Merge tag 'v4.3-rc3' into x86/urgent, before applying dependent fix

Signed-off-by: Ingo Molnar <mingo@kernel.org>

434 files changed, 4956 insertions, 2576 deletions

diff --git a/Documentation/devicetree/bindings/arm/gic-v3.txt b/Documentation/devicetree/bindings/arm/gic-v3.txt
index ddfade40ac59..7803e77d85cb 100644
--- a/Documentation/devicetree/bindings/arm/gic-v3.txt
+++ b/Documentation/devicetree/bindings/arm/gic-v3.txt
@@ -57,6 +57,8 @@ used to route Message Signalled Interrupts (MSI) to the CPUs.
 These nodes must have the following properties:
 - compatible : Should at least contain  "arm,gic-v3-its".
 - msi-controller : Boolean property. Identifies the node as an MSI controller
+- #msi-cells: Must be <1>. The single msi-cell is the DeviceID of the device
+  which will generate the MSI.
 - reg: Specifies the base physical address and size of the ITS
   registers.
 
@@ -83,6 +85,7 @@ Examples:
 		gic-its@2c200000 {
 			compatible = "arm,gic-v3-its";
 			msi-controller;
+			#msi-cells = <1>;
 			reg = <0x0 0x2c200000 0 0x200000>;
 		};
 	};
@@ -107,12 +110,14 @@ Examples:
 		gic-its@2c200000 {
 			compatible = "arm,gic-v3-its";
 			msi-controller;
+			#msi-cells = <1>;
 			reg = <0x0 0x2c200000 0 0x200000>;
 		};
 
 		gic-its@2c400000 {
 			compatible = "arm,gic-v3-its";
 			msi-controller;
+			#msi-cells = <1>;
 			reg = <0x0 0x2c400000 0 0x200000>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/arm/idle-states.txt b/Documentation/devicetree/bindings/arm/idle-states.txt
index a8274eabae2e..b8e41c148a3c 100644
--- a/Documentation/devicetree/bindings/arm/idle-states.txt
+++ b/Documentation/devicetree/bindings/arm/idle-states.txt
@@ -497,7 +497,7 @@ cpus {
 	};
 
 	idle-states {
-		entry-method = "arm,psci";
+		entry-method = "psci";
 
 		CPU_RETENTION_0_0: cpu-retention-0-0 {
 			compatible = "arm,idle-state";
diff --git a/Documentation/devicetree/bindings/gpio/gpio.txt b/Documentation/devicetree/bindings/gpio/gpio.txt
index 5788d5cf1252..82d40e2505f6 100644
--- a/Documentation/devicetree/bindings/gpio/gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio.txt
@@ -16,7 +16,9 @@ properties, each containing a 'gpio-list':
 GPIO properties should be named "[<name>-]gpios", with <name> being the purpose
 of this GPIO for the device. While a non-existent <name> is considered valid
 for compatibility reasons (resolving to the "gpios" property), it is not allowed
-for new bindings.
+for new bindings. Also, GPIO properties named "[<name>-]gpio" are valid and old
+bindings use it, but are only supported for compatibility reasons and should not
+be used for newer bindings since it has been deprecated.
 
 GPIO properties can contain one or more GPIO phandles, but only in exceptional
 cases should they contain more than one. If your device uses several GPIOs with
diff --git a/Documentation/devicetree/bindings/iio/accel/bma180.txt b/Documentation/devicetree/bindings/iio/accel/bma180.txt
index c5933573e0f6..4a3679d54457 100644
--- a/Documentation/devicetree/bindings/iio/accel/bma180.txt
+++ b/Documentation/devicetree/bindings/iio/accel/bma180.txt
@@ -1,10 +1,11 @@
-* Bosch BMA180 triaxial acceleration sensor
+* Bosch BMA180 / BMA250 triaxial acceleration sensor
 
 http://omapworld.com/BMA180_111_1002839.pdf
+http://ae-bst.resource.bosch.com/media/products/dokumente/bma250/bst-bma250-ds002-05.pdf
 
 Required properties:
 
-  - compatible : should be "bosch,bma180"
+  - compatible : should be "bosch,bma180" or "bosch,bma250"
   - reg : the I2C address of the sensor
 
 Optional properties:
@@ -13,6 +14,9 @@ Optional properties:
 
   - interrupts : interrupt mapping for GPIO IRQ, it should by configured with
 		flags IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_EDGE_RISING
+		For the bma250 the first interrupt listed must be the one
+		connected to the INT1 pin, the second (optional) interrupt
+		listed must be the one connected to the INT2 pin.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
index d8ef5bf50f11..7fab84b33531 100644
--- a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
+++ b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
@@ -7,7 +7,8 @@ OHCI and EHCI controllers.
 
 Required properties:
 - compatible: "renesas,pci-r8a7790" for the R8A7790 SoC;
-	      "renesas,pci-r8a7791" for the R8A7791 SoC.
+	      "renesas,pci-r8a7791" for the R8A7791 SoC;
+	      "renesas,pci-r8a7794" for the R8A7794 SoC.
 - reg:	A list of physical regions to access the device: the first is
 	the operational registers for the OHCI/EHCI controllers and the
 	second is for the bridge configuration and control registers.
diff --git a/Documentation/devicetree/bindings/regulator/pbias-regulator.txt b/Documentation/devicetree/bindings/regulator/pbias-regulator.txt
index 32aa26f1e434..acbcb452a69a 100644
--- a/Documentation/devicetree/bindings/regulator/pbias-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/pbias-regulator.txt
@@ -2,7 +2,12 @@ PBIAS internal regulator for SD card dual voltage i/o pads on OMAP SoCs.
 
 Required properties:
 - compatible:
-  - "ti,pbias-omap" for OMAP2, OMAP3, OMAP4, OMAP5, DRA7.
+  - should be "ti,pbias-dra7" for DRA7
+  - should be "ti,pbias-omap2" for OMAP2
+  - should be "ti,pbias-omap3" for OMAP3
+  - should be "ti,pbias-omap4" for OMAP4
+  - should be "ti,pbias-omap5" for OMAP5
+  - "ti,pbias-omap" is deprecated
 - reg: pbias register offset from syscon base and size of pbias register.
 - syscon : phandle of the system control module
 - regulator-name : should be
diff --git a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
index dcefc438272f..6160ffbcb3d3 100644
--- a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
+++ b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
@@ -15,17 +15,18 @@ Required properties:
 - interrupts: Should contain spi interrupt
 
 - clocks: phandles to input clocks.
-  The first should be <&topckgen CLK_TOP_SPI_SEL>.
-  The second should be one of the following.
+  The first should be one of the following. It's PLL.
    -  <&clk26m>: specify parent clock 26MHZ.
    -  <&topckgen CLK_TOP_SYSPLL3_D2>: specify parent clock 109MHZ.
 				      It's the default one.
    -  <&topckgen CLK_TOP_SYSPLL4_D2>: specify parent clock 78MHZ.
    -  <&topckgen CLK_TOP_UNIVPLL2_D4>: specify parent clock 104MHZ.
    -  <&topckgen CLK_TOP_UNIVPLL1_D8>: specify parent clock 78MHZ.
+  The second should be <&topckgen CLK_TOP_SPI_SEL>. It's clock mux.
+  The third is <&pericfg CLK_PERI_SPI0>. It's clock gate.
 
-- clock-names: shall be "spi-clk" for the controller clock, and
-  "parent-clk" for the parent clock.
+- clock-names: shall be "parent-clk" for the parent clock, "sel-clk" for the
+  muxes clock, and "spi-clk" for the clock gate.
 
 Optional properties:
 - mediatek,pad-select: specify which pins group(ck/mi/mo/cs) spi
@@ -44,8 +45,11 @@ spi: spi@1100a000 {
 	#size-cells = <0>;
 	reg = <0 0x1100a000 0 0x1000>;
 	interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_LOW>;
-	clocks = <&topckgen CLK_TOP_SPI_SEL>, <&topckgen CLK_TOP_SYSPLL3_D2>;
-	clock-names = "spi-clk", "parent-clk";
+	clocks = <&topckgen CLK_TOP_SYSPLL3_D2>,
+		 <&topckgen CLK_TOP_SPI_SEL>,
+		 <&pericfg CLK_PERI_SPI0>;
+	clock-names = "parent-clk", "sel-clk", "spi-clk";
+
 	mediatek,pad-select = <0>;
 	status = "disabled";
 };
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
index 8a49362dea6e..41b817f7b670 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -55,19 +55,11 @@ of heat dissipation). For example a fan's cooling states correspond to
 the different fan speeds possible. Cooling states are referred to by
 single unsigned integers, where larger numbers mean greater heat
 dissipation. The precise set of cooling states associated with a device
-(as referred to be the cooling-min-state and cooling-max-state
+(as referred to by the cooling-min-level and cooling-max-level
 properties) should be defined in a particular device's binding.
 For more examples of cooling devices, refer to the example sections below.
 
 Required properties:
-- cooling-min-state:	An integer indicating the smallest
-  Type: unsigned	cooling state accepted. Typically 0.
-  Size: one cell
-
-- cooling-max-state:	An integer indicating the largest
-  Type: unsigned	cooling state accepted.
-  Size: one cell
-
 - #cooling-cells:	Used to provide cooling device specific information
   Type: unsigned	while referring to it. Must be at least 2, in order
   Size: one cell      	to specify minimum and maximum cooling state used
@@ -77,6 +69,15 @@ Required properties:
 			See Cooling device maps section below for more details
 			on how consumers refer to cooling devices.
 
+Optional properties:
+- cooling-min-level:	An integer indicating the smallest
+  Type: unsigned	cooling state accepted. Typically 0.
+  Size: one cell
+
+- cooling-max-level:	An integer indicating the largest
+  Type: unsigned	cooling state accepted.
+  Size: one cell
+
 * Trip points
 
 The trip node is a node to describe a point in the temperature domain
@@ -225,8 +226,8 @@ cpus {
 			396000  950000
 			198000  850000
 		>;
-		cooling-min-state = <0>;
-		cooling-max-state = <3>;
+		cooling-min-level = <0>;
+		cooling-max-level = <3>;
 		#cooling-cells = <2>; /* min followed by max */
 	};
 	...
@@ -240,8 +241,8 @@ cpus {
 	 */
 	fan0: fan@0x48 {
 		...
-		cooling-min-state = <0>;
-		cooling-max-state = <9>;
+		cooling-min-level = <0>;
+		cooling-max-level = <9>;
 		#cooling-cells = <2>; /* min followed by max */
 	};
 };
diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
index d71ef07bca5d..a057b75ba4b5 100644
--- a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
+++ b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
@@ -6,6 +6,7 @@ Required properties:
 	"lsi,zevio-usb"
 	"qcom,ci-hdrc"
 	"chipidea,usb2"
+	"xlnx,zynq-usb-2.20a"
 - reg: base address and length of the registers
 - interrupts: interrupt for the USB controller
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index ac5f0c34ae00..82d2ac97af74 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -203,6 +203,7 @@ sitronix	Sitronix Technology Corporation
 skyworks	Skyworks Solutions, Inc.
 smsc	Standard Microsystems Corporation
 snps	Synopsys, Inc.
+socionext	Socionext Inc.
 solidrun	SolidRun
 solomon        Solomon Systech Limited
 sony	Sony Corporation
diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
new file mode 100644
index 000000000000..031ef4a63485
--- /dev/null
+++ b/Documentation/networking/vrf.txt
@@ -0,0 +1,96 @@
+Virtual Routing and Forwarding (VRF)
+====================================
+The VRF device combined with ip rules provides the ability to create virtual
+routing and forwarding domains (aka VRFs, VRF-lite to be specific) in the
+Linux network stack. One use case is the multi-tenancy problem where each
+tenant has their own unique routing tables and in the very least need
+different default gateways.
+
+Processes can be "VRF aware" by binding a socket to the VRF device. Packets
+through the socket then use the routing table associated with the VRF
+device. An important feature of the VRF device implementation is that it
+impacts only Layer 3 and above so L2 tools (e.g., LLDP) are not affected
+(ie., they do not need to be run in each VRF). The design also allows
+the use of higher priority ip rules (Policy Based Routing, PBR) to take
+precedence over the VRF device rules directing specific traffic as desired.
+
+In addition, VRF devices allow VRFs to be nested within namespaces. For
+example network namespaces provide separation of network interfaces at L1
+(Layer 1 separation), VLANs on the interfaces within a namespace provide
+L2 separation and then VRF devices provide L3 separation.
+
+Design
+------
+A VRF device is created with an associated route table. Network interfaces
+are then enslaved to a VRF device:
+
+         +-----------------------------+
+         |           vrf-blue          |  ===> route table 10
+         +-----------------------------+
+            |        |            |
+         +------+ +------+     +-------------+
+         | eth1 | | eth2 | ... |    bond1    |
+         +------+ +------+     +-------------+
+                                  |       |
+                              +------+ +------+
+                              | eth8 | | eth9 |
+                              +------+ +------+
+
+Packets received on an enslaved device and are switched to the VRF device
+using an rx_handler which gives the impression that packets flow through
+the VRF device. Similarly on egress routing rules are used to send packets
+to the VRF device driver before getting sent out the actual interface. This
+allows tcpdump on a VRF device to capture all packets into and out of the
+VRF as a whole.[1] Similiarly, netfilter [2] and tc rules can be applied
+using the VRF device to specify rules that apply to the VRF domain as a whole.
+
+[1] Packets in the forwarded state do not flow through the device, so those
+    packets are not seen by tcpdump. Will revisit this limitation in a
+    future release.
+
+[2] Iptables on ingress is limited to NF_INET_PRE_ROUTING only with skb->dev
+    set to real ingress device and egress is limited to NF_INET_POST_ROUTING.
+    Will revisit this limitation in a future release.
+
+
+Setup
+-----
+1. VRF device is created with an association to a FIB table.
+   e.g, ip link add vrf-blue type vrf table 10
+        ip link set dev vrf-blue up
+
+2. Rules are added that send lookups to the associated FIB table when the
+   iif or oif is the VRF device. e.g.,
+       ip ru add oif vrf-blue table 10
+       ip ru add iif vrf-blue table 10
+
+   Set the default route for the table (and hence default route for the VRF).
+   e.g, ip route add table 10 prohibit default
+
+3. Enslave L3 interfaces to a VRF device.
+   e.g,  ip link set dev eth1 master vrf-blue
+
+   Local and connected routes for enslaved devices are automatically moved to
+   the table associated with VRF device. Any additional routes depending on
+   the enslaved device will need to be reinserted following the enslavement.
+
+4. Additional VRF routes are added to associated table.
+   e.g., ip route add table 10 ...
+
+
+Applications
+------------
+Applications that are to work within a VRF need to bind their socket to the
+VRF device:
+
+    setsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, dev, strlen(dev)+1);
+
+or to specify the output device using cmsg and IP_PKTINFO.
+
+
+Limitations
+-----------
+VRF device currently only works for IPv4. Support for IPv6 is under development.
+
+Index of original ingress interface is not available via cmsg. Will address
+soon.
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 6294b5186ae5..809ab6efcc74 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -54,13 +54,15 @@ default_qdisc
 --------------
 
 The default queuing discipline to use for network devices. This allows
-overriding the default queue discipline of pfifo_fast with an
-alternative. Since the default queuing discipline is created with the
-no additional parameters so is best suited to queuing disciplines that
-work well without configuration like stochastic fair queue (sfq),
-CoDel (codel) or fair queue CoDel (fq_codel). Don't use queuing disciplines
-like Hierarchical Token Bucket or Deficit Round Robin which require setting
-up classes and bandwidths.
+overriding the default of pfifo_fast with an alternative. Since the default
+queuing discipline is created without additional parameters so is best suited
+to queuing disciplines that work well without configuration like stochastic
+fair queue (sfq), CoDel (codel) or fair queue CoDel (fq_codel). Don't use
+queuing disciplines like Hierarchical Token Bucket or Deficit Round Robin
+which require setting up classes and bandwidths. Note that physical multiqueue
+interfaces still use mq as root qdisc, which in turn uses this default for its
+leaves. Virtual devices (like e.g. lo or veth) ignore this setting and instead
+default to noqueue.
 Default: pfifo_fast
 
 busy_read
diff --git a/Documentation/thermal/power_allocator.txt b/Documentation/thermal/power_allocator.txt
index c3797b529991..a1ce2235f121 100644
--- a/Documentation/thermal/power_allocator.txt
+++ b/Documentation/thermal/power_allocator.txt
@@ -4,7 +4,7 @@ Power allocator governor tunables
 Trip points
 -----------
 
-The governor requires the following two passive trip points:
+The governor works optimally with the following two passive trip points:
 
 1.  "switch on" trip point: temperature above which the governor
     control loop starts operating.  This is the first passive trip
diff --git a/MAINTAINERS b/MAINTAINERS
index 274f85405584..9f6685f6c5a9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -615,9 +615,8 @@ F:	Documentation/hwmon/fam15h_power
 F:	drivers/hwmon/fam15h_power.c
 
 AMD GEODE CS5536 USB DEVICE CONTROLLER DRIVER
-M:	Thomas Dahlmann <dahlmann.thomas@arcor.de>
 L:	linux-geode@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Orphan
 F:	drivers/usb/gadget/udc/amd5536udc.*
 
 AMD GEODE PROCESSOR/CHIPSET SUPPORT
@@ -808,6 +807,13 @@ S:	Maintained
 F:	drivers/video/fbdev/arcfb.c
 F:	drivers/video/fbdev/core/fb_defio.c
 
+ARCNET NETWORK LAYER
+M:	Michael Grzeschik <m.grzeschik@pengutronix.de>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/arcnet/
+F:	include/uapi/linux/if_arcnet.h
+
 ARM MFM AND FLOPPY DRIVERS
 M:	Ian Molton <spyro@f2s.com>
 S:	Maintained
@@ -3394,7 +3400,6 @@ F:	drivers/staging/dgnc/
 
 DIGI EPCA PCI PRODUCTS
 M:	Lidza Louina <lidza.louina@gmail.com>
-M:	Mark Hounschell <markh@compro.net>
 M:	Daeseok Youn <daeseok.youn@gmail.com>
 L:	driverdev-devel@linuxdriverproject.org
 S:	Maintained
@@ -8500,7 +8505,6 @@ F:	Documentation/networking/LICENSE.qla3xxx
 F:	drivers/net/ethernet/qlogic/qla3xxx.*
 
 QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M:	Shahed Shaikh <shahed.shaikh@qlogic.com>
 M:	Dept-GELinuxNICDev@qlogic.com
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -9904,8 +9908,8 @@ F:	drivers/staging/media/lirc/
 STAGING - LUSTRE PARALLEL FILESYSTEM
 M:	Oleg Drokin <oleg.drokin@intel.com>
 M:	Andreas Dilger <andreas.dilger@intel.com>
-L:	HPDD-discuss@lists.01.org (moderated for non-subscribers)
-W:	http://lustre.opensfs.org/
+L:	lustre-devel@lists.lustre.org (moderated for non-subscribers)
+W:	http://wiki.lustre.org/
 S:	Maintained
 F:	drivers/staging/lustre
 
@@ -10338,6 +10342,16 @@ F:	include/uapi/linux/thermal.h
 F:	include/linux/cpu_cooling.h
 F:	Documentation/devicetree/bindings/thermal/
 
+THERMAL/CPU_COOLING
+M:	Amit Daniel Kachhap <amit.kachhap@gmail.com>
+M:	Viresh Kumar <viresh.kumar@linaro.org>
+M:	Javi Merino <javi.merino@arm.com>
+L:	linux-pm@vger.kernel.org
+S:	Supported
+F:	Documentation/thermal/cpu-cooling-api.txt
+F:	drivers/thermal/cpu_cooling.c
+F:	include/linux/cpu_cooling.h
+
 THINGM BLINK(1) USB RGB LED DRIVER
 M:	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
 S:	Maintained
@@ -11187,7 +11201,7 @@ F:	drivers/vlynq/vlynq.c
 F:	include/linux/vlynq.h
 
 VME SUBSYSTEM
-M:	Martyn Welch <martyn.welch@ge.com>
+M:	Martyn Welch <martyn@welchs.me.uk>
 M:	Manohar Vanga <manohar.vanga@gmail.com>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	devel@driverdev.osuosl.org
@@ -11239,7 +11253,6 @@ VOLTAGE AND CURRENT REGULATOR FRAMEWORK
 M:	Liam Girdwood <lgirdwood@gmail.com>
 M:	Mark Brown <broonie@kernel.org>
 L:	linux-kernel@vger.kernel.org
-W:	http://opensource.wolfsonmicro.com/node/15
 W:	http://www.slimlogic.co.uk/?p=48
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator.git
 S:	Supported
@@ -11253,6 +11266,7 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/vrf.c
 F:	include/net/vrf.h
+F:	Documentation/networking/vrf.txt
 
 VT1211 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
@@ -11368,17 +11382,15 @@ WM97XX TOUCHSCREEN DRIVERS
 M:	Mark Brown <broonie@kernel.org>
 M:	Liam Girdwood <lrg@slimlogic.co.uk>
 L:	linux-input@vger.kernel.org
-T:	git git://opensource.wolfsonmicro.com/linux-2.6-touch
-W:	http://opensource.wolfsonmicro.com/node/7
+W:	https://github.com/CirrusLogic/linux-drivers/wiki
 S:	Supported
 F:	drivers/input/touchscreen/*wm97*
 F:	include/linux/wm97xx.h
 
 WOLFSON MICROELECTRONICS DRIVERS
 L:	patches@opensource.wolfsonmicro.com
-T:	git git://opensource.wolfsonmicro.com/linux-2.6-asoc
-T:	git git://opensource.wolfsonmicro.com/linux-2.6-audioplus
-W:	http://opensource.wolfsonmicro.com/content/linux-drivers-wolfson-devices
+T:	git https://github.com/CirrusLogic/linux-drivers.git
+W:	https://github.com/CirrusLogic/linux-drivers/wiki
 S:	Supported
 F:	Documentation/hwmon/wm83??
 F:	arch/arm/mach-s3c64xx/mach-crag6410*
diff --git a/Makefile b/Makefile
index 84f4b31e3c6e..1d341eba143d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 3
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index cded02c890aa..5f387ee5b5c5 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -242,7 +242,12 @@ pci_restore_srm_config(void)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	struct pci_dev *dev;
+	struct pci_dev *dev = bus->self;
+
+	if (pci_has_flag(PCI_PROBE_ONLY) && dev &&
+	    (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		pci_read_bridge_bases(bus);
+	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		pdev_save_srm_config(dev);
diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi
index 4d28fc3aac69..5dd084f3c81c 100644
--- a/arch/arm/boot/dts/am335x-phycore-som.dtsi
+++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi
@@ -252,10 +252,10 @@
 		};
 
 		vdd1_reg: regulator@2 {
-			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
+			/* VDD_MPU voltage limits 0.95V - 1.325V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <912500>;
-			regulator-max-microvolt = <1312500>;
+			regulator-max-microvolt = <1378000>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 3a05b94f59ed..568adf5efde0 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -98,13 +98,6 @@
 		pinctrl-0 = <&extcon_usb1_pins>;
 	};
 
-	extcon_usb2: extcon_usb2 {
-		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&gpio7 24 GPIO_ACTIVE_HIGH>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&extcon_usb2_pins>;
-	};
-
 	hdmi0: connector {
 		compatible = "hdmi-connector";
 		label = "hdmi";
@@ -326,12 +319,6 @@
 		>;
 	};
 
-	extcon_usb2_pins: extcon_usb2_pins {
-		pinctrl-single,pins = <
-			0x3e8 (PIN_INPUT_PULLUP | MUX_MODE14) /* uart1_ctsn.gpio7_24 */
-		>;
-	};
-
 	tpd12s015_pins: pinmux_tpd12s015_pins {
 		pinctrl-single,pins = <
 			0x3b0 (PIN_OUTPUT | MUX_MODE14)		/* gpio7_10 CT_CP_HPD */
@@ -432,7 +419,7 @@
 				};
 
 				ldo3_reg: ldo3 {
-					/* VDDA_1V8_PHY */
+					/* VDDA_1V8_PHYA */
 					regulator-name = "ldo3";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -440,6 +427,15 @@
 					regulator-boot-on;
 				};
 
+				ldo4_reg: ldo4 {
+					/* VDDA_1V8_PHYB */
+					regulator-name = "ldo4";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-boot-on;
+				};
+
 				ldo9_reg: ldo9 {
 					/* VDD_RTC */
 					regulator-name = "ldo9";
@@ -495,6 +491,14 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 		};
+
+		extcon_usb2: tps659038_usb {
+			compatible = "ti,palmas-usb-vid";
+			ti,enable-vbus-detection;
+			ti,enable-id-detection;
+			id-gpios = <&gpio7 24 GPIO_ACTIVE_HIGH>;
+		};
+
 	};
 
 	tmp102: tmp102@48 {
@@ -517,7 +521,8 @@
 	mcp_rtc: rtc@6f {
 		compatible = "microchip,mcp7941x";
 		reg = <0x6f>;
-		interrupts = <GIC_SPI 2 IRQ_TYPE_EDGE_RISING>;  /* IRQ_SYS_1N */
+		interrupts-extended = <&crossbar_mpu GIC_SPI 2 IRQ_TYPE_EDGE_RISING>,
+				      <&dra7_pmx_core 0x424>;
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&mcp79410_pins_default>;
@@ -579,7 +584,6 @@
 	pinctrl-0 = <&mmc1_pins_default>;
 
 	vmmc-supply = <&ldo1_reg>;
-	vmmc_aux-supply = <&vdd_3v3>;
 	bus-width = <4>;
 	cd-gpios = <&gpio6 27 0>; /* gpio 219 */
 };
@@ -623,6 +627,14 @@
 };
 
 &usb2 {
+	/*
+	 * Stand alone usage is peripheral only.
+	 * However, with some resistor modifications
+	 * this port can be used via expansion connectors
+	 * as "host" or "dual-role". If so, provide
+	 * the necessary dr_mode override in the expansion
+	 * board's DT.
+	 */
 	dr_mode = "peripheral";
 };
 
@@ -681,7 +693,7 @@
 
 &hdmi {
 	status = "ok";
-	vdda-supply = <&ldo3_reg>;
+	vdda-supply = <&ldo4_reg>;
 
 	pinctrl-names = "default";
 	pinctrl-0 = <&hdmi_pins>;
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index 92bacd3c8fab..109fd4711647 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -19,10 +19,10 @@
 
 &cpsw_emac0 {
 	phy_id = <&davinci_mdio>, <0>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
 
 &cpsw_emac1 {
 	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 8c4bbc7573df..79838dd8dee7 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -8,7 +8,7 @@
 #include "dm814x.dtsi"
 
 / {
-	model = "DM8148 EVM";
+	model = "HP t410 Smart Zero Client";
 	compatible = "hp,t410", "ti,dm8148";
 
 	memory {
@@ -19,10 +19,10 @@
 
 &cpsw_emac0 {
 	phy_id = <&davinci_mdio>, <0>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
 
 &cpsw_emac1 {
 	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index 972c9c9e885b..7988b42e5764 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -181,9 +181,9 @@
 				ti,hwmods = "timer3";
 			};
 
-			control: control@160000 {
+			control: control@140000 {
 				compatible = "ti,dm814-scm", "simple-bus";
-				reg = <0x160000 0x16d000>;
+				reg = <0x140000 0x16d000>;
 				#address-cells = <1>;
 				#size-cells = <1>;
 				ranges = <0 0x160000 0x16d000>;
@@ -321,9 +321,9 @@
 				mac-address = [ 00 00 00 00 00 00 ];
 			};
 
-			phy_sel: cpsw-phy-sel@0x48160650 {
+			phy_sel: cpsw-phy-sel@48140650 {
 				compatible = "ti,am3352-cpsw-phy-sel";
-				reg= <0x48160650 0x4>;
+				reg= <0x48140650 0x4>;
 				reg-names = "gmii-sel";
 			};
 		};
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 5d65db9ebc2b..e289c706d27d 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -120,9 +120,10 @@
 					reg = <0x0 0x1400>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x0 0x1400>;
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-dra7", "ti,pbias-omap";
 						reg = <0xe00 0x4>;
 						syscon = <&scm_conf>;
 						pbias_mmc_reg: pbias_mmc_omap5 {
@@ -1417,7 +1418,7 @@
 			ti,irqs-safe-map = <0>;
 		};
 
-		mac: ethernet@4a100000 {
+		mac: ethernet@48484000 {
 			compatible = "ti,dra7-cpsw","ti,cpsw";
 			ti,hwmods = "gmac";
 			clocks = <&dpll_gmac_ck>, <&gmac_gmii_ref_clk_div>;
diff --git a/arch/arm/boot/dts/omap2430.dtsi b/arch/arm/boot/dts/omap2430.dtsi
index 2390f387c271..798dda072b2a 100644
--- a/arch/arm/boot/dts/omap2430.dtsi
+++ b/arch/arm/boot/dts/omap2430.dtsi
@@ -56,6 +56,7 @@
 					reg = <0x270 0x240>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x270 0x240>;
 
 					scm_clocks: clocks {
 						#address-cells = <1>;
@@ -63,7 +64,7 @@
 					};
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-omap2", "ti,pbias-omap";
 						reg = <0x230 0x4>;
 						syscon = <&scm_conf>;
 						pbias_mmc_reg: pbias_mmc_omap2430 {
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
index a5474113cd50..67659a0ed13e 100644
--- a/arch/arm/boot/dts/omap3-beagle.dts
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -202,7 +202,7 @@
 
 	tfp410_pins: pinmux_tfp410_pins {
 		pinctrl-single,pins = <
-			0x194 (PIN_OUTPUT | MUX_MODE4)	/* hdq_sio.gpio_170 */
+			0x196 (PIN_OUTPUT | MUX_MODE4)	/* hdq_sio.gpio_170 */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index d5e5cd449b16..2230e1c03320 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -78,12 +78,6 @@
 		>;
 	};
 
-	smsc9221_pins: pinmux_smsc9221_pins {
-		pinctrl-single,pins = <
-			0x1a2 (PIN_INPUT | MUX_MODE4)		/* mcspi1_cs2.gpio_176 */
-		>;
-	};
-
 	i2c1_pins: pinmux_i2c1_pins {
 		pinctrl-single,pins = <
 			0x18a (PIN_INPUT | MUX_MODE0)   /* i2c1_scl.i2c1_scl */
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index e458c2185e3c..5ad688c57a00 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -156,6 +156,12 @@
 			OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0)	/* uart2_rx.uart2_rx */
 		>;
 	};
+
+	smsc9221_pins: pinmux_smsc9221_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21d2, PIN_INPUT | MUX_MODE4)	/* mcspi1_cs2.gpio_176 */
+		>;
+	};
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 69a40cfc1f29..8a2b25332b8c 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -113,10 +113,22 @@
 				};
 
 				scm_conf: scm_conf@270 {
-					compatible = "syscon";
+					compatible = "syscon", "simple-bus";
 					reg = <0x270 0x330>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x270 0x330>;
+
+					pbias_regulator: pbias_regulator {
+						compatible = "ti,pbias-omap3", "ti,pbias-omap";
+						reg = <0x2b0 0x4>;
+						syscon = <&scm_conf>;
+						pbias_mmc_reg: pbias_mmc_omap2430 {
+							regulator-name = "pbias_mmc_omap2430";
+							regulator-min-microvolt = <1800000>;
+							regulator-max-microvolt = <3000000>;
+						};
+					};
 
 					scm_clocks: clocks {
 						#address-cells = <1>;
@@ -202,17 +214,6 @@
 			dma-requests = <96>;
 		};
 
-		pbias_regulator: pbias_regulator {
-			compatible = "ti,pbias-omap";
-			reg = <0x2b0 0x4>;
-			syscon = <&scm_conf>;
-			pbias_mmc_reg: pbias_mmc_omap2430 {
-				regulator-name = "pbias_mmc_omap2430";
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3000000>;
-			};
-		};
-
 		gpio1: gpio@48310000 {
 			compatible = "ti,omap3-gpio";
 			reg = <0x48310000 0x200>;
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index abc4473e6f8a..5a206c100ce2 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -196,9 +196,10 @@
 					reg = <0x5a0 0x170>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x5a0 0x170>;
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-omap4", "ti,pbias-omap";
 						reg = <0x60 0x4>;
 						syscon = <&omap4_padconf_global>;
 						pbias_mmc_reg: pbias_mmc_omap4 {
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 3cc8f357d5b8..3cb030f9d2c4 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -174,8 +174,8 @@
 
 	i2c5_pins: pinmux_i2c5_pins {
 		pinctrl-single,pins = <
-			0x184 (PIN_INPUT | MUX_MODE0)		/* i2c5_scl */
-			0x186 (PIN_INPUT | MUX_MODE0)		/* i2c5_sda */
+			0x186 (PIN_INPUT | MUX_MODE0)		/* i2c5_scl */
+			0x188 (PIN_INPUT | MUX_MODE0)		/* i2c5_sda */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 4205a8ac9ddb..4c04389dab32 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -185,9 +185,10 @@
 					reg = <0x5a0 0xec>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x5a0 0xec>;
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-omap5", "ti,pbias-omap";
 						reg = <0x60 0x4>;
 						syscon = <&omap5_padconf_global>;
 						pbias_mmc_reg: pbias_mmc_omap5 {
diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi
index 2fa7a0dc83f7..275c78ccc0f3 100644
--- a/arch/arm/boot/dts/rk3288-veyron.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron.dtsi
@@ -158,6 +158,7 @@
 };
 
 &hdmi {
+	ddc-i2c-bus = <&i2c5>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/stih407.dtsi b/arch/arm/boot/dts/stih407.dtsi
index 3efa3b2ebe90..6b914e4bb099 100644
--- a/arch/arm/boot/dts/stih407.dtsi
+++ b/arch/arm/boot/dts/stih407.dtsi
@@ -103,48 +103,46 @@
 							 <&clk_s_d0_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>;
-				ranges;
-
-				sti-hdmi@8d04000 {
-					compatible = "st,stih407-hdmi";
-					reg = <0x8d04000 0x1000>;
-					reg-names = "hdmi-reg";
-					interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
-					interrupt-names	= "irq";
-					clock-names = "pix",
-						      "tmds",
-						      "phy",
-						      "audio",
-						      "main_parent",
-						      "aux_parent";
-
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
-						 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
-						 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
-						 <&clk_s_d0_flexgen CLK_PCM_0>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-
-					hdmi,hpd-gpio = <&pio5 3>;
-					reset-names = "hdmi";
-					resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
-					ddc = <&hdmiddc>;
-
-				};
-
-				sti-hda@8d02000 {
-					compatible = "st,stih407-hda";
-					reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
-					reg-names = "hda-reg", "video-dacs-ctrl";
-					clock-names = "pix",
-						      "hddac",
-						      "main_parent",
-						      "aux_parent";
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
-						 <&clk_s_d2_flexgen CLK_HDDAC>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-				};
+			};
+
+			sti-hdmi@8d04000 {
+				compatible = "st,stih407-hdmi";
+				reg = <0x8d04000 0x1000>;
+				reg-names = "hdmi-reg";
+				interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
+				interrupt-names	= "irq";
+				clock-names = "pix",
+					      "tmds",
+					      "phy",
+					      "audio",
+					      "main_parent",
+					      "aux_parent";
+
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
+					 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
+					 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
+					 <&clk_s_d0_flexgen CLK_PCM_0>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
+
+				hdmi,hpd-gpio = <&pio5 3>;
+				reset-names = "hdmi";
+				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
+				ddc = <&hdmiddc>;
+			};
+
+			sti-hda@8d02000 {
+				compatible = "st,stih407-hda";
+				reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
+				reg-names = "hda-reg", "video-dacs-ctrl";
+				clock-names = "pix",
+					      "hddac",
+					      "main_parent",
+					      "aux_parent";
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
+					 <&clk_s_d2_flexgen CLK_HDDAC>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index 6f40bc99c22f..8c6e61a27234 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -178,48 +178,46 @@
 							 <&clk_s_d0_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>;
-				ranges;
-
-				sti-hdmi@8d04000 {
-					compatible = "st,stih407-hdmi";
-					reg = <0x8d04000 0x1000>;
-					reg-names = "hdmi-reg";
-					interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
-					interrupt-names	= "irq";
-					clock-names = "pix",
-						      "tmds",
-						      "phy",
-						      "audio",
-						      "main_parent",
-						      "aux_parent";
-
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
-						 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
-						 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
-						 <&clk_s_d0_flexgen CLK_PCM_0>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-
-					hdmi,hpd-gpio = <&pio5 3>;
-					reset-names = "hdmi";
-					resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
-					ddc = <&hdmiddc>;
-
-				};
-
-				sti-hda@8d02000 {
-					compatible = "st,stih407-hda";
-					reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
-					reg-names = "hda-reg", "video-dacs-ctrl";
-					clock-names = "pix",
-						      "hddac",
-						      "main_parent",
-						      "aux_parent";
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
-						 <&clk_s_d2_flexgen CLK_HDDAC>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-				};
+			};
+
+			sti-hdmi@8d04000 {
+				compatible = "st,stih407-hdmi";
+				reg = <0x8d04000 0x1000>;
+				reg-names = "hdmi-reg";
+				interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
+				interrupt-names	= "irq";
+				clock-names = "pix",
+					      "tmds",
+					      "phy",
+					      "audio",
+					      "main_parent",
+					      "aux_parent";
+
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
+					 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
+					 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
+					 <&clk_s_d0_flexgen CLK_PCM_0>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
+
+				hdmi,hpd-gpio = <&pio5 3>;
+				reset-names = "hdmi";
+				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
+				ddc = <&hdmiddc>;
+			};
+
+			sti-hda@8d02000 {
+				compatible = "st,stih407-hda";
+				reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
+				reg-names = "hda-reg", "video-dacs-ctrl";
+				clock-names = "pix",
+					      "hddac",
+					      "main_parent",
+					      "aux_parent";
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
+					 <&clk_s_d2_flexgen CLK_HDDAC>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
 			};
 		};
 
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 50c84e1876fc..3f15a5cae167 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -240,7 +240,8 @@ CONFIG_SSI_PROTOCOL=m
 CONFIG_PINCTRL_SINGLE=y
 CONFIG_DEBUG_GPIO=y
 CONFIG_GPIO_SYSFS=y
-CONFIG_GPIO_PCF857X=m
+CONFIG_GPIO_PCA953X=m
+CONFIG_GPIO_PCF857X=y
 CONFIG_GPIO_TWL4030=y
 CONFIG_GPIO_PALMAS=y
 CONFIG_W1=m
@@ -350,6 +351,8 @@ CONFIG_USB_MUSB_HDRC=m
 CONFIG_USB_MUSB_OMAP2PLUS=m
 CONFIG_USB_MUSB_AM35X=m
 CONFIG_USB_MUSB_DSPS=m
+CONFIG_USB_INVENTRA_DMA=y
+CONFIG_USB_TI_CPPI41_DMA=y
 CONFIG_USB_DWC3=m
 CONFIG_USB_TEST=m
 CONFIG_AM335X_PHY_USB=y
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 3df1e975f72a..c4072d9f32c7 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -33,6 +33,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #define KVM_VCPU_MAX_FEATURES 2
 
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 32640c431a08..7cba573c2cc9 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -19,7 +19,7 @@
  * This may need to be greater than __NR_last_syscall+1 in order to
  * account for the padding in the syscall table
  */
-#define __NR_syscalls  (388)
+#define __NR_syscalls  (392)
 
 /*
  * *NOTE*: This is a ghost syscall private to the kernel.  Only the
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 0c3f5a0dafd3..7a2a32a1d5a8 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -414,6 +414,8 @@
 #define __NR_memfd_create		(__NR_SYSCALL_BASE+385)
 #define __NR_bpf			(__NR_SYSCALL_BASE+386)
 #define __NR_execveat			(__NR_SYSCALL_BASE+387)
+#define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
+#define __NR_membarrier			(__NR_SYSCALL_BASE+389)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 05745eb838c5..fde6c88d560c 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -397,6 +397,8 @@
 /* 385 */	CALL(sys_memfd_create)
 		CALL(sys_bpf)
 		CALL(sys_execveat)
+		CALL(sys_userfaultfd)
+		CALL(sys_membarrier)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 07d2e100caab..b3a0dff67e3f 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -44,10 +44,11 @@ config SOC_OMAP5
 	select ARM_CPU_SUSPEND if PM
 	select ARM_GIC
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if SMP
 	select HAVE_ARM_ARCH_TIMER
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT
 	select OMAP_INTERCONNECT_BARRIER
+	select PM_OPP if PM
 
 config SOC_AM33XX
 	bool "TI AM33XX"
@@ -70,10 +71,13 @@ config SOC_DRA7XX
 	select ARCH_OMAP2PLUS
 	select ARM_CPU_SUSPEND if PM
 	select ARM_GIC
+	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_ARCH_TIMER
 	select IRQ_CROSSBAR
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT
 	select OMAP_INTERCONNECT_BARRIER
+	select PM_OPP if PM
 
 config ARCH_OMAP2PLUS
 	bool
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 24c9afc9e8a7..6133eaac685d 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -20,13 +20,6 @@
 
 #include "common.h"
 
-#if !(defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3))
-#define intc_of_init	NULL
-#endif
-#ifndef CONFIG_ARCH_OMAP4
-#define gic_of_init		NULL
-#endif
-
 static const struct of_device_id omap_dt_match_table[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "ti,omap-infra", },
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index e3f713ffb06b..54a5ba54d2ff 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -653,8 +653,12 @@ void __init dra7xxx_check_revision(void)
 			omap_revision = DRA752_REV_ES1_0;
 			break;
 		case 1:
-		default:
 			omap_revision = DRA752_REV_ES1_1;
+			break;
+		case 2:
+		default:
+			omap_revision = DRA752_REV_ES2_0;
+			break;
 		}
 		break;
 
@@ -674,7 +678,7 @@ void __init dra7xxx_check_revision(void)
 		/* Unknown default to latest silicon rev as default*/
 		pr_warn("%s: unknown idcode=0x%08x (hawkeye=0x%08x,rev=0x%x)\n",
 			__func__, idcode, hawkeye, rev);
-		omap_revision = DRA752_REV_ES1_1;
+		omap_revision = DRA752_REV_ES2_0;
 	}
 
 	sprintf(soc_name, "DRA%03x", omap_rev() >> 16);
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 980c9372e6fd..3eaeaca5da05 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -676,6 +676,7 @@ void __init am43xx_init_early(void)
 void __init am43xx_init_late(void)
 {
 	omap_common_late_init();
+	omap2_clk_enable_autoidle_all();
 }
 #endif
 
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 4cb8fd9f741f..72ebc4c16bae 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -901,7 +901,8 @@ static int __init omap_device_late_idle(struct device *dev, void *data)
 		if (od->hwmods[i]->flags & HWMOD_INIT_NO_IDLE)
 			return 0;
 
-	if (od->_driver_status != BUS_NOTIFY_BOUND_DRIVER) {
+	if (od->_driver_status != BUS_NOTIFY_BOUND_DRIVER &&
+	    od->_driver_status != BUS_NOTIFY_BIND_DRIVER) {
 		if (od->_state == OMAP_DEVICE_STATE_ENABLED) {
 			dev_warn(dev, "%s: enabled but no driver.  Idling\n",
 				 __func__);
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 425bfcd67db6..b668719b9b25 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -103,7 +103,8 @@ static inline void enable_omap3630_toggle_l2_on_restore(void) { }
 #define PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD	(1 << 0)
 #define PM_OMAP4_CPU_OSWR_DISABLE		(1 << 1)
 
-#if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP4)
+#if defined(CONFIG_PM) && (defined(CONFIG_ARCH_OMAP4) ||\
+	   defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX))
 extern u16 pm44xx_errata;
 #define IS_PM44XX_ERRATUM(id)		(pm44xx_errata & (id))
 #else
diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h
index f97654d11ea5..2d1d3845253c 100644
--- a/arch/arm/mach-omap2/soc.h
+++ b/arch/arm/mach-omap2/soc.h
@@ -469,6 +469,8 @@ IS_OMAP_TYPE(3430, 0x3430)
 #define DRA7XX_CLASS		0x07000000
 #define DRA752_REV_ES1_0	(DRA7XX_CLASS | (0x52 << 16) | (0x10 << 8))
 #define DRA752_REV_ES1_1	(DRA7XX_CLASS | (0x52 << 16) | (0x11 << 8))
+#define DRA752_REV_ES2_0	(DRA7XX_CLASS | (0x52 << 16) | (0x20 << 8))
+#define DRA722_REV_ES1_0	(DRA7XX_CLASS | (0x22 << 16) | (0x10 << 8))
 #define DRA722_REV_ES1_0	(DRA7XX_CLASS | (0x22 << 16) | (0x10 << 8))
 
 void omap2xxx_check_revision(void);
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index e4d8701f99f9..a55655127ef2 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -297,12 +297,8 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer,
 	if (IS_ERR(src))
 		return PTR_ERR(src);
 
-	r = clk_set_parent(timer->fclk, src);
-	if (r < 0) {
-		pr_warn("%s: %s cannot set source\n", __func__, oh->name);
-		clk_put(src);
-		return r;
-	}
+	WARN(clk_set_parent(timer->fclk, src) < 0,
+	     "Cannot set timer parent clock, no PLL clock driver?");
 
 	clk_put(src);
 
diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c
index e5a35f6b83a7..d44d311704ba 100644
--- a/arch/arm/mach-omap2/vc.c
+++ b/arch/arm/mach-omap2/vc.c
@@ -300,7 +300,7 @@ static void __init omap3_vc_init_pmic_signaling(struct voltagedomain *voltdm)
 
 	val = voltdm->read(OMAP3_PRM_POLCTRL_OFFSET);
 	if (!(val & OMAP3430_PRM_POLCTRL_CLKREQ_POL) ||
-	    (val & OMAP3430_PRM_POLCTRL_CLKREQ_POL)) {
+	    (val & OMAP3430_PRM_POLCTRL_OFFMODE_POL)) {
 		val |= OMAP3430_PRM_POLCTRL_CLKREQ_POL;
 		val &= ~OMAP3430_PRM_POLCTRL_OFFMODE_POL;
 		pr_debug("PM: fixing sys_clkreq and sys_off_mode polarity to 0x%x\n",
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index a3ebb517cca1..a727282bfa99 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -502,7 +502,7 @@ static void balloon3_irq_handler(struct irq_desc *desc)
 					balloon3_irq_enabled;
 	do {
 		struct irq_data *d = irq_desc_get_irq_data(desc);
-		struct irq_chip *chip = irq_data_get_chip(d);
+		struct irq_chip *chip = irq_desc_get_chip(desc);
 		unsigned int irq;
 
 		/* clear useless edge notification */
diff --git a/arch/arm/mach-pxa/include/mach/addr-map.h b/arch/arm/mach-pxa/include/mach/addr-map.h
index d28fe291233a..07b93fd24474 100644
--- a/arch/arm/mach-pxa/include/mach/addr-map.h
+++ b/arch/arm/mach-pxa/include/mach/addr-map.h
@@ -44,6 +44,13 @@
  */
 
 /*
+ * DFI Bus for NAND, PXA3xx only
+ */
+#define NAND_PHYS		0x43100000
+#define NAND_VIRT		IOMEM(0xf6300000)
+#define NAND_SIZE		0x00100000
+
+/*
  * Internal Memory Controller (PXA27x and later)
  */
 #define IMEMC_PHYS		0x58000000
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index ce0f8d6242e2..06005d3f2ba3 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -47,6 +47,13 @@ extern void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int));
 #define ISRAM_START	0x5c000000
 #define ISRAM_SIZE	SZ_256K
 
+/*
+ * NAND NFC: DFI bus arbitration subset
+ */
+#define NDCR			(*(volatile u32 __iomem*)(NAND_VIRT + 0))
+#define NDCR_ND_ARB_EN		(1 << 12)
+#define NDCR_ND_ARB_CNTL	(1 << 19)
+
 static void __iomem *sram;
 static unsigned long wakeup_src;
 
@@ -362,7 +369,12 @@ static struct map_desc pxa3xx_io_desc[] __initdata = {
 		.pfn		= __phys_to_pfn(PXA3XX_SMEMC_BASE),
 		.length		= SMEMC_SIZE,
 		.type		= MT_DEVICE
-	}
+	}, {
+		.virtual	= (unsigned long)NAND_VIRT,
+		.pfn		= __phys_to_pfn(NAND_PHYS),
+		.length		= NAND_SIZE,
+		.type		= MT_DEVICE
+	},
 };
 
 void __init pxa3xx_map_io(void)
@@ -419,6 +431,13 @@ static int __init pxa3xx_init(void)
 		 */
 		ASCR &= ~(ASCR_RDH | ASCR_D1S | ASCR_D2S | ASCR_D3S);
 
+		/*
+		 * Disable DFI bus arbitration, to prevent a system bus lock if
+		 * somebody disables the NAND clock (unused clock) while this
+		 * bit remains set.
+		 */
+		NDCR = (NDCR & ~NDCR_ND_ARB_EN) | NDCR_ND_ARB_CNTL;
+
 		if ((ret = pxa_init_dma(IRQ_DMA, 32)))
 			return ret;
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 9769f1eefe3b..00b7f7de28a1 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -365,15 +365,21 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r
  user:
 	if (LDST_L_BIT(instr)) {
 		unsigned long val;
+		unsigned int __ua_flags = uaccess_save_and_enable();
+
 		get16t_unaligned_check(val, addr);
+		uaccess_restore(__ua_flags);
 
 		/* signed half-word? */
 		if (instr & 0x40)
 			val = (signed long)((signed short) val);
 
 		regs->uregs[rd] = val;
-	} else
+	} else {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		put16t_unaligned_check(regs->uregs[rd], addr);
+		uaccess_restore(__ua_flags);
+	}
 
 	return TYPE_LDST;
 
@@ -420,14 +426,21 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
 
  user:
 	if (load) {
-		unsigned long val;
+		unsigned long val, val2;
+		unsigned int __ua_flags = uaccess_save_and_enable();
+
 		get32t_unaligned_check(val, addr);
+		get32t_unaligned_check(val2, addr + 4);
+
+		uaccess_restore(__ua_flags);
+
 		regs->uregs[rd] = val;
-		get32t_unaligned_check(val, addr + 4);
-		regs->uregs[rd2] = val;
+		regs->uregs[rd2] = val2;
 	} else {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		put32t_unaligned_check(regs->uregs[rd], addr);
 		put32t_unaligned_check(regs->uregs[rd2], addr + 4);
+		uaccess_restore(__ua_flags);
 	}
 
 	return TYPE_LDST;
@@ -458,10 +471,15 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg
  trans:
 	if (LDST_L_BIT(instr)) {
 		unsigned int val;
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		get32t_unaligned_check(val, addr);
+		uaccess_restore(__ua_flags);
 		regs->uregs[rd] = val;
-	} else
+	} else {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		put32t_unaligned_check(regs->uregs[rd], addr);
+		uaccess_restore(__ua_flags);
+	}
 	return TYPE_LDST;
 
  fault:
@@ -531,6 +549,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
 #endif
 
 	if (user_mode(regs)) {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		for (regbits = REGMASK_BITS(instr), rd = 0; regbits;
 		     regbits >>= 1, rd += 1)
 			if (regbits & 1) {
@@ -542,6 +561,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
 					put32t_unaligned_check(regs->uregs[rd], eaddr);
 				eaddr += 4;
 			}
+		uaccess_restore(__ua_flags);
 	} else {
 		for (regbits = REGMASK_BITS(instr), rd = 0; regbits;
 		     regbits >>= 1, rd += 1)
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ad9529cc4203..daa1a65f2eb7 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -107,7 +107,6 @@ static const struct of_device_id pxa_ssp_of_ids[] = {
 	{ .compatible = "mvrl,pxa168-ssp",	.data = (void *) PXA168_SSP },
 	{ .compatible = "mrvl,pxa910-ssp",	.data = (void *) PXA910_SSP },
 	{ .compatible = "mrvl,ce4100-ssp",	.data = (void *) CE4100_SSP },
-	{ .compatible = "mrvl,lpss-ssp",	.data = (void *) LPSS_SSP },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, pxa_ssp_of_ids);
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index d18ee4259ee5..06a15644be38 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -81,7 +81,7 @@
 		};
 
 		idle-states {
-			entry-method = "arm,psci";
+			entry-method = "psci";
 
 			CPU_SLEEP_0: cpu-sleep-0 {
 				compatible = "arm,idle-state";
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index a712bea3bf2c..cc093a482aa4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -106,7 +106,7 @@
 		};
 
 		idle-states {
-			entry-method = "arm,psci";
+			entry-method = "psci";
 
 			cpu_sleep: cpu-sleep-0 {
 				compatible = "arm,idle-state";
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 4562459456a6..ed039688c221 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -33,6 +33,7 @@
 #define KVM_USER_MEM_SLOTS 32
 #define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>
diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c
index f9c86c475bbd..f211839e2cae 100644
--- a/arch/frv/mb93090-mb00/pci-vdk.c
+++ b/arch/frv/mb93090-mb00/pci-vdk.c
@@ -294,6 +294,8 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	printk("### PCIBIOS_FIXUP_BUS(%d)\n",bus->number);
 #endif
 
+	pci_read_bridge_bases(bus);
+
 	if (bus->number == 0) {
 		struct pci_dev *dev;
 		list_for_each_entry(dev, &bus->devices, bus_list) {
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index d89b6013c941..7cc3be9fa7c6 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -533,9 +533,10 @@ void pcibios_fixup_bus(struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
-	if (b->self)
+	if (b->self) {
+		pci_read_bridge_bases(b);
 		pcibios_fixup_bridge_resources(b->self);
-
+	}
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
 	platform_pci_fixup_bus(b);
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 6b8b75266801..ae838ed5fcf2 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -863,7 +863,14 @@ void pcibios_setup_bus_devices(struct pci_bus *bus)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	/* Fixup the bus */
+	/* When called from the generic PCI probe, read PCI<->PCI bridge
+	 * bases. This is -not- called when generating the PCI tree from
+	 * the OF device-tree.
+	 */
+	if (bus->self != NULL)
+		pci_read_bridge_bases(bus);
+
+	/* Now fixup the bus bus */
 	pcibios_setup_bus_self(bus);
 
 	/* Now fixup devices on that bus */
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 3a54dbca9f7e..5a1a882e0a75 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -61,6 +61,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 	0
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 
 
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index c6996cf67a5c..b8a0bf5766f2 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -311,6 +311,12 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
+	struct pci_dev *dev = bus->self;
+
+	if (pci_has_flag(PCI_PROBE_ONLY) && dev &&
+	    (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		pci_read_bridge_bases(bus);
+	}
 }
 
 EXPORT_SYMBOL(PCIBIOS_MIN_IO);
diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c
index deaa893efba5..3dfe2d31c67b 100644
--- a/arch/mn10300/unit-asb2305/pci.c
+++ b/arch/mn10300/unit-asb2305/pci.c
@@ -324,6 +324,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	struct pci_dev *dev;
 
 	if (bus->self) {
+		pci_read_bridge_bases(bus);
 		pcibios_fixup_bridge_resources(bus->self);
 	}
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 195886a583ba..827a38d7a9db 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -44,6 +44,7 @@
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 /* These values are internal and can be increased later */
 #define KVM_NR_IRQCHIPS          1
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 4d65499ee1c1..126d0c4f9b7d 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -369,3 +369,4 @@ SYSCALL_SPU(bpf)
 COMPAT_SYS(execveat)
 PPC64ONLY(switch_endian)
 SYSCALL_SPU(userfaultfd)
+SYSCALL_SPU(membarrier)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 4a055b6c2a64..13411be86041 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define __NR_syscalls		365
+#define __NR_syscalls		366
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 6ad58d4c879b..6337738018aa 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -387,5 +387,6 @@
 #define __NR_execveat		362
 #define __NR_switch_endian	363
 #define __NR_userfaultfd	364
+#define __NR_membarrier		365
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index a1d0632d97c6..7587b2ae5f77 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1032,7 +1032,13 @@ void pcibios_set_master(struct pci_dev *dev)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	/* Fixup the bus */
+	/* When called from the generic PCI probe, read PCI<->PCI bridge
+	 * bases. This is -not- called when generating the PCI tree from
+	 * the OF device-tree.
+	 */
+	pci_read_bridge_bases(bus);
+
+	/* Now fixup the bus bus */
 	pcibios_setup_bus_self(bus);
 
 	/* Now fixup devices on that bus */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index cf009167d208..099c79d8c160 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -829,12 +829,15 @@ int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
 	unsigned long size = kvmppc_get_gpr(vcpu, 4);
 	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
 	u64 buf;
+	int srcu_idx;
 	int ret;
 
 	if (!is_power_of_2(size) || (size > sizeof(buf)))
 		return H_TOO_HARD;
 
+	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 	if (ret != 0)
 		return H_TOO_HARD;
 
@@ -869,6 +872,7 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
 	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
 	unsigned long val = kvmppc_get_gpr(vcpu, 6);
 	u64 buf;
+	int srcu_idx;
 	int ret;
 
 	switch (size) {
@@ -892,7 +896,9 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
 		return H_TOO_HARD;
 	}
 
+	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 	if (ret != 0)
 		return H_TOO_HARD;
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9754e6815e52..228049786888 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2692,9 +2692,13 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
 	       (vc->vcore_state == VCORE_RUNNING ||
-		vc->vcore_state == VCORE_EXITING))
+		vc->vcore_state == VCORE_EXITING ||
+		vc->vcore_state == VCORE_PIGGYBACK))
 		kvmppc_wait_for_exec(vc, vcpu, TASK_UNINTERRUPTIBLE);
 
+	if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
+		kvmppc_vcore_end_preempt(vc);
+
 	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
 		kvmppc_remove_runnable(vc, vcpu);
 		vcpu->stat.signal_exits++;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 2273dcacef39..b98889e9851d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1257,6 +1257,7 @@ mc_cont:
 	bl	kvmhv_accumulate_time
 #endif
 
+	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
 	nop
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 1b0184a0f7f2..92805d604173 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -1,7 +1,6 @@
 # CONFIG_SWAP is not set
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_COMPAT_BRK is not set
@@ -54,10 +53,6 @@ CONFIG_RAW_DRIVER=y
 # CONFIG_MONWRITER is not set
 # CONFIG_S390_VMUR is not set
 # CONFIG_HID is not set
-CONFIG_MEMSTICK=y
-CONFIG_MEMSTICK_DEBUG=y
-CONFIG_MEMSTICK_UNSAFE_RESUME=y
-CONFIG_MSPRO_BLOCK=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 6ce4a0b7e8da..8ced426091e1 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -35,6 +35,7 @@
  */
 #define KVM_NR_IRQCHIPS 1
 #define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_HALT_POLL_NS_DEFAULT 0
 
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 525cef73b085..02613bad8bbb 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -8,28 +8,8 @@
 
 #include <uapi/asm/unistd.h>
 
-
 #define __IGNORE_time
 
-/* Ignore system calls that are also reachable via sys_socketcall */
-#define __IGNORE_recvmmsg
-#define __IGNORE_sendmmsg
-#define __IGNORE_socket
-#define __IGNORE_socketpair
-#define __IGNORE_bind
-#define __IGNORE_connect
-#define __IGNORE_listen
-#define __IGNORE_accept4
-#define __IGNORE_getsockopt
-#define __IGNORE_setsockopt
-#define __IGNORE_getsockname
-#define __IGNORE_getpeername
-#define __IGNORE_sendto
-#define __IGNORE_sendmsg
-#define __IGNORE_recvfrom
-#define __IGNORE_recvmsg
-#define __IGNORE_shutdown
-
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 59d2bb4e2d0c..a848adba1504 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -290,7 +290,26 @@
 #define __NR_s390_pci_mmio_write	352
 #define __NR_s390_pci_mmio_read		353
 #define __NR_execveat		354
-#define NR_syscalls 355
+#define __NR_userfaultfd	355
+#define __NR_membarrier		356
+#define __NR_recvmmsg		357
+#define __NR_sendmmsg		358
+#define __NR_socket		359
+#define __NR_socketpair		360
+#define __NR_bind		361
+#define __NR_connect		362
+#define __NR_listen		363
+#define __NR_accept4		364
+#define __NR_getsockopt		365
+#define __NR_setsockopt		366
+#define __NR_getsockname	367
+#define __NR_getpeername	368
+#define __NR_sendto		369
+#define __NR_sendmsg		370
+#define __NR_recvfrom		371
+#define __NR_recvmsg		372
+#define __NR_shutdown		373
+#define NR_syscalls 374
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index eb4664238613..e0f9d270b30f 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -48,6 +48,19 @@ typedef struct
 	struct ucontext32 uc;
 } rt_sigframe32;
 
+static inline void sigset_to_sigset32(unsigned long *set64,
+				      compat_sigset_word *set32)
+{
+	set32[0] = (compat_sigset_word) set64[0];
+	set32[1] = (compat_sigset_word)(set64[0] >> 32);
+}
+
+static inline void sigset32_to_sigset(compat_sigset_word *set32,
+				      unsigned long *set64)
+{
+	set64[0] = (unsigned long) set32[0] | ((unsigned long) set32[1] << 32);
+}
+
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
@@ -281,10 +294,12 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	sigframe32 __user *frame = (sigframe32 __user *)regs->gprs[15];
+	compat_sigset_t cset;
 	sigset_t set;
 
-	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32))
+	if (__copy_from_user(&cset.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32))
 		goto badframe;
+	sigset32_to_sigset(cset.sig, set.sig);
 	set_current_blocked(&set);
 	save_fpu_regs();
 	if (restore_sigregs32(regs, &frame->sregs))
@@ -302,10 +317,12 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	rt_sigframe32 __user *frame = (rt_sigframe32 __user *)regs->gprs[15];
+	compat_sigset_t cset;
 	sigset_t set;
 
-	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+	if (__copy_from_user(&cset, &frame->uc.uc_sigmask, sizeof(cset)))
 		goto badframe;
+	sigset32_to_sigset(cset.sig, set.sig);
 	set_current_blocked(&set);
 	if (compat_restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
@@ -377,7 +394,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 		return -EFAULT;
 
 	/* Create struct sigcontext32 on the signal stack */
-	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32);
+	sigset_to_sigset32(set->sig, sc.oldmask);
 	sc.sregs = (__u32)(unsigned long __force) &frame->sregs;
 	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
 		return -EFAULT;
@@ -438,6 +455,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 			    struct pt_regs *regs)
 {
+	compat_sigset_t cset;
 	rt_sigframe32 __user *frame;
 	unsigned long restorer;
 	size_t frame_size;
@@ -485,11 +503,12 @@ static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 	store_sigregs();
 
 	/* Create ucontext on the signal stack. */
+	sigset_to_sigset32(set->sig, cset.sig);
 	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
 	    __put_user(0, &frame->uc.uc_link) ||
 	    __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
 	    save_sigregs32(regs, &frame->uc.uc_mcontext) ||
-	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, &cset, sizeof(cset)) ||
 	    save_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index f8498dde67b1..09f194052df3 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -52,15 +52,13 @@
  * the regular system call wrappers.
  */
 #define COMPAT_SYSCALL_WRAPx(x, name, ...)					\
-	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));		\
-	asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\
-	asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__))	\
-	{									\
-		return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__));	\
-	}
+asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));			\
+asmlinkage long notrace compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\
+asmlinkage long notrace compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__))	\
+{										\
+	return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__));		\
+}
 
-COMPAT_SYSCALL_WRAP1(exit, int, error_code);
-COMPAT_SYSCALL_WRAP1(close, unsigned int, fd);
 COMPAT_SYSCALL_WRAP2(creat, const char __user *, pathname, umode_t, mode);
 COMPAT_SYSCALL_WRAP2(link, const char __user *, oldname, const char __user *, newname);
 COMPAT_SYSCALL_WRAP1(unlink, const char __user *, pathname);
@@ -68,23 +66,16 @@ COMPAT_SYSCALL_WRAP1(chdir, const char __user *, filename);
 COMPAT_SYSCALL_WRAP3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev);
 COMPAT_SYSCALL_WRAP2(chmod, const char __user *, filename, umode_t, mode);
 COMPAT_SYSCALL_WRAP1(oldumount, char __user *, name);
-COMPAT_SYSCALL_WRAP1(alarm, unsigned int, seconds);
 COMPAT_SYSCALL_WRAP2(access, const char __user *, filename, int, mode);
-COMPAT_SYSCALL_WRAP1(nice, int, increment);
-COMPAT_SYSCALL_WRAP2(kill, int, pid, int, sig);
 COMPAT_SYSCALL_WRAP2(rename, const char __user *, oldname, const char __user *, newname);
 COMPAT_SYSCALL_WRAP2(mkdir, const char __user *, pathname, umode_t, mode);
 COMPAT_SYSCALL_WRAP1(rmdir, const char __user *, pathname);
-COMPAT_SYSCALL_WRAP1(dup, unsigned int, fildes);
 COMPAT_SYSCALL_WRAP1(pipe, int __user *, fildes);
 COMPAT_SYSCALL_WRAP1(brk, unsigned long, brk);
 COMPAT_SYSCALL_WRAP2(signal, int, sig, __sighandler_t, handler);
 COMPAT_SYSCALL_WRAP1(acct, const char __user *, name);
 COMPAT_SYSCALL_WRAP2(umount, char __user *, name, int, flags);
-COMPAT_SYSCALL_WRAP2(setpgid, pid_t, pid, pid_t, pgid);
-COMPAT_SYSCALL_WRAP1(umask, int, mask);
 COMPAT_SYSCALL_WRAP1(chroot, const char __user *, filename);
-COMPAT_SYSCALL_WRAP2(dup2, unsigned int, oldfd, unsigned int, newfd);
 COMPAT_SYSCALL_WRAP3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask);
 COMPAT_SYSCALL_WRAP2(sethostname, char __user *, name, int, len);
 COMPAT_SYSCALL_WRAP2(symlink, const char __user *, old, const char __user *, new);
@@ -93,37 +84,23 @@ COMPAT_SYSCALL_WRAP1(uselib, const char __user *, library);
 COMPAT_SYSCALL_WRAP2(swapon, const char __user *, specialfile, int, swap_flags);
 COMPAT_SYSCALL_WRAP4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg);
 COMPAT_SYSCALL_WRAP2(munmap, unsigned long, addr, size_t, len);
-COMPAT_SYSCALL_WRAP2(fchmod, unsigned int, fd, umode_t, mode);
-COMPAT_SYSCALL_WRAP2(getpriority, int, which, int, who);
-COMPAT_SYSCALL_WRAP3(setpriority, int, which, int, who, int, niceval);
 COMPAT_SYSCALL_WRAP3(syslog, int, type, char __user *, buf, int, len);
 COMPAT_SYSCALL_WRAP1(swapoff, const char __user *, specialfile);
-COMPAT_SYSCALL_WRAP1(fsync, unsigned int, fd);
 COMPAT_SYSCALL_WRAP2(setdomainname, char __user *, name, int, len);
 COMPAT_SYSCALL_WRAP1(newuname, struct new_utsname __user *, name);
 COMPAT_SYSCALL_WRAP3(mprotect, unsigned long, start, size_t, len, unsigned long, prot);
 COMPAT_SYSCALL_WRAP3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs);
 COMPAT_SYSCALL_WRAP2(delete_module, const char __user *, name_user, unsigned int, flags);
 COMPAT_SYSCALL_WRAP4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr);
-COMPAT_SYSCALL_WRAP1(getpgid, pid_t, pid);
-COMPAT_SYSCALL_WRAP1(fchdir, unsigned int, fd);
 COMPAT_SYSCALL_WRAP2(bdflush, int, func, long, data);
 COMPAT_SYSCALL_WRAP3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2);
-COMPAT_SYSCALL_WRAP1(s390_personality, unsigned int, personality);
 COMPAT_SYSCALL_WRAP5(llseek, unsigned int, fd, unsigned long, high, unsigned long, low, loff_t __user *, result, unsigned int, whence);
-COMPAT_SYSCALL_WRAP2(flock, unsigned int, fd, unsigned int, cmd);
 COMPAT_SYSCALL_WRAP3(msync, unsigned long, start, size_t, len, int, flags);
-COMPAT_SYSCALL_WRAP1(getsid, pid_t, pid);
-COMPAT_SYSCALL_WRAP1(fdatasync, unsigned int, fd);
 COMPAT_SYSCALL_WRAP2(mlock, unsigned long, start, size_t, len);
 COMPAT_SYSCALL_WRAP2(munlock, unsigned long, start, size_t, len);
-COMPAT_SYSCALL_WRAP1(mlockall, int, flags);
 COMPAT_SYSCALL_WRAP2(sched_setparam, pid_t, pid, struct sched_param __user *, param);
 COMPAT_SYSCALL_WRAP2(sched_getparam, pid_t, pid, struct sched_param __user *, param);
 COMPAT_SYSCALL_WRAP3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param);
-COMPAT_SYSCALL_WRAP1(sched_getscheduler, pid_t, pid);
-COMPAT_SYSCALL_WRAP1(sched_get_priority_max, int, policy);
-COMPAT_SYSCALL_WRAP1(sched_get_priority_min, int, policy);
 COMPAT_SYSCALL_WRAP5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, unsigned long, new_addr);
 COMPAT_SYSCALL_WRAP3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout);
 COMPAT_SYSCALL_WRAP5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5);
@@ -131,20 +108,11 @@ COMPAT_SYSCALL_WRAP2(getcwd, char __user *, buf, unsigned long, size);
 COMPAT_SYSCALL_WRAP2(capget, cap_user_header_t, header, cap_user_data_t, dataptr);
 COMPAT_SYSCALL_WRAP2(capset, cap_user_header_t, header, const cap_user_data_t, data);
 COMPAT_SYSCALL_WRAP3(lchown, const char __user *, filename, uid_t, user, gid_t, group);
-COMPAT_SYSCALL_WRAP2(setreuid, uid_t, ruid, uid_t, euid);
-COMPAT_SYSCALL_WRAP2(setregid, gid_t, rgid, gid_t, egid);
 COMPAT_SYSCALL_WRAP2(getgroups, int, gidsetsize, gid_t __user *, grouplist);
 COMPAT_SYSCALL_WRAP2(setgroups, int, gidsetsize, gid_t __user *, grouplist);
-COMPAT_SYSCALL_WRAP3(fchown, unsigned int, fd, uid_t, user, gid_t, group);
-COMPAT_SYSCALL_WRAP3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid);
 COMPAT_SYSCALL_WRAP3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid);
-COMPAT_SYSCALL_WRAP3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid);
 COMPAT_SYSCALL_WRAP3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid);
 COMPAT_SYSCALL_WRAP3(chown, const char __user *, filename, uid_t, user, gid_t, group);
-COMPAT_SYSCALL_WRAP1(setuid, uid_t, uid);
-COMPAT_SYSCALL_WRAP1(setgid, gid_t, gid);
-COMPAT_SYSCALL_WRAP1(setfsuid, uid_t, uid);
-COMPAT_SYSCALL_WRAP1(setfsgid, gid_t, gid);
 COMPAT_SYSCALL_WRAP2(pivot_root, const char __user *, new_root, const char __user *, put_old);
 COMPAT_SYSCALL_WRAP3(mincore, unsigned long, start, size_t, len, unsigned char __user *, vec);
 COMPAT_SYSCALL_WRAP3(madvise, unsigned long, start, size_t, len, int, behavior);
@@ -161,23 +129,16 @@ COMPAT_SYSCALL_WRAP3(flistxattr, int, fd, char __user *, list, size_t, size);
 COMPAT_SYSCALL_WRAP2(removexattr, const char __user *, path, const char __user *, name);
 COMPAT_SYSCALL_WRAP2(lremovexattr, const char __user *, path, const char __user *, name);
 COMPAT_SYSCALL_WRAP2(fremovexattr, int, fd, const char __user *, name);
-COMPAT_SYSCALL_WRAP1(exit_group, int, error_code);
 COMPAT_SYSCALL_WRAP1(set_tid_address, int __user *, tidptr);
-COMPAT_SYSCALL_WRAP1(epoll_create, int, size);
 COMPAT_SYSCALL_WRAP4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event);
 COMPAT_SYSCALL_WRAP4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout);
-COMPAT_SYSCALL_WRAP1(timer_getoverrun, timer_t, timer_id);
-COMPAT_SYSCALL_WRAP1(timer_delete, compat_timer_t, compat_timer_id);
 COMPAT_SYSCALL_WRAP1(io_destroy, aio_context_t, ctx);
 COMPAT_SYSCALL_WRAP3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result);
 COMPAT_SYSCALL_WRAP1(mq_unlink, const char __user *, name);
 COMPAT_SYSCALL_WRAP5(add_key, const char __user *, tp, const char __user *, dsc, const void __user *, pld, size_t, len, key_serial_t, id);
 COMPAT_SYSCALL_WRAP4(request_key, const char __user *, tp, const char __user *, dsc, const char __user *, info, key_serial_t, id);
 COMPAT_SYSCALL_WRAP5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags);
-COMPAT_SYSCALL_WRAP3(ioprio_set, int, which, int, who, int, ioprio);
-COMPAT_SYSCALL_WRAP2(ioprio_get, int, which, int, who);
 COMPAT_SYSCALL_WRAP3(inotify_add_watch, int, fd, const char __user *, path, u32, mask);
-COMPAT_SYSCALL_WRAP2(inotify_rm_watch, int, fd, __s32, wd);
 COMPAT_SYSCALL_WRAP3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode);
 COMPAT_SYSCALL_WRAP4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned, dev);
 COMPAT_SYSCALL_WRAP5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag);
@@ -192,23 +153,11 @@ COMPAT_SYSCALL_WRAP1(unshare, unsigned long, unshare_flags);
 COMPAT_SYSCALL_WRAP6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
 COMPAT_SYSCALL_WRAP4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags);
 COMPAT_SYSCALL_WRAP3(getcpu, unsigned __user *, cpu, unsigned __user *, node, struct getcpu_cache __user *, cache);
-COMPAT_SYSCALL_WRAP1(eventfd, unsigned int, count);
-COMPAT_SYSCALL_WRAP2(timerfd_create, int, clockid, int, flags);
-COMPAT_SYSCALL_WRAP2(eventfd2, unsigned int, count, int, flags);
-COMPAT_SYSCALL_WRAP1(inotify_init1, int, flags);
 COMPAT_SYSCALL_WRAP2(pipe2, int __user *, fildes, int, flags);
-COMPAT_SYSCALL_WRAP3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags);
-COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags);
-COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig);
-COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig);
 COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags);
 COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls);
-COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags);
 COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim);
 COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag);
-COMPAT_SYSCALL_WRAP1(syncfs, int, fd);
-COMPAT_SYSCALL_WRAP2(setns, int, fd, int, nstype);
-COMPAT_SYSCALL_WRAP2(s390_runtime_instr, int, command, int, signum);
 COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2);
 COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags);
 COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
@@ -220,3 +169,10 @@ COMPAT_SYSCALL_WRAP2(memfd_create, const char __user *, uname, unsigned int, fla
 COMPAT_SYSCALL_WRAP3(bpf, int, cmd, union bpf_attr *, attr, unsigned int, size);
 COMPAT_SYSCALL_WRAP3(s390_pci_mmio_write, const unsigned long, mmio_addr, const void __user *, user_buffer, const size_t, length);
 COMPAT_SYSCALL_WRAP3(s390_pci_mmio_read, const unsigned long, mmio_addr, void __user *, user_buffer, const size_t, length);
+COMPAT_SYSCALL_WRAP4(socketpair, int, family, int, type, int, protocol, int __user *, usockvec);
+COMPAT_SYSCALL_WRAP3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen);
+COMPAT_SYSCALL_WRAP3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen);
+COMPAT_SYSCALL_WRAP4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen, int, flags);
+COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
+COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
+COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 247b7aae4c6d..09b039d7983d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -1191,6 +1191,7 @@ cleanup_critical:
 	clg	%r9,BASED(.Lcleanup_save_fpu_fpc_end)
 	jhe	1f
 	lg	%r2,__LC_CURRENT
+	aghi	%r2,__TASK_thread
 0:	# Store floating-point controls
 	stfpc	__THREAD_FPU_fpc(%r2)
 1:	# Load register save area and check if VX is active
@@ -1252,6 +1253,7 @@ cleanup_critical:
 	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx_ctl)
 	jhe	6f
 	lg	%r4,__LC_CURRENT
+	aghi	%r4,__TASK_thread
 	lfpc	__THREAD_FPU_fpc(%r4)
 	tm	__THREAD_FPU_flags+3(%r4),FPU_USE_VX	# VX-enabled task ?
 	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 56fdad479115..a9563409c36e 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -157,10 +157,14 @@ static int validate_ctr_auth(const struct hw_perf_event *hwc)
 
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
-	/* check authorization for cpu counter sets */
+	/* Check authorization for cpu counter sets.
+	 * If the particular CPU counter set is not authorized,
+	 * return with -ENOENT in order to fall back to other
+	 * PMUs that might suffice the event request.
+	 */
 	ctrs_state = cpumf_state_ctl[hwc->config_base];
 	if (!(ctrs_state & cpuhw->info.auth_ctl))
-		err = -EPERM;
+		err = -ENOENT;
 
 	put_cpu_var(cpu_hw_events);
 	return err;
@@ -536,7 +540,7 @@ static int cpumf_pmu_add(struct perf_event *event, int flags)
 	 */
 	if (!(cpuhw->flags & PERF_EVENT_TXN))
 		if (validate_ctr_auth(&event->hw))
-			return -EPERM;
+			return -ENOENT;
 
 	ctr_set_enable(&cpuhw->state, event->hw.config_base);
 	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
@@ -611,7 +615,7 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu)
 	state = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
 	state >>= CPUMF_LCCTL_ENABLE_SHIFT;
 	if ((state & cpuhw->info.auth_ctl) != state)
-		return -EPERM;
+		return -ENOENT;
 
 	cpuhw->flags &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index ca6294645dd3..2d6b6e81f812 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -30,6 +30,9 @@ ENTRY(swsusp_arch_suspend)
 	aghi	%r15,-STACK_FRAME_OVERHEAD
 	stg	%r1,__SF_BACKCHAIN(%r15)
 
+	/* Store FPU registers */
+	brasl	%r14,save_fpu_regs
+
 	/* Deactivate DAT */
 	stnsm	__SF_EMPTY(%r15),0xfb
 
@@ -47,23 +50,6 @@ ENTRY(swsusp_arch_suspend)
 
 	/* Store registers */
 	mvc	0x318(4,%r1),__SF_EMPTY(%r15)	/* move prefix to lowcore */
-	stfpc	0x31c(%r1)			/* store fpu control */
-	std	0,0x200(%r1)			/* store f0 */
-	std	1,0x208(%r1)			/* store f1 */
-	std	2,0x210(%r1)			/* store f2 */
-	std	3,0x218(%r1)			/* store f3 */
-	std	4,0x220(%r1)			/* store f4 */
-	std	5,0x228(%r1)			/* store f5 */
-	std	6,0x230(%r1)			/* store f6 */
-	std	7,0x238(%r1)			/* store f7 */
-	std	8,0x240(%r1)			/* store f8 */
-	std	9,0x248(%r1)			/* store f9 */
-	std	10,0x250(%r1)			/* store f10 */
-	std	11,0x258(%r1)			/* store f11 */
-	std	12,0x260(%r1)			/* store f12 */
-	std	13,0x268(%r1)			/* store f13 */
-	std	14,0x270(%r1)			/* store f14 */
-	std	15,0x278(%r1)			/* store f15 */
 	stam	%a0,%a15,0x340(%r1)		/* store access registers */
 	stctg	%c0,%c15,0x380(%r1)		/* store control registers */
 	stmg	%r0,%r15,0x280(%r1)		/* store general registers */
@@ -249,24 +235,6 @@ restore_registers:
 	lctlg	%c0,%c15,0x380(%r13)	/* load control registers */
 	lam	%a0,%a15,0x340(%r13)	/* load access registers */
 
-	lfpc	0x31c(%r13)		/* load fpu control */
-	ld	0,0x200(%r13)		/* load f0 */
-	ld	1,0x208(%r13)		/* load f1 */
-	ld	2,0x210(%r13)		/* load f2 */
-	ld	3,0x218(%r13)		/* load f3 */
-	ld	4,0x220(%r13)		/* load f4 */
-	ld	5,0x228(%r13)		/* load f5 */
-	ld	6,0x230(%r13)		/* load f6 */
-	ld	7,0x238(%r13)		/* load f7 */
-	ld	8,0x240(%r13)		/* load f8 */
-	ld	9,0x248(%r13)		/* load f9 */
-	ld	10,0x250(%r13)		/* load f10 */
-	ld	11,0x258(%r13)		/* load f11 */
-	ld	12,0x260(%r13)		/* load f12 */
-	ld	13,0x268(%r13)		/* load f13 */
-	ld	14,0x270(%r13)		/* load f14 */
-	ld	15,0x278(%r13)		/* load f15 */
-
 	/* Load old stack */
 	lg	%r15,0x2f8(%r13)
 
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index f3f4a137aef6..8c56929c8d82 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -9,12 +9,12 @@
 #define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall)
 
 NI_SYSCALL						/* 0 */
-SYSCALL(sys_exit,compat_sys_exit)
+SYSCALL(sys_exit,sys_exit)
 SYSCALL(sys_fork,sys_fork)
 SYSCALL(sys_read,compat_sys_s390_read)
 SYSCALL(sys_write,compat_sys_s390_write)
 SYSCALL(sys_open,compat_sys_open)			/* 5 */
-SYSCALL(sys_close,compat_sys_close)
+SYSCALL(sys_close,sys_close)
 SYSCALL(sys_restart_syscall,sys_restart_syscall)
 SYSCALL(sys_creat,compat_sys_creat)
 SYSCALL(sys_link,compat_sys_link)
@@ -35,21 +35,21 @@ SYSCALL(sys_ni_syscall,compat_sys_s390_setuid16)	/* old setuid16 syscall*/
 SYSCALL(sys_ni_syscall,compat_sys_s390_getuid16)	/* old getuid16 syscall*/
 SYSCALL(sys_ni_syscall,compat_sys_stime)		/* 25 old stime syscall */
 SYSCALL(sys_ptrace,compat_sys_ptrace)
-SYSCALL(sys_alarm,compat_sys_alarm)
+SYSCALL(sys_alarm,sys_alarm)
 NI_SYSCALL						/* old fstat syscall */
 SYSCALL(sys_pause,sys_pause)
 SYSCALL(sys_utime,compat_sys_utime)			/* 30 */
 NI_SYSCALL						/* old stty syscall */
 NI_SYSCALL						/* old gtty syscall */
 SYSCALL(sys_access,compat_sys_access)
-SYSCALL(sys_nice,compat_sys_nice)
+SYSCALL(sys_nice,sys_nice)
 NI_SYSCALL						/* 35 old ftime syscall */
 SYSCALL(sys_sync,sys_sync)
-SYSCALL(sys_kill,compat_sys_kill)
+SYSCALL(sys_kill,sys_kill)
 SYSCALL(sys_rename,compat_sys_rename)
 SYSCALL(sys_mkdir,compat_sys_mkdir)
 SYSCALL(sys_rmdir,compat_sys_rmdir)			/* 40 */
-SYSCALL(sys_dup,compat_sys_dup)
+SYSCALL(sys_dup,sys_dup)
 SYSCALL(sys_pipe,compat_sys_pipe)
 SYSCALL(sys_times,compat_sys_times)
 NI_SYSCALL						/* old prof syscall */
@@ -65,13 +65,13 @@ NI_SYSCALL						/* old lock syscall */
 SYSCALL(sys_ioctl,compat_sys_ioctl)
 SYSCALL(sys_fcntl,compat_sys_fcntl)			/* 55 */
 NI_SYSCALL						/* intel mpx syscall */
-SYSCALL(sys_setpgid,compat_sys_setpgid)
+SYSCALL(sys_setpgid,sys_setpgid)
 NI_SYSCALL						/* old ulimit syscall */
 NI_SYSCALL						/* old uname syscall */
-SYSCALL(sys_umask,compat_sys_umask)			/* 60 */
+SYSCALL(sys_umask,sys_umask)				/* 60 */
 SYSCALL(sys_chroot,compat_sys_chroot)
 SYSCALL(sys_ustat,compat_sys_ustat)
-SYSCALL(sys_dup2,compat_sys_dup2)
+SYSCALL(sys_dup2,sys_dup2)
 SYSCALL(sys_getppid,sys_getppid)
 SYSCALL(sys_getpgrp,sys_getpgrp)			/* 65 */
 SYSCALL(sys_setsid,sys_setsid)
@@ -102,10 +102,10 @@ SYSCALL(sys_old_mmap,compat_sys_s390_old_mmap)		/* 90 */
 SYSCALL(sys_munmap,compat_sys_munmap)
 SYSCALL(sys_truncate,compat_sys_truncate)
 SYSCALL(sys_ftruncate,compat_sys_ftruncate)
-SYSCALL(sys_fchmod,compat_sys_fchmod)
+SYSCALL(sys_fchmod,sys_fchmod)
 SYSCALL(sys_ni_syscall,compat_sys_s390_fchown16)	/* 95 old fchown16 syscall*/
-SYSCALL(sys_getpriority,compat_sys_getpriority)
-SYSCALL(sys_setpriority,compat_sys_setpriority)
+SYSCALL(sys_getpriority,sys_getpriority)
+SYSCALL(sys_setpriority,sys_setpriority)
 NI_SYSCALL						/* old profil syscall */
 SYSCALL(sys_statfs,compat_sys_statfs)
 SYSCALL(sys_fstatfs,compat_sys_fstatfs)			/* 100 */
@@ -126,7 +126,7 @@ SYSCALL(sys_wait4,compat_sys_wait4)
 SYSCALL(sys_swapoff,compat_sys_swapoff)			/* 115 */
 SYSCALL(sys_sysinfo,compat_sys_sysinfo)
 SYSCALL(sys_s390_ipc,compat_sys_s390_ipc)
-SYSCALL(sys_fsync,compat_sys_fsync)
+SYSCALL(sys_fsync,sys_fsync)
 SYSCALL(sys_sigreturn,compat_sys_sigreturn)
 SYSCALL(sys_clone,compat_sys_clone)			/* 120 */
 SYSCALL(sys_setdomainname,compat_sys_setdomainname)
@@ -140,35 +140,35 @@ SYSCALL(sys_init_module,compat_sys_init_module)
 SYSCALL(sys_delete_module,compat_sys_delete_module)
 NI_SYSCALL						/* 130: old get_kernel_syms */
 SYSCALL(sys_quotactl,compat_sys_quotactl)
-SYSCALL(sys_getpgid,compat_sys_getpgid)
-SYSCALL(sys_fchdir,compat_sys_fchdir)
+SYSCALL(sys_getpgid,sys_getpgid)
+SYSCALL(sys_fchdir,sys_fchdir)
 SYSCALL(sys_bdflush,compat_sys_bdflush)
 SYSCALL(sys_sysfs,compat_sys_sysfs)			/* 135 */
-SYSCALL(sys_s390_personality,compat_sys_s390_personality)
+SYSCALL(sys_s390_personality,sys_s390_personality)
 NI_SYSCALL						/* for afs_syscall */
 SYSCALL(sys_ni_syscall,compat_sys_s390_setfsuid16)	/* old setfsuid16 syscall */
 SYSCALL(sys_ni_syscall,compat_sys_s390_setfsgid16)	/* old setfsgid16 syscall */
 SYSCALL(sys_llseek,compat_sys_llseek)			/* 140 */
 SYSCALL(sys_getdents,compat_sys_getdents)
 SYSCALL(sys_select,compat_sys_select)
-SYSCALL(sys_flock,compat_sys_flock)
+SYSCALL(sys_flock,sys_flock)
 SYSCALL(sys_msync,compat_sys_msync)
 SYSCALL(sys_readv,compat_sys_readv)			/* 145 */
 SYSCALL(sys_writev,compat_sys_writev)
-SYSCALL(sys_getsid,compat_sys_getsid)
-SYSCALL(sys_fdatasync,compat_sys_fdatasync)
+SYSCALL(sys_getsid,sys_getsid)
+SYSCALL(sys_fdatasync,sys_fdatasync)
 SYSCALL(sys_sysctl,compat_sys_sysctl)
 SYSCALL(sys_mlock,compat_sys_mlock)			/* 150 */
 SYSCALL(sys_munlock,compat_sys_munlock)
-SYSCALL(sys_mlockall,compat_sys_mlockall)
+SYSCALL(sys_mlockall,sys_mlockall)
 SYSCALL(sys_munlockall,sys_munlockall)
 SYSCALL(sys_sched_setparam,compat_sys_sched_setparam)
 SYSCALL(sys_sched_getparam,compat_sys_sched_getparam)	/* 155 */
 SYSCALL(sys_sched_setscheduler,compat_sys_sched_setscheduler)
-SYSCALL(sys_sched_getscheduler,compat_sys_sched_getscheduler)
+SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler)
 SYSCALL(sys_sched_yield,sys_sched_yield)
-SYSCALL(sys_sched_get_priority_max,compat_sys_sched_get_priority_max)
-SYSCALL(sys_sched_get_priority_min,compat_sys_sched_get_priority_min)	/* 160 */
+SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max)
+SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min)	/* 160 */
 SYSCALL(sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval)
 SYSCALL(sys_nanosleep,compat_sys_nanosleep)
 SYSCALL(sys_mremap,compat_sys_mremap)
@@ -211,20 +211,20 @@ SYSCALL(sys_getuid,sys_getuid)
 SYSCALL(sys_getgid,sys_getgid)				/* 200 */
 SYSCALL(sys_geteuid,sys_geteuid)
 SYSCALL(sys_getegid,sys_getegid)
-SYSCALL(sys_setreuid,compat_sys_setreuid)
-SYSCALL(sys_setregid,compat_sys_setregid)
+SYSCALL(sys_setreuid,sys_setreuid)
+SYSCALL(sys_setregid,sys_setregid)
 SYSCALL(sys_getgroups,compat_sys_getgroups)		/* 205 */
 SYSCALL(sys_setgroups,compat_sys_setgroups)
-SYSCALL(sys_fchown,compat_sys_fchown)
-SYSCALL(sys_setresuid,compat_sys_setresuid)
+SYSCALL(sys_fchown,sys_fchown)
+SYSCALL(sys_setresuid,sys_setresuid)
 SYSCALL(sys_getresuid,compat_sys_getresuid)
-SYSCALL(sys_setresgid,compat_sys_setresgid)		/* 210 */
+SYSCALL(sys_setresgid,sys_setresgid)			/* 210 */
 SYSCALL(sys_getresgid,compat_sys_getresgid)
 SYSCALL(sys_chown,compat_sys_chown)
-SYSCALL(sys_setuid,compat_sys_setuid)
-SYSCALL(sys_setgid,compat_sys_setgid)
-SYSCALL(sys_setfsuid,compat_sys_setfsuid)		/* 215 */
-SYSCALL(sys_setfsgid,compat_sys_setfsgid)
+SYSCALL(sys_setuid,sys_setuid)
+SYSCALL(sys_setgid,sys_setgid)
+SYSCALL(sys_setfsuid,sys_setfsuid)			/* 215 */
+SYSCALL(sys_setfsgid,sys_setfsgid)
 SYSCALL(sys_pivot_root,compat_sys_pivot_root)
 SYSCALL(sys_mincore,compat_sys_mincore)
 SYSCALL(sys_madvise,compat_sys_madvise)
@@ -245,19 +245,19 @@ SYSCALL(sys_removexattr,compat_sys_removexattr)
 SYSCALL(sys_lremovexattr,compat_sys_lremovexattr)
 SYSCALL(sys_fremovexattr,compat_sys_fremovexattr)	/* 235 */
 SYSCALL(sys_gettid,sys_gettid)
-SYSCALL(sys_tkill,compat_sys_tkill)
+SYSCALL(sys_tkill,sys_tkill)
 SYSCALL(sys_futex,compat_sys_futex)
 SYSCALL(sys_sched_setaffinity,compat_sys_sched_setaffinity)
 SYSCALL(sys_sched_getaffinity,compat_sys_sched_getaffinity)	/* 240 */
-SYSCALL(sys_tgkill,compat_sys_tgkill)
+SYSCALL(sys_tgkill,sys_tgkill)
 NI_SYSCALL						/* reserved for TUX */
 SYSCALL(sys_io_setup,compat_sys_io_setup)
 SYSCALL(sys_io_destroy,compat_sys_io_destroy)
 SYSCALL(sys_io_getevents,compat_sys_io_getevents)	/* 245 */
 SYSCALL(sys_io_submit,compat_sys_io_submit)
 SYSCALL(sys_io_cancel,compat_sys_io_cancel)
-SYSCALL(sys_exit_group,compat_sys_exit_group)
-SYSCALL(sys_epoll_create,compat_sys_epoll_create)
+SYSCALL(sys_exit_group,sys_exit_group)
+SYSCALL(sys_epoll_create,sys_epoll_create)
 SYSCALL(sys_epoll_ctl,compat_sys_epoll_ctl)		/* 250 */
 SYSCALL(sys_epoll_wait,compat_sys_epoll_wait)
 SYSCALL(sys_set_tid_address,compat_sys_set_tid_address)
@@ -265,8 +265,8 @@ SYSCALL(sys_fadvise64_64,compat_sys_s390_fadvise64)
 SYSCALL(sys_timer_create,compat_sys_timer_create)
 SYSCALL(sys_timer_settime,compat_sys_timer_settime)	/* 255 */
 SYSCALL(sys_timer_gettime,compat_sys_timer_gettime)
-SYSCALL(sys_timer_getoverrun,compat_sys_timer_getoverrun)
-SYSCALL(sys_timer_delete,compat_sys_timer_delete)
+SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun)
+SYSCALL(sys_timer_delete,sys_timer_delete)
 SYSCALL(sys_clock_settime,compat_sys_clock_settime)
 SYSCALL(sys_clock_gettime,compat_sys_clock_gettime)	/* 260 */
 SYSCALL(sys_clock_getres,compat_sys_clock_getres)
@@ -290,11 +290,11 @@ SYSCALL(sys_add_key,compat_sys_add_key)
 SYSCALL(sys_request_key,compat_sys_request_key)
 SYSCALL(sys_keyctl,compat_sys_keyctl)			/* 280 */
 SYSCALL(sys_waitid,compat_sys_waitid)
-SYSCALL(sys_ioprio_set,compat_sys_ioprio_set)
-SYSCALL(sys_ioprio_get,compat_sys_ioprio_get)
+SYSCALL(sys_ioprio_set,sys_ioprio_set)
+SYSCALL(sys_ioprio_get,sys_ioprio_get)
 SYSCALL(sys_inotify_init,sys_inotify_init)
 SYSCALL(sys_inotify_add_watch,compat_sys_inotify_add_watch)	/* 285 */
-SYSCALL(sys_inotify_rm_watch,compat_sys_inotify_rm_watch)
+SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch)
 SYSCALL(sys_migrate_pages,compat_sys_migrate_pages)
 SYSCALL(sys_openat,compat_sys_openat)
 SYSCALL(sys_mkdirat,compat_sys_mkdirat)
@@ -326,31 +326,31 @@ SYSCALL(sys_fallocate,compat_sys_s390_fallocate)
 SYSCALL(sys_utimensat,compat_sys_utimensat)		/* 315 */
 SYSCALL(sys_signalfd,compat_sys_signalfd)
 NI_SYSCALL						/* 317 old sys_timer_fd */
-SYSCALL(sys_eventfd,compat_sys_eventfd)
-SYSCALL(sys_timerfd_create,compat_sys_timerfd_create)
+SYSCALL(sys_eventfd,sys_eventfd)
+SYSCALL(sys_timerfd_create,sys_timerfd_create)
 SYSCALL(sys_timerfd_settime,compat_sys_timerfd_settime) /* 320 */
 SYSCALL(sys_timerfd_gettime,compat_sys_timerfd_gettime)
 SYSCALL(sys_signalfd4,compat_sys_signalfd4)
-SYSCALL(sys_eventfd2,compat_sys_eventfd2)
-SYSCALL(sys_inotify_init1,compat_sys_inotify_init1)
+SYSCALL(sys_eventfd2,sys_eventfd2)
+SYSCALL(sys_inotify_init1,sys_inotify_init1)
 SYSCALL(sys_pipe2,compat_sys_pipe2)			/* 325 */
-SYSCALL(sys_dup3,compat_sys_dup3)
-SYSCALL(sys_epoll_create1,compat_sys_epoll_create1)
+SYSCALL(sys_dup3,sys_dup3)
+SYSCALL(sys_epoll_create1,sys_epoll_create1)
 SYSCALL(sys_preadv,compat_sys_preadv)
 SYSCALL(sys_pwritev,compat_sys_pwritev)
 SYSCALL(sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo) /* 330 */
 SYSCALL(sys_perf_event_open,compat_sys_perf_event_open)
-SYSCALL(sys_fanotify_init,compat_sys_fanotify_init)
+SYSCALL(sys_fanotify_init,sys_fanotify_init)
 SYSCALL(sys_fanotify_mark,compat_sys_fanotify_mark)
 SYSCALL(sys_prlimit64,compat_sys_prlimit64)
 SYSCALL(sys_name_to_handle_at,compat_sys_name_to_handle_at) /* 335 */
 SYSCALL(sys_open_by_handle_at,compat_sys_open_by_handle_at)
 SYSCALL(sys_clock_adjtime,compat_sys_clock_adjtime)
-SYSCALL(sys_syncfs,compat_sys_syncfs)
-SYSCALL(sys_setns,compat_sys_setns)
+SYSCALL(sys_syncfs,sys_syncfs)
+SYSCALL(sys_setns,sys_setns)
 SYSCALL(sys_process_vm_readv,compat_sys_process_vm_readv) /* 340 */
 SYSCALL(sys_process_vm_writev,compat_sys_process_vm_writev)
-SYSCALL(sys_s390_runtime_instr,compat_sys_s390_runtime_instr)
+SYSCALL(sys_s390_runtime_instr,sys_s390_runtime_instr)
 SYSCALL(sys_kcmp,compat_sys_kcmp)
 SYSCALL(sys_finit_module,compat_sys_finit_module)
 SYSCALL(sys_sched_setattr,compat_sys_sched_setattr)	/* 345 */
@@ -363,3 +363,22 @@ SYSCALL(sys_bpf,compat_sys_bpf)
 SYSCALL(sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write)
 SYSCALL(sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read)
 SYSCALL(sys_execveat,compat_sys_execveat)
+SYSCALL(sys_userfaultfd,sys_userfaultfd)		/* 355 */
+SYSCALL(sys_membarrier,sys_membarrier)
+SYSCALL(sys_recvmmsg,compat_sys_recvmmsg)
+SYSCALL(sys_sendmmsg,compat_sys_sendmmsg)
+SYSCALL(sys_socket,sys_socket)
+SYSCALL(sys_socketpair,compat_sys_socketpair)		/* 360 */
+SYSCALL(sys_bind,sys_bind)
+SYSCALL(sys_connect,sys_connect)
+SYSCALL(sys_listen,sys_listen)
+SYSCALL(sys_accept4,sys_accept4)
+SYSCALL(sys_getsockopt,compat_sys_getsockopt)		/* 365 */
+SYSCALL(sys_setsockopt,compat_sys_setsockopt)
+SYSCALL(sys_getsockname,compat_sys_getsockname)
+SYSCALL(sys_getpeername,compat_sys_getpeername)
+SYSCALL(sys_sendto,compat_sys_sendto)
+SYSCALL(sys_sendmsg,compat_sys_sendmsg)			/* 370 */
+SYSCALL(sys_recvfrom,compat_sys_recvfrom)
+SYSCALL(sys_recvmsg,compat_sys_recvmsg)
+SYSCALL(sys_shutdown,sys_shutdown)
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index b9ce650e9e99..c8653435c70d 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -89,17 +89,21 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 	if (smp_cpu_mtid &&
 	    time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) {
 		u64 cycles_new[32], *cycles_old;
-		u64 delta, mult, div;
+		u64 delta, fac, mult, div;
 
 		cycles_old = this_cpu_ptr(mt_cycles);
 		if (stcctm5(smp_cpu_mtid + 1, cycles_new) < 2) {
+			fac = 1;
 			mult = div = 0;
 			for (i = 0; i <= smp_cpu_mtid; i++) {
 				delta = cycles_new[i] - cycles_old[i];
-				mult += delta;
-				div += (i + 1) * delta;
+				div += delta;
+				mult *= i + 1;
+				mult += delta * fac;
+				fac *= i + 1;
 			}
-			if (mult > 0) {
+			div *= fac;
+			if (div > 0) {
 				/* Update scaling factor */
 				__this_cpu_write(mt_scaling_mult, mult);
 				__this_cpu_write(mt_scaling_div, div);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 155162ea0e00..ab5f1d447ef9 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -86,6 +86,16 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 					u32 type, u64 attribute);
 
+/*
+ * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
+ * only in kernel binary.  Since the EFI stub linked into a separate binary it
+ * doesn't have __memset().  So we should use standard memset from
+ * arch/x86/boot/compressed/string.c.  The same applies to memcpy and memmove.
+ */
+#undef memcpy
+#undef memset
+#undef memmove
+
 #endif /* CONFIG_X86_32 */
 
 extern struct efi_scratch efi_scratch;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 349f80a82b82..2beee0382088 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -40,6 +40,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c1c0a1c14344..b98b471a3b7e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -331,6 +331,7 @@
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
 #define MSR_K8_TSEG_ADDR		0xc0010112
+#define MSR_K8_TSEG_MASK		0xc0010113
 #define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
 #define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 69088a1ba509..ff606f507913 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3322,7 +3322,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 			break;
 
 		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
-						    leaf);
+						    iterator.level);
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3614,7 +3614,7 @@ static void
 __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			struct rsvd_bits_validate *rsvd_check,
 			int maxphyaddr, int level, bool nx, bool gbpages,
-			bool pse)
+			bool pse, bool amd)
 {
 	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
@@ -3631,7 +3631,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	 * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
 	 * leaf entries) on AMD CPUs only.
 	 */
-	if (guest_cpuid_is_amd(vcpu))
+	if (amd)
 		nonleaf_bit8_rsvd = rsvd_bits(8, 8);
 
 	switch (level) {
@@ -3699,7 +3699,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
 				cpuid_maxphyaddr(vcpu), context->root_level,
 				context->nx, guest_cpuid_has_gbpages(vcpu),
-				is_pse(vcpu));
+				is_pse(vcpu), guest_cpuid_is_amd(vcpu));
 }
 
 static void
@@ -3749,13 +3749,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
+	/*
+	 * Passing "true" to the last argument is okay; it adds a check
+	 * on bit 8 of the SPTEs which KVM doesn't use anyway.
+	 */
 	__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 				boot_cpu_data.x86_phys_bits,
 				context->shadow_root_level, context->nx,
-				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
+				true);
 }
 EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
 
+static inline bool boot_cpu_is_amd(void)
+{
+	WARN_ON_ONCE(!tdp_enabled);
+	return shadow_x_mask == 0;
+}
+
 /*
  * the direct page table on host, use as much mmu features as
  * possible, however, kvm currently does not do execution-protection.
@@ -3764,11 +3775,11 @@ static void
 reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context)
 {
-	if (guest_cpuid_is_amd(vcpu))
+	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 					boot_cpu_data.x86_phys_bits,
 					context->shadow_root_level, false,
-					cpu_has_gbpages, true);
+					cpu_has_gbpages, true, true);
 	else
 		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
 					    boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fdb8cb63a6c0..94b7d15db3fc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -202,6 +202,7 @@ module_param(npt, int, S_IRUGO);
 static int nested = true;
 module_param(nested, int, S_IRUGO);
 
+static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
 
@@ -1263,7 +1264,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
 	 * It also updates the guest-visible cr0 value.
 	 */
-	(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	kvm_mmu_reset_context(&svm->vcpu);
 
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6bbb0dfb99d0..991466bf8dee 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2190,6 +2190,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
 	case MSR_K8_SYSCFG:
+	case MSR_K8_TSEG_ADDR:
+	case MSR_K8_TSEG_MASK:
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K8_INT_PENDING_MSG:
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 09d3afc0a181..dc78a4a9a466 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -166,6 +166,7 @@ void pcibios_fixup_bus(struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
+	pci_read_bridge_bases(b);
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
 }
diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c
index d27b4dcf221f..b848cc3dc913 100644
--- a/arch/xtensa/kernel/pci.c
+++ b/arch/xtensa/kernel/pci.c
@@ -210,6 +210,10 @@ subsys_initcall(pcibios_init);
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
+	if (bus->parent) {
+		/* This is a subordinate bridge */
+		pci_read_bridge_bases(bus);
+	}
 }
 
 void pcibios_set_master(struct pci_dev *dev)
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index a8da3a50e374..0f5cb37636bc 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -1578,9 +1578,7 @@ he_stop(struct he_dev *he_dev)
 
 	kfree(he_dev->rbpl_virt);
 	kfree(he_dev->rbpl_table);
-
-	if (he_dev->rbpl_pool)
-		dma_pool_destroy(he_dev->rbpl_pool);
+	dma_pool_destroy(he_dev->rbpl_pool);
 
 	if (he_dev->rbrq_base)
 		dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_RBRQ_SIZE * sizeof(struct he_rbrq),
@@ -1594,8 +1592,7 @@ he_stop(struct he_dev *he_dev)
 		dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_TBRQ_SIZE * sizeof(struct he_tbrq),
 				  he_dev->tpdrq_base, he_dev->tpdrq_phys);
 
-	if (he_dev->tpd_pool)
-		dma_pool_destroy(he_dev->tpd_pool);
+	dma_pool_destroy(he_dev->tpd_pool);
 
 	if (he_dev->pci_dev) {
 		pci_read_config_word(he_dev->pci_dev, PCI_COMMAND, &command);
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 74e18b0a6d89..3d7fb6516f74 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -805,7 +805,12 @@ static void solos_bh(unsigned long card_arg)
 					continue;
 				}
 
-				skb = alloc_skb(size + 1, GFP_ATOMIC);
+				/* Use netdev_alloc_skb() because it adds NET_SKB_PAD of
+				 * headroom, and ensures we can route packets back out an
+				 * Ethernet interface (for example) without having to
+				 * reallocate. Adding NET_IP_ALIGN also ensures that both
+				 * PPPoATM and PPPoEoBR2684 packets end up aligned. */
+				skb = netdev_alloc_skb_ip_align(NULL, size + 1);
 				if (!skb) {
 					if (net_ratelimit())
 						dev_warn(&card->dev->dev, "Failed to allocate sk_buff for RX\n");
@@ -869,7 +874,10 @@ static void solos_bh(unsigned long card_arg)
 		/* Allocate RX skbs for any ports which need them */
 		if (card->using_dma && card->atmdev[port] &&
 		    !card->rx_skb[port]) {
-			struct sk_buff *skb = alloc_skb(RX_DMA_SIZE, GFP_ATOMIC);
+			/* Unlike the MMIO case (qv) we can't add NET_IP_ALIGN
+			 * here; the FPGA can only DMA to addresses which are
+			 * aligned to 4 bytes. */
+			struct sk_buff *skb = dev_alloc_skb(RX_DMA_SIZE);
 			if (skb) {
 				SKB_CB(skb)->dma_addr =
 					dma_map_single(&card->dev->dev, skb->data,
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 764280a91776..e9fd32e91668 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -148,7 +148,11 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 			if (sibling == cpu) /* skip itself */
 				continue;
+
 			sib_cpu_ci = get_cpu_cacheinfo(sibling);
+			if (!sib_cpu_ci->info_list)
+				continue;
+
 			sib_leaf = sib_cpu_ci->info_list + index;
 			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
 			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
@@ -159,6 +163,9 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 static void free_cache_attributes(unsigned int cpu)
 {
+	if (!per_cpu_cacheinfo(cpu))
+		return;
+
 	cache_shared_cpu_map_remove(cpu);
 
 	kfree(per_cpu_cacheinfo(cpu));
@@ -514,8 +521,7 @@ static int cacheinfo_cpu_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DEAD:
 		cache_remove_dev(cpu);
-		if (per_cpu_cacheinfo(cpu))
-			free_cache_attributes(cpu);
+		free_cache_attributes(cpu);
 		break;
 	}
 	return notifier_from_errno(rc);
diff --git a/drivers/char/hw_random/xgene-rng.c b/drivers/char/hw_random/xgene-rng.c
index c37cf754a985..3c77645405e5 100644
--- a/drivers/char/hw_random/xgene-rng.c
+++ b/drivers/char/hw_random/xgene-rng.c
@@ -344,11 +344,12 @@ static int xgene_rng_probe(struct platform_device *pdev)
 	if (IS_ERR(ctx->csr_base))
 		return PTR_ERR(ctx->csr_base);
 
-	ctx->irq = platform_get_irq(pdev, 0);
-	if (ctx->irq < 0) {
+	rc = platform_get_irq(pdev, 0);
+	if (rc < 0) {
 		dev_err(&pdev->dev, "No IRQ resource\n");
-		return ctx->irq;
+		return rc;
 	}
+	ctx->irq = rc;
 
 	dev_dbg(&pdev->dev, "APM X-Gene RNG BASE %p ALARM IRQ %d",
 		ctx->csr_base, ctx->irq);
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index b60698b30d30..bc2a55bc35e4 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -687,6 +687,33 @@ static inline u32 mv_cesa_get_int_mask(struct mv_cesa_engine *engine)
 
 int mv_cesa_queue_req(struct crypto_async_request *req);
 
+/*
+ * Helper function that indicates whether a crypto request needs to be
+ * cleaned up or not after being enqueued using mv_cesa_queue_req().
+ */
+static inline int mv_cesa_req_needs_cleanup(struct crypto_async_request *req,
+					    int ret)
+{
+	/*
+	 * The queue still had some space, the request was queued
+	 * normally, so there's no need to clean it up.
+	 */
+	if (ret == -EINPROGRESS)
+		return false;
+
+	/*
+	 * The queue had not space left, but since the request is
+	 * flagged with CRYPTO_TFM_REQ_MAY_BACKLOG, it was added to
+	 * the backlog and will be processed later. There's no need to
+	 * clean it up.
+	 */
+	if (ret == -EBUSY && req->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)
+		return false;
+
+	/* Request wasn't queued, we need to clean it up */
+	return true;
+}
+
 /* TDMA functions */
 
 static inline void mv_cesa_req_dma_iter_init(struct mv_cesa_dma_iter *iter,
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index 0745cf3b9c0e..3df2f4e7adb2 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -189,7 +189,6 @@ static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-
 	creq->req.base.engine = engine;
 
 	if (creq->req.base.type == CESA_DMA_REQ)
@@ -431,7 +430,7 @@ static int mv_cesa_des_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -551,7 +550,7 @@ static int mv_cesa_des3_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -693,7 +692,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index ae9272eb9c1a..e8d0d7128137 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -739,10 +739,8 @@ static int mv_cesa_ahash_update(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS) {
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
-		return ret;
-	}
 
 	return ret;
 }
@@ -766,7 +764,7 @@ static int mv_cesa_ahash_final(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
@@ -791,7 +789,7 @@ static int mv_cesa_ahash_finup(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index a57b4194de28..0a5ca0ba5d64 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -88,6 +88,9 @@ static void adf_dev_restore(struct adf_accel_dev *accel_dev)
 	struct pci_dev *parent = pdev->bus->self;
 	uint16_t bridge_ctl = 0;
 
+	if (accel_dev->is_vf)
+		return;
+
 	dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
 		 accel_dev->accel_id);
 
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index a07addde297b..8dd0af1d50bc 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -159,7 +159,7 @@ static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
 static bool is_extcon_changed(u32 prev, u32 new, int idx, bool *attached)
 {
 	if (((prev >> idx) & 0x1) != ((new >> idx) & 0x1)) {
-		*attached = new ? true : false;
+		*attached = ((new >> idx) & 0x1) ? true : false;
 		return true;
 	}
 
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index d8de6a8dd4de..665efca59487 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -139,6 +139,14 @@ config QCOM_SCM
 	bool
 	depends on ARM || ARM64
 
+config QCOM_SCM_32
+	def_bool y
+	depends on QCOM_SCM && ARM
+
+config QCOM_SCM_64
+	def_bool y
+	depends on QCOM_SCM && ARM64
+
 source "drivers/firmware/broadcom/Kconfig"
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 000830fc6707..2ee83474a3c1 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -13,7 +13,8 @@ obj-$(CONFIG_ISCSI_IBFT_FIND)	+= iscsi_ibft_find.o
 obj-$(CONFIG_ISCSI_IBFT)	+= iscsi_ibft.o
 obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
 obj-$(CONFIG_QCOM_SCM)		+= qcom_scm.o
-obj-$(CONFIG_QCOM_SCM)		+= qcom_scm-32.o
+obj-$(CONFIG_QCOM_SCM_64)	+= qcom_scm-64.o
+obj-$(CONFIG_QCOM_SCM_32)	+= qcom_scm-32.o
 CFLAGS_qcom_scm-32.o :=$(call as-instr,.arch_extension sec,-DREQUIRES_SEC=1)
 
 obj-y				+= broadcom/
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index e334a01cf92f..6b6548fda089 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -5,10 +5,6 @@
 /* error code which can't be mistaken for valid address */
 #define EFI_ERROR	(~0UL)
 
-#undef memcpy
-#undef memset
-#undef memmove
-
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
new file mode 100644
index 000000000000..bb6555f6d63b
--- /dev/null
+++ b/drivers/firmware/qcom_scm-64.c
@@ -0,0 +1,63 @@
+/* Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/qcom_scm.h>
+
+/**
+ * qcom_scm_set_cold_boot_addr() - Set the cold boot address for cpus
+ * @entry: Entry point function for the cpus
+ * @cpus: The cpumask of cpus that will use the entry point
+ *
+ * Set the cold boot address of the cpus. Any cpu outside the supported
+ * range would be removed from the cpu present mask.
+ */
+int __qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * qcom_scm_set_warm_boot_addr() - Set the warm boot address for cpus
+ * @entry: Entry point function for the cpus
+ * @cpus: The cpumask of cpus that will use the entry point
+ *
+ * Set the Linux entry point for the SCM to transfer control to when coming
+ * out of a power down. CPU power down may be executed on cpuidle or hotplug.
+ */
+int __qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * qcom_scm_cpu_power_down() - Power down the cpu
+ * @flags - Flags to flush cache
+ *
+ * This is an end point to power down cpu. If there was a pending interrupt,
+ * the control would return from this function, otherwise, the cpu jumps to the
+ * warm boot entry point set for this cpu upon reset.
+ */
+void __qcom_scm_cpu_power_down(u32 flags)
+{
+}
+
+int __qcom_scm_is_call_available(u32 svc_id, u32 cmd_id)
+{
+	return -ENOTSUPP;
+}
+
+int __qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp)
+{
+	return -ENOTSUPP;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 668939a14206..6647fb26ef25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -82,6 +82,7 @@ extern int amdgpu_vm_block_size;
 extern int amdgpu_enable_scheduler;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
+extern int amdgpu_enable_semaphores;
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -432,7 +433,7 @@ int amdgpu_fence_driver_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
 void amdgpu_fence_driver_force_completion(struct amdgpu_device *adev);
 
-void amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring);
+int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring);
 int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 				   struct amdgpu_irq_src *irq_src,
 				   unsigned irq_type);
@@ -890,7 +891,7 @@ struct amdgpu_ring {
 	struct amdgpu_device		*adev;
 	const struct amdgpu_ring_funcs	*funcs;
 	struct amdgpu_fence_driver	fence_drv;
-	struct amd_gpu_scheduler 	*scheduler;
+	struct amd_gpu_scheduler 	sched;
 
 	spinlock_t              fence_lock;
 	struct mutex		*ring_lock;
@@ -1201,8 +1202,6 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_inst_irq;
 	/* gfx status */
 	uint32_t gfx_current_status;
-	/* sync signal for const engine */
-	unsigned ce_sync_offs;
 	/* ce ram size*/
 	unsigned ce_ram_size;
 };
@@ -1274,8 +1273,10 @@ struct amdgpu_job {
 	uint32_t		num_ibs;
 	struct mutex            job_lock;
 	struct amdgpu_user_fence uf;
-	int (*free_job)(struct amdgpu_job *sched_job);
+	int (*free_job)(struct amdgpu_job *job);
 };
+#define to_amdgpu_job(sched_job)		\
+		container_of((sched_job), struct amdgpu_job, base)
 
 static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p, uint32_t ib_idx, int idx)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 496ed2192eba..84d68d658f8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -183,7 +183,7 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 		return -ENOMEM;
 
 	r = amdgpu_bo_create(rdev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_GTT,
-			AMDGPU_GEM_CREATE_CPU_GTT_USWC, NULL, &(*mem)->bo);
+			     AMDGPU_GEM_CREATE_CPU_GTT_USWC, NULL, NULL, &(*mem)->bo);
 	if (r) {
 		dev_err(rdev->dev,
 			"failed to allocate BO for amdkfd (%d)\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 98d59ee640ce..cd639c362df3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -79,7 +79,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	int time;
 
 	n = AMDGPU_BENCHMARK_ITERATIONS;
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, sdomain, 0, NULL, &sobj);
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, sdomain, 0, NULL,
+			     NULL, &sobj);
 	if (r) {
 		goto out_cleanup;
 	}
@@ -91,7 +92,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	if (r) {
 		goto out_cleanup;
 	}
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, ddomain, 0, NULL, &dobj);
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, ddomain, 0, NULL,
+			     NULL, &dobj);
 	if (r) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 6b1243f9f86d..1c3fc99c5465 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -86,7 +86,7 @@ static int amdgpu_cgs_gmap_kmem(void *cgs_device, void *kmem,
 
 	struct sg_table *sg = drm_prime_pages_to_sg(&kmem_page, npages);
 	ret = amdgpu_bo_create(adev, size, PAGE_SIZE, false,
-			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, &bo);
+			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, NULL, &bo);
 	if (ret)
 		return ret;
 	ret = amdgpu_bo_reserve(bo, false);
@@ -197,7 +197,8 @@ static int amdgpu_cgs_alloc_gpu_mem(void *cgs_device,
 
 	ret = amdgpu_bo_create_restricted(adev, size, PAGE_SIZE,
 					  true, domain, flags,
-					  NULL, &placement, &obj);
+					  NULL, &placement, NULL,
+					  &obj);
 	if (ret) {
 		DRM_ERROR("(%d) bo create failed\n", ret);
 		return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 3b355aeb62fd..749420f1ea6f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -154,42 +154,41 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 {
 	union drm_amdgpu_cs *cs = data;
 	uint64_t *chunk_array_user;
-	uint64_t *chunk_array = NULL;
+	uint64_t *chunk_array;
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	unsigned size, i;
-	int r = 0;
+	int ret;
 
-	if (!cs->in.num_chunks)
-		goto out;
+	if (cs->in.num_chunks == 0)
+		return 0;
+
+	chunk_array = kmalloc_array(cs->in.num_chunks, sizeof(uint64_t), GFP_KERNEL);
+	if (!chunk_array)
+		return -ENOMEM;
 
 	p->ctx = amdgpu_ctx_get(fpriv, cs->in.ctx_id);
 	if (!p->ctx) {
-		r = -EINVAL;
-		goto out;
+		ret = -EINVAL;
+		goto free_chunk;
 	}
+
 	p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
 
 	/* get chunks */
 	INIT_LIST_HEAD(&p->validated);
-	chunk_array = kmalloc_array(cs->in.num_chunks, sizeof(uint64_t), GFP_KERNEL);
-	if (chunk_array == NULL) {
-		r = -ENOMEM;
-		goto out;
-	}
-
 	chunk_array_user = (uint64_t __user *)(cs->in.chunks);
 	if (copy_from_user(chunk_array, chunk_array_user,
 			   sizeof(uint64_t)*cs->in.num_chunks)) {
-		r = -EFAULT;
-		goto out;
+		ret = -EFAULT;
+		goto put_bo_list;
 	}
 
 	p->nchunks = cs->in.num_chunks;
 	p->chunks = kmalloc_array(p->nchunks, sizeof(struct amdgpu_cs_chunk),
 			    GFP_KERNEL);
-	if (p->chunks == NULL) {
-		r = -ENOMEM;
-		goto out;
+	if (!p->chunks) {
+		ret = -ENOMEM;
+		goto put_bo_list;
 	}
 
 	for (i = 0; i < p->nchunks; i++) {
@@ -200,8 +199,9 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 		chunk_ptr = (void __user *)chunk_array[i];
 		if (copy_from_user(&user_chunk, chunk_ptr,
 				       sizeof(struct drm_amdgpu_cs_chunk))) {
-			r = -EFAULT;
-			goto out;
+			ret = -EFAULT;
+			i--;
+			goto free_partial_kdata;
 		}
 		p->chunks[i].chunk_id = user_chunk.chunk_id;
 		p->chunks[i].length_dw = user_chunk.length_dw;
@@ -212,13 +212,14 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 
 		p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t));
 		if (p->chunks[i].kdata == NULL) {
-			r = -ENOMEM;
-			goto out;
+			ret = -ENOMEM;
+			i--;
+			goto free_partial_kdata;
 		}
 		size *= sizeof(uint32_t);
 		if (copy_from_user(p->chunks[i].kdata, cdata, size)) {
-			r = -EFAULT;
-			goto out;
+			ret = -EFAULT;
+			goto free_partial_kdata;
 		}
 
 		switch (p->chunks[i].chunk_id) {
@@ -238,15 +239,15 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 				gobj = drm_gem_object_lookup(p->adev->ddev,
 							     p->filp, handle);
 				if (gobj == NULL) {
-					r = -EINVAL;
-					goto out;
+					ret = -EINVAL;
+					goto free_partial_kdata;
 				}
 
 				p->uf.bo = gem_to_amdgpu_bo(gobj);
 				p->uf.offset = fence_data->offset;
 			} else {
-				r = -EINVAL;
-				goto out;
+				ret = -EINVAL;
+				goto free_partial_kdata;
 			}
 			break;
 
@@ -254,19 +255,35 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 			break;
 
 		default:
-			r = -EINVAL;
-			goto out;
+			ret = -EINVAL;
+			goto free_partial_kdata;
 		}
 	}
 
 
 	p->ibs = kcalloc(p->num_ibs, sizeof(struct amdgpu_ib), GFP_KERNEL);
-	if (!p->ibs)
-		r = -ENOMEM;
+	if (!p->ibs) {
+		ret = -ENOMEM;
+		goto free_all_kdata;
+	}
 
-out:
 	kfree(chunk_array);
-	return r;
+	return 0;
+
+free_all_kdata:
+	i = p->nchunks - 1;
+free_partial_kdata:
+	for (; i >= 0; i--)
+		drm_free_large(p->chunks[i].kdata);
+	kfree(p->chunks);
+put_bo_list:
+	if (p->bo_list)
+		amdgpu_bo_list_put(p->bo_list);
+	amdgpu_ctx_put(p->ctx);
+free_chunk:
+	kfree(chunk_array);
+
+	return ret;
 }
 
 /* Returns how many bytes TTM can move per IB.
@@ -321,25 +338,17 @@ static u64 amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev)
 	return max(bytes_moved_threshold, 1024*1024ull);
 }
 
-int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p)
+int amdgpu_cs_list_validate(struct amdgpu_device *adev,
+			    struct amdgpu_vm *vm,
+			    struct list_head *validated)
 {
-	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
-	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_device *adev = p->adev;
 	struct amdgpu_bo_list_entry *lobj;
-	struct list_head duplicates;
 	struct amdgpu_bo *bo;
 	u64 bytes_moved = 0, initial_bytes_moved;
 	u64 bytes_moved_threshold = amdgpu_cs_get_threshold_for_moves(adev);
 	int r;
 
-	INIT_LIST_HEAD(&duplicates);
-	r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true, &duplicates);
-	if (unlikely(r != 0)) {
-		return r;
-	}
-
-	list_for_each_entry(lobj, &p->validated, tv.head) {
+	list_for_each_entry(lobj, validated, tv.head) {
 		bo = lobj->robj;
 		if (!bo->pin_count) {
 			u32 domain = lobj->prefered_domains;
@@ -373,7 +382,6 @@ int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p)
 					domain = lobj->allowed_domains;
 					goto retry;
 				}
-				ttm_eu_backoff_reservation(&p->ticket, &p->validated);
 				return r;
 			}
 		}
@@ -386,6 +394,7 @@ static int amdgpu_cs_parser_relocs(struct amdgpu_cs_parser *p)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_cs_buckets buckets;
+	struct list_head duplicates;
 	bool need_mmap_lock = false;
 	int i, r;
 
@@ -405,8 +414,22 @@ static int amdgpu_cs_parser_relocs(struct amdgpu_cs_parser *p)
 	if (need_mmap_lock)
 		down_read(&current->mm->mmap_sem);
 
-	r = amdgpu_cs_list_validate(p);
+	INIT_LIST_HEAD(&duplicates);
+	r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true, &duplicates);
+	if (unlikely(r != 0))
+		goto error_reserve;
+
+	r = amdgpu_cs_list_validate(p->adev, &fpriv->vm, &p->validated);
+	if (r)
+		goto error_validate;
+
+	r = amdgpu_cs_list_validate(p->adev, &fpriv->vm, &duplicates);
+
+error_validate:
+	if (r)
+		ttm_eu_backoff_reservation(&p->ticket, &p->validated);
 
+error_reserve:
 	if (need_mmap_lock)
 		up_read(&current->mm->mmap_sem);
 
@@ -772,15 +795,15 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int amdgpu_cs_free_job(struct amdgpu_job *sched_job)
+static int amdgpu_cs_free_job(struct amdgpu_job *job)
 {
 	int i;
-	if (sched_job->ibs)
-		for (i = 0; i < sched_job->num_ibs; i++)
-			amdgpu_ib_free(sched_job->adev, &sched_job->ibs[i]);
-	kfree(sched_job->ibs);
-	if (sched_job->uf.bo)
-		drm_gem_object_unreference_unlocked(&sched_job->uf.bo->gem_base);
+	if (job->ibs)
+		for (i = 0; i < job->num_ibs; i++)
+			amdgpu_ib_free(job->adev, &job->ibs[i]);
+	kfree(job->ibs);
+	if (job->uf.bo)
+		drm_gem_object_unreference_unlocked(&job->uf.bo->gem_base);
 	return 0;
 }
 
@@ -804,7 +827,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	r = amdgpu_cs_parser_init(parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
-		amdgpu_cs_parser_fini(parser, r, false);
+		kfree(parser);
 		up_read(&adev->exclusive_lock);
 		r = amdgpu_cs_handle_lockup(adev, r);
 		return r;
@@ -842,7 +865,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
 		if (!job)
 			return -ENOMEM;
-		job->base.sched = ring->scheduler;
+		job->base.sched = &ring->sched;
 		job->base.s_entity = &parser->ctx->rings[ring->idx].entity;
 		job->adev = parser->adev;
 		job->ibs = parser->ibs;
@@ -857,7 +880,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 		job->free_job = amdgpu_cs_free_job;
 		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job((struct amd_sched_job *)job);
+		r = amd_sched_entity_push_job(&job->base);
 		if (r) {
 			mutex_unlock(&job->job_lock);
 			amdgpu_cs_free_job(job);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 20cbc4eb5a6f..e0b80ccdfe8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -43,10 +43,10 @@ int amdgpu_ctx_init(struct amdgpu_device *adev, bool kernel,
 		for (i = 0; i < adev->num_rings; i++) {
 			struct amd_sched_rq *rq;
 			if (kernel)
-				rq = &adev->rings[i]->scheduler->kernel_rq;
+				rq = &adev->rings[i]->sched.kernel_rq;
 			else
-				rq = &adev->rings[i]->scheduler->sched_rq;
-			r = amd_sched_entity_init(adev->rings[i]->scheduler,
+				rq = &adev->rings[i]->sched.sched_rq;
+			r = amd_sched_entity_init(&adev->rings[i]->sched,
 						  &ctx->rings[i].entity,
 						  rq, amdgpu_sched_jobs);
 			if (r)
@@ -55,7 +55,7 @@ int amdgpu_ctx_init(struct amdgpu_device *adev, bool kernel,
 
 		if (i < adev->num_rings) {
 			for (j = 0; j < i; j++)
-				amd_sched_entity_fini(adev->rings[j]->scheduler,
+				amd_sched_entity_fini(&adev->rings[j]->sched,
 						      &ctx->rings[j].entity);
 			kfree(ctx);
 			return r;
@@ -75,7 +75,7 @@ void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 
 	if (amdgpu_enable_scheduler) {
 		for (i = 0; i < adev->num_rings; i++)
-			amd_sched_entity_fini(adev->rings[i]->scheduler,
+			amd_sched_entity_fini(&adev->rings[i]->sched,
 					      &ctx->rings[i].entity);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6ff6ae945794..6068d8207d10 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -246,7 +246,7 @@ static int amdgpu_vram_scratch_init(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev, AMDGPU_GPU_PAGE_SIZE,
 				     PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     NULL, &adev->vram_scratch.robj);
+				     NULL, NULL, &adev->vram_scratch.robj);
 		if (r) {
 			return r;
 		}
@@ -449,7 +449,8 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
 
 	if (adev->wb.wb_obj == NULL) {
 		r = amdgpu_bo_create(adev, AMDGPU_MAX_WB * 4, PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0,  NULL, &adev->wb.wb_obj);
+				     AMDGPU_GEM_DOMAIN_GTT, 0,  NULL, NULL,
+				     &adev->wb.wb_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create WB bo failed\n", r);
 			return r;
@@ -1650,9 +1651,11 @@ int amdgpu_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 	drm_kms_helper_poll_disable(dev);
 
 	/* turn off display hw */
+	drm_modeset_lock_all(dev);
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 	}
+	drm_modeset_unlock_all(dev);
 
 	/* unpin the front buffers */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -1747,9 +1750,11 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	if (fbcon) {
 		drm_helper_resume_force_mode(dev);
 		/* turn on display hw */
+		drm_modeset_lock_all(dev);
 		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 		}
+		drm_modeset_unlock_all(dev);
 	}
 
 	drm_kms_helper_poll_enable(dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0fcc0bd1622c..adb48353f2e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -79,6 +79,7 @@ int amdgpu_exp_hw_support = 0;
 int amdgpu_enable_scheduler = 0;
 int amdgpu_sched_jobs = 16;
 int amdgpu_sched_hw_submission = 2;
+int amdgpu_enable_semaphores = 1;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -152,6 +153,9 @@ module_param_named(sched_jobs, amdgpu_sched_jobs, int, 0444);
 MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)");
 module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 
+MODULE_PARM_DESC(enable_semaphores, "Enable semaphores (1 = enable (default), 0 = disable)");
+module_param_named(enable_semaphores, amdgpu_enable_semaphores, int, 0644);
+
 static struct pci_device_id pciidlist[] = {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 1be2bd6d07ea..b3fc26c59787 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -609,9 +609,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
  * Init the fence driver for the requested ring (all asics).
  * Helper function for amdgpu_fence_driver_init().
  */
-void amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
+int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
 {
-	int i;
+	int i, r;
 
 	ring->fence_drv.cpu_addr = NULL;
 	ring->fence_drv.gpu_addr = 0;
@@ -625,15 +625,19 @@ void amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
 			amdgpu_fence_check_lockup);
 	ring->fence_drv.ring = ring;
 
+	init_waitqueue_head(&ring->fence_drv.fence_queue);
+
 	if (amdgpu_enable_scheduler) {
-		ring->scheduler = amd_sched_create(&amdgpu_sched_ops,
-						   ring->idx,
-						   amdgpu_sched_hw_submission,
-						   (void *)ring->adev);
-		if (!ring->scheduler)
-			DRM_ERROR("Failed to create scheduler on ring %d.\n",
-				  ring->idx);
+		r = amd_sched_init(&ring->sched, &amdgpu_sched_ops,
+				   amdgpu_sched_hw_submission, ring->name);
+		if (r) {
+			DRM_ERROR("Failed to create scheduler on ring %s.\n",
+				  ring->name);
+			return r;
+		}
 	}
+
+	return 0;
 }
 
 /**
@@ -681,8 +685,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 		wake_up_all(&ring->fence_drv.fence_queue);
 		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 			       ring->fence_drv.irq_type);
-		if (ring->scheduler)
-			amd_sched_destroy(ring->scheduler);
+		amd_sched_fini(&ring->sched);
 		ring->fence_drv.initialized = false;
 	}
 	mutex_unlock(&adev->ring_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index cbd3a486c5c2..7312d729d300 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -127,7 +127,7 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev, adev->gart.table_size,
 				     PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     NULL, &adev->gart.robj);
+				     NULL, NULL, &adev->gart.robj);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 5839fab374bf..7297ca3a0ba7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -69,7 +69,8 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 		}
 	}
 retry:
-	r = amdgpu_bo_create(adev, size, alignment, kernel, initial_domain, flags, NULL, &robj);
+	r = amdgpu_bo_create(adev, size, alignment, kernel, initial_domain,
+			     flags, NULL, NULL, &robj);
 	if (r) {
 		if (r != -ERESTARTSYS) {
 			if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) {
@@ -426,6 +427,10 @@ int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
 					   &args->data.data_size_bytes,
 					   &args->data.flags);
 	} else if (args->op == AMDGPU_GEM_METADATA_OP_SET_METADATA) {
+		if (args->data.data_size_bytes > sizeof(args->data.data)) {
+			r = -EINVAL;
+			goto unreserve;
+		}
 		r = amdgpu_bo_set_tiling_flags(robj, args->data.tiling_info);
 		if (!r)
 			r = amdgpu_bo_set_metadata(robj, args->data.data,
@@ -433,6 +438,7 @@ int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
 						   args->data.flags);
 	}
 
+unreserve:
 	amdgpu_bo_unreserve(robj);
 out:
 	drm_gem_object_unreference_unlocked(gobj);
@@ -454,11 +460,12 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	struct ttm_validate_buffer tv, *entry;
 	struct amdgpu_bo_list_entry *vm_bos;
 	struct ww_acquire_ctx ticket;
-	struct list_head list;
+	struct list_head list, duplicates;
 	unsigned domain;
 	int r;
 
 	INIT_LIST_HEAD(&list);
+	INIT_LIST_HEAD(&duplicates);
 
 	tv.bo = &bo_va->bo->tbo;
 	tv.shared = true;
@@ -468,7 +475,8 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	if (!vm_bos)
 		return;
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL);
+	/* Provide duplicates to avoid -EALREADY */
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
 	if (r)
 		goto error_free;
 
@@ -651,7 +659,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 	int r;
 
 	args->pitch = amdgpu_align_pitch(adev, args->width, args->bpp, 0) * ((args->bpp + 1) / 8);
-	args->size = args->pitch * args->height;
+	args->size = (u64)args->pitch * args->height;
 	args->size = ALIGN(args->size, PAGE_SIZE);
 
 	r = amdgpu_gem_object_create(adev, args->size, 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 5c8a803acedc..534fc04e80fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -43,7 +43,7 @@ static int amdgpu_ih_ring_alloc(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev, adev->irq.ih.ring_size,
 				     PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0,
-				     NULL, &adev->irq.ih.ring_obj);
+				     NULL, NULL, &adev->irq.ih.ring_obj);
 		if (r) {
 			DRM_ERROR("amdgpu: failed to create ih ring buffer (%d).\n", r);
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 0aba8e9bc8a0..7c42ff670080 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -140,7 +140,7 @@ void amdgpu_irq_preinstall(struct drm_device *dev)
  */
 int amdgpu_irq_postinstall(struct drm_device *dev)
 {
-	dev->max_vblank_count = 0x001fffff;
+	dev->max_vblank_count = 0x00ffffff;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 22367939ebf1..8c735f544b66 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -390,7 +390,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 				    min((size_t)size, sizeof(vram_gtt))) ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_READ_MMR_REG: {
-		unsigned n, alloc_size = info->read_mmr_reg.count * 4;
+		unsigned n, alloc_size;
 		uint32_t *regs;
 		unsigned se_num = (info->read_mmr_reg.instance >>
 				   AMDGPU_INFO_MMR_SE_INDEX_SHIFT) &
@@ -406,9 +406,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
 
-		regs = kmalloc(alloc_size, GFP_KERNEL);
+		regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL);
 		if (!regs)
 			return -ENOMEM;
+		alloc_size = info->read_mmr_reg.count * sizeof(*regs);
 
 		for (i = 0; i < info->read_mmr_reg.count; i++)
 			if (amdgpu_asic_read_register(adev, se_num, sh_num,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 08b09d55b96f..1a7708f365f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -215,6 +215,7 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 				bool kernel, u32 domain, u64 flags,
 				struct sg_table *sg,
 				struct ttm_placement *placement,
+				struct reservation_object *resv,
 				struct amdgpu_bo **bo_ptr)
 {
 	struct amdgpu_bo *bo;
@@ -261,7 +262,7 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 	/* Kernel allocation are uninterruptible */
 	r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type,
 			&bo->placement, page_align, !kernel, NULL,
-			acc_size, sg, NULL, &amdgpu_ttm_bo_destroy);
+			acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
 	if (unlikely(r != 0)) {
 		return r;
 	}
@@ -275,7 +276,9 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     unsigned long size, int byte_align,
 		     bool kernel, u32 domain, u64 flags,
-		     struct sg_table *sg, struct amdgpu_bo **bo_ptr)
+		     struct sg_table *sg,
+		     struct reservation_object *resv,
+		     struct amdgpu_bo **bo_ptr)
 {
 	struct ttm_placement placement = {0};
 	struct ttm_place placements[AMDGPU_GEM_DOMAIN_MAX + 1];
@@ -286,11 +289,9 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	amdgpu_ttm_placement_init(adev, &placement,
 				  placements, domain, flags);
 
-	return amdgpu_bo_create_restricted(adev, size, byte_align,
-					   kernel, domain, flags,
-					   sg,
-					   &placement,
-					   bo_ptr);
+	return amdgpu_bo_create_restricted(adev, size, byte_align, kernel,
+					   domain, flags, sg, &placement,
+					   resv, bo_ptr);
 }
 
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
@@ -535,12 +536,10 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 	if (metadata == NULL)
 		return -EINVAL;
 
-	buffer = kzalloc(metadata_size, GFP_KERNEL);
+	buffer = kmemdup(metadata, metadata_size, GFP_KERNEL);
 	if (buffer == NULL)
 		return -ENOMEM;
 
-	memcpy(buffer, metadata, metadata_size);
-
 	kfree(bo->metadata);
 	bo->metadata_flags = flags;
 	bo->metadata = buffer;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 6ea18dcec561..3c2ff4567798 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -129,12 +129,14 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 			    unsigned long size, int byte_align,
 			    bool kernel, u32 domain, u64 flags,
 			    struct sg_table *sg,
+			    struct reservation_object *resv,
 			    struct amdgpu_bo **bo_ptr);
 int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 				unsigned long size, int byte_align,
 				bool kernel, u32 domain, u64 flags,
 				struct sg_table *sg,
 				struct ttm_placement *placement,
+			        struct reservation_object *resv,
 				struct amdgpu_bo **bo_ptr);
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr);
 void amdgpu_bo_kunmap(struct amdgpu_bo *bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index d9652fe32d6a..59f735a933a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -61,12 +61,15 @@ struct drm_gem_object *amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 							struct dma_buf_attachment *attach,
 							struct sg_table *sg)
 {
+	struct reservation_object *resv = attach->dmabuf->resv;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_bo *bo;
 	int ret;
 
+	ww_mutex_lock(&resv->lock, NULL);
 	ret = amdgpu_bo_create(adev, attach->dmabuf->size, PAGE_SIZE, false,
-			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, &bo);
+			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, resv, &bo);
+	ww_mutex_unlock(&resv->lock);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 9bec91484c24..30dce235ddeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -357,11 +357,11 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		ring->adev = adev;
 		ring->idx = adev->num_rings++;
 		adev->rings[ring->idx] = ring;
-		amdgpu_fence_driver_init_ring(ring);
+		r = amdgpu_fence_driver_init_ring(ring);
+		if (r)
+			return r;
 	}
 
-	init_waitqueue_head(&ring->fence_drv.fence_queue);
-
 	r = amdgpu_wb_get(adev, &ring->rptr_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
@@ -407,7 +407,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 	if (ring->ring_obj == NULL) {
 		r = amdgpu_bo_create(adev, ring->ring_size, PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0,
-				     NULL, &ring->ring_obj);
+				     NULL, NULL, &ring->ring_obj);
 		if (r) {
 			dev_err(adev->dev, "(%d) ring create failed\n", r);
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 74dad270362c..e90712443fe9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -64,8 +64,8 @@ int amdgpu_sa_bo_manager_init(struct amdgpu_device *adev,
 		INIT_LIST_HEAD(&sa_manager->flist[i]);
 	}
 
-	r = amdgpu_bo_create(adev, size, align, true,
-			     domain, 0, NULL, &sa_manager->bo);
+	r = amdgpu_bo_create(adev, size, align, true, domain,
+			     0, NULL, NULL, &sa_manager->bo);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate bo for manager\n", r);
 		return r;
@@ -145,8 +145,13 @@ static uint32_t amdgpu_sa_get_ring_from_fence(struct fence *f)
 	struct amd_sched_fence *s_fence;
 
 	s_fence = to_amd_sched_fence(f);
-	if (s_fence)
-		return s_fence->scheduler->ring_id;
+	if (s_fence) {
+		struct amdgpu_ring *ring;
+
+		ring = container_of(s_fence->sched, struct amdgpu_ring, sched);
+		return ring->idx;
+	}
+
 	a_fence = to_amdgpu_fence(f);
 	if (a_fence)
 		return a_fence->ring->idx;
@@ -412,6 +417,26 @@ void amdgpu_sa_bo_free(struct amdgpu_device *adev, struct amdgpu_sa_bo **sa_bo,
 }
 
 #if defined(CONFIG_DEBUG_FS)
+
+static void amdgpu_sa_bo_dump_fence(struct fence *fence, struct seq_file *m)
+{
+	struct amdgpu_fence *a_fence = to_amdgpu_fence(fence);
+	struct amd_sched_fence *s_fence = to_amd_sched_fence(fence);
+
+	if (a_fence)
+		seq_printf(m, " protected by 0x%016llx on ring %d",
+			   a_fence->seq, a_fence->ring->idx);
+
+	if (s_fence) {
+		struct amdgpu_ring *ring;
+
+
+		ring = container_of(s_fence->sched, struct amdgpu_ring, sched);
+		seq_printf(m, " protected by 0x%016x on ring %d",
+			   s_fence->base.seqno, ring->idx);
+	}
+}
+
 void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 				  struct seq_file *m)
 {
@@ -428,18 +453,8 @@ void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 		}
 		seq_printf(m, "[0x%010llx 0x%010llx] size %8lld",
 			   soffset, eoffset, eoffset - soffset);
-		if (i->fence) {
-			struct amdgpu_fence *a_fence = to_amdgpu_fence(i->fence);
-			struct amd_sched_fence *s_fence = to_amd_sched_fence(i->fence);
-			if (a_fence)
-				seq_printf(m, " protected by 0x%016llx on ring %d",
-					   a_fence->seq, a_fence->ring->idx);
-			if (s_fence)
-				seq_printf(m, " protected by 0x%016x on ring %d",
-					   s_fence->base.seqno,
-					   s_fence->scheduler->ring_id);
-
-		}
+		if (i->fence)
+			amdgpu_sa_bo_dump_fence(i->fence, m);
 		seq_printf(m, "\n");
 	}
 	spin_unlock(&sa_manager->wq.lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index de98fbd2971e..2e946b2cad88 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -27,63 +27,48 @@
 #include <drm/drmP.h>
 #include "amdgpu.h"
 
-static struct fence *amdgpu_sched_dependency(struct amd_sched_job *job)
+static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job)
 {
-	struct amdgpu_job *sched_job = (struct amdgpu_job *)job;
-	return amdgpu_sync_get_fence(&sched_job->ibs->sync);
+	struct amdgpu_job *job = to_amdgpu_job(sched_job);
+	return amdgpu_sync_get_fence(&job->ibs->sync);
 }
 
-static struct fence *amdgpu_sched_run_job(struct amd_sched_job *job)
+static struct fence *amdgpu_sched_run_job(struct amd_sched_job *sched_job)
 {
-	struct amdgpu_job *sched_job;
-	struct amdgpu_fence *fence;
+	struct amdgpu_fence *fence = NULL;
+	struct amdgpu_job *job;
 	int r;
 
-	if (!job) {
+	if (!sched_job) {
 		DRM_ERROR("job is null\n");
 		return NULL;
 	}
-	sched_job = (struct amdgpu_job *)job;
-	mutex_lock(&sched_job->job_lock);
-	r = amdgpu_ib_schedule(sched_job->adev,
-			       sched_job->num_ibs,
-			       sched_job->ibs,
-			       sched_job->base.owner);
-	if (r)
+	job = to_amdgpu_job(sched_job);
+	mutex_lock(&job->job_lock);
+	r = amdgpu_ib_schedule(job->adev,
+			       job->num_ibs,
+			       job->ibs,
+			       job->base.owner);
+	if (r) {
+		DRM_ERROR("Error scheduling IBs (%d)\n", r);
 		goto err;
-	fence = amdgpu_fence_ref(sched_job->ibs[sched_job->num_ibs - 1].fence);
-
-	if (sched_job->free_job)
-		sched_job->free_job(sched_job);
+	}
 
-	mutex_unlock(&sched_job->job_lock);
-	return &fence->base;
+	fence = amdgpu_fence_ref(job->ibs[job->num_ibs - 1].fence);
 
 err:
-	DRM_ERROR("Run job error\n");
-	mutex_unlock(&sched_job->job_lock);
-	job->sched->ops->process_job(job);
-	return NULL;
-}
+	if (job->free_job)
+		job->free_job(job);
 
-static void amdgpu_sched_process_job(struct amd_sched_job *job)
-{
-	struct amdgpu_job *sched_job;
-
-	if (!job) {
-		DRM_ERROR("job is null\n");
-		return;
-	}
-	sched_job = (struct amdgpu_job *)job;
-	/* after processing job, free memory */
-	fence_put(&sched_job->base.s_fence->base);
-	kfree(sched_job);
+	mutex_unlock(&job->job_lock);
+	fence_put(&job->base.s_fence->base);
+	kfree(job);
+	return fence ? &fence->base : NULL;
 }
 
 struct amd_sched_backend_ops amdgpu_sched_ops = {
 	.dependency = amdgpu_sched_dependency,
 	.run_job = amdgpu_sched_run_job,
-	.process_job = amdgpu_sched_process_job
 };
 
 int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev,
@@ -100,7 +85,7 @@ int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev,
 			kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
 		if (!job)
 			return -ENOMEM;
-		job->base.sched = ring->scheduler;
+		job->base.sched = &ring->sched;
 		job->base.s_entity = &adev->kernel_ctx.rings[ring->idx].entity;
 		job->adev = adev;
 		job->ibs = ibs;
@@ -109,7 +94,7 @@ int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev,
 		mutex_init(&job->job_lock);
 		job->free_job = free_job;
 		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job((struct amd_sched_job *)job);
+		r = amd_sched_entity_push_job(&job->base);
 		if (r) {
 			mutex_unlock(&job->job_lock);
 			kfree(job);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index 068aeaff7183..4921de15b451 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -65,8 +65,14 @@ static bool amdgpu_sync_same_dev(struct amdgpu_device *adev, struct fence *f)
 
 	if (a_fence)
 		return a_fence->ring->adev == adev;
-	if (s_fence)
-		return (struct amdgpu_device *)s_fence->scheduler->priv == adev;
+
+	if (s_fence) {
+		struct amdgpu_ring *ring;
+
+		ring = container_of(s_fence->sched, struct amdgpu_ring, sched);
+		return ring->adev == adev;
+	}
+
 	return false;
 }
 
@@ -251,6 +257,20 @@ int amdgpu_sync_wait(struct amdgpu_sync *sync)
 		fence_put(e->fence);
 		kfree(e);
 	}
+
+	if (amdgpu_enable_semaphores)
+		return 0;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_fence *fence = sync->sync_to[i];
+		if (!fence)
+			continue;
+
+		r = fence_wait(&fence->base, false);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
@@ -285,7 +305,8 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync,
 			return -EINVAL;
 		}
 
-		if (amdgpu_enable_scheduler || (count >= AMDGPU_NUM_SYNCS)) {
+		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores ||
+		    (count >= AMDGPU_NUM_SYNCS)) {
 			/* not enough room, wait manually */
 			r = fence_wait(&fence->base, false);
 			if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index f80b1a43be8a..4865615e9c06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -59,8 +59,9 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		goto out_cleanup;
 	}
 
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM, 0,
-			     NULL, &vram_obj);
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true,
+			     AMDGPU_GEM_DOMAIN_VRAM, 0,
+			     NULL, NULL, &vram_obj);
 	if (r) {
 		DRM_ERROR("Failed to create VRAM object\n");
 		goto out_cleanup;
@@ -80,7 +81,8 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		struct fence *fence = NULL;
 
 		r = amdgpu_bo_create(adev, size, PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, gtt_obj + i);
+				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+				     NULL, gtt_obj + i);
 		if (r) {
 			DRM_ERROR("Failed to create GTT object %d\n", i);
 			goto out_lclean;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index b5abd5cde413..364cbe975332 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -861,7 +861,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	r = amdgpu_bo_create(adev, 256 * 1024, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &adev->stollen_vga_memory);
+			     NULL, NULL, &adev->stollen_vga_memory);
 	if (r) {
 		return r;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 482e66797ae6..5cc95f1a7dab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -247,7 +247,7 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 	const struct common_firmware_header *header = NULL;
 
 	err = amdgpu_bo_create(adev, adev->firmware.fw_size, PAGE_SIZE, true,
-			AMDGPU_GEM_DOMAIN_GTT, 0, NULL, bo);
+			AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL, bo);
 	if (err) {
 		dev_err(adev->dev, "(%d) Firmware buffer allocate failed\n", err);
 		err = -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 2cf6c6b06e3b..d0312364d950 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -156,7 +156,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &adev->uvd.vcpu_bo);
+			     NULL, NULL, &adev->uvd.vcpu_bo);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
 		return r;
@@ -543,46 +543,60 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 		return -EINVAL;
 	}
 
-	if (msg_type == 1) {
+	switch (msg_type) {
+	case 0:
+		/* it's a create msg, calc image size (width * height) */
+		amdgpu_bo_kunmap(bo);
+
+		/* try to alloc a new handle */
+		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				DRM_ERROR("Handle 0x%x already in use!\n", handle);
+				return -EINVAL;
+			}
+
+			if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
+				adev->uvd.filp[i] = ctx->parser->filp;
+				return 0;
+			}
+		}
+
+		DRM_ERROR("No more free UVD handles!\n");
+		return -EINVAL;
+
+	case 1:
 		/* it's a decode msg, calc buffer sizes */
 		r = amdgpu_uvd_cs_msg_decode(msg, ctx->buf_sizes);
 		amdgpu_bo_kunmap(bo);
 		if (r)
 			return r;
 
-	} else if (msg_type == 2) {
+		/* validate the handle */
+		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				if (adev->uvd.filp[i] != ctx->parser->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
+					return -EINVAL;
+				}
+				return 0;
+			}
+		}
+
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
+		return -ENOENT;
+
+	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i)
 			atomic_cmpxchg(&adev->uvd.handles[i], handle, 0);
 		amdgpu_bo_kunmap(bo);
 		return 0;
-	} else {
-		/* it's a create msg */
-		amdgpu_bo_kunmap(bo);
-
-		if (msg_type != 0) {
-			DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
-			return -EINVAL;
-		}
-
-		/* it's a create msg, no special handling needed */
-	}
-
-	/* create or decode, validate the handle */
-	for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
-		if (atomic_read(&adev->uvd.handles[i]) == handle)
-			return 0;
-	}
 
-	/* handle not found try to alloc a new one */
-	for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
-		if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
-			adev->uvd.filp[i] = ctx->parser->filp;
-			return 0;
-		}
+	default:
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+		return -EINVAL;
 	}
-
-	DRM_ERROR("No more free UVD handles!\n");
+	BUG();
 	return -EINVAL;
 }
 
@@ -805,10 +819,10 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx)
 }
 
 static int amdgpu_uvd_free_job(
-	struct amdgpu_job *sched_job)
+	struct amdgpu_job *job)
 {
-	amdgpu_ib_free(sched_job->adev, sched_job->ibs);
-	kfree(sched_job->ibs);
+	amdgpu_ib_free(job->adev, job->ibs);
+	kfree(job->ibs);
 	return 0;
 }
 
@@ -905,7 +919,7 @@ int amdgpu_uvd_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	r = amdgpu_bo_create(adev, 1024, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &bo);
+			     NULL, NULL, &bo);
 	if (r)
 		return r;
 
@@ -954,7 +968,7 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	r = amdgpu_bo_create(adev, 1024, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &bo);
+			     NULL, NULL, &bo);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 3cab96c42aa8..74f2038ac747 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -143,7 +143,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &adev->vce.vcpu_bo);
+			     NULL, NULL, &adev->vce.vcpu_bo);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate VCE bo\n", r);
 		return r;
@@ -342,10 +342,10 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 }
 
 static int amdgpu_vce_free_job(
-	struct amdgpu_job *sched_job)
+	struct amdgpu_job *job)
 {
-	amdgpu_ib_free(sched_job->adev, sched_job->ibs);
-	kfree(sched_job->ibs);
+	amdgpu_ib_free(job->adev, job->ibs);
+	kfree(job->ibs);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index f68b7cdc370a..1e14531353e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -316,12 +316,12 @@ static void amdgpu_vm_update_pages(struct amdgpu_device *adev,
 	}
 }
 
-int amdgpu_vm_free_job(struct amdgpu_job *sched_job)
+int amdgpu_vm_free_job(struct amdgpu_job *job)
 {
 	int i;
-	for (i = 0; i < sched_job->num_ibs; i++)
-		amdgpu_ib_free(sched_job->adev, &sched_job->ibs[i]);
-	kfree(sched_job->ibs);
+	for (i = 0; i < job->num_ibs; i++)
+		amdgpu_ib_free(job->adev, &job->ibs[i]);
+	kfree(job->ibs);
 	return 0;
 }
 
@@ -686,31 +686,6 @@ static int amdgpu_vm_update_ptes(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_vm_fence_pts - fence page tables after an update
- *
- * @vm: requested vm
- * @start: start of GPU address range
- * @end: end of GPU address range
- * @fence: fence to use
- *
- * Fence the page tables in the range @start - @end (cayman+).
- *
- * Global and local mutex must be locked!
- */
-static void amdgpu_vm_fence_pts(struct amdgpu_vm *vm,
-				uint64_t start, uint64_t end,
-				struct fence *fence)
-{
-	unsigned i;
-
-	start >>= amdgpu_vm_block_size;
-	end >>= amdgpu_vm_block_size;
-
-	for (i = start; i <= end; ++i)
-		amdgpu_bo_fence(vm->page_tables[i].bo, fence, true);
-}
-
-/**
  * amdgpu_vm_bo_update_mapping - update a mapping in the vm page table
  *
  * @adev: amdgpu_device pointer
@@ -813,8 +788,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (r)
 		goto error_free;
 
-	amdgpu_vm_fence_pts(vm, mapping->it.start,
-			    mapping->it.last + 1, f);
+	amdgpu_bo_fence(vm->page_directory, f, true);
 	if (fence) {
 		fence_put(*fence);
 		*fence = fence_get(f);
@@ -855,7 +829,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	int r;
 
 	if (mem) {
-		addr = mem->start << PAGE_SHIFT;
+		addr = (u64)mem->start << PAGE_SHIFT;
 		if (mem->mem_type != TTM_PL_TT)
 			addr += adev->vm_manager.vram_base_offset;
 	} else {
@@ -1089,6 +1063,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) {
+		struct reservation_object *resv = vm->page_directory->tbo.resv;
 		struct amdgpu_bo *pt;
 
 		if (vm->page_tables[pt_idx].bo)
@@ -1097,11 +1072,13 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		/* drop mutex to allocate and clear page table */
 		mutex_unlock(&vm->mutex);
 
+		ww_mutex_lock(&resv->lock, NULL);
 		r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8,
 				     AMDGPU_GPU_PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
-				     NULL, &pt);
+				     NULL, resv, &pt);
+		ww_mutex_unlock(&resv->lock);
 		if (r)
 			goto error_free;
 
@@ -1303,7 +1280,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	r = amdgpu_bo_create(adev, pd_size, align, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
-			     NULL, &vm->page_directory);
+			     NULL, NULL, &vm->page_directory);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_smc.c b/drivers/gpu/drm/amd/amdgpu/cz_smc.c
index a72ffc7d6c26..e33180d3314a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_smc.c
@@ -814,7 +814,8 @@ int cz_smu_init(struct amdgpu_device *adev)
 	* 3. map kernel virtual address
 	*/
 	ret = amdgpu_bo_create(adev, priv->toc_buffer.data_size, PAGE_SIZE,
-				true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, toc_buf);
+			       true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
+			       toc_buf);
 
 	if (ret) {
 		dev_err(adev->dev, "(%d) SMC TOC buffer allocation failed\n", ret);
@@ -822,7 +823,8 @@ int cz_smu_init(struct amdgpu_device *adev)
 	}
 
 	ret = amdgpu_bo_create(adev, priv->smu_buffer.data_size, PAGE_SIZE,
-				true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, smu_buf);
+			       true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
+			       smu_buf);
 
 	if (ret) {
 		dev_err(adev->dev, "(%d) SMC Internal buffer allocation failed\n", ret);
diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
index 322edea65857..bda1249eb871 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
@@ -764,7 +764,7 @@ int fiji_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, image_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, toc_buf);
+			       NULL, NULL, toc_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for TOC buffer\n");
 		return -ENOMEM;
@@ -774,7 +774,7 @@ int fiji_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, smu_internal_buffer_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, smu_buf);
+			       NULL, NULL, smu_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for SMU internal buffer\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 4bd1e5cf65ca..e992bf2ff66c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3206,7 +3206,7 @@ static int gfx_v7_0_mec_init(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev,
 				     adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2,
 				     PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
@@ -3373,7 +3373,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev,
 					     sizeof(struct bonaire_mqd),
 					     PAGE_SIZE, true,
-					     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+					     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 					     &ring->mqd_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create MQD bo failed\n", r);
@@ -3610,41 +3610,6 @@ static int gfx_v7_0_cp_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
-static void gfx_v7_0_ce_sync_me(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	u64 gpu_addr = adev->wb.gpu_addr + adev->gfx.ce_sync_offs * 4;
-
-	/* instruct DE to set a magic number */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
-							 WRITE_DATA_DST_SEL(5)));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
-
-	/* let CE wait till condition satisfied */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
-	amdgpu_ring_write(ring, (WAIT_REG_MEM_OPERATION(0) | /* wait */
-							 WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
-							 WAIT_REG_MEM_FUNCTION(3) |  /* == */
-							 WAIT_REG_MEM_ENGINE(2)));   /* ce */
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
-	amdgpu_ring_write(ring, 0xffffffff);
-	amdgpu_ring_write(ring, 4); /* poll interval */
-
-	/* instruct CE to reset wb of ce_sync to zero */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(2) |
-							 WRITE_DATA_DST_SEL(5) |
-							 WR_CONFIRM));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 0);
-}
-
 /*
  * vm
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -3663,6 +3628,13 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					unsigned vm_id, uint64_t pd_addr)
 {
 	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	if (usepfp) {
+		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+	}
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
@@ -3703,7 +3675,10 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 		amdgpu_ring_write(ring, 0x0);
 
 		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
-		gfx_v7_0_ce_sync_me(ring);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
 	}
 }
 
@@ -3788,7 +3763,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev, dws * 4, PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_VRAM,
 					     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-					     NULL, &adev->gfx.rlc.save_restore_obj);
+					     NULL, NULL,
+					     &adev->gfx.rlc.save_restore_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create RLC sr bo failed\n", r);
 				return r;
@@ -3831,7 +3807,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev, dws * 4, PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_VRAM,
 					     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-					     NULL, &adev->gfx.rlc.clear_state_obj);
+					     NULL, NULL,
+					     &adev->gfx.rlc.clear_state_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create RLC c bo failed\n", r);
 				gfx_v7_0_rlc_fini(adev);
@@ -3870,7 +3847,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev, adev->gfx.rlc.cp_table_size, PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_VRAM,
 					     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-					     NULL, &adev->gfx.rlc.cp_table_obj);
+					     NULL, NULL,
+					     &adev->gfx.rlc.cp_table_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create RLC cp table bo failed\n", r);
 				gfx_v7_0_rlc_fini(adev);
@@ -4802,12 +4780,6 @@ static int gfx_v7_0_sw_init(void *handle)
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &adev->gfx.ce_sync_offs);
-	if (r) {
-		DRM_ERROR("(%d) gfx.ce_sync_offs wb alloc failed\n", r);
-		return r;
-	}
-
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
 		ring = &adev->gfx.gfx_ring[i];
 		ring->ring_obj = NULL;
@@ -4851,21 +4823,21 @@ static int gfx_v7_0_sw_init(void *handle)
 	r = amdgpu_bo_create(adev, adev->gds.mem.gfx_partition_size,
 			PAGE_SIZE, true,
 			AMDGPU_GEM_DOMAIN_GDS, 0,
-			NULL, &adev->gds.gds_gfx_bo);
+			NULL, NULL, &adev->gds.gds_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.gws.gfx_partition_size,
 		PAGE_SIZE, true,
 		AMDGPU_GEM_DOMAIN_GWS, 0,
-		NULL, &adev->gds.gws_gfx_bo);
+		NULL, NULL, &adev->gds.gws_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.oa.gfx_partition_size,
 			PAGE_SIZE, true,
 			AMDGPU_GEM_DOMAIN_OA, 0,
-			NULL, &adev->gds.oa_gfx_bo);
+			NULL, NULL, &adev->gds.oa_gfx_bo);
 	if (r)
 		return r;
 
@@ -4886,8 +4858,6 @@ static int gfx_v7_0_sw_fini(void *handle)
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
-	amdgpu_wb_free(adev, adev->gfx.ce_sync_offs);
-
 	gfx_v7_0_cp_compute_fini(adev);
 	gfx_v7_0_rlc_fini(adev);
 	gfx_v7_0_mec_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 53f07439a512..cb4f68f53f24 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -868,7 +868,7 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev,
 				     adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2,
 				     PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
@@ -940,12 +940,6 @@ static int gfx_v8_0_sw_init(void *handle)
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &adev->gfx.ce_sync_offs);
-	if (r) {
-		DRM_ERROR("(%d) gfx.ce_sync_offs wb alloc failed\n", r);
-		return r;
-	}
-
 	/* set up the gfx ring */
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
 		ring = &adev->gfx.gfx_ring[i];
@@ -995,21 +989,21 @@ static int gfx_v8_0_sw_init(void *handle)
 	/* reserve GDS, GWS and OA resource for gfx */
 	r = amdgpu_bo_create(adev, adev->gds.mem.gfx_partition_size,
 			PAGE_SIZE, true,
-			AMDGPU_GEM_DOMAIN_GDS, 0,
+			AMDGPU_GEM_DOMAIN_GDS, 0, NULL,
 			NULL, &adev->gds.gds_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.gws.gfx_partition_size,
 		PAGE_SIZE, true,
-		AMDGPU_GEM_DOMAIN_GWS, 0,
+		AMDGPU_GEM_DOMAIN_GWS, 0, NULL,
 		NULL, &adev->gds.gws_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.oa.gfx_partition_size,
 			PAGE_SIZE, true,
-			AMDGPU_GEM_DOMAIN_OA, 0,
+			AMDGPU_GEM_DOMAIN_OA, 0, NULL,
 			NULL, &adev->gds.oa_gfx_bo);
 	if (r)
 		return r;
@@ -1033,8 +1027,6 @@ static int gfx_v8_0_sw_fini(void *handle)
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
-	amdgpu_wb_free(adev, adev->gfx.ce_sync_offs);
-
 	gfx_v8_0_mec_fini(adev);
 
 	return 0;
@@ -3106,7 +3098,7 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev)
 					     sizeof(struct vi_mqd),
 					     PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
-					     &ring->mqd_obj);
+					     NULL, &ring->mqd_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create MQD bo failed\n", r);
 				return r;
@@ -3965,6 +3957,7 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 			  DATA_SEL(write64bit ? 2 : 1) | INT_SEL(int_sel ? 2 : 0));
 	amdgpu_ring_write(ring, lower_32_bits(seq));
 	amdgpu_ring_write(ring, upper_32_bits(seq));
+
 }
 
 /**
@@ -4005,49 +3998,34 @@ static bool gfx_v8_0_ring_emit_semaphore(struct amdgpu_ring *ring,
 	return true;
 }
 
-static void gfx_v8_0_ce_sync_me(struct amdgpu_ring *ring)
+static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
+					unsigned vm_id, uint64_t pd_addr)
 {
-	struct amdgpu_device *adev = ring->adev;
-	u64 gpu_addr = adev->wb.gpu_addr + adev->gfx.ce_sync_offs * 4;
-
-	/* instruct DE to set a magic number */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
-							 WRITE_DATA_DST_SEL(5)));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
+	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	uint32_t seq = ring->fence_drv.sync_seq[ring->idx];
+	uint64_t addr = ring->fence_drv.gpu_addr;
 
-	/* let CE wait till condition satisfied */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
-	amdgpu_ring_write(ring, (WAIT_REG_MEM_OPERATION(0) | /* wait */
-							 WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
-							 WAIT_REG_MEM_FUNCTION(3) |  /* == */
-							 WAIT_REG_MEM_ENGINE(2)));   /* ce */
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
+	amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
+		 WAIT_REG_MEM_FUNCTION(3))); /* equal */
+	amdgpu_ring_write(ring, addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+	amdgpu_ring_write(ring, seq);
 	amdgpu_ring_write(ring, 0xffffffff);
 	amdgpu_ring_write(ring, 4); /* poll interval */
 
-	/* instruct CE to reset wb of ce_sync to zero */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(2) |
-							 WRITE_DATA_DST_SEL(5) |
-							 WR_CONFIRM));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 0);
-}
-
-static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
-{
-	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	if (usepfp) {
+		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+	}
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
-				 WRITE_DATA_DST_SEL(0)));
+				 WRITE_DATA_DST_SEL(0)) |
+				 WR_CONFIRM);
 	if (vm_id < 8) {
 		amdgpu_ring_write(ring,
 				  (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
@@ -4083,9 +4061,10 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 		/* sync PFP to ME, otherwise we might get invalid PFP reads */
 		amdgpu_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
 		amdgpu_ring_write(ring, 0x0);
-
-		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
-		gfx_v8_0_ce_sync_me(ring);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
index c900aa942ade..966d4b2ed9da 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
@@ -625,7 +625,7 @@ int iceland_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, image_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, toc_buf);
+			       NULL, NULL, toc_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for TOC buffer\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
index 1f5ac941a610..5421309c1862 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
@@ -763,7 +763,7 @@ int tonga_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, image_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, toc_buf);
+			       NULL, NULL, toc_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for TOC buffer\n");
 		return -ENOMEM;
@@ -773,7 +773,7 @@ int tonga_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, smu_internal_buffer_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, smu_buf);
+			       NULL, NULL, smu_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for SMU internal buffer\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 5fac5da694f0..ed50dd725788 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -224,11 +224,11 @@ static int uvd_v4_2_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = uvd_v4_2_hw_fini(adev);
+	r = amdgpu_uvd_suspend(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
+	r = uvd_v4_2_hw_fini(adev);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 2d5c59c318af..9ad8b9906c0b 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -220,11 +220,11 @@ static int uvd_v5_0_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = uvd_v5_0_hw_fini(adev);
+	r = amdgpu_uvd_suspend(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
+	r = uvd_v5_0_hw_fini(adev);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index d9f553fce531..7e9934fa4193 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -214,14 +214,16 @@ static int uvd_v6_0_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/* Skip this for APU for now */
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_uvd_suspend(adev);
+		if (r)
+			return r;
+	}
 	r = uvd_v6_0_hw_fini(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
-	if (r)
-		return r;
-
 	return r;
 }
 
@@ -230,10 +232,12 @@ static int uvd_v6_0_resume(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = amdgpu_uvd_resume(adev);
-	if (r)
-		return r;
-
+	/* Skip this for APU for now */
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_uvd_resume(adev);
+		if (r)
+			return r;
+	}
 	r = uvd_v6_0_hw_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 552d9e75ad1b..b55ceb14fdcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1400,7 +1400,8 @@ static int vi_common_early_init(void *handle)
 	case CHIP_CARRIZO:
 		adev->has_uvd = true;
 		adev->cg_flags = 0;
-		adev->pg_flags = AMDGPU_PG_SUPPORT_UVD | AMDGPU_PG_SUPPORT_VCE;
+		/* Disable UVD pg */
+		adev->pg_flags = /* AMDGPU_PG_SUPPORT_UVD | */AMDGPU_PG_SUPPORT_VCE;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		if (amdgpu_smc_load_fw && smc_enabled)
 			adev->firmware.smu_load = true;
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
new file mode 100644
index 000000000000..144f50acc971
--- /dev/null
+++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
@@ -0,0 +1,41 @@
+#if !defined(_GPU_SCHED_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _GPU_SCHED_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#include <drm/drmP.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gpu_sched
+#define TRACE_INCLUDE_FILE gpu_sched_trace
+
+TRACE_EVENT(amd_sched_job,
+	    TP_PROTO(struct amd_sched_job *sched_job),
+	    TP_ARGS(sched_job),
+	    TP_STRUCT__entry(
+			     __field(struct amd_sched_entity *, entity)
+			     __field(const char *, name)
+			     __field(u32, job_count)
+			     __field(int, hw_job_count)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->entity = sched_job->s_entity;
+			   __entry->name = sched_job->sched->name;
+			   __entry->job_count = kfifo_len(
+				   &sched_job->s_entity->job_queue) / sizeof(sched_job);
+			   __entry->hw_job_count = atomic_read(
+				   &sched_job->sched->hw_rq_count);
+			   ),
+	    TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d",
+		      __entry->entity, __entry->name, __entry->job_count,
+		      __entry->hw_job_count)
+);
+#endif
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 9259f1b6664c..3697eeeecf82 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -27,6 +27,9 @@
 #include <drm/drmP.h>
 #include "gpu_scheduler.h"
 
+#define CREATE_TRACE_POINTS
+#include "gpu_sched_trace.h"
+
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity);
 static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
@@ -65,29 +68,29 @@ static struct amd_sched_job *
 amd_sched_rq_select_job(struct amd_sched_rq *rq)
 {
 	struct amd_sched_entity *entity;
-	struct amd_sched_job *job;
+	struct amd_sched_job *sched_job;
 
 	spin_lock(&rq->lock);
 
 	entity = rq->current_entity;
 	if (entity) {
 		list_for_each_entry_continue(entity, &rq->entities, list) {
-			job = amd_sched_entity_pop_job(entity);
-			if (job) {
+			sched_job = amd_sched_entity_pop_job(entity);
+			if (sched_job) {
 				rq->current_entity = entity;
 				spin_unlock(&rq->lock);
-				return job;
+				return sched_job;
 			}
 		}
 	}
 
 	list_for_each_entry(entity, &rq->entities, list) {
 
-		job = amd_sched_entity_pop_job(entity);
-		if (job) {
+		sched_job = amd_sched_entity_pop_job(entity);
+		if (sched_job) {
 			rq->current_entity = entity;
 			spin_unlock(&rq->lock);
-			return job;
+			return sched_job;
 		}
 
 		if (entity == rq->current_entity)
@@ -115,23 +118,27 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 			  struct amd_sched_rq *rq,
 			  uint32_t jobs)
 {
+	int r;
+
 	if (!(sched && entity && rq))
 		return -EINVAL;
 
 	memset(entity, 0, sizeof(struct amd_sched_entity));
-	entity->belongto_rq = rq;
-	entity->scheduler = sched;
-	entity->fence_context = fence_context_alloc(1);
-	if(kfifo_alloc(&entity->job_queue,
-		       jobs * sizeof(void *),
-		       GFP_KERNEL))
-		return -EINVAL;
+	INIT_LIST_HEAD(&entity->list);
+	entity->rq = rq;
+	entity->sched = sched;
 
 	spin_lock_init(&entity->queue_lock);
+	r = kfifo_alloc(&entity->job_queue, jobs * sizeof(void *), GFP_KERNEL);
+	if (r)
+		return r;
+
 	atomic_set(&entity->fence_seq, 0);
+	entity->fence_context = fence_context_alloc(1);
 
 	/* Add the entity to the run queue */
 	amd_sched_rq_add_entity(rq, entity);
+
 	return 0;
 }
 
@@ -146,8 +153,8 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 static bool amd_sched_entity_is_initialized(struct amd_gpu_scheduler *sched,
 					    struct amd_sched_entity *entity)
 {
-	return entity->scheduler == sched &&
-		entity->belongto_rq != NULL;
+	return entity->sched == sched &&
+		entity->rq != NULL;
 }
 
 /**
@@ -177,7 +184,7 @@ static bool amd_sched_entity_is_idle(struct amd_sched_entity *entity)
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity)
 {
-	struct amd_sched_rq *rq = entity->belongto_rq;
+	struct amd_sched_rq *rq = entity->rq;
 
 	if (!amd_sched_entity_is_initialized(sched, entity))
 		return;
@@ -198,22 +205,22 @@ static void amd_sched_entity_wakeup(struct fence *f, struct fence_cb *cb)
 		container_of(cb, struct amd_sched_entity, cb);
 	entity->dependency = NULL;
 	fence_put(f);
-	amd_sched_wakeup(entity->scheduler);
+	amd_sched_wakeup(entity->sched);
 }
 
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 {
-	struct amd_gpu_scheduler *sched = entity->scheduler;
-	struct amd_sched_job *job;
+	struct amd_gpu_scheduler *sched = entity->sched;
+	struct amd_sched_job *sched_job;
 
 	if (ACCESS_ONCE(entity->dependency))
 		return NULL;
 
-	if (!kfifo_out_peek(&entity->job_queue, &job, sizeof(job)))
+	if (!kfifo_out_peek(&entity->job_queue, &sched_job, sizeof(sched_job)))
 		return NULL;
 
-	while ((entity->dependency = sched->ops->dependency(job))) {
+	while ((entity->dependency = sched->ops->dependency(sched_job))) {
 
 		if (fence_add_callback(entity->dependency, &entity->cb,
 				       amd_sched_entity_wakeup))
@@ -222,32 +229,33 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 			return NULL;
 	}
 
-	return job;
+	return sched_job;
 }
 
 /**
  * Helper to submit a job to the job queue
  *
- * @job		The pointer to job required to submit
+ * @sched_job		The pointer to job required to submit
  *
  * Returns true if we could submit the job.
  */
-static bool amd_sched_entity_in(struct amd_sched_job *job)
+static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 {
-	struct amd_sched_entity *entity = job->s_entity;
+	struct amd_sched_entity *entity = sched_job->s_entity;
 	bool added, first = false;
 
 	spin_lock(&entity->queue_lock);
-	added = kfifo_in(&entity->job_queue, &job, sizeof(job)) == sizeof(job);
+	added = kfifo_in(&entity->job_queue, &sched_job,
+			sizeof(sched_job)) == sizeof(sched_job);
 
-	if (added && kfifo_len(&entity->job_queue) == sizeof(job))
+	if (added && kfifo_len(&entity->job_queue) == sizeof(sched_job))
 		first = true;
 
 	spin_unlock(&entity->queue_lock);
 
 	/* first job wakes up scheduler */
 	if (first)
-		amd_sched_wakeup(job->sched);
+		amd_sched_wakeup(sched_job->sched);
 
 	return added;
 }
@@ -255,7 +263,7 @@ static bool amd_sched_entity_in(struct amd_sched_job *job)
 /**
  * Submit a job to the job queue
  *
- * @job		The pointer to job required to submit
+ * @sched_job		The pointer to job required to submit
  *
  * Returns 0 for success, negative error code otherwise.
  */
@@ -271,9 +279,9 @@ int amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 	fence_get(&fence->base);
 	sched_job->s_fence = fence;
 
-	wait_event(entity->scheduler->job_scheduled,
+	wait_event(entity->sched->job_scheduled,
 		   amd_sched_entity_in(sched_job));
-
+	trace_amd_sched_job(sched_job);
 	return 0;
 }
 
@@ -301,30 +309,28 @@ static void amd_sched_wakeup(struct amd_gpu_scheduler *sched)
 static struct amd_sched_job *
 amd_sched_select_job(struct amd_gpu_scheduler *sched)
 {
-	struct amd_sched_job *job;
+	struct amd_sched_job *sched_job;
 
 	if (!amd_sched_ready(sched))
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	job = amd_sched_rq_select_job(&sched->kernel_rq);
-	if (job == NULL)
-		job = amd_sched_rq_select_job(&sched->sched_rq);
+	sched_job = amd_sched_rq_select_job(&sched->kernel_rq);
+	if (sched_job == NULL)
+		sched_job = amd_sched_rq_select_job(&sched->sched_rq);
 
-	return job;
+	return sched_job;
 }
 
 static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
 {
-	struct amd_sched_job *sched_job =
-		container_of(cb, struct amd_sched_job, cb);
-	struct amd_gpu_scheduler *sched;
+	struct amd_sched_fence *s_fence =
+		container_of(cb, struct amd_sched_fence, cb);
+	struct amd_gpu_scheduler *sched = s_fence->sched;
 
-	sched = sched_job->sched;
-	amd_sched_fence_signal(sched_job->s_fence);
 	atomic_dec(&sched->hw_rq_count);
-	fence_put(&sched_job->s_fence->base);
-	sched->ops->process_job(sched_job);
+	amd_sched_fence_signal(s_fence);
+	fence_put(&s_fence->base);
 	wake_up_interruptible(&sched->wake_up_worker);
 }
 
@@ -338,87 +344,82 @@ static int amd_sched_main(void *param)
 
 	while (!kthread_should_stop()) {
 		struct amd_sched_entity *entity;
-		struct amd_sched_job *job;
+		struct amd_sched_fence *s_fence;
+		struct amd_sched_job *sched_job;
 		struct fence *fence;
 
 		wait_event_interruptible(sched->wake_up_worker,
 			kthread_should_stop() ||
-			(job = amd_sched_select_job(sched)));
+			(sched_job = amd_sched_select_job(sched)));
 
-		if (!job)
+		if (!sched_job)
 			continue;
 
-		entity = job->s_entity;
+		entity = sched_job->s_entity;
+		s_fence = sched_job->s_fence;
 		atomic_inc(&sched->hw_rq_count);
-		fence = sched->ops->run_job(job);
+		fence = sched->ops->run_job(sched_job);
 		if (fence) {
-			r = fence_add_callback(fence, &job->cb,
+			r = fence_add_callback(fence, &s_fence->cb,
 					       amd_sched_process_job);
 			if (r == -ENOENT)
-				amd_sched_process_job(fence, &job->cb);
+				amd_sched_process_job(fence, &s_fence->cb);
 			else if (r)
 				DRM_ERROR("fence add callback failed (%d)\n", r);
 			fence_put(fence);
+		} else {
+			DRM_ERROR("Failed to run job!\n");
+			amd_sched_process_job(NULL, &s_fence->cb);
 		}
 
-		count = kfifo_out(&entity->job_queue, &job, sizeof(job));
-		WARN_ON(count != sizeof(job));
+		count = kfifo_out(&entity->job_queue, &sched_job,
+				sizeof(sched_job));
+		WARN_ON(count != sizeof(sched_job));
 		wake_up(&sched->job_scheduled);
 	}
 	return 0;
 }
 
 /**
- * Create a gpu scheduler
+ * Init a gpu scheduler instance
  *
+ * @sched		The pointer to the scheduler
  * @ops			The backend operations for this scheduler.
- * @ring		The the ring id for the scheduler.
  * @hw_submissions	Number of hw submissions to do.
+ * @name		Name used for debugging
  *
- * Return the pointer to scheduler for success, otherwise return NULL
+ * Return 0 on success, otherwise error code.
 */
-struct amd_gpu_scheduler *amd_sched_create(struct amd_sched_backend_ops *ops,
-					   unsigned ring, unsigned hw_submission,
-					   void *priv)
+int amd_sched_init(struct amd_gpu_scheduler *sched,
+		   struct amd_sched_backend_ops *ops,
+		   unsigned hw_submission, const char *name)
 {
-	struct amd_gpu_scheduler *sched;
-
-	sched = kzalloc(sizeof(struct amd_gpu_scheduler), GFP_KERNEL);
-	if (!sched)
-		return NULL;
-
 	sched->ops = ops;
-	sched->ring_id = ring;
 	sched->hw_submission_limit = hw_submission;
-	sched->priv = priv;
-	snprintf(sched->name, sizeof(sched->name), "amdgpu[%d]", ring);
+	sched->name = name;
 	amd_sched_rq_init(&sched->sched_rq);
 	amd_sched_rq_init(&sched->kernel_rq);
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
 	atomic_set(&sched->hw_rq_count, 0);
+
 	/* Each scheduler will run on a seperate kernel thread */
 	sched->thread = kthread_run(amd_sched_main, sched, sched->name);
 	if (IS_ERR(sched->thread)) {
-		DRM_ERROR("Failed to create scheduler for id %d.\n", ring);
-		kfree(sched);
-		return NULL;
+		DRM_ERROR("Failed to create scheduler for %s.\n", name);
+		return PTR_ERR(sched->thread);
 	}
 
-	return sched;
+	return 0;
 }
 
 /**
  * Destroy a gpu scheduler
  *
  * @sched	The pointer to the scheduler
- *
- * return 0 if succeed. -1 if failed.
  */
-int amd_sched_destroy(struct amd_gpu_scheduler *sched)
+void amd_sched_fini(struct amd_gpu_scheduler *sched)
 {
 	kthread_stop(sched->thread);
-	kfree(sched);
-	return  0;
 }
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 2af0e4d4d817..80b64dc22214 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -38,13 +38,15 @@ struct amd_sched_rq;
 */
 struct amd_sched_entity {
 	struct list_head		list;
-	struct amd_sched_rq		*belongto_rq;
-	atomic_t			fence_seq;
-	/* the job_queue maintains the jobs submitted by clients */
-	struct kfifo                    job_queue;
+	struct amd_sched_rq		*rq;
+	struct amd_gpu_scheduler	*sched;
+
 	spinlock_t			queue_lock;
-	struct amd_gpu_scheduler	*scheduler;
+	struct kfifo                    job_queue;
+
+	atomic_t			fence_seq;
 	uint64_t                        fence_context;
+
 	struct fence			*dependency;
 	struct fence_cb			cb;
 };
@@ -62,13 +64,13 @@ struct amd_sched_rq {
 
 struct amd_sched_fence {
 	struct fence                    base;
-	struct amd_gpu_scheduler	*scheduler;
+	struct fence_cb                 cb;
+	struct amd_gpu_scheduler	*sched;
 	spinlock_t			lock;
 	void                            *owner;
 };
 
 struct amd_sched_job {
-	struct fence_cb                 cb;
 	struct amd_gpu_scheduler        *sched;
 	struct amd_sched_entity         *s_entity;
 	struct amd_sched_fence          *s_fence;
@@ -91,32 +93,29 @@ static inline struct amd_sched_fence *to_amd_sched_fence(struct fence *f)
  * these functions should be implemented in driver side
 */
 struct amd_sched_backend_ops {
-	struct fence *(*dependency)(struct amd_sched_job *job);
-	struct fence *(*run_job)(struct amd_sched_job *job);
-	void (*process_job)(struct amd_sched_job *job);
+	struct fence *(*dependency)(struct amd_sched_job *sched_job);
+	struct fence *(*run_job)(struct amd_sched_job *sched_job);
 };
 
 /**
  * One scheduler is implemented for each hardware ring
 */
 struct amd_gpu_scheduler {
-	struct task_struct		*thread;
+	struct amd_sched_backend_ops	*ops;
+	uint32_t			hw_submission_limit;
+	const char			*name;
 	struct amd_sched_rq		sched_rq;
 	struct amd_sched_rq		kernel_rq;
-	atomic_t			hw_rq_count;
-	struct amd_sched_backend_ops	*ops;
-	uint32_t			ring_id;
 	wait_queue_head_t		wake_up_worker;
 	wait_queue_head_t		job_scheduled;
-	uint32_t                        hw_submission_limit;
-	char                            name[20];
-	void                            *priv;
+	atomic_t			hw_rq_count;
+	struct task_struct		*thread;
 };
 
-struct amd_gpu_scheduler *
-amd_sched_create(struct amd_sched_backend_ops *ops,
-		 uint32_t ring, uint32_t hw_submission, void *priv);
-int amd_sched_destroy(struct amd_gpu_scheduler *sched);
+int amd_sched_init(struct amd_gpu_scheduler *sched,
+		   struct amd_sched_backend_ops *ops,
+		   uint32_t hw_submission, const char *name);
+void amd_sched_fini(struct amd_gpu_scheduler *sched);
 
 int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 			  struct amd_sched_entity *entity,
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index e62c37920e11..d802638094f4 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -36,7 +36,7 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity
 	if (fence == NULL)
 		return NULL;
 	fence->owner = owner;
-	fence->scheduler = s_entity->scheduler;
+	fence->sched = s_entity->sched;
 	spin_lock_init(&fence->lock);
 
 	seq = atomic_inc_return(&s_entity->fence_seq);
@@ -63,7 +63,7 @@ static const char *amd_sched_fence_get_driver_name(struct fence *fence)
 static const char *amd_sched_fence_get_timeline_name(struct fence *f)
 {
 	struct amd_sched_fence *fence = to_amd_sched_fence(f);
-	return (const char *)fence->scheduler->name;
+	return (const char *)fence->sched->name;
 }
 
 static bool amd_sched_fence_enable_signaling(struct fence *f)
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 9a860ca1e9d7..d93e7378c077 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -520,7 +520,8 @@ EXPORT_SYMBOL(drm_ioctl_permit);
 
 /** Ioctl table */
 static const struct drm_ioctl_desc drm_ioctls[] = {
-	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version,
+		      DRM_UNLOCKED|DRM_RENDER_ALLOW|DRM_CONTROL_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
index 82be6b86a168..d1e300dcd544 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
@@ -58,7 +58,8 @@ static void fsl_dcu_drm_plane_atomic_disable(struct drm_plane *plane,
 					     struct drm_plane_state *old_state)
 {
 	struct fsl_dcu_drm_device *fsl_dev = plane->dev->dev_private;
-	unsigned int index, value, ret;
+	unsigned int value;
+	int index, ret;
 
 	index = fsl_dcu_drm_plane_index(plane);
 	if (index < 0)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 5a244ab9395b..39d73dbc1c47 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -640,6 +640,32 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
 
 	/*
+	 * On HSW, the DSL reg (0x70000) appears to return 0 if we
+	 * read it just before the start of vblank.  So try it again
+	 * so we don't accidentally end up spanning a vblank frame
+	 * increment, causing the pipe_update_end() code to squak at us.
+	 *
+	 * The nature of this problem means we can't simply check the ISR
+	 * bit and return the vblank start value; nor can we use the scanline
+	 * debug register in the transcoder as it appears to have the same
+	 * problem.  We may need to extend this to include other platforms,
+	 * but so far testing only shows the problem on HSW.
+	 */
+	if (IS_HASWELL(dev) && !position) {
+		int i, temp;
+
+		for (i = 0; i < 100; i++) {
+			udelay(1);
+			temp = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) &
+				DSL_LINEMASK_GEN3;
+			if (temp != position) {
+				position = temp;
+				break;
+			}
+		}
+	}
+
+	/*
 	 * See update_scanline_offset() for the details on the
 	 * scanline_offset adjustment.
 	 */
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 89c1a8ce1f98..2a5c76faf9f8 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -430,7 +430,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 
 /**
  * intel_audio_codec_disable - Disable the audio codec for HD audio
- * @encoder: encoder on which to disable audio
+ * @intel_encoder: encoder on which to disable audio
  *
  * The disable sequences must be performed before disabling the transcoder or
  * port.
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index b3e437b3bb54..c19e669ffe50 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -42,7 +42,7 @@ find_section(const void *_bdb, int section_id)
 	const struct bdb_header *bdb = _bdb;
 	const u8 *base = _bdb;
 	int index = 0;
-	u16 total, current_size;
+	u32 total, current_size;
 	u8 current_id;
 
 	/* skip to first section */
@@ -57,6 +57,10 @@ find_section(const void *_bdb, int section_id)
 		current_size = *((const u16 *)(base + index));
 		index += 2;
 
+		/* The MIPI Sequence Block v3+ has a separate size field. */
+		if (current_id == BDB_MIPI_SEQUENCE && *(base + index) >= 3)
+			current_size = *((const u32 *)(base + index + 1));
+
 		if (index + current_size > total)
 			return NULL;
 
@@ -799,6 +803,12 @@ parse_mipi(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 		return;
 	}
 
+	/* Fail gracefully for forward incompatible sequence block. */
+	if (sequence->version >= 3) {
+		DRM_ERROR("Unable to parse MIPI Sequence Block v3+\n");
+		return;
+	}
+
 	DRM_DEBUG_DRIVER("Found MIPI sequence block\n");
 
 	block_size = get_blocksize(sequence);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 8cc9264f7809..cf418be7d30a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15087,9 +15087,12 @@ static void readout_plane_state(struct intel_crtc *crtc,
 
 		plane_state = to_intel_plane_state(p->base.state);
 
-		if (p->base.type == DRM_PLANE_TYPE_PRIMARY)
+		if (p->base.type == DRM_PLANE_TYPE_PRIMARY) {
 			plane_state->visible = primary_get_hw_state(crtc);
-		else {
+			if (plane_state->visible)
+				crtc->base.state->plane_mask |=
+					1 << drm_plane_index(&p->base);
+		} else {
 			if (active)
 				p->disable_plane(&p->base, &crtc->base);
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_fb.c b/drivers/gpu/drm/mgag200/mgag200_fb.c
index 87de15ea1f93..b35b5b2db4ec 100644
--- a/drivers/gpu/drm/mgag200/mgag200_fb.c
+++ b/drivers/gpu/drm/mgag200/mgag200_fb.c
@@ -186,17 +186,19 @@ static int mgag200fb_create(struct drm_fb_helper *helper,
 
 	sysram = vmalloc(size);
 	if (!sysram)
-		return -ENOMEM;
+		goto err_sysram;
 
 	info = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(info))
-		return PTR_ERR(info);
+	if (IS_ERR(info)) {
+		ret = PTR_ERR(info);
+		goto err_alloc_fbi;
+	}
 
 	info->par = mfbdev;
 
 	ret = mgag200_framebuffer_init(dev, &mfbdev->mfb, &mode_cmd, gobj);
 	if (ret)
-		return ret;
+		goto err_framebuffer_init;
 
 	mfbdev->sysram = sysram;
 	mfbdev->size = size;
@@ -225,7 +227,17 @@ static int mgag200fb_create(struct drm_fb_helper *helper,
 
 	DRM_DEBUG_KMS("allocated %dx%d\n",
 		      fb->width, fb->height);
+
 	return 0;
+
+err_framebuffer_init:
+	drm_fb_helper_release_fbi(helper);
+err_alloc_fbi:
+	vfree(sysram);
+err_sysram:
+	drm_gem_object_unreference_unlocked(gobj);
+
+	return ret;
 }
 
 static int mga_fbdev_destroy(struct drm_device *dev,
@@ -276,23 +288,26 @@ int mgag200_fbdev_init(struct mga_device *mdev)
 	ret = drm_fb_helper_init(mdev->dev, &mfbdev->helper,
 				 mdev->num_crtc, MGAG200FB_CONN_LIMIT);
 	if (ret)
-		return ret;
+		goto err_fb_helper;
 
 	ret = drm_fb_helper_single_add_all_connectors(&mfbdev->helper);
 	if (ret)
-		goto fini;
+		goto err_fb_setup;
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
 	drm_helper_disable_unused_functions(mdev->dev);
 
 	ret = drm_fb_helper_initial_config(&mfbdev->helper, bpp_sel);
 	if (ret)
-		goto fini;
+		goto err_fb_setup;
 
 	return 0;
 
-fini:
+err_fb_setup:
 	drm_fb_helper_fini(&mfbdev->helper);
+err_fb_helper:
+	mdev->mfbdev = NULL;
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index de06388069e7..b1a0f5656175 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -220,7 +220,7 @@ int mgag200_driver_load(struct drm_device *dev, unsigned long flags)
 	}
 	r = mgag200_mm_init(mdev);
 	if (r)
-		goto out;
+		goto err_mm;
 
 	drm_mode_config_init(dev);
 	dev->mode_config.funcs = (void *)&mga_mode_funcs;
@@ -233,7 +233,7 @@ int mgag200_driver_load(struct drm_device *dev, unsigned long flags)
 	r = mgag200_modeset_init(mdev);
 	if (r) {
 		dev_err(&dev->pdev->dev, "Fatal error during modeset init: %d\n", r);
-		goto out;
+		goto err_modeset;
 	}
 
 	/* Make small buffers to store a hardware cursor (double buffered icon updates) */
@@ -241,20 +241,24 @@ int mgag200_driver_load(struct drm_device *dev, unsigned long flags)
 					  &mdev->cursor.pixels_1);
 	mgag200_bo_create(dev, roundup(48*64, PAGE_SIZE), 0, 0,
 					  &mdev->cursor.pixels_2);
-	if (!mdev->cursor.pixels_2 || !mdev->cursor.pixels_1)
-		goto cursor_nospace;
-	mdev->cursor.pixels_current = mdev->cursor.pixels_1;
-	mdev->cursor.pixels_prev = mdev->cursor.pixels_2;
-	goto cursor_done;
- cursor_nospace:
-	mdev->cursor.pixels_1 = NULL;
-	mdev->cursor.pixels_2 = NULL;
-	dev_warn(&dev->pdev->dev, "Could not allocate space for cursors. Not doing hardware cursors.\n");
- cursor_done:
-
-out:
-	if (r)
-		mgag200_driver_unload(dev);
+	if (!mdev->cursor.pixels_2 || !mdev->cursor.pixels_1) {
+		mdev->cursor.pixels_1 = NULL;
+		mdev->cursor.pixels_2 = NULL;
+		dev_warn(&dev->pdev->dev,
+			"Could not allocate space for cursors. Not doing hardware cursors.\n");
+	} else {
+		mdev->cursor.pixels_current = mdev->cursor.pixels_1;
+		mdev->cursor.pixels_prev = mdev->cursor.pixels_2;
+	}
+
+	return 0;
+
+err_modeset:
+	drm_mode_config_cleanup(dev);
+	mgag200_mm_fini(mdev);
+err_mm:
+	dev->dev_private = NULL;
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 7c6225c84ba6..dd845f82cc24 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -886,13 +886,15 @@ static enum drm_connector_status qxl_conn_detect(
 		drm_connector_to_qxl_output(connector);
 	struct drm_device *ddev = connector->dev;
 	struct qxl_device *qdev = ddev->dev_private;
-	int connected;
+	bool connected = false;
 
 	/* The first monitor is always connected */
-	connected = (output->index == 0) ||
-		    (qdev->client_monitors_config &&
-		     qdev->client_monitors_config->count > output->index &&
-		     qxl_head_enabled(&qdev->client_monitors_config->heads[output->index]));
+	if (!qdev->client_monitors_config) {
+		if (output->index == 0)
+			connected = true;
+	} else
+		connected = qdev->client_monitors_config->count > output->index &&
+		     qxl_head_enabled(&qdev->client_monitors_config->heads[output->index]);
 
 	DRM_DEBUG("#%d connected: %d\n", output->index, connected);
 	if (!connected)
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index d8319dae8358..f3f562f6d848 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1573,10 +1573,12 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 
 	drm_kms_helper_poll_disable(dev);
 
+	drm_modeset_lock_all(dev);
 	/* turn off display hw */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 	}
+	drm_modeset_unlock_all(dev);
 
 	/* unpin the front buffers and cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -1734,9 +1736,11 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	if (fbcon) {
 		drm_helper_resume_force_mode(dev);
 		/* turn on display hw */
+		drm_modeset_lock_all(dev);
 		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 		}
+		drm_modeset_unlock_all(dev);
 	}
 
 	drm_kms_helper_poll_enable(dev);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 787cd8fd897f..e9115d3f67b0 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2927,6 +2927,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = {
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 },
 	{ 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8d9b7de25613..745e996d2dbc 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -882,6 +882,8 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
+		if (!man->has_type || !man->use_type)
+			continue;
 
 		type_ok = ttm_bo_mt_compatible(man, mem_type, place,
 						&cur_flags);
@@ -889,6 +891,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (!type_ok)
 			continue;
 
+		type_found = true;
 		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
 						  cur_flags);
 		/*
@@ -901,12 +904,10 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (mem_type == TTM_PL_SYSTEM)
 			break;
 
-		if (man->has_type && man->use_type) {
-			type_found = true;
-			ret = (*man->func->get_node)(man, bo, place, mem);
-			if (unlikely(ret))
-				return ret;
-		}
+		ret = (*man->func->get_node)(man, bo, place, mem);
+		if (unlikely(ret))
+			return ret;
+		
 		if (mem->mm_node)
 			break;
 	}
@@ -917,9 +918,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		return 0;
 	}
 
-	if (!type_found)
-		return -EINVAL;
-
 	for (i = 0; i < placement->num_busy_placement; ++i) {
 		const struct ttm_place *place = &placement->busy_placement[i];
 
@@ -927,11 +925,12 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
-		if (!man->has_type)
+		if (!man->has_type || !man->use_type)
 			continue;
 		if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
 			continue;
 
+		type_found = true;
 		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
 						  cur_flags);
 		/*
@@ -957,8 +956,13 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (ret == -ERESTARTSYS)
 			has_erestartsys = true;
 	}
-	ret = (has_erestartsys) ? -ERESTARTSYS : -ENOMEM;
-	return ret;
+
+	if (!type_found) {
+		printk(KERN_ERR TTM_PFX "No compatible memory type found.\n");
+		return -EINVAL;
+	}
+
+	return (has_erestartsys) ? -ERESTARTSYS : -ENOMEM;
 }
 EXPORT_SYMBOL(ttm_bo_mem_space);
 
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index 67720f70fe29..b49445df8a7e 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -1,6 +1,6 @@
 config DRM_VMWGFX
 	tristate "DRM driver for VMware Virtual GPU"
-	depends on DRM && PCI
+	depends on DRM && PCI && X86
 	select FB_DEFERRED_IO
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index ce659a125f2b..092ea81eeff7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -311,7 +311,6 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 	struct vmw_private *dev_priv = res->dev_priv;
 	struct ttm_buffer_object *bo = val_buf->bo;
 	struct vmw_fence_obj *fence;
-	int ret;
 
 	if (list_empty(&res->mob_head))
 		return 0;
@@ -328,7 +327,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
 
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index e13b20bd9908..2c7a25c71af2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -752,12 +752,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
 	dev_priv->active_master = &dev_priv->fbdev_master;
 
-
-	dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start,
-					       dev_priv->mmio_size);
-
-	dev_priv->mmio_virt = ioremap_wc(dev_priv->mmio_start,
-					 dev_priv->mmio_size);
+	dev_priv->mmio_virt = ioremap_cache(dev_priv->mmio_start,
+					    dev_priv->mmio_size);
 
 	if (unlikely(dev_priv->mmio_virt == NULL)) {
 		ret = -ENOMEM;
@@ -913,7 +909,6 @@ out_no_device:
 out_err4:
 	iounmap(dev_priv->mmio_virt);
 out_err3:
-	arch_phys_wc_del(dev_priv->mmio_mtrr);
 	vmw_ttm_global_release(dev_priv);
 out_err0:
 	for (i = vmw_res_context; i < vmw_res_max; ++i)
@@ -964,7 +959,6 @@ static int vmw_driver_unload(struct drm_device *dev)
 
 	ttm_object_device_release(&dev_priv->tdev);
 	iounmap(dev_priv->mmio_virt);
-	arch_phys_wc_del(dev_priv->mmio_mtrr);
 	if (dev_priv->ctx.staged_bindings)
 		vmw_binding_state_free(dev_priv->ctx.staged_bindings);
 	vmw_ttm_global_release(dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 6d02de6dc36c..f19fd39b43e1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -376,7 +376,6 @@ struct vmw_private {
 	uint32_t initial_width;
 	uint32_t initial_height;
 	u32 __iomem *mmio_virt;
-	int mmio_mtrr;
 	uint32_t capabilities;
 	uint32_t max_gmr_ids;
 	uint32_t max_gmr_pages;
@@ -631,7 +630,8 @@ extern int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
 				 uint32_t size,
 				 bool shareable,
 				 uint32_t *handle,
-				 struct vmw_dma_buffer **p_dma_buf);
+				 struct vmw_dma_buffer **p_dma_buf,
+				 struct ttm_base_object **p_base);
 extern int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
 				     struct vmw_dma_buffer *dma_buf,
 				     uint32_t *handle);
@@ -645,7 +645,8 @@ extern uint32_t vmw_dmabuf_validate_node(struct ttm_buffer_object *bo,
 					 uint32_t cur_validate_node);
 extern void vmw_dmabuf_validate_clear(struct ttm_buffer_object *bo);
 extern int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-				  uint32_t id, struct vmw_dma_buffer **out);
+				  uint32_t id, struct vmw_dma_buffer **out,
+				  struct ttm_base_object **base);
 extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
 extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index b56565457c96..5da5de0cb522 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1236,7 +1236,8 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo);
+	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
+				     NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use MOB buffer.\n");
 		ret = -EINVAL;
@@ -1296,7 +1297,8 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo);
+	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
+				     NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use GMR region.\n");
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 61fb7f3de311..15a6c01cd016 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1685,7 +1685,6 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 	struct drm_crtc *crtc;
 	u32 num_units = 0;
 	u32 i, k;
-	int ret;
 
 	dirty->dev_priv = dev_priv;
 
@@ -1711,7 +1710,7 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 			if (!dirty->cmd) {
 				DRM_ERROR("Couldn't reserve fifo space "
 					  "for dirty blits.\n");
-				return ret;
+				return -ENOMEM;
 			}
 			memset(dirty->cmd, 0, dirty->fifo_reserve_size);
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
index 76069f093ccf..222c9c2123a1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -484,7 +484,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
-	ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf);
+	ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf, NULL);
 	if (ret)
 		goto out_unlock;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index c1912f852b42..e57667ca7557 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -354,7 +354,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 	}
 
 	*out_surf = NULL;
-	ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf);
+	ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf, NULL);
 	return ret;
 }
 
@@ -481,7 +481,8 @@ int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
 			  uint32_t size,
 			  bool shareable,
 			  uint32_t *handle,
-			  struct vmw_dma_buffer **p_dma_buf)
+			  struct vmw_dma_buffer **p_dma_buf,
+			  struct ttm_base_object **p_base)
 {
 	struct vmw_user_dma_buffer *user_bo;
 	struct ttm_buffer_object *tmp;
@@ -515,6 +516,10 @@ int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
 	}
 
 	*p_dma_buf = &user_bo->dma;
+	if (p_base) {
+		*p_base = &user_bo->prime.base;
+		kref_get(&(*p_base)->refcount);
+	}
 	*handle = user_bo->prime.base.hash.key;
 
 out_no_base_object:
@@ -631,6 +636,7 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 	struct vmw_dma_buffer *dma_buf;
 	struct vmw_user_dma_buffer *user_bo;
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct ttm_base_object *buffer_base;
 	int ret;
 
 	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
@@ -643,7 +649,8 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 
 	switch (arg->op) {
 	case drm_vmw_synccpu_grab:
-		ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf);
+		ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf,
+					     &buffer_base);
 		if (unlikely(ret != 0))
 			return ret;
 
@@ -651,6 +658,7 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 				       dma);
 		ret = vmw_user_dmabuf_synccpu_grab(user_bo, tfile, arg->flags);
 		vmw_dmabuf_unreference(&dma_buf);
+		ttm_base_object_unref(&buffer_base);
 		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
 			     ret != -EBUSY)) {
 			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
@@ -692,7 +700,8 @@ int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
 		return ret;
 
 	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    req->size, false, &handle, &dma_buf);
+				    req->size, false, &handle, &dma_buf,
+				    NULL);
 	if (unlikely(ret != 0))
 		goto out_no_dmabuf;
 
@@ -721,7 +730,8 @@ int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
 }
 
 int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-			   uint32_t handle, struct vmw_dma_buffer **out)
+			   uint32_t handle, struct vmw_dma_buffer **out,
+			   struct ttm_base_object **p_base)
 {
 	struct vmw_user_dma_buffer *vmw_user_bo;
 	struct ttm_base_object *base;
@@ -743,7 +753,10 @@ int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
 	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
 				   prime.base);
 	(void)ttm_bo_reference(&vmw_user_bo->dma.base);
-	ttm_base_object_unref(&base);
+	if (p_base)
+		*p_base = base;
+	else
+		ttm_base_object_unref(&base);
 	*out = &vmw_user_bo->dma;
 
 	return 0;
@@ -1004,7 +1017,7 @@ int vmw_dumb_create(struct drm_file *file_priv,
 
 	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
 				    args->size, false, &args->handle,
-				    &dma_buf);
+				    &dma_buf, NULL);
 	if (unlikely(ret != 0))
 		goto out_no_dmabuf;
 
@@ -1032,7 +1045,7 @@ int vmw_dumb_map_offset(struct drm_file *file_priv,
 	struct vmw_dma_buffer *out_buf;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf);
+	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf, NULL);
 	if (ret != 0)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index bba1ee395478..fd47547b0234 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -855,7 +855,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 
 	if (buffer_handle != SVGA3D_INVALID_ID) {
 		ret = vmw_user_dmabuf_lookup(tfile, buffer_handle,
-					     &buffer);
+					     &buffer, NULL);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Could not find buffer for shader "
 				  "creation.\n");
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 3361769842f4..64b50409fa07 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -46,6 +46,7 @@ struct vmw_user_surface {
 	struct vmw_surface srf;
 	uint32_t size;
 	struct drm_master *master;
+	struct ttm_base_object *backup_base;
 };
 
 /**
@@ -656,6 +657,7 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base)
 	struct vmw_resource *res = &user_srf->srf.res;
 
 	*p_base = NULL;
+	ttm_base_object_unref(&user_srf->backup_base);
 	vmw_resource_unreference(&res);
 }
 
@@ -851,7 +853,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 					    res->backup_size,
 					    true,
 					    &backup_handle,
-					    &res->backup);
+					    &res->backup,
+					    &user_srf->backup_base);
 		if (unlikely(ret != 0)) {
 			vmw_resource_unreference(&res);
 			goto out_unlock;
@@ -1321,7 +1324,8 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 
 	if (req->buffer_handle != SVGA3D_INVALID_ID) {
 		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
-					     &res->backup);
+					     &res->backup,
+					     &user_srf->backup_base);
 		if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
 		    res->backup_size) {
 			DRM_ERROR("Surface backup buffer is too small.\n");
@@ -1335,7 +1339,8 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 					    req->drm_surface_flags &
 					    drm_vmw_surface_flag_shareable,
 					    &backup_handle,
-					    &res->backup);
+					    &res->backup,
+					    &user_srf->backup_base);
 
 	if (unlikely(ret != 0)) {
 		vmw_resource_unreference(&res);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 2f9aead4ecfc..652afd11a9ef 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -204,6 +204,8 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 		spin_lock_irqsave(&vmbus_connection.channel_lock, flags);
 		list_del(&channel->listentry);
 		spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags);
+
+		primary_channel = channel;
 	} else {
 		primary_channel = channel->primary_channel;
 		spin_lock_irqsave(&primary_channel->lock, flags);
@@ -211,6 +213,14 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 		primary_channel->num_sc--;
 		spin_unlock_irqrestore(&primary_channel->lock, flags);
 	}
+
+	/*
+	 * We need to free the bit for init_vp_index() to work in the case
+	 * of sub-channel, when we reload drivers like hv_netvsc.
+	 */
+	cpumask_clear_cpu(channel->target_cpu,
+			  &primary_channel->alloced_cpus_in_node);
+
 	free_channel(channel);
 }
 
@@ -458,6 +468,13 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 			continue;
 		}
 
+		/*
+		 * NOTE: in the case of sub-channel, we clear the sub-channel
+		 * related bit(s) in primary->alloced_cpus_in_node in
+		 * hv_process_channel_removal(), so when we reload drivers
+		 * like hv_netvsc in SMP guest, here we're able to re-allocate
+		 * bit from primary->alloced_cpus_in_node.
+		 */
 		if (!cpumask_test_cpu(cur_cpu,
 				&primary->alloced_cpus_in_node)) {
 			cpumask_set_cpu(cur_cpu,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 403bd29443b8..aa59037d7504 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -238,8 +238,6 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 		rx_sg->lkey = device->pd->local_dma_lkey;
 	}
 
-	isert_conn->rx_desc_head = 0;
-
 	return 0;
 
 dma_map_fail:
@@ -634,7 +632,7 @@ static void
 isert_init_conn(struct isert_conn *isert_conn)
 {
 	isert_conn->state = ISER_CONN_INIT;
-	INIT_LIST_HEAD(&isert_conn->accept_node);
+	INIT_LIST_HEAD(&isert_conn->node);
 	init_completion(&isert_conn->login_comp);
 	init_completion(&isert_conn->login_req_comp);
 	init_completion(&isert_conn->wait);
@@ -762,28 +760,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	ret = isert_rdma_post_recvl(isert_conn);
 	if (ret)
 		goto out_conn_dev;
-	/*
-	 * Obtain the second reference now before isert_rdma_accept() to
-	 * ensure that any initiator generated REJECT CM event that occurs
-	 * asynchronously won't drop the last reference until the error path
-	 * in iscsi_target_login_sess_out() does it's ->iscsit_free_conn() ->
-	 * isert_free_conn() -> isert_put_conn() -> kref_put().
-	 */
-	if (!kref_get_unless_zero(&isert_conn->kref)) {
-		isert_warn("conn %p connect_release is running\n", isert_conn);
-		goto out_conn_dev;
-	}
 
 	ret = isert_rdma_accept(isert_conn);
 	if (ret)
 		goto out_conn_dev;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	list_add_tail(&isert_conn->accept_node, &isert_np->np_accept_list);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	list_add_tail(&isert_conn->node, &isert_np->accepted);
+	mutex_unlock(&isert_np->mutex);
 
-	isert_info("np %p: Allow accept_np to continue\n", np);
-	up(&isert_np->np_sem);
 	return 0;
 
 out_conn_dev:
@@ -831,13 +816,21 @@ static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
+	struct isert_np *isert_np = cma_id->context;
 
 	isert_info("conn %p\n", isert_conn);
 
 	mutex_lock(&isert_conn->mutex);
-	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
-		isert_conn->state = ISER_CONN_UP;
+	isert_conn->state = ISER_CONN_UP;
+	kref_get(&isert_conn->kref);
 	mutex_unlock(&isert_conn->mutex);
+
+	mutex_lock(&isert_np->mutex);
+	list_move_tail(&isert_conn->node, &isert_np->pending);
+	mutex_unlock(&isert_np->mutex);
+
+	isert_info("np %p: Allow accept_np to continue\n", isert_np);
+	up(&isert_np->sem);
 }
 
 static void
@@ -903,14 +896,14 @@ isert_np_cma_handler(struct isert_np *isert_np,
 
 	switch (event) {
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-		isert_np->np_cm_id = NULL;
+		isert_np->cm_id = NULL;
 		break;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
-		isert_np->np_cm_id = isert_setup_id(isert_np);
-		if (IS_ERR(isert_np->np_cm_id)) {
+		isert_np->cm_id = isert_setup_id(isert_np);
+		if (IS_ERR(isert_np->cm_id)) {
 			isert_err("isert np %p setup id failed: %ld\n",
-				  isert_np, PTR_ERR(isert_np->np_cm_id));
-			isert_np->np_cm_id = NULL;
+				  isert_np, PTR_ERR(isert_np->cm_id));
+			isert_np->cm_id = NULL;
 		}
 		break;
 	default:
@@ -929,7 +922,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	struct isert_conn *isert_conn;
 	bool terminating = false;
 
-	if (isert_np->np_cm_id == cma_id)
+	if (isert_np->cm_id == cma_id)
 		return isert_np_cma_handler(cma_id->context, event);
 
 	isert_conn = cma_id->qp->qp_context;
@@ -945,13 +938,13 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	if (terminating)
 		goto out;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_conn->accept_node)) {
-		list_del_init(&isert_conn->accept_node);
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_conn->node)) {
+		list_del_init(&isert_conn->node);
 		isert_put_conn(isert_conn);
 		queue_work(isert_release_wq, &isert_conn->release_work);
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 out:
 	return 0;
@@ -962,6 +955,7 @@ isert_connect_error(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
+	list_del_init(&isert_conn->node);
 	isert_conn->cm_id = NULL;
 	isert_put_conn(isert_conn);
 
@@ -1006,35 +1000,51 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 }
 
 static int
-isert_post_recv(struct isert_conn *isert_conn, u32 count)
+isert_post_recvm(struct isert_conn *isert_conn, u32 count)
 {
 	struct ib_recv_wr *rx_wr, *rx_wr_failed;
 	int i, ret;
-	unsigned int rx_head = isert_conn->rx_desc_head;
 	struct iser_rx_desc *rx_desc;
 
 	for (rx_wr = isert_conn->rx_wr, i = 0; i < count; i++, rx_wr++) {
-		rx_desc		= &isert_conn->rx_descs[rx_head];
-		rx_wr->wr_id	= (uintptr_t)rx_desc;
-		rx_wr->sg_list	= &rx_desc->rx_sg;
-		rx_wr->num_sge	= 1;
-		rx_wr->next	= rx_wr + 1;
-		rx_head = (rx_head + 1) & (ISERT_QP_MAX_RECV_DTOS - 1);
+		rx_desc = &isert_conn->rx_descs[i];
+		rx_wr->wr_id = (uintptr_t)rx_desc;
+		rx_wr->sg_list = &rx_desc->rx_sg;
+		rx_wr->num_sge = 1;
+		rx_wr->next = rx_wr + 1;
 	}
-
 	rx_wr--;
 	rx_wr->next = NULL; /* mark end of work requests list */
 
 	isert_conn->post_recv_buf_count += count;
 	ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr,
-				&rx_wr_failed);
+			   &rx_wr_failed);
 	if (ret) {
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
 		isert_conn->post_recv_buf_count -= count;
-	} else {
-		isert_dbg("Posted %d RX buffers\n", count);
-		isert_conn->rx_desc_head = rx_head;
 	}
+
+	return ret;
+}
+
+static int
+isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc)
+{
+	struct ib_recv_wr *rx_wr_failed, rx_wr;
+	int ret;
+
+	rx_wr.wr_id = (uintptr_t)rx_desc;
+	rx_wr.sg_list = &rx_desc->rx_sg;
+	rx_wr.num_sge = 1;
+	rx_wr.next = NULL;
+
+	isert_conn->post_recv_buf_count++;
+	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_failed);
+	if (ret) {
+		isert_err("ib_post_recv() failed with ret: %d\n", ret);
+		isert_conn->post_recv_buf_count--;
+	}
+
 	return ret;
 }
 
@@ -1205,7 +1215,8 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 			if (ret)
 				return ret;
 
-			ret = isert_post_recv(isert_conn, ISERT_MIN_POSTED_RX);
+			ret = isert_post_recvm(isert_conn,
+					       ISERT_QP_MAX_RECV_DTOS);
 			if (ret)
 				return ret;
 
@@ -1278,7 +1289,7 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 }
 
 static struct iscsi_cmd
-*isert_allocate_cmd(struct iscsi_conn *conn)
+*isert_allocate_cmd(struct iscsi_conn *conn, struct iser_rx_desc *rx_desc)
 {
 	struct isert_conn *isert_conn = conn->context;
 	struct isert_cmd *isert_cmd;
@@ -1292,6 +1303,7 @@ static struct iscsi_cmd
 	isert_cmd = iscsit_priv_cmd(cmd);
 	isert_cmd->conn = isert_conn;
 	isert_cmd->iscsi_cmd = cmd;
+	isert_cmd->rx_desc = rx_desc;
 
 	return cmd;
 }
@@ -1303,9 +1315,9 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 {
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)buf;
-	struct scatterlist *sg;
 	int imm_data, imm_data_len, unsol_data, sg_nents, rc;
 	bool dump_payload = false;
+	unsigned int data_len;
 
 	rc = iscsit_setup_scsi_cmd(conn, cmd, buf);
 	if (rc < 0)
@@ -1314,7 +1326,10 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	imm_data = cmd->immediate_data;
 	imm_data_len = cmd->first_burst_len;
 	unsol_data = cmd->unsolicited_data;
+	data_len = cmd->se_cmd.data_length;
 
+	if (imm_data && imm_data_len == data_len)
+		cmd->se_cmd.se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
 	rc = iscsit_process_scsi_cmd(conn, cmd, hdr);
 	if (rc < 0) {
 		return 0;
@@ -1326,13 +1341,20 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	if (!imm_data)
 		return 0;
 
-	sg = &cmd->se_cmd.t_data_sg[0];
-	sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
-
-	isert_dbg("Copying Immediate SG: %p sg_nents: %u from %p imm_data_len: %d\n",
-		  sg, sg_nents, &rx_desc->data[0], imm_data_len);
-
-	sg_copy_from_buffer(sg, sg_nents, &rx_desc->data[0], imm_data_len);
+	if (imm_data_len != data_len) {
+		sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
+		sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents,
+				    &rx_desc->data[0], imm_data_len);
+		isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n",
+			  sg_nents, imm_data_len);
+	} else {
+		sg_init_table(&isert_cmd->sg, 1);
+		cmd->se_cmd.t_data_sg = &isert_cmd->sg;
+		cmd->se_cmd.t_data_nents = 1;
+		sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len);
+		isert_dbg("Transfer Immediate imm_data_len: %d\n",
+			  imm_data_len);
+	}
 
 	cmd->write_data_done += imm_data_len;
 
@@ -1407,6 +1429,15 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn,
 	if (rc < 0)
 		return rc;
 
+	/*
+	 * multiple data-outs on the same command can arrive -
+	 * so post the buffer before hand
+	 */
+	rc = isert_post_recv(isert_conn, rx_desc);
+	if (rc) {
+		isert_err("ib_post_recv failed with %d\n", rc);
+		return rc;
+	}
 	return 0;
 }
 
@@ -1479,7 +1510,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 
 	switch (opcode) {
 	case ISCSI_OP_SCSI_CMD:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1493,7 +1524,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 					rx_desc, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_NOOP_OUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1506,7 +1537,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_SCSI_TMFUNC:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1514,22 +1545,20 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_LOGOUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
 		ret = iscsit_handle_logout_cmd(conn, cmd, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_TEXT:
-		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF) {
+		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF)
 			cmd = iscsit_find_cmd_from_itt(conn, hdr->itt);
-			if (!cmd)
-				break;
-		} else {
-			cmd = isert_allocate_cmd(conn);
-			if (!cmd)
-				break;
-		}
+		else
+			cmd = isert_allocate_cmd(conn, rx_desc);
+
+		if (!cmd)
+			break;
 
 		isert_cmd = iscsit_priv_cmd(cmd);
 		ret = isert_handle_text_cmd(isert_conn, isert_cmd, cmd,
@@ -1589,7 +1618,7 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 	struct ib_device *ib_dev = isert_conn->cm_id->device;
 	struct iscsi_hdr *hdr;
 	u64 rx_dma;
-	int rx_buflen, outstanding;
+	int rx_buflen;
 
 	if ((char *)desc == isert_conn->login_req_buf) {
 		rx_dma = isert_conn->login_req_dma;
@@ -1629,22 +1658,6 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 				      DMA_FROM_DEVICE);
 
 	isert_conn->post_recv_buf_count--;
-	isert_dbg("Decremented post_recv_buf_count: %d\n",
-		  isert_conn->post_recv_buf_count);
-
-	if ((char *)desc == isert_conn->login_req_buf)
-		return;
-
-	outstanding = isert_conn->post_recv_buf_count;
-	if (outstanding + ISERT_MIN_POSTED_RX <= ISERT_QP_MAX_RECV_DTOS) {
-		int err, count = min(ISERT_QP_MAX_RECV_DTOS - outstanding,
-				ISERT_MIN_POSTED_RX);
-		err = isert_post_recv(isert_conn, count);
-		if (err) {
-			isert_err("isert_post_recv() count: %d failed, %d\n",
-			       count, err);
-		}
-	}
 }
 
 static int
@@ -2156,6 +2169,12 @@ isert_post_response(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd)
 	struct ib_send_wr *wr_failed;
 	int ret;
 
+	ret = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+	if (ret) {
+		isert_err("ib_post_recv failed with %d\n", ret);
+		return ret;
+	}
+
 	ret = ib_post_send(isert_conn->qp, &isert_cmd->tx_desc.send_wr,
 			   &wr_failed);
 	if (ret) {
@@ -2950,6 +2969,12 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 				   &isert_cmd->tx_desc.send_wr);
 		isert_cmd->rdma_wr.s_send_wr.next = &isert_cmd->tx_desc.send_wr;
 		wr->send_wr_num += 1;
+
+		rc = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+		if (rc) {
+			isert_err("ib_post_recv failed with %d\n", rc);
+			return rc;
+		}
 	}
 
 	rc = ib_post_send(isert_conn->qp, wr->send_wr, &wr_failed);
@@ -2999,9 +3024,16 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
 static int
 isert_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
 {
-	int ret;
+	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+	int ret = 0;
 
 	switch (state) {
+	case ISTATE_REMOVE:
+		spin_lock_bh(&conn->cmd_lock);
+		list_del_init(&cmd->i_conn_node);
+		spin_unlock_bh(&conn->cmd_lock);
+		isert_put_cmd(isert_cmd, true);
+		break;
 	case ISTATE_SEND_NOPIN_WANT_RESPONSE:
 		ret = isert_put_nopin(cmd, conn, false);
 		break;
@@ -3106,10 +3138,10 @@ isert_setup_np(struct iscsi_np *np,
 		isert_err("Unable to allocate struct isert_np\n");
 		return -ENOMEM;
 	}
-	sema_init(&isert_np->np_sem, 0);
-	mutex_init(&isert_np->np_accept_mutex);
-	INIT_LIST_HEAD(&isert_np->np_accept_list);
-	init_completion(&isert_np->np_login_comp);
+	sema_init(&isert_np->sem, 0);
+	mutex_init(&isert_np->mutex);
+	INIT_LIST_HEAD(&isert_np->accepted);
+	INIT_LIST_HEAD(&isert_np->pending);
 	isert_np->np = np;
 
 	/*
@@ -3125,7 +3157,7 @@ isert_setup_np(struct iscsi_np *np,
 		goto out;
 	}
 
-	isert_np->np_cm_id = isert_lid;
+	isert_np->cm_id = isert_lid;
 	np->np_context = isert_np;
 
 	return 0;
@@ -3214,7 +3246,7 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	int ret;
 
 accept_wait:
-	ret = down_interruptible(&isert_np->np_sem);
+	ret = down_interruptible(&isert_np->sem);
 	if (ret)
 		return -ENODEV;
 
@@ -3231,15 +3263,15 @@ accept_wait:
 	}
 	spin_unlock_bh(&np->np_thread_lock);
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (list_empty(&isert_np->np_accept_list)) {
-		mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	if (list_empty(&isert_np->pending)) {
+		mutex_unlock(&isert_np->mutex);
 		goto accept_wait;
 	}
-	isert_conn = list_first_entry(&isert_np->np_accept_list,
-			struct isert_conn, accept_node);
-	list_del_init(&isert_conn->accept_node);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	isert_conn = list_first_entry(&isert_np->pending,
+			struct isert_conn, node);
+	list_del_init(&isert_conn->node);
+	mutex_unlock(&isert_np->mutex);
 
 	conn->context = isert_conn;
 	isert_conn->conn = conn;
@@ -3257,28 +3289,39 @@ isert_free_np(struct iscsi_np *np)
 	struct isert_np *isert_np = np->np_context;
 	struct isert_conn *isert_conn, *n;
 
-	if (isert_np->np_cm_id)
-		rdma_destroy_id(isert_np->np_cm_id);
+	if (isert_np->cm_id)
+		rdma_destroy_id(isert_np->cm_id);
 
 	/*
 	 * FIXME: At this point we don't have a good way to insure
 	 * that at this point we don't have hanging connections that
 	 * completed RDMA establishment but didn't start iscsi login
 	 * process. So work-around this by cleaning up what ever piled
-	 * up in np_accept_list.
+	 * up in accepted and pending lists.
 	 */
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_np->np_accept_list)) {
-		isert_info("Still have isert connections, cleaning up...\n");
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_np->pending)) {
+		isert_info("Still have isert pending connections\n");
+		list_for_each_entry_safe(isert_conn, n,
+					 &isert_np->pending,
+					 node) {
+			isert_info("cleaning isert_conn %p state (%d)\n",
+				   isert_conn, isert_conn->state);
+			isert_connect_release(isert_conn);
+		}
+	}
+
+	if (!list_empty(&isert_np->accepted)) {
+		isert_info("Still have isert accepted connections\n");
 		list_for_each_entry_safe(isert_conn, n,
-					 &isert_np->np_accept_list,
-					 accept_node) {
+					 &isert_np->accepted,
+					 node) {
 			isert_info("cleaning isert_conn %p state (%d)\n",
 				   isert_conn, isert_conn->state);
 			isert_connect_release(isert_conn);
 		}
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 	np->np_context = NULL;
 	kfree(isert_np);
@@ -3345,6 +3388,41 @@ isert_wait4flush(struct isert_conn *isert_conn)
 	wait_for_completion(&isert_conn->wait_comp_err);
 }
 
+/**
+ * isert_put_unsol_pending_cmds() - Drop commands waiting for
+ *     unsolicitate dataout
+ * @conn:    iscsi connection
+ *
+ * We might still have commands that are waiting for unsolicited
+ * dataouts messages. We must put the extra reference on those
+ * before blocking on the target_wait_for_session_cmds
+ */
+static void
+isert_put_unsol_pending_cmds(struct iscsi_conn *conn)
+{
+	struct iscsi_cmd *cmd, *tmp;
+	static LIST_HEAD(drop_cmd_list);
+
+	spin_lock_bh(&conn->cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &conn->conn_cmd_list, i_conn_node) {
+		if ((cmd->cmd_flags & ICF_NON_IMMEDIATE_UNSOLICITED_DATA) &&
+		    (cmd->write_data_done < conn->sess->sess_ops->FirstBurstLength) &&
+		    (cmd->write_data_done < cmd->se_cmd.data_length))
+			list_move_tail(&cmd->i_conn_node, &drop_cmd_list);
+	}
+	spin_unlock_bh(&conn->cmd_lock);
+
+	list_for_each_entry_safe(cmd, tmp, &drop_cmd_list, i_conn_node) {
+		list_del_init(&cmd->i_conn_node);
+		if (cmd->i_state != ISTATE_REMOVE) {
+			struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+
+			isert_info("conn %p dropping cmd %p\n", conn, cmd);
+			isert_put_cmd(isert_cmd, true);
+		}
+	}
+}
+
 static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
@@ -3363,8 +3441,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->mutex);
 
-	isert_wait4cmds(conn);
 	isert_wait4flush(isert_conn);
+	isert_put_unsol_pending_cmds(conn);
+	isert_wait4cmds(conn);
 	isert_wait4logout(isert_conn);
 
 	queue_work(isert_release_wq, &isert_conn->release_work);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 6a04ba3c0f72..c5b99bcecbcf 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -113,7 +113,6 @@ enum {
 };
 
 struct isert_rdma_wr {
-	struct list_head	wr_list;
 	struct isert_cmd	*isert_cmd;
 	enum iser_ib_op_code	iser_ib_op;
 	struct ib_sge		*ib_sge;
@@ -134,14 +133,13 @@ struct isert_cmd {
 	uint64_t		write_va;
 	u64			pdu_buf_dma;
 	u32			pdu_buf_len;
-	u32			read_va_off;
-	u32			write_va_off;
-	u32			rdma_wr_num;
 	struct isert_conn	*conn;
 	struct iscsi_cmd	*iscsi_cmd;
 	struct iser_tx_desc	tx_desc;
+	struct iser_rx_desc	*rx_desc;
 	struct isert_rdma_wr	rdma_wr;
 	struct work_struct	comp_work;
+	struct scatterlist	sg;
 };
 
 struct isert_device;
@@ -159,11 +157,10 @@ struct isert_conn {
 	u64			login_req_dma;
 	int			login_req_len;
 	u64			login_rsp_dma;
-	unsigned int		rx_desc_head;
 	struct iser_rx_desc	*rx_descs;
-	struct ib_recv_wr	rx_wr[ISERT_MIN_POSTED_RX];
+	struct ib_recv_wr	rx_wr[ISERT_QP_MAX_RECV_DTOS];
 	struct iscsi_conn	*conn;
-	struct list_head	accept_node;
+	struct list_head	node;
 	struct completion	login_comp;
 	struct completion	login_req_comp;
 	struct iser_tx_desc	login_tx_desc;
@@ -222,9 +219,9 @@ struct isert_device {
 
 struct isert_np {
 	struct iscsi_np         *np;
-	struct semaphore	np_sem;
-	struct rdma_cm_id	*np_cm_id;
-	struct mutex		np_accept_mutex;
-	struct list_head	np_accept_list;
-	struct completion	np_login_comp;
+	struct semaphore	sem;
+	struct rdma_cm_id	*cm_id;
+	struct mutex		mutex;
+	struct list_head	accepted;
+	struct list_head	pending;
 };
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 9da9942ac83c..f6d680485bee 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -88,28 +88,36 @@ static void aic5_mask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Disable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Disable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IDCR);
 	gc->mask_cache &= ~d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static void aic5_unmask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Enable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Enable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IECR);
 	gc->mask_cache |= d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static int aic5_retrigger(struct irq_data *d)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index d60c88df5234..4b3b6f8aff0c 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -968,7 +968,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
 
 /*
  * Generate a new unfragmented bio with the given size
- * This should never violate the device limitations
+ * This should never violate the device limitations (but only because
+ * max_segment_size is being constrained to PAGE_SIZE).
  *
  * This function may be called concurrently. If we allocate from the mempool
  * concurrently, there is a possibility of deadlock. For example, if we have
@@ -2045,9 +2046,20 @@ static int crypt_iterate_devices(struct dm_target *ti,
 	return fn(ti, cc->dev, cc->start, ti->len, data);
 }
 
+static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	/*
+	 * Unfortunate constraint that is required to avoid the potential
+	 * for exceeding underlying device's max_segments limits -- due to
+	 * crypt_alloc_buffer() possibly allocating pages for the encryption
+	 * bio that are not as physically contiguous as the original bio.
+	 */
+	limits->max_segment_size = PAGE_SIZE;
+}
+
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 14, 0},
+	.version = {1, 14, 1},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
@@ -2058,6 +2070,7 @@ static struct target_type crypt_target = {
 	.resume = crypt_resume,
 	.message = crypt_message,
 	.iterate_devices = crypt_iterate_devices,
+	.io_hints = crypt_io_hints,
 };
 
 static int __init dm_crypt_init(void)
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 6578b7bc1fbb..6fcbfb063366 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -4249,6 +4249,10 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct thin_c *tc = ti->private;
 	struct pool *pool = tc->pool;
+	struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md);
+
+	if (!pool_limits->discard_granularity)
+		return; /* pool's discard support is disabled */
 
 	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 	limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 25868c2ec03e..02006f7109a8 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -592,6 +592,8 @@ int cxl_sysfs_afu_add(struct cxl_afu *afu)
 
 	/* conditionally create the add the binary file for error info buffer */
 	if (afu->eb_len) {
+		sysfs_attr_init(&afu->attr_eb.attr);
+
 		afu->attr_eb.attr.name = "afu_err_buff";
 		afu->attr_eb.attr.mode = S_IRUGO;
 		afu->attr_eb.size = afu->eb_len;
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index 4b469cf9e60f..8504dbeacd3b 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -204,6 +204,8 @@ int mei_dbgfs_register(struct mei_device *dev, const char *name)
 	if (!dir)
 		return -ENOMEM;
 
+	dev->dbgfs_dir = dir;
+
 	f = debugfs_create_file("meclients", S_IRUSR, dir,
 				dev, &mei_dbgfs_fops_meclients);
 	if (!f) {
@@ -228,7 +230,6 @@ int mei_dbgfs_register(struct mei_device *dev, const char *name)
 		dev_err(dev->dev, "allow_fixed_address: registration failed\n");
 		goto err;
 	}
-	dev->dbgfs_dir = dir;
 	return 0;
 err:
 	mei_dbgfs_deregister(dev);
diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index 10f71c732b59..816d0e94961c 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -326,7 +326,7 @@ static void arcdev_setup(struct net_device *dev)
 	dev->type = ARPHRD_ARCNET;
 	dev->netdev_ops = &arcnet_netdev_ops;
 	dev->header_ops = &arcnet_header_ops;
-	dev->hard_header_len = sizeof(struct archdr);
+	dev->hard_header_len = sizeof(struct arc_hardware);
 	dev->mtu = choose_mtu();
 
 	dev->addr_len = ARCNET_ALEN;
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index 6f13f7206762..f8baa897d1a0 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -2000,6 +2000,7 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port)
 		 */
 		reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_PCS_CTRL);
 		if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
+			reg &= ~PORT_PCS_CTRL_UNFORCED;
 			reg |= PORT_PCS_CTRL_FORCE_LINK |
 				PORT_PCS_CTRL_LINK_UP |
 				PORT_PCS_CTRL_DUPLEX_FULL |
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index cfa37041ab71..c4bb8027b3fb 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -689,16 +689,24 @@ static int xgene_enet_phy_connect(struct net_device *ndev)
 			netdev_dbg(ndev, "No phy-handle found in DT\n");
 			return -ENODEV;
 		}
-		pdata->phy_dev = of_phy_find_device(phy_np);
-	}
 
-	phy_dev = pdata->phy_dev;
+		phy_dev = of_phy_connect(ndev, phy_np, &xgene_enet_adjust_link,
+					 0, pdata->phy_mode);
+		if (!phy_dev) {
+			netdev_err(ndev, "Could not connect to PHY\n");
+			return -ENODEV;
+		}
+
+		pdata->phy_dev = phy_dev;
+	} else {
+		phy_dev = pdata->phy_dev;
 
-	if (!phy_dev ||
-	    phy_connect_direct(ndev, phy_dev, &xgene_enet_adjust_link,
-			       pdata->phy_mode)) {
-		netdev_err(ndev, "Could not connect to PHY\n");
-		return  -ENODEV;
+		if (!phy_dev ||
+		    phy_connect_direct(ndev, phy_dev, &xgene_enet_adjust_link,
+				       pdata->phy_mode)) {
+			netdev_err(ndev, "Could not connect to PHY\n");
+			return  -ENODEV;
+		}
 	}
 
 	pdata->phy_speed = SPEED_UNKNOWN;
diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c
index f9cb99bfb511..ffd180570920 100644
--- a/drivers/net/ethernet/arc/emac_arc.c
+++ b/drivers/net/ethernet/arc/emac_arc.c
@@ -78,6 +78,7 @@ static const struct of_device_id emac_arc_dt_ids[] = {
 	{ .compatible = "snps,arc-emac" },
 	{ /* Sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, emac_arc_dt_ids);
 
 static struct platform_driver emac_arc_driver = {
 	.probe = emac_arc_probe,
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index b9a5a97ed4dd..f1b5364f3521 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2079,6 +2079,7 @@ static const struct of_device_id bcm_sysport_of_match[] = {
 	{ .compatible = "brcm,systemport" },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, bcm_sysport_of_match);
 
 static struct platform_driver bcm_sysport_driver = {
 	.probe	= bcm_sysport_probe,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index ba936635322a..b5e64b02200c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1946,6 +1946,7 @@ struct bnx2x {
 	u16 vlan_cnt;
 	u16 vlan_credit;
 	u16 vxlan_dst_port;
+	u8 vxlan_dst_port_count;
 	bool accept_any_vlan;
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index e3da2bddf143..f1d62d5dbaff 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -3705,16 +3705,14 @@ out:
 
 void bnx2x_update_mfw_dump(struct bnx2x *bp)
 {
-	struct timeval epoc;
 	u32 drv_ver;
 	u32 valid_dump;
 
 	if (!SHMEM2_HAS(bp, drv_info))
 		return;
 
-	/* Update Driver load time */
-	do_gettimeofday(&epoc);
-	SHMEM2_WR(bp, drv_info.epoc, epoc.tv_sec);
+	/* Update Driver load time, possibly broken in y2038 */
+	SHMEM2_WR(bp, drv_info.epoc, (u32)ktime_get_real_seconds());
 
 	drv_ver = bnx2x_update_mng_version_utility(DRV_MODULE_VERSION, true);
 	SHMEM2_WR(bp, drv_info.drv_ver, drv_ver);
@@ -10110,12 +10108,18 @@ static void __bnx2x_add_vxlan_port(struct bnx2x *bp, u16 port)
 	if (!netif_running(bp->dev))
 		return;
 
-	if (bp->vxlan_dst_port || !IS_PF(bp)) {
+	if (bp->vxlan_dst_port_count && bp->vxlan_dst_port == port) {
+		bp->vxlan_dst_port_count++;
+		return;
+	}
+
+	if (bp->vxlan_dst_port_count || !IS_PF(bp)) {
 		DP(BNX2X_MSG_SP, "Vxlan destination port limit reached\n");
 		return;
 	}
 
 	bp->vxlan_dst_port = port;
+	bp->vxlan_dst_port_count = 1;
 	bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_ADD_VXLAN_PORT, 0);
 }
 
@@ -10130,10 +10134,14 @@ static void bnx2x_add_vxlan_port(struct net_device *netdev,
 
 static void __bnx2x_del_vxlan_port(struct bnx2x *bp, u16 port)
 {
-	if (!bp->vxlan_dst_port || bp->vxlan_dst_port != port || !IS_PF(bp)) {
+	if (!bp->vxlan_dst_port_count || bp->vxlan_dst_port != port ||
+	    !IS_PF(bp)) {
 		DP(BNX2X_MSG_SP, "Invalid vxlan port\n");
 		return;
 	}
+	bp->vxlan_dst_port--;
+	if (bp->vxlan_dst_port)
+		return;
 
 	if (netif_running(bp->dev)) {
 		bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_DEL_VXLAN_PORT, 0);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index c9bd7f16018e..ff702a707a91 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -4319,8 +4319,16 @@ static int bnx2x_setup_rss(struct bnx2x *bp,
 
 	/* RSS keys */
 	if (test_bit(BNX2X_RSS_SET_SRCH, &p->rss_flags)) {
-		memcpy(&data->rss_key[0], &p->rss_key[0],
-		       sizeof(data->rss_key));
+		u8 *dst = (u8 *)(data->rss_key) + sizeof(data->rss_key);
+		const u8 *src = (const u8 *)p->rss_key;
+		int i;
+
+		/* Apparently, bnx2x reads this array in reverse order
+		 * We need to byte swap rss_key to comply with Toeplitz specs.
+		 */
+		for (i = 0; i < sizeof(data->rss_key); i++)
+			*--dst = *src++;
+
 		caps |= ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index fadbd0088d3e..3bc701e4c59e 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3155,6 +3155,7 @@ static const struct of_device_id bcmgenet_match[] = {
 	{ .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, bcmgenet_match);
 
 static int bcmgenet_probe(struct platform_device *pdev)
 {
diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
index 5d0753cc7e73..04b0d16b210e 100644
--- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
+++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
@@ -2400,6 +2400,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad,
 		q0->rcb->id = 0;
 		q0->rx_packets = q0->rx_bytes = 0;
 		q0->rx_packets_with_error = q0->rxbuf_alloc_failed = 0;
+		q0->rxbuf_map_failed = 0;
 
 		bna_rxq_qpt_setup(q0, rxp, dpage_count, PAGE_SIZE,
 			&dqpt_mem[i], &dsqpt_mem[i], &dpage_mem[i]);
@@ -2428,6 +2429,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad,
 					: rx_cfg->q1_buf_size;
 			q1->rx_packets = q1->rx_bytes = 0;
 			q1->rx_packets_with_error = q1->rxbuf_alloc_failed = 0;
+			q1->rxbuf_map_failed = 0;
 
 			bna_rxq_qpt_setup(q1, rxp, hpage_count, PAGE_SIZE,
 				&hqpt_mem[i], &hsqpt_mem[i],
diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h
index e0e797f2ea14..c438d032e8bf 100644
--- a/drivers/net/ethernet/brocade/bna/bna_types.h
+++ b/drivers/net/ethernet/brocade/bna/bna_types.h
@@ -587,6 +587,7 @@ struct bna_rxq {
 	u64		rx_bytes;
 	u64		rx_packets_with_error;
 	u64		rxbuf_alloc_failed;
+	u64		rxbuf_map_failed;
 };
 
 /* RxQ pair */
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 506047c38607..21a0cfc3e7ec 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -399,7 +399,13 @@ bnad_rxq_refill_page(struct bnad *bnad, struct bna_rcb *rcb, u32 nalloc)
 		}
 
 		dma_addr = dma_map_page(&bnad->pcidev->dev, page, page_offset,
-				unmap_q->map_size, DMA_FROM_DEVICE);
+					unmap_q->map_size, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+			put_page(page);
+			BNAD_UPDATE_CTR(bnad, rxbuf_map_failed);
+			rcb->rxq->rxbuf_map_failed++;
+			goto finishing;
+		}
 
 		unmap->page = page;
 		unmap->page_offset = page_offset;
@@ -454,8 +460,15 @@ bnad_rxq_refill_skb(struct bnad *bnad, struct bna_rcb *rcb, u32 nalloc)
 			rcb->rxq->rxbuf_alloc_failed++;
 			goto finishing;
 		}
+
 		dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data,
 					  buff_sz, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+			dev_kfree_skb_any(skb);
+			BNAD_UPDATE_CTR(bnad, rxbuf_map_failed);
+			rcb->rxq->rxbuf_map_failed++;
+			goto finishing;
+		}
 
 		unmap->skb = skb;
 		dma_unmap_addr_set(&unmap->vector, dma_addr, dma_addr);
@@ -3025,6 +3038,11 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	unmap = head_unmap;
 	dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data,
 				  len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+		dev_kfree_skb_any(skb);
+		BNAD_UPDATE_CTR(bnad, tx_skb_map_failed);
+		return NETDEV_TX_OK;
+	}
 	BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[0].host_addr);
 	txqent->vector[0].length = htons(len);
 	dma_unmap_addr_set(&unmap->vectors[0], dma_addr, dma_addr);
@@ -3056,6 +3074,15 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 		dma_addr = skb_frag_dma_map(&bnad->pcidev->dev, frag,
 					    0, size, DMA_TO_DEVICE);
+		if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+			/* Undo the changes starting at tcb->producer_index */
+			bnad_tx_buff_unmap(bnad, unmap_q, q_depth,
+					   tcb->producer_index);
+			dev_kfree_skb_any(skb);
+			BNAD_UPDATE_CTR(bnad, tx_skb_map_failed);
+			return NETDEV_TX_OK;
+		}
+
 		dma_unmap_len_set(&unmap->vectors[vect_id], dma_len, size);
 		BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[vect_id].host_addr);
 		txqent->vector[vect_id].length = htons(size);
diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h
index faedbf24777e..f4ed816b93ee 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.h
+++ b/drivers/net/ethernet/brocade/bna/bnad.h
@@ -175,6 +175,7 @@ struct bnad_drv_stats {
 	u64		tx_skb_headlen_zero;
 	u64		tx_skb_frag_zero;
 	u64		tx_skb_len_mismatch;
+	u64		tx_skb_map_failed;
 
 	u64		hw_stats_updates;
 	u64		netif_rx_dropped;
@@ -189,6 +190,7 @@ struct bnad_drv_stats {
 	u64		rx_unmap_q_alloc_failed;
 
 	u64		rxbuf_alloc_failed;
+	u64		rxbuf_map_failed;
 };
 
 /* Complete driver stats */
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index 2bdfc5dff4b1..0e4fdc3dd729 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -90,6 +90,7 @@ static const char *bnad_net_stats_strings[BNAD_ETHTOOL_STATS_NUM] = {
 	"tx_skb_headlen_zero",
 	"tx_skb_frag_zero",
 	"tx_skb_len_mismatch",
+	"tx_skb_map_failed",
 	"hw_stats_updates",
 	"netif_rx_dropped",
 
@@ -102,6 +103,7 @@ static const char *bnad_net_stats_strings[BNAD_ETHTOOL_STATS_NUM] = {
 	"tx_unmap_q_alloc_failed",
 	"rx_unmap_q_alloc_failed",
 	"rxbuf_alloc_failed",
+	"rxbuf_map_failed",
 
 	"mac_stats_clr_cnt",
 	"mac_frame_64",
@@ -807,6 +809,7 @@ bnad_per_q_stats_fill(struct bnad *bnad, u64 *buf, int bi)
 							rx_packets_with_error;
 					buf[bi++] = rcb->rxq->
 							rxbuf_alloc_failed;
+					buf[bi++] = rcb->rxq->rxbuf_map_failed;
 					buf[bi++] = rcb->producer_index;
 					buf[bi++] = rcb->consumer_index;
 				}
@@ -821,6 +824,7 @@ bnad_per_q_stats_fill(struct bnad *bnad, u64 *buf, int bi)
 							rx_packets_with_error;
 					buf[bi++] = rcb->rxq->
 							rxbuf_alloc_failed;
+					buf[bi++] = rcb->rxq->rxbuf_map_failed;
 					buf[bi++] = rcb->producer_index;
 					buf[bi++] = rcb->consumer_index;
 				}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index 8353a6cbfcc2..03ed00c49823 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -157,6 +157,11 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x5090),	/* Custom T540-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x5091),	/* Custom T522-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x5092),	/* Custom T520-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5093),	/* Custom T580-LP-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5094),	/* Custom T540-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5095),	/* Custom T540-CR-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x5096),	/* Custom T580-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5097),	/* Custom T520-KR */
 
 	/* T6 adapters:
 	 */
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 0a27805cbbbd..821540913343 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -582,6 +582,7 @@ struct be_adapter {
 	u16 pvid;
 	__be16 vxlan_port;
 	int vxlan_port_count;
+	int vxlan_port_aliases;
 	struct phy_info phy;
 	u8 wol_cap;
 	bool wol_en;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 12687bf52b95..7bf51a1a0a77 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5176,6 +5176,11 @@ static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
 	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
 
+	if (adapter->vxlan_port == port && adapter->vxlan_port_count) {
+		adapter->vxlan_port_aliases++;
+		return;
+	}
+
 	if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) {
 		dev_info(dev,
 			 "Only one UDP port supported for VxLAN offloads\n");
@@ -5226,6 +5231,11 @@ static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
 	if (adapter->vxlan_port != port)
 		goto done;
 
+	if (adapter->vxlan_port_aliases) {
+		adapter->vxlan_port_aliases--;
+		return;
+	}
+
 	be_disable_vxlan_offloads(adapter);
 
 	dev_info(&adapter->pdev->dev,
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 4b69d061d90f..710715fcb23d 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1710,8 +1710,10 @@ static void gfar_configure_serdes(struct net_device *dev)
 	 * everything for us?  Resetting it takes the link down and requires
 	 * several seconds for it to come back.
 	 */
-	if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS)
+	if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) {
+		put_device(&tbiphy->dev);
 		return;
+	}
 
 	/* Single clk mode, mii mode off(for serdes communication) */
 	phy_write(tbiphy, MII_TBICON, TBICON_CLK_SELECT);
@@ -1723,6 +1725,8 @@ static void gfar_configure_serdes(struct net_device *dev)
 	phy_write(tbiphy, MII_BMCR,
 		  BMCR_ANENABLE | BMCR_ANRESTART | BMCR_FULLDPLX |
 		  BMCR_SPEED1000);
+
+	put_device(&tbiphy->dev);
 }
 
 static int __gfar_is_rx_idle(struct gfar_private *priv)
@@ -1970,8 +1974,7 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 		/* Install our interrupt handlers for Error,
 		 * Transmit, and Receive
 		 */
-		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error,
-				  IRQF_NO_SUSPEND,
+		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0,
 				  gfar_irq(grp, ER)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -1979,6 +1982,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 
 			goto err_irq_fail;
 		}
+		enable_irq_wake(gfar_irq(grp, ER)->irq);
+
 		err = request_irq(gfar_irq(grp, TX)->irq, gfar_transmit, 0,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
@@ -1994,14 +1999,14 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 			goto rx_irq_fail;
 		}
 	} else {
-		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt,
-				  IRQF_NO_SUSPEND,
+		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
 				  gfar_irq(grp, TX)->irq);
 			goto err_irq_fail;
 		}
+		enable_irq_wake(gfar_irq(grp, TX)->irq);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index 8e3cd77aa347..664d0c261269 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -557,6 +557,7 @@ static const struct of_device_id match_table[] = {
 	{ .compatible = "fsl,etsec-ptp" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, match_table);
 
 static struct platform_driver gianfar_ptp_driver = {
 	.driver = {
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 4dd40e057f40..650f7888e32b 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1384,6 +1384,8 @@ static int adjust_enet_interface(struct ucc_geth_private *ugeth)
 		value = phy_read(tbiphy, ENET_TBI_MII_CR);
 		value &= ~0x1000;	/* Turn off autonegotiation */
 		phy_write(tbiphy, ENET_TBI_MII_CR, value);
+
+		put_device(&tbiphy->dev);
 	}
 
 	init_check_frame_length_mode(ug_info->lengthCheckRx, &ug_regs->maccfg2);
@@ -1702,8 +1704,10 @@ static void uec_configure_serdes(struct net_device *dev)
 	 * everything for us?  Resetting it takes the link down and requires
 	 * several seconds for it to come back.
 	 */
-	if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS)
+	if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS) {
+		put_device(&tbiphy->dev);
 		return;
+	}
 
 	/* Single clk mode, mii mode off(for serdes communication) */
 	phy_write(tbiphy, ENET_TBI_MII_ANA, TBIANA_SETTINGS);
@@ -1711,6 +1715,8 @@ static void uec_configure_serdes(struct net_device *dev)
 	phy_write(tbiphy, ENET_TBI_MII_TBICON, TBICON_CLK_SELECT);
 
 	phy_write(tbiphy, ENET_TBI_MII_CR, TBICR_SETTINGS);
+
+	put_device(&tbiphy->dev);
 }
 
 /* Configure the PHY for dev.
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index fe2299ac4f5c..514df76fc70f 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1479,6 +1479,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
 		struct sk_buff *skb;
 		unsigned char *data;
+		dma_addr_t phys_addr;
 		u32 rx_status;
 		int rx_bytes, err;
 
@@ -1486,6 +1487,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		data = (unsigned char *)rx_desc->buf_cookie;
+		phys_addr = rx_desc->buf_phys_addr;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
 		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
@@ -1534,7 +1536,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		if (!skb)
 			goto err_drop_frame;
 
-		dma_unmap_single(dev->dev.parent, rx_desc->buf_phys_addr,
+		dma_unmap_single(dev->dev.parent, phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
 
 		rcvd_pkts++;
@@ -3173,6 +3175,8 @@ static int mvneta_probe(struct platform_device *pdev)
 		struct phy_device *phy = of_phy_find_device(dn);
 
 		mvneta_fixed_link_update(pp, phy);
+
+		put_device(&phy->dev);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 4c7de8c44659..e7a5000aa12c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1270,8 +1270,6 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 		rss_context->hash_fn = MLX4_RSS_HASH_TOP;
 		memcpy(rss_context->rss_key, priv->rss_key,
 		       MLX4_EN_RSS_KEY_SIZE);
-		netdev_rss_key_fill(rss_context->rss_key,
-				    MLX4_EN_RSS_KEY_SIZE);
 	} else {
 		en_err(priv, "Unknown RSS hash function requested\n");
 		err = -EINVAL;
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 66d4ab703f45..60f43ec22175 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1601,6 +1601,7 @@ static const struct of_device_id ks8851_match_table[] = {
 	{ .compatible = "micrel,ks8851" },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, ks8851_match_table);
 
 static struct spi_driver ks8851_driver = {
 	.driver = {
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index becbb5f1f5a7..a10c928bbd6b 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -552,6 +552,7 @@ static const struct of_device_id moxart_mac_match[] = {
 	{ .compatible = "moxa,moxart-mac" },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, moxart_mac_match);
 
 static struct platform_driver moxart_mac_driver = {
 	.probe	= moxart_mac_probe,
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 06bcc734fe8d..d6696cfa11d2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -536,6 +536,7 @@ struct qlcnic_hardware_context {
 	u8 extend_lb_time;
 	u8 phys_port_id[ETH_ALEN];
 	u8 lb_mode;
+	u8 vxlan_port_count;
 	u16 vxlan_port;
 	struct device *hwmon_dev;
 	u32 post_mode;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 8b08b20e8b30..d4481454b5f8 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -483,11 +483,17 @@ static void qlcnic_add_vxlan_port(struct net_device *netdev,
 	/* Adapter supports only one VXLAN port. Use very first port
 	 * for enabling offload
 	 */
-	if (!qlcnic_encap_rx_offload(adapter) || ahw->vxlan_port)
+	if (!qlcnic_encap_rx_offload(adapter))
 		return;
+	if (!ahw->vxlan_port_count) {
+		ahw->vxlan_port_count = 1;
+		ahw->vxlan_port = ntohs(port);
+		adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
+		return;
+	}
+	if (ahw->vxlan_port == ntohs(port))
+		ahw->vxlan_port_count++;
 
-	ahw->vxlan_port = ntohs(port);
-	adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
 }
 
 static void qlcnic_del_vxlan_port(struct net_device *netdev,
@@ -496,11 +502,13 @@ static void qlcnic_del_vxlan_port(struct net_device *netdev,
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 
-	if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port ||
+	if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port_count ||
 	    (ahw->vxlan_port != ntohs(port)))
 		return;
 
-	adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
+	ahw->vxlan_port_count--;
+	if (!ahw->vxlan_port_count)
+		adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
 }
 
 static netdev_features_t qlcnic_features_check(struct sk_buff *skb,
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index d79e33b3c191..686334f4588d 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -157,6 +157,7 @@ enum {
 	NWayAdvert	= 0x66, /* MII ADVERTISE */
 	NWayLPAR	= 0x68, /* MII LPA */
 	NWayExpansion	= 0x6A, /* MII Expansion */
+	TxDmaOkLowDesc  = 0x82, /* Low 16 bit address of a Tx descriptor. */
 	Config5		= 0xD8,	/* Config5 */
 	TxPoll		= 0xD9,	/* Tell chip to check Tx descriptors for work */
 	RxMaxSize	= 0xDA, /* Max size of an Rx packet (8169 only) */
@@ -341,6 +342,7 @@ struct cp_private {
 	unsigned		tx_tail;
 	struct cp_desc		*tx_ring;
 	struct sk_buff		*tx_skb[CP_TX_RING_SIZE];
+	u32			tx_opts[CP_TX_RING_SIZE];
 
 	unsigned		rx_buf_sz;
 	unsigned		wol_enabled : 1; /* Is Wake-on-LAN enabled? */
@@ -665,7 +667,7 @@ static void cp_tx (struct cp_private *cp)
 		BUG_ON(!skb);
 
 		dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr),
-				 le32_to_cpu(txd->opts1) & 0xffff,
+				 cp->tx_opts[tx_tail] & 0xffff,
 				 PCI_DMA_TODEVICE);
 
 		if (status & LastFrag) {
@@ -733,7 +735,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned entry;
-	u32 eor, flags;
+	u32 eor, opts1;
 	unsigned long intr_flags;
 	__le32 opts2;
 	int mss = 0;
@@ -753,6 +755,21 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 	mss = skb_shinfo(skb)->gso_size;
 
 	opts2 = cpu_to_le32(cp_tx_vlan_tag(skb));
+	opts1 = DescOwn;
+	if (mss)
+		opts1 |= LargeSend | ((mss & MSSMask) << MSSShift);
+	else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		const struct iphdr *ip = ip_hdr(skb);
+		if (ip->protocol == IPPROTO_TCP)
+			opts1 |= IPCS | TCPCS;
+		else if (ip->protocol == IPPROTO_UDP)
+			opts1 |= IPCS | UDPCS;
+		else {
+			WARN_ONCE(1,
+				  "Net bug: asked to checksum invalid Legacy IP packet\n");
+			goto out_dma_error;
+		}
+	}
 
 	if (skb_shinfo(skb)->nr_frags == 0) {
 		struct cp_desc *txd = &cp->tx_ring[entry];
@@ -768,31 +785,20 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		txd->addr = cpu_to_le64(mapping);
 		wmb();
 
-		flags = eor | len | DescOwn | FirstFrag | LastFrag;
-
-		if (mss)
-			flags |= LargeSend | ((mss & MSSMask) << MSSShift);
-		else if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			const struct iphdr *ip = ip_hdr(skb);
-			if (ip->protocol == IPPROTO_TCP)
-				flags |= IPCS | TCPCS;
-			else if (ip->protocol == IPPROTO_UDP)
-				flags |= IPCS | UDPCS;
-			else
-				WARN_ON(1);	/* we need a WARN() */
-		}
+		opts1 |= eor | len | FirstFrag | LastFrag;
 
-		txd->opts1 = cpu_to_le32(flags);
+		txd->opts1 = cpu_to_le32(opts1);
 		wmb();
 
 		cp->tx_skb[entry] = skb;
-		entry = NEXT_TX(entry);
+		cp->tx_opts[entry] = opts1;
+		netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n",
+			  entry, skb->len);
 	} else {
 		struct cp_desc *txd;
-		u32 first_len, first_eor;
+		u32 first_len, first_eor, ctrl;
 		dma_addr_t first_mapping;
 		int frag, first_entry = entry;
-		const struct iphdr *ip = ip_hdr(skb);
 
 		/* We must give this initial chunk to the device last.
 		 * Otherwise we could race with the device.
@@ -805,14 +811,14 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			goto out_dma_error;
 
 		cp->tx_skb[entry] = skb;
-		entry = NEXT_TX(entry);
 
 		for (frag = 0; frag < skb_shinfo(skb)->nr_frags; frag++) {
 			const skb_frag_t *this_frag = &skb_shinfo(skb)->frags[frag];
 			u32 len;
-			u32 ctrl;
 			dma_addr_t mapping;
 
+			entry = NEXT_TX(entry);
+
 			len = skb_frag_size(this_frag);
 			mapping = dma_map_single(&cp->pdev->dev,
 						 skb_frag_address(this_frag),
@@ -824,19 +830,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 
 			eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
 
-			ctrl = eor | len | DescOwn;
-
-			if (mss)
-				ctrl |= LargeSend |
-					((mss & MSSMask) << MSSShift);
-			else if (skb->ip_summed == CHECKSUM_PARTIAL) {
-				if (ip->protocol == IPPROTO_TCP)
-					ctrl |= IPCS | TCPCS;
-				else if (ip->protocol == IPPROTO_UDP)
-					ctrl |= IPCS | UDPCS;
-				else
-					BUG();
-			}
+			ctrl = opts1 | eor | len;
 
 			if (frag == skb_shinfo(skb)->nr_frags - 1)
 				ctrl |= LastFrag;
@@ -849,8 +843,8 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			txd->opts1 = cpu_to_le32(ctrl);
 			wmb();
 
+			cp->tx_opts[entry] = ctrl;
 			cp->tx_skb[entry] = skb;
-			entry = NEXT_TX(entry);
 		}
 
 		txd = &cp->tx_ring[first_entry];
@@ -858,27 +852,17 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		txd->addr = cpu_to_le64(first_mapping);
 		wmb();
 
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			if (ip->protocol == IPPROTO_TCP)
-				txd->opts1 = cpu_to_le32(first_eor | first_len |
-							 FirstFrag | DescOwn |
-							 IPCS | TCPCS);
-			else if (ip->protocol == IPPROTO_UDP)
-				txd->opts1 = cpu_to_le32(first_eor | first_len |
-							 FirstFrag | DescOwn |
-							 IPCS | UDPCS);
-			else
-				BUG();
-		} else
-			txd->opts1 = cpu_to_le32(first_eor | first_len |
-						 FirstFrag | DescOwn);
+		ctrl = opts1 | first_eor | first_len | FirstFrag;
+		txd->opts1 = cpu_to_le32(ctrl);
 		wmb();
+
+		cp->tx_opts[first_entry] = ctrl;
+		netif_dbg(cp, tx_queued, cp->dev, "tx queued, slots %d-%d, skblen %d\n",
+			  first_entry, entry, skb->len);
 	}
-	cp->tx_head = entry;
+	cp->tx_head = NEXT_TX(entry);
 
 	netdev_sent_queue(dev, skb->len);
-	netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n",
-		  entry, skb->len);
 	if (TX_BUFFS_AVAIL(cp) <= (MAX_SKB_FRAGS + 1))
 		netif_stop_queue(dev);
 
@@ -1115,6 +1099,7 @@ static int cp_init_rings (struct cp_private *cp)
 {
 	memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE);
 	cp->tx_ring[CP_TX_RING_SIZE - 1].opts1 = cpu_to_le32(RingEnd);
+	memset(cp->tx_opts, 0, sizeof(cp->tx_opts));
 
 	cp_init_rings_index(cp);
 
@@ -1151,7 +1136,7 @@ static void cp_clean_rings (struct cp_private *cp)
 			desc = cp->rx_ring + i;
 			dma_unmap_single(&cp->pdev->dev,le64_to_cpu(desc->addr),
 					 cp->rx_buf_sz, PCI_DMA_FROMDEVICE);
-			dev_kfree_skb(cp->rx_skb[i]);
+			dev_kfree_skb_any(cp->rx_skb[i]);
 		}
 	}
 
@@ -1164,7 +1149,7 @@ static void cp_clean_rings (struct cp_private *cp)
 					 le32_to_cpu(desc->opts1) & 0xffff,
 					 PCI_DMA_TODEVICE);
 			if (le32_to_cpu(desc->opts1) & LastFrag)
-				dev_kfree_skb(skb);
+				dev_kfree_skb_any(skb);
 			cp->dev->stats.tx_dropped++;
 		}
 	}
@@ -1172,6 +1157,7 @@ static void cp_clean_rings (struct cp_private *cp)
 
 	memset(cp->rx_ring, 0, sizeof(struct cp_desc) * CP_RX_RING_SIZE);
 	memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE);
+	memset(cp->tx_opts, 0, sizeof(cp->tx_opts));
 
 	memset(cp->rx_skb, 0, sizeof(struct sk_buff *) * CP_RX_RING_SIZE);
 	memset(cp->tx_skb, 0, sizeof(struct sk_buff *) * CP_TX_RING_SIZE);
@@ -1249,7 +1235,7 @@ static void cp_tx_timeout(struct net_device *dev)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned long flags;
-	int rc;
+	int rc, i;
 
 	netdev_warn(dev, "Transmit timeout, status %2x %4x %4x %4x\n",
 		    cpr8(Cmd), cpr16(CpCmd),
@@ -1257,13 +1243,26 @@ static void cp_tx_timeout(struct net_device *dev)
 
 	spin_lock_irqsave(&cp->lock, flags);
 
+	netif_dbg(cp, tx_err, cp->dev, "TX ring head %d tail %d desc %x\n",
+		  cp->tx_head, cp->tx_tail, cpr16(TxDmaOkLowDesc));
+	for (i = 0; i < CP_TX_RING_SIZE; i++) {
+		netif_dbg(cp, tx_err, cp->dev,
+			  "TX slot %d @%p: %08x (%08x) %08x %llx %p\n",
+			  i, &cp->tx_ring[i], le32_to_cpu(cp->tx_ring[i].opts1),
+			  cp->tx_opts[i], le32_to_cpu(cp->tx_ring[i].opts2),
+			  le64_to_cpu(cp->tx_ring[i].addr),
+			  cp->tx_skb[i]);
+	}
+
 	cp_stop_hw(cp);
 	cp_clean_rings(cp);
 	rc = cp_init_rings(cp);
 	cp_start_hw(cp);
-	cp_enable_irq(cp);
+	__cp_set_rx_mode(dev);
+	cpw16_f(IntrMask, cp_norx_intr_mask);
 
 	netif_wake_queue(dev);
+	napi_schedule_irqoff(&cp->napi);
 
 	spin_unlock_irqrestore(&cp->lock, flags);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index b735fa22ac95..ebf6abc4853f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -161,11 +161,16 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 
 		if (!gpio_request(reset_gpio, "mdio-reset")) {
 			gpio_direction_output(reset_gpio, active_low ? 1 : 0);
-			udelay(data->delays[0]);
+			if (data->delays[0])
+				msleep(DIV_ROUND_UP(data->delays[0], 1000));
+
 			gpio_set_value(reset_gpio, active_low ? 0 : 1);
-			udelay(data->delays[1]);
+			if (data->delays[1])
+				msleep(DIV_ROUND_UP(data->delays[1], 1000));
+
 			gpio_set_value(reset_gpio, active_low ? 1 : 0);
-			udelay(data->delays[2]);
+			if (data->delays[2])
+				msleep(DIV_ROUND_UP(data->delays[2], 1000));
 		}
 	}
 #endif
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 53fe200e0b79..cc106d892e29 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1756,7 +1756,8 @@ static const struct net_device_ops vnet_ops = {
 #endif
 };
 
-static struct vnet *vnet_new(const u64 *local_mac)
+static struct vnet *vnet_new(const u64 *local_mac,
+			     struct vio_dev *vdev)
 {
 	struct net_device *dev;
 	struct vnet *vp;
@@ -1790,6 +1791,8 @@ static struct vnet *vnet_new(const u64 *local_mac)
 			   NETIF_F_HW_CSUM | NETIF_F_SG;
 	dev->features = dev->hw_features;
 
+	SET_NETDEV_DEV(dev, &vdev->dev);
+
 	err = register_netdev(dev);
 	if (err) {
 		pr_err("Cannot register net device, aborting\n");
@@ -1808,7 +1811,8 @@ err_out_free_dev:
 	return ERR_PTR(err);
 }
 
-static struct vnet *vnet_find_or_create(const u64 *local_mac)
+static struct vnet *vnet_find_or_create(const u64 *local_mac,
+					struct vio_dev *vdev)
 {
 	struct vnet *iter, *vp;
 
@@ -1821,7 +1825,7 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac)
 		}
 	}
 	if (!vp)
-		vp = vnet_new(local_mac);
+		vp = vnet_new(local_mac, vdev);
 	mutex_unlock(&vnet_list_mutex);
 
 	return vp;
@@ -1848,7 +1852,8 @@ static void vnet_cleanup(void)
 static const char *local_mac_prop = "local-mac-address";
 
 static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
-						u64 port_node)
+				     u64 port_node,
+				     struct vio_dev *vdev)
 {
 	const u64 *local_mac = NULL;
 	u64 a;
@@ -1869,7 +1874,7 @@ static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
 	if (!local_mac)
 		return ERR_PTR(-ENODEV);
 
-	return vnet_find_or_create(local_mac);
+	return vnet_find_or_create(local_mac, vdev);
 }
 
 static struct ldc_channel_config vnet_ldc_cfg = {
@@ -1923,7 +1928,7 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 
 	hp = mdesc_grab();
 
-	vp = vnet_find_parent(hp, vdev->mp);
+	vp = vnet_find_parent(hp, vdev->mp, vdev);
 	if (IS_ERR(vp)) {
 		pr_err("Cannot find port parent vnet\n");
 		err = PTR_ERR(vp);
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 1a5aca55ea9f..9f9832f0dea9 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -291,13 +291,6 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 			    interface_list) {
 		struct netcp_intf_modpriv *intf_modpriv;
 
-		/* If interface not registered then register now */
-		if (!netcp_intf->netdev_registered)
-			ret = netcp_register_interface(netcp_intf);
-
-		if (ret)
-			return -ENODEV;
-
 		intf_modpriv = devm_kzalloc(dev, sizeof(*intf_modpriv),
 					    GFP_KERNEL);
 		if (!intf_modpriv)
@@ -306,6 +299,11 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 		interface = of_parse_phandle(netcp_intf->node_interface,
 					     module->name, 0);
 
+		if (!interface) {
+			devm_kfree(dev, intf_modpriv);
+			continue;
+		}
+
 		intf_modpriv->netcp_priv = netcp_intf;
 		intf_modpriv->netcp_module = module;
 		list_add_tail(&intf_modpriv->intf_list,
@@ -323,6 +321,18 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 			continue;
 		}
 	}
+
+	/* Now register the interface with netdev */
+	list_for_each_entry(netcp_intf,
+			    &netcp_device->interface_head,
+			    interface_list) {
+		/* If interface not registered then register now */
+		if (!netcp_intf->netdev_registered) {
+			ret = netcp_register_interface(netcp_intf);
+			if (ret)
+				return -ENODEV;
+		}
+	}
 	return 0;
 }
 
@@ -357,7 +367,6 @@ int netcp_register_module(struct netcp_module *module)
 		if (ret < 0)
 			goto fail;
 	}
-
 	mutex_unlock(&netcp_modules_lock);
 	return 0;
 
@@ -796,7 +805,7 @@ static void netcp_rxpool_free(struct netcp_intf *netcp)
 	netcp->rx_pool = NULL;
 }
 
-static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
+static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 {
 	struct knav_dma_desc *hwdesc;
 	unsigned int buf_len, dma_sz;
@@ -810,7 +819,7 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	hwdesc = knav_pool_desc_get(netcp->rx_pool);
 	if (IS_ERR_OR_NULL(hwdesc)) {
 		dev_dbg(netcp->ndev_dev, "out of rx pool desc\n");
-		return;
+		return -ENOMEM;
 	}
 
 	if (likely(fdq == 0)) {
@@ -862,25 +871,26 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	knav_pool_desc_map(netcp->rx_pool, hwdesc, sizeof(*hwdesc), &dma,
 			   &dma_sz);
 	knav_queue_push(netcp->rx_fdq[fdq], dma, sizeof(*hwdesc), 0);
-	return;
+	return 0;
 
 fail:
 	knav_pool_desc_put(netcp->rx_pool, hwdesc);
+	return -ENOMEM;
 }
 
 /* Refill Rx FDQ with descriptors & attached buffers */
 static void netcp_rxpool_refill(struct netcp_intf *netcp)
 {
 	u32 fdq_deficit[KNAV_DMA_FDQ_PER_CHAN] = {0};
-	int i;
+	int i, ret = 0;
 
 	/* Calculate the FDQ deficit and refill */
 	for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && netcp->rx_fdq[i]; i++) {
 		fdq_deficit[i] = netcp->rx_queue_depths[i] -
 				 knav_queue_get_count(netcp->rx_fdq[i]);
 
-		while (fdq_deficit[i]--)
-			netcp_allocate_rx_buf(netcp, i);
+		while (fdq_deficit[i]-- && !ret)
+			ret = netcp_allocate_rx_buf(netcp, i);
 	} /* end for fdqs */
 }
 
@@ -893,12 +903,12 @@ static int netcp_rx_poll(struct napi_struct *napi, int budget)
 
 	packets = netcp_process_rx_packets(netcp, budget);
 
+	netcp_rxpool_refill(netcp);
 	if (packets < budget) {
 		napi_complete(&netcp->rx_napi);
 		knav_queue_enable_notify(netcp->rx_queue);
 	}
 
-	netcp_rxpool_refill(netcp);
 	return packets;
 }
 
@@ -1384,7 +1394,6 @@ static void netcp_addr_sweep_del(struct netcp_intf *netcp)
 			continue;
 		dev_dbg(netcp->ndev_dev, "deleting address %pM, type %x\n",
 			naddr->addr, naddr->type);
-		mutex_lock(&netcp_modules_lock);
 		for_each_module(netcp, priv) {
 			module = priv->netcp_module;
 			if (!module->del_addr)
@@ -1393,7 +1402,6 @@ static void netcp_addr_sweep_del(struct netcp_intf *netcp)
 						 naddr);
 			WARN_ON(error);
 		}
-		mutex_unlock(&netcp_modules_lock);
 		netcp_addr_del(netcp, naddr);
 	}
 }
@@ -1410,7 +1418,7 @@ static void netcp_addr_sweep_add(struct netcp_intf *netcp)
 			continue;
 		dev_dbg(netcp->ndev_dev, "adding address %pM, type %x\n",
 			naddr->addr, naddr->type);
-		mutex_lock(&netcp_modules_lock);
+
 		for_each_module(netcp, priv) {
 			module = priv->netcp_module;
 			if (!module->add_addr)
@@ -1418,7 +1426,6 @@ static void netcp_addr_sweep_add(struct netcp_intf *netcp)
 			error = module->add_addr(priv->module_priv, naddr);
 			WARN_ON(error);
 		}
-		mutex_unlock(&netcp_modules_lock);
 	}
 }
 
@@ -1432,6 +1439,7 @@ static void netcp_set_rx_mode(struct net_device *ndev)
 		   ndev->flags & IFF_ALLMULTI ||
 		   netdev_mc_count(ndev) > NETCP_MAX_MCAST_ADDR);
 
+	spin_lock(&netcp->lock);
 	/* first clear all marks */
 	netcp_addr_clear_mark(netcp);
 
@@ -1450,6 +1458,7 @@ static void netcp_set_rx_mode(struct net_device *ndev)
 	/* finally sweep and callout into modules */
 	netcp_addr_sweep_del(netcp);
 	netcp_addr_sweep_add(netcp);
+	spin_unlock(&netcp->lock);
 }
 
 static void netcp_free_navigator_resources(struct netcp_intf *netcp)
@@ -1614,7 +1623,6 @@ static int netcp_ndo_open(struct net_device *ndev)
 		goto fail;
 	}
 
-	mutex_lock(&netcp_modules_lock);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (module->open) {
@@ -1625,7 +1633,6 @@ static int netcp_ndo_open(struct net_device *ndev)
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
 
 	napi_enable(&netcp->rx_napi);
 	napi_enable(&netcp->tx_napi);
@@ -1642,7 +1649,6 @@ fail_open:
 		if (module->close)
 			module->close(intf_modpriv->module_priv, ndev);
 	}
-	mutex_unlock(&netcp_modules_lock);
 
 fail:
 	netcp_free_navigator_resources(netcp);
@@ -1666,7 +1672,6 @@ static int netcp_ndo_stop(struct net_device *ndev)
 	napi_disable(&netcp->rx_napi);
 	napi_disable(&netcp->tx_napi);
 
-	mutex_lock(&netcp_modules_lock);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (module->close) {
@@ -1675,7 +1680,6 @@ static int netcp_ndo_stop(struct net_device *ndev)
 				dev_err(netcp->ndev_dev, "Close failed\n");
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
 
 	/* Recycle Rx descriptors from completion queue */
 	netcp_empty_rx_queue(netcp);
@@ -1703,7 +1707,6 @@ static int netcp_ndo_ioctl(struct net_device *ndev,
 	if (!netif_running(ndev))
 		return -EINVAL;
 
-	mutex_lock(&netcp_modules_lock);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (!module->ioctl)
@@ -1719,7 +1722,6 @@ static int netcp_ndo_ioctl(struct net_device *ndev,
 	}
 
 out:
-	mutex_unlock(&netcp_modules_lock);
 	return (ret == 0) ? 0 : err;
 }
 
@@ -1754,11 +1756,12 @@ static int netcp_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 	struct netcp_intf *netcp = netdev_priv(ndev);
 	struct netcp_intf_modpriv *intf_modpriv;
 	struct netcp_module *module;
+	unsigned long flags;
 	int err = 0;
 
 	dev_dbg(netcp->ndev_dev, "adding rx vlan id: %d\n", vid);
 
-	mutex_lock(&netcp_modules_lock);
+	spin_lock_irqsave(&netcp->lock, flags);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if ((module->add_vid) && (vid != 0)) {
@@ -1770,7 +1773,8 @@ static int netcp_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
+	spin_unlock_irqrestore(&netcp->lock, flags);
+
 	return err;
 }
 
@@ -1779,11 +1783,12 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 	struct netcp_intf *netcp = netdev_priv(ndev);
 	struct netcp_intf_modpriv *intf_modpriv;
 	struct netcp_module *module;
+	unsigned long flags;
 	int err = 0;
 
 	dev_dbg(netcp->ndev_dev, "removing rx vlan id: %d\n", vid);
 
-	mutex_lock(&netcp_modules_lock);
+	spin_lock_irqsave(&netcp->lock, flags);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (module->del_vid) {
@@ -1795,7 +1800,7 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
+	spin_unlock_irqrestore(&netcp->lock, flags);
 	return err;
 }
 
@@ -2040,7 +2045,6 @@ static int netcp_probe(struct platform_device *pdev)
 	struct device_node *child, *interfaces;
 	struct netcp_device *netcp_device;
 	struct device *dev = &pdev->dev;
-	struct netcp_module *module;
 	int ret;
 
 	if (!node) {
@@ -2087,14 +2091,6 @@ static int netcp_probe(struct platform_device *pdev)
 	/* Add the device instance to the list */
 	list_add_tail(&netcp_device->device_list, &netcp_devices);
 
-	/* Probe & attach any modules already registered */
-	mutex_lock(&netcp_modules_lock);
-	for_each_netcp_module(module) {
-		ret = netcp_module_probe(netcp_device, module);
-		if (ret < 0)
-			dev_err(dev, "module(%s) probe failed\n", module->name);
-	}
-	mutex_unlock(&netcp_modules_lock);
 	return 0;
 
 probe_quit_interface:
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 6f16d6aaf7b7..6bff8d82ceab 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -77,6 +77,7 @@
 #define GBENU_ALE_OFFSET		0x1e000
 #define GBENU_HOST_PORT_NUM		0
 #define GBENU_NUM_ALE_ENTRIES		1024
+#define GBENU_SGMII_MODULE_SIZE		0x100
 
 /* 10G Ethernet SS defines */
 #define XGBE_MODULE_NAME		"netcp-xgbe"
@@ -149,8 +150,8 @@
 #define XGBE_STATS2_MODULE			2
 
 /* s: 0-based slave_port */
-#define SGMII_BASE(s) \
-	(((s) < 2) ? gbe_dev->sgmii_port_regs : gbe_dev->sgmii_port34_regs)
+#define SGMII_BASE(d, s) \
+	(((s) < 2) ? (d)->sgmii_port_regs : (d)->sgmii_port34_regs)
 
 #define GBE_TX_QUEUE				648
 #define	GBE_TXHOOK_ORDER			0
@@ -1997,13 +1998,8 @@ static void netcp_ethss_update_link_state(struct gbe_priv *gbe_dev,
 		return;
 
 	if (!SLAVE_LINK_IS_XGMII(slave)) {
-		if (gbe_dev->ss_version == GBE_SS_VERSION_14)
-			sgmii_link_state =
-				netcp_sgmii_get_port_link(SGMII_BASE(sp), sp);
-		else
-			sgmii_link_state =
-				netcp_sgmii_get_port_link(
-						gbe_dev->sgmii_port_regs, sp);
+		sgmii_link_state =
+			netcp_sgmii_get_port_link(SGMII_BASE(gbe_dev, sp), sp);
 	}
 
 	phy_link_state = gbe_phy_link_status(slave);
@@ -2100,17 +2096,11 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave,
 static void gbe_sgmii_rtreset(struct gbe_priv *priv,
 			      struct gbe_slave *slave, bool set)
 {
-	void __iomem *sgmii_port_regs;
-
 	if (SLAVE_LINK_IS_XGMII(slave))
 		return;
 
-	if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
-		sgmii_port_regs = priv->sgmii_port34_regs;
-	else
-		sgmii_port_regs = priv->sgmii_port_regs;
-
-	netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set);
+	netcp_sgmii_rtreset(SGMII_BASE(priv, slave->slave_num),
+			    slave->slave_num, set);
 }
 
 static void gbe_slave_stop(struct gbe_intf *intf)
@@ -2136,17 +2126,12 @@ static void gbe_slave_stop(struct gbe_intf *intf)
 
 static void gbe_sgmii_config(struct gbe_priv *priv, struct gbe_slave *slave)
 {
-	void __iomem *sgmii_port_regs;
-
-	sgmii_port_regs = priv->sgmii_port_regs;
-	if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
-		sgmii_port_regs = priv->sgmii_port34_regs;
+	if (SLAVE_LINK_IS_XGMII(slave))
+		return;
 
-	if (!SLAVE_LINK_IS_XGMII(slave)) {
-		netcp_sgmii_reset(sgmii_port_regs, slave->slave_num);
-		netcp_sgmii_config(sgmii_port_regs, slave->slave_num,
-				   slave->link_interface);
-	}
+	netcp_sgmii_reset(SGMII_BASE(priv, slave->slave_num), slave->slave_num);
+	netcp_sgmii_config(SGMII_BASE(priv, slave->slave_num), slave->slave_num,
+			   slave->link_interface);
 }
 
 static int gbe_slave_open(struct gbe_intf *gbe_intf)
@@ -2997,6 +2982,14 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev,
 	gbe_dev->switch_regs = regs;
 
 	gbe_dev->sgmii_port_regs = gbe_dev->ss_regs + GBENU_SGMII_MODULE_OFFSET;
+
+	/* Although sgmii modules are mem mapped to one contiguous
+	 * region on GBENU devices, setting sgmii_port34_regs allows
+	 * consistent code when accessing sgmii api
+	 */
+	gbe_dev->sgmii_port34_regs = gbe_dev->sgmii_port_regs +
+				     (2 * GBENU_SGMII_MODULE_SIZE);
+
 	gbe_dev->host_port_regs = gbe_dev->switch_regs + GBENU_HOST_PORT_OFFSET;
 
 	for (i = 0; i < (gbe_dev->max_num_ports); i++)
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index 2f1264b882b9..d3d094742a7e 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -17,7 +17,7 @@ if NET_VENDOR_VIA
 
 config VIA_RHINE
 	tristate "VIA Rhine support"
-	depends on (PCI || OF_IRQ)
+	depends on PCI || (OF_IRQ && GENERIC_PCI_IOMAP)
 	depends on HAS_DMA
 	select CRC32
 	select MII
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 6008eee01a33..cf468c87ce57 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -828,6 +828,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev)
 		if (!phydev)
 			dev_info(dev,
 				 "MDIO of the phy is not registered yet\n");
+		else
+			put_device(&phydev->dev);
 		return 0;
 	}
 
diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c
index b5f4a78da828..2d3848c9dc35 100644
--- a/drivers/net/fjes/fjes_hw.c
+++ b/drivers/net/fjes/fjes_hw.c
@@ -1011,11 +1011,11 @@ static void fjes_hw_update_zone_task(struct work_struct *work)
 					set_bit(epidx, &irq_bit);
 				break;
 			}
-		}
-
-		hw->ep_shm_info[epidx].es_status = info[epidx].es_status;
-		hw->ep_shm_info[epidx].zone = info[epidx].zone;
 
+			hw->ep_shm_info[epidx].es_status =
+				info[epidx].es_status;
+			hw->ep_shm_info[epidx].zone = info[epidx].zone;
+		}
 		break;
 	}
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index da3259ce7c8d..8f5c02eed47d 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -126,6 +126,8 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 	__be32 addr;
 	int err;
 
+	iph = ip_hdr(skb); /* outer IP header... */
+
 	if (gs->collect_md) {
 		static u8 zero_vni[3];
 
@@ -133,7 +135,6 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 		addr = 0;
 	} else {
 		vni = gnvh->vni;
-		iph = ip_hdr(skb); /* Still outer IP header... */
 		addr = iph->saddr;
 	}
 
@@ -178,7 +179,6 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 
-	iph = ip_hdr(skb); /* Now inner IP header... */
 	err = IP_ECN_decapsulate(iph, skb);
 
 	if (unlikely(err)) {
@@ -626,6 +626,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct geneve_sock *gs = geneve->sock;
 	struct ip_tunnel_info *info = NULL;
 	struct rtable *rt = NULL;
+	const struct iphdr *iip; /* interior IP header */
 	struct flowi4 fl4;
 	__u8 tos, ttl;
 	__be16 sport;
@@ -653,6 +654,8 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
+	iip = ip_hdr(skb);
+
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -668,19 +671,16 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (unlikely(err))
 			goto err;
 
-		tos = key->tos;
+		tos = ip_tunnel_ecn_encap(key->tos, iip, skb);
 		ttl = key->ttl;
 		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 	} else {
-		const struct iphdr *iip; /* interior IP header */
-
 		udp_csum = false;
 		err = geneve_build_skb(rt, skb, 0, geneve->vni,
 				       0, NULL, udp_csum);
 		if (unlikely(err))
 			goto err;
 
-		iip = ip_hdr(skb);
 		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);
 		ttl = geneve->ttl;
 		if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
@@ -748,12 +748,8 @@ static void geneve_setup(struct net_device *dev)
 	dev->features    |= NETIF_F_RXCSUM;
 	dev->features    |= NETIF_F_GSO_SOFTWARE;
 
-	dev->vlan_features = dev->features;
-	dev->features    |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
-
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
-	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 
 	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
@@ -819,7 +815,7 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn,
 
 static int geneve_configure(struct net *net, struct net_device *dev,
 			    __be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos,
-			    __u16 dst_port, bool metadata)
+			    __be16 dst_port, bool metadata)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *t, *geneve = netdev_priv(dev);
@@ -844,10 +840,10 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 
 	geneve->ttl = ttl;
 	geneve->tos = tos;
-	geneve->dst_port = htons(dst_port);
+	geneve->dst_port = dst_port;
 	geneve->collect_md = metadata;
 
-	t = geneve_find_dev(gn, htons(dst_port), rem_addr, geneve->vni,
+	t = geneve_find_dev(gn, dst_port, rem_addr, geneve->vni,
 			    &tun_on_same_port, &tun_collect_md);
 	if (t)
 		return -EBUSY;
@@ -871,7 +867,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 static int geneve_newlink(struct net *net, struct net_device *dev,
 			  struct nlattr *tb[], struct nlattr *data[])
 {
-	__u16 dst_port = GENEVE_UDP_PORT;
+	__be16 dst_port = htons(GENEVE_UDP_PORT);
 	__u8 ttl = 0, tos = 0;
 	bool metadata = false;
 	__be32 rem_addr;
@@ -890,7 +886,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 		tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
 
 	if (data[IFLA_GENEVE_PORT])
-		dst_port = nla_get_u16(data[IFLA_GENEVE_PORT]);
+		dst_port = nla_get_be16(data[IFLA_GENEVE_PORT]);
 
 	if (data[IFLA_GENEVE_COLLECT_METADATA])
 		metadata = true;
@@ -913,7 +909,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TTL */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TOS */
-		nla_total_size(sizeof(__u16)) +  /* IFLA_GENEVE_PORT */
+		nla_total_size(sizeof(__be16)) +  /* IFLA_GENEVE_PORT */
 		nla_total_size(0) +	 /* IFLA_GENEVE_COLLECT_METADATA */
 		0;
 }
@@ -935,7 +931,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos))
 		goto nla_put_failure;
 
-	if (nla_put_u16(skb, IFLA_GENEVE_PORT, ntohs(geneve->dst_port)))
+	if (nla_put_be16(skb, IFLA_GENEVE_PORT, geneve->dst_port))
 		goto nla_put_failure;
 
 	if (geneve->collect_md) {
@@ -975,7 +971,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 	if (IS_ERR(dev))
 		return dev;
 
-	err = geneve_configure(net, dev, 0, 0, 0, 0, dst_port, true);
+	err = geneve_configure(net, dev, 0, 0, 0, 0, htons(dst_port), true);
 	if (err) {
 		free_netdev(dev);
 		return ERR_PTR(err);
diff --git a/drivers/net/irda/ali-ircc.c b/drivers/net/irda/ali-ircc.c
index 58ae11a14bb6..64bb44d5d867 100644
--- a/drivers/net/irda/ali-ircc.c
+++ b/drivers/net/irda/ali-ircc.c
@@ -1031,7 +1031,6 @@ static void ali_ircc_fir_change_speed(struct ali_ircc_cb *priv, __u32 baud)
 static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 {
 	struct ali_ircc_cb *self = priv;
-	unsigned long flags;
 	int iobase; 
 	int fcr;    /* FIFO control reg */
 	int lcr;    /* Line control reg */
@@ -1061,8 +1060,6 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 	/* Update accounting for new speed */
 	self->io.speed = speed;
 
-	spin_lock_irqsave(&self->lock, flags);
-
 	divisor = 115200/speed;
 	
 	fcr = UART_FCR_ENABLE_FIFO;
@@ -1089,9 +1086,6 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 	/* without this, the connection will be broken after come back from FIR speed,
 	   but with this, the SIR connection is harder to established */
 	outb((UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2), iobase+UART_MCR);
-	
-	spin_unlock_irqrestore(&self->lock, flags);
-	
 }
 
 static void ali_ircc_change_dongle_speed(struct ali_ircc_cb *priv, int speed)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index edd77342773a..248478c6f6e4 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1111,10 +1111,10 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 		return 0;
 
 	case TUNSETSNDBUF:
-		if (get_user(u, up))
+		if (get_user(s, sp))
 			return -EFAULT;
 
-		q->sk.sk_sndbuf = u;
+		q->sk.sk_sndbuf = s;
 		return 0;
 
 	case TUNGETVNETHDRSZ:
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index fb1299c6326e..e23bf5b90e17 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -220,7 +220,7 @@ int fixed_phy_update_state(struct phy_device *phydev,
 	struct fixed_mdio_bus *fmb = &platform_fmb;
 	struct fixed_phy *fp;
 
-	if (!phydev || !phydev->bus)
+	if (!phydev || phydev->bus != fmb->mii_bus)
 		return -EINVAL;
 
 	list_for_each_entry(fp, &fmb->phys, node) {
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index e6897b6a8a53..5de8d5827536 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -785,6 +785,7 @@ static int marvell_read_status(struct phy_device *phydev)
 	int adv;
 	int err;
 	int lpa;
+	int lpagb;
 	int status = 0;
 
 	/* Update the link, but return if there
@@ -802,10 +803,17 @@ static int marvell_read_status(struct phy_device *phydev)
 		if (lpa < 0)
 			return lpa;
 
+		lpagb = phy_read(phydev, MII_STAT1000);
+		if (lpagb < 0)
+			return lpagb;
+
 		adv = phy_read(phydev, MII_ADVERTISE);
 		if (adv < 0)
 			return adv;
 
+		phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb) |
+					 mii_lpa_to_ethtool_lpa_t(lpa);
+
 		lpa &= adv;
 
 		if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
@@ -853,6 +861,7 @@ static int marvell_read_status(struct phy_device *phydev)
 			phydev->speed = SPEED_10;
 
 		phydev->pause = phydev->asym_pause = 0;
+		phydev->lp_advertising = 0;
 	}
 
 	return 0;
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 6a52a7f0fa0d..4bde5e728fe0 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -244,6 +244,7 @@ static const struct of_device_id unimac_mdio_ids[] = {
 	{ .compatible = "brcm,unimac-mdio", },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, unimac_mdio_ids);
 
 static struct platform_driver unimac_mdio_driver = {
 	.driver = {
diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 7dc21e56a7aa..3bc9f03349f3 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -261,6 +261,7 @@ static const struct of_device_id mdio_gpio_of_match[] = {
 	{ .compatible = "virtual,mdio-gpio", },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, mdio_gpio_of_match);
 
 static struct platform_driver mdio_gpio_driver = {
 	.probe = mdio_gpio_probe,
diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c
index 4d4d25efc1e1..280c7c311f72 100644
--- a/drivers/net/phy/mdio-mux.c
+++ b/drivers/net/phy/mdio-mux.c
@@ -113,18 +113,18 @@ int mdio_mux_init(struct device *dev,
 	if (!parent_bus_node)
 		return -ENODEV;
 
-	parent_bus = of_mdio_find_bus(parent_bus_node);
-	if (parent_bus == NULL) {
-		ret_val = -EPROBE_DEFER;
-		goto err_parent_bus;
-	}
-
 	pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL);
 	if (pb == NULL) {
 		ret_val = -ENOMEM;
 		goto err_parent_bus;
 	}
 
+	parent_bus = of_mdio_find_bus(parent_bus_node);
+	if (parent_bus == NULL) {
+		ret_val = -EPROBE_DEFER;
+		goto err_parent_bus;
+	}
+
 	pb->switch_data = data;
 	pb->switch_fn = switch_fn;
 	pb->current_child = -1;
@@ -173,6 +173,10 @@ int mdio_mux_init(struct device *dev,
 		dev_info(dev, "Version " DRV_VERSION "\n");
 		return 0;
 	}
+
+	/* balance the reference of_mdio_find_bus() took */
+	put_device(&pb->mii_bus->dev);
+
 err_parent_bus:
 	of_node_put(parent_bus_node);
 	return ret_val;
@@ -189,6 +193,9 @@ void mdio_mux_uninit(void *mux_handle)
 		mdiobus_free(cb->mii_bus);
 		cb = cb->next;
 	}
+
+	/* balance the reference of_mdio_find_bus() in mdio_mux_init() took */
+	put_device(&pb->mii_bus->dev);
 }
 EXPORT_SYMBOL_GPL(mdio_mux_uninit);
 
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 02a4615b65f8..12f44c53cc8e 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -167,7 +167,9 @@ static int of_mdio_bus_match(struct device *dev, const void *mdio_bus_np)
  * of_mdio_find_bus - Given an mii_bus node, find the mii_bus.
  * @mdio_bus_np: Pointer to the mii_bus.
  *
- * Returns a pointer to the mii_bus, or NULL if none found.
+ * Returns a reference to the mii_bus, or NULL if none found.  The
+ * embedded struct device will have its reference count incremented,
+ * and this must be put once the bus is finished with.
  *
  * Because the association of a device_node and mii_bus is made via
  * of_mdiobus_register(), the mii_bus cannot be found before it is
@@ -234,15 +236,18 @@ static inline void of_mdiobus_link_phydev(struct mii_bus *mdio,
 #endif
 
 /**
- * mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
+ * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
  * @bus: target mii_bus
+ * @owner: module containing bus accessor functions
  *
  * Description: Called by a bus driver to bring up all the PHYs
- *   on a given bus, and attach them to the bus.
+ *   on a given bus, and attach them to the bus. Drivers should use
+ *   mdiobus_register() rather than __mdiobus_register() unless they
+ *   need to pass a specific owner module.
  *
  * Returns 0 on success or < 0 on error.
  */
-int mdiobus_register(struct mii_bus *bus)
+int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 {
 	int i, err;
 
@@ -253,6 +258,7 @@ int mdiobus_register(struct mii_bus *bus)
 	BUG_ON(bus->state != MDIOBUS_ALLOCATED &&
 	       bus->state != MDIOBUS_UNREGISTERED);
 
+	bus->owner = owner;
 	bus->dev.parent = bus->parent;
 	bus->dev.class = &mdio_bus_class;
 	bus->dev.groups = NULL;
@@ -288,13 +294,16 @@ int mdiobus_register(struct mii_bus *bus)
 
 error:
 	while (--i >= 0) {
-		if (bus->phy_map[i])
-			device_unregister(&bus->phy_map[i]->dev);
+		struct phy_device *phydev = bus->phy_map[i];
+		if (phydev) {
+			phy_device_remove(phydev);
+			phy_device_free(phydev);
+		}
 	}
 	device_del(&bus->dev);
 	return err;
 }
-EXPORT_SYMBOL(mdiobus_register);
+EXPORT_SYMBOL(__mdiobus_register);
 
 void mdiobus_unregister(struct mii_bus *bus)
 {
@@ -304,9 +313,11 @@ void mdiobus_unregister(struct mii_bus *bus)
 	bus->state = MDIOBUS_UNREGISTERED;
 
 	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		if (bus->phy_map[i])
-			device_unregister(&bus->phy_map[i]->dev);
-		bus->phy_map[i] = NULL;
+		struct phy_device *phydev = bus->phy_map[i];
+		if (phydev) {
+			phy_device_remove(phydev);
+			phy_device_free(phydev);
+		}
 	}
 	device_del(&bus->dev);
 }
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index c0f211127274..f761288abe66 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -384,6 +384,24 @@ int phy_device_register(struct phy_device *phydev)
 EXPORT_SYMBOL(phy_device_register);
 
 /**
+ * phy_device_remove - Remove a previously registered phy device from the MDIO bus
+ * @phydev: phy_device structure to remove
+ *
+ * This doesn't free the phy_device itself, it merely reverses the effects
+ * of phy_device_register(). Use phy_device_free() to free the device
+ * after calling this function.
+ */
+void phy_device_remove(struct phy_device *phydev)
+{
+	struct mii_bus *bus = phydev->bus;
+	int addr = phydev->addr;
+
+	device_del(&phydev->dev);
+	bus->phy_map[addr] = NULL;
+}
+EXPORT_SYMBOL(phy_device_remove);
+
+/**
  * phy_find_first - finds the first PHY device on the bus
  * @bus: the target MII bus
  */
@@ -578,14 +596,22 @@ EXPORT_SYMBOL(phy_init_hw);
  *     generic driver is used.  The phy_device is given a ptr to
  *     the attaching device, and given a callback for link status
  *     change.  The phy_device is returned to the attaching driver.
+ *     This function takes a reference on the phy device.
  */
 int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		      u32 flags, phy_interface_t interface)
 {
+	struct mii_bus *bus = phydev->bus;
 	struct device *d = &phydev->dev;
-	struct module *bus_module;
 	int err;
 
+	if (!try_module_get(bus->owner)) {
+		dev_err(&dev->dev, "failed to get the bus module\n");
+		return -EIO;
+	}
+
+	get_device(d);
+
 	/* Assume that if there is no driver, that it doesn't
 	 * exist, and we should use the genphy driver.
 	 */
@@ -600,20 +626,13 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 			err = device_bind_driver(d);
 
 		if (err)
-			return err;
+			goto error;
 	}
 
 	if (phydev->attached_dev) {
 		dev_err(&dev->dev, "PHY already attached\n");
-		return -EBUSY;
-	}
-
-	/* Increment the bus module reference count */
-	bus_module = phydev->bus->dev.driver ?
-		     phydev->bus->dev.driver->owner : NULL;
-	if (!try_module_get(bus_module)) {
-		dev_err(&dev->dev, "failed to get the bus module\n");
-		return -EIO;
+		err = -EBUSY;
+		goto error;
 	}
 
 	phydev->attached_dev = dev;
@@ -636,6 +655,11 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		phy_resume(phydev);
 
 	return err;
+
+error:
+	put_device(d);
+	module_put(bus->owner);
+	return err;
 }
 EXPORT_SYMBOL(phy_attach_direct);
 
@@ -677,14 +701,15 @@ EXPORT_SYMBOL(phy_attach);
 /**
  * phy_detach - detach a PHY device from its network device
  * @phydev: target phy_device struct
+ *
+ * This detaches the phy device from its network device and the phy
+ * driver, and drops the reference count taken in phy_attach_direct().
  */
 void phy_detach(struct phy_device *phydev)
 {
+	struct mii_bus *bus;
 	int i;
 
-	if (phydev->bus->dev.driver)
-		module_put(phydev->bus->dev.driver->owner);
-
 	phydev->attached_dev->phydev = NULL;
 	phydev->attached_dev = NULL;
 	phy_suspend(phydev);
@@ -700,6 +725,15 @@ void phy_detach(struct phy_device *phydev)
 			break;
 		}
 	}
+
+	/*
+	 * The phydev might go away on the put_device() below, so avoid
+	 * a use-after-free bug by reading the underlying bus first.
+	 */
+	bus = phydev->bus;
+
+	put_device(&phydev->dev);
+	module_put(bus->owner);
 }
 EXPORT_SYMBOL(phy_detach);
 
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 17cad185169d..76cad712ddb2 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -66,7 +66,6 @@
 #define PHY_ID_VSC8244			0x000fc6c0
 #define PHY_ID_VSC8514			0x00070670
 #define PHY_ID_VSC8574			0x000704a0
-#define PHY_ID_VSC8641			0x00070431
 #define PHY_ID_VSC8662			0x00070660
 #define PHY_ID_VSC8221			0x000fc550
 #define PHY_ID_VSC8211			0x000fc4b0
@@ -273,18 +272,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_intr    = &vsc82xx_config_intr,
 	.driver         = { .owner = THIS_MODULE,},
 }, {
-	.phy_id         = PHY_ID_VSC8641,
-	.name           = "Vitesse VSC8641",
-	.phy_id_mask    = 0x000ffff0,
-	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
-	.config_init    = &vsc824x_config_init,
-	.config_aneg    = &vsc82x4_config_aneg,
-	.read_status    = &genphy_read_status,
-	.ack_interrupt  = &vsc824x_ack_interrupt,
-	.config_intr    = &vsc82xx_config_intr,
-	.driver         = { .owner = THIS_MODULE,},
-}, {
 	.phy_id         = PHY_ID_VSC8662,
 	.name           = "Vitesse VSC8662",
 	.phy_id_mask    = 0x000ffff0,
@@ -331,7 +318,6 @@ static struct mdio_device_id __maybe_unused vitesse_tbl[] = {
 	{ PHY_ID_VSC8244, 0x000fffc0 },
 	{ PHY_ID_VSC8514, 0x000ffff0 },
 	{ PHY_ID_VSC8574, 0x000ffff0 },
-	{ PHY_ID_VSC8641, 0x000ffff0 },
 	{ PHY_ID_VSC8662, 0x000ffff0 },
 	{ PHY_ID_VSC8221, 0x000ffff0 },
 	{ PHY_ID_VSC8211, 0x000ffff0 },
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 0481daf9201a..ed00446759b2 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2755,6 +2755,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 	 */
 	dev_net_set(dev, net);
 
+	rtnl_lock();
 	mutex_lock(&pn->all_ppp_mutex);
 
 	if (unit < 0) {
@@ -2785,7 +2786,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 	ppp->file.index = unit;
 	sprintf(dev->name, "ppp%d", unit);
 
-	ret = register_netdev(dev);
+	ret = register_netdevice(dev);
 	if (ret != 0) {
 		unit_put(&pn->units_idr, unit);
 		netdev_err(ppp->dev, "PPP: couldn't register device %s (%d)\n",
@@ -2797,6 +2798,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 
 	atomic_inc(&ppp_unit_count);
 	mutex_unlock(&pn->all_ppp_mutex);
+	rtnl_unlock();
 
 	*retp = 0;
 	return ppp;
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 1610b79ae386..fbb9325d1f6e 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -583,4 +583,15 @@ config USB_VL600
 
 	  http://ubuntuforums.org/showpost.php?p=10589647&postcount=17
 
+config USB_NET_CH9200
+	tristate "QingHeng CH9200 USB ethernet support"
+	depends on USB_USBNET
+	select MII
+	help
+	  Choose this option if you have a USB ethernet adapter with a QinHeng
+	  CH9200 chipset.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ch9200.
+
 endif # USB_NET_DRIVERS
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index cf6a0e610a7f..b5f04068dbe4 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -38,4 +38,4 @@ obj-$(CONFIG_USB_NET_HUAWEI_CDC_NCM)	+= huawei_cdc_ncm.o
 obj-$(CONFIG_USB_VL600)		+= lg-vl600.o
 obj-$(CONFIG_USB_NET_QMI_WWAN)	+= qmi_wwan.o
 obj-$(CONFIG_USB_NET_CDC_MBIM)	+= cdc_mbim.o
-
+obj-$(CONFIG_USB_NET_CH9200)	+= ch9200.o
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
new file mode 100644
index 000000000000..5e151e6a3e09
--- /dev/null
+++ b/drivers/net/usb/ch9200.c
@@ -0,0 +1,432 @@
+/*
+ * USB 10M/100M ethernet adapter
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/crc32.h>
+#include <linux/usb/usbnet.h>
+#include <linux/slab.h>
+
+#define CH9200_VID		0x1A86
+#define CH9200_PID_E092		0xE092
+
+#define CTRL_TIMEOUT_MS		1000
+
+#define CONTROL_TIMEOUT_MS 1000
+
+#define REQUEST_READ	0x0E
+#define REQUEST_WRITE	0x0F
+
+/* Address space:
+ * 00-63 : MII
+ * 64-128: MAC
+ *
+ * Note: all accesses must be 16-bit
+ */
+
+#define MAC_REG_CTRL 64
+#define MAC_REG_STATUS 66
+#define MAC_REG_INTERRUPT_MASK 68
+#define MAC_REG_PHY_COMMAND 70
+#define MAC_REG_PHY_DATA 72
+#define MAC_REG_STATION_L 74
+#define MAC_REG_STATION_M 76
+#define MAC_REG_STATION_H 78
+#define MAC_REG_HASH_L 80
+#define MAC_REG_HASH_M1 82
+#define MAC_REG_HASH_M2 84
+#define MAC_REG_HASH_H 86
+#define MAC_REG_THRESHOLD 88
+#define MAC_REG_FIFO_DEPTH 90
+#define MAC_REG_PAUSE 92
+#define MAC_REG_FLOW_CONTROL 94
+
+/* Control register bits
+ *
+ * Note: bits 13 and 15 are reserved
+ */
+#define LOOPBACK		(0x01 << 14)
+#define BASE100X		(0x01 << 12)
+#define MBPS_10			(0x01 << 11)
+#define DUPLEX_MODE		(0x01 << 10)
+#define PAUSE_FRAME		(0x01 << 9)
+#define PROMISCUOUS		(0x01 << 8)
+#define MULTICAST		(0x01 << 7)
+#define BROADCAST		(0x01 << 6)
+#define HASH			(0x01 << 5)
+#define APPEND_PAD		(0x01 << 4)
+#define APPEND_CRC		(0x01 << 3)
+#define TRANSMITTER_ACTION	(0x01 << 2)
+#define RECEIVER_ACTION		(0x01 << 1)
+#define DMA_ACTION		(0x01 << 0)
+
+/* Status register bits
+ *
+ * Note: bits 7-15 are reserved
+ */
+#define ALIGNMENT		(0x01 << 6)
+#define FIFO_OVER_RUN		(0x01 << 5)
+#define FIFO_UNDER_RUN		(0x01 << 4)
+#define RX_ERROR		(0x01 << 3)
+#define RX_COMPLETE		(0x01 << 2)
+#define TX_ERROR		(0x01 << 1)
+#define TX_COMPLETE		(0x01 << 0)
+
+/* FIFO depth register bits
+ *
+ * Note: bits 6 and 14 are reserved
+ */
+
+#define ETH_TXBD		(0x01 << 15)
+#define ETN_TX_FIFO_DEPTH	(0x01 << 8)
+#define ETH_RXBD		(0x01 << 7)
+#define ETH_RX_FIFO_DEPTH	(0x01 << 0)
+
+static int control_read(struct usbnet *dev,
+			unsigned char request, unsigned short value,
+			unsigned short index, void *data, unsigned short size,
+			int timeout)
+{
+	unsigned char *buf = NULL;
+	unsigned char request_type;
+	int err = 0;
+
+	if (request == REQUEST_READ)
+		request_type = (USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_OTHER);
+	else
+		request_type = (USB_DIR_IN | USB_TYPE_VENDOR |
+				USB_RECIP_DEVICE);
+
+	netdev_dbg(dev->net, "Control_read() index=0x%02x size=%d\n",
+		   index, size);
+
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	err = usb_control_msg(dev->udev,
+			      usb_rcvctrlpipe(dev->udev, 0),
+			      request, request_type, value, index, buf, size,
+			      timeout);
+	if (err == size)
+		memcpy(data, buf, size);
+	else if (err >= 0)
+		err = -EINVAL;
+	kfree(buf);
+
+	return err;
+
+err_out:
+	return err;
+}
+
+static int control_write(struct usbnet *dev, unsigned char request,
+			 unsigned short value, unsigned short index,
+			 void *data, unsigned short size, int timeout)
+{
+	unsigned char *buf = NULL;
+	unsigned char request_type;
+	int err = 0;
+
+	if (request == REQUEST_WRITE)
+		request_type = (USB_DIR_OUT | USB_TYPE_VENDOR |
+				USB_RECIP_OTHER);
+	else
+		request_type = (USB_DIR_OUT | USB_TYPE_VENDOR |
+				USB_RECIP_DEVICE);
+
+	netdev_dbg(dev->net, "Control_write() index=0x%02x size=%d\n",
+		   index, size);
+
+	if (data) {
+		buf = kmalloc(size, GFP_KERNEL);
+		if (!buf) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+		memcpy(buf, data, size);
+	}
+
+	err = usb_control_msg(dev->udev,
+			      usb_sndctrlpipe(dev->udev, 0),
+			      request, request_type, value, index, buf, size,
+			      timeout);
+	if (err >= 0 && err < size)
+		err = -EINVAL;
+	kfree(buf);
+
+	return 0;
+
+err_out:
+	return err;
+}
+
+static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	unsigned char buff[2];
+
+	netdev_dbg(netdev, "ch9200_mdio_read phy_id:%02x loc:%02x\n",
+		   phy_id, loc);
+
+	if (phy_id != 0)
+		return -ENODEV;
+
+	control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
+		     CONTROL_TIMEOUT_MS);
+
+	return (buff[0] | buff[1] << 8);
+}
+
+static void ch9200_mdio_write(struct net_device *netdev,
+			      int phy_id, int loc, int val)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	unsigned char buff[2];
+
+	netdev_dbg(netdev, "ch9200_mdio_write() phy_id=%02x loc:%02x\n",
+		   phy_id, loc);
+
+	if (phy_id != 0)
+		return;
+
+	buff[0] = (unsigned char)val;
+	buff[1] = (unsigned char)(val >> 8);
+
+	control_write(dev, REQUEST_WRITE, 0, loc * 2, buff, 0x02,
+		      CONTROL_TIMEOUT_MS);
+}
+
+static int ch9200_link_reset(struct usbnet *dev)
+{
+	struct ethtool_cmd ecmd;
+
+	mii_check_media(&dev->mii, 1, 1);
+	mii_ethtool_gset(&dev->mii, &ecmd);
+
+	netdev_dbg(dev->net, "link_reset() speed:%d duplex:%d\n",
+		   ecmd.speed, ecmd.duplex);
+
+	return 0;
+}
+
+static void ch9200_status(struct usbnet *dev, struct urb *urb)
+{
+	int link;
+	unsigned char *buf;
+
+	if (urb->actual_length < 16)
+		return;
+
+	buf = urb->transfer_buffer;
+	link = !!(buf[0] & 0x01);
+
+	if (link) {
+		netif_carrier_on(dev->net);
+		usbnet_defer_kevent(dev, EVENT_LINK_RESET);
+	} else {
+		netif_carrier_off(dev->net);
+	}
+}
+
+static struct sk_buff *ch9200_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
+				       gfp_t flags)
+{
+	int i = 0;
+	int len = 0;
+	int tx_overhead = 0;
+
+	tx_overhead = 0x40;
+
+	len = skb->len;
+	if (skb_headroom(skb) < tx_overhead) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_copy_expand(skb, tx_overhead, 0, flags);
+		dev_kfree_skb_any(skb);
+		skb = skb2;
+		if (!skb)
+			return NULL;
+	}
+
+	__skb_push(skb, tx_overhead);
+	/* usbnet adds padding if length is a multiple of packet size
+	 * if so, adjust length value in header
+	 */
+	if ((skb->len % dev->maxpacket) == 0)
+		len++;
+
+	skb->data[0] = len;
+	skb->data[1] = len >> 8;
+	skb->data[2] = 0x00;
+	skb->data[3] = 0x80;
+
+	for (i = 4; i < 48; i++)
+		skb->data[i] = 0x00;
+
+	skb->data[48] = len;
+	skb->data[49] = len >> 8;
+	skb->data[50] = 0x00;
+	skb->data[51] = 0x80;
+
+	for (i = 52; i < 64; i++)
+		skb->data[i] = 0x00;
+
+	return skb;
+}
+
+static int ch9200_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	int len = 0;
+	int rx_overhead = 0;
+
+	rx_overhead = 64;
+
+	if (unlikely(skb->len < rx_overhead)) {
+		dev_err(&dev->udev->dev, "unexpected tiny rx frame\n");
+		return 0;
+	}
+
+	len = (skb->data[skb->len - 16] | skb->data[skb->len - 15] << 8);
+	skb_trim(skb, len);
+
+	return 1;
+}
+
+static int get_mac_address(struct usbnet *dev, unsigned char *data)
+{
+	int err = 0;
+	unsigned char mac_addr[0x06];
+	int rd_mac_len = 0;
+
+	netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n",
+		   dev->udev->descriptor.idVendor,
+		   dev->udev->descriptor.idProduct);
+
+	memset(mac_addr, 0, sizeof(mac_addr));
+	rd_mac_len = control_read(dev, REQUEST_READ, 0,
+				  MAC_REG_STATION_L, mac_addr, 0x02,
+				  CONTROL_TIMEOUT_MS);
+	rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_M,
+				   mac_addr + 2, 0x02, CONTROL_TIMEOUT_MS);
+	rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_H,
+				   mac_addr + 4, 0x02, CONTROL_TIMEOUT_MS);
+	if (rd_mac_len != ETH_ALEN)
+		err = -EINVAL;
+
+	data[0] = mac_addr[5];
+	data[1] = mac_addr[4];
+	data[2] = mac_addr[3];
+	data[3] = mac_addr[2];
+	data[4] = mac_addr[1];
+	data[5] = mac_addr[0];
+
+	return err;
+}
+
+static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	int retval = 0;
+	unsigned char data[2];
+
+	retval = usbnet_get_endpoints(dev, intf);
+	if (retval)
+		return retval;
+
+	dev->mii.dev = dev->net;
+	dev->mii.mdio_read = ch9200_mdio_read;
+	dev->mii.mdio_write = ch9200_mdio_write;
+	dev->mii.reg_num_mask = 0x1f;
+
+	dev->mii.phy_id_mask = 0x1f;
+
+	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
+	dev->rx_urb_size = 24 * 64 + 16;
+	mii_nway_restart(&dev->mii);
+
+	data[0] = 0x01;
+	data[1] = 0x0F;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_THRESHOLD, data,
+			       0x02, CONTROL_TIMEOUT_MS);
+
+	data[0] = 0xA0;
+	data[1] = 0x90;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FIFO_DEPTH, data,
+			       0x02, CONTROL_TIMEOUT_MS);
+
+	data[0] = 0x30;
+	data[1] = 0x00;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_PAUSE, data,
+			       0x02, CONTROL_TIMEOUT_MS);
+
+	data[0] = 0x17;
+	data[1] = 0xD8;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FLOW_CONTROL,
+			       data, 0x02, CONTROL_TIMEOUT_MS);
+
+	/* Undocumented register */
+	data[0] = 0x01;
+	data[1] = 0x00;
+	retval = control_write(dev, REQUEST_WRITE, 0, 254, data, 0x02,
+			       CONTROL_TIMEOUT_MS);
+
+	data[0] = 0x5F;
+	data[1] = 0x0D;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_CTRL, data, 0x02,
+			       CONTROL_TIMEOUT_MS);
+
+	retval = get_mac_address(dev, dev->net->dev_addr);
+
+	return retval;
+}
+
+static const struct driver_info ch9200_info = {
+	.description = "CH9200 USB to Network Adaptor",
+	.flags = FLAG_ETHER,
+	.bind = ch9200_bind,
+	.rx_fixup = ch9200_rx_fixup,
+	.tx_fixup = ch9200_tx_fixup,
+	.status = ch9200_status,
+	.link_reset = ch9200_link_reset,
+	.reset = ch9200_link_reset,
+};
+
+static const struct usb_device_id ch9200_products[] = {
+	{
+	 USB_DEVICE(0x1A86, 0xE092),
+	 .driver_info = (unsigned long)&ch9200_info,
+	 },
+	{},
+};
+
+MODULE_DEVICE_TABLE(usb, ch9200_products);
+
+static struct usb_driver ch9200_driver = {
+	.name = "ch9200",
+	.id_table = ch9200_products,
+	.probe = usbnet_probe,
+	.disconnect = usbnet_disconnect,
+	.suspend = usbnet_suspend,
+	.resume = usbnet_resume,
+};
+
+module_usb_driver(ch9200_driver);
+
+MODULE_DESCRIPTION("QinHeng CH9200 USB Network device");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index e7094fbd7568..488c6f50df73 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -193,7 +193,8 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 		.flowi4_oif = vrf_dev->ifindex,
 		.flowi4_iif = LOOPBACK_IFINDEX,
 		.flowi4_tos = RT_TOS(ip4h->tos),
-		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC,
+		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC |
+				FLOWI_FLAG_SKIP_NH_OIF,
 		.daddr = ip4h->daddr,
 	};
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index cf8b7f0473b3..bbac1d35ed4e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2392,10 +2392,6 @@ static void vxlan_setup(struct net_device *dev)
 
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
-	if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
-		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
-	else
-		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = free_netdev;
@@ -2640,8 +2636,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		dst->remote_ip.sa.sa_family = AF_INET;
 
 	if (dst->remote_ip.sa.sa_family == AF_INET6 ||
-	    vxlan->cfg.saddr.sa.sa_family == AF_INET6)
+	    vxlan->cfg.saddr.sa.sa_family == AF_INET6) {
+		if (!IS_ENABLED(CONFIG_IPV6))
+			return -EPFNOSUPPORT;
 		use_ipv6 = true;
+	}
 
 	if (conf->remote_ifindex) {
 		struct net_device *lowerdev
@@ -2670,8 +2669,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 
 		dev->needed_headroom = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
-	} else if (use_ipv6)
+	} else if (use_ipv6) {
 		vxlan->flags |= VXLAN_F_IPV6;
+		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
+	} else {
+		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
+	}
 
 	memcpy(&vxlan->cfg, conf, sizeof(*conf));
 	if (!vxlan->cfg.dst_port)
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 1350fa25cdb0..a87a868fed64 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -197,7 +197,8 @@ static int of_phy_match(struct device *dev, void *phy_np)
  * of_phy_find_device - Give a PHY node, find the phy_device
  * @phy_np: Pointer to the phy's device tree node
  *
- * Returns a pointer to the phy_device.
+ * If successful, returns a pointer to the phy_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure.
  */
 struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
@@ -217,7 +218,9 @@ EXPORT_SYMBOL(of_phy_find_device);
  * @hndlr: Link state callback for the network device
  * @iface: PHY data interface type
  *
- * Returns a pointer to the phy_device if successful.  NULL otherwise
+ * If successful, returns a pointer to the phy_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure. The
+ * refcount must be dropped by calling phy_disconnect() or phy_detach().
  */
 struct phy_device *of_phy_connect(struct net_device *dev,
 				  struct device_node *phy_np,
@@ -225,13 +228,19 @@ struct phy_device *of_phy_connect(struct net_device *dev,
 				  phy_interface_t iface)
 {
 	struct phy_device *phy = of_phy_find_device(phy_np);
+	int ret;
 
 	if (!phy)
 		return NULL;
 
 	phy->dev_flags = flags;
 
-	return phy_connect_direct(dev, phy, hndlr, iface) ? NULL : phy;
+	ret = phy_connect_direct(dev, phy, hndlr, iface);
+
+	/* refcount is held by phy_connect_direct() on success */
+	put_device(&phy->dev);
+
+	return ret ? NULL : phy;
 }
 EXPORT_SYMBOL(of_phy_connect);
 
@@ -241,17 +250,27 @@ EXPORT_SYMBOL(of_phy_connect);
  * @phy_np: Node pointer for the PHY
  * @flags: flags to pass to the PHY
  * @iface: PHY data interface type
+ *
+ * If successful, returns a pointer to the phy_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure. The
+ * refcount must be dropped by calling phy_disconnect() or phy_detach().
  */
 struct phy_device *of_phy_attach(struct net_device *dev,
 				 struct device_node *phy_np, u32 flags,
 				 phy_interface_t iface)
 {
 	struct phy_device *phy = of_phy_find_device(phy_np);
+	int ret;
 
 	if (!phy)
 		return NULL;
 
-	return phy_attach_direct(dev, phy, flags, iface) ? NULL : phy;
+	ret = phy_attach_direct(dev, phy, flags, iface);
+
+	/* refcount is held by phy_attach_direct() on success */
+	put_device(&phy->dev);
+
+	return ret ? NULL : phy;
 }
 EXPORT_SYMBOL(of_phy_attach);
 
diff --git a/drivers/of/of_pci_irq.c b/drivers/of/of_pci_irq.c
index 1710d9dc7fc2..2306313c0029 100644
--- a/drivers/of/of_pci_irq.c
+++ b/drivers/of/of_pci_irq.c
@@ -38,8 +38,8 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 	 */
 	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
 	if (rc != 0)
-		return rc;
-	/* No pin, exit */
+		goto err;
+	/* No pin, exit with no error message. */
 	if (pin == 0)
 		return -ENODEV;
 
@@ -53,8 +53,10 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 			ppnode = pci_bus_to_OF_node(pdev->bus);
 
 			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
+			if (ppnode == NULL) {
+				rc = -EINVAL;
+				goto err;
+			}
 		} else {
 			/* We found a P2P bridge, check if it has a node */
 			ppnode = pci_device_to_OF_node(ppdev);
@@ -86,7 +88,13 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 	out_irq->args[0] = pin;
 	laddr[0] = cpu_to_be32((pdev->bus->number << 16) | (pdev->devfn << 8));
 	laddr[1] = laddr[2] = cpu_to_be32(0);
-	return of_irq_parse_raw(laddr, out_irq);
+	rc = of_irq_parse_raw(laddr, out_irq);
+	if (rc)
+		goto err;
+	return 0;
+err:
+	dev_err(&pdev->dev, "of_irq_parse_pci() failed with rc=%d\n", rc);
+	return rc;
 }
 EXPORT_SYMBOL_GPL(of_irq_parse_pci);
 
@@ -105,10 +113,8 @@ int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin)
 	int ret;
 
 	ret = of_irq_parse_pci(dev, &oirq);
-	if (ret) {
-		dev_err(&dev->dev, "of_irq_parse_pci() failed with rc=%d\n", ret);
+	if (ret)
 		return 0; /* Proper return code 0 == NO_IRQ */
-	}
 
 	return irq_create_of_mapping(&oirq);
 }
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index baec33c4e698..a0580afe1713 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -560,6 +560,9 @@ dino_fixup_bus(struct pci_bus *bus)
 	} else if (bus->parent) {
 		int i;
 
+		pci_read_bridge_bases(bus);
+
+
 		for(i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) {
 			if((bus->self->resource[i].flags & 
 			    (IORESOURCE_IO | IORESOURCE_MEM)) == 0)
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index 7b9e89ba0465..a32c1f6c252c 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -693,6 +693,7 @@ lba_fixup_bus(struct pci_bus *bus)
 	if (bus->parent) {
 		int i;
 		/* PCI-PCI Bridge */
+		pci_read_bridge_bases(bus);
 		for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++)
 			pci_claim_bridge_resource(bus->self, i);
 	} else {
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 769f7e35f1a2..59ac36fe7c42 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -442,7 +442,8 @@ static const struct pci_vpd_ops pci_vpd_pci22_ops = {
 static ssize_t pci_vpd_f0_read(struct pci_dev *dev, loff_t pos, size_t count,
 			       void *arg)
 {
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
+	struct pci_dev *tdev = pci_get_slot(dev->bus,
+					    PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
 	ssize_t ret;
 
 	if (!tdev)
@@ -456,7 +457,8 @@ static ssize_t pci_vpd_f0_read(struct pci_dev *dev, loff_t pos, size_t count,
 static ssize_t pci_vpd_f0_write(struct pci_dev *dev, loff_t pos, size_t count,
 				const void *arg)
 {
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
+	struct pci_dev *tdev = pci_get_slot(dev->bus,
+					    PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
 	ssize_t ret;
 
 	if (!tdev)
@@ -473,22 +475,6 @@ static const struct pci_vpd_ops pci_vpd_f0_ops = {
 	.release = pci_vpd_pci22_release,
 };
 
-static int pci_vpd_f0_dev_check(struct pci_dev *dev)
-{
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
-	int ret = 0;
-
-	if (!tdev)
-		return -ENODEV;
-	if (!tdev->vpd || !tdev->multifunction ||
-	    dev->class != tdev->class || dev->vendor != tdev->vendor ||
-	    dev->device != tdev->device)
-		ret = -ENODEV;
-
-	pci_dev_put(tdev);
-	return ret;
-}
-
 int pci_vpd_pci22_init(struct pci_dev *dev)
 {
 	struct pci_vpd_pci22 *vpd;
@@ -497,12 +483,7 @@ int pci_vpd_pci22_init(struct pci_dev *dev)
 	cap = pci_find_capability(dev, PCI_CAP_ID_VPD);
 	if (!cap)
 		return -ENODEV;
-	if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0) {
-		int ret = pci_vpd_f0_dev_check(dev);
 
-		if (ret)
-			return ret;
-	}
 	vpd = kzalloc(sizeof(*vpd), GFP_ATOMIC);
 	if (!vpd)
 		return -ENOMEM;
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 6fbd3f2b5992..d3346d23963b 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -256,6 +256,8 @@ bool pci_bus_clip_resource(struct pci_dev *dev, int idx)
 
 		res->start = start;
 		res->end = end;
+		res->flags &= ~IORESOURCE_UNSET;
+		orig_res.flags &= ~IORESOURCE_UNSET;
 		dev_printk(KERN_DEBUG, &dev->dev, "%pR clipped to %pR\n",
 				 &orig_res, res);
 
diff --git a/drivers/pci/host/pci-rcar-gen2.c b/drivers/pci/host/pci-rcar-gen2.c
index 367e28fa7564..c4f64bfee551 100644
--- a/drivers/pci/host/pci-rcar-gen2.c
+++ b/drivers/pci/host/pci-rcar-gen2.c
@@ -362,6 +362,7 @@ static int rcar_pci_probe(struct platform_device *pdev)
 static struct of_device_id rcar_pci_of_match[] = {
 	{ .compatible = "renesas,pci-r8a7790", },
 	{ .compatible = "renesas,pci-r8a7791", },
+	{ .compatible = "renesas,pci-r8a7794", },
 	{ },
 };
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 0b2be174d981..8361d27e5eca 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -676,15 +676,20 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus)
 static void pci_set_bus_msi_domain(struct pci_bus *bus)
 {
 	struct irq_domain *d;
+	struct pci_bus *b;
 
 	/*
-	 * Either bus is the root, and we must obtain it from the
-	 * firmware, or we inherit it from the bridge device.
+	 * The bus can be a root bus, a subordinate bus, or a virtual bus
+	 * created by an SR-IOV device.  Walk up to the first bridge device
+	 * found or derive the domain from the host bridge.
 	 */
-	if (pci_is_root_bus(bus))
-		d = pci_host_bridge_msi_domain(bus);
-	else
-		d = dev_get_msi_domain(&bus->self->dev);
+	for (b = bus, d = NULL; !d && !pci_is_root_bus(b); b = b->parent) {
+		if (b->self)
+			d = dev_get_msi_domain(&b->self->dev);
+	}
+
+	if (!d)
+		d = pci_host_bridge_msi_domain(b);
 
 	dev_set_msi_domain(&bus->dev, d);
 }
@@ -855,9 +860,6 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 			child->bridge_ctl = bctl;
 		}
 
-		/* Read and initialize bridge resources */
-		pci_read_bridge_bases(child);
-
 		cmax = pci_scan_child_bus(child);
 		if (cmax > subordinate)
 			dev_warn(&dev->dev, "bridge has subordinate %02x but max busn %02x\n",
@@ -918,9 +920,6 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 
 		if (!is_cardbus) {
 			child->bridge_ctl = bctl;
-
-			/* Read and initialize bridge resources */
-			pci_read_bridge_bases(child);
 			max = pci_scan_child_bus(child);
 		} else {
 			/*
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 6a30252cd79f..b03373fd05ca 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1907,11 +1907,27 @@ static void quirk_netmos(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_NETMOS, PCI_ANY_ID,
 			 PCI_CLASS_COMMUNICATION_SERIAL, 8, quirk_netmos);
 
+/*
+ * Quirk non-zero PCI functions to route VPD access through function 0 for
+ * devices that share VPD resources between functions.  The functions are
+ * expected to be identical devices.
+ */
 static void quirk_f0_vpd_link(struct pci_dev *dev)
 {
-	if (!dev->multifunction || !PCI_FUNC(dev->devfn))
+	struct pci_dev *f0;
+
+	if (!PCI_FUNC(dev->devfn))
 		return;
-	dev->dev_flags |= PCI_DEV_FLAGS_VPD_REF_F0;
+
+	f0 = pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+	if (!f0)
+		return;
+
+	if (f0->vpd && dev->class == f0->class &&
+	    dev->vendor == f0->vendor && dev->device == f0->device)
+		dev->dev_flags |= PCI_DEV_FLAGS_VPD_REF_F0;
+
+	pci_dev_put(f0);
 }
 DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
 			      PCI_CLASS_NETWORK_ETHERNET, 8, quirk_f0_vpd_link);
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 738adfa5332b..52ea605f8130 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -318,6 +318,7 @@ static const struct of_device_id of_anatop_regulator_match_tbl[] = {
 	{ .compatible = "fsl,anatop-regulator", },
 	{ /* end */ }
 };
+MODULE_DEVICE_TABLE(of, of_anatop_regulator_match_tbl);
 
 static struct platform_driver anatop_regulator_driver = {
 	.driver = {
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 7a85ac9e32c5..7849187d91ae 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1394,15 +1394,15 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		return 0;
 
 	r = regulator_dev_lookup(dev, rdev->supply_name, &ret);
-	if (ret == -ENODEV) {
-		/*
-		 * No supply was specified for this regulator and
-		 * there will never be one.
-		 */
-		return 0;
-	}
-
 	if (!r) {
+		if (ret == -ENODEV) {
+			/*
+			 * No supply was specified for this regulator and
+			 * there will never be one.
+			 */
+			return 0;
+		}
+
 		if (have_full_constraints()) {
 			r = dummy_regulator_rdev;
 		} else {
@@ -1422,11 +1422,10 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		return ret;
 
 	/* Cascade always-on state to supply */
-	if (_regulator_is_enabled(rdev)) {
+	if (_regulator_is_enabled(rdev) && rdev->supply) {
 		ret = regulator_enable(rdev->supply);
 		if (ret < 0) {
-			if (rdev->supply)
-				_regulator_put(rdev->supply);
+			_regulator_put(rdev->supply);
 			return ret;
 		}
 	}
diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 464018de7e97..7bba8b747f30 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -394,6 +394,7 @@ static const struct of_device_id regulator_gpio_of_match[] = {
 	{ .compatible = "regulator-gpio", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, regulator_gpio_of_match);
 #endif
 
 static struct platform_driver gpio_regulator_driver = {
diff --git a/drivers/regulator/pbias-regulator.c b/drivers/regulator/pbias-regulator.c
index 4fa7bcaf454e..f9d74d63be7c 100644
--- a/drivers/regulator/pbias-regulator.c
+++ b/drivers/regulator/pbias-regulator.c
@@ -45,6 +45,10 @@ struct pbias_regulator_data {
 	int voltage;
 };
 
+struct pbias_of_data {
+	unsigned int offset;
+};
+
 static const unsigned int pbias_volt_table[] = {
 	1800000,
 	3000000
@@ -102,8 +106,35 @@ static struct of_regulator_match pbias_matches[] = {
 };
 #define PBIAS_NUM_REGS	ARRAY_SIZE(pbias_matches)
 
+/* Offset from SCM general area (and syscon) base */
+
+static const struct pbias_of_data pbias_of_data_omap2 = {
+	.offset = 0x230,
+};
+
+static const struct pbias_of_data pbias_of_data_omap3 = {
+	.offset = 0x2b0,
+};
+
+static const struct pbias_of_data pbias_of_data_omap4 = {
+	.offset = 0x60,
+};
+
+static const struct pbias_of_data pbias_of_data_omap5 = {
+	.offset = 0x60,
+};
+
+static const struct pbias_of_data pbias_of_data_dra7 = {
+	.offset = 0xe00,
+};
+
 static const struct of_device_id pbias_of_match[] = {
 	{ .compatible = "ti,pbias-omap", },
+	{ .compatible = "ti,pbias-omap2", .data = &pbias_of_data_omap2, },
+	{ .compatible = "ti,pbias-omap3", .data = &pbias_of_data_omap3, },
+	{ .compatible = "ti,pbias-omap4", .data = &pbias_of_data_omap4, },
+	{ .compatible = "ti,pbias-omap5", .data = &pbias_of_data_omap5, },
+	{ .compatible = "ti,pbias-dra7", .data = &pbias_of_data_dra7, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, pbias_of_match);
@@ -118,6 +149,9 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 	const struct pbias_reg_info *info;
 	int ret = 0;
 	int count, idx, data_idx = 0;
+	const struct of_device_id *match;
+	const struct pbias_of_data *data;
+	unsigned int offset;
 
 	count = of_regulator_match(&pdev->dev, np, pbias_matches,
 						PBIAS_NUM_REGS);
@@ -133,6 +167,20 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 	if (IS_ERR(syscon))
 		return PTR_ERR(syscon);
 
+	match = of_match_device(of_match_ptr(pbias_of_match), &pdev->dev);
+	if (match && match->data) {
+		data = match->data;
+		offset = data->offset;
+	} else {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (!res)
+			return -EINVAL;
+
+		offset = res->start;
+		dev_WARN(&pdev->dev,
+			 "using legacy dt data for pbias offset\n");
+	}
+
 	cfg.regmap = syscon;
 	cfg.dev = &pdev->dev;
 
@@ -145,10 +193,6 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 		if (!info)
 			return -ENODEV;
 
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		if (!res)
-			return -EINVAL;
-
 		drvdata[data_idx].syscon = syscon;
 		drvdata[data_idx].info = info;
 		drvdata[data_idx].desc.name = info->name;
@@ -158,9 +202,9 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 		drvdata[data_idx].desc.volt_table = pbias_volt_table;
 		drvdata[data_idx].desc.n_voltages = 2;
 		drvdata[data_idx].desc.enable_time = info->enable_time;
-		drvdata[data_idx].desc.vsel_reg = res->start;
+		drvdata[data_idx].desc.vsel_reg = offset;
 		drvdata[data_idx].desc.vsel_mask = info->vmode;
-		drvdata[data_idx].desc.enable_reg = res->start;
+		drvdata[data_idx].desc.enable_reg = offset;
 		drvdata[data_idx].desc.enable_mask = info->enable_mask;
 		drvdata[data_idx].desc.enable_val = info->enable;
 		drvdata[data_idx].desc.disable_val = info->disable_val;
diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c
index 7f97223f95c5..a02c1b961039 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -73,7 +73,7 @@ static const struct regulator_linear_range dcdc4_ranges[] = {
 };
 
 static struct tps_info tps65218_pmic_regs[] = {
-	TPS65218_INFO(DCDC1, "DCDC1", 850000, 167500),
+	TPS65218_INFO(DCDC1, "DCDC1", 850000, 1675000),
 	TPS65218_INFO(DCDC2, "DCDC2", 850000, 1675000),
 	TPS65218_INFO(DCDC3, "DCDC3", 900000, 3400000),
 	TPS65218_INFO(DCDC4, "DCDC4", 1175000, 3400000),
diff --git a/drivers/regulator/vexpress.c b/drivers/regulator/vexpress.c
index bed9d3ee4198..c810cbbd463f 100644
--- a/drivers/regulator/vexpress.c
+++ b/drivers/regulator/vexpress.c
@@ -103,6 +103,7 @@ static const struct of_device_id vexpress_regulator_of_match[] = {
 	{ .compatible = "arm,vexpress-volt", },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, vexpress_regulator_of_match);
 
 static struct platform_driver vexpress_regulator_driver = {
 	.probe = vexpress_regulator_probe,
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index d3d1891cda3c..25abd4eb7d10 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -35,20 +35,11 @@ static struct pm_clk_notifier_block platform_bus_notifier = {
 static int __init sh_pm_runtime_init(void)
 {
 	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE_MULTI)) {
-		if (!of_machine_is_compatible("renesas,emev2") &&
-		    !of_machine_is_compatible("renesas,r7s72100") &&
-#ifndef CONFIG_PM_GENERIC_DOMAINS_OF
-		    !of_machine_is_compatible("renesas,r8a73a4") &&
-		    !of_machine_is_compatible("renesas,r8a7740") &&
-		    !of_machine_is_compatible("renesas,sh73a0") &&
-#endif
-		    !of_machine_is_compatible("renesas,r8a7778") &&
-		    !of_machine_is_compatible("renesas,r8a7779") &&
-		    !of_machine_is_compatible("renesas,r8a7790") &&
-		    !of_machine_is_compatible("renesas,r8a7791") &&
-		    !of_machine_is_compatible("renesas,r8a7792") &&
-		    !of_machine_is_compatible("renesas,r8a7793") &&
-		    !of_machine_is_compatible("renesas,r8a7794"))
+		if (!of_find_compatible_node(NULL, NULL,
+					     "renesas,cpg-mstp-clocks"))
+			return 0;
+		if (IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS_OF) &&
+		    of_find_node_with_property(NULL, "#power-domain-cells"))
 			return 0;
 	}
 
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index bf9ed380bb1c..63318e2afba1 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1720,6 +1720,7 @@ static int atmel_spi_runtime_resume(struct device *dev)
 	return clk_prepare_enable(as->clk);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int atmel_spi_suspend(struct device *dev)
 {
 	struct spi_master *master = dev_get_drvdata(dev);
@@ -1756,6 +1757,7 @@ static int atmel_spi_resume(struct device *dev)
 
 	return ret;
 }
+#endif
 
 static const struct dev_pm_ops atmel_spi_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(atmel_spi_suspend, atmel_spi_resume)
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index e7874a6171ec..3e8eeb23d4e9 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -386,14 +386,14 @@ static bool bcm2835_spi_can_dma(struct spi_master *master,
 	/* otherwise we only allow transfers within the same page
 	 * to avoid wasting time on dma_mapping when it is not practical
 	 */
-	if (((size_t)tfr->tx_buf & PAGE_MASK) + tfr->len > PAGE_SIZE) {
+	if (((size_t)tfr->tx_buf & (PAGE_SIZE - 1)) + tfr->len > PAGE_SIZE) {
 		dev_warn_once(&spi->dev,
 			      "Unaligned spi tx-transfer bridging page\n");
 		return false;
 	}
-	if (((size_t)tfr->rx_buf & PAGE_MASK) + tfr->len > PAGE_SIZE) {
+	if (((size_t)tfr->rx_buf & (PAGE_SIZE - 1)) + tfr->len > PAGE_SIZE) {
 		dev_warn_once(&spi->dev,
-			      "Unaligned spi tx-transfer bridging page\n");
+			      "Unaligned spi rx-transfer bridging page\n");
 		return false;
 	}
 
diff --git a/drivers/spi/spi-meson-spifc.c b/drivers/spi/spi-meson-spifc.c
index 5468fc70dbf8..2465259f6241 100644
--- a/drivers/spi/spi-meson-spifc.c
+++ b/drivers/spi/spi-meson-spifc.c
@@ -444,6 +444,7 @@ static const struct of_device_id meson_spifc_dt_match[] = {
 	{ .compatible = "amlogic,meson6-spifc", },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, meson_spifc_dt_match);
 
 static struct platform_driver meson_spifc_driver = {
 	.probe	= meson_spifc_probe,
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 5f6315c47920..ecb6c58238c4 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -85,7 +85,7 @@ struct mtk_spi {
 	void __iomem *base;
 	u32 state;
 	u32 pad_sel;
-	struct clk *spi_clk, *parent_clk;
+	struct clk *parent_clk, *sel_clk, *spi_clk;
 	struct spi_transfer *cur_transfer;
 	u32 xfer_len;
 	struct scatterlist *tx_sgl, *rx_sgl;
@@ -173,22 +173,6 @@ static void mtk_spi_config(struct mtk_spi *mdata,
 		writel(mdata->pad_sel, mdata->base + SPI_PAD_SEL_REG);
 }
 
-static int mtk_spi_prepare_hardware(struct spi_master *master)
-{
-	struct spi_transfer *trans;
-	struct mtk_spi *mdata = spi_master_get_devdata(master);
-	struct spi_message *msg = master->cur_msg;
-
-	trans = list_first_entry(&msg->transfers, struct spi_transfer,
-				 transfer_list);
-	if (!trans->cs_change) {
-		mdata->state = MTK_SPI_IDLE;
-		mtk_spi_reset(mdata);
-	}
-
-	return 0;
-}
-
 static int mtk_spi_prepare_message(struct spi_master *master,
 				   struct spi_message *msg)
 {
@@ -228,11 +212,15 @@ static void mtk_spi_set_cs(struct spi_device *spi, bool enable)
 	struct mtk_spi *mdata = spi_master_get_devdata(spi->master);
 
 	reg_val = readl(mdata->base + SPI_CMD_REG);
-	if (!enable)
+	if (!enable) {
 		reg_val |= SPI_CMD_PAUSE_EN;
-	else
+		writel(reg_val, mdata->base + SPI_CMD_REG);
+	} else {
 		reg_val &= ~SPI_CMD_PAUSE_EN;
-	writel(reg_val, mdata->base + SPI_CMD_REG);
+		writel(reg_val, mdata->base + SPI_CMD_REG);
+		mdata->state = MTK_SPI_IDLE;
+		mtk_spi_reset(mdata);
+	}
 }
 
 static void mtk_spi_prepare_transfer(struct spi_master *master,
@@ -509,7 +497,6 @@ static int mtk_spi_probe(struct platform_device *pdev)
 	master->mode_bits = SPI_CPOL | SPI_CPHA;
 
 	master->set_cs = mtk_spi_set_cs;
-	master->prepare_transfer_hardware = mtk_spi_prepare_hardware;
 	master->prepare_message = mtk_spi_prepare_message;
 	master->transfer_one = mtk_spi_transfer_one;
 	master->can_dma = mtk_spi_can_dma;
@@ -576,13 +563,6 @@ static int mtk_spi_probe(struct platform_device *pdev)
 		goto err_put_master;
 	}
 
-	mdata->spi_clk = devm_clk_get(&pdev->dev, "spi-clk");
-	if (IS_ERR(mdata->spi_clk)) {
-		ret = PTR_ERR(mdata->spi_clk);
-		dev_err(&pdev->dev, "failed to get spi-clk: %d\n", ret);
-		goto err_put_master;
-	}
-
 	mdata->parent_clk = devm_clk_get(&pdev->dev, "parent-clk");
 	if (IS_ERR(mdata->parent_clk)) {
 		ret = PTR_ERR(mdata->parent_clk);
@@ -590,13 +570,27 @@ static int mtk_spi_probe(struct platform_device *pdev)
 		goto err_put_master;
 	}
 
+	mdata->sel_clk = devm_clk_get(&pdev->dev, "sel-clk");
+	if (IS_ERR(mdata->sel_clk)) {
+		ret = PTR_ERR(mdata->sel_clk);
+		dev_err(&pdev->dev, "failed to get sel-clk: %d\n", ret);
+		goto err_put_master;
+	}
+
+	mdata->spi_clk = devm_clk_get(&pdev->dev, "spi-clk");
+	if (IS_ERR(mdata->spi_clk)) {
+		ret = PTR_ERR(mdata->spi_clk);
+		dev_err(&pdev->dev, "failed to get spi-clk: %d\n", ret);
+		goto err_put_master;
+	}
+
 	ret = clk_prepare_enable(mdata->spi_clk);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to enable spi_clk (%d)\n", ret);
 		goto err_put_master;
 	}
 
-	ret = clk_set_parent(mdata->spi_clk, mdata->parent_clk);
+	ret = clk_set_parent(mdata->sel_clk, mdata->parent_clk);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to clk_set_parent (%d)\n", ret);
 		goto err_disable_clk;
@@ -630,7 +624,6 @@ static int mtk_spi_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 
 	mtk_spi_reset(mdata);
-	clk_disable_unprepare(mdata->spi_clk);
 	spi_master_put(master);
 
 	return 0;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index fdd791977041..a8ef38ebb9c9 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -654,6 +654,10 @@ static irqreturn_t ssp_int(int irq, void *dev_id)
 	if (!(sccr1_reg & SSCR1_TIE))
 		mask &= ~SSSR_TFS;
 
+	/* Ignore RX timeout interrupt if it is disabled */
+	if (!(sccr1_reg & SSCR1_TINTE))
+		mask &= ~SSSR_TINT;
+
 	if (!(status & mask))
 		return IRQ_NONE;
 
diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c
index 2e32ea2f194f..be6155cba9de 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -34,13 +34,13 @@ struct xtfpga_spi {
 static inline void xtfpga_spi_write32(const struct xtfpga_spi *spi,
 				      unsigned addr, u32 val)
 {
-	iowrite32(val, spi->regs + addr);
+	__raw_writel(val, spi->regs + addr);
 }
 
 static inline unsigned int xtfpga_spi_read32(const struct xtfpga_spi *spi,
 					     unsigned addr)
 {
-	return ioread32(spi->regs + addr);
+	return __raw_readl(spi->regs + addr);
 }
 
 static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 3abb3903f2ad..a5f53de813d3 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1610,8 +1610,7 @@ static struct class spi_master_class = {
  *
  * The caller is responsible for assigning the bus number and initializing
  * the master's methods before calling spi_register_master(); and (after errors
- * adding the device) calling spi_master_put() and kfree() to prevent a memory
- * leak.
+ * adding the device) calling spi_master_put() to prevent a memory leak.
  */
 struct spi_master *spi_alloc_master(struct device *dev, unsigned size)
 {
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index fba92a526531..ef008e52f953 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -651,7 +651,8 @@ static int spidev_release(struct inode *inode, struct file *filp)
 		kfree(spidev->rx_buffer);
 		spidev->rx_buffer = NULL;
 
-		spidev->speed_hz = spidev->spi->max_speed_hz;
+		if (spidev->spi)
+			spidev->speed_hz = spidev->spi->max_speed_hz;
 
 		/* ... after we unbound from the underlying device? */
 		spin_lock_irq(&spidev->spi_lock);
diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO
index 20288fc53946..8f3ac37bfe12 100644
--- a/drivers/staging/android/TODO
+++ b/drivers/staging/android/TODO
@@ -5,5 +5,25 @@ TODO:
 	- add proper arch dependencies as needed
 	- audit userspace interfaces to make sure they are sane
 
+
+ion/
+ - Remove ION_IOC_SYNC: Flushing for devices should be purely a kernel internal
+   interface on top of dma-buf. flush_for_device needs to be added to dma-buf
+   first.
+ - Remove ION_IOC_CUSTOM: Atm used for cache flushing for cpu access in some
+   vendor trees. Should be replaced with an ioctl on the dma-buf to expose the
+   begin/end_cpu_access hooks to userspace.
+ - Clarify the tricks ion plays with explicitly managing coherency behind the
+   dma api's back (this is absolutely needed for high-perf gpu drivers): Add an
+   explicit coherency management mode to flush_for_device to be used by drivers
+   which want to manage caches themselves and which indicates whether cpu caches
+   need flushing.
+ - With those removed there's probably no use for ION_IOC_IMPORT anymore either
+   since ion would just be the central allocator for shared buffers.
+ - Add dt-binding to expose cma regions as ion heaps, with the rule that any
+   such cma regions must already be used by some device for dma. I.e. ion only
+   exposes existing cma regions and doesn't reserve unecessarily memory when
+   booting a system which doesn't use ion.
+
 Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
 Arve Hjønnevåg <arve@android.com> and Riley Andrews <riandrews@android.com>
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 217aa537c4eb..6e8d8392ca38 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1179,13 +1179,13 @@ struct ion_handle *ion_import_dma_buf(struct ion_client *client, int fd)
 		mutex_unlock(&client->lock);
 		goto end;
 	}
-	mutex_unlock(&client->lock);
 
 	handle = ion_handle_create(client, buffer);
-	if (IS_ERR(handle))
+	if (IS_ERR(handle)) {
+		mutex_unlock(&client->lock);
 		goto end;
+	}
 
-	mutex_lock(&client->lock);
 	ret = ion_handle_add(client, handle);
 	mutex_unlock(&client->lock);
 	if (ret) {
diff --git a/drivers/staging/fbtft/fb_uc1611.c b/drivers/staging/fbtft/fb_uc1611.c
index 32f3a9d921d6..5cafa50d1fac 100644
--- a/drivers/staging/fbtft/fb_uc1611.c
+++ b/drivers/staging/fbtft/fb_uc1611.c
@@ -76,7 +76,7 @@ static int init_display(struct fbtft_par *par)
 
 	/* Set CS active high */
 	par->spi->mode |= SPI_CS_HIGH;
-	ret = par->spi->master->setup(par->spi);
+	ret = spi_setup(par->spi);
 	if (ret) {
 		dev_err(par->info->device, "Could not set SPI_CS_HIGH\n");
 		return ret;
diff --git a/drivers/staging/fbtft/fb_watterott.c b/drivers/staging/fbtft/fb_watterott.c
index 88fb2c0132d5..8eae6ef25846 100644
--- a/drivers/staging/fbtft/fb_watterott.c
+++ b/drivers/staging/fbtft/fb_watterott.c
@@ -169,7 +169,7 @@ static int init_display(struct fbtft_par *par)
 	/* enable SPI interface by having CS and MOSI low during reset */
 	save_mode = par->spi->mode;
 	par->spi->mode |= SPI_CS_HIGH;
-	ret = par->spi->master->setup(par->spi); /* set CS inactive low */
+	ret = spi_setup(par->spi); /* set CS inactive low */
 	if (ret) {
 		dev_err(par->info->device, "Could not set SPI_CS_HIGH\n");
 		return ret;
@@ -180,7 +180,7 @@ static int init_display(struct fbtft_par *par)
 	par->fbtftops.reset(par);
 	mdelay(1000);
 	par->spi->mode = save_mode;
-	ret = par->spi->master->setup(par->spi);
+	ret = spi_setup(par->spi);
 	if (ret) {
 		dev_err(par->info->device, "Could not restore SPI mode\n");
 		return ret;
diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c
index 23392eb6799e..7f5fa3d1cab0 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -1436,15 +1436,11 @@ int fbtft_probe_common(struct fbtft_display *display,
 
 	/* 9-bit SPI setup */
 	if (par->spi && display->buswidth == 9) {
-		par->spi->bits_per_word = 9;
-		ret = par->spi->master->setup(par->spi);
-		if (ret) {
+		if (par->spi->master->bits_per_word_mask & SPI_BPW_MASK(9)) {
+			par->spi->bits_per_word = 9;
+		} else {
 			dev_warn(&par->spi->dev,
 				"9-bit SPI not available, emulating using 8-bit.\n");
-			par->spi->bits_per_word = 8;
-			ret = par->spi->master->setup(par->spi);
-			if (ret)
-				goto out_release;
 			/* allocate buffer with room for dc bits */
 			par->extra = devm_kzalloc(par->info->device,
 				par->txbuf.len + (par->txbuf.len / 8) + 8,
diff --git a/drivers/staging/fbtft/flexfb.c b/drivers/staging/fbtft/flexfb.c
index c763efc5de7d..3f380a0086c3 100644
--- a/drivers/staging/fbtft/flexfb.c
+++ b/drivers/staging/fbtft/flexfb.c
@@ -463,15 +463,12 @@ static int flexfb_probe_common(struct spi_device *sdev,
 			}
 			par->fbtftops.write_register = fbtft_write_reg8_bus9;
 			par->fbtftops.write_vmem = fbtft_write_vmem16_bus9;
-			sdev->bits_per_word = 9;
-			ret = sdev->master->setup(sdev);
-			if (ret) {
+			if (par->spi->master->bits_per_word_mask
+			    & SPI_BPW_MASK(9)) {
+				par->spi->bits_per_word = 9;
+			} else {
 				dev_warn(dev,
 					"9-bit SPI not available, emulating using 8-bit.\n");
-				sdev->bits_per_word = 8;
-				ret = sdev->master->setup(sdev);
-				if (ret)
-					goto out_release;
 				/* allocate buffer with room for dc bits */
 				par->extra = devm_kzalloc(par->info->device,
 						par->txbuf.len + (par->txbuf.len / 8) + 8,
diff --git a/drivers/staging/lustre/README.txt b/drivers/staging/lustre/README.txt
index cf0ca50ff83b..0676243eea9e 100644
--- a/drivers/staging/lustre/README.txt
+++ b/drivers/staging/lustre/README.txt
@@ -14,10 +14,8 @@ Unlike shared disk storage cluster filesystems (e.g. OCFS2, GFS, GPFS),
 Lustre has independent Metadata and Data servers that clients can access
 in parallel to maximize performance.
 
-In order to use Lustre client you will need to download lustre client
-tools from
-https://downloads.hpdd.intel.com/public/lustre/latest-feature-release/
-the package name is lustre-client.
+In order to use Lustre client you will need to download the "lustre-client"
+package that contains the userspace tools from http://lustre.org/download/
 
 You will need to install and configure your Lustre servers separately.
 
@@ -76,12 +74,10 @@ Mount Options
 
 More Information
 ================
-You can get more information at
-OpenSFS website: http://lustre.opensfs.org/about/
-Intel HPDD wiki: https://wiki.hpdd.intel.com
+You can get more information at the Lustre website: http://wiki.lustre.org/
 
-Out of tree Lustre client and server code is available at:
-http://git.whamcloud.com/fs/lustre-release.git
+Source for the userspace tools and out-of-tree client and server code
+is available at: http://git.hpdd.intel.com/fs/lustre-release.git
 
 Latest binary packages:
-http://lustre.opensfs.org/download-lustre/
+http://lustre.org/download/
diff --git a/drivers/staging/most/Kconfig b/drivers/staging/most/Kconfig
index d50de03de7b9..0b9b9b539f70 100644
--- a/drivers/staging/most/Kconfig
+++ b/drivers/staging/most/Kconfig
@@ -1,5 +1,6 @@
 menuconfig MOST
         tristate "MOST driver"
+	depends on HAS_DMA
         select MOSTCORE
         default n
         ---help---
diff --git a/drivers/staging/most/hdm-dim2/Kconfig b/drivers/staging/most/hdm-dim2/Kconfig
index 1d4ad1d67758..fc548769479b 100644
--- a/drivers/staging/most/hdm-dim2/Kconfig
+++ b/drivers/staging/most/hdm-dim2/Kconfig
@@ -5,6 +5,7 @@
 config HDM_DIM2
 	tristate "DIM2 HDM"
 	depends on AIM_NETWORK
+	depends on HAS_IOMEM
 
 	---help---
 	  Say Y here if you want to connect via MediaLB to network transceiver.
diff --git a/drivers/staging/most/hdm-usb/Kconfig b/drivers/staging/most/hdm-usb/Kconfig
index a482c3fdf34b..ec1546312ee6 100644
--- a/drivers/staging/most/hdm-usb/Kconfig
+++ b/drivers/staging/most/hdm-usb/Kconfig
@@ -4,7 +4,7 @@
 
 config HDM_USB
 	tristate "USB HDM"
-	depends on USB
+	depends on USB && NET
 	select AIM_NETWORK
 	---help---
 	  Say Y here if you want to connect via USB to network tranceiver.
diff --git a/drivers/staging/most/mostcore/Kconfig b/drivers/staging/most/mostcore/Kconfig
index 38abf1b21b66..47172546d728 100644
--- a/drivers/staging/most/mostcore/Kconfig
+++ b/drivers/staging/most/mostcore/Kconfig
@@ -4,6 +4,7 @@
 
 config MOSTCORE
 	tristate "MOST Core"
+	depends on HAS_DMA
 
 	---help---
 	  Say Y here if you want to enable MOST support.
diff --git a/drivers/staging/unisys/visorbus/Makefile b/drivers/staging/unisys/visorbus/Makefile
index fa27ee5f336c..fc790e7592fc 100644
--- a/drivers/staging/unisys/visorbus/Makefile
+++ b/drivers/staging/unisys/visorbus/Makefile
@@ -10,4 +10,3 @@ visorbus-y += visorchipset.o
 visorbus-y += periodic_work.o
 
 ccflags-y += -Idrivers/staging/unisys/include
-ccflags-y += -Idrivers/staging/unisys/visorutil
diff --git a/drivers/staging/unisys/visorbus/visorbus_main.c b/drivers/staging/unisys/visorbus/visorbus_main.c
index 2309f5f2b238..a272b48bab28 100644
--- a/drivers/staging/unisys/visorbus/visorbus_main.c
+++ b/drivers/staging/unisys/visorbus/visorbus_main.c
@@ -37,6 +37,8 @@ static int visorbus_debugref;
 #define POLLJIFFIES_TESTWORK         100
 #define POLLJIFFIES_NORMALCHANNEL     10
 
+static int busreg_rc = -ENODEV; /* stores the result from bus registration */
+
 static int visorbus_uevent(struct device *xdev, struct kobj_uevent_env *env);
 static int visorbus_match(struct device *xdev, struct device_driver *xdrv);
 static void fix_vbus_dev_info(struct visor_device *visordev);
@@ -863,6 +865,9 @@ int visorbus_register_visor_driver(struct visor_driver *drv)
 {
 	int rc = 0;
 
+	if (busreg_rc < 0)
+		return -ENODEV; /*can't register on a nonexistent bus*/
+
 	drv->driver.name = drv->name;
 	drv->driver.bus = &visorbus_type;
 	drv->driver.probe = visordriver_probe_device;
@@ -885,6 +890,8 @@ int visorbus_register_visor_driver(struct visor_driver *drv)
 	if (rc < 0)
 		return rc;
 	rc = register_driver_attributes(drv);
+	if (rc < 0)
+		driver_unregister(&drv->driver);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(visorbus_register_visor_driver);
@@ -1260,10 +1267,8 @@ remove_bus_instance(struct visor_device *dev)
 static int
 create_bus_type(void)
 {
-	int rc = 0;
-
-	rc = bus_register(&visorbus_type);
-	return rc;
+	busreg_rc = bus_register(&visorbus_type);
+	return busreg_rc;
 }
 
 /** Remove the one-and-only one instance of the visor bus type (visorbus_type).
diff --git a/drivers/staging/unisys/visornic/visornic_main.c b/drivers/staging/unisys/visornic/visornic_main.c
index 8c9da7ea7845..9d3c1e282062 100644
--- a/drivers/staging/unisys/visornic/visornic_main.c
+++ b/drivers/staging/unisys/visornic/visornic_main.c
@@ -1189,16 +1189,16 @@ visornic_rx(struct uiscmdrsp *cmdrsp)
 	spin_lock_irqsave(&devdata->priv_lock, flags);
 	atomic_dec(&devdata->num_rcvbuf_in_iovm);
 
-	/* update rcv stats - call it with priv_lock held */
-	devdata->net_stats.rx_packets++;
-	devdata->net_stats.rx_bytes = skb->len;
-
 	/* set length to how much was ACTUALLY received -
 	 * NOTE: rcv_done_len includes actual length of data rcvd
 	 * including ethhdr
 	 */
 	skb->len = cmdrsp->net.rcv.rcv_done_len;
 
+	/* update rcv stats - call it with priv_lock held */
+	devdata->net_stats.rx_packets++;
+	devdata->net_stats.rx_bytes += skb->len;
+
 	/* test enabled while holding lock */
 	if (!(devdata->enabled && devdata->enab_dis_acked)) {
 		/* don't process it unless we're in enable mode and until
@@ -1924,13 +1924,16 @@ static int visornic_probe(struct visor_device *dev)
 			"%s debugfs_create_dir %s failed\n",
 			__func__, netdev->name);
 		err = -ENOMEM;
-		goto cleanup_xmit_cmdrsp;
+		goto cleanup_register_netdev;
 	}
 
 	dev_info(&dev->device, "%s success netdev=%s\n",
 		 __func__, netdev->name);
 	return 0;
 
+cleanup_register_netdev:
+	unregister_netdev(netdev);
+
 cleanup_napi_add:
 	del_timer_sync(&devdata->irq_poll_timer);
 	netif_napi_del(&devdata->napi);
@@ -2128,8 +2131,9 @@ static int visornic_init(void)
 	if (!dev_num_pool)
 		goto cleanup_workqueue;
 
-	visorbus_register_visor_driver(&visornic_driver);
-	return 0;
+	err = visorbus_register_visor_driver(&visornic_driver);
+	if (!err)
+		return 0;
 
 cleanup_workqueue:
 	if (visornic_timeout_reset_workqueue) {
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index e8a52f7d6204..51d1734d5390 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -407,6 +407,7 @@ int iscsi_create_default_params(struct iscsi_param_list **param_list_ptr)
 			TYPERANGE_UTF8, USE_INITIAL_ONLY);
 	if (!param)
 		goto out;
+
 	/*
 	 * Extra parameters for ISER from RFC-5046
 	 */
@@ -496,9 +497,9 @@ int iscsi_set_keys_to_negotiate(
 		} else if (!strcmp(param->name, SESSIONTYPE)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, IFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, IFMARKINT)) {
 			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKINT)) {
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index dcc424ac35d4..88ea4e4f124b 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -62,22 +62,13 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	struct se_session *se_sess = se_cmd->se_sess;
 	struct se_node_acl *nacl = se_sess->se_node_acl;
 	struct se_dev_entry *deve;
+	sense_reason_t ret = TCM_NO_SENSE;
 
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, unpacked_lun);
 	if (deve) {
 		atomic_long_inc(&deve->total_cmds);
 
-		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
-		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
-			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
-				" Access for 0x%08llx\n",
-				se_cmd->se_tfo->get_fabric_name(),
-				unpacked_lun);
-			rcu_read_unlock();
-			return TCM_WRITE_PROTECTED;
-		}
-
 		if (se_cmd->data_direction == DMA_TO_DEVICE)
 			atomic_long_add(se_cmd->data_length,
 					&deve->write_bytes);
@@ -93,6 +84,17 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
+
+		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
+		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
+			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
+				" Access for 0x%08llx\n",
+				se_cmd->se_tfo->get_fabric_name(),
+				unpacked_lun);
+			rcu_read_unlock();
+			ret = TCM_WRITE_PROTECTED;
+			goto ref_dev;
+		}
 	}
 	rcu_read_unlock();
 
@@ -109,12 +111,6 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 				unpacked_lun);
 			return TCM_NON_EXISTENT_LUN;
 		}
-		/*
-		 * Force WRITE PROTECT for virtual LUN 0
-		 */
-		if ((se_cmd->data_direction != DMA_FROM_DEVICE) &&
-		    (se_cmd->data_direction != DMA_NONE))
-			return TCM_WRITE_PROTECTED;
 
 		se_lun = se_sess->se_tpg->tpg_virt_lun0;
 		se_cmd->se_lun = se_sess->se_tpg->tpg_virt_lun0;
@@ -123,6 +119,15 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
+
+		/*
+		 * Force WRITE PROTECT for virtual LUN 0
+		 */
+		if ((se_cmd->data_direction != DMA_FROM_DEVICE) &&
+		    (se_cmd->data_direction != DMA_NONE)) {
+			ret = TCM_WRITE_PROTECTED;
+			goto ref_dev;
+		}
 	}
 	/*
 	 * RCU reference protected by percpu se_lun->lun_ref taken above that
@@ -130,6 +135,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	 * pointer can be kfree_rcu() by the final se_lun->lun_group put via
 	 * target_core_fabric_configfs.c:target_fabric_port_release
 	 */
+ref_dev:
 	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 	atomic_long_inc(&se_cmd->se_dev->num_cmds);
 
@@ -140,7 +146,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 		atomic_long_add(se_cmd->data_length,
 				&se_cmd->se_dev->read_bytes);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(transport_lookup_cmd_lun);
 
@@ -427,8 +433,6 @@ void core_disable_device_list_for_node(
 
 	hlist_del_rcu(&orig->link);
 	clear_bit(DEF_PR_REG_ACTIVE, &orig->deve_flags);
-	rcu_assign_pointer(orig->se_lun, NULL);
-	rcu_assign_pointer(orig->se_lun_acl, NULL);
 	orig->lun_flags = 0;
 	orig->creation_time = 0;
 	orig->attach_count--;
@@ -439,6 +443,9 @@ void core_disable_device_list_for_node(
 	kref_put(&orig->pr_kref, target_pr_kref_release);
 	wait_for_completion(&orig->pr_comp);
 
+	rcu_assign_pointer(orig->se_lun, NULL);
+	rcu_assign_pointer(orig->se_lun_acl, NULL);
+
 	kfree_rcu(orig, rcu_head);
 
 	core_scsi3_free_pr_reg_from_nacl(dev, nacl);
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index 9522960c7fdd..22390e0e046c 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -187,5 +187,5 @@ core_delete_hba(struct se_hba *hba)
 
 bool target_sense_desc_format(struct se_device *dev)
 {
-	return dev->transport->get_blocks(dev) > U32_MAX;
+	return (dev) ? dev->transport->get_blocks(dev) > U32_MAX : false;
 }
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 5a9982f5d5d6..0f19e11acac2 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -105,6 +105,8 @@ static int iblock_configure_device(struct se_device *dev)
 	mode = FMODE_READ|FMODE_EXCL;
 	if (!ib_dev->ibd_readonly)
 		mode |= FMODE_WRITE;
+	else
+		dev->dev_flags |= DF_READ_ONLY;
 
 	bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev);
 	if (IS_ERR(bd)) {
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 5ab7100de17e..e7933115087a 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -618,7 +618,7 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
 	struct se_lun *lun,
-	struct se_dev_entry *deve,
+	struct se_dev_entry *dest_deve,
 	u64 mapped_lun,
 	unsigned char *isid,
 	u64 sa_res_key,
@@ -640,7 +640,29 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	INIT_LIST_HEAD(&pr_reg->pr_reg_atp_mem_list);
 	atomic_set(&pr_reg->pr_res_holders, 0);
 	pr_reg->pr_reg_nacl = nacl;
-	pr_reg->pr_reg_deve = deve;
+	/*
+	 * For destination registrations for ALL_TG_PT=1 and SPEC_I_PT=1,
+	 * the se_dev_entry->pr_ref will have been already obtained by
+	 * core_get_se_deve_from_rtpi() or __core_scsi3_alloc_registration().
+	 *
+	 * Otherwise, locate se_dev_entry now and obtain a reference until
+	 * registration completes in __core_scsi3_add_registration().
+	 */
+	if (dest_deve) {
+		pr_reg->pr_reg_deve = dest_deve;
+	} else {
+		rcu_read_lock();
+		pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+		if (!pr_reg->pr_reg_deve) {
+			rcu_read_unlock();
+			pr_err("Unable to locate PR deve %s mapped_lun: %llu\n",
+				nacl->initiatorname, mapped_lun);
+			kmem_cache_free(t10_pr_reg_cache, pr_reg);
+			return NULL;
+		}
+		kref_get(&pr_reg->pr_reg_deve->pr_kref);
+		rcu_read_unlock();
+	}
 	pr_reg->pr_res_mapped_lun = mapped_lun;
 	pr_reg->pr_aptpl_target_lun = lun->unpacked_lun;
 	pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
@@ -936,17 +958,29 @@ static int __core_scsi3_check_aptpl_registration(
 		    !(strcmp(pr_reg->pr_tport, t_port)) &&
 		     (pr_reg->pr_reg_tpgt == tpgt) &&
 		     (pr_reg->pr_aptpl_target_lun == target_lun)) {
+			/*
+			 * Obtain the ->pr_reg_deve pointer + reference, that
+			 * is released by __core_scsi3_add_registration() below.
+			 */
+			rcu_read_lock();
+			pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+			if (!pr_reg->pr_reg_deve) {
+				pr_err("Unable to locate PR APTPL %s mapped_lun:"
+					" %llu\n", nacl->initiatorname, mapped_lun);
+				rcu_read_unlock();
+				continue;
+			}
+			kref_get(&pr_reg->pr_reg_deve->pr_kref);
+			rcu_read_unlock();
 
 			pr_reg->pr_reg_nacl = nacl;
 			pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
-
 			list_del(&pr_reg->pr_reg_aptpl_list);
 			spin_unlock(&pr_tmpl->aptpl_reg_lock);
 			/*
 			 * At this point all of the pointers in *pr_reg will
 			 * be setup, so go ahead and add the registration.
 			 */
-
 			__core_scsi3_add_registration(dev, nacl, pr_reg, 0, 0);
 			/*
 			 * If this registration is the reservation holder,
@@ -1044,18 +1078,11 @@ static void __core_scsi3_add_registration(
 
 	__core_scsi3_dump_registration(tfo, dev, nacl, pr_reg, register_type);
 	spin_unlock(&pr_tmpl->registration_lock);
-
-	rcu_read_lock();
-	deve = pr_reg->pr_reg_deve;
-	if (deve)
-		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
-	rcu_read_unlock();
-
 	/*
 	 * Skip extra processing for ALL_TG_PT=0 or REGISTER_AND_MOVE.
 	 */
 	if (!pr_reg->pr_reg_all_tg_pt || register_move)
-		return;
+		goto out;
 	/*
 	 * Walk pr_reg->pr_reg_atp_list and add registrations for ALL_TG_PT=1
 	 * allocated in __core_scsi3_alloc_registration()
@@ -1075,19 +1102,31 @@ static void __core_scsi3_add_registration(
 		__core_scsi3_dump_registration(tfo, dev, nacl_tmp, pr_reg_tmp,
 					       register_type);
 		spin_unlock(&pr_tmpl->registration_lock);
-
+		/*
+		 * Drop configfs group dependency reference and deve->pr_kref
+		 * obtained from  __core_scsi3_alloc_registration() code.
+		 */
 		rcu_read_lock();
 		deve = pr_reg_tmp->pr_reg_deve;
-		if (deve)
+		if (deve) {
 			set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+			core_scsi3_lunacl_undepend_item(deve);
+			pr_reg_tmp->pr_reg_deve = NULL;
+		}
 		rcu_read_unlock();
-
-		/*
-		 * Drop configfs group dependency reference from
-		 * __core_scsi3_alloc_registration()
-		 */
-		core_scsi3_lunacl_undepend_item(pr_reg_tmp->pr_reg_deve);
 	}
+out:
+	/*
+	 * Drop deve->pr_kref obtained in __core_scsi3_do_alloc_registration()
+	 */
+	rcu_read_lock();
+	deve = pr_reg->pr_reg_deve;
+	if (deve) {
+		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+		kref_put(&deve->pr_kref, target_pr_kref_release);
+		pr_reg->pr_reg_deve = NULL;
+	}
+	rcu_read_unlock();
 }
 
 static int core_scsi3_alloc_registration(
@@ -1785,9 +1824,11 @@ core_scsi3_decode_spec_i_port(
 			dest_node_acl->initiatorname, i_buf, (dest_se_deve) ?
 			dest_se_deve->mapped_lun : 0);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
@@ -1823,9 +1864,11 @@ out:
 
 		kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 2d0381dd105c..5fb9dd7f08bb 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -668,7 +668,10 @@ int core_tpg_add_lun(
 	list_add_tail(&lun->lun_dev_link, &dev->dev_sep_list);
 	spin_unlock(&dev->se_port_lock);
 
-	lun->lun_access = lun_access;
+	if (dev->dev_flags & DF_READ_ONLY)
+		lun->lun_access = TRANSPORT_LUNFLAGS_READ_ONLY;
+	else
+		lun->lun_access = lun_access;
 	if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		hlist_add_head_rcu(&lun->link, &tpg->tpg_lun_hlist);
 	mutex_unlock(&tpg->tpg_lun_mutex);
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 039004400987..5aabc4bc0d75 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -163,7 +163,7 @@ config THERMAL_EMULATION
 
 config HISI_THERMAL
 	tristate "Hisilicon thermal driver"
-	depends on ARCH_HISI && CPU_THERMAL && OF
+	depends on (ARCH_HISI && CPU_THERMAL && OF) || COMPILE_TEST
 	help
 	  Enable this to plug hisilicon's thermal sensor driver into the Linux
 	  thermal framework. cpufreq is used as the cooling device to throttle
@@ -182,7 +182,7 @@ config IMX_THERMAL
 
 config SPEAR_THERMAL
 	bool "SPEAr thermal sensor driver"
-	depends on PLAT_SPEAR
+	depends on PLAT_SPEAR || COMPILE_TEST
 	depends on OF
 	help
 	  Enable this to plug the SPEAr thermal sensor driver into the Linux
@@ -190,7 +190,7 @@ config SPEAR_THERMAL
 
 config ROCKCHIP_THERMAL
 	tristate "Rockchip thermal driver"
-	depends on ARCH_ROCKCHIP
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
 	depends on RESET_CONTROLLER
 	help
 	  Rockchip thermal driver provides support for Temperature sensor
@@ -208,7 +208,7 @@ config RCAR_THERMAL
 
 config KIRKWOOD_THERMAL
 	tristate "Temperature sensor on Marvell Kirkwood SoCs"
-	depends on MACH_KIRKWOOD
+	depends on MACH_KIRKWOOD || COMPILE_TEST
 	depends on OF
 	help
 	  Support for the Kirkwood thermal sensor driver into the Linux thermal
@@ -216,7 +216,7 @@ config KIRKWOOD_THERMAL
 
 config DOVE_THERMAL
 	tristate "Temperature sensor on Marvell Dove SoCs"
-	depends on ARCH_DOVE || MACH_DOVE
+	depends on ARCH_DOVE || MACH_DOVE || COMPILE_TEST
 	depends on OF
 	help
 	  Support for the Dove thermal sensor driver in the Linux thermal
@@ -234,7 +234,7 @@ config DB8500_THERMAL
 
 config ARMADA_THERMAL
 	tristate "Armada 370/XP thermal management"
-	depends on ARCH_MVEBU
+	depends on ARCH_MVEBU || COMPILE_TEST
 	depends on OF
 	help
 	  Enable this option if you want to have support for thermal management
@@ -349,11 +349,12 @@ config INTEL_PCH_THERMAL
 	  programmable trip points and other information.
 
 menu "Texas Instruments thermal drivers"
+depends on ARCH_HAS_BANDGAP || COMPILE_TEST
 source "drivers/thermal/ti-soc-thermal/Kconfig"
 endmenu
 
 menu "Samsung thermal drivers"
-depends on ARCH_EXYNOS
+depends on ARCH_EXYNOS || COMPILE_TEST
 source "drivers/thermal/samsung/Kconfig"
 endmenu
 
@@ -364,7 +365,7 @@ endmenu
 
 config QCOM_SPMI_TEMP_ALARM
 	tristate "Qualcomm SPMI PMIC Temperature Alarm"
-	depends on OF && SPMI && IIO
+	depends on OF && (SPMI || COMPILE_TEST) && IIO
 	select REGMAP_SPMI
 	help
 	  This enables a thermal sysfs driver for Qualcomm plug-and-play (QPNP)
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 620dcd405ff6..42c6f71bdcc1 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -262,7 +262,9 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
  * efficiently.  Power is stored in mW, frequency in KHz.  The
  * resulting table is in ascending order.
  *
- * Return: 0 on success, -E* on error.
+ * Return: 0 on success, -EINVAL if there are no OPPs for any CPUs,
+ * -ENOMEM if we run out of memory or -EAGAIN if an OPP was
+ * added/enabled while the function was executing.
  */
 static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 				 u32 capacitance)
@@ -273,8 +275,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 	int num_opps = 0, cpu, i, ret = 0;
 	unsigned long freq;
 
-	rcu_read_lock();
-
 	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
 		dev = get_cpu_device(cpu);
 		if (!dev) {
@@ -284,24 +284,20 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		}
 
 		num_opps = dev_pm_opp_get_opp_count(dev);
-		if (num_opps > 0) {
+		if (num_opps > 0)
 			break;
-		} else if (num_opps < 0) {
-			ret = num_opps;
-			goto unlock;
-		}
+		else if (num_opps < 0)
+			return num_opps;
 	}
 
-	if (num_opps == 0) {
-		ret = -EINVAL;
-		goto unlock;
-	}
+	if (num_opps == 0)
+		return -EINVAL;
 
 	power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
-	if (!power_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!power_table)
+		return -ENOMEM;
+
+	rcu_read_lock();
 
 	for (freq = 0, i = 0;
 	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
@@ -309,6 +305,12 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		u32 freq_mhz, voltage_mv;
 		u64 power;
 
+		if (i >= num_opps) {
+			rcu_read_unlock();
+			ret = -EAGAIN;
+			goto free_power_table;
+		}
+
 		freq_mhz = freq / 1000000;
 		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
 
@@ -326,17 +328,22 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		power_table[i].power = power;
 	}
 
-	if (i == 0) {
+	rcu_read_unlock();
+
+	if (i != num_opps) {
 		ret = PTR_ERR(opp);
-		goto unlock;
+		goto free_power_table;
 	}
 
 	cpufreq_device->cpu_dev = dev;
 	cpufreq_device->dyn_power_table = power_table;
 	cpufreq_device->dyn_power_table_entries = i;
 
-unlock:
-	rcu_read_unlock();
+	return 0;
+
+free_power_table:
+	kfree(power_table);
+
 	return ret;
 }
 
@@ -847,7 +854,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
 	if (ret) {
 		cool_dev = ERR_PTR(ret);
-		goto free_table;
+		goto free_power_table;
 	}
 
 	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
@@ -889,6 +896,8 @@ __cpufreq_cooling_register(struct device_node *np,
 
 remove_idr:
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+free_power_table:
+	kfree(cpufreq_dev->dyn_power_table);
 free_table:
 	kfree(cpufreq_dev->freq_table);
 free_time_in_idle_timestamp:
@@ -1039,6 +1048,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+	kfree(cpufreq_dev->dyn_power_table);
 	kfree(cpufreq_dev->time_in_idle_timestamp);
 	kfree(cpufreq_dev->time_in_idle);
 	kfree(cpufreq_dev->freq_table);
diff --git a/drivers/thermal/db8500_cpufreq_cooling.c b/drivers/thermal/db8500_cpufreq_cooling.c
index 607b62c7e611..e58bd0b658b5 100644
--- a/drivers/thermal/db8500_cpufreq_cooling.c
+++ b/drivers/thermal/db8500_cpufreq_cooling.c
@@ -72,6 +72,7 @@ static const struct of_device_id db8500_cpufreq_cooling_match[] = {
 	{ .compatible = "stericsson,db8500-cpufreq-cooling" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, db8500_cpufreq_cooling_match);
 #endif
 
 static struct platform_driver db8500_cpufreq_cooling_driver = {
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index 9c8a7aad0252..7ff96270c933 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -24,6 +24,8 @@
 
 #include "thermal_core.h"
 
+#define INVALID_TRIP -1
+
 #define FRAC_BITS 10
 #define int_to_frac(x) ((x) << FRAC_BITS)
 #define frac_to_int(x) ((x) >> FRAC_BITS)
@@ -56,16 +58,21 @@ static inline s64 div_frac(s64 x, s64 y)
 
 /**
  * struct power_allocator_params - parameters for the power allocator governor
+ * @allocated_tzp:	whether we have allocated tzp for this thermal zone and
+ *			it needs to be freed on unbind
  * @err_integral:	accumulated error in the PID controller.
  * @prev_err:	error in the previous iteration of the PID controller.
  *		Used to calculate the derivative term.
  * @trip_switch_on:	first passive trip point of the thermal zone.  The
  *			governor switches on when this trip point is crossed.
+ *			If the thermal zone only has one passive trip point,
+ *			@trip_switch_on should be INVALID_TRIP.
  * @trip_max_desired_temperature:	last passive trip point of the thermal
  *					zone.  The temperature we are
  *					controlling for.
  */
 struct power_allocator_params {
+	bool allocated_tzp;
 	s64 err_integral;
 	s32 prev_err;
 	int trip_switch_on;
@@ -73,6 +80,88 @@ struct power_allocator_params {
 };
 
 /**
+ * estimate_sustainable_power() - Estimate the sustainable power of a thermal zone
+ * @tz: thermal zone we are operating in
+ *
+ * For thermal zones that don't provide a sustainable_power in their
+ * thermal_zone_params, estimate one.  Calculate it using the minimum
+ * power of all the cooling devices as that gives a valid value that
+ * can give some degree of functionality.  For optimal performance of
+ * this governor, provide a sustainable_power in the thermal zone's
+ * thermal_zone_params.
+ */
+static u32 estimate_sustainable_power(struct thermal_zone_device *tz)
+{
+	u32 sustainable_power = 0;
+	struct thermal_instance *instance;
+	struct power_allocator_params *params = tz->governor_data;
+
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		struct thermal_cooling_device *cdev = instance->cdev;
+		u32 min_power;
+
+		if (instance->trip != params->trip_max_desired_temperature)
+			continue;
+
+		if (power_actor_get_min_power(cdev, tz, &min_power))
+			continue;
+
+		sustainable_power += min_power;
+	}
+
+	return sustainable_power;
+}
+
+/**
+ * estimate_pid_constants() - Estimate the constants for the PID controller
+ * @tz:		thermal zone for which to estimate the constants
+ * @sustainable_power:	sustainable power for the thermal zone
+ * @trip_switch_on:	trip point number for the switch on temperature
+ * @control_temp:	target temperature for the power allocator governor
+ * @force:	whether to force the update of the constants
+ *
+ * This function is used to update the estimation of the PID
+ * controller constants in struct thermal_zone_parameters.
+ * Sustainable power is provided in case it was estimated.  The
+ * estimated sustainable_power should not be stored in the
+ * thermal_zone_parameters so it has to be passed explicitly to this
+ * function.
+ *
+ * If @force is not set, the values in the thermal zone's parameters
+ * are preserved if they are not zero.  If @force is set, the values
+ * in thermal zone's parameters are overwritten.
+ */
+static void estimate_pid_constants(struct thermal_zone_device *tz,
+				   u32 sustainable_power, int trip_switch_on,
+				   int control_temp, bool force)
+{
+	int ret;
+	int switch_on_temp;
+	u32 temperature_threshold;
+
+	ret = tz->ops->get_trip_temp(tz, trip_switch_on, &switch_on_temp);
+	if (ret)
+		switch_on_temp = 0;
+
+	temperature_threshold = control_temp - switch_on_temp;
+
+	if (!tz->tzp->k_po || force)
+		tz->tzp->k_po = int_to_frac(sustainable_power) /
+			temperature_threshold;
+
+	if (!tz->tzp->k_pu || force)
+		tz->tzp->k_pu = int_to_frac(2 * sustainable_power) /
+			temperature_threshold;
+
+	if (!tz->tzp->k_i || force)
+		tz->tzp->k_i = int_to_frac(10) / 1000;
+	/*
+	 * The default for k_d and integral_cutoff is 0, so we can
+	 * leave them as they are.
+	 */
+}
+
+/**
  * pid_controller() - PID controller
  * @tz:	thermal zone we are operating in
  * @current_temp:	the current temperature in millicelsius
@@ -98,10 +187,20 @@ static u32 pid_controller(struct thermal_zone_device *tz,
 {
 	s64 p, i, d, power_range;
 	s32 err, max_power_frac;
+	u32 sustainable_power;
 	struct power_allocator_params *params = tz->governor_data;
 
 	max_power_frac = int_to_frac(max_allocatable_power);
 
+	if (tz->tzp->sustainable_power) {
+		sustainable_power = tz->tzp->sustainable_power;
+	} else {
+		sustainable_power = estimate_sustainable_power(tz);
+		estimate_pid_constants(tz, sustainable_power,
+				       params->trip_switch_on, control_temp,
+				       true);
+	}
+
 	err = control_temp - current_temp;
 	err = int_to_frac(err);
 
@@ -139,7 +238,7 @@ static u32 pid_controller(struct thermal_zone_device *tz,
 	power_range = p + i + d;
 
 	/* feed-forward the known sustainable dissipatable power */
-	power_range = tz->tzp->sustainable_power + frac_to_int(power_range);
+	power_range = sustainable_power + frac_to_int(power_range);
 
 	power_range = clamp(power_range, (s64)0, (s64)max_allocatable_power);
 
@@ -247,6 +346,11 @@ static int allocate_power(struct thermal_zone_device *tz,
 		}
 	}
 
+	if (!num_actors) {
+		ret = -ENODEV;
+		goto unlock;
+	}
+
 	/*
 	 * We need to allocate five arrays of the same size:
 	 * req_power, max_power, granted_power, extra_actor_power and
@@ -340,43 +444,66 @@ unlock:
 	return ret;
 }
 
-static int get_governor_trips(struct thermal_zone_device *tz,
-			      struct power_allocator_params *params)
+/**
+ * get_governor_trips() - get the number of the two trip points that are key for this governor
+ * @tz:	thermal zone to operate on
+ * @params:	pointer to private data for this governor
+ *
+ * The power allocator governor works optimally with two trips points:
+ * a "switch on" trip point and a "maximum desired temperature".  These
+ * are defined as the first and last passive trip points.
+ *
+ * If there is only one trip point, then that's considered to be the
+ * "maximum desired temperature" trip point and the governor is always
+ * on.  If there are no passive or active trip points, then the
+ * governor won't do anything.  In fact, its throttle function
+ * won't be called at all.
+ */
+static void get_governor_trips(struct thermal_zone_device *tz,
+			       struct power_allocator_params *params)
 {
-	int i, ret, last_passive;
+	int i, last_active, last_passive;
 	bool found_first_passive;
 
 	found_first_passive = false;
-	last_passive = -1;
-	ret = -EINVAL;
+	last_active = INVALID_TRIP;
+	last_passive = INVALID_TRIP;
 
 	for (i = 0; i < tz->trips; i++) {
 		enum thermal_trip_type type;
+		int ret;
 
 		ret = tz->ops->get_trip_type(tz, i, &type);
-		if (ret)
-			return ret;
+		if (ret) {
+			dev_warn(&tz->device,
+				 "Failed to get trip point %d type: %d\n", i,
+				 ret);
+			continue;
+		}
 
-		if (!found_first_passive) {
-			if (type == THERMAL_TRIP_PASSIVE) {
+		if (type == THERMAL_TRIP_PASSIVE) {
+			if (!found_first_passive) {
 				params->trip_switch_on = i;
 				found_first_passive = true;
+			} else  {
+				last_passive = i;
 			}
-		} else if (type == THERMAL_TRIP_PASSIVE) {
-			last_passive = i;
+		} else if (type == THERMAL_TRIP_ACTIVE) {
+			last_active = i;
 		} else {
 			break;
 		}
 	}
 
-	if (last_passive != -1) {
+	if (last_passive != INVALID_TRIP) {
 		params->trip_max_desired_temperature = last_passive;
-		ret = 0;
+	} else if (found_first_passive) {
+		params->trip_max_desired_temperature = params->trip_switch_on;
+		params->trip_switch_on = INVALID_TRIP;
 	} else {
-		ret = -EINVAL;
+		params->trip_switch_on = INVALID_TRIP;
+		params->trip_max_desired_temperature = last_active;
 	}
-
-	return ret;
 }
 
 static void reset_pid_controller(struct power_allocator_params *params)
@@ -405,60 +532,45 @@ static void allow_maximum_power(struct thermal_zone_device *tz)
  * power_allocator_bind() - bind the power_allocator governor to a thermal zone
  * @tz:	thermal zone to bind it to
  *
- * Check that the thermal zone is valid for this governor, that is, it
- * has two thermal trips.  If so, initialize the PID controller
- * parameters and bind it to the thermal zone.
+ * Initialize the PID controller parameters and bind it to the thermal
+ * zone.
  *
- * Return: 0 on success, -EINVAL if the trips were invalid or -ENOMEM
- * if we ran out of memory.
+ * Return: 0 on success, or -ENOMEM if we ran out of memory.
  */
 static int power_allocator_bind(struct thermal_zone_device *tz)
 {
 	int ret;
 	struct power_allocator_params *params;
-	int switch_on_temp, control_temp;
-	u32 temperature_threshold;
-
-	if (!tz->tzp || !tz->tzp->sustainable_power) {
-		dev_err(&tz->device,
-			"power_allocator: missing sustainable_power\n");
-		return -EINVAL;
-	}
+	int control_temp;
 
 	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (!params)
 		return -ENOMEM;
 
-	ret = get_governor_trips(tz, params);
-	if (ret) {
-		dev_err(&tz->device,
-			"thermal zone %s has wrong trip setup for power allocator\n",
-			tz->type);
-		goto free;
-	}
+	if (!tz->tzp) {
+		tz->tzp = kzalloc(sizeof(*tz->tzp), GFP_KERNEL);
+		if (!tz->tzp) {
+			ret = -ENOMEM;
+			goto free_params;
+		}
 
-	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
-				     &switch_on_temp);
-	if (ret)
-		goto free;
+		params->allocated_tzp = true;
+	}
 
-	ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
-				     &control_temp);
-	if (ret)
-		goto free;
+	if (!tz->tzp->sustainable_power)
+		dev_warn(&tz->device, "power_allocator: sustainable_power will be estimated\n");
 
-	temperature_threshold = control_temp - switch_on_temp;
+	get_governor_trips(tz, params);
 
-	tz->tzp->k_po = tz->tzp->k_po ?:
-		int_to_frac(tz->tzp->sustainable_power) / temperature_threshold;
-	tz->tzp->k_pu = tz->tzp->k_pu ?:
-		int_to_frac(2 * tz->tzp->sustainable_power) /
-		temperature_threshold;
-	tz->tzp->k_i = tz->tzp->k_i ?: int_to_frac(10) / 1000;
-	/*
-	 * The default for k_d and integral_cutoff is 0, so we can
-	 * leave them as they are.
-	 */
+	if (tz->trips > 0) {
+		ret = tz->ops->get_trip_temp(tz,
+					params->trip_max_desired_temperature,
+					&control_temp);
+		if (!ret)
+			estimate_pid_constants(tz, tz->tzp->sustainable_power,
+					       params->trip_switch_on,
+					       control_temp, false);
+	}
 
 	reset_pid_controller(params);
 
@@ -466,14 +578,23 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
 
 	return 0;
 
-free:
+free_params:
 	kfree(params);
+
 	return ret;
 }
 
 static void power_allocator_unbind(struct thermal_zone_device *tz)
 {
+	struct power_allocator_params *params = tz->governor_data;
+
 	dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
+
+	if (params->allocated_tzp) {
+		kfree(tz->tzp);
+		tz->tzp = NULL;
+	}
+
 	kfree(tz->governor_data);
 	tz->governor_data = NULL;
 }
@@ -499,13 +620,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 
 	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
 				     &switch_on_temp);
-	if (ret) {
-		dev_warn(&tz->device,
-			 "Failed to get switch on temperature: %d\n", ret);
-		return ret;
-	}
-
-	if (current_temp < switch_on_temp) {
+	if (!ret && (current_temp < switch_on_temp)) {
 		tz->passive = 0;
 		reset_pid_controller(params);
 		allow_maximum_power(tz);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5e5fc7015c7f..d9e525cc9c1c 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1013,6 +1013,34 @@ int power_actor_get_max_power(struct thermal_cooling_device *cdev,
 }
 
 /**
+ * power_actor_get_min_power() - get the mainimum power that a cdev can consume
+ * @cdev:	pointer to &thermal_cooling_device
+ * @tz:		a valid thermal zone device pointer
+ * @min_power:	pointer in which to store the minimum power
+ *
+ * Calculate the minimum power consumption in milliwatts that the
+ * cooling device can currently consume and store it in @min_power.
+ *
+ * Return: 0 on success, -EINVAL if @cdev doesn't support the
+ * power_actor API or -E* on other error.
+ */
+int power_actor_get_min_power(struct thermal_cooling_device *cdev,
+			      struct thermal_zone_device *tz, u32 *min_power)
+{
+	unsigned long max_state;
+	int ret;
+
+	if (!cdev_is_power_actor(cdev))
+		return -EINVAL;
+
+	ret = cdev->ops->get_max_state(cdev, &max_state);
+	if (ret)
+		return ret;
+
+	return cdev->ops->state2power(cdev, tz, max_state, min_power);
+}
+
+/**
  * power_actor_set_power() - limit the maximum power that a cooling device can consume
  * @cdev:	pointer to &thermal_cooling_device
  * @instance:	thermal instance to update
diff --git a/drivers/thermal/ti-soc-thermal/Kconfig b/drivers/thermal/ti-soc-thermal/Kconfig
index bd4c7beba679..cb6686ff09ae 100644
--- a/drivers/thermal/ti-soc-thermal/Kconfig
+++ b/drivers/thermal/ti-soc-thermal/Kconfig
@@ -1,7 +1,5 @@
 config TI_SOC_THERMAL
 	tristate "Texas Instruments SoCs temperature sensor driver"
-	depends on THERMAL
-	depends on ARCH_HAS_BANDGAP
 	help
 	  If you say yes here you get support for the Texas Instruments
 	  OMAP4460+ on die bandgap temperature sensor support. The register
@@ -24,7 +22,7 @@ config TI_THERMAL
 config OMAP4_THERMAL
 	bool "Texas Instruments OMAP4 thermal support"
 	depends on TI_SOC_THERMAL
-	depends on ARCH_OMAP4
+	depends on ARCH_OMAP4 || COMPILE_TEST
 	help
 	  If you say yes here you get thermal support for the Texas Instruments
 	  OMAP4 SoC family. The current chip supported are:
@@ -38,7 +36,7 @@ config OMAP4_THERMAL
 config OMAP5_THERMAL
 	bool "Texas Instruments OMAP5 thermal support"
 	depends on TI_SOC_THERMAL
-	depends on SOC_OMAP5
+	depends on SOC_OMAP5 || COMPILE_TEST
 	help
 	  If you say yes here you get thermal support for the Texas Instruments
 	  OMAP5 SoC family. The current chip supported are:
@@ -50,7 +48,7 @@ config OMAP5_THERMAL
 config DRA752_THERMAL
 	bool "Texas Instruments DRA752 thermal support"
 	depends on TI_SOC_THERMAL
-	depends on SOC_DRA7XX
+	depends on SOC_DRA7XX || COMPILE_TEST
 	help
 	  If you say yes here you get thermal support for the Texas Instruments
 	  DRA752 SoC family. The current chip supported are:
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index c68fe1222c16..20a41f7de76f 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -643,7 +643,7 @@ static struct pci_device_id nhi_ids[] = {
 	{
 		.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
 		.vendor = PCI_VENDOR_ID_INTEL, .device = 0x156c,
-		.subvendor = 0x2222, .subdevice = 0x1111,
+		.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID,
 	},
 	{ 0,}
 };
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 54e6c8ddef5d..b1e0ba3e525b 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2910,3 +2910,5 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe)
 }
 
 #endif /* CONFIG_SERIAL_8250_CONSOLE */
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 867e9f3f3859..dcc50c878159 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -61,7 +61,7 @@ static const struct of_device_id ci_hdrc_imx_dt_ids[] = {
 	{ .compatible = "fsl,imx27-usb", .data = &imx27_usb_data},
 	{ .compatible = "fsl,imx6q-usb", .data = &imx6q_usb_data},
 	{ .compatible = "fsl,imx6sl-usb", .data = &imx6sl_usb_data},
-	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sl_usb_data},
+	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sx_usb_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, ci_hdrc_imx_dt_ids);
diff --git a/drivers/usb/chipidea/ci_hdrc_usb2.c b/drivers/usb/chipidea/ci_hdrc_usb2.c
index 9eae1a16cef9..4456d2cf80ff 100644
--- a/drivers/usb/chipidea/ci_hdrc_usb2.c
+++ b/drivers/usb/chipidea/ci_hdrc_usb2.c
@@ -12,6 +12,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/usb/chipidea.h>
@@ -30,18 +31,36 @@ static const struct ci_hdrc_platform_data ci_default_pdata = {
 	.flags		= CI_HDRC_DISABLE_STREAMING,
 };
 
+static struct ci_hdrc_platform_data ci_zynq_pdata = {
+	.capoffset	= DEF_CAPOFFSET,
+};
+
+static const struct of_device_id ci_hdrc_usb2_of_match[] = {
+	{ .compatible = "chipidea,usb2"},
+	{ .compatible = "xlnx,zynq-usb-2.20a", .data = &ci_zynq_pdata},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ci_hdrc_usb2_of_match);
+
 static int ci_hdrc_usb2_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ci_hdrc_usb2_priv *priv;
 	struct ci_hdrc_platform_data *ci_pdata = dev_get_platdata(dev);
 	int ret;
+	const struct of_device_id *match;
 
 	if (!ci_pdata) {
 		ci_pdata = devm_kmalloc(dev, sizeof(*ci_pdata), GFP_KERNEL);
 		*ci_pdata = ci_default_pdata;	/* struct copy */
 	}
 
+	match = of_match_device(ci_hdrc_usb2_of_match, &pdev->dev);
+	if (match && match->data) {
+		/* struct copy */
+		*ci_pdata = *(struct ci_hdrc_platform_data *)match->data;
+	}
+
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -96,12 +115,6 @@ static int ci_hdrc_usb2_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id ci_hdrc_usb2_of_match[] = {
-	{ .compatible = "chipidea,usb2" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, ci_hdrc_usb2_of_match);
-
 static struct platform_driver ci_hdrc_usb2_driver = {
 	.probe	= ci_hdrc_usb2_probe,
 	.remove	= ci_hdrc_usb2_remove,
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index a637da25dda0..8223fe73ea85 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -656,6 +656,44 @@ __acquires(hwep->lock)
 	return 0;
 }
 
+static int _ep_set_halt(struct usb_ep *ep, int value, bool check_transfer)
+{
+	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
+	int direction, retval = 0;
+	unsigned long flags;
+
+	if (ep == NULL || hwep->ep.desc == NULL)
+		return -EINVAL;
+
+	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
+		return -EOPNOTSUPP;
+
+	spin_lock_irqsave(hwep->lock, flags);
+
+	if (value && hwep->dir == TX && check_transfer &&
+		!list_empty(&hwep->qh.queue) &&
+			!usb_endpoint_xfer_control(hwep->ep.desc)) {
+		spin_unlock_irqrestore(hwep->lock, flags);
+		return -EAGAIN;
+	}
+
+	direction = hwep->dir;
+	do {
+		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
+
+		if (!value)
+			hwep->wedge = 0;
+
+		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
+			hwep->dir = (hwep->dir == TX) ? RX : TX;
+
+	} while (hwep->dir != direction);
+
+	spin_unlock_irqrestore(hwep->lock, flags);
+	return retval;
+}
+
+
 /**
  * _gadget_stop_activity: stops all USB activity, flushes & disables all endpts
  * @gadget: gadget
@@ -1051,7 +1089,7 @@ __acquires(ci->lock)
 				num += ci->hw_ep_max / 2;
 
 			spin_unlock(&ci->lock);
-			err = usb_ep_set_halt(&ci->ci_hw_ep[num].ep);
+			err = _ep_set_halt(&ci->ci_hw_ep[num].ep, 1, false);
 			spin_lock(&ci->lock);
 			if (!err)
 				isr_setup_status_phase(ci);
@@ -1117,8 +1155,8 @@ delegate:
 
 	if (err < 0) {
 		spin_unlock(&ci->lock);
-		if (usb_ep_set_halt(&hwep->ep))
-			dev_err(ci->dev, "error: ep_set_halt\n");
+		if (_ep_set_halt(&hwep->ep, 1, false))
+			dev_err(ci->dev, "error: _ep_set_halt\n");
 		spin_lock(&ci->lock);
 	}
 }
@@ -1149,9 +1187,9 @@ __acquires(ci->lock)
 					err = isr_setup_status_phase(ci);
 				if (err < 0) {
 					spin_unlock(&ci->lock);
-					if (usb_ep_set_halt(&hwep->ep))
+					if (_ep_set_halt(&hwep->ep, 1, false))
 						dev_err(ci->dev,
-							"error: ep_set_halt\n");
+						"error: _ep_set_halt\n");
 					spin_lock(&ci->lock);
 				}
 			}
@@ -1397,41 +1435,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
  */
 static int ep_set_halt(struct usb_ep *ep, int value)
 {
-	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
-	int direction, retval = 0;
-	unsigned long flags;
-
-	if (ep == NULL || hwep->ep.desc == NULL)
-		return -EINVAL;
-
-	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
-		return -EOPNOTSUPP;
-
-	spin_lock_irqsave(hwep->lock, flags);
-
-#ifndef STALL_IN
-	/* g_file_storage MS compliant but g_zero fails chapter 9 compliance */
-	if (value && hwep->type == USB_ENDPOINT_XFER_BULK && hwep->dir == TX &&
-	    !list_empty(&hwep->qh.queue)) {
-		spin_unlock_irqrestore(hwep->lock, flags);
-		return -EAGAIN;
-	}
-#endif
-
-	direction = hwep->dir;
-	do {
-		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
-
-		if (!value)
-			hwep->wedge = 0;
-
-		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
-			hwep->dir = (hwep->dir == TX) ? RX : TX;
-
-	} while (hwep->dir != direction);
-
-	spin_unlock_irqrestore(hwep->lock, flags);
-	return retval;
+	return _ep_set_halt(ep, value, true);
 }
 
 /**
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index b2a540b43f97..b9ddf0c1ffe5 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -112,7 +112,7 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 				cfgno, inum, asnum, ep->desc.bEndpointAddress);
 		ep->ss_ep_comp.bmAttributes = 16;
 	} else if (usb_endpoint_xfer_isoc(&ep->desc) &&
-			desc->bmAttributes > 2) {
+		   USB_SS_MULT(desc->bmAttributes) > 3) {
 		dev_warn(ddev, "Isoc endpoint has Mult of %d in "
 				"config %d interface %d altsetting %d ep %d: "
 				"setting to 3\n", desc->bmAttributes + 1,
@@ -121,7 +121,8 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 	}
 
 	if (usb_endpoint_xfer_isoc(&ep->desc))
-		max_tx = (desc->bMaxBurst + 1) * (desc->bmAttributes + 1) *
+		max_tx = (desc->bMaxBurst + 1) *
+			(USB_SS_MULT(desc->bmAttributes)) *
 			usb_endpoint_maxp(&ep->desc);
 	else if (usb_endpoint_xfer_int(&ep->desc))
 		max_tx = usb_endpoint_maxp(&ep->desc) *
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index a5a1b7c45743..22e9606d8e08 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -514,8 +514,6 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 		goto err1;
 	}
 
-	dwc3_omap_enable_irqs(omap);
-
 	ret = dwc3_omap_extcon_register(omap);
 	if (ret < 0)
 		goto err2;
@@ -526,6 +524,8 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 		goto err3;
 	}
 
+	dwc3_omap_enable_irqs(omap);
+
 	return 0;
 
 err3:
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 0c25704dcb6b..1e8bdf817811 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2665,8 +2665,6 @@ static irqreturn_t dwc3_interrupt(int irq, void *_dwc)
 	int				i;
 	irqreturn_t			ret = IRQ_NONE;
 
-	spin_lock(&dwc->lock);
-
 	for (i = 0; i < dwc->num_event_buffers; i++) {
 		irqreturn_t status;
 
@@ -2675,8 +2673,6 @@ static irqreturn_t dwc3_interrupt(int irq, void *_dwc)
 			ret = status;
 	}
 
-	spin_unlock(&dwc->lock);
-
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/epautoconf.c b/drivers/usb/gadget/epautoconf.c
index 978435a51038..6399c106a3a5 100644
--- a/drivers/usb/gadget/epautoconf.c
+++ b/drivers/usb/gadget/epautoconf.c
@@ -186,6 +186,7 @@ void usb_ep_autoconfig_reset (struct usb_gadget *gadget)
 
 	list_for_each_entry (ep, &gadget->ep_list, ep_list) {
 		ep->claimed = false;
+		ep->driver_data = NULL;
 	}
 	gadget->in_epnum = 0;
 	gadget->out_epnum = 0;
diff --git a/drivers/usb/gadget/udc/amd5536udc.c b/drivers/usb/gadget/udc/amd5536udc.c
index fdacddb18c00..175ca93fe5e2 100644
--- a/drivers/usb/gadget/udc/amd5536udc.c
+++ b/drivers/usb/gadget/udc/amd5536udc.c
@@ -3138,8 +3138,8 @@ static void udc_pci_remove(struct pci_dev *pdev)
 	writel(AMD_BIT(UDC_DEVCFG_SOFTRESET), &dev->regs->cfg);
 	if (dev->irq_registered)
 		free_irq(pdev->irq, dev);
-	if (dev->regs)
-		iounmap(dev->regs);
+	if (dev->virt_addr)
+		iounmap(dev->virt_addr);
 	if (dev->mem_region)
 		release_mem_region(pci_resource_start(pdev, 0),
 				pci_resource_len(pdev, 0));
@@ -3226,17 +3226,13 @@ static int udc_pci_probe(
 
 	/* init */
 	dev = kzalloc(sizeof(struct udc), GFP_KERNEL);
-	if (!dev) {
-		retval = -ENOMEM;
-		goto finished;
-	}
+	if (!dev)
+		return -ENOMEM;
 
 	/* pci setup */
 	if (pci_enable_device(pdev) < 0) {
-		kfree(dev);
-		dev = NULL;
 		retval = -ENODEV;
-		goto finished;
+		goto err_pcidev;
 	}
 	dev->active = 1;
 
@@ -3246,28 +3242,22 @@ static int udc_pci_probe(
 
 	if (!request_mem_region(resource, len, name)) {
 		dev_dbg(&pdev->dev, "pci device used already\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -EBUSY;
-		goto finished;
+		goto err_memreg;
 	}
 	dev->mem_region = 1;
 
 	dev->virt_addr = ioremap_nocache(resource, len);
 	if (dev->virt_addr == NULL) {
 		dev_dbg(&pdev->dev, "start address cannot be mapped\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -EFAULT;
-		goto finished;
+		goto err_ioremap;
 	}
 
 	if (!pdev->irq) {
 		dev_err(&pdev->dev, "irq not set\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -ENODEV;
-		goto finished;
+		goto err_irq;
 	}
 
 	spin_lock_init(&dev->lock);
@@ -3283,10 +3273,8 @@ static int udc_pci_probe(
 
 	if (request_irq(pdev->irq, udc_irq, IRQF_SHARED, name, dev) != 0) {
 		dev_dbg(&pdev->dev, "request_irq(%d) fail\n", pdev->irq);
-		kfree(dev);
-		dev = NULL;
 		retval = -EBUSY;
-		goto finished;
+		goto err_irq;
 	}
 	dev->irq_registered = 1;
 
@@ -3314,8 +3302,17 @@ static int udc_pci_probe(
 		return 0;
 
 finished:
-	if (dev)
-		udc_pci_remove(pdev);
+	udc_pci_remove(pdev);
+	return retval;
+
+err_irq:
+	iounmap(dev->virt_addr);
+err_ioremap:
+	release_mem_region(resource, len);
+err_memreg:
+	pci_disable_device(pdev);
+err_pcidev:
+	kfree(dev);
 	return retval;
 }
 
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 3dfada8d6061..f0f2b066ac08 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -2002,6 +2002,17 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
 		ep->udc = udc;
 		INIT_LIST_HEAD(&ep->queue);
 
+		if (ep->index == 0) {
+			ep->ep.caps.type_control = true;
+		} else {
+			ep->ep.caps.type_iso = ep->can_isoc;
+			ep->ep.caps.type_bulk = true;
+			ep->ep.caps.type_int = true;
+		}
+
+		ep->ep.caps.dir_in = true;
+		ep->ep.caps.dir_out = true;
+
 		if (i)
 			list_add_tail(&ep->ep.ep_list, &udc->gadget.ep_list);
 
diff --git a/drivers/usb/gadget/udc/bdc/bdc_core.c b/drivers/usb/gadget/udc/bdc/bdc_core.c
index 5c8f4effb62a..ccb9c213cc9f 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_core.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_core.c
@@ -324,8 +324,7 @@ static void bdc_mem_free(struct bdc *bdc)
 				bdc->scratchpad.buff, bdc->scratchpad.sp_dma);
 
 	/* Destroy the dma pools */
-	if (bdc->bd_table_pool)
-		dma_pool_destroy(bdc->bd_table_pool);
+	dma_pool_destroy(bdc->bd_table_pool);
 
 	/* Free the bdc_ep array */
 	kfree(bdc->bdc_ep_array);
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 1379ad40d864..27af0f008b57 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1348,6 +1348,7 @@ static int transfer(struct dummy_hcd *dum_hcd, struct urb *urb,
 {
 	struct dummy		*dum = dum_hcd->dum;
 	struct dummy_request	*req;
+	int			sent = 0;
 
 top:
 	/* if there's no request queued, the device is NAKing; return */
@@ -1385,12 +1386,15 @@ top:
 			if (len == 0)
 				break;
 
-			/* use an extra pass for the final short packet */
-			if (len > ep->ep.maxpacket) {
-				rescan = 1;
-				len -= (len % ep->ep.maxpacket);
+			/* send multiple of maxpacket first, then remainder */
+			if (len >= ep->ep.maxpacket) {
+				is_short = 0;
+				if (len % ep->ep.maxpacket)
+					rescan = 1;
+				len -= len % ep->ep.maxpacket;
+			} else {
+				is_short = 1;
 			}
-			is_short = (len % ep->ep.maxpacket) != 0;
 
 			len = dummy_perform_transfer(urb, req, len);
 
@@ -1399,6 +1403,7 @@ top:
 				req->req.status = len;
 			} else {
 				limit -= len;
+				sent += len;
 				urb->actual_length += len;
 				req->req.actual += len;
 			}
@@ -1421,7 +1426,7 @@ top:
 					*status = -EOVERFLOW;
 				else
 					*status = 0;
-			} else if (!to_host) {
+			} else {
 				*status = 0;
 				if (host_len > dev_len)
 					req->req.status = -EOVERFLOW;
@@ -1429,15 +1434,24 @@ top:
 					req->req.status = 0;
 			}
 
-		/* many requests terminate without a short packet */
+		/*
+		 * many requests terminate without a short packet.
+		 * send a zlp if demanded by flags.
+		 */
 		} else {
-			if (req->req.length == req->req.actual
-					&& !req->req.zero)
-				req->req.status = 0;
-			if (urb->transfer_buffer_length == urb->actual_length
-					&& !(urb->transfer_flags
-						& URB_ZERO_PACKET))
-				*status = 0;
+			if (req->req.length == req->req.actual) {
+				if (req->req.zero && to_host)
+					rescan = 1;
+				else
+					req->req.status = 0;
+			}
+			if (urb->transfer_buffer_length == urb->actual_length) {
+				if (urb->transfer_flags & URB_ZERO_PACKET &&
+				    !to_host)
+					rescan = 1;
+				else
+					*status = 0;
+			}
 		}
 
 		/* device side completion --> continuable */
@@ -1460,7 +1474,7 @@ top:
 		if (rescan)
 			goto top;
 	}
-	return limit;
+	return sent;
 }
 
 static int periodic_bytes(struct dummy *dum, struct dummy_ep *ep)
@@ -1890,7 +1904,7 @@ restart:
 		default:
 treat_control_like_bulk:
 			ep->last_io = jiffies;
-			total = transfer(dum_hcd, urb, ep, limit, &status);
+			total -= transfer(dum_hcd, urb, ep, limit, &status);
 			break;
 		}
 
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index 8aa2593c2c36..b9429bc42511 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -2117,8 +2117,7 @@ static int gr_remove(struct platform_device *pdev)
 		return -EBUSY;
 
 	gr_dfs_delete(dev);
-	if (dev->desc_pool)
-		dma_pool_destroy(dev->desc_pool);
+	dma_pool_destroy(dev->desc_pool);
 	platform_set_drvdata(pdev, NULL);
 
 	gr_free_request(&dev->epi[0].ep, &dev->ep0reqi->req);
diff --git a/drivers/usb/gadget/udc/mv_u3d_core.c b/drivers/usb/gadget/udc/mv_u3d_core.c
index 4c489692745e..dafe74eb9ade 100644
--- a/drivers/usb/gadget/udc/mv_u3d_core.c
+++ b/drivers/usb/gadget/udc/mv_u3d_core.c
@@ -1767,8 +1767,7 @@ static int mv_u3d_remove(struct platform_device *dev)
 	usb_del_gadget_udc(&u3d->gadget);
 
 	/* free memory allocated in probe */
-	if (u3d->trb_pool)
-		dma_pool_destroy(u3d->trb_pool);
+	dma_pool_destroy(u3d->trb_pool);
 
 	if (u3d->ep_context)
 		dma_free_coherent(&dev->dev, u3d->ep_context_size,
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index 339af51df57d..81b6229c7805 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -2100,8 +2100,7 @@ static int mv_udc_remove(struct platform_device *pdev)
 	}
 
 	/* free memory allocated in probe */
-	if (udc->dtd_pool)
-		dma_pool_destroy(udc->dtd_pool);
+	dma_pool_destroy(udc->dtd_pool);
 
 	if (udc->ep_dqh)
 		dma_free_coherent(&pdev->dev, udc->ep_dqh_size,
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 9a8c936cd42c..41f841fa6c4d 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1498,10 +1498,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	 * use Event Data TRBs, and we don't chain in a link TRB on short
 	 * transfers, we're basically dividing by 1.
 	 *
-	 * xHCI 1.0 specification indicates that the Average TRB Length should
-	 * be set to 8 for control endpoints.
+	 * xHCI 1.0 and 1.1 specification indicates that the Average TRB Length
+	 * should be set to 8 for control endpoints.
 	 */
-	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version == 0x100)
+	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
 		ep_ctx->tx_info |= cpu_to_le32(AVG_TRB_LENGTH_FOR_EP(8));
 	else
 		ep_ctx->tx_info |=
@@ -1792,8 +1792,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	int size;
 	int i, j, num_ports;
 
-	if (timer_pending(&xhci->cmd_timer))
-		del_timer_sync(&xhci->cmd_timer);
+	del_timer_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);
@@ -2321,6 +2320,10 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 
 	INIT_LIST_HEAD(&xhci->cmd_list);
 
+	/* init command timeout timer */
+	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
+		    (unsigned long)xhci);
+
 	page_size = readl(&xhci->op_regs->page_size);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"Supported page size register = 0x%x", page_size);
@@ -2505,10 +2508,6 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 			"Wrote ERST address to ir_set 0.");
 	xhci_print_ir_set(xhci, 0);
 
-	/* init command timeout timer */
-	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
-		    (unsigned long)xhci);
-
 	/*
 	 * XXX: Might need to set the Interrupter Moderation Register to
 	 * something other than the default (~1ms minimum between interrupts).
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 5590eac2b22d..c79d33676672 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -180,51 +180,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 				"QUIRK: Resetting on resume");
 }
 
-/*
- * In some Intel xHCI controllers, in order to get D3 working,
- * through a vendor specific SSIC CONFIG register at offset 0x883c,
- * SSIC PORT need to be marked as "unused" before putting xHCI
- * into D3. After D3 exit, the SSIC port need to be marked as "used".
- * Without this change, xHCI might not enter D3 state.
- * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
- * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
- */
-static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
-{
-	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
-	u32 val;
-	void __iomem *reg;
-
-	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
-		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
-
-		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
-
-		/* Notify SSIC that SSIC profile programming is not done */
-		val = readl(reg) & ~PROG_DONE;
-		writel(val, reg);
-
-		/* Mark SSIC port as unused(suspend) or used(resume) */
-		val = readl(reg);
-		if (suspend)
-			val |= SSIC_PORT_UNUSED;
-		else
-			val &= ~SSIC_PORT_UNUSED;
-		writel(val, reg);
-
-		/* Notify SSIC that SSIC profile programming is done */
-		val = readl(reg) | PROG_DONE;
-		writel(val, reg);
-		readl(reg);
-	}
-
-	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
-	val = readl(reg);
-	writel(val | BIT(28), reg);
-	readl(reg);
-}
-
 #ifdef CONFIG_ACPI
 static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev)
 {
@@ -345,6 +300,51 @@ static void xhci_pci_remove(struct pci_dev *dev)
 }
 
 #ifdef CONFIG_PM
+/*
+ * In some Intel xHCI controllers, in order to get D3 working,
+ * through a vendor specific SSIC CONFIG register at offset 0x883c,
+ * SSIC PORT need to be marked as "unused" before putting xHCI
+ * into D3. After D3 exit, the SSIC port need to be marked as "used".
+ * Without this change, xHCI might not enter D3 state.
+ * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
+ * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
+ */
+static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
+{
+	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
+	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
+	u32 val;
+	void __iomem *reg;
+
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
+
+		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
+
+		/* Notify SSIC that SSIC profile programming is not done */
+		val = readl(reg) & ~PROG_DONE;
+		writel(val, reg);
+
+		/* Mark SSIC port as unused(suspend) or used(resume) */
+		val = readl(reg);
+		if (suspend)
+			val |= SSIC_PORT_UNUSED;
+		else
+			val &= ~SSIC_PORT_UNUSED;
+		writel(val, reg);
+
+		/* Notify SSIC that SSIC profile programming is done */
+		val = readl(reg) | PROG_DONE;
+		writel(val, reg);
+		readl(reg);
+	}
+
+	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
+	val = readl(reg);
+	writel(val | BIT(28), reg);
+	readl(reg);
+}
+
 static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index a47a1e897086..43291f93afeb 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -302,6 +302,15 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 	ret = xhci_handshake(&xhci->op_regs->cmd_ring,
 			CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
 	if (ret < 0) {
+		/* we are about to kill xhci, give it one more chance */
+		xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
+			      &xhci->op_regs->cmd_ring);
+		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");
 		xhci->xhc_state |= XHCI_STATE_DYING;
@@ -3461,8 +3470,8 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	if (start_cycle == 0)
 		field |= 0x1;
 
-	/* xHCI 1.0 6.4.1.2.1: Transfer Type field */
-	if (xhci->hci_version == 0x100) {
+	/* xHCI 1.0/1.1 6.4.1.2.1: Transfer Type field */
+	if (xhci->hci_version >= 0x100) {
 		if (urb->transfer_buffer_length > 0) {
 			if (setup->bRequestType & USB_DIR_IN)
 				field |= TRB_TX_TYPE(TRB_DATA_IN);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6b0f4a47e402..9957bd96d4bc 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -146,7 +146,8 @@ static int xhci_start(struct xhci_hcd *xhci)
 				"waited %u microseconds.\n",
 				XHCI_MAX_HALT_USEC);
 	if (!ret)
-		xhci->xhc_state &= ~XHCI_STATE_HALTED;
+		xhci->xhc_state &= ~(XHCI_STATE_HALTED | XHCI_STATE_DYING);
+
 	return ret;
 }
 
@@ -654,15 +655,6 @@ int xhci_run(struct usb_hcd *hcd)
 }
 EXPORT_SYMBOL_GPL(xhci_run);
 
-static void xhci_only_stop_hcd(struct usb_hcd *hcd)
-{
-	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-
-	spin_lock_irq(&xhci->lock);
-	xhci_halt(xhci);
-	spin_unlock_irq(&xhci->lock);
-}
-
 /*
  * Stop xHCI driver.
  *
@@ -677,12 +669,14 @@ void xhci_stop(struct usb_hcd *hcd)
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 
-	if (!usb_hcd_is_primary_hcd(hcd)) {
-		xhci_only_stop_hcd(xhci->shared_hcd);
+	if (xhci->xhc_state & XHCI_STATE_HALTED)
 		return;
-	}
 
+	mutex_lock(&xhci->mutex);
 	spin_lock_irq(&xhci->lock);
+	xhci->xhc_state |= XHCI_STATE_HALTED;
+	xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
+
 	/* Make sure the xHC is halted for a USB3 roothub
 	 * (xhci_stop() could be called as part of failed init).
 	 */
@@ -717,6 +711,7 @@ void xhci_stop(struct usb_hcd *hcd)
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"xhci_stop completed - status = %x",
 			readl(&xhci->op_regs->status));
+	mutex_unlock(&xhci->mutex);
 }
 
 /*
@@ -3793,6 +3788,9 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 
 	mutex_lock(&xhci->mutex);
 
+	if (xhci->xhc_state)	/* dying or halted */
+		goto out;
+
 	if (!udev->slot_id) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_address,
 				"Bad Slot ID %d", udev->slot_id);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 514a6cdaeff6..4a518ff12310 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1051,6 +1051,7 @@ void musb_start(struct musb *musb)
 	 * (c) peripheral initiates, using SRP
 	 */
 	if (musb->port_mode != MUSB_PORT_MODE_HOST &&
+			musb->xceiv->otg->state != OTG_STATE_A_WAIT_BCON &&
 			(devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS) {
 		musb->is_active = 1;
 	} else {
@@ -2448,6 +2449,9 @@ static int musb_suspend(struct device *dev)
 	struct musb	*musb = dev_to_musb(dev);
 	unsigned long	flags;
 
+	musb_platform_disable(musb);
+	musb_generic_disable(musb);
+
 	spin_lock_irqsave(&musb->lock, flags);
 
 	if (is_peripheral_active(musb)) {
@@ -2501,6 +2505,9 @@ static int musb_resume(struct device *dev)
 	pm_runtime_disable(dev);
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
+
+	musb_start(musb);
+
 	return 0;
 }
 
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index d07cafb7d5f5..e499b862a946 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -551,6 +551,9 @@ static int cppi41_dma_channel_abort(struct dma_channel *channel)
 	} else {
 		cppi41_set_autoreq_mode(cppi41_channel, EP_MODE_AUTOREQ_NONE);
 
+		/* delay to drain to cppi dma pipeline for isoch */
+		udelay(250);
+
 		csr = musb_readw(epio, MUSB_RXCSR);
 		csr &= ~(MUSB_RXCSR_H_REQPKT | MUSB_RXCSR_DMAENAB);
 		musb_writew(epio, MUSB_RXCSR, csr);
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index a0cfead6150f..84512d1d5eee 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -225,8 +225,11 @@ static void dsps_musb_enable(struct musb *musb)
 
 	dsps_writel(reg_base, wrp->epintr_set, epmask);
 	dsps_writel(reg_base, wrp->coreintr_set, coremask);
-	/* start polling for ID change. */
-	mod_timer(&glue->timer, jiffies + msecs_to_jiffies(wrp->poll_timeout));
+	/* start polling for ID change in dual-role idle mode */
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
+			musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
+		mod_timer(&glue->timer, jiffies +
+				msecs_to_jiffies(wrp->poll_timeout));
 	dsps_musb_try_idle(musb, 0);
 }
 
diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c
index 39168fe9b406..b2685e75a683 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -379,6 +379,8 @@ static const struct of_device_id ux500_match[] = {
         {}
 };
 
+MODULE_DEVICE_TABLE(of, ux500_match);
+
 static struct platform_driver ux500_driver = {
 	.probe		= ux500_probe,
 	.remove		= ux500_remove,
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 7d3beee2a587..173132416170 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -155,7 +155,7 @@ config USB_MSM_OTG
 config USB_QCOM_8X16_PHY
 	tristate "Qualcomm APQ8016/MSM8916 on-chip USB PHY controller support"
 	depends on ARCH_QCOM || COMPILE_TEST
-	depends on RESET_CONTROLLER
+	depends on RESET_CONTROLLER && EXTCON
 	select USB_PHY
 	select USB_ULPI_VIEWPORT
 	help
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index ec6ecd03269c..5320cb8642cb 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -232,7 +232,8 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop,
 		clk_rate = pdata->clk_rate;
 		needs_vcc = pdata->needs_vcc;
 		if (gpio_is_valid(pdata->gpio_reset)) {
-			err = devm_gpio_request_one(dev, pdata->gpio_reset, 0,
+			err = devm_gpio_request_one(dev, pdata->gpio_reset,
+						    GPIOF_ACTIVE_LOW,
 						    dev_name(dev));
 			if (!err)
 				nop->gpiod_reset =
diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c
index 8a55b37d1a02..db68156568e6 100644
--- a/drivers/usb/phy/phy-isp1301.c
+++ b/drivers/usb/phy/phy-isp1301.c
@@ -31,6 +31,7 @@ static const struct i2c_device_id isp1301_id[] = {
 	{ "isp1301", 0 },
 	{ }
 };
+MODULE_DEVICE_TABLE(i2c, isp1301_id);
 
 static struct i2c_client *isp1301_i2c_client;
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 6d1941a2396a..6956c4f62216 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -278,6 +278,10 @@ static void option_instat_callback(struct urb *urb);
 #define ZTE_PRODUCT_MF622			0x0001
 #define ZTE_PRODUCT_MF628			0x0015
 #define ZTE_PRODUCT_MF626			0x0031
+#define ZTE_PRODUCT_ZM8620_X			0x0396
+#define ZTE_PRODUCT_ME3620_MBIM			0x0426
+#define ZTE_PRODUCT_ME3620_X			0x1432
+#define ZTE_PRODUCT_ME3620_L			0x1433
 #define ZTE_PRODUCT_AC2726			0xfff1
 #define ZTE_PRODUCT_MG880			0xfffd
 #define ZTE_PRODUCT_CDMA_TECH			0xfffe
@@ -544,6 +548,18 @@ static const struct option_blacklist_info zte_mc2716_z_blacklist = {
 	.sendsetup = BIT(1) | BIT(2) | BIT(3),
 };
 
+static const struct option_blacklist_info zte_me3620_mbim_blacklist = {
+	.reserved = BIT(2) | BIT(3) | BIT(4),
+};
+
+static const struct option_blacklist_info zte_me3620_xl_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
+static const struct option_blacklist_info zte_zm8620_x_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
 static const struct option_blacklist_info huawei_cdc12_blacklist = {
 	.reserved = BIT(1) | BIT(2),
 };
@@ -1591,6 +1607,14 @@ static const struct usb_device_id option_ids[] = {
 	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
 	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_L),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_MBIM),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_mbim_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_X),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ZM8620_X),
+	 .driver_info = (kernel_ulong_t)&zte_zm8620_x_blacklist },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 6c3734d2b45a..d3ea90bef84d 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -80,6 +80,8 @@ static int  whiteheat_firmware_download(struct usb_serial *serial,
 static int  whiteheat_firmware_attach(struct usb_serial *serial);
 
 /* function prototypes for the Connect Tech WhiteHEAT serial converter */
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id);
 static int  whiteheat_attach(struct usb_serial *serial);
 static void whiteheat_release(struct usb_serial *serial);
 static int  whiteheat_port_probe(struct usb_serial_port *port);
@@ -116,6 +118,7 @@ static struct usb_serial_driver whiteheat_device = {
 	.description =		"Connect Tech - WhiteHEAT",
 	.id_table =		id_table_std,
 	.num_ports =		4,
+	.probe =		whiteheat_probe,
 	.attach =		whiteheat_attach,
 	.release =		whiteheat_release,
 	.port_probe =		whiteheat_port_probe,
@@ -217,6 +220,34 @@ static int whiteheat_firmware_attach(struct usb_serial *serial)
 /*****************************************************************************
  * Connect Tech's White Heat serial driver functions
  *****************************************************************************/
+
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id)
+{
+	struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *endpoint;
+	size_t num_bulk_in = 0;
+	size_t num_bulk_out = 0;
+	size_t min_num_bulk;
+	unsigned int i;
+
+	iface_desc = serial->interface->cur_altsetting;
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) {
+		endpoint = &iface_desc->endpoint[i].desc;
+		if (usb_endpoint_is_bulk_in(endpoint))
+			++num_bulk_in;
+		if (usb_endpoint_is_bulk_out(endpoint))
+			++num_bulk_out;
+	}
+
+	min_num_bulk = COMMAND_PORT + 1;
+	if (num_bulk_in < min_num_bulk || num_bulk_out < min_num_bulk)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int whiteheat_attach(struct usb_serial *serial)
 {
 	struct usb_serial_port *command_port;
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 81220b2203c6..0ef5cc13fae2 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -44,8 +44,6 @@
 #define BTRFS_INODE_IN_DELALLOC_LIST		9
 #define BTRFS_INODE_READDIO_NEED_LOCK		10
 #define BTRFS_INODE_HAS_PROPS		        11
-/* DIO is ready to submit */
-#define BTRFS_INODE_DIO_READY		        12
 /*
  * The following 3 bits are meant only for the btree inode.
  * When any of them is set, it means an error happened while writing an
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 0d98aee34fee..295795aebe0b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3765,9 +3765,7 @@ void close_ctree(struct btrfs_root *root)
 		 * block groups queued for removal, the deletion will be
 		 * skipped when we quit the cleaner thread.
 		 */
-		mutex_lock(&root->fs_info->cleaner_mutex);
 		btrfs_delete_unused_bgs(root->fs_info);
-		mutex_unlock(&root->fs_info->cleaner_mutex);
 
 		ret = btrfs_commit_super(root);
 		if (ret)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5411f0ab5683..9f9604201333 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3742,10 +3742,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	found->bytes_reserved = 0;
 	found->bytes_readonly = 0;
 	found->bytes_may_use = 0;
-	if (total_bytes > 0)
-		found->full = 0;
-	else
-		found->full = 1;
+	found->full = 0;
 	found->force_alloc = CHUNK_ALLOC_NO_FORCE;
 	found->chunk_alloc = 0;
 	found->flush = 0;
@@ -8668,7 +8665,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	}
 
 	if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) {
-		btrfs_drop_and_free_fs_root(tree_root->fs_info, root);
+		btrfs_add_dropped_root(trans, root);
 	} else {
 		free_extent_buffer(root->node);
 		free_extent_buffer(root->commit_root);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f1018cfbfefa..e2357e31609a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2798,7 +2798,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			      bio_end_io_t end_io_func,
 			      int mirror_num,
 			      unsigned long prev_bio_flags,
-			      unsigned long bio_flags)
+			      unsigned long bio_flags,
+			      bool force_bio_submit)
 {
 	int ret = 0;
 	struct bio *bio;
@@ -2814,6 +2815,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			contig = bio_end_sector(bio) == sector;
 
 		if (prev_bio_flags != bio_flags || !contig ||
+		    force_bio_submit ||
 		    merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, offset) < page_size) {
 			ret = submit_one_bio(rw, bio, mirror_num,
@@ -2910,7 +2912,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 			 get_extent_t *get_extent,
 			 struct extent_map **em_cached,
 			 struct bio **bio, int mirror_num,
-			 unsigned long *bio_flags, int rw)
+			 unsigned long *bio_flags, int rw,
+			 u64 *prev_em_start)
 {
 	struct inode *inode = page->mapping->host;
 	u64 start = page_offset(page);
@@ -2958,6 +2961,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 	}
 	while (cur <= end) {
 		unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
+		bool force_bio_submit = false;
 
 		if (cur >= last_byte) {
 			char *userpage;
@@ -3008,6 +3012,49 @@ static int __do_readpage(struct extent_io_tree *tree,
 		block_start = em->block_start;
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			block_start = EXTENT_MAP_HOLE;
+
+		/*
+		 * If we have a file range that points to a compressed extent
+		 * and it's followed by a consecutive file range that points to
+		 * to the same compressed extent (possibly with a different
+		 * offset and/or length, so it either points to the whole extent
+		 * or only part of it), we must make sure we do not submit a
+		 * single bio to populate the pages for the 2 ranges because
+		 * this makes the compressed extent read zero out the pages
+		 * belonging to the 2nd range. Imagine the following scenario:
+		 *
+		 *  File layout
+		 *  [0 - 8K]                     [8K - 24K]
+		 *    |                               |
+		 *    |                               |
+		 * points to extent X,         points to extent X,
+		 * offset 4K, length of 8K     offset 0, length 16K
+		 *
+		 * [extent X, compressed length = 4K uncompressed length = 16K]
+		 *
+		 * If the bio to read the compressed extent covers both ranges,
+		 * it will decompress extent X into the pages belonging to the
+		 * first range and then it will stop, zeroing out the remaining
+		 * pages that belong to the other range that points to extent X.
+		 * So here we make sure we submit 2 bios, one for the first
+		 * range and another one for the third range. Both will target
+		 * the same physical extent from disk, but we can't currently
+		 * make the compressed bio endio callback populate the pages
+		 * for both ranges because each compressed bio is tightly
+		 * coupled with a single extent map, and each range can have
+		 * an extent map with a different offset value relative to the
+		 * uncompressed data of our extent and different lengths. This
+		 * is a corner case so we prioritize correctness over
+		 * non-optimal behavior (submitting 2 bios for the same extent).
+		 */
+		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
+		    prev_em_start && *prev_em_start != (u64)-1 &&
+		    *prev_em_start != em->orig_start)
+			force_bio_submit = true;
+
+		if (prev_em_start)
+			*prev_em_start = em->orig_start;
+
 		free_extent_map(em);
 		em = NULL;
 
@@ -3057,7 +3104,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 					 bdev, bio, pnr,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
-					 this_bio_flag);
+					 this_bio_flag,
+					 force_bio_submit);
 		if (!ret) {
 			nr++;
 			*bio_flags = this_bio_flag;
@@ -3089,6 +3137,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 	struct inode *inode;
 	struct btrfs_ordered_extent *ordered;
 	int index;
+	u64 prev_em_start = (u64)-1;
 
 	inode = pages[0]->mapping->host;
 	while (1) {
@@ -3104,7 +3153,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 
 	for (index = 0; index < nr_pages; index++) {
 		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
-			      mirror_num, bio_flags, rw);
+			      mirror_num, bio_flags, rw, &prev_em_start);
 		page_cache_release(pages[index]);
 	}
 }
@@ -3172,7 +3221,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	}
 
 	ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
-			    bio_flags, rw);
+			    bio_flags, rw, NULL);
 	return ret;
 }
 
@@ -3198,7 +3247,7 @@ int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
 	int ret;
 
 	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-				      &bio_flags, READ);
+			    &bio_flags, READ, NULL);
 	if (bio)
 		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
 	return ret;
@@ -3451,7 +3500,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 						 sector, iosize, pg_offset,
 						 bdev, &epd->bio, max_nr,
 						 end_bio_extent_writepage,
-						 0, 0, 0);
+						 0, 0, 0, false);
 			if (ret)
 				SetPageError(page);
 		}
@@ -3754,7 +3803,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
 					 PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
 					 -1, end_bio_extent_buffer_writepage,
-					 0, epd->bio_flags, bio_flags);
+					 0, epd->bio_flags, bio_flags, false);
 		epd->bio_flags = bio_flags;
 		if (ret) {
 			set_btree_ioerr(p);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a0fa7253a2d7..611b66d73e80 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5084,7 +5084,8 @@ void btrfs_evict_inode(struct inode *inode)
 		goto no_delete;
 	}
 	/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
-	btrfs_wait_ordered_range(inode, 0, (u64)-1);
+	if (!special_file(inode->i_mode))
+		btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
 	btrfs_free_io_failure_record(inode, 0, (u64)-1);
 
@@ -7408,6 +7409,10 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 	return em;
 }
 
+struct btrfs_dio_data {
+	u64 outstanding_extents;
+	u64 reserve;
+};
 
 static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -7415,10 +7420,10 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	struct extent_map *em;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_state *cached_state = NULL;
+	struct btrfs_dio_data *dio_data = NULL;
 	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
 	u64 len = bh_result->b_size;
-	u64 *outstanding_extents = NULL;
 	int unlock_bits = EXTENT_LOCKED;
 	int ret = 0;
 
@@ -7436,7 +7441,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		 * that anything that needs to check if there's a transction doesn't get
 		 * confused.
 		 */
-		outstanding_extents = current->journal_info;
+		dio_data = current->journal_info;
 		current->journal_info = NULL;
 	}
 
@@ -7568,17 +7573,18 @@ unlock:
 		 * within our reservation, otherwise we need to adjust our inode
 		 * counter appropriately.
 		 */
-		if (*outstanding_extents) {
-			(*outstanding_extents)--;
+		if (dio_data->outstanding_extents) {
+			(dio_data->outstanding_extents)--;
 		} else {
 			spin_lock(&BTRFS_I(inode)->lock);
 			BTRFS_I(inode)->outstanding_extents++;
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
-		current->journal_info = outstanding_extents;
 		btrfs_free_reserved_data_space(inode, len);
-		set_bit(BTRFS_INODE_DIO_READY, &BTRFS_I(inode)->runtime_flags);
+		WARN_ON(dio_data->reserve < len);
+		dio_data->reserve -= len;
+		current->journal_info = dio_data;
 	}
 
 	/*
@@ -7601,8 +7607,8 @@ unlock:
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
-	if (outstanding_extents)
-		current->journal_info = outstanding_extents;
+	if (dio_data)
+		current->journal_info = dio_data;
 	return ret;
 }
 
@@ -8329,7 +8335,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	u64 outstanding_extents = 0;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_dio_data dio_data = { 0 };
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
@@ -8367,7 +8374,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		ret = btrfs_delalloc_reserve_space(inode, count);
 		if (ret)
 			goto out;
-		outstanding_extents = div64_u64(count +
+		dio_data.outstanding_extents = div64_u64(count +
 						BTRFS_MAX_EXTENT_SIZE - 1,
 						BTRFS_MAX_EXTENT_SIZE);
 
@@ -8376,7 +8383,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		 * do the accounting properly if we go over the number we
 		 * originally calculated.  Abuse current->journal_info for this.
 		 */
-		current->journal_info = &outstanding_extents;
+		dio_data.reserve = round_up(count, root->sectorsize);
+		current->journal_info = &dio_data;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_end(inode);
@@ -8391,16 +8399,9 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == WRITE) {
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED) {
-			/*
-			 * If the error comes from submitting stage,
-			 * btrfs_get_blocsk_direct() has free'd data space,
-			 * and metadata space will be handled by
-			 * finish_ordered_fn, don't do that again to make
-			 * sure bytes_may_use is correct.
-			 */
-			if (!test_and_clear_bit(BTRFS_INODE_DIO_READY,
-				     &BTRFS_I(inode)->runtime_flags))
-				btrfs_delalloc_release_space(inode, count);
+			if (dio_data.reserve)
+				btrfs_delalloc_release_space(inode,
+							dio_data.reserve);
 		} else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode,
 						     count - (size_t)ret);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2b07b3581781..11d1eab9234d 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1658,9 +1658,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		 * groups on disk until we're mounted read-write again
 		 * unless we clean them up here.
 		 */
-		mutex_lock(&root->fs_info->cleaner_mutex);
 		btrfs_delete_unused_bgs(fs_info);
-		mutex_unlock(&root->fs_info->cleaner_mutex);
 
 		btrfs_dev_replace_suspend_for_unmount(fs_info);
 		btrfs_scrub_cancel(fs_info);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8f259b3a66b3..74bc3338418b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -117,6 +117,18 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans,
 			btrfs_unpin_free_ino(root);
 		clear_btree_io_tree(&root->dirty_log_pages);
 	}
+
+	/* We can free old roots now. */
+	spin_lock(&trans->dropped_roots_lock);
+	while (!list_empty(&trans->dropped_roots)) {
+		root = list_first_entry(&trans->dropped_roots,
+					struct btrfs_root, root_list);
+		list_del_init(&root->root_list);
+		spin_unlock(&trans->dropped_roots_lock);
+		btrfs_drop_and_free_fs_root(fs_info, root);
+		spin_lock(&trans->dropped_roots_lock);
+	}
+	spin_unlock(&trans->dropped_roots_lock);
 	up_write(&fs_info->commit_root_sem);
 }
 
@@ -255,11 +267,13 @@ loop:
 	INIT_LIST_HEAD(&cur_trans->pending_ordered);
 	INIT_LIST_HEAD(&cur_trans->dirty_bgs);
 	INIT_LIST_HEAD(&cur_trans->io_bgs);
+	INIT_LIST_HEAD(&cur_trans->dropped_roots);
 	mutex_init(&cur_trans->cache_write_mutex);
 	cur_trans->num_dirty_bgs = 0;
 	spin_lock_init(&cur_trans->dirty_bgs_lock);
 	INIT_LIST_HEAD(&cur_trans->deleted_bgs);
 	spin_lock_init(&cur_trans->deleted_bgs_lock);
+	spin_lock_init(&cur_trans->dropped_roots_lock);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
 			     fs_info->btree_inode->i_mapping);
@@ -336,6 +350,24 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 }
 
 
+void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root)
+{
+	struct btrfs_transaction *cur_trans = trans->transaction;
+
+	/* Add ourselves to the transaction dropped list */
+	spin_lock(&cur_trans->dropped_roots_lock);
+	list_add_tail(&root->root_list, &cur_trans->dropped_roots);
+	spin_unlock(&cur_trans->dropped_roots_lock);
+
+	/* Make sure we don't try to update the root at commit time */
+	spin_lock(&root->fs_info->fs_roots_radix_lock);
+	radix_tree_tag_clear(&root->fs_info->fs_roots_radix,
+			     (unsigned long)root->root_key.objectid,
+			     BTRFS_ROOT_TRANS_TAG);
+	spin_unlock(&root->fs_info->fs_roots_radix_lock);
+}
+
 int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root)
 {
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index edc2fbc262d7..87964bf8892d 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -65,6 +65,7 @@ struct btrfs_transaction {
 	struct list_head switch_commits;
 	struct list_head dirty_bgs;
 	struct list_head io_bgs;
+	struct list_head dropped_roots;
 	u64 num_dirty_bgs;
 
 	/*
@@ -76,6 +77,7 @@ struct btrfs_transaction {
 	spinlock_t dirty_bgs_lock;
 	struct list_head deleted_bgs;
 	spinlock_t deleted_bgs_lock;
+	spinlock_t dropped_roots_lock;
 	struct btrfs_delayed_ref_root delayed_refs;
 	int aborted;
 	int dirty_bg_run;
@@ -216,5 +218,6 @@ int btrfs_transaction_blocked(struct btrfs_fs_info *info);
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
 void btrfs_put_transaction(struct btrfs_transaction *transaction);
 void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info);
-
+void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root);
 #endif
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index aa0dc2573374..afa09fce8151 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -444,6 +444,48 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	return 0;
 }
 
+/* Server has provided av pairs/target info in the type 2 challenge
+ * packet and we have plucked it and stored within smb session.
+ * We parse that blob here to find the server given timestamp
+ * as part of ntlmv2 authentication (or local current time as
+ * default in case of failure)
+ */
+static __le64
+find_timestamp(struct cifs_ses *ses)
+{
+	unsigned int attrsize;
+	unsigned int type;
+	unsigned int onesize = sizeof(struct ntlmssp2_name);
+	unsigned char *blobptr;
+	unsigned char *blobend;
+	struct ntlmssp2_name *attrptr;
+
+	if (!ses->auth_key.len || !ses->auth_key.response)
+		return 0;
+
+	blobptr = ses->auth_key.response;
+	blobend = blobptr + ses->auth_key.len;
+
+	while (blobptr + onesize < blobend) {
+		attrptr = (struct ntlmssp2_name *) blobptr;
+		type = le16_to_cpu(attrptr->type);
+		if (type == NTLMSSP_AV_EOL)
+			break;
+		blobptr += 2; /* advance attr type */
+		attrsize = le16_to_cpu(attrptr->length);
+		blobptr += 2; /* advance attr size */
+		if (blobptr + attrsize > blobend)
+			break;
+		if (type == NTLMSSP_AV_TIMESTAMP) {
+			if (attrsize == sizeof(u64))
+				return *((__le64 *)blobptr);
+		}
+		blobptr += attrsize; /* advance attr value */
+	}
+
+	return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+}
+
 static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 			    const struct nls_table *nls_cp)
 {
@@ -641,6 +683,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	struct ntlmv2_resp *ntlmv2;
 	char ntlmv2_hash[16];
 	unsigned char *tiblob = NULL; /* target info blob */
+	__le64 rsp_timestamp;
 
 	if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) {
 		if (!ses->domainName) {
@@ -659,6 +702,12 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 		}
 	}
 
+	/* Must be within 5 minutes of the server (or in range +/-2h
+	 * in case of Mac OS X), so simply carry over server timestamp
+	 * (as Windows 7 does)
+	 */
+	rsp_timestamp = find_timestamp(ses);
+
 	baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp);
 	tilen = ses->auth_key.len;
 	tiblob = ses->auth_key.response;
@@ -675,8 +724,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 			(ses->auth_key.response + CIFS_SESS_KEY_SIZE);
 	ntlmv2->blob_signature = cpu_to_le32(0x00000101);
 	ntlmv2->reserved = 0;
-	/* Must be within 5 minutes of the server */
-	ntlmv2->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+	ntlmv2->time = rsp_timestamp;
+
 	get_random_bytes(&ntlmv2->client_chal, sizeof(ntlmv2->client_chal));
 	ntlmv2->reserved2 = 0;
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index df91bcf56d67..18da19f4f811 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -50,9 +50,13 @@ change_conf(struct TCP_Server_Info *server)
 		break;
 	default:
 		server->echoes = true;
-		server->oplocks = true;
+		if (enable_oplocks) {
+			server->oplocks = true;
+			server->oplock_credits = 1;
+		} else
+			server->oplocks = false;
+
 		server->echo_credits = 1;
-		server->oplock_credits = 1;
 	}
 	server->credits -= server->echo_credits + server->oplock_credits;
 	return 0;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 070fb2ad85ce..ce83e2edbe0a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -46,6 +46,7 @@
 #include "smb2status.h"
 #include "smb2glob.h"
 #include "cifspdu.h"
+#include "cifs_spnego.h"
 
 /*
  *  The following table defines the expected "StructureSize" of SMB2 requests
@@ -486,19 +487,15 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		cifs_dbg(FYI, "missing security blob on negprot\n");
 
 	rc = cifs_enable_signing(server, ses->sign);
-#ifdef CONFIG_SMB2_ASN1  /* BB REMOVEME when updated asn1.c ready */
 	if (rc)
 		goto neg_exit;
-	if (blob_length)
+	if (blob_length) {
 		rc = decode_negTokenInit(security_blob, blob_length, server);
-	if (rc == 1)
-		rc = 0;
-	else if (rc == 0) {
-		rc = -EIO;
-		goto neg_exit;
+		if (rc == 1)
+			rc = 0;
+		else if (rc == 0)
+			rc = -EIO;
 	}
-#endif
-
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -592,7 +589,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	__le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */
 	struct TCP_Server_Info *server = ses->server;
 	u16 blob_length = 0;
-	char *security_blob;
+	struct key *spnego_key = NULL;
+	char *security_blob = NULL;
 	char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
 
@@ -620,7 +618,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	ses->ntlmssp->sesskey_per_smbsess = true;
 
 	/* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */
-	ses->sectype = RawNTLMSSP;
+	if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
+		ses->sectype = RawNTLMSSP;
 
 ssetup_ntlmssp_authenticate:
 	if (phase == NtLmChallenge)
@@ -649,7 +648,48 @@ ssetup_ntlmssp_authenticate:
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field and 1 for pad */
 	iov[0].iov_len = get_rfc1002_length(req) + 4 - 1;
-	if (phase == NtLmNegotiate) {
+
+	if (ses->sectype == Kerberos) {
+#ifdef CONFIG_CIFS_UPCALL
+		struct cifs_spnego_msg *msg;
+
+		spnego_key = cifs_get_spnego_key(ses);
+		if (IS_ERR(spnego_key)) {
+			rc = PTR_ERR(spnego_key);
+			spnego_key = NULL;
+			goto ssetup_exit;
+		}
+
+		msg = spnego_key->payload.data;
+		/*
+		 * check version field to make sure that cifs.upcall is
+		 * sending us a response in an expected form
+		 */
+		if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) {
+			cifs_dbg(VFS,
+				  "bad cifs.upcall version. Expected %d got %d",
+				  CIFS_SPNEGO_UPCALL_VERSION, msg->version);
+			rc = -EKEYREJECTED;
+			goto ssetup_exit;
+		}
+		ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
+						 GFP_KERNEL);
+		if (!ses->auth_key.response) {
+			cifs_dbg(VFS,
+				"Kerberos can't allocate (%u bytes) memory",
+				msg->sesskey_len);
+			rc = -ENOMEM;
+			goto ssetup_exit;
+		}
+		ses->auth_key.len = msg->sesskey_len;
+		blob_length = msg->secblob_len;
+		iov[1].iov_base = msg->data + msg->sesskey_len;
+		iov[1].iov_len = blob_length;
+#else
+		rc = -EOPNOTSUPP;
+		goto ssetup_exit;
+#endif /* CONFIG_CIFS_UPCALL */
+	} else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */
 		ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE),
 				       GFP_KERNEL);
 		if (ntlmssp_blob == NULL) {
@@ -672,6 +712,8 @@ ssetup_ntlmssp_authenticate:
 			/* with raw NTLMSSP we don't encapsulate in SPNEGO */
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else if (phase == NtLmAuthenticate) {
 		req->hdr.SessionId = ses->Suid;
 		ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
@@ -699,6 +741,8 @@ ssetup_ntlmssp_authenticate:
 		} else {
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else {
 		cifs_dbg(VFS, "illegal ntlmssp phase\n");
 		rc = -EIO;
@@ -710,8 +754,6 @@ ssetup_ntlmssp_authenticate:
 				cpu_to_le16(sizeof(struct smb2_sess_setup_req) -
 					    1 /* pad */ - 4 /* rfc1001 len */);
 	req->SecurityBufferLength = cpu_to_le16(blob_length);
-	iov[1].iov_base = security_blob;
-	iov[1].iov_len = blob_length;
 
 	inc_rfc1001_len(req, blob_length - 1 /* pad */);
 
@@ -722,6 +764,7 @@ ssetup_ntlmssp_authenticate:
 
 	kfree(security_blob);
 	rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base;
+	ses->Suid = rsp->hdr.SessionId;
 	if (resp_buftype != CIFS_NO_BUFFER &&
 	    rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) {
 		if (phase != NtLmNegotiate) {
@@ -739,7 +782,6 @@ ssetup_ntlmssp_authenticate:
 		/* NTLMSSP Negotiate sent now processing challenge (response) */
 		phase = NtLmChallenge; /* process ntlmssp challenge */
 		rc = 0; /* MORE_PROCESSING is not an error here but expected */
-		ses->Suid = rsp->hdr.SessionId;
 		rc = decode_ntlmssp_challenge(rsp->Buffer,
 				le16_to_cpu(rsp->SecurityBufferLength), ses);
 	}
@@ -796,6 +838,10 @@ keygen_exit:
 		kfree(ses->auth_key.response);
 		ses->auth_key.response = NULL;
 	}
+	if (spnego_key) {
+		key_invalidate(spnego_key);
+		key_put(spnego_key);
+	}
 	kfree(ses->ntlmssp);
 
 	return rc;
@@ -876,6 +922,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	if (tcon && tcon->bad_network_name)
 		return -ENOENT;
 
+	if ((tcon->seal) &&
+	    ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) {
+		cifs_dbg(VFS, "encryption requested but no server support");
+		return -EOPNOTSUPP;
+	}
+
 	unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
 	if (unc_path == NULL)
 		return -ENOMEM;
@@ -955,6 +1007,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
 		cifs_dbg(VFS, "DFS capability contradicts DFS flag\n");
 	init_copy_chunk_defaults(tcon);
+	if (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)
+		cifs_dbg(VFS, "Encrypted shares not supported");
 	if (tcon->ses->server->ops->validate_negotiate)
 		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 2714ef835bdd..be806ead7f4d 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -113,7 +113,8 @@ out:
 	return status;
 }
 
-static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
+static int nfs_delegation_claim_opens(struct inode *inode,
+		const nfs4_stateid *stateid, fmode_t type)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_context *ctx;
@@ -140,7 +141,7 @@ again:
 		/* Block nfs4_proc_unlck */
 		mutex_lock(&sp->so_delegreturn_mutex);
 		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
-		err = nfs4_open_delegation_recall(ctx, state, stateid);
+		err = nfs4_open_delegation_recall(ctx, state, stateid, type);
 		if (!err)
 			err = nfs_delegation_claim_locks(ctx, state, stateid);
 		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
@@ -411,7 +412,8 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 	do {
 		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
 			break;
-		err = nfs_delegation_claim_opens(inode, &delegation->stateid);
+		err = nfs_delegation_claim_opens(inode, &delegation->stateid,
+				delegation->type);
 		if (!issync || err != -EAGAIN)
 			break;
 		/*
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index a44829173e57..333063e032f0 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -54,7 +54,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 
 /* NFSv4 delegation-related procedures */
 int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
 int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
 bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 38678d9a5cc4..4b1d08f56aba 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -166,8 +166,11 @@ nfs_direct_select_verf(struct nfs_direct_req *dreq,
 	struct nfs_writeverf *verfp = &dreq->verf;
 
 #ifdef CONFIG_NFS_V4_1
-	if (ds_clp) {
-		/* pNFS is in use, use the DS verf */
+	/*
+	 * pNFS is in use, use the DS verf except commit_through_mds is set
+	 * for layout segment where nbuckets is zero.
+	 */
+	if (ds_clp && dreq->ds_cinfo.nbuckets > 0) {
 		if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets)
 			verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf;
 		else
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index b34f2e228601..02ec07973bc4 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -629,23 +629,18 @@ out_put:
 	goto out;
 }
 
-static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl)
+static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
 {
 	int i;
 
-	for (i = 0; i < fl->num_fh; i++) {
-		if (!fl->fh_array[i])
-			break;
-		kfree(fl->fh_array[i]);
+	if (fl->fh_array) {
+		for (i = 0; i < fl->num_fh; i++) {
+			if (!fl->fh_array[i])
+				break;
+			kfree(fl->fh_array[i]);
+		}
+		kfree(fl->fh_array);
 	}
-	kfree(fl->fh_array);
-	fl->fh_array = NULL;
-}
-
-static void
-_filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
-{
-	filelayout_free_fh_array(fl);
 	kfree(fl);
 }
 
@@ -716,21 +711,21 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 		/* Do we want to use a mempool here? */
 		fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags);
 		if (!fl->fh_array[i])
-			goto out_err_free;
+			goto out_err;
 
 		p = xdr_inline_decode(&stream, 4);
 		if (unlikely(!p))
-			goto out_err_free;
+			goto out_err;
 		fl->fh_array[i]->size = be32_to_cpup(p++);
 		if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
 			printk(KERN_ERR "NFS: Too big fh %d received %d\n",
 			       i, fl->fh_array[i]->size);
-			goto out_err_free;
+			goto out_err;
 		}
 
 		p = xdr_inline_decode(&stream, fl->fh_array[i]->size);
 		if (unlikely(!p))
-			goto out_err_free;
+			goto out_err;
 		memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
 		dprintk("DEBUG: %s: fh len %d\n", __func__,
 			fl->fh_array[i]->size);
@@ -739,8 +734,6 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 	__free_page(scratch);
 	return 0;
 
-out_err_free:
-	filelayout_free_fh_array(fl);
 out_err:
 	__free_page(scratch);
 	return -EIO;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index d731bbf974aa..0f020e4d8421 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -175,10 +175,12 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
-	int err;
+	loff_t err;
 
 	do {
 		err = _nfs42_proc_llseek(filep, offset, whence);
+		if (err >= 0)
+			break;
 		if (err == -ENOTSUPP)
 			return -EOPNOTSUPP;
 		err = nfs4_handle_exception(server, err, &exception);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 693b903b48bd..f93b9cdb4934 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1127,6 +1127,21 @@ static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task)
 	return ret;
 }
 
+static bool nfs4_mode_match_open_stateid(struct nfs4_state *state,
+		fmode_t fmode)
+{
+	switch(fmode & (FMODE_READ|FMODE_WRITE)) {
+	case FMODE_READ|FMODE_WRITE:
+		return state->n_rdwr != 0;
+	case FMODE_WRITE:
+		return state->n_wronly != 0;
+	case FMODE_READ:
+		return state->n_rdonly != 0;
+	}
+	WARN_ON_ONCE(1);
+	return false;
+}
+
 static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode)
 {
 	int ret = 0;
@@ -1571,17 +1586,13 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context
 	return opendata;
 }
 
-static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmode, struct nfs4_state **res)
+static int nfs4_open_recover_helper(struct nfs4_opendata *opendata,
+		fmode_t fmode)
 {
 	struct nfs4_state *newstate;
 	int ret;
 
-	if ((opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR ||
-	     opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEG_CUR_FH) &&
-	    (opendata->o_arg.u.delegation_type & fmode) != fmode)
-		/* This mode can't have been delegated, so we must have
-		 * a valid open_stateid to cover it - not need to reclaim.
-		 */
+	if (!nfs4_mode_match_open_stateid(opendata->state, fmode))
 		return 0;
 	opendata->o_arg.open_flags = 0;
 	opendata->o_arg.fmode = fmode;
@@ -1597,14 +1608,14 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
 	newstate = nfs4_opendata_to_nfs4_state(opendata);
 	if (IS_ERR(newstate))
 		return PTR_ERR(newstate);
+	if (newstate != opendata->state)
+		ret = -ESTALE;
 	nfs4_close_state(newstate, fmode);
-	*res = newstate;
-	return 0;
+	return ret;
 }
 
 static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *state)
 {
-	struct nfs4_state *newstate;
 	int ret;
 
 	/* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */
@@ -1615,27 +1626,15 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
 	clear_bit(NFS_DELEGATED_STATE, &state->flags);
 	clear_bit(NFS_OPEN_STATE, &state->flags);
 	smp_rmb();
-	if (state->n_rdwr != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
-	if (state->n_wronly != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
-	if (state->n_rdonly != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
+	ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
+	if (ret != 0)
+		return ret;
+	ret = nfs4_open_recover_helper(opendata, FMODE_WRITE);
+	if (ret != 0)
+		return ret;
+	ret = nfs4_open_recover_helper(opendata, FMODE_READ);
+	if (ret != 0)
+		return ret;
 	/*
 	 * We may have performed cached opens for all three recoveries.
 	 * Check if we need to update the current stateid.
@@ -1759,18 +1758,32 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 	return err;
 }
 
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
+		struct nfs4_state *state, const nfs4_stateid *stateid,
+		fmode_t type)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
 	struct nfs4_opendata *opendata;
-	int err;
+	int err = 0;
 
 	opendata = nfs4_open_recoverdata_alloc(ctx, state,
 			NFS4_OPEN_CLAIM_DELEG_CUR_FH);
 	if (IS_ERR(opendata))
 		return PTR_ERR(opendata);
 	nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
-	err = nfs4_open_recover(opendata, state);
+	clear_bit(NFS_DELEGATED_STATE, &state->flags);
+	switch (type & (FMODE_READ|FMODE_WRITE)) {
+	case FMODE_READ|FMODE_WRITE:
+	case FMODE_WRITE:
+		err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
+		if (err)
+			break;
+		err = nfs4_open_recover_helper(opendata, FMODE_WRITE);
+		if (err)
+			break;
+	case FMODE_READ:
+		err = nfs4_open_recover_helper(opendata, FMODE_READ);
+	}
 	nfs4_opendata_put(opendata);
 	return nfs4_handle_delegation_recall_error(server, state, stateid, err);
 }
@@ -2645,6 +2658,15 @@ out:
 	return err;
 }
 
+static bool
+nfs4_wait_on_layoutreturn(struct inode *inode, struct rpc_task *task)
+{
+	if (inode == NULL || !nfs_have_layout(inode))
+		return false;
+
+	return pnfs_wait_on_layoutreturn(inode, task);
+}
+
 struct nfs4_closedata {
 	struct inode *inode;
 	struct nfs4_state *state;
@@ -2763,6 +2785,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		goto out_no_action;
 	}
 
+	if (nfs4_wait_on_layoutreturn(inode, task)) {
+		nfs_release_seqid(calldata->arg.seqid);
+		goto out_wait;
+	}
+
 	if (calldata->arg.fmode == 0)
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
 	if (calldata->roc)
@@ -5308,6 +5335,9 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
 
 	d_data = (struct nfs4_delegreturndata *)data;
 
+	if (nfs4_wait_on_layoutreturn(d_data->inode, task))
+		return;
+
 	if (d_data->roc)
 		pnfs_roc_get_barrier(d_data->inode, &d_data->roc_barrier);
 
@@ -7800,39 +7830,46 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
 				__func__, delay);
 			rpc_delay(task, delay);
-			task->tk_status = 0;
-			rpc_restart_call_prepare(task);
-			goto out; /* Do not call nfs4_async_handle_error() */
+			/* Do not call nfs4_async_handle_error() */
+			goto out_restart;
 		}
 		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
 		spin_lock(&inode->i_lock);
-		lo = NFS_I(inode)->layout;
-		if (!lo || list_empty(&lo->plh_segs)) {
+		if (nfs4_stateid_match(&lgp->args.stateid,
+					&lgp->args.ctx->state->stateid)) {
 			spin_unlock(&inode->i_lock);
 			/* If the open stateid was bad, then recover it. */
 			state = lgp->args.ctx->state;
-		} else {
+			break;
+		}
+		lo = NFS_I(inode)->layout;
+		if (lo && nfs4_stateid_match(&lgp->args.stateid,
+					&lo->plh_stateid)) {
 			LIST_HEAD(head);
 
 			/*
 			 * Mark the bad layout state as invalid, then retry
 			 * with the current stateid.
 			 */
+			set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
 			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
 			spin_unlock(&inode->i_lock);
 			pnfs_free_lseg_list(&head);
-	
-			task->tk_status = 0;
-			rpc_restart_call_prepare(task);
-		}
+		} else
+			spin_unlock(&inode->i_lock);
+		goto out_restart;
 	}
 	if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
-		rpc_restart_call_prepare(task);
+		goto out_restart;
 out:
 	dprintk("<-- %s\n", __func__);
 	return;
+out_restart:
+	task->tk_status = 0;
+	rpc_restart_call_prepare(task);
+	return;
 out_overflow:
 	task->tk_status = -EOVERFLOW;
 	goto out;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index da73bc443238..5db324635e92 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1481,7 +1481,7 @@ restart:
 					spin_unlock(&state->state_lock);
 				}
 				nfs4_put_open_state(state);
-				clear_bit(NFS4CLNT_RECLAIM_NOGRACE,
+				clear_bit(NFS_STATE_RECLAIM_NOGRACE,
 					&state->flags);
 				spin_lock(&sp->so_lock);
 				goto restart;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 7c5718ba625e..fe3ddd20ff89 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -508,7 +508,7 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 	 * for it without upsetting the slab allocator.
 	 */
 	if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
-			sizeof(struct page) > PAGE_SIZE)
+			sizeof(struct page *) > PAGE_SIZE)
 		return 0;
 
 	return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index ba1246433794..8abe27165ad0 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1104,20 +1104,15 @@ bool pnfs_roc(struct inode *ino)
 			mark_lseg_invalid(lseg, &tmp_list);
 			found = true;
 		}
-	/* pnfs_prepare_layoutreturn() grabs lo ref and it will be put
-	 * in pnfs_roc_release(). We don't really send a layoutreturn but
-	 * still want others to view us like we are sending one!
-	 *
-	 * If pnfs_prepare_layoutreturn() fails, it means someone else is doing
-	 * LAYOUTRETURN, so we proceed like there are no layouts to return.
-	 *
-	 * ROC in three conditions:
+	/* ROC in two conditions:
 	 * 1. there are ROC lsegs
 	 * 2. we don't send layoutreturn
-	 * 3. no others are sending layoutreturn
 	 */
-	if (found && !layoutreturn && pnfs_prepare_layoutreturn(lo))
+	if (found && !layoutreturn) {
+		/* lo ref dropped in pnfs_roc_release() */
+		pnfs_get_layout_hdr(lo);
 		roc = true;
+	}
 
 out_noroc:
 	spin_unlock(&ino->i_lock);
@@ -1172,6 +1167,26 @@ void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier)
 	spin_unlock(&ino->i_lock);
 }
 
+bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
+{
+	struct nfs_inode *nfsi = NFS_I(ino);
+        struct pnfs_layout_hdr *lo;
+        bool sleep = false;
+
+	/* we might not have grabbed lo reference. so need to check under
+	 * i_lock */
+        spin_lock(&ino->i_lock);
+        lo = nfsi->layout;
+        if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+                sleep = true;
+        spin_unlock(&ino->i_lock);
+
+        if (sleep)
+                rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+
+        return sleep;
+}
+
 /*
  * Compare two layout segments for sorting into layout cache.
  * We want to preferentially return RW over RO layouts, so ensure those
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 78c9351ff117..d1990e90e7a0 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -270,6 +270,7 @@ bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier);
+bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task);
 void pnfs_set_layoutcommit(struct inode *, struct pnfs_layout_segment *, loff_t);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
@@ -639,6 +640,12 @@ pnfs_roc_get_barrier(struct inode *ino, u32 *barrier)
 {
 }
 
+static inline bool
+pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
+{
+	return false;
+}
+
 static inline void set_pnfs_layoutdriver(struct nfs_server *s,
 					 const struct nfs_fh *mntfh, u32 id)
 {
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index ae0ff7a11b40..01b8cc8e8cfc 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -72,6 +72,9 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_pgio_mirror *mirror;
 
+	if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
+		pgio->pg_ops->pg_cleanup(pgio);
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
 
 	/* read path should never have more than one mirror */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 388f48079c43..72624dc4a623 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1351,6 +1351,9 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_pgio_mirror *mirror;
 
+	if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
+		pgio->pg_ops->pg_cleanup(pgio);
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
 
 	nfs_pageio_stop_mirroring(pgio);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 46b8b2bbc95a..ee5aa4daaea0 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1439,6 +1439,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	int found, ret;
 	int set_maybe;
 	int dispatch_assert = 0;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm))
 		return DLM_MASTER_RESP_NO;
@@ -1658,15 +1659,18 @@ send_response:
 			mlog(ML_ERROR, "failed to dispatch assert master work\n");
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
-		} else
+		} else {
+			dispatched = 1;
 			__dlm_lockres_grab_inflight_worker(dlm, res);
+		}
 		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
 	}
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return response;
 }
 
@@ -2090,7 +2094,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm,
 
 
 	/* queue up work for dlm_assert_master_worker */
-	dlm_grab(dlm);  /* get an extra ref for the work item */
 	dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL);
 	item->u.am.lockres = res; /* already have a ref */
 	/* can optionally ignore node numbers higher than this node */
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index ce12e0b1a31f..3d90ad7ff91f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1694,6 +1694,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	unsigned int hash;
 	int master = DLM_LOCK_RES_OWNER_UNKNOWN;
 	u32 flags = DLM_ASSERT_MASTER_REQUERY;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm)) {
 		/* since the domain has gone away on this
@@ -1719,8 +1720,10 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				dlm_put(dlm);
 				/* sender will take care of this and retry */
 				return ret;
-			} else
+			} else {
+				dispatched = 1;
 				__dlm_lockres_grab_inflight_worker(dlm, res);
+			}
 			spin_unlock(&res->spinlock);
 		} else {
 			/* put.. incase we are not the master */
@@ -1730,7 +1733,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 	spin_unlock(&dlm->spinlock);
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return master;
 }
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f9aeb40a7197..50311703135b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -467,8 +467,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * the fault_*wqh.
 	 */
 	spin_lock(&ctx->fault_pending_wqh.lock);
-	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, &range);
-	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range);
+	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
+	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
 	wake_up_poll(&ctx->fd_wqh, POLLHUP);
@@ -650,10 +650,10 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx,
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/* wake all in the range and autoremove */
 	if (waitqueue_active(&ctx->fault_pending_wqh))
-		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0,
+		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
 				     range);
 	if (waitqueue_active(&ctx->fault_wqh))
-		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, range);
+		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 }
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5a5d79ee256f..d5eb4ad1c534 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
+#include <linux/memcontrol.h>
 #include <linux/blk-cgroup.h>
 #include <linux/backing-dev-defs.h>
 #include <linux/slab.h>
@@ -252,13 +253,19 @@ int inode_congested(struct inode *inode, int cong_bits);
  * @inode: inode of interest
  *
  * cgroup writeback requires support from both the bdi and filesystem.
- * Test whether @inode has both.
+ * Also, both memcg and iocg have to be on the default hierarchy.  Test
+ * whether all conditions are met.
+ *
+ * Note that the test result may change dynamically on the same inode
+ * depending on how memcg and iocg are configured.
  */
 static inline bool inode_cgwb_enabled(struct inode *inode)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
 
-	return bdi_cap_account_dirty(bdi) &&
+	return cgroup_on_dfl(mem_cgroup_root_css->cgroup) &&
+		cgroup_on_dfl(blkcg_root_css->cgroup) &&
+		bdi_cap_account_dirty(bdi) &&
 		(bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
 		(inode->i_sb->s_iflags & SB_I_CGROUPWB);
 }
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4d8fcf2187dc..8492721b39be 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -473,31 +473,8 @@ struct cgroup_subsys {
 	unsigned int depends_on;
 };
 
-extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
-
-/**
- * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_begin() and allows cgroup operations to
- * synchronize against threadgroup changes using a percpu_rw_semaphore.
- */
-static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
-{
-	percpu_down_read(&cgroup_threadgroup_rwsem);
-}
-
-/**
- * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_end().  Counterpart of
- * cgroup_threadcgroup_change_begin().
- */
-static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
-{
-	percpu_up_read(&cgroup_threadgroup_rwsem);
-}
+void cgroup_threadgroup_change_begin(struct task_struct *tsk);
+void cgroup_threadgroup_change_end(struct task_struct *tsk);
 
 #else	/* CONFIG_CGROUPS */
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index d0b380ee7d67..e38681f4912d 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -25,6 +25,13 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
+#ifdef CONFIG_CGROUPS
+#define INIT_GROUP_RWSEM(sig)						\
+	.group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem),
+#else
+#define INIT_GROUP_RWSEM(sig)
+#endif
+
 #ifdef CONFIG_CPUSETS
 #define INIT_CPUSET_SEQ(tsk)							\
 	.mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq),
@@ -57,6 +64,7 @@ extern struct fs_struct init_fs;
 	INIT_PREV_CPUTIME(sig)						\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
+	INIT_GROUP_RWSEM(sig)						\
 }
 
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88a00694eda5..2d15e3831440 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n)
 	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
 	smp_mb__before_atomic();
 	clear_bit(NAPI_STATE_SCHED, &n->state);
+	clear_bit(NAPI_STATE_NPSVC, &n->state);
 }
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 962387a192f1..4a4e3a092337 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -19,6 +19,7 @@
 #include <linux/spinlock.h>
 #include <linux/ethtool.h>
 #include <linux/mii.h>
+#include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/mod_devicetable.h>
@@ -153,6 +154,7 @@ struct sk_buff;
  * PHYs should register using this structure
  */
 struct mii_bus {
+	struct module *owner;
 	const char *name;
 	char id[MII_BUS_ID_SIZE];
 	void *priv;
@@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void)
 	return mdiobus_alloc_size(0);
 }
 
-int mdiobus_register(struct mii_bus *bus);
+int __mdiobus_register(struct mii_bus *bus, struct module *owner);
+#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE)
 void mdiobus_unregister(struct mii_bus *bus);
 void mdiobus_free(struct mii_bus *bus);
 struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv);
@@ -742,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
 				     struct phy_c45_device_ids *c45_ids);
 struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45);
 int phy_device_register(struct phy_device *phy);
+void phy_device_remove(struct phy_device *phydev);
 int phy_init_hw(struct phy_device *phydev);
 int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a4ab9daa387c..b7b9501b41af 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -762,6 +762,18 @@ struct signal_struct {
 	unsigned audit_tty_log_passwd;
 	struct tty_audit_buf *tty_audit_buf;
 #endif
+#ifdef CONFIG_CGROUPS
+	/*
+	 * group_rwsem prevents new tasks from entering the threadgroup and
+	 * member tasks from exiting,a more specifically, setting of
+	 * PF_EXITING.  fork and exit paths are protected with this rwsem
+	 * using threadgroup_change_begin/end().  Users which require
+	 * threadgroup to remain stable should use threadgroup_[un]lock()
+	 * which also takes care of exec path.  Currently, cgroup is the
+	 * only user.
+	 */
+	struct rw_semaphore group_rwsem;
+#endif
 
 	oom_flags_t oom_flags;
 	short oom_score_adj;		/* OOM kill score adjustment */
diff --git a/include/linux/security.h b/include/linux/security.h
index 79d85ddf8093..2f4c1f7aa7db 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -946,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2,
 				      unsigned long arg4,
 				      unsigned long arg5)
 {
-	return cap_task_prctl(option, arg2, arg3, arg3, arg5);
+	return cap_task_prctl(option, arg2, arg3, arg4, arg5);
 }
 
 static inline void security_task_to_inode(struct task_struct *p, struct inode *inode)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2738d355cdf9..2b0a30a6e31c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -179,6 +179,9 @@ struct nf_bridge_info {
 	u8			bridged_dnat:1;
 	__u16			frag_max_size;
 	struct net_device	*physindev;
+
+	/* always valid & non-NULL from FORWARD on, for physdev match */
+	struct net_device	*physoutdev;
 	union {
 		/* prerouting: detect dnat in orig/reply direction */
 		__be32          ipv4_daddr;
@@ -189,9 +192,6 @@ struct nf_bridge_info {
 		 * skb is out in neigh layer.
 		 */
 		char neigh_header[8];
-
-		/* always valid & non-NULL from FORWARD on, for physdev match */
-		struct net_device *physoutdev;
 	};
 };
 #endif
@@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 {
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
+	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		 skb_checksum_start_offset(skb) <= len)
+		skb->ip_summed = CHECKSUM_NONE;
 }
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 269e8afd3e2a..6b00f18f5e6b 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -34,7 +34,7 @@ extern struct bus_type spi_bus_type;
 
 /**
  * struct spi_statistics - statistics for spi transfers
- * @clock:         lock protecting this structure
+ * @lock:          lock protecting this structure
  *
  * @messages:      number of spi-messages handled
  * @transfers:     number of spi_transfers handled
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 7591788e9fbf..357e44c1a46b 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -42,6 +42,7 @@ struct sock_xprt {
 	/*
 	 * Connection of transports
 	 */
+	unsigned long		sock_state;
 	struct delayed_work	connect_worker;
 	struct sockaddr_storage	srcaddr;
 	unsigned short		srcport;
@@ -76,6 +77,8 @@ struct sock_xprt {
  */
 #define TCP_RPC_REPLY		(1UL << 6)
 
+#define XPRT_SOCK_CONNECTING	1U
+
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_SUNRPC_XPRTSOCK_H */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 17292fee8686..157d366e761b 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -360,7 +360,7 @@ static inline struct thermal_zone_device *
 thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
 				const struct thermal_zone_of_device_ops *ops)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 static inline
@@ -380,6 +380,8 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
 
 int power_actor_get_max_power(struct thermal_cooling_device *,
 			      struct thermal_zone_device *tz, u32 *max_power);
+int power_actor_get_min_power(struct thermal_cooling_device *,
+			      struct thermal_zone_device *tz, u32 *min_power);
 int power_actor_set_power(struct thermal_cooling_device *,
 			  struct thermal_instance *, u32);
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
@@ -415,6 +417,10 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
 static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev,
 			      struct thermal_zone_device *tz, u32 *max_power)
 { return 0; }
+static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev,
+					    struct thermal_zone_device *tz,
+					    u32 *min_power)
+{ return -ENODEV; }
 static inline int power_actor_set_power(struct thermal_cooling_device *cdev,
 			  struct thermal_instance *tz, u32 power)
 { return 0; }
diff --git a/include/linux/wait.h b/include/linux/wait.h
index d3d077228d4c..1e1bf9f963a9 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 
 typedef int wait_bit_action_f(struct wait_bit_key *);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
-			  void *key);
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up_poll(x, m)						\
 	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
 #define wake_up_locked_poll(x, m)					\
-	__wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m))
+	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
 #define wake_up_interruptible_poll(x, m)				\
 	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
 #define wake_up_interruptible_sync_poll(x, m)				\
diff --git a/include/net/flow.h b/include/net/flow.h
index acd6a096250e..9b85db85f13c 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -35,6 +35,7 @@ struct flowi_common {
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_KNOWN_NH		0x02
 #define FLOWI_FLAG_VRFSRC		0x04
+#define FLOWI_FLAG_SKIP_NH_OIF		0x08
 	__u32	flowic_secid;
 	struct flowi_tunnel flowic_tun_key;
 };
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 879d6e5a973b..186f3a1e1b1f 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -110,7 +110,19 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 			   struct inet_hashinfo *hashinfo);
 
-void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo);
+void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
+			  bool rearm);
+
+static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
+{
+	__inet_twsk_schedule(tw, timeo, false);
+}
+
+static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
+{
+	__inet_twsk_schedule(tw, timeo, true);
+}
+
 void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
 
 void inet_twsk_purge(struct inet_hashinfo *hashinfo,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 063d30474cf6..aaf9700fc9e5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -275,7 +275,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	     struct nl_info *info, struct mx6_config *mxc);
 int fib6_del(struct rt6_info *rt, struct nl_info *info);
 
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info);
+void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
+		     unsigned int flags);
 
 void fib6_run_gc(unsigned long expires, struct net *net, bool force);
 
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index b8529aa1dae7..fa915fa0f703 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -32,6 +32,12 @@ struct __ip6_tnl_parm {
 	__be32			o_key;
 };
 
+struct ip6_tnl_dst {
+	seqlock_t lock;
+	struct dst_entry __rcu *dst;
+	u32 cookie;
+};
+
 /* IPv6 tunnel */
 struct ip6_tnl {
 	struct ip6_tnl __rcu *next;	/* next tunnel in list */
@@ -39,8 +45,7 @@ struct ip6_tnl {
 	struct net *net;	/* netns for packet i/o */
 	struct __ip6_tnl_parm parms;	/* tunnel configuration parameters */
 	struct flowi fl;	/* flowi template for xmit */
-	struct dst_entry *dst_cache;    /* cached dst */
-	u32 dst_cookie;
+	struct ip6_tnl_dst __percpu *dst_cache;	/* cached dst */
 
 	int err_count;
 	unsigned long err_time;
@@ -60,9 +65,11 @@ struct ipv6_tlv_tnl_enc_lim {
 	__u8 encap_limit;	/* tunnel encapsulation limit   */
 } __packed;
 
-struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t);
+struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t);
+int ip6_tnl_dst_init(struct ip6_tnl *t);
+void ip6_tnl_dst_destroy(struct ip6_tnl *t);
 void ip6_tnl_dst_reset(struct ip6_tnl *t);
-void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst);
+void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst);
 int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
 		const struct in6_addr *raddr);
 int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
@@ -79,7 +86,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	struct net_device_stats *stats = &dev->stats;
 	int pkt_len, err;
 
-	pkt_len = skb->len;
+	pkt_len = skb->len - skb_inner_network_offset(skb);
 	err = ip6_local_out_sk(sk, skb);
 
 	if (net_xmit_eval(err) == 0) {
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a37d0432bebd..727d6e9a9685 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -236,8 +236,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 	rcu_read_lock();
 
 	tb = fib_get_table(net, RT_TABLE_MAIN);
-	if (tb && !fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF))
-		err = 0;
+	if (tb)
+		err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF);
+
+	if (err == -EAGAIN)
+		err = -ENETUNREACH;
 
 	rcu_read_unlock();
 
@@ -258,7 +261,7 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 			     struct fib_result *res, unsigned int flags)
 {
 	struct fib_table *tb;
-	int err;
+	int err = -ENETUNREACH;
 
 	flags |= FIB_LOOKUP_NOREF;
 	if (net->ipv4.fib_has_custom_rules)
@@ -268,15 +271,20 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 
 	res->tclassid = 0;
 
-	for (err = 0; !err; err = -ENETUNREACH) {
-		tb = rcu_dereference_rtnl(net->ipv4.fib_main);
-		if (tb && !fib_table_lookup(tb, flp, res, flags))
-			break;
+	tb = rcu_dereference_rtnl(net->ipv4.fib_main);
+	if (tb)
+		err = fib_table_lookup(tb, flp, res, flags);
+
+	if (!err)
+		goto out;
+
+	tb = rcu_dereference_rtnl(net->ipv4.fib_default);
+	if (tb)
+		err = fib_table_lookup(tb, flp, res, flags);
 
-		tb = rcu_dereference_rtnl(net->ipv4.fib_default);
-		if (tb && !fib_table_lookup(tb, flp, res, flags))
-			break;
-	}
+out:
+	if (err == -EAGAIN)
+		err = -ENETUNREACH;
 
 	rcu_read_unlock();
 
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 9a6a3ba888e8..f6dafec9102c 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -276,6 +276,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
 int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, u8 proto,
 		  u8 tos, u8 ttl, __be16 df, bool xnet);
+struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
+					     gfp_t flags);
 
 struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
 					 int gso_type_mask);
diff --git a/include/net/route.h b/include/net/route.h
index cc61cb95f059..f46af256880c 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -255,7 +255,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
 	if (netif_index_is_vrf(sock_net(sk), oif))
-		flow_flags |= FLOWI_FLAG_VRFSRC;
+		flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF;
 
 	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
 			   protocol, flow_flags, dst, src, dport, sport);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index ac9bf1c0e42d..5f48754dc36a 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -730,6 +730,7 @@ struct se_device {
 #define DF_EMULATED_VPD_UNIT_SERIAL		0x00000004
 #define DF_USING_UDEV_PATH			0x00000008
 #define DF_USING_ALIAS				0x00000010
+#define DF_READ_ONLY				0x00000020
 	/* Physical device queue depth */
 	u32			queue_depth;
 	/* Used for SPC-2 reservations enforce of ISIDs */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8da542a2874d..ee124009e12a 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -709,17 +709,19 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
 __SYSCALL(__NR_bpf, sys_bpf)
 #define __NR_execveat 281
 __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
-#define __NR_membarrier 282
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
 __SYSCALL(__NR_membarrier, sys_membarrier)
 
 #undef __NR_syscalls
-#define __NR_syscalls 283
+#define __NR_syscalls 284
 
 /*
  * All syscalls below here should go away really,
  * these are provided for both review and as a porting
  * help for the C library version.
-*
+ *
  * Last chance: are any of these important enough to
  * enable by default?
  */
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
index 34141a5dfe74..f8b01887a495 100644
--- a/include/uapi/linux/lwtunnel.h
+++ b/include/uapi/linux/lwtunnel.h
@@ -21,8 +21,6 @@ enum lwtunnel_ip_t {
 	LWTUNNEL_IP_SRC,
 	LWTUNNEL_IP_TTL,
 	LWTUNNEL_IP_TOS,
-	LWTUNNEL_IP_SPORT,
-	LWTUNNEL_IP_DPORT,
 	LWTUNNEL_IP_FLAGS,
 	__LWTUNNEL_IP_MAX,
 };
@@ -36,8 +34,6 @@ enum lwtunnel_ip6_t {
 	LWTUNNEL_IP6_SRC,
 	LWTUNNEL_IP6_HOPLIMIT,
 	LWTUNNEL_IP6_TC,
-	LWTUNNEL_IP6_SPORT,
-	LWTUNNEL_IP6_DPORT,
 	LWTUNNEL_IP6_FLAGS,
 	__LWTUNNEL_IP6_MAX,
 };
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2cf0f79f1fc9..2c9eae6ad970 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -46,7 +46,6 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/rwsem.h>
-#include <linux/percpu-rwsem.h>
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
@@ -104,8 +103,6 @@ static DEFINE_SPINLOCK(cgroup_idr_lock);
  */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
-struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
-
 #define cgroup_assert_mutex_or_rcu_locked()				\
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
 			   !lockdep_is_held(&cgroup_mutex),		\
@@ -874,6 +871,48 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	return cset;
 }
 
+void cgroup_threadgroup_change_begin(struct task_struct *tsk)
+{
+	down_read(&tsk->signal->group_rwsem);
+}
+
+void cgroup_threadgroup_change_end(struct task_struct *tsk)
+{
+	up_read(&tsk->signal->group_rwsem);
+}
+
+/**
+ * threadgroup_lock - lock threadgroup
+ * @tsk: member task of the threadgroup to lock
+ *
+ * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
+ * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
+ * change ->group_leader/pid.  This is useful for cases where the threadgroup
+ * needs to stay stable across blockable operations.
+ *
+ * fork and exit explicitly call threadgroup_change_{begin|end}() for
+ * synchronization.  While held, no new task will be added to threadgroup
+ * and no existing live task will have its PF_EXITING set.
+ *
+ * de_thread() does threadgroup_change_{begin|end}() when a non-leader
+ * sub-thread becomes a new leader.
+ */
+static void threadgroup_lock(struct task_struct *tsk)
+{
+	down_write(&tsk->signal->group_rwsem);
+}
+
+/**
+ * threadgroup_unlock - unlock threadgroup
+ * @tsk: member task of the threadgroup to unlock
+ *
+ * Reverse threadgroup_lock().
+ */
+static inline void threadgroup_unlock(struct task_struct *tsk)
+{
+	up_write(&tsk->signal->group_rwsem);
+}
+
 static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
 	struct cgroup *root_cgrp = kf_root->kn->priv;
@@ -2074,9 +2113,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 	lockdep_assert_held(&css_set_rwsem);
 
 	/*
-	 * We are synchronized through cgroup_threadgroup_rwsem against
-	 * PF_EXITING setting such that we can't race against cgroup_exit()
-	 * changing the css_set to init_css_set and dropping the old one.
+	 * We are synchronized through threadgroup_lock() against PF_EXITING
+	 * setting such that we can't race against cgroup_exit() changing the
+	 * css_set to init_css_set and dropping the old one.
 	 */
 	WARN_ON_ONCE(tsk->flags & PF_EXITING);
 	old_cset = task_css_set(tsk);
@@ -2133,11 +2172,10 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
  * @src_cset and add it to @preloaded_csets, which should later be cleaned
  * up by cgroup_migrate_finish().
  *
- * This function may be called without holding cgroup_threadgroup_rwsem
- * even if the target is a process.  Threads may be created and destroyed
- * but as long as cgroup_mutex is not dropped, no new css_set can be put
- * into play and the preloaded css_sets are guaranteed to cover all
- * migrations.
+ * This function may be called without holding threadgroup_lock even if the
+ * target is a process.  Threads may be created and destroyed but as long
+ * as cgroup_mutex is not dropped, no new css_set can be put into play and
+ * the preloaded css_sets are guaranteed to cover all migrations.
  */
 static void cgroup_migrate_add_src(struct css_set *src_cset,
 				   struct cgroup *dst_cgrp,
@@ -2240,7 +2278,7 @@ err:
  * @threadgroup: whether @leader points to the whole process or a single task
  *
  * Migrate a process or task denoted by @leader to @cgrp.  If migrating a
- * process, the caller must be holding cgroup_threadgroup_rwsem.  The
+ * process, the caller must be holding threadgroup_lock of @leader.  The
  * caller is also responsible for invoking cgroup_migrate_add_src() and
  * cgroup_migrate_prepare_dst() on the targets before invoking this
  * function and following up with cgroup_migrate_finish().
@@ -2368,7 +2406,7 @@ out_release_tset:
  * @leader: the task or the leader of the threadgroup to be attached
  * @threadgroup: attach the whole threadgroup?
  *
- * Call holding cgroup_mutex and cgroup_threadgroup_rwsem.
+ * Call holding cgroup_mutex and threadgroup_lock of @leader.
  */
 static int cgroup_attach_task(struct cgroup *dst_cgrp,
 			      struct task_struct *leader, bool threadgroup)
@@ -2460,13 +2498,14 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	if (!cgrp)
 		return -ENODEV;
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+retry_find_task:
 	rcu_read_lock();
 	if (pid) {
 		tsk = find_task_by_vpid(pid);
 		if (!tsk) {
+			rcu_read_unlock();
 			ret = -ESRCH;
-			goto out_unlock_rcu;
+			goto out_unlock_cgroup;
 		}
 	} else {
 		tsk = current;
@@ -2482,23 +2521,37 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	 */
 	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
-		goto out_unlock_rcu;
+		rcu_read_unlock();
+		goto out_unlock_cgroup;
 	}
 
 	get_task_struct(tsk);
 	rcu_read_unlock();
 
+	threadgroup_lock(tsk);
+	if (threadgroup) {
+		if (!thread_group_leader(tsk)) {
+			/*
+			 * a race with de_thread from another thread's exec()
+			 * may strip us of our leadership, if this happens,
+			 * there is no choice but to throw this task away and
+			 * try again; this is
+			 * "double-double-toil-and-trouble-check locking".
+			 */
+			threadgroup_unlock(tsk);
+			put_task_struct(tsk);
+			goto retry_find_task;
+		}
+	}
+
 	ret = cgroup_procs_write_permission(tsk, cgrp, of);
 	if (!ret)
 		ret = cgroup_attach_task(cgrp, tsk, threadgroup);
 
-	put_task_struct(tsk);
-	goto out_unlock_threadgroup;
+	threadgroup_unlock(tsk);
 
-out_unlock_rcu:
-	rcu_read_unlock();
-out_unlock_threadgroup:
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	put_task_struct(tsk);
+out_unlock_cgroup:
 	cgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
 }
@@ -2643,8 +2696,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
-
 	/* look up all csses currently attached to @cgrp's subtree */
 	down_read(&css_set_rwsem);
 	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
@@ -2700,8 +2751,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 				goto out_finish;
 			last_task = task;
 
+			threadgroup_lock(task);
+			/* raced against de_thread() from another thread? */
+			if (!thread_group_leader(task)) {
+				threadgroup_unlock(task);
+				put_task_struct(task);
+				continue;
+			}
+
 			ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
 
+			threadgroup_unlock(task);
 			put_task_struct(task);
 
 			if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
@@ -2711,7 +2771,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 out_finish:
 	cgroup_migrate_finish(&preloaded_csets);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
 	return ret;
 }
 
@@ -5024,7 +5083,6 @@ int __init cgroup_init(void)
 	unsigned long key;
 	int ssid, err;
 
-	BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 7d5f0f118a63..2845623fb582 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1149,6 +1149,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	tty_audit_fork(sig);
 	sched_autogroup_fork(sig);
 
+#ifdef CONFIG_CGROUPS
+	init_rwsem(&sig->group_rwsem);
+#endif
+
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 272d9322bc5d..052e02672d12 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -106,10 +106,9 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
-			  void *key)
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
 {
-	__wake_up_common(q, mode, nr, 0, key);
+	__wake_up_common(q, mode, 1, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
@@ -284,7 +283,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
 	if (!list_empty(&wait->task_list))
 		list_del_init(&wait->task_list);
 	else if (waitqueue_active(q))
-		__wake_up_locked_key(q, mode, 1, key);
+		__wake_up_locked_key(q, mode, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(abort_exclusive_wait);
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
index ff19f66d3f7f..b1c93e94ca7a 100644
--- a/lib/iommu-common.c
+++ b/lib/iommu-common.c
@@ -21,8 +21,7 @@ static	DEFINE_PER_CPU(unsigned int, iommu_hash_common);
 
 static inline bool need_flush(struct iommu_map_table *iommu)
 {
-	return (iommu->lazy_flush != NULL &&
-		(iommu->flags & IOMMU_NEED_FLUSH) != 0);
+	return ((iommu->flags & IOMMU_NEED_FLUSH) != 0);
 }
 
 static inline void set_flush(struct iommu_map_table *iommu)
@@ -211,7 +210,8 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 			goto bail;
 		}
 	}
-	if (n < pool->hint || need_flush(iommu)) {
+	if (iommu->lazy_flush &&
+	    (n < pool->hint || need_flush(iommu))) {
 		clear_flush(iommu);
 		iommu->lazy_flush(iommu);
 	}
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index cc0c69710dcf..a54ff8949f91 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -187,10 +187,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
 	head = rht_dereference_bucket(new_tbl->buckets[new_hash],
 				      new_tbl, new_hash);
 
-	if (rht_is_a_nulls(head))
-		INIT_RHT_NULLS_HEAD(entry->next, ht, new_hash);
-	else
-		RCU_INIT_POINTER(entry->next, head);
+	RCU_INIT_POINTER(entry->next, head);
 
 	rcu_assign_pointer(new_tbl->buckets[new_hash], entry);
 	spin_unlock(new_bucket_lock);
diff --git a/mm/migrate.c b/mm/migrate.c
index c3cb566af3e2..7452a00bbb50 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1075,7 +1075,7 @@ out:
 	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
 		put_new_page(new_hpage, private);
 	else
-		put_page(new_hpage);
+		putback_active_hugepage(new_hpage);
 
 	if (result) {
 		if (rc)
diff --git a/mm/mmap.c b/mm/mmap.c
index c739d6db7193..79bcc9f92e48 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1490,13 +1490,14 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 int vma_wants_writenotify(struct vm_area_struct *vma)
 {
 	vm_flags_t vm_flags = vma->vm_flags;
+	const struct vm_operations_struct *vm_ops = vma->vm_ops;
 
 	/* If it was private or non-writable, the write bit is already clear */
 	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
 		return 0;
 
 	/* The backer wishes to know when pages are first written to? */
-	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+	if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite))
 		return 1;
 
 	/* The open routine did something to the protections that pgprot_modify
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2d978b28a410..7f63a9381f71 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -175,7 +175,7 @@ static bool sane_reclaim(struct scan_control *sc)
 	if (!memcg)
 		return true;
 #ifdef CONFIG_CGROUP_WRITEBACK
-	if (memcg->css.cgroup)
+	if (cgroup_on_dfl(memcg->css.cgroup))
 		return true;
 #endif
 	return false;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 17e55dfecbe2..e07f551a863c 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -317,6 +317,9 @@ static int clip_constructor(struct neighbour *neigh)
 
 static int clip_encap(struct atm_vcc *vcc, int mode)
 {
+	if (!CLIP_VCC(vcc))
+		return -EBADFD;
+
 	CLIP_VCC(vcc)->encap = mode;
 	return 0;
 }
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index ad82324f710f..0510a577a7b5 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2311,12 +2311,6 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 	if (!conn)
 		return 1;
 
-	chan = conn->smp;
-	if (!chan) {
-		BT_ERR("SMP security requested but not available");
-		return 1;
-	}
-
 	if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED))
 		return 1;
 
@@ -2330,6 +2324,12 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 		if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
 			return 0;
 
+	chan = conn->smp;
+	if (!chan) {
+		BT_ERR("SMP security requested but not available");
+		return 1;
+	}
+
 	l2cap_chan_lock(chan);
 
 	/* If SMP is already in progress ignore this request */
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 66efdc21f548..480b3de1a0e3 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1006,7 +1006,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 
 	ih = igmpv3_report_hdr(skb);
 	num = ntohs(ih->ngrec);
-	len = sizeof(*ih);
+	len = skb_transport_offset(skb) + sizeof(*ih);
 
 	for (i = 0; i < num; i++) {
 		len += sizeof(*grec);
@@ -1067,7 +1067,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 	icmp6h = icmp6_hdr(skb);
 	num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
-	len = sizeof(*icmp6h);
+	len = skb_transport_offset(skb) + sizeof(*icmp6h);
 
 	for (i = 0; i < num; i++) {
 		__be16 *nsrcs, _nsrcs;
diff --git a/net/core/dev.c b/net/core/dev.c
index 877c84834d81..6bb6470f5b7b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4713,6 +4713,8 @@ void napi_disable(struct napi_struct *n)
 
 	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
 		msleep(1);
+	while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state))
+		msleep(1);
 
 	hrtimer_cancel(&n->timer);
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index bf77e3639ce0..365de66436ac 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -631,15 +631,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	int idx = 0;
 	struct fib_rule *rule;
+	int err = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 		if (idx < cb->args[1])
 			goto skip;
 
-		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
-				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
-				     NLM_F_MULTI, ops) < 0)
+		err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, RTM_NEWRULE,
+				       NLM_F_MULTI, ops);
+		if (err)
 			break;
 skip:
 		idx++;
@@ -648,7 +650,7 @@ skip:
 	cb->args[1] = idx;
 	rules_ops_put(ops);
 
-	return skb->len;
+	return err;
 }
 
 static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -664,7 +666,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ops == NULL)
 			return -EAFNOSUPPORT;
 
-		return dump_rules(skb, cb, ops);
+		dump_rules(skb, cb, ops);
+
+		return skb->len;
 	}
 
 	rcu_read_lock();
diff --git a/net/core/filter.c b/net/core/filter.c
index 13079f03902e..05a04ea87172 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -478,9 +478,9 @@ do_pass:
 				bpf_src = BPF_X;
 			} else {
 				insn->dst_reg = BPF_REG_A;
-				insn->src_reg = BPF_REG_X;
 				insn->imm = fp->k;
 				bpf_src = BPF_SRC(fp->code);
+				insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0;
 			}
 
 			/* Common case where 'jump_false' is next insn. */
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index b279077c3089..805a95a48107 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1481,6 +1481,15 @@ static int of_dev_node_match(struct device *dev, const void *data)
 	return ret == 0 ? dev->of_node == data : ret;
 }
 
+/*
+ * of_find_net_device_by_node - lookup the net device for the device node
+ * @np: OF device node
+ *
+ * Looks up the net_device structure corresponding with the device node.
+ * If successful, returns a pointer to the net_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure. The
+ * refcount must be dropped when done with the net_device.
+ */
 struct net_device *of_find_net_device_by_node(struct device_node *np)
 {
 	struct device *dev;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 6aa3db8dfc3b..8bdada242a7d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -142,7 +142,7 @@ static void queue_process(struct work_struct *work)
  */
 static int poll_one_napi(struct napi_struct *napi, int budget)
 {
-	int work;
+	int work = 0;
 
 	/* net_rx_action's ->poll() invocations and our's are
 	 * synchronized by this test which is only made while
@@ -151,7 +151,12 @@ static int poll_one_napi(struct napi_struct *napi, int budget)
 	if (!test_bit(NAPI_STATE_SCHED, &napi->state))
 		return budget;
 
-	set_bit(NAPI_STATE_NPSVC, &napi->state);
+	/* If we set this bit but see that it has already been set,
+	 * that indicates that napi has been disabled and we need
+	 * to abort this operation
+	 */
+	if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state))
+		goto out;
 
 	work = napi->poll(napi, budget);
 	WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
@@ -159,6 +164,7 @@ static int poll_one_napi(struct napi_struct *napi, int budget)
 
 	clear_bit(NAPI_STATE_NPSVC, &napi->state);
 
+out:
 	return budget - work;
 }
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a466821d1441..0ec48403ed68 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3047,6 +3047,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 	u32 portid = NETLINK_CB(cb->skb).portid;
 	u32 seq = cb->nlh->nlmsg_seq;
 	u32 filter_mask = 0;
+	int err;
 
 	if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) {
 		struct nlattr *extfilt;
@@ -3067,20 +3068,25 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 
 		if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
-			if (idx >= cb->args[0] &&
-			    br_dev->netdev_ops->ndo_bridge_getlink(
-				    skb, portid, seq, dev, filter_mask,
-				    NLM_F_MULTI) < 0)
-				break;
+			if (idx >= cb->args[0]) {
+				err = br_dev->netdev_ops->ndo_bridge_getlink(
+						skb, portid, seq, dev,
+						filter_mask, NLM_F_MULTI);
+				if (err < 0 && err != -EOPNOTSUPP)
+					break;
+			}
 			idx++;
 		}
 
 		if (ops->ndo_bridge_getlink) {
-			if (idx >= cb->args[0] &&
-			    ops->ndo_bridge_getlink(skb, portid, seq, dev,
-						    filter_mask,
-						    NLM_F_MULTI) < 0)
-				break;
+			if (idx >= cb->args[0]) {
+				err = ops->ndo_bridge_getlink(skb, portid,
+							      seq, dev,
+							      filter_mask,
+							      NLM_F_MULTI);
+				if (err < 0 && err != -EOPNOTSUPP)
+					break;
+			}
 			idx++;
 		}
 	}
diff --git a/net/core/sock.c b/net/core/sock.c
index ca2984afe16e..3307c02244d3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2740,10 +2740,8 @@ static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 		return;
 	kfree(rsk_prot->slab_name);
 	rsk_prot->slab_name = NULL;
-	if (rsk_prot->slab) {
-		kmem_cache_destroy(rsk_prot->slab);
-		rsk_prot->slab = NULL;
-	}
+	kmem_cache_destroy(rsk_prot->slab);
+	rsk_prot->slab = NULL;
 }
 
 static int req_prot_init(const struct proto *prot)
@@ -2828,10 +2826,8 @@ void proto_unregister(struct proto *prot)
 	list_del(&prot->node);
 	mutex_unlock(&proto_list_mutex);
 
-	if (prot->slab != NULL) {
-		kmem_cache_destroy(prot->slab);
-		prot->slab = NULL;
-	}
+	kmem_cache_destroy(prot->slab);
+	prot->slab = NULL;
 
 	req_prot_cleanup(prot->rsk_prot);
 
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
index bd9e718c2a20..3de0d0362d7f 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -398,12 +398,8 @@ out_err:
 
 void dccp_ackvec_exit(void)
 {
-	if (dccp_ackvec_slab != NULL) {
-		kmem_cache_destroy(dccp_ackvec_slab);
-		dccp_ackvec_slab = NULL;
-	}
-	if (dccp_ackvec_record_slab != NULL) {
-		kmem_cache_destroy(dccp_ackvec_record_slab);
-		dccp_ackvec_record_slab = NULL;
-	}
+	kmem_cache_destroy(dccp_ackvec_slab);
+	dccp_ackvec_slab = NULL;
+	kmem_cache_destroy(dccp_ackvec_record_slab);
+	dccp_ackvec_record_slab = NULL;
 }
diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c
index 83498975165f..90f77d08cc37 100644
--- a/net/dccp/ccid.c
+++ b/net/dccp/ccid.c
@@ -95,8 +95,7 @@ static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_f
 
 static void ccid_kmem_cache_destroy(struct kmem_cache *slab)
 {
-	if (slab != NULL)
-		kmem_cache_destroy(slab);
+	kmem_cache_destroy(slab);
 }
 
 static int __init ccid_activate(struct ccid_operations *ccid_ops)
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 30addee2dd03..838f524cf11a 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -48,8 +48,6 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 			tw->tw_ipv6only = sk->sk_ipv6only;
 		}
 #endif
-		/* Linkage updates. */
-		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 
 		/* Get the TIME_WAIT timeout firing. */
 		if (timeo < rto)
@@ -60,6 +58,8 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 			timeo = DCCP_TIMEWAIT_LEN;
 
 		inet_twsk_schedule(tw, timeo);
+		/* Linkage updates. */
+		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 		inet_twsk_put(tw);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 76e3800765f8..c59fa5d9c22c 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -634,6 +634,10 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
 			port_index++;
 		}
 		kfree(pd->chip[i].rtable);
+
+		/* Drop our reference to the MDIO bus device */
+		if (pd->chip[i].host_dev)
+			put_device(pd->chip[i].host_dev);
 	}
 	kfree(pd->chip);
 }
@@ -661,16 +665,22 @@ static int dsa_of_probe(struct device *dev)
 		return -EPROBE_DEFER;
 
 	ethernet = of_parse_phandle(np, "dsa,ethernet", 0);
-	if (!ethernet)
-		return -EINVAL;
+	if (!ethernet) {
+		ret = -EINVAL;
+		goto out_put_mdio;
+	}
 
 	ethernet_dev = of_find_net_device_by_node(ethernet);
-	if (!ethernet_dev)
-		return -EPROBE_DEFER;
+	if (!ethernet_dev) {
+		ret = -EPROBE_DEFER;
+		goto out_put_mdio;
+	}
 
 	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
-	if (!pd)
-		return -ENOMEM;
+	if (!pd) {
+		ret = -ENOMEM;
+		goto out_put_ethernet;
+	}
 
 	dev->platform_data = pd;
 	pd->of_netdev = ethernet_dev;
@@ -691,7 +701,9 @@ static int dsa_of_probe(struct device *dev)
 		cd = &pd->chip[chip_index];
 
 		cd->of_node = child;
-		cd->host_dev = &mdio_bus->dev;
+
+		/* When assigning the host device, increment its refcount */
+		cd->host_dev = get_device(&mdio_bus->dev);
 
 		sw_addr = of_get_property(child, "reg", NULL);
 		if (!sw_addr)
@@ -711,6 +723,12 @@ static int dsa_of_probe(struct device *dev)
 				ret = -EPROBE_DEFER;
 				goto out_free_chip;
 			}
+
+			/* Drop the mdio_bus device ref, replacing the host
+			 * device with the mdio_bus_switch device, keeping
+			 * the refcount from of_mdio_find_bus() above.
+			 */
+			put_device(cd->host_dev);
 			cd->host_dev = &mdio_bus_switch->dev;
 		}
 
@@ -744,6 +762,10 @@ static int dsa_of_probe(struct device *dev)
 		}
 	}
 
+	/* The individual chips hold their own refcount on the mdio bus,
+	 * so drop ours */
+	put_device(&mdio_bus->dev);
+
 	return 0;
 
 out_free_chip:
@@ -751,6 +773,10 @@ out_free_chip:
 out_free:
 	kfree(pd);
 	dev->platform_data = NULL;
+out_put_ethernet:
+	put_device(&ethernet_dev->dev);
+out_put_mdio:
+	put_device(&mdio_bus->dev);
 	return ret;
 }
 
@@ -762,6 +788,7 @@ static void dsa_of_remove(struct device *dev)
 		return;
 
 	dsa_of_free_platform_data(pd);
+	put_device(&pd->of_netdev->dev);
 	kfree(pd);
 }
 #else
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index d25efc93d8f1..b6ca0890d018 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -78,7 +78,7 @@ static int trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	trailer = skb_tail_pointer(skb) - 4;
 	if (trailer[0] != 0x80 || (trailer[1] & 0xf8) != 0x00 ||
-	    (trailer[3] & 0xef) != 0x00 || trailer[3] != 0x00)
+	    (trailer[2] & 0xef) != 0x00 || trailer[3] != 0x00)
 		goto out_drop;
 
 	source_port = trailer[1] & 7;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 30409b75e925..f03db8b7abee 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -113,6 +113,8 @@
 #include <net/arp.h>
 #include <net/ax25.h>
 #include <net/netrom.h>
+#include <net/dst_metadata.h>
+#include <net/ip_tunnels.h>
 
 #include <linux/uaccess.h>
 
@@ -296,7 +298,8 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip,
 			 struct net_device *dev, __be32 src_ip,
 			 const unsigned char *dest_hw,
 			 const unsigned char *src_hw,
-			 const unsigned char *target_hw, struct sk_buff *oskb)
+			 const unsigned char *target_hw,
+			 struct dst_entry *dst)
 {
 	struct sk_buff *skb;
 
@@ -309,9 +312,7 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip,
 	if (!skb)
 		return;
 
-	if (oskb)
-		skb_dst_copy(skb, oskb);
-
+	skb_dst_set(skb, dst);
 	arp_xmit(skb);
 }
 
@@ -333,6 +334,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
 	__be32 target = *(__be32 *)neigh->primary_key;
 	int probes = atomic_read(&neigh->probes);
 	struct in_device *in_dev;
+	struct dst_entry *dst = NULL;
 
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(dev);
@@ -381,9 +383,10 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
 		}
 	}
 
+	if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE))
+		dst = dst_clone(skb_dst(skb));
 	arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr,
-		     dst_hw, dev->dev_addr, NULL,
-		     dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb);
+		     dst_hw, dev->dev_addr, NULL, dst);
 }
 
 static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)
@@ -649,6 +652,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb)
 	int addr_type;
 	struct neighbour *n;
 	struct net *net = dev_net(dev);
+	struct dst_entry *reply_dst = NULL;
 	bool is_garp = false;
 
 	/* arp_rcv below verifies the ARP header and verifies the device
@@ -749,13 +753,18 @@ static int arp_process(struct sock *sk, struct sk_buff *skb)
  *  cache.
  */
 
+	if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb))
+		reply_dst = (struct dst_entry *)
+			    iptunnel_metadata_reply(skb_metadata_dst(skb),
+						    GFP_ATOMIC);
+
 	/* Special case: IPv4 duplicate address detection packet (RFC2131) */
 	if (sip == 0) {
 		if (arp->ar_op == htons(ARPOP_REQUEST) &&
 		    inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL &&
 		    !arp_ignore(in_dev, sip, tip))
-			arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
-				 dev->dev_addr, sha);
+			arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip,
+				     sha, dev->dev_addr, sha, reply_dst);
 		goto out;
 	}
 
@@ -774,9 +783,10 @@ static int arp_process(struct sock *sk, struct sk_buff *skb)
 			if (!dont_send) {
 				n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
 				if (n) {
-					arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
-						 dev, tip, sha, dev->dev_addr,
-						 sha);
+					arp_send_dst(ARPOP_REPLY, ETH_P_ARP,
+						     sip, dev, tip, sha,
+						     dev->dev_addr, sha,
+						     reply_dst);
 					neigh_release(n);
 				}
 			}
@@ -794,9 +804,10 @@ static int arp_process(struct sock *sk, struct sk_buff *skb)
 				if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED ||
 				    skb->pkt_type == PACKET_HOST ||
 				    NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) {
-					arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
-						 dev, tip, sha, dev->dev_addr,
-						 sha);
+					arp_send_dst(ARPOP_REPLY, ETH_P_ARP,
+						     sip, dev, tip, sha,
+						     dev->dev_addr, sha,
+						     reply_dst);
 				} else {
 					pneigh_enqueue(&arp_tbl,
 						       in_dev->arp_parms, skb);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 26d6ffb6d23c..6c2af797f2f9 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1426,7 +1426,7 @@ found:
 			    nh->nh_flags & RTNH_F_LINKDOWN &&
 			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
 				continue;
-			if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) {
+			if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
 				if (flp->flowi4_oif &&
 				    flp->flowi4_oif != nh->nh_oif)
 					continue;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 79fe05befcae..e5eb8ac4089d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
-	fl4.flowi4_oif = vrf_master_ifindex(skb->dev) ? : skb->dev->ifindex;
+	fl4.flowi4_oif = vrf_master_ifindex(skb->dev);
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
@@ -461,7 +461,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
 	fl4->fl4_icmp_code = code;
-	fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev) ? : skb_in->dev->ifindex;
+	fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
 	rt = __ip_route_output_key(net, fl4);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 134957159c27..7bb9c39e0a4d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -685,20 +685,20 @@ void reqsk_queue_hash_req(struct request_sock_queue *queue,
 	req->num_timeout = 0;
 	req->sk = NULL;
 
+	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
+	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
+	req->rsk_hash = hash;
+
 	/* before letting lookups find us, make sure all req fields
 	 * are committed to memory and refcnt initialized.
 	 */
 	smp_wmb();
 	atomic_set(&req->rsk_refcnt, 2);
-	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
-	req->rsk_hash = hash;
 
 	spin_lock(&queue->syn_wait_lock);
 	req->dl_next = lopt->syn_table[hash];
 	lopt->syn_table[hash] = req;
 	spin_unlock(&queue->syn_wait_lock);
-
-	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
 }
 EXPORT_SYMBOL(reqsk_queue_hash_req);
 
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index ae22cc24fbe8..c67f9bd7699c 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -123,13 +123,15 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	/*
 	 * Step 2: Hash TW into tcp ehash chain.
 	 * Notes :
-	 * - tw_refcnt is set to 3 because :
+	 * - tw_refcnt is set to 4 because :
 	 * - We have one reference from bhash chain.
 	 * - We have one reference from ehash chain.
+	 * - We have one reference from timer.
+	 * - One reference for ourself (our caller will release it).
 	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
 	 * committed into memory all tw fields.
 	 */
-	atomic_set(&tw->tw_refcnt, 1 + 1 + 1);
+	atomic_set(&tw->tw_refcnt, 4);
 	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
 	/* Step 3: Remove SK from hash chain */
@@ -217,7 +219,7 @@ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL(inet_twsk_deschedule_put);
 
-void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo)
+void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 {
 	/* timeout := RTO * 3.5
 	 *
@@ -245,12 +247,14 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo)
 	 */
 
 	tw->tw_kill = timeo <= 4*HZ;
-	if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) {
-		atomic_inc(&tw->tw_refcnt);
+	if (!rearm) {
+		BUG_ON(mod_timer_pinned(&tw->tw_timer, jiffies + timeo));
 		atomic_inc(&tw->tw_dr->tw_count);
+	} else {
+		mod_timer_pending(&tw->tw_timer, jiffies + timeo);
 	}
 }
-EXPORT_SYMBOL_GPL(inet_twsk_schedule);
+EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
 void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 		     struct inet_timewait_death_row *twdr, int family)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 29ed6c5a5185..84dce6a92f93 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -46,12 +46,13 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
+#include <net/dst_metadata.h>
 
 int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, __u8 proto,
 		  __u8 tos, __u8 ttl, __be16 df, bool xnet)
 {
-	int pkt_len = skb->len;
+	int pkt_len = skb->len - skb_inner_network_offset(skb);
 	struct iphdr *iph;
 	int err;
 
@@ -119,6 +120,33 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 }
 EXPORT_SYMBOL_GPL(iptunnel_pull_header);
 
+struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
+					     gfp_t flags)
+{
+	struct metadata_dst *res;
+	struct ip_tunnel_info *dst, *src;
+
+	if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
+		return NULL;
+
+	res = metadata_dst_alloc(0, flags);
+	if (!res)
+		return NULL;
+
+	dst = &res->u.tun_info;
+	src = &md->u.tun_info;
+	dst->key.tun_id = src->key.tun_id;
+	if (src->mode & IP_TUNNEL_INFO_IPV6)
+		memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
+		       sizeof(struct in6_addr));
+	else
+		dst->key.u.ipv4.dst = src->key.u.ipv4.src;
+	dst->mode = src->mode | IP_TUNNEL_INFO_TX;
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(iptunnel_metadata_reply);
+
 struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb,
 					 bool csum_help,
 					 int gso_type_mask)
@@ -198,8 +226,6 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
 	[LWTUNNEL_IP_SRC]	= { .type = NLA_U32 },
 	[LWTUNNEL_IP_TTL]	= { .type = NLA_U8 },
 	[LWTUNNEL_IP_TOS]	= { .type = NLA_U8 },
-	[LWTUNNEL_IP_SPORT]	= { .type = NLA_U16 },
-	[LWTUNNEL_IP_DPORT]	= { .type = NLA_U16 },
 	[LWTUNNEL_IP_FLAGS]	= { .type = NLA_U16 },
 };
 
@@ -239,12 +265,6 @@ static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr,
 	if (tb[LWTUNNEL_IP_TOS])
 		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
 
-	if (tb[LWTUNNEL_IP_SPORT])
-		tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP_SPORT]);
-
-	if (tb[LWTUNNEL_IP_DPORT])
-		tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP_DPORT]);
-
 	if (tb[LWTUNNEL_IP_FLAGS])
 		tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP_FLAGS]);
 
@@ -266,8 +286,6 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb,
 	    nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
 	    nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
 	    nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
-	    nla_put_u16(skb, LWTUNNEL_IP_SPORT, tun_info->key.tp_src) ||
-	    nla_put_u16(skb, LWTUNNEL_IP_DPORT, tun_info->key.tp_dst) ||
 	    nla_put_u16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags))
 		return -ENOMEM;
 
@@ -281,8 +299,6 @@ static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
 		+ nla_total_size(4)	/* LWTUNNEL_IP_SRC */
 		+ nla_total_size(1)	/* LWTUNNEL_IP_TOS */
 		+ nla_total_size(1)	/* LWTUNNEL_IP_TTL */
-		+ nla_total_size(2)	/* LWTUNNEL_IP_SPORT */
-		+ nla_total_size(2)	/* LWTUNNEL_IP_DPORT */
 		+ nla_total_size(2);	/* LWTUNNEL_IP_FLAGS */
 }
 
@@ -305,8 +321,6 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
 	[LWTUNNEL_IP6_SRC]		= { .len = sizeof(struct in6_addr) },
 	[LWTUNNEL_IP6_HOPLIMIT]		= { .type = NLA_U8 },
 	[LWTUNNEL_IP6_TC]		= { .type = NLA_U8 },
-	[LWTUNNEL_IP6_SPORT]		= { .type = NLA_U16 },
-	[LWTUNNEL_IP6_DPORT]		= { .type = NLA_U16 },
 	[LWTUNNEL_IP6_FLAGS]		= { .type = NLA_U16 },
 };
 
@@ -346,12 +360,6 @@ static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr,
 	if (tb[LWTUNNEL_IP6_TC])
 		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
 
-	if (tb[LWTUNNEL_IP6_SPORT])
-		tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP6_SPORT]);
-
-	if (tb[LWTUNNEL_IP6_DPORT])
-		tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP6_DPORT]);
-
 	if (tb[LWTUNNEL_IP6_FLAGS])
 		tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP6_FLAGS]);
 
@@ -373,8 +381,6 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb,
 	    nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
 	    nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) ||
 	    nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) ||
-	    nla_put_u16(skb, LWTUNNEL_IP6_SPORT, tun_info->key.tp_src) ||
-	    nla_put_u16(skb, LWTUNNEL_IP6_DPORT, tun_info->key.tp_dst) ||
 	    nla_put_u16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags))
 		return -ENOMEM;
 
@@ -388,8 +394,6 @@ static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
 		+ nla_total_size(16)	/* LWTUNNEL_IP6_SRC */
 		+ nla_total_size(1)	/* LWTUNNEL_IP6_HOPLIMIT */
 		+ nla_total_size(1)	/* LWTUNNEL_IP6_TC */
-		+ nla_total_size(2)	/* LWTUNNEL_IP6_SPORT */
-		+ nla_total_size(2)	/* LWTUNNEL_IP6_DPORT */
 		+ nla_total_size(2);	/* LWTUNNEL_IP6_FLAGS */
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5f4a5565ad8b..c6ad99ad0ffb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2045,6 +2045,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	struct fib_result res;
 	struct rtable *rth;
 	int orig_oif;
+	int err = -ENETUNREACH;
 
 	res.tclassid	= 0;
 	res.fi		= NULL;
@@ -2153,7 +2154,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 		goto make_route;
 	}
 
-	if (fib_lookup(net, fl4, &res, 0)) {
+	err = fib_lookup(net, fl4, &res, 0);
+	if (err) {
 		res.fi = NULL;
 		res.table = NULL;
 		if (fl4->flowi4_oif) {
@@ -2181,7 +2183,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 			res.type = RTN_UNICAST;
 			goto make_route;
 		}
-		rth = ERR_PTR(-ENETUNREACH);
+		rth = ERR_PTR(err);
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index c6ded6b2a79f..448c2615fece 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -154,14 +154,20 @@ static void bictcp_init(struct sock *sk)
 static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 {
 	if (event == CA_EVENT_TX_START) {
-		s32 delta = tcp_time_stamp - tcp_sk(sk)->lsndtime;
 		struct bictcp *ca = inet_csk_ca(sk);
+		u32 now = tcp_time_stamp;
+		s32 delta;
+
+		delta = now - tcp_sk(sk)->lsndtime;
 
 		/* We were application limited (idle) for a while.
 		 * Shift epoch_start to keep cwnd growth to cubic curve.
 		 */
-		if (ca->epoch_start && delta > 0)
+		if (ca->epoch_start && delta > 0) {
 			ca->epoch_start += delta;
+			if (after(ca->epoch_start, now))
+				ca->epoch_start = now;
+		}
 		return;
 	}
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 6d8795b066ac..def765911ff8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -162,9 +162,9 @@ kill_with_rst:
 		if (tcp_death_row.sysctl_tw_recycle &&
 		    tcptw->tw_ts_recent_stamp &&
 		    tcp_tw_remember_stamp(tw))
-			inet_twsk_schedule(tw, tw->tw_timeout);
+			inet_twsk_reschedule(tw, tw->tw_timeout);
 		else
-			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 		return TCP_TW_ACK;
 	}
 
@@ -201,7 +201,7 @@ kill:
 				return TCP_TW_SUCCESS;
 			}
 		}
-		inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
@@ -251,7 +251,7 @@ kill:
 		 * Do not reschedule in the last case.
 		 */
 		if (paws_reject || th->ack)
-			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		return tcp_timewait_check_oow_rate_limit(
 			tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT);
@@ -322,9 +322,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		} while (0);
 #endif
 
-		/* Linkage updates. */
-		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
-
 		/* Get the TIME_WAIT timeout firing. */
 		if (timeo < rto)
 			timeo = rto;
@@ -338,6 +335,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		}
 
 		inet_twsk_schedule(tw, timeo);
+		/* Linkage updates. */
+		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 		inet_twsk_put(tw);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f9a8a12b62ee..1100ffe4a722 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2897,6 +2897,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	skb_reserve(skb, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
+	skb_mstamp_get(&skb->skb_mstamp);
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c0a15e7f359f..f7d1d5e19e95 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1024,7 +1024,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		if (netif_index_is_vrf(net, ipc.oif)) {
 			flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 					   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-					   (flow_flags | FLOWI_FLAG_VRFSRC),
+					   (flow_flags | FLOWI_FLAG_VRFSRC |
+					    FLOWI_FLAG_SKIP_NH_OIF),
 					   faddr, saddr, dport,
 					   inet->inet_sport);
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index bb919b28619f..c10a9ee68433 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -33,6 +33,8 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
 	if (saddr)
 		fl4->saddr = saddr->a4;
 
+	fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF;
+
 	rt = __ip_route_output_key(net, fl4);
 	if (!IS_ERR(rt))
 		return &rt->dst;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 030fefdc9aed..900113376d4e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5127,13 +5127,12 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 
 			rt = addrconf_get_prefix_route(&ifp->peer_addr, 128,
 						       ifp->idev->dev, 0, 0);
-			if (rt && ip6_del_rt(rt))
-				dst_free(&rt->dst);
+			if (rt)
+				ip6_del_rt(rt);
 		}
 		dst_hold(&ifp->rt->dst);
 
-		if (ip6_del_rt(ifp->rt))
-			dst_free(&ifp->rt->dst);
+		ip6_del_rt(ifp->rt);
 
 		rt_genid_bump_ipv6(net);
 		break;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 418d9823692b..7d2e0023c72d 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -155,6 +155,11 @@ static void node_free(struct fib6_node *fn)
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
+static void rt6_rcu_free(struct rt6_info *rt)
+{
+	call_rcu(&rt->dst.rcu_head, dst_rcu_free);
+}
+
 static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 {
 	int cpu;
@@ -169,7 +174,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 		ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
 		pcpu_rt = *ppcpu_rt;
 		if (pcpu_rt) {
-			dst_free(&pcpu_rt->dst);
+			rt6_rcu_free(pcpu_rt);
 			*ppcpu_rt = NULL;
 		}
 	}
@@ -181,7 +186,7 @@ static void rt6_release(struct rt6_info *rt)
 {
 	if (atomic_dec_and_test(&rt->rt6i_ref)) {
 		rt6_free_pcpu(rt);
-		dst_free(&rt->dst);
+		rt6_rcu_free(rt);
 	}
 }
 
@@ -846,7 +851,7 @@ add:
 		*ins = rt;
 		rt->rt6i_node = fn;
 		atomic_inc(&rt->rt6i_ref);
-		inet6_rt_notify(RTM_NEWROUTE, rt, info);
+		inet6_rt_notify(RTM_NEWROUTE, rt, info, 0);
 		info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
 
 		if (!(fn->fn_flags & RTN_RTINFO)) {
@@ -872,7 +877,7 @@ add:
 		rt->rt6i_node = fn;
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
-		inet6_rt_notify(RTM_NEWROUTE, rt, info);
+		inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
 			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
 			fn->fn_flags |= RTN_RTINFO;
@@ -933,6 +938,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	int replace_required = 0;
 	int sernum = fib6_new_sernum(info->nl_net);
 
+	if (WARN_ON_ONCE((rt->dst.flags & DST_NOCACHE) &&
+			 !atomic_read(&rt->dst.__refcnt)))
+		return -EINVAL;
+
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
 			allow_create = 0;
@@ -1025,6 +1034,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 		fib6_start_gc(info->nl_net, rt);
 		if (!(rt->rt6i_flags & RTF_CACHE))
 			fib6_prune_clones(info->nl_net, pn);
+		rt->dst.flags &= ~DST_NOCACHE;
 	}
 
 out:
@@ -1049,7 +1059,8 @@ out:
 			atomic_inc(&pn->leaf->rt6i_ref);
 		}
 #endif
-		dst_free(&rt->dst);
+		if (!(rt->dst.flags & DST_NOCACHE))
+			dst_free(&rt->dst);
 	}
 	return err;
 
@@ -1060,7 +1071,8 @@ out:
 st_failure:
 	if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
 		fib6_repair_tree(info->nl_net, fn);
-	dst_free(&rt->dst);
+	if (!(rt->dst.flags & DST_NOCACHE))
+		dst_free(&rt->dst);
 	return err;
 #endif
 }
@@ -1410,7 +1422,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 
 	fib6_purge_rt(rt, fn, net);
 
-	inet6_rt_notify(RTM_DELROUTE, rt, info);
+	inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
 	rt6_release(rt);
 }
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4038c694ec03..3c7b9310b33f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -404,13 +404,13 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		struct ipv6_tlv_tnl_enc_lim *tel;
 		__u32 mtu;
 	case ICMPV6_DEST_UNREACH:
-		net_warn_ratelimited("%s: Path to destination invalid or inactive!\n",
-				     t->parms.name);
+		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
+				    t->parms.name);
 		break;
 	case ICMPV6_TIME_EXCEED:
 		if (code == ICMPV6_EXC_HOPLIMIT) {
-			net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
-					     t->parms.name);
+			net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
+					    t->parms.name);
 		}
 		break;
 	case ICMPV6_PARAMPROB:
@@ -421,12 +421,12 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (teli && teli == be32_to_cpu(info) - 2) {
 			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
 			if (tel->encap_limit == 0) {
-				net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
-						     t->parms.name);
+				net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
+						    t->parms.name);
 			}
 		} else {
-			net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
-					     t->parms.name);
+			net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
+					    t->parms.name);
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
@@ -634,20 +634,20 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 	}
 
 	if (!fl6->flowi6_mark)
-		dst = ip6_tnl_dst_check(tunnel);
+		dst = ip6_tnl_dst_get(tunnel);
 
 	if (!dst) {
-		ndst = ip6_route_output(net, NULL, fl6);
+		dst = ip6_route_output(net, NULL, fl6);
 
-		if (ndst->error)
+		if (dst->error)
 			goto tx_err_link_failure;
-		ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0);
-		if (IS_ERR(ndst)) {
-			err = PTR_ERR(ndst);
-			ndst = NULL;
+		dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0);
+		if (IS_ERR(dst)) {
+			err = PTR_ERR(dst);
+			dst = NULL;
 			goto tx_err_link_failure;
 		}
-		dst = ndst;
+		ndst = dst;
 	}
 
 	tdev = dst->dev;
@@ -702,12 +702,9 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 		skb = new_skb;
 	}
 
-	if (fl6->flowi6_mark) {
-		skb_dst_set(skb, dst);
-		ndst = NULL;
-	} else {
-		skb_dst_set_noref(skb, dst);
-	}
+	if (!fl6->flowi6_mark && ndst)
+		ip6_tnl_dst_set(tunnel, ndst);
+	skb_dst_set(skb, dst);
 
 	proto = NEXTHDR_GRE;
 	if (encap_limit >= 0) {
@@ -762,14 +759,12 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 	skb_set_inner_protocol(skb, protocol);
 
 	ip6tunnel_xmit(NULL, skb, dev);
-	if (ndst)
-		ip6_tnl_dst_store(tunnel, ndst);
 	return 0;
 tx_err_link_failure:
 	stats->tx_carrier_errors++;
 	dst_link_failure(skb);
 tx_err_dst_release:
-	dst_release(ndst);
+	dst_release(dst);
 	return err;
 }
 
@@ -1223,6 +1218,9 @@ static const struct net_device_ops ip6gre_netdev_ops = {
 
 static void ip6gre_dev_free(struct net_device *dev)
 {
+	struct ip6_tnl *t = netdev_priv(dev);
+
+	ip6_tnl_dst_destroy(t);
 	free_percpu(dev->tstats);
 	free_netdev(dev);
 }
@@ -1245,9 +1243,10 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 }
 
-static int ip6gre_tunnel_init(struct net_device *dev)
+static int ip6gre_tunnel_init_common(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
+	int ret;
 
 	tunnel = netdev_priv(dev);
 
@@ -1255,16 +1254,37 @@ static int ip6gre_tunnel_init(struct net_device *dev)
 	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	ret = ip6_tnl_dst_init(tunnel);
+	if (ret) {
+		free_percpu(dev->tstats);
+		dev->tstats = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ip6gre_tunnel_init(struct net_device *dev)
+{
+	struct ip6_tnl *tunnel;
+	int ret;
+
+	ret = ip6gre_tunnel_init_common(dev);
+	if (ret)
+		return ret;
+
+	tunnel = netdev_priv(dev);
+
 	memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr));
 	memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr));
 
 	if (ipv6_addr_any(&tunnel->parms.raddr))
 		dev->header_ops = &ip6gre_header_ops;
 
-	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
 	return 0;
 }
 
@@ -1460,19 +1480,16 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 static int ip6gre_tap_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
+	int ret;
 
-	tunnel = netdev_priv(dev);
+	ret = ip6gre_tunnel_init_common(dev);
+	if (ret)
+		return ret;
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-	strcpy(tunnel->parms.name, dev->name);
+	tunnel = netdev_priv(dev);
 
 	ip6gre_tnl_link_config(tunnel, 1);
 
-	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
 	return 0;
 }
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 26ea47930740..92b1aa38f121 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -586,20 +586,22 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 	frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
 				    &ipv6_hdr(skb)->saddr);
 
+	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	if (skb_has_frag_list(skb)) {
 		int first_len = skb_pagelen(skb);
 		struct sk_buff *frag2;
 
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
-		    skb_cloned(skb))
+		    skb_cloned(skb) ||
+		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
 			goto slow_path;
 
 		skb_walk_frags(skb, frag) {
 			/* Correct geometry. */
 			if (frag->len > mtu ||
 			    ((frag->len & 7) && frag->next) ||
-			    skb_headroom(frag) < hlen)
+			    skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr)))
 				goto slow_path_clean;
 
 			/* Partially cloned skb? */
@@ -616,8 +618,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 
 		err = 0;
 		offset = 0;
-		frag = skb_shinfo(skb)->frag_list;
-		skb_frag_list_init(skb);
 		/* BUILD HEADER */
 
 		*prevhdr = NEXTHDR_FRAGMENT;
@@ -625,8 +625,11 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 		if (!tmp_hdr) {
 			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 				      IPSTATS_MIB_FRAGFAILS);
-			return -ENOMEM;
+			err = -ENOMEM;
+			goto fail;
 		}
+		frag = skb_shinfo(skb)->frag_list;
+		skb_frag_list_init(skb);
 
 		__skb_pull(skb, hlen);
 		fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr));
@@ -723,7 +726,6 @@ slow_path:
 	 */
 
 	*prevhdr = NEXTHDR_FRAGMENT;
-	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	troom = rt->dst.dev->needed_tailroom;
 
 	/*
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b0ab420612bc..eabffbb89795 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -126,36 +126,92 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev)
  * Locking : hash tables are protected by RCU and RTNL
  */
 
-struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
+static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst,
+				    struct dst_entry *dst)
 {
-	struct dst_entry *dst = t->dst_cache;
+	write_seqlock_bh(&idst->lock);
+	dst_release(rcu_dereference_protected(
+			    idst->dst,
+			    lockdep_is_held(&idst->lock.lock)));
+	if (dst) {
+		dst_hold(dst);
+		idst->cookie = rt6_get_cookie((struct rt6_info *)dst);
+	} else {
+		idst->cookie = 0;
+	}
+	rcu_assign_pointer(idst->dst, dst);
+	write_sequnlock_bh(&idst->lock);
+}
+
+struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t)
+{
+	struct ip6_tnl_dst *idst;
+	struct dst_entry *dst;
+	unsigned int seq;
+	u32 cookie;
 
-	if (dst && dst->obsolete &&
-	    !dst->ops->check(dst, t->dst_cookie)) {
-		t->dst_cache = NULL;
+	idst = raw_cpu_ptr(t->dst_cache);
+
+	rcu_read_lock();
+	do {
+		seq = read_seqbegin(&idst->lock);
+		dst = rcu_dereference(idst->dst);
+		cookie = idst->cookie;
+	} while (read_seqretry(&idst->lock, seq));
+
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
+	rcu_read_unlock();
+
+	if (dst && dst->obsolete && !dst->ops->check(dst, cookie)) {
+		ip6_tnl_per_cpu_dst_set(idst, NULL);
 		dst_release(dst);
-		return NULL;
+		dst = NULL;
 	}
-
 	return dst;
 }
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_check);
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_get);
 
 void ip6_tnl_dst_reset(struct ip6_tnl *t)
 {
-	dst_release(t->dst_cache);
-	t->dst_cache = NULL;
+	int i;
+
+	for_each_possible_cpu(i)
+		ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL);
 }
 EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
 
-void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
+void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst)
+{
+	ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst);
+
+}
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_set);
+
+void ip6_tnl_dst_destroy(struct ip6_tnl *t)
 {
-	struct rt6_info *rt = (struct rt6_info *) dst;
-	t->dst_cookie = rt6_get_cookie(rt);
-	dst_release(t->dst_cache);
-	t->dst_cache = dst;
+	if (!t->dst_cache)
+		return;
+
+	ip6_tnl_dst_reset(t);
+	free_percpu(t->dst_cache);
 }
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_store);
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_destroy);
+
+int ip6_tnl_dst_init(struct ip6_tnl *t)
+{
+	int i;
+
+	t->dst_cache = alloc_percpu(struct ip6_tnl_dst);
+	if (!t->dst_cache)
+		return -ENOMEM;
+
+	for_each_possible_cpu(i)
+		seqlock_init(&per_cpu_ptr(t->dst_cache, i)->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_init);
 
 /**
  * ip6_tnl_lookup - fetch tunnel matching the end-point addresses
@@ -271,6 +327,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
 
 static void ip6_dev_free(struct net_device *dev)
 {
+	struct ip6_tnl *t = netdev_priv(dev);
+
+	ip6_tnl_dst_destroy(t);
 	free_percpu(dev->tstats);
 	free_netdev(dev);
 }
@@ -510,14 +569,14 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 		struct ipv6_tlv_tnl_enc_lim *tel;
 		__u32 mtu;
 	case ICMPV6_DEST_UNREACH:
-		net_warn_ratelimited("%s: Path to destination invalid or inactive!\n",
-				     t->parms.name);
+		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
+				    t->parms.name);
 		rel_msg = 1;
 		break;
 	case ICMPV6_TIME_EXCEED:
 		if ((*code) == ICMPV6_EXC_HOPLIMIT) {
-			net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
-					     t->parms.name);
+			net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
+					    t->parms.name);
 			rel_msg = 1;
 		}
 		break;
@@ -529,13 +588,13 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 		if (teli && teli == *info - 2) {
 			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
 			if (tel->encap_limit == 0) {
-				net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
-						     t->parms.name);
+				net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
+						    t->parms.name);
 				rel_msg = 1;
 			}
 		} else {
-			net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
-					     t->parms.name);
+			net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
+					    t->parms.name);
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
@@ -1010,23 +1069,23 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
 		neigh_release(neigh);
 	} else if (!fl6->flowi6_mark)
-		dst = ip6_tnl_dst_check(t);
+		dst = ip6_tnl_dst_get(t);
 
 	if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
 		goto tx_err_link_failure;
 
 	if (!dst) {
-		ndst = ip6_route_output(net, NULL, fl6);
+		dst = ip6_route_output(net, NULL, fl6);
 
-		if (ndst->error)
+		if (dst->error)
 			goto tx_err_link_failure;
-		ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0);
-		if (IS_ERR(ndst)) {
-			err = PTR_ERR(ndst);
-			ndst = NULL;
+		dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0);
+		if (IS_ERR(dst)) {
+			err = PTR_ERR(dst);
+			dst = NULL;
 			goto tx_err_link_failure;
 		}
-		dst = ndst;
+		ndst = dst;
 	}
 
 	tdev = dst->dev;
@@ -1072,12 +1131,11 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		consume_skb(skb);
 		skb = new_skb;
 	}
-	if (fl6->flowi6_mark) {
-		skb_dst_set(skb, dst);
-		ndst = NULL;
-	} else {
-		skb_dst_set_noref(skb, dst);
-	}
+
+	if (!fl6->flowi6_mark && ndst)
+		ip6_tnl_dst_set(t, ndst);
+	skb_dst_set(skb, dst);
+
 	skb->transport_header = skb->network_header;
 
 	proto = fl6->flowi6_proto;
@@ -1101,14 +1159,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	ipv6h->saddr = fl6->saddr;
 	ipv6h->daddr = fl6->daddr;
 	ip6tunnel_xmit(NULL, skb, dev);
-	if (ndst)
-		ip6_tnl_dst_store(t, ndst);
 	return 0;
 tx_err_link_failure:
 	stats->tx_carrier_errors++;
 	dst_link_failure(skb);
 tx_err_dst_release:
-	dst_release(ndst);
+	dst_release(dst);
 	return err;
 }
 
@@ -1573,12 +1629,21 @@ static inline int
 ip6_tnl_dev_init_gen(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
+	int ret;
 
 	t->dev = dev;
 	t->net = dev_net(dev);
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
+
+	ret = ip6_tnl_dst_init(t);
+	if (ret) {
+		free_percpu(dev->tstats);
+		dev->tstats = NULL;
+		return ret;
+	}
+
 	return 0;
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 53617d715188..f204089e854c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1322,8 +1322,7 @@ static void ip6_link_failure(struct sk_buff *skb)
 	if (rt) {
 		if (rt->rt6i_flags & RTF_CACHE) {
 			dst_hold(&rt->dst);
-			if (ip6_del_rt(rt))
-				dst_free(&rt->dst);
+			ip6_del_rt(rt);
 		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) {
 			rt->rt6i_node->fn_sernum = -1;
 		}
@@ -1886,9 +1885,11 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
 			rt->dst.input = ip6_pkt_prohibit;
 			break;
 		case RTN_THROW:
+		case RTN_UNREACHABLE:
 		default:
 			rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN
-					: -ENETUNREACH;
+					: (cfg->fc_type == RTN_UNREACHABLE)
+					? -EHOSTUNREACH : -ENETUNREACH;
 			rt->dst.output = ip6_pkt_discard_out;
 			rt->dst.input = ip6_pkt_discard;
 			break;
@@ -2028,7 +2029,8 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
 	struct fib6_table *table;
 	struct net *net = dev_net(rt->dst.dev);
 
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt == net->ipv6.ip6_null_entry ||
+	    rt->dst.flags & DST_NOCACHE) {
 		err = -ENOENT;
 		goto out;
 	}
@@ -2515,6 +2517,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	rt->rt6i_dst.addr = *addr;
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
+	rt->dst.flags |= DST_NOCACHE;
 
 	atomic_set(&rt->dst.__refcnt, 1);
 
@@ -3303,7 +3306,8 @@ errout:
 	return err;
 }
 
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
+void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
+		     unsigned int nlm_flags)
 {
 	struct sk_buff *skb;
 	struct net *net = info->nl_net;
@@ -3318,7 +3322,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
 		goto errout;
 
 	err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
-				event, info->portid, seq, 0, 0, 0);
+				event, info->portid, seq, 0, 0, nlm_flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 17b1fe961c5d..7a77a1470f25 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2474,6 +2474,7 @@ static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy,
 
 	bss_conf->cqm_rssi_thold = rssi_thold;
 	bss_conf->cqm_rssi_hyst = rssi_hyst;
+	sdata->u.mgd.last_cqm_event_signal = 0;
 
 	/* tell the driver upon association, unless already associated */
 	if (sdata->u.mgd.associated &&
@@ -2518,15 +2519,17 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 			continue;
 
 		for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) {
-			if (~sdata->rc_rateidx_mcs_mask[i][j])
+			if (~sdata->rc_rateidx_mcs_mask[i][j]) {
 				sdata->rc_has_mcs_mask[i] = true;
+				break;
+			}
+		}
 
-			if (~sdata->rc_rateidx_vht_mcs_mask[i][j])
+		for (j = 0; j < NL80211_VHT_NSS_MAX; j++) {
+			if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) {
 				sdata->rc_has_vht_mcs_mask[i] = true;
-
-			if (sdata->rc_has_mcs_mask[i] &&
-			    sdata->rc_has_vht_mcs_mask[i])
 				break;
+			}
 		}
 	}
 
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 675d12c69e32..a5d41dfa9f05 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -107,12 +107,17 @@ EXPORT_SYMBOL(nf_log_register);
 
 void nf_log_unregister(struct nf_logger *logger)
 {
+	const struct nf_logger *log;
 	int i;
 
 	mutex_lock(&nf_log_mutex);
-	for (i = 0; i < NFPROTO_NUMPROTO; i++)
-		RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+		log = nft_log_dereference(loggers[i][logger->type]);
+		if (log == logger)
+			RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+	}
 	mutex_unlock(&nf_log_mutex);
+	synchronize_rcu();
 }
 EXPORT_SYMBOL(nf_log_unregister);
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 66def315eb56..9c8fab00164b 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -619,6 +619,13 @@ struct nft_xt {
 
 static struct nft_expr_type nft_match_type;
 
+static bool nft_match_cmp(const struct xt_match *match,
+			  const char *name, u32 rev, u32 family)
+{
+	return strcmp(match->name, name) == 0 && match->revision == rev &&
+	       (match->family == NFPROTO_UNSPEC || match->family == family);
+}
+
 static const struct nft_expr_ops *
 nft_match_select_ops(const struct nft_ctx *ctx,
 		     const struct nlattr * const tb[])
@@ -626,7 +633,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	struct nft_xt *nft_match;
 	struct xt_match *match;
 	char *mt_name;
-	__u32 rev, family;
+	u32 rev, family;
 
 	if (tb[NFTA_MATCH_NAME] == NULL ||
 	    tb[NFTA_MATCH_REV] == NULL ||
@@ -641,8 +648,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_match, &nft_match_list, head) {
 		struct xt_match *match = nft_match->ops.data;
 
-		if (strcmp(match->name, mt_name) == 0 &&
-		    match->revision == rev && match->family == family) {
+		if (nft_match_cmp(match, mt_name, rev, family)) {
 			if (!try_module_get(match->me))
 				return ERR_PTR(-ENOENT);
 
@@ -693,6 +699,13 @@ static LIST_HEAD(nft_target_list);
 
 static struct nft_expr_type nft_target_type;
 
+static bool nft_target_cmp(const struct xt_target *tg,
+			   const char *name, u32 rev, u32 family)
+{
+	return strcmp(tg->name, name) == 0 && tg->revision == rev &&
+	       (tg->family == NFPROTO_UNSPEC || tg->family == family);
+}
+
 static const struct nft_expr_ops *
 nft_target_select_ops(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
@@ -700,7 +713,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	struct nft_xt *nft_target;
 	struct xt_target *target;
 	char *tg_name;
-	__u32 rev, family;
+	u32 rev, family;
 
 	if (tb[NFTA_TARGET_NAME] == NULL ||
 	    tb[NFTA_TARGET_REV] == NULL ||
@@ -715,8 +728,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_target, &nft_target_list, head) {
 		struct xt_target *target = nft_target->ops.data;
 
-		if (strcmp(target->name, tg_name) == 0 &&
-		    target->revision == rev && target->family == family) {
+		if (nft_target_cmp(target, tg_name, rev, family)) {
 			if (!try_module_get(target->me))
 				return ERR_PTR(-ENOENT);
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7f86d3b55060..8f060d7f9a0e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -125,6 +125,24 @@ static inline u32 netlink_group_mask(u32 group)
 	return group ? 1 << (group - 1) : 0;
 }
 
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+					   gfp_t gfp_mask)
+{
+	unsigned int len = skb_end_offset(skb);
+	struct sk_buff *new;
+
+	new = alloc_skb(len, gfp_mask);
+	if (new == NULL)
+		return NULL;
+
+	NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+	NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+	NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+	memcpy(skb_put(new, len), skb->data, len);
+	return new;
+}
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -206,7 +224,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	int ret = -ENOMEM;
 
 	dev_hold(dev);
-	nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+	else
+		nskb = skb_clone(skb, GFP_ATOMIC);
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
@@ -279,11 +301,6 @@ static void netlink_rcv_wake(struct sock *sk)
 }
 
 #ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
 static bool netlink_rx_is_mmaped(struct sock *sk)
 {
 	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -846,7 +863,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb)	false
 #define netlink_rx_is_mmaped(sk)	false
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
@@ -1094,8 +1110,8 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	lock_sock(sk);
 
-	err = -EBUSY;
-	if (nlk_sk(sk)->portid)
+	err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
+	if (nlk_sk(sk)->bound)
 		goto err;
 
 	err = -ENOMEM;
@@ -1115,10 +1131,14 @@ static int netlink_insert(struct sock *sk, u32 portid)
 			err = -EOVERFLOW;
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
-		nlk_sk(sk)->portid = 0;
 		sock_put(sk);
+		goto err;
 	}
 
+	/* We need to ensure that the socket is hashed and visible. */
+	smp_wmb();
+	nlk_sk(sk)->bound = portid;
+
 err:
 	release_sock(sk);
 	return err;
@@ -1503,6 +1523,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
 	long unsigned int groups = nladdr->nl_groups;
+	bool bound;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1519,9 +1540,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			return err;
 	}
 
-	if (nlk->portid)
+	bound = nlk->bound;
+	if (bound) {
+		/* Ensure nlk->portid is up-to-date. */
+		smp_rmb();
+
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
+	}
 
 	if (nlk->netlink_bind && groups) {
 		int group;
@@ -1537,7 +1563,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		}
 	}
 
-	if (!nlk->portid) {
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!bound) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
@@ -1585,7 +1614,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
-	if (!nlk->portid)
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!nlk->bound)
 		err = netlink_autobind(sock);
 
 	if (err == 0) {
@@ -2426,10 +2458,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		dst_group = nlk->dst_group;
 	}
 
-	if (!nlk->portid) {
+	if (!nlk->bound) {
 		err = netlink_autobind(sock);
 		if (err)
 			goto out;
+	} else {
+		/* Ensure nlk is hashed and visible. */
+		smp_rmb();
 	}
 
 	/* It's a really convoluted way for userland to ask for mmaped
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 89008405d6b4..14437d9b1965 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -35,6 +35,7 @@ struct netlink_sock {
 	unsigned long		state;
 	size_t			max_recvmsg_len;
 	wait_queue_head_t	wait;
+	bool			bound;
 	bool			cb_running;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
@@ -59,6 +60,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
+static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETLINK_MMAP
+	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+#else
+	return false;
+#endif /* CONFIG_NETLINK_MMAP */
+}
+
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 2a071f470d57..d143aa9f6654 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -5,7 +5,8 @@
 config OPENVSWITCH
 	tristate "Open vSwitch"
 	depends on INET
-	depends on (!NF_CONNTRACK || NF_CONNTRACK)
+	depends on !NF_CONNTRACK || \
+		   (NF_CONNTRACK && (!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6))
 	select LIBCRC32C
 	select MPLS
 	select NET_MPLS_GSO
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e8e524ad8a01..002a755fa07e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -275,13 +275,15 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto)
 	case NFPROTO_IPV6: {
 		u8 nexthdr = ipv6_hdr(skb)->nexthdr;
 		__be16 frag_off;
+		int ofs;
 
-		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
-					   &nexthdr, &frag_off);
-		if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				       &frag_off);
+		if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
 			pr_debug("proto header not found\n");
 			return NF_ACCEPT;
 		}
+		protoff = ofs;
 		break;
 	}
 	default:
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6fbd2decb19e..b816ff871528 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -952,7 +952,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &key, true, &mask);
 
 	/* Extract flow identifier. */
 	error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
@@ -1080,7 +1080,7 @@ static struct sw_flow_actions *get_flow_actions(struct net *net,
 	struct sw_flow_key masked_key;
 	int error;
 
-	ovs_flow_mask_key(&masked_key, key, mask);
+	ovs_flow_mask_key(&masked_key, key, true, mask);
 	error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log);
 	if (error) {
 		OVS_NLERR(log,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c92d6a262bc5..5c030a4d7338 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -57,6 +57,7 @@ struct ovs_len_tbl {
 };
 
 #define OVS_ATTR_NESTED -1
+#define OVS_ATTR_VARIABLE -2
 
 static void update_range(struct sw_flow_match *match,
 			 size_t offset, size_t size, bool is_mask)
@@ -304,6 +305,10 @@ size_t ovs_key_attr_size(void)
 		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
 }
 
+static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
+	[OVS_VXLAN_EXT_GBP]	    = { .len = sizeof(u32) },
+};
+
 static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
 	[OVS_TUNNEL_KEY_ATTR_ID]	    = { .len = sizeof(u64) },
 	[OVS_TUNNEL_KEY_ATTR_IPV4_SRC]	    = { .len = sizeof(u32) },
@@ -315,8 +320,9 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
 	[OVS_TUNNEL_KEY_ATTR_TP_SRC]	    = { .len = sizeof(u16) },
 	[OVS_TUNNEL_KEY_ATTR_TP_DST]	    = { .len = sizeof(u16) },
 	[OVS_TUNNEL_KEY_ATTR_OAM]	    = { .len = 0 },
-	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_NESTED },
-	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED },
+	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_VARIABLE },
+	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED,
+						.next = ovs_vxlan_ext_key_lens },
 };
 
 /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
@@ -349,6 +355,13 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_CT_LABEL]	 = { .len = sizeof(struct ovs_key_ct_label) },
 };
 
+static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
+{
+	return expected_len == attr_len ||
+	       expected_len == OVS_ATTR_NESTED ||
+	       expected_len == OVS_ATTR_VARIABLE;
+}
+
 static bool is_all_zero(const u8 *fp, size_t size)
 {
 	int i;
@@ -388,7 +401,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 		}
 
 		expected_len = ovs_key_lens[type].len;
-		if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) {
+		if (!check_attr_len(nla_len(nla), expected_len)) {
 			OVS_NLERR(log, "Key %d has unexpected len %d expected %d",
 				  type, nla_len(nla), expected_len);
 			return -EINVAL;
@@ -473,29 +486,50 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a,
 	return 0;
 }
 
-static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = {
-	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_U32 },
-};
-
-static int vxlan_tun_opt_from_nlattr(const struct nlattr *a,
+static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr,
 				     struct sw_flow_match *match, bool is_mask,
 				     bool log)
 {
-	struct nlattr *tb[OVS_VXLAN_EXT_MAX+1];
+	struct nlattr *a;
+	int rem;
 	unsigned long opt_key_offset;
 	struct vxlan_metadata opts;
-	int err;
 
 	BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));
 
-	err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy);
-	if (err < 0)
-		return err;
-
 	memset(&opts, 0, sizeof(opts));
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
 
-	if (tb[OVS_VXLAN_EXT_GBP])
-		opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]);
+		if (type > OVS_VXLAN_EXT_MAX) {
+			OVS_NLERR(log, "VXLAN extension %d out of range max %d",
+				  type, OVS_VXLAN_EXT_MAX);
+			return -EINVAL;
+		}
+
+		if (!check_attr_len(nla_len(a),
+				    ovs_vxlan_ext_key_lens[type].len)) {
+			OVS_NLERR(log, "VXLAN extension %d has unexpected len %d expected %d",
+				  type, nla_len(a),
+				  ovs_vxlan_ext_key_lens[type].len);
+			return -EINVAL;
+		}
+
+		switch (type) {
+		case OVS_VXLAN_EXT_GBP:
+			opts.gbp = nla_get_u32(a);
+			break;
+		default:
+			OVS_NLERR(log, "Unknown VXLAN extension attribute %d",
+				  type);
+			return -EINVAL;
+		}
+	}
+	if (rem) {
+		OVS_NLERR(log, "VXLAN extension message has %d unknown bytes.",
+			  rem);
+		return -EINVAL;
+	}
 
 	if (!is_mask)
 		SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false);
@@ -528,8 +562,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			return -EINVAL;
 		}
 
-		if (ovs_tunnel_key_lens[type].len != nla_len(a) &&
-		    ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) {
+		if (!check_attr_len(nla_len(a),
+				    ovs_tunnel_key_lens[type].len)) {
 			OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d",
 				  type, nla_len(a), ovs_tunnel_key_lens[type].len);
 			return -EINVAL;
@@ -1052,10 +1086,13 @@ static void nlattr_set(struct nlattr *attr, u8 val,
 
 	/* The nlattr stream should already have been validated */
 	nla_for_each_nested(nla, attr, rem) {
-		if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
-			nlattr_set(nla, val, tbl[nla_type(nla)].next);
-		else
+		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
+			if (tbl[nla_type(nla)].next)
+				tbl = tbl[nla_type(nla)].next;
+			nlattr_set(nla, val, tbl);
+		} else {
 			memset(nla_data(nla), val, nla_len(nla));
+		}
 	}
 }
 
@@ -1922,8 +1959,7 @@ static int validate_set(const struct nlattr *a,
 		key_len /= 2;
 
 	if (key_type > OVS_KEY_ATTR_MAX ||
-	    (ovs_key_lens[key_type].len != key_len &&
-	     ovs_key_lens[key_type].len != OVS_ATTR_NESTED))
+	    !check_attr_len(key_len, ovs_key_lens[key_type].len))
 		return -EINVAL;
 
 	if (masked && !validate_masked(nla_data(ovs_key), key_len))
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index d22d8e948d0f..f2ea83ba4763 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -57,20 +57,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 }
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask)
+		       bool full, const struct sw_flow_mask *mask)
 {
-	const long *m = (const long *)((const u8 *)&mask->key +
-				mask->range.start);
-	const long *s = (const long *)((const u8 *)src +
-				mask->range.start);
-	long *d = (long *)((u8 *)dst + mask->range.start);
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
 	int i;
 
-	/* The memory outside of the 'mask->range' are not set since
-	 * further operations on 'dst' only uses contents within
-	 * 'mask->range'.
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
 	 */
-	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+	for (i = 0; i < len; i += sizeof(long))
 		*d++ = *s++ & *m++;
 }
 
@@ -475,7 +476,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	u32 hash;
 	struct sw_flow_key masked_key;
 
-	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
 	hash = flow_hash(&masked_key, &mask->range);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 616eda10d955..2dd9900f533d 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
 bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
+		       bool full, const struct sw_flow_mask *mask);
 #endif /* flow_table.h */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 7b8e39a22387..aa4b15c35884 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -230,6 +230,8 @@ struct packet_skb_cb {
 	} sa;
 };
 
+#define vio_le() virtio_legacy_is_little_endian()
+
 #define PACKET_SKB_CB(__skb)	((struct packet_skb_cb *)((__skb)->cb))
 
 #define GET_PBDQC_FROM_RB(x)	((struct tpacket_kbdq_core *)(&(x)->prb_bdqc))
@@ -2680,15 +2682,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_unlock;
 
 		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    (__virtio16_to_cpu(false, vnet_hdr.csum_start) +
-		     __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2 >
-		      __virtio16_to_cpu(false, vnet_hdr.hdr_len)))
-			vnet_hdr.hdr_len = __cpu_to_virtio16(false,
-				 __virtio16_to_cpu(false, vnet_hdr.csum_start) +
-				__virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2);
+		    (__virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
+		     __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2 >
+		      __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len)))
+			vnet_hdr.hdr_len = __cpu_to_virtio16(vio_le(),
+				 __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
+				__virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2);
 
 		err = -EINVAL;
-		if (__virtio16_to_cpu(false, vnet_hdr.hdr_len) > len)
+		if (__virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len) > len)
 			goto out_unlock;
 
 		if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
@@ -2731,7 +2733,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
 	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(false, vnet_hdr.hdr_len),
+			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
@@ -2778,8 +2780,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-			u16 s = __virtio16_to_cpu(false, vnet_hdr.csum_start);
-			u16 o = __virtio16_to_cpu(false, vnet_hdr.csum_offset);
+			u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start);
+			u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset);
 			if (!skb_partial_csum_set(skb, s, o)) {
 				err = -EINVAL;
 				goto out_free;
@@ -2787,7 +2789,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		}
 
 		skb_shinfo(skb)->gso_size =
-			__virtio16_to_cpu(false, vnet_hdr.gso_size);
+			__virtio16_to_cpu(vio_le(), vnet_hdr.gso_size);
 		skb_shinfo(skb)->gso_type = gso_type;
 
 		/* Header must be checked, and gso_segs computed. */
@@ -3161,9 +3163,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 			/* This is a hint as to how much should be linear. */
 			vnet_hdr.hdr_len =
-				__cpu_to_virtio16(false, skb_headlen(skb));
+				__cpu_to_virtio16(vio_le(), skb_headlen(skb));
 			vnet_hdr.gso_size =
-				__cpu_to_virtio16(false, sinfo->gso_size);
+				__cpu_to_virtio16(vio_le(), sinfo->gso_size);
 			if (sinfo->gso_type & SKB_GSO_TCPV4)
 				vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 			else if (sinfo->gso_type & SKB_GSO_TCPV6)
@@ -3181,9 +3183,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			vnet_hdr.csum_start = __cpu_to_virtio16(false,
+			vnet_hdr.csum_start = __cpu_to_virtio16(vio_le(),
 					  skb_checksum_start_offset(skb));
-			vnet_hdr.csum_offset = __cpu_to_virtio16(false,
+			vnet_hdr.csum_offset = __cpu_to_virtio16(vio_le(),
 							 skb->csum_offset);
 		} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 715e01e5910a..f23a3b68bba6 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -33,7 +33,6 @@
 
 struct fw_head {
 	u32			mask;
-	bool			mask_set;
 	struct fw_filter __rcu	*ht[HTSIZE];
 	struct rcu_head		rcu;
 };
@@ -84,7 +83,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			}
 		}
 	} else {
-		/* old method */
+		/* Old method: classify the packet using its skb mark. */
 		if (id && (TC_H_MAJ(id) == 0 ||
 			   !(TC_H_MAJ(id ^ tp->q->handle)))) {
 			res->classid = id;
@@ -114,14 +113,9 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle)
 
 static int fw_init(struct tcf_proto *tp)
 {
-	struct fw_head *head;
-
-	head = kzalloc(sizeof(struct fw_head), GFP_KERNEL);
-	if (head == NULL)
-		return -ENOBUFS;
-
-	head->mask_set = false;
-	rcu_assign_pointer(tp->root, head);
+	/* We don't allocate fw_head here, because in the old method
+	 * we don't need it at all.
+	 */
 	return 0;
 }
 
@@ -252,7 +246,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	int err;
 
 	if (!opt)
-		return handle ? -EINVAL : 0;
+		return handle ? -EINVAL : 0; /* Succeed if it is old method. */
 
 	err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy);
 	if (err < 0)
@@ -302,11 +296,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (!handle)
 		return -EINVAL;
 
-	if (!head->mask_set) {
-		head->mask = 0xFFFFFFFF;
+	if (!head) {
+		u32 mask = 0xFFFFFFFF;
 		if (tb[TCA_FW_MASK])
-			head->mask = nla_get_u32(tb[TCA_FW_MASK]);
-		head->mask_set = true;
+			mask = nla_get_u32(tb[TCA_FW_MASK]);
+
+		head = kzalloc(sizeof(*head), GFP_KERNEL);
+		if (!head)
+			return -ENOBUFS;
+		head->mask = mask;
+
+		rcu_assign_pointer(tp->root, head);
 	}
 
 	f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index b7143337e4fa..3d9ea9a48289 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1186,7 +1186,7 @@ static void sctp_v4_del_protocol(void)
 	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
 }
 
-static int __net_init sctp_net_init(struct net *net)
+static int __net_init sctp_defaults_init(struct net *net)
 {
 	int status;
 
@@ -1279,12 +1279,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	sctp_dbg_objcnt_init(net);
 
-	/* Initialize the control inode/socket for handling OOTB packets.  */
-	if ((status = sctp_ctl_sock_init(net))) {
-		pr_err("Failed to initialize the SCTP control sock\n");
-		goto err_ctl_sock_init;
-	}
-
 	/* Initialize the local address list. */
 	INIT_LIST_HEAD(&net->sctp.local_addr_list);
 	spin_lock_init(&net->sctp.local_addr_lock);
@@ -1300,9 +1294,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	return 0;
 
-err_ctl_sock_init:
-	sctp_dbg_objcnt_exit(net);
-	sctp_proc_exit(net);
 err_init_proc:
 	cleanup_sctp_mibs(net);
 err_init_mibs:
@@ -1311,15 +1302,12 @@ err_sysctl_register:
 	return status;
 }
 
-static void __net_exit sctp_net_exit(struct net *net)
+static void __net_exit sctp_defaults_exit(struct net *net)
 {
 	/* Free the local address list */
 	sctp_free_addr_wq(net);
 	sctp_free_local_addr_list(net);
 
-	/* Free the control endpoint.  */
-	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-
 	sctp_dbg_objcnt_exit(net);
 
 	sctp_proc_exit(net);
@@ -1327,9 +1315,32 @@ static void __net_exit sctp_net_exit(struct net *net)
 	sctp_sysctl_net_unregister(net);
 }
 
-static struct pernet_operations sctp_net_ops = {
-	.init = sctp_net_init,
-	.exit = sctp_net_exit,
+static struct pernet_operations sctp_defaults_ops = {
+	.init = sctp_defaults_init,
+	.exit = sctp_defaults_exit,
+};
+
+static int __net_init sctp_ctrlsock_init(struct net *net)
+{
+	int status;
+
+	/* Initialize the control inode/socket for handling OOTB packets.  */
+	status = sctp_ctl_sock_init(net);
+	if (status)
+		pr_err("Failed to initialize the SCTP control sock\n");
+
+	return status;
+}
+
+static void __net_init sctp_ctrlsock_exit(struct net *net)
+{
+	/* Free the control endpoint.  */
+	inet_ctl_sock_destroy(net->sctp.ctl_sock);
+}
+
+static struct pernet_operations sctp_ctrlsock_ops = {
+	.init = sctp_ctrlsock_init,
+	.exit = sctp_ctrlsock_exit,
 };
 
 /* Initialize the universe into something sensible.  */
@@ -1462,8 +1473,11 @@ static __init int sctp_init(void)
 	sctp_v4_pf_init();
 	sctp_v6_pf_init();
 
-	status = sctp_v4_protosw_init();
+	status = register_pernet_subsys(&sctp_defaults_ops);
+	if (status)
+		goto err_register_defaults;
 
+	status = sctp_v4_protosw_init();
 	if (status)
 		goto err_protosw_init;
 
@@ -1471,9 +1485,9 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_protosw_init;
 
-	status = register_pernet_subsys(&sctp_net_ops);
+	status = register_pernet_subsys(&sctp_ctrlsock_ops);
 	if (status)
-		goto err_register_pernet_subsys;
+		goto err_register_ctrlsock;
 
 	status = sctp_v4_add_protocol();
 	if (status)
@@ -1489,12 +1503,14 @@ out:
 err_v6_add_protocol:
 	sctp_v4_del_protocol();
 err_add_protocol:
-	unregister_pernet_subsys(&sctp_net_ops);
-err_register_pernet_subsys:
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
+err_register_ctrlsock:
 	sctp_v6_protosw_exit();
 err_v6_protosw_init:
 	sctp_v4_protosw_exit();
 err_protosw_init:
+	unregister_pernet_subsys(&sctp_defaults_ops);
+err_register_defaults:
 	sctp_v4_pf_exit();
 	sctp_v6_pf_exit();
 	sctp_sysctl_unregister();
@@ -1527,12 +1543,14 @@ static __exit void sctp_exit(void)
 	sctp_v6_del_protocol();
 	sctp_v4_del_protocol();
 
-	unregister_pernet_subsys(&sctp_net_ops);
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
 
 	/* Free protosw registrations */
 	sctp_v6_protosw_exit();
 	sctp_v4_protosw_exit();
 
+	unregister_pernet_subsys(&sctp_defaults_ops);
+
 	/* Unregister with socket layer. */
 	sctp_v6_pf_exit();
 	sctp_v4_pf_exit();
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index b140c092d226..f14f24ee9983 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -297,7 +297,7 @@ static int rpc_complete_task(struct rpc_task *task)
 	clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
 	ret = atomic_dec_and_test(&task->tk_count);
 	if (waitqueue_active(wq))
-		__wake_up_locked_key(wq, TASK_NORMAL, 1, &k);
+		__wake_up_locked_key(wq, TASK_NORMAL, &k);
 	spin_unlock_irqrestore(&wq->lock, flags);
 	return ret;
 }
@@ -1092,14 +1092,10 @@ void
 rpc_destroy_mempool(void)
 {
 	rpciod_stop();
-	if (rpc_buffer_mempool)
-		mempool_destroy(rpc_buffer_mempool);
-	if (rpc_task_mempool)
-		mempool_destroy(rpc_task_mempool);
-	if (rpc_task_slabp)
-		kmem_cache_destroy(rpc_task_slabp);
-	if (rpc_buffer_slabp)
-		kmem_cache_destroy(rpc_buffer_slabp);
+	mempool_destroy(rpc_buffer_mempool);
+	mempool_destroy(rpc_task_mempool);
+	kmem_cache_destroy(rpc_task_slabp);
+	kmem_cache_destroy(rpc_buffer_slabp);
 	rpc_destroy_wait_queue(&delay_queue);
 }
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index ab5dd621ae0c..2e98f4a243e5 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -614,6 +614,7 @@ static void xprt_autoclose(struct work_struct *work)
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	xprt->ops->close(xprt);
 	xprt_release_write(xprt, NULL);
+	wake_up_bit(&xprt->state, XPRT_LOCKED);
 }
 
 /**
@@ -723,6 +724,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
 	xprt->ops->release_xprt(xprt, NULL);
 out:
 	spin_unlock_bh(&xprt->transport_lock);
+	wake_up_bit(&xprt->state, XPRT_LOCKED);
 }
 
 /**
@@ -1394,6 +1396,10 @@ out:
 static void xprt_destroy(struct rpc_xprt *xprt)
 {
 	dprintk("RPC:       destroying transport %p\n", xprt);
+
+	/* Exclude transport connect/disconnect handlers */
+	wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE);
+
 	del_timer_sync(&xprt->timer);
 
 	rpc_xprt_debugfs_unregister(xprt);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 7be90bc1a7c2..1a85e0ed0b48 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -777,7 +777,6 @@ static void xs_sock_mark_closed(struct rpc_xprt *xprt)
 	xs_sock_reset_connection_flags(xprt);
 	/* Mark transport as closed and wake up all pending tasks */
 	xprt_disconnect_done(xprt);
-	xprt_force_disconnect(xprt);
 }
 
 /**
@@ -881,8 +880,11 @@ static void xs_xprt_free(struct rpc_xprt *xprt)
  */
 static void xs_destroy(struct rpc_xprt *xprt)
 {
+	struct sock_xprt *transport = container_of(xprt,
+			struct sock_xprt, xprt);
 	dprintk("RPC:       xs_destroy xprt %p\n", xprt);
 
+	cancel_delayed_work_sync(&transport->connect_worker);
 	xs_close(xprt);
 	xs_xprt_free(xprt);
 	module_put(THIS_MODULE);
@@ -1435,6 +1437,7 @@ out:
 static void xs_tcp_state_change(struct sock *sk)
 {
 	struct rpc_xprt *xprt;
+	struct sock_xprt *transport;
 
 	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
@@ -1446,13 +1449,12 @@ static void xs_tcp_state_change(struct sock *sk)
 			sock_flag(sk, SOCK_ZAPPED),
 			sk->sk_shutdown);
 
+	transport = container_of(xprt, struct sock_xprt, xprt);
 	trace_rpc_socket_state_change(xprt, sk->sk_socket);
 	switch (sk->sk_state) {
 	case TCP_ESTABLISHED:
 		spin_lock(&xprt->transport_lock);
 		if (!xprt_test_and_set_connected(xprt)) {
-			struct sock_xprt *transport = container_of(xprt,
-					struct sock_xprt, xprt);
 
 			/* Reset TCP record info */
 			transport->tcp_offset = 0;
@@ -1461,6 +1463,8 @@ static void xs_tcp_state_change(struct sock *sk)
 			transport->tcp_flags =
 				TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;
 			xprt->connect_cookie++;
+			clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state);
+			xprt_clear_connecting(xprt);
 
 			xprt_wake_pending_tasks(xprt, -EAGAIN);
 		}
@@ -1496,6 +1500,9 @@ static void xs_tcp_state_change(struct sock *sk)
 		smp_mb__after_atomic();
 		break;
 	case TCP_CLOSE:
+		if (test_and_clear_bit(XPRT_SOCK_CONNECTING,
+					&transport->sock_state))
+			xprt_clear_connecting(xprt);
 		xs_sock_mark_closed(xprt);
 	}
  out:
@@ -2179,6 +2186,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 	/* Tell the socket layer to start connecting... */
 	xprt->stat.connect_count++;
 	xprt->stat.connect_start = jiffies;
+	set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state);
 	ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
 	switch (ret) {
 	case 0:
@@ -2240,7 +2248,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case -EINPROGRESS:
 	case -EALREADY:
 		xprt_unlock_connect(xprt, transport);
-		xprt_clear_connecting(xprt);
 		return;
 	case -EINVAL:
 		/* Happens, for instance, if the user specified a link
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 562c926a51cc..c5ac436235e0 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -539,6 +539,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 	*err = -TIPC_ERR_NO_NAME;
 	if (skb_linearize(skb))
 		return false;
+	msg = buf_msg(skb);
 	if (msg_reroute_cnt(msg))
 		return false;
 	dnode = addr_domain(net, msg_lookup_scope(msg));
diff --git a/sound/arm/Kconfig b/sound/arm/Kconfig
index 885683a3b0bd..e0406211716b 100644
--- a/sound/arm/Kconfig
+++ b/sound/arm/Kconfig
@@ -9,6 +9,14 @@ menuconfig SND_ARM
 	  Drivers that are implemented on ASoC can be found in
 	  "ALSA for SoC audio support" section.
 
+config SND_PXA2XX_LIB
+	tristate
+	select SND_AC97_CODEC if SND_PXA2XX_LIB_AC97
+	select SND_DMAENGINE_PCM
+
+config SND_PXA2XX_LIB_AC97
+	bool
+
 if SND_ARM
 
 config SND_ARMAACI
@@ -21,13 +29,6 @@ config SND_PXA2XX_PCM
 	tristate
 	select SND_PCM
 
-config SND_PXA2XX_LIB
-	tristate
-	select SND_AC97_CODEC if SND_PXA2XX_LIB_AC97
-
-config SND_PXA2XX_LIB_AC97
-	bool
-
 config SND_PXA2XX_AC97
 	tristate "AC97 driver for the Intel PXA2xx chip"
 	depends on ARCH_PXA
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 477742cb70a2..58c0aad37284 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -73,6 +73,7 @@ struct hda_tegra {
 	struct clk *hda2codec_2x_clk;
 	struct clk *hda2hdmi_clk;
 	void __iomem *regs;
+	struct work_struct probe_work;
 };
 
 #ifdef CONFIG_PM
@@ -294,7 +295,9 @@ static int hda_tegra_dev_disconnect(struct snd_device *device)
 static int hda_tegra_dev_free(struct snd_device *device)
 {
 	struct azx *chip = device->device_data;
+	struct hda_tegra *hda = container_of(chip, struct hda_tegra, chip);
 
+	cancel_work_sync(&hda->probe_work);
 	if (azx_bus(chip)->chip_init) {
 		azx_stop_all_streams(chip);
 		azx_stop_chip(chip);
@@ -426,6 +429,9 @@ static int hda_tegra_first_init(struct azx *chip, struct platform_device *pdev)
 /*
  * constructor
  */
+
+static void hda_tegra_probe_work(struct work_struct *work);
+
 static int hda_tegra_create(struct snd_card *card,
 			    unsigned int driver_caps,
 			    struct hda_tegra *hda)
@@ -452,6 +458,8 @@ static int hda_tegra_create(struct snd_card *card,
 	chip->single_cmd = false;
 	chip->snoop = true;
 
+	INIT_WORK(&hda->probe_work, hda_tegra_probe_work);
+
 	err = azx_bus_init(chip, NULL, &hda_tegra_io_ops);
 	if (err < 0)
 		return err;
@@ -499,6 +507,21 @@ static int hda_tegra_probe(struct platform_device *pdev)
 	card->private_data = chip;
 
 	dev_set_drvdata(&pdev->dev, card);
+	schedule_work(&hda->probe_work);
+
+	return 0;
+
+out_free:
+	snd_card_free(card);
+	return err;
+}
+
+static void hda_tegra_probe_work(struct work_struct *work)
+{
+	struct hda_tegra *hda = container_of(work, struct hda_tegra, probe_work);
+	struct azx *chip = &hda->chip;
+	struct platform_device *pdev = to_platform_device(hda->dev);
+	int err;
 
 	err = hda_tegra_first_init(chip, pdev);
 	if (err < 0)
@@ -520,11 +543,8 @@ static int hda_tegra_probe(struct platform_device *pdev)
 	chip->running = 1;
 	snd_hda_set_power_save(&chip->bus, power_save * 1000);
 
-	return 0;
-
-out_free:
-	snd_card_free(card);
-	return err;
+ out_free:
+	return; /* no error return from async probe */
 }
 
 static int hda_tegra_remove(struct platform_device *pdev)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a75b5611d1e4..afec6dc9f91f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4188,6 +4188,24 @@ static void alc_fixup_disable_aamix(struct hda_codec *codec,
 	}
 }
 
+/* fixup for Thinkpad docks: add dock pins, avoid HP parser fixup */
+static void alc_fixup_tpt440_dock(struct hda_codec *codec,
+				  const struct hda_fixup *fix, int action)
+{
+	static const struct hda_pintbl pincfgs[] = {
+		{ 0x16, 0x21211010 }, /* dock headphone */
+		{ 0x19, 0x21a11010 }, /* dock mic */
+		{ }
+	};
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
+		codec->power_save_node = 0; /* avoid click noises */
+		snd_hda_apply_pincfgs(codec, pincfgs);
+	}
+}
+
 static void alc_shutup_dell_xps13(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -4562,7 +4580,6 @@ enum {
 	ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,
 	ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC292_FIXUP_TPT440_DOCK,
-	ALC292_FIXUP_TPT440_DOCK2,
 	ALC283_FIXUP_BXBT2807_MIC,
 	ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
 	ALC282_FIXUP_ASPIRE_V5_PINS,
@@ -5029,17 +5046,7 @@ static const struct hda_fixup alc269_fixups[] = {
 	},
 	[ALC292_FIXUP_TPT440_DOCK] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
-		.chained = true,
-		.chain_id = ALC292_FIXUP_TPT440_DOCK2
-	},
-	[ALC292_FIXUP_TPT440_DOCK2] = {
-		.type = HDA_FIXUP_PINS,
-		.v.pins = (const struct hda_pintbl[]) {
-			{ 0x16, 0x21211010 }, /* dock headphone */
-			{ 0x19, 0x21a11010 }, /* dock mic */
-			{ }
-		},
+		.v.func = alc_fixup_tpt440_dock,
 		.chained = true,
 		.chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST
 	},
diff --git a/sound/soc/au1x/psc-i2s.c b/sound/soc/au1x/psc-i2s.c
index 38e853add96e..0bf9d62b91a0 100644
--- a/sound/soc/au1x/psc-i2s.c
+++ b/sound/soc/au1x/psc-i2s.c
@@ -296,7 +296,6 @@ static int au1xpsc_i2s_drvprobe(struct platform_device *pdev)
 {
 	struct resource *iores, *dmares;
 	unsigned long sel;
-	int ret;
 	struct au1xpsc_audio_data *wd;
 
 	wd = devm_kzalloc(&pdev->dev, sizeof(struct au1xpsc_audio_data),
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 4972bf3efa91..268a28bd1df4 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -732,14 +732,14 @@ static const struct snd_kcontrol_new rt5645_mono_adc_r_mix[] = {
 static const struct snd_kcontrol_new rt5645_dac_l_mix[] = {
 	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5645_AD_DA_MIXER,
 			RT5645_M_ADCMIX_L_SFT, 1, 1),
-	SOC_DAPM_SINGLE("DAC1 Switch", RT5645_AD_DA_MIXER,
+	SOC_DAPM_SINGLE_AUTODISABLE("DAC1 Switch", RT5645_AD_DA_MIXER,
 			RT5645_M_DAC1_L_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5645_dac_r_mix[] = {
 	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5645_AD_DA_MIXER,
 			RT5645_M_ADCMIX_R_SFT, 1, 1),
-	SOC_DAPM_SINGLE("DAC1 Switch", RT5645_AD_DA_MIXER,
+	SOC_DAPM_SINGLE_AUTODISABLE("DAC1 Switch", RT5645_AD_DA_MIXER,
 			RT5645_M_DAC1_R_SFT, 1, 1),
 };
 
@@ -1381,7 +1381,7 @@ static void hp_amp_power(struct snd_soc_codec *codec, int on)
 				regmap_write(rt5645->regmap, RT5645_PR_BASE +
 					RT5645_MAMP_INT_REG2, 0xfc00);
 				snd_soc_write(codec, RT5645_DEPOP_M2, 0x1140);
-				mdelay(5);
+				msleep(40);
 				rt5645->hp_on = true;
 			} else {
 				/* depop parameters */
@@ -2829,13 +2829,12 @@ static int rt5645_jack_detect(struct snd_soc_codec *codec, int jack_insert)
 			snd_soc_dapm_sync(dapm);
 			rt5645->jack_type = SND_JACK_HEADPHONE;
 		}
-
-		snd_soc_update_bits(codec, RT5645_CHARGE_PUMP, 0x0300, 0x0200);
-		snd_soc_write(codec, RT5645_DEPOP_M1, 0x001d);
-		snd_soc_write(codec, RT5645_DEPOP_M1, 0x0001);
 	} else { /* jack out */
 		rt5645->jack_type = 0;
 
+		regmap_update_bits(rt5645->regmap, RT5645_HP_VOL,
+			RT5645_L_MUTE | RT5645_R_MUTE,
+			RT5645_L_MUTE | RT5645_R_MUTE);
 		regmap_update_bits(rt5645->regmap, RT5645_IN1_CTRL2,
 			RT5645_CBJ_MN_JD, RT5645_CBJ_MN_JD);
 		regmap_update_bits(rt5645->regmap, RT5645_IN1_CTRL1,
@@ -2880,8 +2879,6 @@ int rt5645_set_jack_detect(struct snd_soc_codec *codec,
 		rt5645->en_button_func = true;
 		regmap_update_bits(rt5645->regmap, RT5645_GPIO_CTRL1,
 				RT5645_GP1_PIN_IRQ, RT5645_GP1_PIN_IRQ);
-		regmap_update_bits(rt5645->regmap, RT5645_DEPOP_M1,
-				RT5645_HP_CB_MASK, RT5645_HP_CB_PU);
 		regmap_update_bits(rt5645->regmap, RT5645_GEN_CTRL1,
 				RT5645_DIG_GATE_CTRL, RT5645_DIG_GATE_CTRL);
 	}
@@ -3205,6 +3202,13 @@ static const struct dmi_system_id dmi_platform_intel_braswell[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Celes"),
 		},
 	},
+	{
+		.ident = "Google Ultima",
+		.callback = strago_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "Ultima"),
+		},
+	},
 	{ }
 };
 
diff --git a/sound/soc/codecs/wm0010.c b/sound/soc/codecs/wm0010.c
index f2c6ad4b8fde..581ec1502228 100644
--- a/sound/soc/codecs/wm0010.c
+++ b/sound/soc/codecs/wm0010.c
@@ -577,7 +577,6 @@ static int wm0010_boot(struct snd_soc_codec *codec)
 	struct wm0010_priv *wm0010 = snd_soc_codec_get_drvdata(codec);
 	unsigned long flags;
 	int ret;
-	const struct firmware *fw;
 	struct spi_message m;
 	struct spi_transfer t;
 	struct dfw_pllrec pll_rec;
@@ -623,14 +622,6 @@ static int wm0010_boot(struct snd_soc_codec *codec)
 	wm0010->state = WM0010_OUT_OF_RESET;
 	spin_unlock_irqrestore(&wm0010->irq_lock, flags);
 
-	/* First the bootloader */
-	ret = request_firmware(&fw, "wm0010_stage2.bin", codec->dev);
-	if (ret != 0) {
-		dev_err(codec->dev, "Failed to request stage2 loader: %d\n",
-			ret);
-		goto abort;
-	}
-
 	if (!wait_for_completion_timeout(&wm0010->boot_completion,
 					 msecs_to_jiffies(20)))
 		dev_err(codec->dev, "Failed to get interrupt from DSP\n");
@@ -673,7 +664,7 @@ static int wm0010_boot(struct snd_soc_codec *codec)
 
 		img_swap = kzalloc(len, GFP_KERNEL | GFP_DMA);
 		if (!img_swap)
-			goto abort;
+			goto abort_out;
 
 		/* We need to re-order for 0010 */
 		byte_swap_64((u64 *)&pll_rec, img_swap, len);
@@ -688,16 +679,16 @@ static int wm0010_boot(struct snd_soc_codec *codec)
 		spi_message_add_tail(&t, &m);
 
 		ret = spi_sync(spi, &m);
-		if (ret != 0) {
+		if (ret) {
 			dev_err(codec->dev, "First PLL write failed: %d\n", ret);
-			goto abort;
+			goto abort_swap;
 		}
 
 		/* Use a second send of the message to get the return status */
 		ret = spi_sync(spi, &m);
-		if (ret != 0) {
+		if (ret) {
 			dev_err(codec->dev, "Second PLL write failed: %d\n", ret);
-			goto abort;
+			goto abort_swap;
 		}
 
 		p = (u32 *)out;
@@ -730,6 +721,10 @@ static int wm0010_boot(struct snd_soc_codec *codec)
 
 	return 0;
 
+abort_swap:
+	kfree(img_swap);
+abort_out:
+	kfree(out);
 abort:
 	/* Put the chip back into reset */
 	wm0010_halt(codec);
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index e3b7d0c57411..dbd88408861a 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -211,28 +211,38 @@ static int wm8960_put_deemph(struct snd_kcontrol *kcontrol,
 	return wm8960_set_deemph(codec);
 }
 
-static const DECLARE_TLV_DB_SCALE(adc_tlv, -9700, 50, 0);
-static const DECLARE_TLV_DB_SCALE(dac_tlv, -12700, 50, 1);
+static const DECLARE_TLV_DB_SCALE(adc_tlv, -9750, 50, 1);
+static const DECLARE_TLV_DB_SCALE(inpga_tlv, -1725, 75, 0);
+static const DECLARE_TLV_DB_SCALE(dac_tlv, -12750, 50, 1);
 static const DECLARE_TLV_DB_SCALE(bypass_tlv, -2100, 300, 0);
 static const DECLARE_TLV_DB_SCALE(out_tlv, -12100, 100, 1);
-static const DECLARE_TLV_DB_SCALE(boost_tlv, -1200, 300, 1);
+static const DECLARE_TLV_DB_SCALE(lineinboost_tlv, -1500, 300, 1);
+static const unsigned int micboost_tlv[] = {
+	TLV_DB_RANGE_HEAD(2),
+	0, 1, TLV_DB_SCALE_ITEM(0, 1300, 0),
+	2, 3, TLV_DB_SCALE_ITEM(2000, 900, 0),
+};
 
 static const struct snd_kcontrol_new wm8960_snd_controls[] = {
 SOC_DOUBLE_R_TLV("Capture Volume", WM8960_LINVOL, WM8960_RINVOL,
-		 0, 63, 0, adc_tlv),
+		 0, 63, 0, inpga_tlv),
 SOC_DOUBLE_R("Capture Volume ZC Switch", WM8960_LINVOL, WM8960_RINVOL,
 	6, 1, 0),
 SOC_DOUBLE_R("Capture Switch", WM8960_LINVOL, WM8960_RINVOL,
 	7, 1, 0),
 
 SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
-	       WM8960_INBMIX1, 4, 7, 0, boost_tlv),
+	       WM8960_INBMIX1, 4, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT2 Volume",
-	       WM8960_INBMIX1, 1, 7, 0, boost_tlv),
+	       WM8960_INBMIX1, 1, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT3 Volume",
-	       WM8960_INBMIX2, 4, 7, 0, boost_tlv),
+	       WM8960_INBMIX2, 4, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT2 Volume",
-	       WM8960_INBMIX2, 1, 7, 0, boost_tlv),
+	       WM8960_INBMIX2, 1, 7, 0, lineinboost_tlv),
+SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT1 Volume",
+		WM8960_RINPATH, 4, 3, 0, micboost_tlv),
+SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT1 Volume",
+		WM8960_LINPATH, 4, 3, 0, micboost_tlv),
 
 SOC_DOUBLE_R_TLV("Playback Volume", WM8960_LDAC, WM8960_RDAC,
 		 0, 255, 0, dac_tlv),
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index b4eb975da981..293e47a6ff59 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2944,7 +2944,8 @@ static int wm8962_mute(struct snd_soc_dai *dai, int mute)
 				   WM8962_DAC_MUTE, val);
 }
 
-#define WM8962_RATES SNDRV_PCM_RATE_8000_96000
+#define WM8962_RATES (SNDRV_PCM_RATE_8000_48000 |\
+		SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000)
 
 #define WM8962_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE |\
 			SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S32_LE)
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index add6bb99661d..7d45d98a861f 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -663,7 +663,7 @@ static int mcasp_common_hw_param(struct davinci_mcasp *mcasp, int stream,
 	u8 rx_ser = 0;
 	u8 slots = mcasp->tdm_slots;
 	u8 max_active_serializers = (channels + slots - 1) / slots;
-	int active_serializers, numevt, n;
+	int active_serializers, numevt;
 	u32 reg;
 	/* Default configuration */
 	if (mcasp->version < MCASP_VERSION_3)
@@ -745,9 +745,8 @@ static int mcasp_common_hw_param(struct davinci_mcasp *mcasp, int stream,
 	 * The number of words for numevt need to be in steps of active
 	 * serializers.
 	 */
-	n = numevt % active_serializers;
-	if (n)
-		numevt += (active_serializers - n);
+	numevt = (numevt / active_serializers) * active_serializers;
+
 	while (period_words % numevt && numevt > 0)
 		numevt -= active_serializers;
 	if (numevt <= 0)
@@ -1299,6 +1298,7 @@ static struct snd_soc_dai_driver davinci_mcasp_dai[] = {
 		.ops 		= &davinci_mcasp_dai_ops,
 
 		.symmetric_samplebits	= 1,
+		.symmetric_rates	= 1,
 	},
 	{
 		.name		= "davinci-mcasp.1",
@@ -1685,7 +1685,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq_byname(pdev, "common");
 	if (irq >= 0) {
-		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_common\n",
+		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_common",
 					  dev_name(&pdev->dev));
 		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 						davinci_mcasp_common_irq_handler,
@@ -1702,7 +1702,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq_byname(pdev, "rx");
 	if (irq >= 0) {
-		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_rx\n",
+		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_rx",
 					  dev_name(&pdev->dev));
 		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 						davinci_mcasp_rx_irq_handler,
@@ -1717,7 +1717,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq_byname(pdev, "tx");
 	if (irq >= 0) {
-		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_tx\n",
+		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_tx",
 					  dev_name(&pdev->dev));
 		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 						davinci_mcasp_tx_irq_handler,
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 5aeb6ed4827e..96f55ae75c71 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -488,7 +488,8 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 		priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
 	} else {
 		dev_err(&pdev->dev, "unknown Device Tree compatible\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto asrc_fail;
 	}
 
 	/* Common settings for corresponding Freescale CPU DAI driver */
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 8ec6fb208ea0..37c5cd4d0e59 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -249,7 +249,8 @@ MODULE_DEVICE_TABLE(of, fsl_ssi_ids);
 
 static bool fsl_ssi_is_ac97(struct fsl_ssi_private *ssi_private)
 {
-	return !!(ssi_private->dai_fmt & SND_SOC_DAIFMT_AC97);
+	return (ssi_private->dai_fmt & SND_SOC_DAIFMT_FORMAT_MASK) ==
+		SND_SOC_DAIFMT_AC97;
 }
 
 static bool fsl_ssi_is_i2s_master(struct fsl_ssi_private *ssi_private)
@@ -947,7 +948,7 @@ static int _fsl_ssi_set_dai_fmt(struct device *dev,
 				CCSR_SSI_SCR_TCH_EN);
 	}
 
-	if (fmt & SND_SOC_DAIFMT_AC97)
+	if ((fmt & SND_SOC_DAIFMT_FORMAT_MASK) == SND_SOC_DAIFMT_AC97)
 		fsl_ssi_setup_ac97(ssi_private);
 
 	return 0;
diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c
index f6efa9d4acad..b27f25f70730 100644
--- a/sound/soc/intel/haswell/sst-haswell-ipc.c
+++ b/sound/soc/intel/haswell/sst-haswell-ipc.c
@@ -302,6 +302,10 @@ struct sst_hsw {
 	struct sst_hsw_ipc_dx_reply dx;
 	void *dx_context;
 	dma_addr_t dx_context_paddr;
+	enum sst_hsw_device_id dx_dev;
+	enum sst_hsw_device_mclk dx_mclk;
+	enum sst_hsw_device_mode dx_mode;
+	u32 dx_clock_divider;
 
 	/* boot */
 	wait_queue_head_t boot_wait;
@@ -1400,10 +1404,10 @@ int sst_hsw_device_set_config(struct sst_hsw *hsw,
 
 	trace_ipc_request("set device config", dev);
 
-	config.ssp_interface = dev;
-	config.clock_frequency = mclk;
-	config.mode = mode;
-	config.clock_divider = clock_divider;
+	hsw->dx_dev = config.ssp_interface = dev;
+	hsw->dx_mclk = config.clock_frequency = mclk;
+	hsw->dx_mode = config.mode = mode;
+	hsw->dx_clock_divider = config.clock_divider = clock_divider;
 	if (mode == SST_HSW_DEVICE_TDM_CLOCK_MASTER)
 		config.channels = 4;
 	else
@@ -1704,10 +1708,10 @@ int sst_hsw_dsp_runtime_resume(struct sst_hsw *hsw)
 		return -EIO;
 	}
 
-	/* Set ADSP SSP port settings */
-	ret = sst_hsw_device_set_config(hsw, SST_HSW_DEVICE_SSP_0,
-					SST_HSW_DEVICE_MCLK_FREQ_24_MHZ,
-					SST_HSW_DEVICE_CLOCK_MASTER, 9);
+	/* Set ADSP SSP port settings - sadly the FW does not store SSP port
+	   settings as part of the PM context. */
+	ret = sst_hsw_device_set_config(hsw, hsw->dx_dev, hsw->dx_mclk,
+					hsw->dx_mode, hsw->dx_clock_divider);
 	if (ret < 0)
 		dev_err(dev, "error: SSP re-initialization failed\n");
 
diff --git a/sound/soc/mediatek/mtk-afe-pcm.c b/sound/soc/mediatek/mtk-afe-pcm.c
index d190fe017559..f5baf3c38863 100644
--- a/sound/soc/mediatek/mtk-afe-pcm.c
+++ b/sound/soc/mediatek/mtk-afe-pcm.c
@@ -549,6 +549,23 @@ static int mtk_afe_dais_startup(struct snd_pcm_substream *substream,
 	memif->substream = substream;
 
 	snd_soc_set_runtime_hwparams(substream, &mtk_afe_hardware);
+
+	/*
+	 * Capture cannot use ping-pong buffer since hw_ptr at IRQ may be
+	 * smaller than period_size due to AFE's internal buffer.
+	 * This easily leads to overrun when avail_min is period_size.
+	 * One more period can hold the possible unread buffer.
+	 */
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		ret = snd_pcm_hw_constraint_minmax(runtime,
+						   SNDRV_PCM_HW_PARAM_PERIODS,
+						   3,
+						   mtk_afe_hardware.periods_max);
+		if (ret < 0) {
+			dev_err(afe->dev, "hw_constraint_minmax failed\n");
+			return ret;
+		}
+	}
 	ret = snd_pcm_hw_constraint_integer(runtime,
 					    SNDRV_PCM_HW_PARAM_PERIODS);
 	if (ret < 0)
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 39cea80846c3..f2bf8661dd21 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -1,7 +1,6 @@
 config SND_PXA2XX_SOC
 	tristate "SoC Audio for the Intel PXA2xx chip"
 	depends on ARCH_PXA
-	select SND_ARM
 	select SND_PXA2XX_LIB
 	help
 	  Say Y or M if you want to add support for codecs attached to
@@ -25,7 +24,6 @@ config SND_PXA2XX_AC97
 config SND_PXA2XX_SOC_AC97
 	tristate
 	select AC97_BUS
-	select SND_ARM
 	select SND_PXA2XX_LIB_AC97
 	select SND_SOC_AC97_BUS
 
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 1f6054650991..9e4b04e0fbd1 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -49,7 +49,7 @@ static struct snd_ac97_bus_ops pxa2xx_ac97_ops = {
 	.reset	= pxa2xx_ac97_cold_reset,
 };
 
-static unsigned long pxa2xx_ac97_pcm_stereo_in_req = 12;
+static unsigned long pxa2xx_ac97_pcm_stereo_in_req = 11;
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_in = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
@@ -57,7 +57,7 @@ static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_in = {
 	.filter_data	= &pxa2xx_ac97_pcm_stereo_in_req,
 };
 
-static unsigned long pxa2xx_ac97_pcm_stereo_out_req = 11;
+static unsigned long pxa2xx_ac97_pcm_stereo_out_req = 12;
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_out = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index f4bf21a5539b..ff8bda471b25 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3501,7 +3501,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w,
 
 	default:
 		WARN(1, "Unknown event %d\n", event);
-		return -EINVAL;
+		ret = -EINVAL;
 	}
 
 out:
diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c
index 362c69ac1d6c..53dd085d3ee2 100644
--- a/sound/soc/soc-utils.c
+++ b/sound/soc/soc-utils.c
@@ -101,6 +101,15 @@ static struct snd_soc_codec_driver dummy_codec;
 			SNDRV_PCM_FMTBIT_S32_LE | \
 			SNDRV_PCM_FMTBIT_U32_LE | \
 			SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE)
+/*
+ * The dummy CODEC is only meant to be used in situations where there is no
+ * actual hardware.
+ *
+ * If there is actual hardware even if it does not have a control bus
+ * the hardware will still have constraints like supported samplerates, etc.
+ * which should be modelled. And the data flow graph also should be modelled
+ * using DAPM.
+ */
 static struct snd_soc_dai_driver dummy_dai = {
 	.name = "snd-soc-dummy-dai",
 	.playback = {
diff --git a/sound/soc/spear/Kconfig b/sound/soc/spear/Kconfig
index 0a53053495f3..4fb91412ebec 100644
--- a/sound/soc/spear/Kconfig
+++ b/sound/soc/spear/Kconfig
@@ -1,6 +1,6 @@
 config SND_SPEAR_SOC
 	tristate
-	select SND_DMAENGINE_PCM
+	select SND_SOC_GENERIC_DMAENGINE_PCM
 
 config SND_SPEAR_SPDIF_OUT
 	tristate
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index f6eefe1b8f8f..843f037a317d 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -989,8 +989,8 @@ static int uni_player_parse_dt(struct platform_device *pdev,
 	if (!info)
 		return -ENOMEM;
 
-	of_property_read_u32(pnode, "version", &player->ver);
-	if (player->ver == SND_ST_UNIPERIF_VERSION_UNKNOWN) {
+	if (of_property_read_u32(pnode, "version", &player->ver) ||
+	    player->ver == SND_ST_UNIPERIF_VERSION_UNKNOWN) {
 		dev_err(dev, "Unknown uniperipheral version ");
 		return -EINVAL;
 	}
@@ -998,10 +998,16 @@ static int uni_player_parse_dt(struct platform_device *pdev,
 	if (player->ver >= SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
 		info->underflow_enabled = 1;
 
-	of_property_read_u32(pnode, "uniperiph-id", &info->id);
+	if (of_property_read_u32(pnode, "uniperiph-id", &info->id)) {
+		dev_err(dev, "uniperipheral id not defined");
+		return -EINVAL;
+	}
 
 	/* Read the device mode property */
-	of_property_read_string(pnode, "mode", &mode);
+	if (of_property_read_string(pnode, "mode", &mode)) {
+		dev_err(dev, "uniperipheral mode not defined");
+		return -EINVAL;
+	}
 
 	if (strcasecmp(mode, "hdmi") == 0)
 		info->player_type = SND_ST_UNIPERIF_PLAYER_TYPE_HDMI;
diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
index c502626f339b..f791239a3087 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -316,7 +316,11 @@ static int uni_reader_parse_dt(struct platform_device *pdev,
 	if (!info)
 		return -ENOMEM;
 
-	of_property_read_u32(node, "version", &reader->ver);
+	if (of_property_read_u32(node, "version", &reader->ver) ||
+	    reader->ver == SND_ST_UNIPERIF_VERSION_UNKNOWN) {
+		dev_err(&pdev->dev, "Unknown uniperipheral version ");
+		return -EINVAL;
+	}
 
 	/* Save the info structure */
 	reader->info = info;
diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile
index 877a50355d7f..a1a97085847d 100644
--- a/tools/testing/selftests/membarrier/Makefile
+++ b/tools/testing/selftests/membarrier/Makefile
@@ -1,11 +1,10 @@
 CFLAGS += -g -I../../../../usr/include/
 
-all:
-	$(CC) $(CFLAGS) membarrier_test.c -o membarrier_test
-
 TEST_PROGS := membarrier_test
 
+all: $(TEST_PROGS)
+
 include ../lib.mk
 
 clean:
-	$(RM) membarrier_test
+	$(RM) $(TEST_PROGS)
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index dde312508007..535f0fef4d0b 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -1,9 +1,6 @@
 #define _GNU_SOURCE
-#define __EXPORTED_HEADERS__
-
 #include <linux/membarrier.h>
-#include <asm-generic/unistd.h>
-#include <sys/syscall.h>
+#include <syscall.h>
 #include <stdio.h>
 #include <errno.h>
 #include <string.h>
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d36fab7d8ebd..3c53cac15de1 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,6 +1,6 @@
 # Makefile for vm selftests
 
-CFLAGS = -Wall
+CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 BINARIES = compaction_test
 BINARIES += hugepage-mmap
 BINARIES += hugepage-shm
@@ -12,8 +12,11 @@ BINARIES += userfaultfd
 all: $(BINARIES)
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^ -lrt
-userfaultfd: userfaultfd.c
-	$(CC) $(CFLAGS) -O2 -o $@ $^ -lpthread
+userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h
+	$(CC) $(CFLAGS) -O2 -o $@ $< -lpthread
+
+../../../../usr/include/linux/kernel.h:
+	make -C ../../../.. headers_install
 
 TEST_PROGS := run_vmtests
 TEST_FILES := $(BINARIES)
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 2c7cca6f26a4..d77ed41b2094 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -64,17 +64,9 @@
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
 #include <pthread.h>
-#include "../../../../include/uapi/linux/userfaultfd.h"
-
-#ifdef __x86_64__
-#define __NR_userfaultfd 323
-#elif defined(__i386__)
-#define __NR_userfaultfd 374
-#elif defined(__powewrpc__)
-#define __NR_userfaultfd 364
-#else
-#error "missing __NR_userfaultfd definition"
-#endif
+#include <linux/userfaultfd.h>
+
+#ifdef __NR_userfaultfd
 
 static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
 
@@ -430,7 +422,7 @@ static int userfaultfd_stress(void)
 	struct uffdio_register uffdio_register;
 	struct uffdio_api uffdio_api;
 	unsigned long cpu;
-	int uffd_flags;
+	int uffd_flags, err;
 	unsigned long userfaults[nr_cpus];
 
 	if (posix_memalign(&area, page_size, nr_pages * page_size)) {
@@ -473,6 +465,14 @@ static int userfaultfd_stress(void)
 		*area_mutex(area_src, nr) = (pthread_mutex_t)
 			PTHREAD_MUTEX_INITIALIZER;
 		count_verify[nr] = *area_count(area_src, nr) = 1;
+		/*
+		 * In the transition between 255 to 256, powerpc will
+		 * read out of order in my_bcmp and see both bytes as
+		 * zero, so leave a placeholder below always non-zero
+		 * after the count, to avoid my_bcmp to trigger false
+		 * positives.
+		 */
+		*(area_count(area_src, nr) + 1) = 1;
 	}
 
 	pipefd = malloc(sizeof(int) * nr_cpus * 2);
@@ -499,6 +499,7 @@ static int userfaultfd_stress(void)
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, 16*1024*1024);
 
+	err = 0;
 	while (bounces--) {
 		unsigned long expected_ioctls;
 
@@ -579,20 +580,13 @@ static int userfaultfd_stress(void)
 		/* verification */
 		if (bounces & BOUNCE_VERIFY) {
 			for (nr = 0; nr < nr_pages; nr++) {
-				if (my_bcmp(area_dst,
-					    area_dst + nr * page_size,
-					    sizeof(pthread_mutex_t))) {
-					fprintf(stderr,
-						"error mutex 2 %lu\n",
-						nr);
-					bounces = 0;
-				}
 				if (*area_count(area_dst, nr) != count_verify[nr]) {
 					fprintf(stderr,
 						"error area_count %Lu %Lu %lu\n",
 						*area_count(area_src, nr),
 						count_verify[nr],
 						nr);
+					err = 1;
 					bounces = 0;
 				}
 			}
@@ -609,7 +603,7 @@ static int userfaultfd_stress(void)
 		printf("\n");
 	}
 
-	return 0;
+	return err;
 }
 
 int main(int argc, char **argv)
@@ -618,8 +612,8 @@ int main(int argc, char **argv)
 		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	page_size = sysconf(_SC_PAGE_SIZE);
-	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) >
-	    page_size)
+	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
+	    > page_size)
 		fprintf(stderr, "Impossible to run this test\n"), exit(2);
 	nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size /
 		nr_cpus;
@@ -637,3 +631,15 @@ int main(int argc, char **argv)
 	       nr_pages, nr_pages_per_cpu);
 	return userfaultfd_stress();
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+	return 0;
+}
+
+#endif /* __NR_userfaultfd */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 04146a2e1d81..8db1d9361993 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -66,8 +66,8 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
-/* halt polling only reduces halt latency by 5-7 us, 500us is enough */
-static unsigned int halt_poll_ns = 500000;
+/* Architectures should define their poll value according to the halt latency */
+static unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
 module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
 
 /* Default doubles per-vcpu halt_poll_ns. */