13 @@
 struct page;
 struct scatterlist;
 
-extern int swiotlb_force;
+enum swiotlb_force {
+	SWIOTLB_NORMAL,		/* Default - depending on HW DMA mask etc. */
+	SWIOTLB_FORCE,		/* swiotlb=force */
+	SWIOTLB_NO_FORCE,	/* swiotlb=noforce */
+};
+
+extern enum swiotlb_force swiotlb_force;
 
 /*
  * Maximum allowable number of contiguous slabs to map,
@@ -108,11 +114,14 @@
 
 #ifdef CONFIG_SWIOTLB
 extern void __init swiotlb_free(void);
+unsigned int swiotlb_max_segment(void);
 #else
 static inline void swiotlb_free(void) { }
+static inline unsigned int swiotlb_max_segment(void) { return 0; }
 #endif
 
 extern void swiotlb_print_info(void);
 extern int is_swiotlb_buffer(phys_addr_t paddr);
+extern void swiotlb_set_max_segment(unsigned int);
 
 #endif /* __LINUX_SWIOTLB_H */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index f0cf5a1..0378e88 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -110,6 +110,7 @@
 	int sysctl_tcp_orphan_retries;
 	int sysctl_tcp_fin_timeout;
 	unsigned int sysctl_tcp_notsent_lowat;
+	int sysctl_tcp_tw_reuse;
 
 	int sysctl_igmp_max_memberships;
 	int sysctl_igmp_max_msf;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 207147b..6061963 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -252,7 +252,6 @@
 extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
 extern int sysctl_tcp_adv_win_scale;
-extern int sysctl_tcp_tw_reuse;
 extern int sysctl_tcp_frto;
 extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;
diff --git a/include/trace/events/swiotlb.h b/include/trace/events/swiotlb.h
index 7ea4c5e..288c0c5 100644
--- a/include/trace/events/swiotlb.h
+++ b/include/trace/events/swiotlb.h
@@ -11,16 +11,16 @@
 	TP_PROTO(struct device *dev,
 		 dma_addr_t dev_addr,
 		 size_t size,
-		 int swiotlb_force),
+		 enum swiotlb_force swiotlb_force),
 
 	TP_ARGS(dev, dev_addr, size, swiotlb_force),
 
 	TP_STRUCT__entry(
-		__string(	dev_name,	dev_name(dev)	)
-		__field(	u64,	dma_mask		)
-		__field(	dma_addr_t,	dev_addr	)
-		__field(	size_t,	size			)
-		__field(	int,	swiotlb_force		)
+		__string(	dev_name,	dev_name(dev)		)
+		__field(	u64,	dma_mask			)
+		__field(	dma_addr_t,	dev_addr		)
+		__field(	size_t,	size				)
+		__field(	enum swiotlb_force,	swiotlb_force	)
 	),
 
 	TP_fast_assign(
@@ -37,7 +37,10 @@
 		__entry->dma_mask,
 		(unsigned long long)__entry->dev_addr,
 		__entry->size,
-		__entry->swiotlb_force ? "swiotlb_force" : "" )
+		__print_symbolic(__entry->swiotlb_force,
+			{ SWIOTLB_NORMAL,	"NORMAL" },
+			{ SWIOTLB_FORCE,	"FORCE" },
+			{ SWIOTLB_NO_FORCE,	"NO_FORCE" }))
 );
 
 #endif /*  _TRACE_SWIOTLB_H */
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index acc6369..b2a31a5 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -93,6 +93,7 @@
  * |   0 | magic     | LE32         | FUNCTIONFS_DESCRIPTORS_MAGIC_V2      |
  * |   4 | length    | LE32         | length of the whole data chunk       |
  * |   8 | flags     | LE32         | combination of functionfs_flags      |
+ * |     | eventfd   | LE32         | eventfd file descriptor              |
  * |     | fs_count  | LE32         | number of full-speed descriptors     |
  * |     | hs_count  | LE32         | number of high-speed descriptors     |
  * |     | ss_count  | LE32         | number of super-speed descriptors    |
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 8b1dde9..7b44195 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -231,9 +231,11 @@
 	if (size)
 		new = alloc_chunk(size);
 
+	mutex_lock(&entry->group->mark_mutex);
 	spin_lock(&entry->lock);
 	if (chunk->dead || !entry->inode) {
 		spin_unlock(&entry->lock);
+		mutex_unlock(&entry->group->mark_mutex);
 		if (new)
 			free_chunk(new);
 		goto out;
@@ -251,6 +253,7 @@
 		list_del_rcu(&chunk->hash);
 		spin_unlock(&hash_lock);
 		spin_unlock(&entry->lock);
+		mutex_unlock(&entry->group->mark_mutex);
 		fsnotify_destroy_mark(entry, audit_tree_group);
 		goto out;
 	}
@@ -258,8 +261,8 @@
 	if (!new)
 		goto Fallback;
 
-	fsnotify_duplicate_mark(&new->mark, entry);
-	if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.inode, NULL, 1)) {
+	if (fsnotify_add_mark_locked(&new->mark, entry->group, entry->inode,
+				     NULL, 1)) {
 		fsnotify_put_mark(&new->mark);
 		goto Fallback;
 	}
@@ -293,6 +296,7 @@
 		owner->root = new;
 	spin_unlock(&hash_lock);
 	spin_unlock(&entry->lock);
+	mutex_unlock(&entry->group->mark_mutex);
 	fsnotify_destroy_mark(entry, audit_tree_group);
 	fsnotify_put_mark(&new->mark);	/* drop initial reference */
 	goto out;
@@ -309,6 +313,7 @@
 	put_tree(owner);
 	spin_unlock(&hash_lock);
 	spin_unlock(&entry->lock);
+	mutex_unlock(&entry->group->mark_mutex);
 out:
 	fsnotify_put_mark(entry);
 	spin_lock(&hash_lock);
@@ -386,18 +391,21 @@
 
 	chunk_entry = &chunk->mark;
 
+	mutex_lock(&old_entry->group->mark_mutex);
 	spin_lock(&old_entry->lock);
 	if (!old_entry->inode) {
 		/* old_entry is being shot, lets just lie */
 		spin_unlock(&old_entry->lock);
+		mutex_unlock(&old_entry->group->mark_mutex);
 		fsnotify_put_mark(old_entry);
 		free_chunk(chunk);
 		return -ENOENT;
 	}
 
-	fsnotify_duplicate_mark(chunk_entry, old_entry);
-	if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->inode, NULL, 1)) {
+	if (fsnotify_add_mark_locked(chunk_entry, old_entry->group,
+				     old_entry->inode, NULL, 1)) {
 		spin_unlock(&old_entry->lock);
+		mutex_unlock(&old_entry->group->mark_mutex);
 		fsnotify_put_mark(chunk_entry);
 		fsnotify_put_mark(old_entry);
 		return -ENOSPC;
@@ -413,6 +421,7 @@
 		chunk->dead = 1;
 		spin_unlock(&chunk_entry->lock);
 		spin_unlock(&old_entry->lock);
+		mutex_unlock(&old_entry->group->mark_mutex);
 
 		fsnotify_destroy_mark(chunk_entry, audit_tree_group);
 
@@ -445,6 +454,7 @@
 	spin_unlock(&hash_lock);
 	spin_unlock(&chunk_entry->lock);
 	spin_unlock(&old_entry->lock);
+	mutex_unlock(&old_entry->group->mark_mutex);
 	fsnotify_destroy_mark(old_entry, audit_tree_group);
 	fsnotify_put_mark(chunk_entry);	/* drop initial reference */
 	fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 042fd7e..f75c4d0 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1471,6 +1471,7 @@
 			bool multi_instance)
 {
 	int cpu, ret = 0;
+	bool dynstate;
 
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
@@ -1480,6 +1481,12 @@
 	ret = cpuhp_store_callbacks(state, name, startup, teardown,
 				    multi_instance);
 
+	dynstate = state == CPUHP_AP_ONLINE_DYN;
+	if (ret > 0 && dynstate) {
+		state = ret;
+		ret = 0;
+	}
+
 	if (ret || !invoke || !startup)
 		goto out;
 
@@ -1508,7 +1515,7 @@
 	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
 	 * dynamically allocated state in case of success.
 	 */
-	if (!ret && state == CPUHP_AP_ONLINE_DYN)
+	if (!ret && dynstate)
 		return state;
 	return ret;
 }
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 6f382e0..0b92d60 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -640,6 +640,7 @@
 				update_node(node, private);
 		}
 
+		WARN_ON_ONCE(!list_empty(&node->private_list));
 		radix_tree_node_free(node);
 	}
 }
@@ -666,6 +667,7 @@
 			root->rnode = NULL;
 		}
 
+		WARN_ON_ONCE(!list_empty(&node->private_list));
 		radix_tree_node_free(node);
 
 		node = parent;
@@ -767,6 +769,7 @@
 			struct radix_tree_node *old = child;
 			offset = child->offset + 1;
 			child = child->parent;
+			WARN_ON_ONCE(!list_empty(&node->private_list));
 			radix_tree_node_free(old);
 			if (old == entry_to_node(node))
 				return;
@@ -1824,15 +1827,19 @@
  *	__radix_tree_delete_node    -    try to free node after clearing a slot
  *	@root:		radix tree root
  *	@node:		node containing @index
+ *	@update_node:	callback for changing leaf nodes
+ *	@private:	private data to pass to @update_node
  *
  *	After clearing the slot at @index in @node from radix tree
  *	rooted at @root, call this function to attempt freeing the
  *	node and shrinking the tree.
  */
 void __radix_tree_delete_node(struct radix_tree_root *root,
-			      struct radix_tree_node *node)
+			      struct radix_tree_node *node,
+			      radix_tree_update_node_t update_node,
+			      void *private)
 {
-	delete_node(root, node, NULL, NULL);
+	delete_node(root, node, update_node, private);
 }
 
 /**
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index cb1b54e..975b8fc 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -53,7 +53,7 @@
  */
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 
-int swiotlb_force;
+enum swiotlb_force swiotlb_force;
 
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
@@ -83,6 +83,12 @@
 static unsigned int io_tlb_index;
 
 /*
+ * Max segment that we can provide which (if pages are contingous) will
+ * not be bounced (unless SWIOTLB_FORCE is set).
+ */
+unsigned int max_segment;
+
+/*
  * We need to save away the original address corresponding to a mapped entry
  * for the sync operations.
  */
@@ -106,8 +112,12 @@
 	}
 	if (*str == ',')
 		++str;
-	if (!strcmp(str, "force"))
-		swiotlb_force = 1;
+	if (!strcmp(str, "force")) {
+		swiotlb_force = SWIOTLB_FORCE;
+	} else if (!strcmp(str, "noforce")) {
+		swiotlb_force = SWIOTLB_NO_FORCE;
+		io_tlb_nslabs = 1;
+	}
 
 	return 0;
 }
@@ -120,6 +130,20 @@
 }
 EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
 
+unsigned int swiotlb_max_segment(void)
+{
+	return max_segment;
+}
+EXPORT_SYMBOL_GPL(swiotlb_max_segment);
+
+void swiotlb_set_max_segment(unsigned int val)
+{
+	if (swiotlb_force == SWIOTLB_FORCE)
+		max_segment = 1;
+	else
+		max_segment = rounddown(val, PAGE_SIZE);
+}
+
 /* default to 64MB */
 #define IO_TLB_DEFAULT_SIZE (64UL<<20)
 unsigned long swiotlb_size_or_default(void)
@@ -201,6 +225,7 @@
 	if (verbose)
 		swiotlb_print_info();
 
+	swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
 	return 0;
 }
 
@@ -279,6 +304,7 @@
 	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
 	if (rc)
 		free_pages((unsigned long)vstart, order);
+
 	return rc;
 }
 
@@ -333,6 +359,8 @@
 
 	late_alloc = 1;
 
+	swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+
 	return 0;
 
 cleanup4:
@@ -347,6 +375,7 @@
 	io_tlb_end = 0;
 	io_tlb_start = 0;
 	io_tlb_nslabs = 0;
+	max_segment = 0;
 	return -ENOMEM;
 }
 
@@ -375,6 +404,7 @@
 				   PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
 	}
 	io_tlb_nslabs = 0;
+	max_segment = 0;
 }
 
 int is_swiotlb_buffer(phys_addr_t paddr)
@@ -543,8 +573,15 @@
 map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 	   enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
+	dma_addr_t start_dma_addr;
 
+	if (swiotlb_force == SWIOTLB_NO_FORCE) {
+		dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
+				     &phys);
+		return SWIOTLB_MAP_ERROR;
+	}
+
+	start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
 	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
 				      dir, attrs);
 }
@@ -721,6 +758,9 @@
 swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
 	     int do_panic)
 {
+	if (swiotlb_force == SWIOTLB_NO_FORCE)
+		return;
+
 	/*
 	 * Ran out of IOMMU space for this operation. This is very bad.
 	 * Unfortunately the drivers cannot handle this operation properly.
@@ -763,7 +803,7 @@
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
+	if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
 		return dev_addr;
 
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
@@ -904,7 +944,7 @@
 		phys_addr_t paddr = sg_phys(sg);
 		dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
 
-		if (swiotlb_force ||
+		if (swiotlb_force == SWIOTLB_FORCE ||
 		    !dma_capable(hwdev, dev_addr, sg->length)) {
 			phys_addr_t map = map_single(hwdev, sg_phys(sg),
 						     sg->length, dir, attrs);
diff --git a/mm/filemap.c b/mm/filemap.c
index 82f26cd..d0e4d10 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -912,6 +912,29 @@
 }
 EXPORT_SYMBOL_GPL(add_page_wait_queue);
 
+#ifndef clear_bit_unlock_is_negative_byte
+
+/*
+ * PG_waiters is the high bit in the same byte as PG_lock.
+ *
+ * On x86 (and on many other architectures), we can clear PG_lock and
+ * test the sign bit at the same time. But if the architecture does
+ * not support that special operation, we just do this all by hand
+ * instead.
+ *
+ * The read of PG_waiters has to be after (or concurrently with) PG_locked
+ * being cleared, but a memory barrier should be unneccssary since it is
+ * in the same byte as PG_locked.
+ */
+static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
+{
+	clear_bit_unlock(nr, mem);
+	/* smp_mb__after_atomic(); */
+	return test_bit(PG_waiters, mem);
+}
+
+#endif
+
 /**
  * unlock_page - unlock a locked page
  * @page: the page
@@ -921,16 +944,19 @@
  * mechanism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
- * The mb is necessary to enforce ordering between the clear_bit and the read
- * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
+ * Note that this depends on PG_waiters being the sign bit in the byte
+ * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
+ * clear the PG_locked bit and test PG_waiters at the same time fairly
+ * portably (architectures that do LL/SC can test any bit, while x86 can
+ * test the sign bit).
  */
 void unlock_page(struct page *page)
 {
+	BUILD_BUG_ON(PG_waiters != 7);
 	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	clear_bit_unlock(PG_locked, &page->flags);
-	smp_mb__after_atomic();
-	wake_up_page(page, PG_locked);
+	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
+		wake_up_page_bit(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);
 
diff --git a/mm/memory.c b/mm/memory.c
index 7d23b50..9f2c15c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3008,13 +3008,6 @@
 	ret = 0;
 	count_vm_event(THP_FILE_MAPPED);
 out:
-	/*
-	 * If we are going to fallback to pte mapping, do a
-	 * withdraw with pmd lock held.
-	 */
-	if (arch_needs_pgtable_deposit() && ret == VM_FAULT_FALLBACK)
-		vmf->prealloc_pte = pgtable_trans_huge_withdraw(vma->vm_mm,
-								vmf->pmd);
 	spin_unlock(vmf->ptl);
 	return ret;
 }
@@ -3055,20 +3048,18 @@
 
 		ret = do_set_pmd(vmf, page);
 		if (ret != VM_FAULT_FALLBACK)
-			goto fault_handled;
+			return ret;
 	}
 
 	if (!vmf->pte) {
 		ret = pte_alloc_one_map(vmf);
 		if (ret)
-			goto fault_handled;
+			return ret;
 	}
 
 	/* Re-check under ptl */
-	if (unlikely(!pte_none(*vmf->pte))) {
-		ret = VM_FAULT_NOPAGE;
-		goto fault_handled;
-	}
+	if (unlikely(!pte_none(*vmf->pte)))
+		return VM_FAULT_NOPAGE;
 
 	flush_icache_page(vma, page);
 	entry = mk_pte(page, vma->vm_page_prot);
@@ -3088,15 +3079,8 @@
 
 	/* no need to invalidate: a not-present page won't be cached */
 	update_mmu_cache(vma, vmf->address, vmf->pte);
-	ret = 0;
 
-fault_handled:
-	/* preallocated pagetable is unused: free it */
-	if (vmf->prealloc_pte) {
-		pte_free(vmf->vma->vm_mm, vmf->prealloc_pte);
-		vmf->prealloc_pte = 0;
-	}
-	return ret;
+	return 0;
 }
 
 
@@ -3360,15 +3344,24 @@
 static int do_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	int ret;
 
 	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
 	if (!vma->vm_ops->fault)
-		return VM_FAULT_SIGBUS;
-	if (!(vmf->flags & FAULT_FLAG_WRITE))
-		return do_read_fault(vmf);
-	if (!(vma->vm_flags & VM_SHARED))
-		return do_cow_fault(vmf);
-	return do_shared_fault(vmf);
+		ret = VM_FAULT_SIGBUS;
+	else if (!(vmf->flags & FAULT_FLAG_WRITE))
+		ret = do_read_fault(vmf);
+	else if (!(vma->vm_flags & VM_SHARED))
+		ret = do_cow_fault(vmf);
+	else
+		ret = do_shared_fault(vmf);
+
+	/* preallocated pagetable is unused: free it */
+	if (vmf->prealloc_pte) {
+		pte_free(vma->vm_mm, vmf->prealloc_pte);
+		vmf->prealloc_pte = 0;
+	}
+	return ret;
 }
 
 static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
diff --git a/mm/truncate.c b/mm/truncate.c
index fd97f1d..dd7b24e 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -24,20 +24,12 @@
 #include <linux/rmap.h>
 #include "internal.h"
 
-static void clear_exceptional_entry(struct address_space *mapping,
-				    pgoff_t index, void *entry)
+static void clear_shadow_entry(struct address_space *mapping, pgoff_t index,
+			       void *entry)
 {
 	struct radix_tree_node *node;
 	void **slot;
 
-	/* Handled by shmem itself */
-	if (shmem_mapping(mapping))
-		return;
-
-	if (dax_mapping(mapping)) {
-		dax_delete_mapping_entry(mapping, index);
-		return;
-	}
 	spin_lock_irq(&mapping->tree_lock);
 	/*
 	 * Regular page slots are stabilized by the page lock even
@@ -55,6 +47,56 @@
 	spin_unlock_irq(&mapping->tree_lock);
 }
 
+/*
+ * Unconditionally remove exceptional entry. Usually called from truncate path.
+ */
+static void truncate_exceptional_entry(struct address_space *mapping,
+				       pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	if (dax_mapping(mapping)) {
+		dax_delete_mapping_entry(mapping, index);
+		return;
+	}
+	clear_shadow_entry(mapping, index, entry);
+}
+
+/*
+ * Invalidate exceptional entry if easily possible. This handles exceptional
+ * entries for invalidate_inode_pages() so for DAX it evicts only unlocked and
+ * clean entries.
+ */
+static int invalidate_exceptional_entry(struct address_space *mapping,
+					pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
+/*
+ * Invalidate exceptional entry if clean. This handles exceptional entries for
+ * invalidate_inode_pages2() so for DAX it evicts only clean entries.
+ */
+static int invalidate_exceptional_entry2(struct address_space *mapping,
+					 pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry_sync(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
 /**
  * do_invalidatepage - invalidate part or all of a page
  * @page: the page which is affected
@@ -262,7 +304,8 @@
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -351,7 +394,8 @@
 			}
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -470,7 +514,8 @@
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				invalidate_exceptional_entry(mapping, index,
+							     page);
 				continue;
 			}
 
@@ -592,7 +637,9 @@
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				if (!invalidate_exceptional_entry2(mapping,
+								   index, page))
+					ret = -EBUSY;
 				continue;
 			}
 
diff --git a/mm/workingset.c b/mm/workingset.c
index 241fa5d..abb58ff 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -473,7 +473,8 @@
 	if (WARN_ON_ONCE(node->exceptional))
 		goto out_invalid;
 	inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM);
-	__radix_tree_delete_node(&mapping->page_tree, node);
+	__radix_tree_delete_node(&mapping->page_tree, node,
+				 workingset_update_node, mapping);
 
 out_invalid:
 	spin_unlock(&mapping->tree_lock);
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 019557d..09cfe87 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -1059,7 +1059,9 @@
 {
 	int i;
 
+#ifdef CONFIG_PROC_FS
 	remove_proc_entry("lec", atm_proc_root);
+#endif
 
 	deregister_atm_ioctl(&lane_ioctl_ops);
 
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 8e0c063..fb55327 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -75,6 +75,7 @@
 	struct nlattr *nla;
 	struct sk_buff *skb;
 	unsigned long flags;
+	void *msg_header;
 
 	al = sizeof(struct net_dm_alert_msg);
 	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
@@ -82,21 +83,41 @@
 
 	skb = genlmsg_new(al, GFP_KERNEL);
 
-	if (skb) {
-		genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
-				0, NET_DM_CMD_ALERT);
-		nla = nla_reserve(skb, NLA_UNSPEC,
-				  sizeof(struct net_dm_alert_msg));
-		msg = nla_data(nla);
-		memset(msg, 0, al);
-	} else {
-		mod_timer(&data->send_timer, jiffies + HZ / 10);
-	}
+	if (!skb)
+		goto err;
 
+	msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+				 0, NET_DM_CMD_ALERT);
+	if (!msg_header) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
+	}
+	nla = nla_reserve(skb, NLA_UNSPEC,
+			  sizeof(struct net_dm_alert_msg));
+	if (!nla) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
+	}
+	msg = nla_data(nla);
+	memset(msg, 0, al);
+	goto out;
+
+err:
+	mod_timer(&data->send_timer, jiffies + HZ / 10);
+out:
 	spin_lock_irqsave(&data->lock, flags);
 	swap(data->skb, skb);
 	spin_unlock_irqrestore(&data->lock, flags);
 
+	if (skb) {
+		struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
+		struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh);
+
+		genlmsg_end(skb, genlmsg_data(gnlh));
+	}
+
 	return skb;
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index e6c412b..1969b3f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2972,12 +2972,6 @@
 }
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 
-void bpf_warn_invalid_xdp_buffer(void)
-{
-	WARN_ONCE(1, "Illegal XDP buffer encountered, expect throughput degradation\n");
-}
-EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_buffer);
-
 static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
 					int src_reg, int ctx_off,
 					struct bpf_insn *insn_buf,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d6447dc..fe4e153 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -468,8 +468,9 @@
 			if (hdr->flags & GRE_ACK)
 				offset += sizeof(((struct pptp_gre_header *)0)->ack);
 
-			ppp_hdr = skb_header_pointer(skb, nhoff + offset,
-						     sizeof(_ppp_hdr), _ppp_hdr);
+			ppp_hdr = __skb_header_pointer(skb, nhoff + offset,
+						     sizeof(_ppp_hdr),
+						     data, hlen, _ppp_hdr);
 			if (!ppp_hdr)
 				goto out_bad;
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 18b5aae..75e3ea7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3898,6 +3898,9 @@
 	u32 filter_mask;
 	int err;
 
+	if (nlmsg_len(nlh) < sizeof(*ifsm))
+		return -EINVAL;
+
 	ifsm = nlmsg_data(nlh);
 	if (ifsm->ifindex > 0)
 		dev = __dev_get_by_index(net, ifsm->ifindex);
@@ -3947,6 +3950,9 @@
 
 	cb->seq = net->dev_base_seq;
 
+	if (nlmsg_len(cb->nlh) < sizeof(*ifsm))
+		return -EINVAL;
+
 	ifsm = nlmsg_data(cb->nlh);
 	filter_mask = ifsm->filter_mask;
 	if (!filter_mask)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3ff8938..eae0332 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -85,7 +85,7 @@
 	if (tb)
 		return tb;
 
-	if (id == RT_TABLE_LOCAL)
+	if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
 		alias = fib_new_table(net, RT_TABLE_MAIN);
 
 	tb = fib_trie_table(id, alias);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 68d6221..5b15459 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -219,9 +219,14 @@
 static void igmp_gq_start_timer(struct in_device *in_dev)
 {
 	int tv = prandom_u32() % in_dev->mr_maxdelay;
+	unsigned long exp = jiffies + tv + 2;
+
+	if (in_dev->mr_gq_running &&
+	    time_after_eq(exp, (in_dev->mr_gq_timer).expires))
+		return;
 
 	in_dev->mr_gq_running = 1;
-	if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2))
+	if (!mod_timer(&in_dev->mr_gq_timer, exp))
 		in_dev_hold(in_dev);
 }
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 57e1405..53ae0c6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1225,8 +1225,14 @@
 		 * which has interface index (iif) as the first member of the
 		 * underlying inet{6}_skb_parm struct. This code then overlays
 		 * PKTINFO_SKB_CB and in_pktinfo also has iif as the first
-		 * element so the iif is picked up from the prior IPCB
+		 * element so the iif is picked up from the prior IPCB. If iif
+		 * is the loopback interface, then return the sending interface
+		 * (e.g., process binds socket to eth0 for Tx which is
+		 * redirected to loopback in the rtable/dst).
 		 */
+		if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX)
+			pktinfo->ipi_ifindex = inet_iif(skb);
+
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
 	} else {
 		pktinfo->ipi_ifindex = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a82a117..0fcac8e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1914,7 +1914,8 @@
 		}
 	}
 
-	rth = rt_dst_alloc(net->loopback_dev, flags | RTCF_LOCAL, res.type,
+	rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
+			   flags | RTCF_LOCAL, res.type,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache);
 	if (!rth)
 		goto e_nobufs;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 80bc36b..22cbd61 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -433,13 +433,6 @@
 		.extra2		= &tcp_adv_win_scale_max,
 	},
 	{
-		.procname	= "tcp_tw_reuse",
-		.data		= &sysctl_tcp_tw_reuse,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_frto",
 		.data		= &sysctl_tcp_frto,
 		.maxlen		= sizeof(int),
@@ -960,6 +953,13 @@
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_tw_reuse",
+		.data		= &init_net.ipv4.sysctl_tcp_tw_reuse,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30d81f5..fe9da4f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,7 +84,6 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -120,7 +119,7 @@
 	   and use initial timestamp retrieved from peer table.
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
-	    (!twp || (sysctl_tcp_tw_reuse &&
+	    (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
 			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
 		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
 		if (tp->write_seq == 0)
@@ -2456,6 +2455,7 @@
 	net->ipv4.sysctl_tcp_orphan_retries = 0;
 	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+	net->ipv4.sysctl_tcp_tw_reuse = 0;
 
 	return 0;
 fail:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 70d0de40..38122d0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1373,7 +1373,7 @@
 	 */
 
 	cork->length += length;
-	if (((length > mtu) ||
+	if ((((length + fragheaderlen) > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 8938b6b..3d73278 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -47,7 +47,8 @@
 	return (struct l2tp_ip_sock *)sk;
 }
 
-static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif, u32 tunnel_id)
+static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr,
+					  __be32 raddr, int dif, u32 tunnel_id)
 {
 	struct sock *sk;
 
@@ -61,6 +62,7 @@
 		if ((l2tp->conn_id == tunnel_id) &&
 		    net_eq(sock_net(sk), net) &&
 		    !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
+		    (!inet->inet_daddr || !raddr || inet->inet_daddr == raddr) &&
 		    (!sk->sk_bound_dev_if || !dif ||
 		     sk->sk_bound_dev_if == dif))
 			goto found;
@@ -71,15 +73,6 @@
 	return sk;
 }
 
-static inline struct sock *l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif, u32 tunnel_id)
-{
-	struct sock *sk = __l2tp_ip_bind_lookup(net, laddr, dif, tunnel_id);
-	if (sk)
-		sock_hold(sk);
-
-	return sk;
-}
-
 /* When processing receive frames, there are two cases to
  * consider. Data frames consist of a non-zero session-id and an
  * optional cookie. Control frames consist of a regular L2TP header
@@ -183,8 +176,8 @@
 		struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
 
 		read_lock_bh(&l2tp_ip_lock);
-		sk = __l2tp_ip_bind_lookup(net, iph->daddr, inet_iif(skb),
-					   tunnel_id);
+		sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr,
+					   inet_iif(skb), tunnel_id);
 		if (!sk) {
 			read_unlock_bh(&l2tp_ip_lock);
 			goto discard;
@@ -280,7 +273,7 @@
 		inet->inet_saddr = 0;  /* Use device */
 
 	write_lock_bh(&l2tp_ip_lock);
-	if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr,
+	if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0,
 				  sk->sk_bound_dev_if, addr->l2tp_conn_id)) {
 		write_unlock_bh(&l2tp_ip_lock);
 		ret = -EADDRINUSE;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index f092ac4..331ccf5 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -59,12 +59,14 @@
 
 static struct sock *__l2tp_ip6_bind_lookup(struct net *net,
 					   struct in6_addr *laddr,
+					   const struct in6_addr *raddr,
 					   int dif, u32 tunnel_id)
 {
 	struct sock *sk;
 
 	sk_for_each_bound(sk, &l2tp_ip6_bind_table) {
-		const struct in6_addr *addr = inet6_rcv_saddr(sk);
+		const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk);
+		const struct in6_addr *sk_raddr = &sk->sk_v6_daddr;
 		struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
 
 		if (l2tp == NULL)
@@ -72,7 +74,8 @@
 
 		if ((l2tp->conn_id == tunnel_id) &&
 		    net_eq(sock_net(sk), net) &&
-		    (!addr || ipv6_addr_equal(addr, laddr)) &&
+		    (!sk_laddr || ipv6_addr_any(sk_laddr) || ipv6_addr_equal(sk_laddr, laddr)) &&
+		    (!raddr || ipv6_addr_any(sk_raddr) || ipv6_addr_equal(sk_raddr, raddr)) &&
 		    (!sk->sk_bound_dev_if || !dif ||
 		     sk->sk_bound_dev_if == dif))
 			goto found;
@@ -83,17 +86,6 @@
 	return sk;
 }
 
-static inline struct sock *l2tp_ip6_bind_lookup(struct net *net,
-						struct in6_addr *laddr,
-						int dif, u32 tunnel_id)
-{
-	struct sock *sk = __l2tp_ip6_bind_lookup(net, laddr, dif, tunnel_id);
-	if (sk)
-		sock_hold(sk);
-
-	return sk;
-}
-
 /* When processing receive frames, there are two cases to
  * consider. Data frames consist of a non-zero session-id and an
  * optional cookie. Control frames consist of a regular L2TP header
@@ -197,8 +189,8 @@
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		read_lock_bh(&l2tp_ip6_lock);
-		sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, inet6_iif(skb),
-					    tunnel_id);
+		sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr,
+					    inet6_iif(skb), tunnel_id);
 		if (!sk) {
 			read_unlock_bh(&l2tp_ip6_lock);
 			goto discard;
@@ -330,7 +322,7 @@
 	rcu_read_unlock();
 
 	write_lock_bh(&l2tp_ip6_lock);
-	if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, bound_dev_if,
+	if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if,
 				   addr->l2tp_conn_id)) {
 		write_unlock_bh(&l2tp_ip6_lock);
 		err = -EADDRINUSE;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 2c21b70..0d8b716 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3287,7 +3287,7 @@
 	int extra_head = fast_tx->hdr_len - (ETH_HLEN - 2);
 	int hw_headroom = sdata->local->hw.extra_tx_headroom;
 	struct ethhdr eth;
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_info *info;
 	struct ieee80211_hdr *hdr = (void *)fast_tx->hdr;
 	struct ieee80211_tx_data tx;
 	ieee80211_tx_result r;
@@ -3351,6 +3351,7 @@
 	memcpy(skb->data + fast_tx->da_offs, eth.h_dest, ETH_ALEN);
 	memcpy(skb->data + fast_tx->sa_offs, eth.h_source, ETH_ALEN);
 
+	info = IEEE80211_SKB_CB(skb);
 	memset(info, 0, sizeof(*info));
 	info->band = fast_tx->band;
 	info->control.vif = &sdata->vif;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 2d4c4d3..9c62b63 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -606,7 +606,6 @@
 	rcu_assign_pointer(flow->sf_acts, acts);
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;
-	packet->protocol = flow->key.eth.type;
 
 	rcu_read_lock();
 	dp = get_dp_rcu(net, ovs_header->dp_ifindex);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 08aa926..2c0a00f 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -312,7 +312,8 @@
  * Returns 0 if it encounters a non-vlan or incomplete packet.
  * Returns 1 after successfully parsing vlan tag.
  */
-static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
+static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
+			  bool untag_vlan)
 {
 	struct vlan_head *vh = (struct vlan_head *)skb->data;
 
@@ -330,7 +331,20 @@
 	key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT);
 	key_vh->tpid = vh->tpid;
 
-	__skb_pull(skb, sizeof(struct vlan_head));
+	if (unlikely(untag_vlan)) {
+		int offset = skb->data - skb_mac_header(skb);
+		u16 tci;
+		int err;
+
+		__skb_push(skb, offset);
+		err = __skb_vlan_pop(skb, &tci);
+		__skb_pull(skb, offset);
+		if (err)
+			return err;
+		__vlan_hwaccel_put_tag(skb, key_vh->tpid, tci);
+	} else {
+		__skb_pull(skb, sizeof(struct vlan_head));
+	}
 	return 1;
 }
 
@@ -351,13 +365,13 @@
 		key->eth.vlan.tpid = skb->vlan_proto;
 	} else {
 		/* Parse outer vlan tag in the non-accelerated case. */
-		res = parse_vlan_tag(skb, &key->eth.vlan);
+		res = parse_vlan_tag(skb, &key->eth.vlan, true);
 		if (res <= 0)
 			return res;
 	}
 
 	/* Parse inner vlan tag. */
-	res = parse_vlan_tag(skb, &key->eth.cvlan);
+	res = parse_vlan_tag(skb, &key->eth.cvlan, false);
 	if (res <= 0)
 		return res;
 
@@ -800,29 +814,15 @@
 	if (err)
 		return err;
 
-	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
-		/* key_extract assumes that skb->protocol is set-up for
-		 * layer 3 packets which is the case for other callers,
-		 * in particular packets recieved from the network stack.
-		 * Here the correct value can be set from the metadata
-		 * extracted above.
-		 */
-		skb->protocol = key->eth.type;
-	} else {
-		struct ethhdr *eth;
+	/* key_extract assumes that skb->protocol is set-up for
+	 * layer 3 packets which is the case for other callers,
+	 * in particular packets received from the network stack.
+	 * Here the correct value can be set from the metadata
+	 * extracted above.
+	 * For L2 packet key eth type would be zero. skb protocol
+	 * would be set to correct value later during key-extact.
+	 */
 
-		skb_reset_mac_header(skb);
-		eth = eth_hdr(skb);
-
-		/* Normally, setting the skb 'protocol' field would be
-		 * handled by a call to eth_type_trans(), but it assumes
-		 * there's a sending device, which we may not have.
-		 */
-		if (eth_proto_is_802_3(eth->h_proto))
-			skb->protocol = eth->h_proto;
-		else
-			skb->protocol = htons(ETH_P_802_2);
-	}
-
+	skb->protocol = key->eth.type;
 	return key_extract(skb, key);
 }
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3fbba79..1ecdf80 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -148,13 +148,15 @@
 	unsigned long cl;
 	unsigned long fh;
 	int err;
-	int tp_created = 0;
+	int tp_created;
 
 	if ((n->nlmsg_type != RTM_GETTFILTER) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
+	tp_created = 0;
+
 	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
 	if (err < 0)
 		return err;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 333f8e2..970db7a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -153,10 +153,14 @@
 
 		switch (ip_tunnel_info_af(info)) {
 		case AF_INET:
+			skb_key.enc_control.addr_type =
+				FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 			skb_key.enc_ipv4.src = key->u.ipv4.src;
 			skb_key.enc_ipv4.dst = key->u.ipv4.dst;
 			break;
 		case AF_INET6:
+			skb_key.enc_control.addr_type =
+				FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 			skb_key.enc_ipv6.src = key->u.ipv6.src;
 			skb_key.enc_ipv6.dst = key->u.ipv6.dst;
 			break;
diff --git a/net/socket.c b/net/socket.c
index 8487bf1..a8c2307 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -537,7 +537,7 @@
 {
 	int err = simple_setattr(dentry, iattr);
 
-	if (!err) {
+	if (!err && (iattr->ia_valid & ATTR_UID)) {
 		struct socket *sock = SOCKET_I(d_inode(dentry));
 
 		sock->sk->sk_uid = iattr->ia_uid;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 333c5da..800caaa 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -441,15 +441,19 @@
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
 		if (TIPC_SKB_CB(skb)->bytes_read) {
 			kfree_skb(skb);
-		} else {
-			if (!tipc_sk_type_connectionless(sk) &&
-			    sk->sk_state != TIPC_DISCONNECTING) {
-				tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-				tipc_node_remove_conn(net, dnode, tsk->portid);
-			}
-			tipc_sk_respond(sk, skb, error);
+			continue;
 		}
+		if (!tipc_sk_type_connectionless(sk) &&
+		    sk->sk_state != TIPC_DISCONNECTING) {
+			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+			tipc_node_remove_conn(net, dnode, tsk->portid);
+		}
+		tipc_sk_respond(sk, skb, error);
 	}
+
+	if (tipc_sk_type_connectionless(sk))
+		return;
+
 	if (sk->sk_state != TIPC_DISCONNECTING) {
 		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
 				      TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
@@ -457,10 +461,8 @@
 				      tsk->portid, error);
 		if (skb)
 			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
-		if (!tipc_sk_type_connectionless(sk)) {
-			tipc_node_remove_conn(net, dnode, tsk->portid);
-			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-		}
+		tipc_node_remove_conn(net, dnode, tsk->portid);
+		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
 	}
 }
 
diff --git a/samples/Kconfig b/samples/Kconfig
index a6d2a43..b124f62 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -105,4 +105,11 @@
 	help
 	  Build samples of blackfin gptimers sample module.
 
+config SAMPLE_VFIO_MDEV_MTTY
+	tristate "Build VFIO mtty example mediated device sample code -- loadable modules only"
+	depends on VFIO_MDEV_DEVICE && m
+	help
+	  Build a virtual tty sample driver for use as a VFIO
+	  mediated device
+
 endif # SAMPLES
diff --git a/samples/Makefile b/samples/Makefile
index e17d66d..86a137e 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -2,4 +2,5 @@
 
 obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ trace_events/ livepatch/ \
 			   hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
-			   configfs/ connector/ v4l/ trace_printk/ blackfin/
+			   configfs/ connector/ v4l/ trace_printk/ blackfin/ \
+			   vfio-mdev/
diff --git a/samples/vfio-mdev/Makefile b/samples/vfio-mdev/Makefile
index a932edb..cbbd868 100644
--- a/samples/vfio-mdev/Makefile
+++ b/samples/vfio-mdev/Makefile
@@ -1,13 +1 @@
-#
-# Makefile for mtty.c file
-#
-KERNEL_DIR:=/lib/modules/$(shell uname -r)/build
-
-obj-m:=mtty.o
-
-modules clean modules_install:
-	$(MAKE) -C $(KERNEL_DIR) SUBDIRS=$(PWD) $@
-
-default: modules
-
-module: modules
+obj-$(CONFIG_SAMPLE_VFIO_MDEV_MTTY) += mtty.o
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index 6b633a4..1fc57a5 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -164,7 +164,7 @@
 	struct mdev_state *mds;
 
 	list_for_each_entry(mds, &mdev_devices_list, next) {
-		if (uuid_le_cmp(mds->mdev->uuid, uuid) == 0)
+		if (uuid_le_cmp(mdev_uuid(mds->mdev), uuid) == 0)
 			return mds;
 	}
 
@@ -341,7 +341,8 @@
 				pr_err("Serial port %d: Fifo level trigger\n",
 					index);
 #endif
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+						mdev_uuid(mdev_state->mdev));
 			}
 		} else {
 #if defined(DEBUG_INTR)
@@ -355,7 +356,8 @@
 			 */
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 								UART_IER_RLSI)
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+						mdev_uuid(mdev_state->mdev));
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 		break;
@@ -374,7 +376,8 @@
 				pr_err("Serial port %d: IER_THRI write\n",
 					index);
 #endif
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+						mdev_uuid(mdev_state->mdev));
 			}
 
 			mutex_unlock(&mdev_state->rxtx_lock);
@@ -445,7 +448,7 @@
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR_OUT2 write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_state->mdev->uuid);
+			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
 		}
 
 		if ((mdev_state->s[index].uart_reg[UART_IER] & UART_IER_MSI) &&
@@ -453,7 +456,7 @@
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR RTS/DTR write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_state->mdev->uuid);
+			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
 		}
 		break;
 
@@ -504,7 +507,8 @@
 #endif
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 							 UART_IER_THRI)
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+					mdev_uuid(mdev_state->mdev));
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 
@@ -734,7 +738,7 @@
 
 	for (i = 0; i < 2; i++) {
 		snprintf(name, MTTY_STRING_LEN, "%s-%d",
-			dev_driver_string(mdev->parent->dev), i + 1);
+			dev_driver_string(mdev_parent_dev(mdev)), i + 1);
 		if (!strcmp(kobj->name, name)) {
 			nr_ports = i + 1;
 			break;
@@ -1298,10 +1302,8 @@
 sample_mdev_dev_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
-	struct mdev_device *mdev = to_mdev_device(dev);
-
-	if (mdev)
-		return sprintf(buf, "This is MDEV %s\n", dev_name(&mdev->dev));
+	if (mdev_from_dev(dev))
+		return sprintf(buf, "This is MDEV %s\n", dev_name(dev));
 
 	return sprintf(buf, "\n");
 }
@@ -1402,7 +1404,7 @@
 	NULL,
 };
 
-struct parent_ops mdev_fops = {
+struct mdev_parent_ops mdev_fops = {
 	.owner                  = THIS_MODULE,
 	.dev_attr_groups        = mtty_dev_groups,
 	.mdev_attr_groups       = mdev_dev_groups,
@@ -1447,6 +1449,7 @@
 
 	if (IS_ERR(mtty_dev.vd_class)) {
 		pr_err("Error: failed to register mtty_dev class\n");
+		ret = PTR_ERR(mtty_dev.vd_class);
 		goto failed1;
 	}
 
@@ -1458,7 +1461,8 @@
 	if (ret)
 		goto failed2;
 
-	if (mdev_register_device(&mtty_dev.dev, &mdev_fops) != 0)
+	ret = mdev_register_device(&mtty_dev.dev, &mdev_fops);
+	if (ret)
 		goto failed3;
 
 	mutex_init(&mdev_list_lock);
diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
index 950fd2e..12262c0 100644
--- a/scripts/gcc-plugins/gcc-common.h
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -39,6 +39,9 @@
 #include "hash-map.h"
 #endif
 
+#if BUILDING_GCC_VERSION >= 7000
+#include "memmodel.h"
+#endif
 #include "emit-rtl.h"
 #include "debug.h"
 #include "target.h"
@@ -91,6 +94,9 @@
 #include "tree-ssa-alias.h"
 #include "tree-ssa.h"
 #include "stringpool.h"
+#if BUILDING_GCC_VERSION >= 7000
+#include "tree-vrp.h"
+#endif
 #include "tree-ssanames.h"
 #include "print-tree.h"
 #include "tree-eh.h"
@@ -287,6 +293,22 @@
 	return NULL;
 }
 
+static inline bool cgraph_for_node_and_aliases(cgraph_node_ptr node, bool (*callback)(cgraph_node_ptr, void *), void *data, bool include_overwritable)
+{
+	cgraph_node_ptr alias;
+
+	if (callback(node, data))
+		return true;
+
+	for (alias = node->same_body; alias; alias = alias->next) {
+		if (include_overwritable || cgraph_function_body_availability(alias) > AVAIL_OVERWRITABLE)
+			if (cgraph_for_node_and_aliases(alias, callback, data, include_overwritable))
+				return true;
+	}
+
+	return false;
+}
+
 #define FOR_EACH_FUNCTION_WITH_GIMPLE_BODY(node) \
 	for ((node) = cgraph_first_function_with_gimple_body(); (node); \
 		(node) = cgraph_next_function_with_gimple_body(node))
@@ -399,6 +421,7 @@
 typedef union gimple_statement_d gcall;
 typedef union gimple_statement_d gcond;
 typedef union gimple_statement_d gdebug;
+typedef union gimple_statement_d ggoto;
 typedef union gimple_statement_d gphi;
 typedef union gimple_statement_d greturn;
 
@@ -452,6 +475,16 @@
 	return stmt;
 }
 
+static inline ggoto *as_a_ggoto(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const ggoto *as_a_const_ggoto(const_gimple stmt)
+{
+	return stmt;
+}
+
 static inline gphi *as_a_gphi(gimple stmt)
 {
 	return stmt;
@@ -496,6 +529,14 @@
 
 typedef struct rtx_def rtx_insn;
 
+static inline const char *get_decl_section_name(const_tree decl)
+{
+	if (DECL_SECTION_NAME(decl) == NULL_TREE)
+		return NULL;
+
+	return TREE_STRING_POINTER(DECL_SECTION_NAME(decl));
+}
+
 static inline void set_decl_section_name(tree node, const char *value)
 {
 	if (value)
@@ -511,6 +552,7 @@
 typedef struct gimple_statement_call gcall;
 typedef struct gimple_statement_base gcond;
 typedef struct gimple_statement_base gdebug;
+typedef struct gimple_statement_base ggoto;
 typedef struct gimple_statement_phi gphi;
 typedef struct gimple_statement_base greturn;
 
@@ -564,6 +606,16 @@
 	return stmt;
 }
 
+static inline ggoto *as_a_ggoto(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const ggoto *as_a_const_ggoto(const_gimple stmt)
+{
+	return stmt;
+}
+
 static inline gphi *as_a_gphi(gimple stmt)
 {
 	return as_a<gphi>(stmt);
@@ -611,6 +663,11 @@
 
 #define INSN_DELETED_P(insn) (insn)->deleted()
 
+static inline const char *get_decl_section_name(const_tree decl)
+{
+	return DECL_SECTION_NAME(decl);
+}
+
 /* symtab/cgraph related */
 #define debug_cgraph_node(node) (node)->debug()
 #define cgraph_get_node(decl) cgraph_node::get(decl)
@@ -619,6 +676,7 @@
 #define cgraph_n_nodes symtab->cgraph_count
 #define cgraph_max_uid symtab->cgraph_max_uid
 #define varpool_get_node(decl) varpool_node::get(decl)
+#define dump_varpool_node(file, node) (node)->dump(file)
 
 #define cgraph_create_edge(caller, callee, call_stmt, count, freq, nest) \
 	(caller)->create_edge((callee), (call_stmt), (count), (freq))
@@ -674,6 +732,11 @@
 	return node->get_alias_target();
 }
 
+static inline bool cgraph_for_node_and_aliases(cgraph_node_ptr node, bool (*callback)(cgraph_node_ptr, void *), void *data, bool include_overwritable)
+{
+	return node->call_for_symbol_thunks_and_aliases(callback, data, include_overwritable);
+}
+
 static inline struct cgraph_node_hook_list *cgraph_add_function_insertion_hook(cgraph_node_hook hook, void *data)
 {
 	return symtab->add_cgraph_insertion_hook(hook, data);
@@ -731,6 +794,13 @@
 
 template <>
 template <>
+inline bool is_a_helper<const ggoto *>::test(const_gimple gs)
+{
+	return gs->code == GIMPLE_GOTO;
+}
+
+template <>
+template <>
 inline bool is_a_helper<const greturn *>::test(const_gimple gs)
 {
 	return gs->code == GIMPLE_RETURN;
@@ -766,6 +836,16 @@
 	return as_a<const gcall *>(stmt);
 }
 
+static inline ggoto *as_a_ggoto(gimple stmt)
+{
+	return as_a<ggoto *>(stmt);
+}
+
+static inline const ggoto *as_a_const_ggoto(const_gimple stmt)
+{
+	return as_a<const ggoto *>(stmt);
+}
+
 static inline gphi *as_a_gphi(gimple stmt)
 {
 	return as_a<gphi *>(stmt);
@@ -828,4 +908,9 @@
 #define debug_gimple_stmt(s) debug_gimple_stmt(CONST_CAST_GIMPLE(s))
 #endif
 
+#if BUILDING_GCC_VERSION >= 7000
+#define get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, preversep, pvolatilep, keep_aligning)	\
+	get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, preversep, pvolatilep)
+#endif
+
 #endif
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c
index 1254112..8ff203a 100644
--- a/scripts/gcc-plugins/latent_entropy_plugin.c
+++ b/scripts/gcc-plugins/latent_entropy_plugin.c
@@ -328,9 +328,9 @@
 			op = LROTATE_EXPR;
 			/*
 			 * This code limits the value of random_const to
-			 * the size of a wide int for the rotation
+			 * the size of a long for the rotation
 			 */
-			random_const &= HOST_BITS_PER_WIDE_INT - 1;
+			random_const %= TYPE_PRECISION(long_unsigned_type_node);
 			break;
 		}
 
diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c
index ee47924..827161b 100644
--- a/sound/firewire/fireworks/fireworks_stream.c
+++ b/sound/firewire/fireworks/fireworks_stream.c
@@ -117,7 +117,7 @@
 		conn = &efw->in_conn;
 
 	amdtp_stream_destroy(stream);
-	cmp_connection_destroy(&efw->out_conn);
+	cmp_connection_destroy(conn);
 }
 
 static int
diff --git a/sound/firewire/tascam/tascam-stream.c b/sound/firewire/tascam/tascam-stream.c
index 4ad3bd7..f1657a4 100644
--- a/sound/firewire/tascam/tascam-stream.c
+++ b/sound/firewire/tascam/tascam-stream.c
@@ -343,7 +343,7 @@
 	if (err < 0)
 		amdtp_stream_destroy(&tscm->rx_stream);
 
-	return 0;
+	return err;
 }
 
 /* At bus reset, streaming is stopped and some registers are clear. */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 9448daf..7d660ee 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2230,6 +2230,7 @@
 	SND_PCI_QUIRK(0x1043, 0x1971, "Asus W2JC", ALC882_FIXUP_ASUS_W2JC),
 	SND_PCI_QUIRK(0x1043, 0x835f, "Asus Eee 1601", ALC888_FIXUP_EEE1601),
 	SND_PCI_QUIRK(0x1043, 0x84bc, "ASUS ET2700", ALC887_FIXUP_ASUS_BASS),
+	SND_PCI_QUIRK(0x1043, 0x8691, "ASUS ROG Ranger VIII", ALC882_FIXUP_GPIO3),
 	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),
@@ -6983,6 +6984,7 @@
 	SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16),
 	SND_PCI_QUIRK(0x1043, 0x177d, "ASUS N551", ALC668_FIXUP_ASUS_Nx51),
 	SND_PCI_QUIRK(0x1043, 0x17bd, "ASUS N751", ALC668_FIXUP_ASUS_Nx51),
+	SND_PCI_QUIRK(0x1043, 0x1963, "ASUS X71SL", ALC662_FIXUP_ASUS_MODE8),
 	SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16),
 	SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_BASS_MODE4_CHMAP),
 	SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 15d1d5c..c90607e 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -384,6 +384,9 @@
 	if (unlikely(atomic_read(&ep->chip->shutdown)))
 		goto exit_clear;
 
+	if (unlikely(!test_bit(EP_FLAG_RUNNING, &ep->flags)))
+		goto exit_clear;
+
 	if (usb_pipeout(ep->pipe)) {
 		retire_outbound_urb(ep, ctx);
 		/* can be stopped during retire callback */
@@ -534,6 +537,11 @@
 			alive, ep->ep_num);
 	clear_bit(EP_FLAG_STOPPING, &ep->flags);
 
+	ep->data_subs = NULL;
+	ep->sync_slave = NULL;
+	ep->retire_data_urb = NULL;
+	ep->prepare_data_urb = NULL;
+
 	return 0;
 }
 
@@ -912,9 +920,7 @@
 /**
  * snd_usb_endpoint_start: start an snd_usb_endpoint
  *
- * @ep:		the endpoint to start
- * @can_sleep:	flag indicating whether the operation is executed in
- * 		non-atomic context
+ * @ep: the endpoint to start
  *
  * A call to this function will increment the use count of the endpoint.
  * In case it is not already running, the URBs for this endpoint will be
@@ -924,7 +930,7 @@
  *
  * Returns an error if the URB submission failed, 0 in all other cases.
  */
-int snd_usb_endpoint_start(struct snd_usb_endpoint *ep, bool can_sleep)
+int snd_usb_endpoint_start(struct snd_usb_endpoint *ep)
 {
 	int err;
 	unsigned int i;
@@ -938,8 +944,6 @@
 
 	/* just to be sure */
 	deactivate_urbs(ep, false);
-	if (can_sleep)
-		wait_clear_urbs(ep);
 
 	ep->active_mask = 0;
 	ep->unlink_mask = 0;
@@ -1020,10 +1024,6 @@
 
 	if (--ep->use_count == 0) {
 		deactivate_urbs(ep, false);
-		ep->data_subs = NULL;
-		ep->sync_slave = NULL;
-		ep->retire_data_urb = NULL;
-		ep->prepare_data_urb = NULL;
 		set_bit(EP_FLAG_STOPPING, &ep->flags);
 	}
 }
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 6428392..584f295 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -18,7 +18,7 @@
 				struct audioformat *fmt,
 				struct snd_usb_endpoint *sync_ep);
 
-int  snd_usb_endpoint_start(struct snd_usb_endpoint *ep, bool can_sleep);
+int  snd_usb_endpoint_start(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep);
 int  snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 34c6d4f..9aa5b18 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -218,7 +218,7 @@
 	}
 }
 
-static int start_endpoints(struct snd_usb_substream *subs, bool can_sleep)
+static int start_endpoints(struct snd_usb_substream *subs)
 {
 	int err;
 
@@ -231,7 +231,7 @@
 		dev_dbg(&subs->dev->dev, "Starting data EP @%p\n", ep);
 
 		ep->data_subs = subs;
-		err = snd_usb_endpoint_start(ep, can_sleep);
+		err = snd_usb_endpoint_start(ep);
 		if (err < 0) {
 			clear_bit(SUBSTREAM_FLAG_DATA_EP_STARTED, &subs->flags);
 			return err;
@@ -260,7 +260,7 @@
 		dev_dbg(&subs->dev->dev, "Starting sync EP @%p\n", ep);
 
 		ep->sync_slave = subs->data_endpoint;
-		err = snd_usb_endpoint_start(ep, can_sleep);
+		err = snd_usb_endpoint_start(ep);
 		if (err < 0) {
 			clear_bit(SUBSTREAM_FLAG_SYNC_EP_STARTED, &subs->flags);
 			return err;
@@ -850,7 +850,7 @@
 	/* for playback, submit the URBs now; otherwise, the first hwptr_done
 	 * updates for all URBs would happen at the same time when starting */
 	if (subs->direction == SNDRV_PCM_STREAM_PLAYBACK)
-		ret = start_endpoints(subs, true);
+		ret = start_endpoints(subs);
 
  unlock:
 	snd_usb_unlock_shutdown(subs->stream->chip);
@@ -1666,7 +1666,7 @@
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
-		err = start_endpoints(subs, false);
+		err = start_endpoints(subs);
 		if (err < 0)
 			return err;
 
diff --git a/usr/Makefile b/usr/Makefile
index 17a5132..0b87e71 100644
--- a/usr/Makefile
+++ b/usr/Makefile
@@ -5,8 +5,10 @@
 klibcdirs:;
 PHONY += klibcdirs
 
-suffix_y = $(CONFIG_INITRAMFS_COMPRESSION)
-AFLAGS_initramfs_data.o += -DINITRAMFS_IMAGE="usr/initramfs_data.cpio$(suffix_y)"
+suffix_y = $(subst $\",,$(CONFIG_INITRAMFS_COMPRESSION))
+datafile_y = initramfs_data.cpio$(suffix_y)
+AFLAGS_initramfs_data.o += -DINITRAMFS_IMAGE="usr/$(datafile_y)"
+
 
 # Generate builtin.o based on initramfs_data.o
 obj-$(CONFIG_BLK_DEV_INITRD) := initramfs_data.o
@@ -14,7 +16,7 @@
 # initramfs_data.o contains the compressed initramfs_data.cpio image.
 # The image is included using .incbin, a dependency which is not
 # tracked automatically.
-$(obj)/initramfs_data.o: $(obj)/initramfs_data.cpio$(suffix_y) FORCE
+$(obj)/initramfs_data.o: $(obj)/$(datafile_y) FORCE
 
 #####
 # Generate the initramfs cpio archive
@@ -38,10 +40,8 @@
 quiet_cmd_initfs = GEN     $@
       cmd_initfs = $(initramfs) -o $@ $(ramfs-args) $(ramfs-input)
 
-targets := initramfs_data.cpio.gz initramfs_data.cpio.bz2 \
-	initramfs_data.cpio.lzma initramfs_data.cpio.xz \
-	initramfs_data.cpio.lzo initramfs_data.cpio.lz4 \
-	initramfs_data.cpio
+targets := $(datafile_y)
+
 # do not try to update files included in initramfs
 $(deps_initramfs): ;
 
@@ -51,6 +51,6 @@
 # 2) There are changes in which files are included (added or deleted)
 # 3) If gen_init_cpio are newer than initramfs_data.cpio
 # 4) arguments to gen_initramfs.sh changes
-$(obj)/initramfs_data.cpio$(suffix_y): $(obj)/gen_init_cpio $(deps_initramfs) klibcdirs
+$(obj)/$(datafile_y): $(obj)/gen_init_cpio $(deps_initramfs) klibcdirs
 	$(Q)$(initramfs) -l $(ramfs-input) > $(obj)/.initramfs_data.cpio.d
 	$(call if_changed,initfs)